diff options
889 files changed, 39394 insertions, 12439 deletions
@@ -518,7 +518,7 @@ N: Zach Brown E: zab@zabbo.net D: maestro pci sound -M: David Brownell +N: David Brownell D: Kernel engineer, mentor, and friend. Maintained USB EHCI and D: gadget layers, SPI subsystem, GPIO subsystem, and more than a few D: device drivers. His encouragement also helped many engineers get diff --git a/Documentation/Changes b/Documentation/Changes index 5f4828a0..b175808 100644 --- a/Documentation/Changes +++ b/Documentation/Changes @@ -2,13 +2,7 @@ Intro ===== This document is designed to provide a list of the minimum levels of -software necessary to run the 2.6 kernels, as well as provide brief -instructions regarding any other "Gotchas" users may encounter when -trying life on the Bleeding Edge. If upgrading from a pre-2.4.x -kernel, please consult the Changes file included with 2.4.x kernels for -additional information; most of that information will not be repeated -here. Basically, this document assumes that your system is already -functional and running at least 2.4.x kernels. +software necessary to run the 3.0 kernels. This document is originally based on my "Changes" file for 2.0.x kernels and therefore owes credit to the same people as that file (Jared Mauch, @@ -22,11 +16,10 @@ Upgrade to at *least* these software revisions before thinking you've encountered a bug! If you're unsure what version you're currently running, the suggested command should tell you. -Again, keep in mind that this list assumes you are already -functionally running a Linux 2.4 kernel. Also, not all tools are -necessary on all systems; obviously, if you don't have any ISDN -hardware, for example, you probably needn't concern yourself with -isdn4k-utils. +Again, keep in mind that this list assumes you are already functionally +running a Linux kernel. Also, not all tools are necessary on all +systems; obviously, if you don't have any ISDN hardware, for example, +you probably needn't concern yourself with isdn4k-utils. o Gnu C 3.2 # gcc --version o Gnu make 3.80 # make --version @@ -114,12 +107,12 @@ Ksymoops If the unthinkable happens and your kernel oopses, you may need the ksymoops tool to decode it, but in most cases you don't. -In the 2.6 kernel it is generally preferred to build the kernel with -CONFIG_KALLSYMS so that it produces readable dumps that can be used as-is -(this also produces better output than ksymoops). -If for some reason your kernel is not build with CONFIG_KALLSYMS and -you have no way to rebuild and reproduce the Oops with that option, then -you can still decode that Oops with ksymoops. +It is generally preferred to build the kernel with CONFIG_KALLSYMS so +that it produces readable dumps that can be used as-is (this also +produces better output than ksymoops). If for some reason your kernel +is not build with CONFIG_KALLSYMS and you have no way to rebuild and +reproduce the Oops with that option, then you can still decode that Oops +with ksymoops. Module-Init-Tools ----------------- @@ -261,8 +254,8 @@ needs to be recompiled or (preferably) upgraded. NFS-utils --------- -In 2.4 and earlier kernels, the nfs server needed to know about any -client that expected to be able to access files via NFS. This +In ancient (2.4 and earlier) kernels, the nfs server needed to know +about any client that expected to be able to access files via NFS. This information would be given to the kernel by "mountd" when the client mounted the filesystem, or by "exportfs" at system startup. exportfs would take information about active clients from /var/lib/nfs/rmtab. @@ -272,11 +265,11 @@ which is not always easy, particularly when trying to implement fail-over. Even when the system is working well, rmtab suffers from getting lots of old entries that never get removed. -With 2.6 we have the option of having the kernel tell mountd when it -gets a request from an unknown host, and mountd can give appropriate -export information to the kernel. This removes the dependency on -rmtab and means that the kernel only needs to know about currently -active clients. +With modern kernels we have the option of having the kernel tell mountd +when it gets a request from an unknown host, and mountd can give +appropriate export information to the kernel. This removes the +dependency on rmtab and means that the kernel only needs to know about +currently active clients. To enable this new functionality, you need to: diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle index 58b0bf9..fa6e25b 100644 --- a/Documentation/CodingStyle +++ b/Documentation/CodingStyle @@ -680,8 +680,8 @@ ones already enabled by DEBUG. Chapter 14: Allocating memory The kernel provides the following general purpose memory allocators: -kmalloc(), kzalloc(), kcalloc(), and vmalloc(). Please refer to the API -documentation for further information about them. +kmalloc(), kzalloc(), kcalloc(), vmalloc(), and vzalloc(). Please refer to +the API documentation for further information about them. The preferred form for passing a size of a struct is the following: diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt index cd45c8e..84f0a15 100644 --- a/Documentation/cgroups/blkio-controller.txt +++ b/Documentation/cgroups/blkio-controller.txt @@ -77,7 +77,7 @@ Throttling/Upper Limit policy - Specify a bandwidth rate on particular device for root group. The format for policy is "<major>:<minor> <byes_per_second>". - echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.read_bps_device + echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device Above will put a limit of 1MB/second on reads happening for root group on device having major/minor number 8:16. @@ -90,7 +90,7 @@ Throttling/Upper Limit policy 1024+0 records out 4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s - Limits for writes can be put using blkio.write_bps_device file. + Limits for writes can be put using blkio.throttle.write_bps_device file. Hierarchical Cgroups ==================== @@ -286,28 +286,28 @@ Throttling/Upper limit policy files specified in bytes per second. Rules are per deivce. Following is the format. - echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.read_bps_device + echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.read_bps_device - blkio.throttle.write_bps_device - Specifies upper limit on WRITE rate to the device. IO rate is specified in bytes per second. Rules are per deivce. Following is the format. - echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.write_bps_device + echo "<major>:<minor> <rate_bytes_per_second>" > /cgrp/blkio.throttle.write_bps_device - blkio.throttle.read_iops_device - Specifies upper limit on READ rate from the device. IO rate is specified in IO per second. Rules are per deivce. Following is the format. - echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.read_iops_device + echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.read_iops_device - blkio.throttle.write_iops_device - Specifies upper limit on WRITE rate to the device. IO rate is specified in io per second. Rules are per deivce. Following is the format. - echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.write_iops_device + echo "<major>:<minor> <rate_io_per_second>" > /cgrp/blkio.throttle.write_iops_device Note: If both BW and IOPS rules are specified for a device, then IO is subjectd to both the constraints. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 72e2384..b1c921c 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -583,3 +583,25 @@ Why: Superseded by the UVCIOC_CTRL_QUERY ioctl. Who: Laurent Pinchart <laurent.pinchart@ideasonboard.com> ---------------------------- + +What: For VIDIOC_S_FREQUENCY the type field must match the device node's type. + If not, return -EINVAL. +When: 3.2 +Why: It makes no sense to switch the tuner to radio mode by calling + VIDIOC_S_FREQUENCY on a video node, or to switch the tuner to tv mode by + calling VIDIOC_S_FREQUENCY on a radio node. This is the first step of a + move to more consistent handling of tv and radio tuners. +Who: Hans Verkuil <hans.verkuil@cisco.com> + +---------------------------- + +What: Opening a radio device node will no longer automatically switch the + tuner mode from tv to radio. +When: 3.3 +Why: Just opening a V4L device should not change the state of the hardware + like that. It's very unexpected and against the V4L spec. Instead, you + switch to radio mode by calling VIDIOC_S_FREQUENCY. This is the second + and last step of the move to consistent handling of tv and radio tuners. +Who: Hans Verkuil <hans.verkuil@cisco.com> + +---------------------------- diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt index a167ab8..7cc6bf2 100644 --- a/Documentation/filesystems/caching/netfs-api.txt +++ b/Documentation/filesystems/caching/netfs-api.txt @@ -673,6 +673,22 @@ storage request to complete, or it may attempt to cancel the storage request - in which case the page will not be stored in the cache this time. +BULK INODE PAGE UNCACHE +----------------------- + +A convenience routine is provided to perform an uncache on all the pages +attached to an inode. This assumes that the pages on the inode correspond on a +1:1 basis with the pages in the cache. + + void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, + struct inode *inode); + +This takes the netfs cookie that the pages were cached with and the inode that +the pages are attached to. This function will wait for pages to finish being +written to the cache and for the cache to finish with the page generally. No +error is returned. + + ========================== INDEX AND DATA FILE UPDATE ========================== diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt index d5c0cef..873a2ab 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.txt @@ -40,7 +40,6 @@ Features which NILFS2 does not support yet: - POSIX ACLs - quotas - fsck - - resize - defragmentation Mount options diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt index 8e4fab6..a0a61d2 100644 --- a/Documentation/filesystems/ubifs.txt +++ b/Documentation/filesystems/ubifs.txt @@ -111,34 +111,6 @@ The following is an example of the kernel boot arguments to attach mtd0 to UBI and mount volume "rootfs": ubi.mtd=0 root=ubi0:rootfs rootfstype=ubifs - -Module Parameters for Debugging -=============================== - -When UBIFS has been compiled with debugging enabled, there are 2 module -parameters that are available to control aspects of testing and debugging. - -debug_chks Selects extra checks that UBIFS can do while running: - - Check Flag value - - General checks 1 - Check Tree Node Cache (TNC) 2 - Check indexing tree size 4 - Check orphan area 8 - Check old indexing tree 16 - Check LEB properties (lprops) 32 - Check leaf nodes and inodes 64 - -debug_tsts Selects a mode of testing, as follows: - - Test mode Flag value - - Failure mode for recovery testing 4 - -For example, set debug_chks to 3 to enable general and TNC checks. - - References ========== diff --git a/Documentation/hwmon/f71882fg b/Documentation/hwmon/f71882fg index 84d2623..de91c0d 100644 --- a/Documentation/hwmon/f71882fg +++ b/Documentation/hwmon/f71882fg @@ -22,6 +22,10 @@ Supported chips: Prefix: 'f71869' Addresses scanned: none, address read from Super I/O config space Datasheet: Available from the Fintek website + * Fintek F71869A + Prefix: 'f71869a' + Addresses scanned: none, address read from Super I/O config space + Datasheet: Not public * Fintek F71882FG and F71883FG Prefix: 'f71882fg' Addresses scanned: none, address read from Super I/O config space diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp index 0393c89..a10f736 100644 --- a/Documentation/hwmon/k10temp +++ b/Documentation/hwmon/k10temp @@ -9,8 +9,8 @@ Supported chips: Socket S1G3: Athlon II, Sempron, Turion II * AMD Family 11h processors: Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra) -* AMD Family 12h processors: "Llano" -* AMD Family 14h processors: "Brazos" (C/E/G-Series) +* AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series) +* AMD Family 14h processors: "Brazos" (C/E/G/Z-Series) * AMD Family 15h processors: "Bulldozer" Prefix: 'k10temp' @@ -20,12 +20,16 @@ Supported chips: http://support.amd.com/us/Processor_TechDocs/31116.pdf BIOS and Kernel Developer's Guide (BKDG) for AMD Family 11h Processors: http://support.amd.com/us/Processor_TechDocs/41256.pdf + BIOS and Kernel Developer's Guide (BKDG) for AMD Family 12h Processors: + http://support.amd.com/us/Processor_TechDocs/41131.pdf BIOS and Kernel Developer's Guide (BKDG) for AMD Family 14h Models 00h-0Fh Processors: http://support.amd.com/us/Processor_TechDocs/43170.pdf Revision Guide for AMD Family 10h Processors: http://support.amd.com/us/Processor_TechDocs/41322.pdf Revision Guide for AMD Family 11h Processors: http://support.amd.com/us/Processor_TechDocs/41788.pdf + Revision Guide for AMD Family 12h Processors: + http://support.amd.com/us/Processor_TechDocs/44739.pdf Revision Guide for AMD Family 14h Models 00h-0Fh Processors: http://support.amd.com/us/Processor_TechDocs/47534.pdf AMD Family 11h Processor Power and Thermal Data Sheet for Notebooks: diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index fd248a31..aa47be7 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2015,6 +2015,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. the default. off: Turn ECRC off on: Turn ECRC on. + realloc reallocate PCI resources if allocations done by BIOS + are erroneous. pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power Management. diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index 1565eef..6181548 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -534,6 +534,8 @@ Events that are never propagated by the driver: 0x2404 System is waking up from hibernation to undock 0x2405 System is waking up from hibernation to eject bay 0x5010 Brightness level changed/control event +0x6000 KEYBOARD: Numlock key pressed +0x6005 KEYBOARD: Fn key pressed (TO BE VERIFIED) Events that are propagated by the driver to userspace: @@ -545,6 +547,8 @@ Events that are propagated by the driver to userspace: 0x3006 Bay hotplug request (hint to power up SATA link when the optical drive tray is ejected) 0x4003 Undocked (see 0x2x04), can sleep again +0x4010 Docked into hotplug port replicator (non-ACPI dock) +0x4011 Undocked from hotplug port replicator (non-ACPI dock) 0x500B Tablet pen inserted into its storage bay 0x500C Tablet pen removed from its storage bay 0x6011 ALARM: battery is too hot @@ -552,6 +556,7 @@ Events that are propagated by the driver to userspace: 0x6021 ALARM: a sensor is too hot 0x6022 ALARM: a sensor is extremely hot 0x6030 System thermal table changed +0x6040 Nvidia Optimus/AC adapter related (TO BE VERIFIED) Battery nearly empty alarms are a last resort attempt to get the operating system to hibernate or shutdown cleanly (0x2313), or shutdown diff --git a/Documentation/mmc/00-INDEX b/Documentation/mmc/00-INDEX index 93dd7a7..a9ba672 100644 --- a/Documentation/mmc/00-INDEX +++ b/Documentation/mmc/00-INDEX @@ -4,3 +4,5 @@ mmc-dev-attrs.txt - info on SD and MMC device attributes mmc-dev-parts.txt - info on SD and MMC device partitions +mmc-async-req.txt + - info on mmc asynchronous requests diff --git a/Documentation/mmc/mmc-async-req.txt b/Documentation/mmc/mmc-async-req.txt new file mode 100644 index 0000000..ae1907b --- /dev/null +++ b/Documentation/mmc/mmc-async-req.txt @@ -0,0 +1,87 @@ +Rationale +========= + +How significant is the cache maintenance overhead? +It depends. Fast eMMC and multiple cache levels with speculative cache +pre-fetch makes the cache overhead relatively significant. If the DMA +preparations for the next request are done in parallel with the current +transfer, the DMA preparation overhead would not affect the MMC performance. +The intention of non-blocking (asynchronous) MMC requests is to minimize the +time between when an MMC request ends and another MMC request begins. +Using mmc_wait_for_req(), the MMC controller is idle while dma_map_sg and +dma_unmap_sg are processing. Using non-blocking MMC requests makes it +possible to prepare the caches for next job in parallel with an active +MMC request. + +MMC block driver +================ + +The mmc_blk_issue_rw_rq() in the MMC block driver is made non-blocking. +The increase in throughput is proportional to the time it takes to +prepare (major part of preparations are dma_map_sg() and dma_unmap_sg()) +a request and how fast the memory is. The faster the MMC/SD is the +more significant the prepare request time becomes. Roughly the expected +performance gain is 5% for large writes and 10% on large reads on a L2 cache +platform. In power save mode, when clocks run on a lower frequency, the DMA +preparation may cost even more. As long as these slower preparations are run +in parallel with the transfer performance won't be affected. + +Details on measurements from IOZone and mmc_test +================================================ + +https://wiki.linaro.org/WorkingGroups/Kernel/Specs/StoragePerfMMC-async-req + +MMC core API extension +====================== + +There is one new public function mmc_start_req(). +It starts a new MMC command request for a host. The function isn't +truly non-blocking. If there is an ongoing async request it waits +for completion of that request and starts the new one and returns. It +doesn't wait for the new request to complete. If there is no ongoing +request it starts the new request and returns immediately. + +MMC host extensions +=================== + +There are two optional members in the mmc_host_ops -- pre_req() and +post_req() -- that the host driver may implement in order to move work +to before and after the actual mmc_host_ops.request() function is called. +In the DMA case pre_req() may do dma_map_sg() and prepare the DMA +descriptor, and post_req() runs the dma_unmap_sg(). + +Optimize for the first request +============================== + +The first request in a series of requests can't be prepared in parallel +with the previous transfer, since there is no previous request. +The argument is_first_req in pre_req() indicates that there is no previous +request. The host driver may optimize for this scenario to minimize +the performance loss. A way to optimize for this is to split the current +request in two chunks, prepare the first chunk and start the request, +and finally prepare the second chunk and start the transfer. + +Pseudocode to handle is_first_req scenario with minimal prepare overhead: + +if (is_first_req && req->size > threshold) + /* start MMC transfer for the complete transfer size */ + mmc_start_command(MMC_CMD_TRANSFER_FULL_SIZE); + + /* + * Begin to prepare DMA while cmd is being processed by MMC. + * The first chunk of the request should take the same time + * to prepare as the "MMC process command time". + * If prepare time exceeds MMC cmd time + * the transfer is delayed, guesstimate max 4k as first chunk size. + */ + prepare_1st_chunk_for_dma(req); + /* flush pending desc to the DMAC (dmaengine.h) */ + dma_issue_pending(req->dma_desc); + + prepare_2nd_chunk_for_dma(req); + /* + * The second issue_pending should be called before MMC runs out + * of the first chunk. If the MMC runs out of the first data chunk + * before this call, the transfer is delayed. + */ + dma_issue_pending(req->dma_desc); diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index d3d653a..bfe9242 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -346,7 +346,7 @@ tcp_orphan_retries - INTEGER when RTO retransmissions remain unacknowledged. See tcp_retries2 for more details. - The default value is 7. + The default value is 8. If your machine is a loaded WEB server, you should think about lowering this value, such sockets may consume significant resources. Cf. tcp_max_orphans. diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt index 8888083..64565aa 100644 --- a/Documentation/power/devices.txt +++ b/Documentation/power/devices.txt @@ -520,59 +520,20 @@ Support for power domains is provided through the pwr_domain field of struct device. This field is a pointer to an object of type struct dev_power_domain, defined in include/linux/pm.h, providing a set of power management callbacks analogous to the subsystem-level and device driver callbacks that are executed -for the given device during all power transitions, in addition to the respective -subsystem-level callbacks. Specifically, the power domain "suspend" callbacks -(i.e. ->runtime_suspend(), ->suspend(), ->freeze(), ->poweroff(), etc.) are -executed after the analogous subsystem-level callbacks, while the power domain -"resume" callbacks (i.e. ->runtime_resume(), ->resume(), ->thaw(), ->restore, -etc.) are executed before the analogous subsystem-level callbacks. Error codes -returned by the "suspend" and "resume" power domain callbacks are ignored. - -Power domain ->runtime_idle() callback is executed before the subsystem-level -->runtime_idle() callback and the result returned by it is not ignored. Namely, -if it returns error code, the subsystem-level ->runtime_idle() callback will not -be called and the helper function rpm_idle() executing it will return error -code. This mechanism is intended to help platforms where saving device state -is a time consuming operation and should only be carried out if all devices -in the power domain are idle, before turning off the shared power resource(s). -Namely, the power domain ->runtime_idle() callback may return error code until -the pm_runtime_idle() helper (or its asychronous version) has been called for -all devices in the power domain (it is recommended that the returned error code -be -EBUSY in those cases), preventing the subsystem-level ->runtime_idle() -callback from being run prematurely. - -The support for device power domains is only relevant to platforms needing to -use the same subsystem-level (e.g. platform bus type) and device driver power -management callbacks in many different power domain configurations and wanting -to avoid incorporating the support for power domains into the subsystem-level -callbacks. The other platforms need not implement it or take it into account -in any way. - - -System Devices --------------- -System devices (sysdevs) follow a slightly different API, which can be found in - - include/linux/sysdev.h - drivers/base/sys.c - -System devices will be suspended with interrupts disabled, and after all other -devices have been suspended. On resume, they will be resumed before any other -devices, and also with interrupts disabled. These things occur in special -"sysdev_driver" phases, which affect only system devices. - -Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when -the non-boot CPUs are all offline and IRQs are disabled on the remaining online -CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a -sleep state (or a system image is created). During resume (or after the image -has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs -are enabled on the only online CPU, the non-boot CPUs are enabled, and the -resume_noirq (or thaw_noirq or restore_noirq) phase begins. - -Code to actually enter and exit the system-wide low power state sometimes -involves hardware details that are only known to the boot firmware, and -may leave a CPU running software (from SRAM or flash memory) that monitors -the system and manages its wakeup sequence. +for the given device during all power transitions, instead of the respective +subsystem-level callbacks. Specifically, if a device's pm_domain pointer is +not NULL, the ->suspend() callback from the object pointed to by it will be +executed instead of its subsystem's (e.g. bus type's) ->suspend() callback and +anlogously for all of the remaining callbacks. In other words, power management +domain callbacks, if defined for the given device, always take precedence over +the callbacks provided by the device's subsystem (e.g. bus type). + +The support for device power management domains is only relevant to platforms +needing to use the same device driver power management callbacks in many +different power domain configurations and wanting to avoid incorporating the +support for power domains into subsystem-level callbacks, for example by +modifying the platform bus type. Other platforms need not implement it or take +it into account in any way. Device Low Power (suspend) States diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt index 654097b..b24875b 100644 --- a/Documentation/power/runtime_pm.txt +++ b/Documentation/power/runtime_pm.txt @@ -501,13 +501,29 @@ helper functions described in Section 4. In that case, pm_runtime_resume() should be used. Of course, for this purpose the device's run-time PM has to be enabled earlier by calling pm_runtime_enable(). -If the device bus type's or driver's ->probe() or ->remove() callback runs +If the device bus type's or driver's ->probe() callback runs pm_runtime_suspend() or pm_runtime_idle() or their asynchronous counterparts, they will fail returning -EAGAIN, because the device's usage counter is -incremented by the core before executing ->probe() and ->remove(). Still, it -may be desirable to suspend the device as soon as ->probe() or ->remove() has -finished, so the PM core uses pm_runtime_idle_sync() to invoke the -subsystem-level idle callback for the device at that time. +incremented by the driver core before executing ->probe(). Still, it may be +desirable to suspend the device as soon as ->probe() has finished, so the driver +core uses pm_runtime_put_sync() to invoke the subsystem-level idle callback for +the device at that time. + +Moreover, the driver core prevents runtime PM callbacks from racing with the bus +notifier callback in __device_release_driver(), which is necessary, because the +notifier is used by some subsystems to carry out operations affecting the +runtime PM functionality. It does so by calling pm_runtime_get_sync() before +driver_sysfs_remove() and the BUS_NOTIFY_UNBIND_DRIVER notifications. This +resumes the device if it's in the suspended state and prevents it from +being suspended again while those routines are being executed. + +To allow bus types and drivers to put devices into the suspended state by +calling pm_runtime_suspend() from their ->remove() routines, the driver core +executes pm_runtime_put_sync() after running the BUS_NOTIFY_UNBIND_DRIVER +notifications in __device_release_driver(). This requires bus types and +drivers to make their ->remove() callbacks avoid races with runtime PM directly, +but also it allows of more flexibility in the handling of devices during the +removal of their drivers. The user space can effectively disallow the driver of the device to power manage it at run time by changing the value of its /sys/devices/.../power/control @@ -566,11 +582,6 @@ to do this is: pm_runtime_set_active(dev); pm_runtime_enable(dev); -The PM core always increments the run-time usage counter before calling the -->prepare() callback and decrements it after calling the ->complete() callback. -Hence disabling run-time PM temporarily like this will not cause any run-time -suspend callbacks to be lost. - 7. Generic subsystem callbacks Subsystems may wish to conserve code space by using the set of generic power diff --git a/Documentation/spinlocks.txt b/Documentation/spinlocks.txt index 2e3c64b..9dbe885 100644 --- a/Documentation/spinlocks.txt +++ b/Documentation/spinlocks.txt @@ -13,18 +13,8 @@ static DEFINE_SPINLOCK(xxx_lock); The above is always safe. It will disable interrupts _locally_, but the spinlock itself will guarantee the global lock, so it will guarantee that there is only one thread-of-control within the region(s) protected by that -lock. This works well even under UP. The above sequence under UP -essentially is just the same as doing - - unsigned long flags; - - save_flags(flags); cli(); - ... critical section ... - restore_flags(flags); - -so the code does _not_ need to worry about UP vs SMP issues: the spinlocks -work correctly under both (and spinlocks are actually more efficient on -architectures that allow doing the "save_flags + cli" in one operation). +lock. This works well even under UP also, so the code does _not_ need to +worry about UP vs SMP issues: the spinlocks work correctly under both. NOTE! Implications of spin_locks for memory are further described in: @@ -36,27 +26,7 @@ The above is usually pretty simple (you usually need and want only one spinlock for most things - using more than one spinlock can make things a lot more complex and even slower and is usually worth it only for sequences that you _know_ need to be split up: avoid it at all cost if you -aren't sure). HOWEVER, it _does_ mean that if you have some code that does - - cli(); - .. critical section .. - sti(); - -and another sequence that does - - spin_lock_irqsave(flags); - .. critical section .. - spin_unlock_irqrestore(flags); - -then they are NOT mutually exclusive, and the critical regions can happen -at the same time on two different CPU's. That's fine per se, but the -critical regions had better be critical for different things (ie they -can't stomp on each other). - -The above is a problem mainly if you end up mixing code - for example the -routines in ll_rw_block() tend to use cli/sti to protect the atomicity of -their actions, and if a driver uses spinlocks instead then you should -think about issues like the above. +aren't sure). This is really the only really hard part about spinlocks: once you start using spinlocks they tend to expand to areas you might not have noticed @@ -120,11 +90,10 @@ Lesson 3: spinlocks revisited. The single spin-lock primitives above are by no means the only ones. They are the most safe ones, and the ones that work under all circumstances, -but partly _because_ they are safe they are also fairly slow. They are -much faster than a generic global cli/sti pair, but slower than they'd -need to be, because they do have to disable interrupts (which is just a -single instruction on a x86, but it's an expensive one - and on other -architectures it can be worse). +but partly _because_ they are safe they are also fairly slow. They are slower +than they'd need to be, because they do have to disable interrupts +(which is just a single instruction on a x86, but it's an expensive one - +and on other architectures it can be worse). If you have a case where you have to protect a data structure across several CPU's and you want to use spinlocks you can potentially use diff --git a/Documentation/usb/error-codes.txt b/Documentation/usb/error-codes.txt index d83703e..b3f606b 100644 --- a/Documentation/usb/error-codes.txt +++ b/Documentation/usb/error-codes.txt @@ -76,6 +76,13 @@ A transfer's actual_length may be positive even when an error has been reported. That's because transfers often involve several packets, so that one or more packets could finish before an error stops further endpoint I/O. +For isochronous URBs, the urb status value is non-zero only if the URB is +unlinked, the device is removed, the host controller is disabled, or the total +transferred length is less than the requested length and the URB_SHORT_NOT_OK +flag is set. Completion handlers for isochronous URBs should only see +urb->status set to zero, -ENOENT, -ECONNRESET, -ESHUTDOWN, or -EREMOTEIO. +Individual frame descriptor status fields may report more status codes. + 0 Transfer completed successfully @@ -132,7 +139,7 @@ one or more packets could finish before an error stops further endpoint I/O. device removal events immediately. -EXDEV ISO transfer only partially completed - look at individual frame status for details + (only set in iso_frame_desc[n].status, not urb->status) -EINVAL ISO madness, if this happens: Log off and go home diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 9b7221a..7c3a880 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -674,7 +674,7 @@ Protocol: 2.10+ Field name: init_size Type: read -Offset/size: 0x25c/4 +Offset/size: 0x260/4 This field indicates the amount of linear contiguous memory starting at the kernel runtime start address that the kernel needs before it diff --git a/MAINTAINERS b/MAINTAINERS index f0358cd..789fed6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1,4 +1,5 @@ + List of maintainers and how to submit kernel changes Please try to follow the guidelines below. This will make things @@ -594,6 +595,16 @@ S: Maintained F: arch/arm/lib/floppydma.S F: arch/arm/include/asm/floppy.h +ARM PMU PROFILING AND DEBUGGING +M: Will Deacon <will.deacon@arm.com> +S: Maintained +F: arch/arm/kernel/perf_event* +F: arch/arm/oprofile/common.c +F: arch/arm/kernel/pmu.c +F: arch/arm/include/asm/pmu.h +F: arch/arm/kernel/hw_breakpoint.c +F: arch/arm/include/asm/hw_breakpoint.h + ARM PORT M: Russell King <linux@arm.linux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1345,16 +1356,18 @@ F: drivers/auxdisplay/ F: include/linux/cfag12864b.h AVR32 ARCHITECTURE -M: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> +M: Haavard Skinnemoen <hskinnemoen@gmail.com> +M: Hans-Christian Egtvedt <egtvedt@samfundet.no> W: http://www.atmel.com/products/AVR32/ W: http://avr32linux.org/ W: http://avrfreaks.net/ -S: Supported +S: Maintained F: arch/avr32/ AVR32/AT32AP MACHINE SUPPORT -M: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com> -S: Supported +M: Haavard Skinnemoen <hskinnemoen@gmail.com> +M: Hans-Christian Egtvedt <egtvedt@samfundet.no> +S: Maintained F: arch/avr32/mach-at32ap/ AX.25 NETWORK LAYER @@ -1390,7 +1403,6 @@ F: include/linux/backlight.h BATMAN ADVANCED M: Marek Lindner <lindner_marek@yahoo.de> M: Simon Wunderlich <siwu@hrz.tu-chemnitz.de> -M: Sven Eckelmann <sven@narfation.org> L: b.a.t.m.a.n@lists.open-mesh.org W: http://www.open-mesh.org/ S: Maintained @@ -1423,7 +1435,6 @@ S: Supported F: arch/blackfin/ BLACKFIN EMAC DRIVER -M: Michael Hennerich <michael.hennerich@analog.com> L: uclinux-dist-devel@blackfin.uclinux.org W: http://blackfin.uclinux.org S: Supported @@ -1639,7 +1650,7 @@ CAN NETWORK LAYER M: Oliver Hartkopp <socketcan@hartkopp.net> M: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> M: Urs Thuermann <urs.thuermann@volkswagen.de> -L: socketcan-core@lists.berlios.de +L: socketcan-core@lists.berlios.de (subscribers-only) L: netdev@vger.kernel.org W: http://developer.berlios.de/projects/socketcan/ S: Maintained @@ -1651,7 +1662,7 @@ F: include/linux/can/raw.h CAN NETWORK DRIVERS M: Wolfgang Grandegger <wg@grandegger.com> -L: socketcan-core@lists.berlios.de +L: socketcan-core@lists.berlios.de (subscribers-only) L: netdev@vger.kernel.org W: http://developer.berlios.de/projects/socketcan/ S: Maintained @@ -2197,7 +2208,7 @@ F: drivers/acpi/dock.c DOCUMENTATION M: Randy Dunlap <rdunlap@xenotime.net> L: linux-doc@vger.kernel.org -T: quilt oss.oracle.com/~rdunlap/kernel-doc-patches/current/ +T: quilt http://userweb.kernel.org/~rdunlap/kernel-doc-patches/current/ S: Maintained F: Documentation/ @@ -4574,9 +4585,8 @@ S: Maintained F: drivers/mmc/host/omap.c OMAP HS MMC SUPPORT -M: Madhusudhan Chikkature <madhu.cr@ti.com> L: linux-omap@vger.kernel.org -S: Maintained +S: Orphan F: drivers/mmc/host/omap_hsmmc.c OMAP RANDOM NUMBER GENERATOR SUPPORT @@ -4982,7 +4992,7 @@ F: drivers/power/power_supply* PNP SUPPORT M: Adam Belay <abelay@mit.edu> -M: Bjorn Helgaas <bjorn.helgaas@hp.com> +M: Bjorn Helgaas <bhelgaas@google.com> S: Maintained F: drivers/pnp/ @@ -5181,6 +5191,7 @@ S: Supported F: drivers/net/qlcnic/ QLOGIC QLGE 10Gb ETHERNET DRIVER +M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> M: Ron Mercer <ron.mercer@qlogic.com> M: linux-driver@qlogic.com L: netdev@vger.kernel.org @@ -6231,9 +6242,14 @@ F: drivers/char/toshiba.c F: include/linux/toshiba.h TMIO MMC DRIVER +M: Guennadi Liakhovetski <g.liakhovetski@gmx.de> M: Ian Molton <ian@mnementh.co.uk> +L: linux-mmc@vger.kernel.org S: Maintained -F: drivers/mmc/host/tmio_mmc.* +F: drivers/mmc/host/tmio_mmc* +F: drivers/mmc/host/sh_mobile_sdhi.c +F: include/linux/mmc/tmio.h +F: include/linux/mmc/sh_mobile_sdhi.h TMPFS (SHMEM FILESYSTEM) M: Hugh Dickins <hughd@google.com> @@ -6310,7 +6326,7 @@ F: drivers/scsi/u14-34f.c UBI FILE SYSTEM (UBIFS) M: Artem Bityutskiy <dedekind1@gmail.com> -M: Adrian Hunter <adrian.hunter@nokia.com> +M: Adrian Hunter <adrian.hunter@intel.com> L: linux-mtd@lists.infradead.org T: git git://git.infradead.org/ubifs-2.6.git W: http://www.linux-mtd.infradead.org/doc/ubifs.html @@ -6434,8 +6450,9 @@ S: Maintained F: drivers/usb/misc/rio500* USB EHCI DRIVER +M: Alan Stern <stern@rowland.harvard.edu> L: linux-usb@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/usb/ehci.txt F: drivers/usb/host/ehci* @@ -6465,6 +6482,12 @@ S: Maintained F: Documentation/hid/hiddev.txt F: drivers/hid/usbhid/ +USB/IP DRIVERS +M: Matt Mooney <mfm@muteddisk.com> +L: linux-usb@vger.kernel.org +S: Maintained +F: drivers/staging/usbip/ + USB ISP116X DRIVER M: Olav Kongas <ok@artecdesign.ee> L: linux-usb@vger.kernel.org @@ -6494,8 +6517,9 @@ S: Maintained F: sound/usb/midi.* USB OHCI DRIVER +M: Alan Stern <stern@rowland.harvard.edu> L: linux-usb@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/usb/ohci.txt F: drivers/usb/host/ohci* @@ -6724,6 +6748,7 @@ F: fs/fat/ VIDEOBUF2 FRAMEWORK M: Pawel Osciak <pawel@osciak.com> M: Marek Szyprowski <m.szyprowski@samsung.com> +M: Kyungmin Park <kyungmin.park@samsung.com> L: linux-media@vger.kernel.org S: Maintained F: drivers/media/video/videobuf2-* @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = NAME = Sneaky Weasel # *DOCUMENTATION* @@ -1,6 +1,6 @@ - Linux kernel release 2.6.xx <http://kernel.org/> + Linux kernel release 3.x <http://kernel.org/> -These are the release notes for Linux version 2.6. Read them carefully, +These are the release notes for Linux version 3. Read them carefully, as they tell you what this is all about, explain how to install the kernel, and what to do if something goes wrong. @@ -62,10 +62,10 @@ INSTALLING the kernel source: directory where you have permissions (eg. your home directory) and unpack it: - gzip -cd linux-2.6.XX.tar.gz | tar xvf - + gzip -cd linux-3.X.tar.gz | tar xvf - or - bzip2 -dc linux-2.6.XX.tar.bz2 | tar xvf - + bzip2 -dc linux-3.X.tar.bz2 | tar xvf - Replace "XX" with the version number of the latest kernel. @@ -75,15 +75,15 @@ INSTALLING the kernel source: files. They should match the library, and not get messed up by whatever the kernel-du-jour happens to be. - - You can also upgrade between 2.6.xx releases by patching. Patches are + - You can also upgrade between 3.x releases by patching. Patches are distributed in the traditional gzip and the newer bzip2 format. To install by patching, get all the newer patch files, enter the - top level directory of the kernel source (linux-2.6.xx) and execute: + top level directory of the kernel source (linux-3.x) and execute: - gzip -cd ../patch-2.6.xx.gz | patch -p1 + gzip -cd ../patch-3.x.gz | patch -p1 or - bzip2 -dc ../patch-2.6.xx.bz2 | patch -p1 + bzip2 -dc ../patch-3.x.bz2 | patch -p1 (repeat xx for all versions bigger than the version of your current source tree, _in_order_) and you should be ok. You may want to remove @@ -91,9 +91,9 @@ INSTALLING the kernel source: failed patches (xxx# or xxx.rej). If there are, either you or me has made a mistake. - Unlike patches for the 2.6.x kernels, patches for the 2.6.x.y kernels + Unlike patches for the 3.x kernels, patches for the 3.x.y kernels (also known as the -stable kernels) are not incremental but instead apply - directly to the base 2.6.x kernel. Please read + directly to the base 3.x kernel. Please read Documentation/applying-patches.txt for more information. Alternatively, the script patch-kernel can be used to automate this @@ -107,14 +107,14 @@ INSTALLING the kernel source: an alternative directory can be specified as the second argument. - If you are upgrading between releases using the stable series patches - (for example, patch-2.6.xx.y), note that these "dot-releases" are - not incremental and must be applied to the 2.6.xx base tree. For - example, if your base kernel is 2.6.12 and you want to apply the - 2.6.12.3 patch, you do not and indeed must not first apply the - 2.6.12.1 and 2.6.12.2 patches. Similarly, if you are running kernel - version 2.6.12.2 and want to jump to 2.6.12.3, you must first - reverse the 2.6.12.2 patch (that is, patch -R) _before_ applying - the 2.6.12.3 patch. + (for example, patch-3.x.y), note that these "dot-releases" are + not incremental and must be applied to the 3.x base tree. For + example, if your base kernel is 3.0 and you want to apply the + 3.0.3 patch, you do not and indeed must not first apply the + 3.0.1 and 3.0.2 patches. Similarly, if you are running kernel + version 3.0.2 and want to jump to 3.0.3, you must first + reverse the 3.0.2 patch (that is, patch -R) _before_ applying + the 3.0.3 patch. You can read more on this in Documentation/applying-patches.txt - Make sure you have no stale .o files and dependencies lying around: @@ -126,7 +126,7 @@ INSTALLING the kernel source: SOFTWARE REQUIREMENTS - Compiling and running the 2.6.xx kernels requires up-to-date + Compiling and running the 3.x kernels requires up-to-date versions of various software packages. Consult Documentation/Changes for the minimum version numbers required and how to get updates for these packages. Beware that using @@ -142,11 +142,11 @@ BUILD directory for the kernel: Using the option "make O=output/dir" allow you to specify an alternate place for the output files (including .config). Example: - kernel source code: /usr/src/linux-2.6.N + kernel source code: /usr/src/linux-3.N build directory: /home/name/build/kernel To configure and build the kernel use: - cd /usr/src/linux-2.6.N + cd /usr/src/linux-3.N make O=/home/name/build/kernel menuconfig make O=/home/name/build/kernel sudo make O=/home/name/build/kernel modules_install install diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h index 8af56ce..445dc42 100644 --- a/arch/alpha/include/asm/mmzone.h +++ b/arch/alpha/include/asm/mmzone.h @@ -56,7 +56,6 @@ PLAT_NODE_DATA_LOCALNR(unsigned long p, int n) * Given a kernel address, find the home node of the underlying memory. */ #define kvaddr_to_nid(kaddr) pa_to_nid(__pa(kaddr)) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) /* * Given a kaddr, LOCAL_BASE_ADDR finds the owning node of the memory diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 942fad9..940b201 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -597,6 +597,8 @@ __common_mmu_cache_on: sub pc, lr, r0, lsr #32 @ properly flush pipeline #endif +#define PROC_ENTRY_SIZE (4*5) + /* * Here follow the relocatable cache support functions for the * various processors. This is a generic hook for locating an @@ -624,7 +626,7 @@ call_cache_fn: adr r12, proc_types ARM( addeq pc, r12, r3 ) @ call cache function THUMB( addeq r12, r3 ) THUMB( moveq pc, r12 ) @ call cache function - add r12, r12, #4*5 + add r12, r12, #PROC_ENTRY_SIZE b 1b /* @@ -794,6 +796,16 @@ proc_types: .size proc_types, . - proc_types + /* + * If you get a "non-constant expression in ".if" statement" + * error from the assembler on this line, check that you have + * not accidentally written a "b" instruction where you should + * have written W(b). + */ + .if (. - proc_types) % PROC_ENTRY_SIZE != 0 + .error "The size of one or more proc_types entries is wrong." + .endif + /* * Turn off the Cache and MMU. ARMv3 does not support * reading the control register, but ARMv4 does. diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c index e568163..841df7d 100644 --- a/arch/arm/common/dmabounce.c +++ b/arch/arm/common/dmabounce.c @@ -255,7 +255,7 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size, if (buf == 0) { dev_err(dev, "%s: unable to map unsafe buffer %p!\n", __func__, ptr); - return 0; + return ~0; } dev_dbg(dev, diff --git a/arch/arm/configs/mmp2_defconfig b/arch/arm/configs/mmp2_defconfig index 47ad3b1..5a58452 100644 --- a/arch/arm/configs/mmp2_defconfig +++ b/arch/arm/configs/mmp2_defconfig @@ -8,6 +8,7 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_ARCH_MMP=y +CONFIG_MACH_BROWNSTONE=y CONFIG_MACH_FLINT=y CONFIG_MACH_MARVELL_JASPER=y CONFIG_HIGH_RES_TIMERS=y @@ -63,10 +64,16 @@ CONFIG_BACKLIGHT_MAX8925=y # CONFIG_USB_SUPPORT is not set CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_MAX8925=y +CONFIG_MMC=y # CONFIG_DNOTIFY is not set CONFIG_INOTIFY=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y +CONFIG_EXT2_FS=y +CONFIG_EXT3_FS=y +CONFIG_EXT4_FS=y +CONFIG_MSDOS_FS=y +CONFIG_FAT_DEFAULT_CODEPAGE=437 CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y CONFIG_NFS_FS=y @@ -81,7 +88,7 @@ CONFIG_DEBUG_KERNEL=y # CONFIG_DEBUG_PREEMPT is not set CONFIG_DEBUG_INFO=y # CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_DYNAMIC_DEBUG=y +# CONFIG_DYNAMIC_DEBUG is not set CONFIG_DEBUG_USER=y CONFIG_DEBUG_ERRORS=y # CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index bc2d2d7..65c3f24 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -13,6 +13,9 @@ * Do not include any C declarations in this file - it is included by * assembler source. */ +#ifndef __ASM_ASSEMBLER_H__ +#define __ASM_ASSEMBLER_H__ + #ifndef __ASSEMBLY__ #error "Only include this from assembly code" #endif @@ -290,3 +293,4 @@ .macro ldrusr, reg, ptr, inc, cond=al, rept=1, abort=9001f usracc ldr, \reg, \ptr, \inc, \cond, \rept, \abort .endm +#endif /* __ASM_ASSEMBLER_H__ */ diff --git a/arch/arm/include/asm/entry-macro-multi.S b/arch/arm/include/asm/entry-macro-multi.S index ec0bbf7..2da8547 100644 --- a/arch/arm/include/asm/entry-macro-multi.S +++ b/arch/arm/include/asm/entry-macro-multi.S @@ -1,3 +1,5 @@ +#include <asm/assembler.h> + /* * Interrupt handling. Preserves r7, r8, r9 */ diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index fee7c36..016d6a0 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -193,8 +193,17 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, offset -= 0x02000000; offset += sym->st_value - loc; - /* only Thumb addresses allowed (no interworking) */ - if (!(offset & 1) || + /* + * For function symbols, only Thumb addresses are + * allowed (no interworking). + * + * For non-function symbols, the destination + * has no specific ARM/Thumb disposition, so + * the branch is resolved under the assumption + * that interworking is not required. + */ + if ((ELF32_ST_TYPE(sym->st_info) == STT_FUNC && + !(offset & 1)) || offset <= (s32)0xff000000 || offset >= (s32)0x01000000) { pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n", diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c index d53c0ab..2b5b142 100644 --- a/arch/arm/kernel/perf_event.c +++ b/arch/arm/kernel/perf_event.c @@ -583,7 +583,7 @@ static int armpmu_event_init(struct perf_event *event) static void armpmu_enable(struct pmu *pmu) { /* Enable all of the perf events on hardware. */ - int idx; + int idx, enabled = 0; struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); if (!armpmu) @@ -596,9 +596,11 @@ static void armpmu_enable(struct pmu *pmu) continue; armpmu->enable(&event->hw, idx); + enabled = 1; } - armpmu->start(); + if (enabled) + armpmu->start(); } static void armpmu_disable(struct pmu *pmu) diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index ed11fb0..acbb447 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -73,6 +73,7 @@ __setup("fpe=", fpe_setup); #endif extern void paging_init(struct machine_desc *desc); +extern void sanity_check_meminfo(void); extern void reboot_setup(char *str); unsigned int processor_id; @@ -900,6 +901,7 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); + sanity_check_meminfo(); arm_memblock_init(&meminfo, mdesc); paging_init(mdesc); diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 344e52b..e7f92a4 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -318,9 +318,13 @@ asmlinkage void __cpuinit secondary_start_kernel(void) smp_store_cpu_info(cpu); /* - * OK, now it's safe to let the boot CPU continue + * OK, now it's safe to let the boot CPU continue. Wait for + * the CPU migration code to notice that the CPU is online + * before we continue. */ set_cpu_online(cpu, true); + while (!cpu_active(cpu)) + cpu_relax(); /* * OK, it's off to the idle thread for us diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c index 60636f4..2c277d4 100644 --- a/arch/arm/kernel/smp_twd.c +++ b/arch/arm/kernel/smp_twd.c @@ -115,7 +115,7 @@ static void __cpuinit twd_calibrate_rate(void) twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); printk("%lu.%02luMHz.\n", twd_timer_rate / 1000000, - (twd_timer_rate / 1000000) % 100); + (twd_timer_rate / 10000) % 100); } } diff --git a/arch/arm/mach-at91/at91cap9.c b/arch/arm/mach-at91/at91cap9.c index 17fae4a..f1013d0 100644 --- a/arch/arm/mach-at91/at91cap9.c +++ b/arch/arm/mach-at91/at91cap9.c @@ -223,15 +223,15 @@ static struct clk *periph_clocks[] __initdata = { }; static struct clk_lookup periph_clocks_lookups[] = { - CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk), - CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk), + CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk), + CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk), CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk), CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk), CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk), CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk), CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb_clk), - CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk), - CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk), + CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk), + CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk), }; static struct clk_lookup usart_clocks_lookups[] = { diff --git a/arch/arm/mach-at91/at91cap9_devices.c b/arch/arm/mach-at91/at91cap9_devices.c index cd850ed..dba0d8d 100644 --- a/arch/arm/mach-at91/at91cap9_devices.c +++ b/arch/arm/mach-at91/at91cap9_devices.c @@ -1220,7 +1220,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91cap9_set_console_clock(portnr); + at91cap9_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c index b228ce9..83a1a3f 100644 --- a/arch/arm/mach-at91/at91rm9200.c +++ b/arch/arm/mach-at91/at91rm9200.c @@ -199,9 +199,9 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.1", &tc3_clk), CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.1", &tc4_clk), CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.1", &tc5_clk), - CLKDEV_CON_DEV_ID("ssc", "ssc.0", &ssc0_clk), - CLKDEV_CON_DEV_ID("ssc", "ssc.1", &ssc1_clk), - CLKDEV_CON_DEV_ID("ssc", "ssc.2", &ssc2_clk), + CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk), + CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk), + CLKDEV_CON_DEV_ID("pclk", "ssc.2", &ssc2_clk), }; static struct clk_lookup usart_clocks_lookups[] = { diff --git a/arch/arm/mach-at91/at91rm9200_devices.c b/arch/arm/mach-at91/at91rm9200_devices.c index a0ba475..7227755 100644 --- a/arch/arm/mach-at91/at91rm9200_devices.c +++ b/arch/arm/mach-at91/at91rm9200_devices.c @@ -1135,7 +1135,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91rm9200_set_console_clock(portnr); + at91rm9200_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c index 1fdeb90..39f81f4 100644 --- a/arch/arm/mach-at91/at91sam9260_devices.c +++ b/arch/arm/mach-at91/at91sam9260_devices.c @@ -1173,7 +1173,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91sam9260_set_console_clock(portnr); + at91sam9260_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c index 3eb4538..5004bf0 100644 --- a/arch/arm/mach-at91/at91sam9261_devices.c +++ b/arch/arm/mach-at91/at91sam9261_devices.c @@ -1013,7 +1013,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91sam9261_set_console_clock(portnr); + at91sam9261_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c index ffe081b..a050f41 100644 --- a/arch/arm/mach-at91/at91sam9263_devices.c +++ b/arch/arm/mach-at91/at91sam9263_devices.c @@ -1395,7 +1395,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91sam9263_set_console_clock(portnr); + at91sam9263_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c index 2bb6ff9..11e2141 100644 --- a/arch/arm/mach-at91/at91sam9g45.c +++ b/arch/arm/mach-at91/at91sam9g45.c @@ -217,11 +217,11 @@ static struct clk *periph_clocks[] __initdata = { static struct clk_lookup periph_clocks_lookups[] = { /* One additional fake clock for ohci */ CLKDEV_CON_ID("ohci_clk", &uhphs_clk), - CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci.0", &uhphs_clk), - CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk), - CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk), - CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.0", &mmc0_clk), - CLKDEV_CON_DEV_ID("mci_clk", "at91_mci.1", &mmc1_clk), + CLKDEV_CON_DEV_ID("ehci_clk", "atmel-ehci", &uhphs_clk), + CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk), + CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk), + CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.0", &mmc0_clk), + CLKDEV_CON_DEV_ID("mci_clk", "atmel_mci.1", &mmc1_clk), CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.0", &spi0_clk), CLKDEV_CON_DEV_ID("spi_clk", "atmel_spi.1", &spi1_clk), CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tcb0_clk), diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c index 0567486..600bffb 100644 --- a/arch/arm/mach-at91/at91sam9g45_devices.c +++ b/arch/arm/mach-at91/at91sam9g45_devices.c @@ -1550,7 +1550,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91sam9g45_set_console_clock(portnr); + at91sam9g45_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/at91sam9rl.c b/arch/arm/mach-at91/at91sam9rl.c index 1a40f16..29dff18 100644 --- a/arch/arm/mach-at91/at91sam9rl.c +++ b/arch/arm/mach-at91/at91sam9rl.c @@ -191,8 +191,8 @@ static struct clk *periph_clocks[] __initdata = { }; static struct clk_lookup periph_clocks_lookups[] = { - CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc.0", &utmi_clk), - CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc.0", &udphs_clk), + CLKDEV_CON_DEV_ID("hclk", "atmel_usba_udc", &utmi_clk), + CLKDEV_CON_DEV_ID("pclk", "atmel_usba_udc", &udphs_clk), CLKDEV_CON_DEV_ID("t0_clk", "atmel_tcb.0", &tc0_clk), CLKDEV_CON_DEV_ID("t1_clk", "atmel_tcb.0", &tc1_clk), CLKDEV_CON_DEV_ID("t2_clk", "atmel_tcb.0", &tc2_clk), diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c index c296045..aacb19d 100644 --- a/arch/arm/mach-at91/at91sam9rl_devices.c +++ b/arch/arm/mach-at91/at91sam9rl_devices.c @@ -1168,7 +1168,7 @@ void __init at91_set_serial_console(unsigned portnr) { if (portnr < ATMEL_MAX_UART) { atmel_default_console_device = at91_uarts[portnr]; - at91sam9rl_set_console_clock(portnr); + at91sam9rl_set_console_clock(at91_uarts[portnr]->id); } } diff --git a/arch/arm/mach-at91/board-cap9adk.c b/arch/arm/mach-at91/board-cap9adk.c index 1904fdf..cdb65d4 100644 --- a/arch/arm/mach-at91/board-cap9adk.c +++ b/arch/arm/mach-at91/board-cap9adk.c @@ -215,7 +215,7 @@ static void __init cap9adk_add_device_nand(void) csa = at91_sys_read(AT91_MATRIX_EBICSA); at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_VDDIOMSEL_3_3V); - cap9adk_nand_data.bus_width_16 = !board_have_nand_8bit(); + cap9adk_nand_data.bus_width_16 = board_have_nand_16bit(); /* setup bus-width (8 or 16) */ if (cap9adk_nand_data.bus_width_16) cap9adk_nand_smc_config.mode |= AT91_SMC_DBW_16; diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c index d600dc1..5c24074 100644 --- a/arch/arm/mach-at91/board-sam9260ek.c +++ b/arch/arm/mach-at91/board-sam9260ek.c @@ -214,7 +214,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = { static void __init ek_add_device_nand(void) { - ek_nand_data.bus_width_16 = !board_have_nand_8bit(); + ek_nand_data.bus_width_16 = board_have_nand_16bit(); /* setup bus-width (8 or 16) */ if (ek_nand_data.bus_width_16) ek_nand_smc_config.mode |= AT91_SMC_DBW_16; diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c index f897f84..b60c22b 100644 --- a/arch/arm/mach-at91/board-sam9261ek.c +++ b/arch/arm/mach-at91/board-sam9261ek.c @@ -220,7 +220,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = { static void __init ek_add_device_nand(void) { - ek_nand_data.bus_width_16 = !board_have_nand_8bit(); + ek_nand_data.bus_width_16 = board_have_nand_16bit(); /* setup bus-width (8 or 16) */ if (ek_nand_data.bus_width_16) ek_nand_smc_config.mode |= AT91_SMC_DBW_16; diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c index 605b26f..9bbdc92 100644 --- a/arch/arm/mach-at91/board-sam9263ek.c +++ b/arch/arm/mach-at91/board-sam9263ek.c @@ -221,7 +221,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = { static void __init ek_add_device_nand(void) { - ek_nand_data.bus_width_16 = !board_have_nand_8bit(); + ek_nand_data.bus_width_16 = board_have_nand_16bit(); /* setup bus-width (8 or 16) */ if (ek_nand_data.bus_width_16) ek_nand_smc_config.mode |= AT91_SMC_DBW_16; diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c index 7624cf0..1325a50 100644 --- a/arch/arm/mach-at91/board-sam9g20ek.c +++ b/arch/arm/mach-at91/board-sam9g20ek.c @@ -198,7 +198,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = { static void __init ek_add_device_nand(void) { - ek_nand_data.bus_width_16 = !board_have_nand_8bit(); + ek_nand_data.bus_width_16 = board_have_nand_16bit(); /* setup bus-width (8 or 16) */ if (ek_nand_data.bus_width_16) ek_nand_smc_config.mode |= AT91_SMC_DBW_16; diff --git a/arch/arm/mach-at91/board-sam9m10g45ek.c b/arch/arm/mach-at91/board-sam9m10g45ek.c index 063c95d..33eaa13 100644 --- a/arch/arm/mach-at91/board-sam9m10g45ek.c +++ b/arch/arm/mach-at91/board-sam9m10g45ek.c @@ -178,7 +178,7 @@ static struct sam9_smc_config __initdata ek_nand_smc_config = { static void __init ek_add_device_nand(void) { - ek_nand_data.bus_width_16 = !board_have_nand_8bit(); + ek_nand_data.bus_width_16 = board_have_nand_16bit(); /* setup bus-width (8 or 16) */ if (ek_nand_data.bus_width_16) ek_nand_smc_config.mode |= AT91_SMC_DBW_16; diff --git a/arch/arm/mach-at91/include/mach/system_rev.h b/arch/arm/mach-at91/include/mach/system_rev.h index b855ee7..8f48660 100644 --- a/arch/arm/mach-at91/include/mach/system_rev.h +++ b/arch/arm/mach-at91/include/mach/system_rev.h @@ -13,13 +13,13 @@ * the 16-31 bit are reserved for at91 generic information * * bit 31: - * 0 => nand 16 bit - * 1 => nand 8 bit + * 0 => nand 8 bit + * 1 => nand 16 bit */ -#define BOARD_HAVE_NAND_8BIT (1 << 31) -static int inline board_have_nand_8bit(void) +#define BOARD_HAVE_NAND_16BIT (1 << 31) +static inline int board_have_nand_16bit(void) { - return system_rev & BOARD_HAVE_NAND_8BIT; + return system_rev & BOARD_HAVE_NAND_16BIT; } #endif /* __ARCH_SYSTEM_REV_H__ */ diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index c67f684..09a87e6 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -520,7 +520,7 @@ fail: */ if (have_imager()) { label = "HD imager"; - mux |= 1; + mux |= 2; /* externally mux MMC1/ENET/AIC33 to imager */ mux |= BIT(6) | BIT(5) | BIT(3); @@ -540,7 +540,7 @@ fail: resets &= ~BIT(1); if (have_tvp7002()) { - mux |= 2; + mux |= 1; resets &= ~BIT(2); label = "tvp7002 HD"; } else { diff --git a/arch/arm/mach-davinci/gpio.c b/arch/arm/mach-davinci/gpio.c index e722139..cafbe13 100644 --- a/arch/arm/mach-davinci/gpio.c +++ b/arch/arm/mach-davinci/gpio.c @@ -254,8 +254,10 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc) { struct davinci_gpio_regs __iomem *g; u32 mask = 0xffff; + struct davinci_gpio_controller *d; - g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc); + d = (struct davinci_gpio_controller *)irq_desc_get_handler_data(desc); + g = (struct davinci_gpio_regs __iomem *)d->regs; /* we only care about one bank */ if (irq & 1) @@ -274,11 +276,14 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc) if (!status) break; __raw_writel(status, &g->intstat); - if (irq & 1) - status >>= 16; /* now demux them to the right lowlevel handler */ - n = (int)irq_get_handler_data(irq); + n = d->irq_base; + if (irq & 1) { + n += 16; + status >>= 16; + } + while (status) { res = ffs(status); n += res; @@ -424,7 +429,13 @@ static int __init davinci_gpio_irq_setup(void) /* set up all irqs in this bank */ irq_set_chained_handler(bank_irq, gpio_irq_handler); - irq_set_handler_data(bank_irq, (__force void *)g); + + /* + * Each chip handles 32 gpios, and each irq bank consists of 16 + * gpio irqs. Pass the irq bank's corresponding controller to + * the chained irq handler. + */ + irq_set_handler_data(bank_irq, &chips[gpio / 32]); for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) { irq_set_chip(irq, &gpio_irqchip); diff --git a/arch/arm/mach-davinci/irq.c b/arch/arm/mach-davinci/irq.c index bfe68ec..952dc12 100644 --- a/arch/arm/mach-davinci/irq.c +++ b/arch/arm/mach-davinci/irq.c @@ -52,8 +52,14 @@ davinci_alloc_gc(void __iomem *base, unsigned int irq_start, unsigned int num) struct irq_chip_type *ct; gc = irq_alloc_generic_chip("AINTC", 1, irq_start, base, handle_edge_irq); + if (!gc) { + pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n", + __func__, irq_start); + return; + } + ct = gc->chip_types; - ct->chip.irq_ack = irq_gc_ack; + ct->chip.irq_ack = irq_gc_ack_set_bit; ct->chip.irq_mask = irq_gc_mask_clr_bit; ct->chip.irq_unmask = irq_gc_mask_set_bit; diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c index 1d4b65f..6659a0d 100644 --- a/arch/arm/mach-ep93xx/core.c +++ b/arch/arm/mach-ep93xx/core.c @@ -251,9 +251,9 @@ static void ep93xx_uart_set_mctrl(struct amba_device *dev, unsigned int mcr; mcr = 0; - if (!(mctrl & TIOCM_RTS)) + if (mctrl & TIOCM_RTS) mcr |= 2; - if (!(mctrl & TIOCM_DTR)) + if (mctrl & TIOCM_DTR) mcr |= 1; __raw_writel(mcr, base + EP93XX_UART_MCR_OFFSET); diff --git a/arch/arm/mach-exynos4/cpu.c b/arch/arm/mach-exynos4/cpu.c index 9babe44..bfd6214 100644 --- a/arch/arm/mach-exynos4/cpu.c +++ b/arch/arm/mach-exynos4/cpu.c @@ -23,6 +23,7 @@ #include <plat/sdhci.h> #include <plat/devs.h> #include <plat/fimc-core.h> +#include <plat/iic-core.h> #include <mach/regs-irq.h> @@ -132,6 +133,11 @@ void __init exynos4_map_io(void) s3c_fimc_setname(1, "exynos4-fimc"); s3c_fimc_setname(2, "exynos4-fimc"); s3c_fimc_setname(3, "exynos4-fimc"); + + /* The I2C bus controllers are directly compatible with s3c2440 */ + s3c_i2c0_setname("s3c2440-i2c"); + s3c_i2c1_setname("s3c2440-i2c"); + s3c_i2c2_setname("s3c2440-i2c"); } void __init exynos4_init_clocks(int xtal) diff --git a/arch/arm/mach-exynos4/dev-audio.c b/arch/arm/mach-exynos4/dev-audio.c index 1eed5f9..983069a 100644 --- a/arch/arm/mach-exynos4/dev-audio.c +++ b/arch/arm/mach-exynos4/dev-audio.c @@ -330,7 +330,7 @@ struct platform_device exynos4_device_ac97 = { static int exynos4_spdif_cfg_gpio(struct platform_device *pdev) { - s3c_gpio_cfgpin_range(EXYNOS4_GPC1(0), 2, S3C_GPIO_SFN(3)); + s3c_gpio_cfgpin_range(EXYNOS4_GPC1(0), 2, S3C_GPIO_SFN(4)); return 0; } diff --git a/arch/arm/mach-exynos4/headsmp.S b/arch/arm/mach-exynos4/headsmp.S index 6c6cfc5..3cdeb36 100644 --- a/arch/arm/mach-exynos4/headsmp.S +++ b/arch/arm/mach-exynos4/headsmp.S @@ -13,7 +13,7 @@ #include <linux/linkage.h> #include <linux/init.h> - __INIT + __CPUINIT /* * exynos4 specific entry point for secondary CPUs. This provides diff --git a/arch/arm/mach-exynos4/init.c b/arch/arm/mach-exynos4/init.c index cf91f50..a8a83e3 100644 --- a/arch/arm/mach-exynos4/init.c +++ b/arch/arm/mach-exynos4/init.c @@ -35,6 +35,7 @@ void __init exynos4_common_init_uarts(struct s3c2410_uartcfg *cfg, int no) tcfg->clocks = exynos4_serial_clocks; tcfg->clocks_size = ARRAY_SIZE(exynos4_serial_clocks); } + tcfg->flags |= NO_NEED_CHECK_CLKSRC; } s3c24xx_init_uartdevs("s5pv210-uart", s5p_uart_resources, cfg, no); diff --git a/arch/arm/mach-exynos4/mach-smdkv310.c b/arch/arm/mach-exynos4/mach-smdkv310.c index 1526764..edd8141 100644 --- a/arch/arm/mach-exynos4/mach-smdkv310.c +++ b/arch/arm/mach-exynos4/mach-smdkv310.c @@ -78,9 +78,7 @@ static struct s3c2410_uartcfg smdkv310_uartcfgs[] __initdata = { }; static struct s3c_sdhci_platdata smdkv310_hsmmc0_pdata __initdata = { - .cd_type = S3C_SDHCI_CD_GPIO, - .ext_cd_gpio = EXYNOS4_GPK0(2), - .ext_cd_gpio_invert = 1, + .cd_type = S3C_SDHCI_CD_INTERNAL, .clk_type = S3C_SDHCI_CLK_DIV_EXTERNAL, #ifdef CONFIG_EXYNOS4_SDHCI_CH0_8BIT .max_width = 8, @@ -96,9 +94,7 @@ static struct s3c_sdhci_platdata smdkv310_hsmmc1_pdata __initdata = { }; static struct s3c_sdhci_platdata smdkv310_hsmmc2_pdata __initdata = { - .cd_type = S3C_SDHCI_CD_GPIO, - .ext_cd_gpio = EXYNOS4_GPK2(2), - .ext_cd_gpio_invert = 1, + .cd_type = S3C_SDHCI_CD_INTERNAL, .clk_type = S3C_SDHCI_CLK_DIV_EXTERNAL, #ifdef CONFIG_EXYNOS4_SDHCI_CH2_8BIT .max_width = 8, diff --git a/arch/arm/mach-h720x/Kconfig b/arch/arm/mach-h720x/Kconfig index 9b6982e..abf356c 100644 --- a/arch/arm/mach-h720x/Kconfig +++ b/arch/arm/mach-h720x/Kconfig @@ -6,12 +6,14 @@ config ARCH_H7201 bool "gms30c7201" depends on ARCH_H720X select CPU_H7201 + select ZONE_DMA help Say Y here if you are using the Hynix GMS30C7201 Reference Board config ARCH_H7202 bool "hms30c7202" select CPU_H7202 + select ZONE_DMA depends on ARCH_H720X help Say Y here if you are using the Hynix HMS30C7202 Reference Board diff --git a/arch/arm/mach-ixp4xx/common.c b/arch/arm/mach-ixp4xx/common.c index 74ed81a..0777257 100644 --- a/arch/arm/mach-ixp4xx/common.c +++ b/arch/arm/mach-ixp4xx/common.c @@ -419,14 +419,20 @@ static void notrace ixp4xx_update_sched_clock(void) /* * clocksource */ + +static cycle_t ixp4xx_clocksource_read(struct clocksource *c) +{ + return *IXP4XX_OSTS; +} + unsigned long ixp4xx_timer_freq = IXP4XX_TIMER_FREQ; EXPORT_SYMBOL(ixp4xx_timer_freq); static void __init ixp4xx_clocksource_init(void) { init_sched_clock(&cd, ixp4xx_update_sched_clock, 32, ixp4xx_timer_freq); - clocksource_mmio_init(&IXP4XX_OSTS, "OSTS", ixp4xx_timer_freq, 200, 32, - clocksource_mmio_readl_up); + clocksource_mmio_init(NULL, "OSTS", ixp4xx_timer_freq, 200, 32, + ixp4xx_clocksource_read); } /* diff --git a/arch/arm/mach-mmp/brownstone.c b/arch/arm/mach-mmp/brownstone.c index 7bb78fd..c79162a 100644 --- a/arch/arm/mach-mmp/brownstone.c +++ b/arch/arm/mach-mmp/brownstone.c @@ -177,9 +177,16 @@ static struct i2c_board_info brownstone_twsi1_info[] = { }; static struct sdhci_pxa_platdata mmp2_sdh_platdata_mmc0 = { - .max_speed = 25000000, + .clk_delay_cycles = 0x1f, }; +static struct sdhci_pxa_platdata mmp2_sdh_platdata_mmc2 = { + .clk_delay_cycles = 0x1f, + .flags = PXA_FLAG_CARD_PERMANENT + | PXA_FLAG_SD_8_BIT_CAPABLE_SLOT, +}; + + static void __init brownstone_init(void) { mfp_config(ARRAY_AND_SIZE(brownstone_pin_config)); @@ -189,6 +196,7 @@ static void __init brownstone_init(void) mmp2_add_uart(3); mmp2_add_twsi(1, NULL, ARRAY_AND_SIZE(brownstone_twsi1_info)); mmp2_add_sdhost(0, &mmp2_sdh_platdata_mmc0); /* SD/MMC */ + mmp2_add_sdhost(2, &mmp2_sdh_platdata_mmc2); /* eMMC */ /* enable 5v regulator */ platform_device_register(&brownstone_v_5vp_device); diff --git a/arch/arm/mach-mmp/include/mach/mmp2.h b/arch/arm/mach-mmp/include/mach/mmp2.h index 2cbf6df..de7b888 100644 --- a/arch/arm/mach-mmp/include/mach/mmp2.h +++ b/arch/arm/mach-mmp/include/mach/mmp2.h @@ -1,7 +1,7 @@ #ifndef __ASM_MACH_MMP2_H #define __ASM_MACH_MMP2_H -#include <plat/sdhci.h> +#include <linux/platform_data/pxa_sdhci.h> struct sys_timer; diff --git a/arch/arm/mach-mmp/jasper.c b/arch/arm/mach-mmp/jasper.c index 24172a0..5d6421d 100644 --- a/arch/arm/mach-mmp/jasper.c +++ b/arch/arm/mach-mmp/jasper.c @@ -154,7 +154,7 @@ static struct i2c_board_info jasper_twsi1_info[] = { }; static struct sdhci_pxa_platdata mmp2_sdh_platdata_mmc0 = { - .max_speed = 25000000, + .clk_delay_cycles = 0x1f, }; static void __init jasper_init(void) diff --git a/arch/arm/mach-mmp/mmp2.c b/arch/arm/mach-mmp/mmp2.c index 8e6c3ac..079c188 100644 --- a/arch/arm/mach-mmp/mmp2.c +++ b/arch/arm/mach-mmp/mmp2.c @@ -168,10 +168,10 @@ static struct clk_lookup mmp2_clkregs[] = { INIT_CLKREG(&clk_twsi5, "pxa2xx-i2c.4", NULL), INIT_CLKREG(&clk_twsi6, "pxa2xx-i2c.5", NULL), INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), - INIT_CLKREG(&clk_sdh0, "sdhci-pxa.0", "PXA-SDHCLK"), - INIT_CLKREG(&clk_sdh1, "sdhci-pxa.1", "PXA-SDHCLK"), - INIT_CLKREG(&clk_sdh2, "sdhci-pxa.2", "PXA-SDHCLK"), - INIT_CLKREG(&clk_sdh3, "sdhci-pxa.3", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh0, "sdhci-pxav3.0", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh1, "sdhci-pxav3.1", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh2, "sdhci-pxav3.2", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh3, "sdhci-pxav3.3", "PXA-SDHCLK"), }; static int __init mmp2_init(void) @@ -222,8 +222,8 @@ MMP2_DEVICE(twsi4, "pxa2xx-i2c", 3, TWSI4, 0xd4033000, 0x70); MMP2_DEVICE(twsi5, "pxa2xx-i2c", 4, TWSI5, 0xd4033800, 0x70); MMP2_DEVICE(twsi6, "pxa2xx-i2c", 5, TWSI6, 0xd4034000, 0x70); MMP2_DEVICE(nand, "pxa3xx-nand", -1, NAND, 0xd4283000, 0x100, 28, 29); -MMP2_DEVICE(sdh0, "sdhci-pxa", 0, MMC, 0xd4280000, 0x120); -MMP2_DEVICE(sdh1, "sdhci-pxa", 1, MMC2, 0xd4280800, 0x120); -MMP2_DEVICE(sdh2, "sdhci-pxa", 2, MMC3, 0xd4281000, 0x120); -MMP2_DEVICE(sdh3, "sdhci-pxa", 3, MMC4, 0xd4281800, 0x120); +MMP2_DEVICE(sdh0, "sdhci-pxav3", 0, MMC, 0xd4280000, 0x120); +MMP2_DEVICE(sdh1, "sdhci-pxav3", 1, MMC2, 0xd4280800, 0x120); +MMP2_DEVICE(sdh2, "sdhci-pxav3", 2, MMC3, 0xd4281000, 0x120); +MMP2_DEVICE(sdh3, "sdhci-pxav3", 3, MMC4, 0xd4281800, 0x120); diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c index 72b4e76..ab9f999 100644 --- a/arch/arm/mach-mmp/pxa168.c +++ b/arch/arm/mach-mmp/pxa168.c @@ -79,7 +79,7 @@ static APBC_CLK(ssp4, PXA168_SSP4, 4, 0); static APBC_CLK(ssp5, PXA168_SSP5, 4, 0); static APBC_CLK(keypad, PXA168_KPC, 0, 32000); -static APMU_CLK(nand, NAND, 0x01db, 208000000); +static APMU_CLK(nand, NAND, 0x19b, 156000000); static APMU_CLK(lcd, LCD, 0x7f, 312000000); /* device and clock bindings */ diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c index 8f92ccd..1464607 100644 --- a/arch/arm/mach-mmp/pxa910.c +++ b/arch/arm/mach-mmp/pxa910.c @@ -110,7 +110,7 @@ static APBC_CLK(pwm2, PXA910_PWM2, 1, 13000000); static APBC_CLK(pwm3, PXA910_PWM3, 1, 13000000); static APBC_CLK(pwm4, PXA910_PWM4, 1, 13000000); -static APMU_CLK(nand, NAND, 0x01db, 208000000); +static APMU_CLK(nand, NAND, 0x19b, 156000000); static APMU_CLK(u2o, USB, 0x1b, 480000000); /* device and clock bindings */ diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index de88c92..f49ce85 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -215,7 +215,7 @@ static struct omap_kp_platform_data ams_delta_kp_data __initdata = { .delay = 9, }; -static struct platform_device ams_delta_kp_device __initdata = { +static struct platform_device ams_delta_kp_device = { .name = "omap-keypad", .id = -1, .dev = { @@ -225,12 +225,12 @@ static struct platform_device ams_delta_kp_device __initdata = { .resource = ams_delta_kp_resources, }; -static struct platform_device ams_delta_lcd_device __initdata = { +static struct platform_device ams_delta_lcd_device = { .name = "lcd_ams_delta", .id = -1, }; -static struct platform_device ams_delta_led_device __initdata = { +static struct platform_device ams_delta_led_device = { .name = "ams-delta-led", .id = -1 }; @@ -267,7 +267,7 @@ static struct soc_camera_link ams_delta_iclink = { .power = ams_delta_camera_power, }; -static struct platform_device ams_delta_camera_device __initdata = { +static struct platform_device ams_delta_camera_device = { .name = "soc-camera-pdrv", .id = 0, .dev = { diff --git a/arch/arm/mach-omap1/gpio15xx.c b/arch/arm/mach-omap1/gpio15xx.c index 04c4b04..364137c 100644 --- a/arch/arm/mach-omap1/gpio15xx.c +++ b/arch/arm/mach-omap1/gpio15xx.c @@ -41,7 +41,7 @@ static struct __initdata omap_gpio_platform_data omap15xx_mpu_gpio_config = { .bank_stride = 1, }; -static struct __initdata platform_device omap15xx_mpu_gpio = { +static struct platform_device omap15xx_mpu_gpio = { .name = "omap_gpio", .id = 0, .dev = { @@ -70,7 +70,7 @@ static struct __initdata omap_gpio_platform_data omap15xx_gpio_config = { .bank_width = 16, }; -static struct __initdata platform_device omap15xx_gpio = { +static struct platform_device omap15xx_gpio = { .name = "omap_gpio", .id = 1, .dev = { diff --git a/arch/arm/mach-omap1/gpio16xx.c b/arch/arm/mach-omap1/gpio16xx.c index 5dd0d4c..293a246 100644 --- a/arch/arm/mach-omap1/gpio16xx.c +++ b/arch/arm/mach-omap1/gpio16xx.c @@ -44,7 +44,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_mpu_gpio_config = { .bank_stride = 1, }; -static struct __initdata platform_device omap16xx_mpu_gpio = { +static struct platform_device omap16xx_mpu_gpio = { .name = "omap_gpio", .id = 0, .dev = { @@ -73,7 +73,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio1_config = { .bank_width = 16, }; -static struct __initdata platform_device omap16xx_gpio1 = { +static struct platform_device omap16xx_gpio1 = { .name = "omap_gpio", .id = 1, .dev = { @@ -102,7 +102,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio2_config = { .bank_width = 16, }; -static struct __initdata platform_device omap16xx_gpio2 = { +static struct platform_device omap16xx_gpio2 = { .name = "omap_gpio", .id = 2, .dev = { @@ -131,7 +131,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio3_config = { .bank_width = 16, }; -static struct __initdata platform_device omap16xx_gpio3 = { +static struct platform_device omap16xx_gpio3 = { .name = "omap_gpio", .id = 3, .dev = { @@ -160,7 +160,7 @@ static struct __initdata omap_gpio_platform_data omap16xx_gpio4_config = { .bank_width = 16, }; -static struct __initdata platform_device omap16xx_gpio4 = { +static struct platform_device omap16xx_gpio4 = { .name = "omap_gpio", .id = 4, .dev = { diff --git a/arch/arm/mach-omap1/gpio7xx.c b/arch/arm/mach-omap1/gpio7xx.c index 1204c8b..c6ad248 100644 --- a/arch/arm/mach-omap1/gpio7xx.c +++ b/arch/arm/mach-omap1/gpio7xx.c @@ -46,7 +46,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_mpu_gpio_config = { .bank_stride = 2, }; -static struct __initdata platform_device omap7xx_mpu_gpio = { +static struct platform_device omap7xx_mpu_gpio = { .name = "omap_gpio", .id = 0, .dev = { @@ -75,7 +75,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio1_config = { .bank_width = 32, }; -static struct __initdata platform_device omap7xx_gpio1 = { +static struct platform_device omap7xx_gpio1 = { .name = "omap_gpio", .id = 1, .dev = { @@ -104,7 +104,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio2_config = { .bank_width = 32, }; -static struct __initdata platform_device omap7xx_gpio2 = { +static struct platform_device omap7xx_gpio2 = { .name = "omap_gpio", .id = 2, .dev = { @@ -133,7 +133,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio3_config = { .bank_width = 32, }; -static struct __initdata platform_device omap7xx_gpio3 = { +static struct platform_device omap7xx_gpio3 = { .name = "omap_gpio", .id = 3, .dev = { @@ -162,7 +162,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio4_config = { .bank_width = 32, }; -static struct __initdata platform_device omap7xx_gpio4 = { +static struct platform_device omap7xx_gpio4 = { .name = "omap_gpio", .id = 4, .dev = { @@ -191,7 +191,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio5_config = { .bank_width = 32, }; -static struct __initdata platform_device omap7xx_gpio5 = { +static struct platform_device omap7xx_gpio5 = { .name = "omap_gpio", .id = 5, .dev = { @@ -220,7 +220,7 @@ static struct __initdata omap_gpio_platform_data omap7xx_gpio6_config = { .bank_width = 32, }; -static struct __initdata platform_device omap7xx_gpio6 = { +static struct platform_device omap7xx_gpio6 = { .name = "omap_gpio", .id = 6, .dev = { diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index 9903667..88bd6f7 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -558,7 +558,7 @@ static struct radio_si4713_platform_data rx51_si4713_data __initdata_or_module = .subdev_board_info = &rx51_si4713_board_info, }; -static struct platform_device rx51_si4713_dev __initdata_or_module = { +static struct platform_device rx51_si4713_dev = { .name = "radio-si4713", .id = -1, .dev = { diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c index 87ae312..b27544b 100644 --- a/arch/arm/mach-pxa/mfp-pxa2xx.c +++ b/arch/arm/mach-pxa/mfp-pxa2xx.c @@ -347,9 +347,9 @@ static int pxa2xx_mfp_suspend(void) if ((gpio_desc[i].config & MFP_LPM_KEEP_OUTPUT) && (GPDR(i) & GPIO_bit(i))) { if (GPLR(i) & GPIO_bit(i)) - PGSR(i) |= GPIO_bit(i); + PGSR(gpio_to_bank(i)) |= GPIO_bit(i); else - PGSR(i) &= ~GPIO_bit(i); + PGSR(gpio_to_bank(i)) &= ~GPIO_bit(i); } } diff --git a/arch/arm/mach-pxa/raumfeld.c b/arch/arm/mach-pxa/raumfeld.c index d130f77..2f37d43 100644 --- a/arch/arm/mach-pxa/raumfeld.c +++ b/arch/arm/mach-pxa/raumfeld.c @@ -573,10 +573,10 @@ static struct pxafb_mode_info sharp_lq043t3dx02_mode = { .xres = 480, .yres = 272, .bpp = 16, - .hsync_len = 4, + .hsync_len = 41, .left_margin = 2, .right_margin = 1, - .vsync_len = 1, + .vsync_len = 10, .upper_margin = 3, .lower_margin = 1, .sync = 0, @@ -596,29 +596,31 @@ static void __init raumfeld_lcd_init(void) { int ret; - pxa_set_fb_info(NULL, &raumfeld_sharp_lcd_info); - - /* Earlier devices had the backlight regulator controlled - * via PWM, later versions use another controller for that */ - if ((system_rev & 0xff) < 2) { - mfp_cfg_t raumfeld_pwm_pin_config = GPIO17_PWM0_OUT; - pxa3xx_mfp_config(&raumfeld_pwm_pin_config, 1); - platform_device_register(&raumfeld_pwm_backlight_device); - } else - platform_device_register(&raumfeld_lt3593_device); - ret = gpio_request(GPIO_TFT_VA_EN, "display VA enable"); if (ret < 0) pr_warning("Unable to request GPIO_TFT_VA_EN\n"); else gpio_direction_output(GPIO_TFT_VA_EN, 1); + msleep(100); + ret = gpio_request(GPIO_DISPLAY_ENABLE, "display enable"); if (ret < 0) pr_warning("Unable to request GPIO_DISPLAY_ENABLE\n"); else gpio_direction_output(GPIO_DISPLAY_ENABLE, 1); + /* Hardware revision 2 has the backlight regulator controlled + * by an LT3593, earlier and later devices use PWM for that. */ + if ((system_rev & 0xff) == 2) { + platform_device_register(&raumfeld_lt3593_device); + } else { + mfp_cfg_t raumfeld_pwm_pin_config = GPIO17_PWM0_OUT; + pxa3xx_mfp_config(&raumfeld_pwm_pin_config, 1); + platform_device_register(&raumfeld_pwm_backlight_device); + } + + pxa_set_fb_info(NULL, &raumfeld_sharp_lcd_info); platform_device_register(&pxa3xx_device_gcu); } @@ -657,10 +659,10 @@ static struct lis3lv02d_platform_data lis3_pdata = { #define SPI_AK4104 \ { \ - .modalias = "ak4104", \ - .max_speed_hz = 10000, \ - .bus_num = 0, \ - .chip_select = 0, \ + .modalias = "ak4104-codec", \ + .max_speed_hz = 10000, \ + .bus_num = 0, \ + .chip_select = 0, \ .controller_data = (void *) GPIO_SPDIF_CS, \ } diff --git a/arch/arm/mach-s3c2440/mach-mini2440.c b/arch/arm/mach-s3c2440/mach-mini2440.c index dd3120d..fc2dc0b 100644 --- a/arch/arm/mach-s3c2440/mach-mini2440.c +++ b/arch/arm/mach-s3c2440/mach-mini2440.c @@ -552,7 +552,7 @@ struct mini2440_features_t { struct platform_device *optional[8]; }; -static void mini2440_parse_features( +static void __init mini2440_parse_features( struct mini2440_features_t * features, const char * features_str ) { diff --git a/arch/arm/mach-s3c64xx/dev-spi.c b/arch/arm/mach-s3c64xx/dev-spi.c index 82db072..5e6b420 100644 --- a/arch/arm/mach-s3c64xx/dev-spi.c +++ b/arch/arm/mach-s3c64xx/dev-spi.c @@ -88,6 +88,7 @@ static struct s3c64xx_spi_info s3c64xx_spi0_pdata = { .cfg_gpio = s3c64xx_spi_cfg_gpio, .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 13, + .tx_st_done = 21, }; static u64 spi_dmamask = DMA_BIT_MASK(32); @@ -132,6 +133,7 @@ static struct s3c64xx_spi_info s3c64xx_spi1_pdata = { .cfg_gpio = s3c64xx_spi_cfg_gpio, .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 13, + .tx_st_done = 21, }; struct platform_device s3c64xx_device_spi1 = { diff --git a/arch/arm/mach-s3c64xx/dma.c b/arch/arm/mach-s3c64xx/dma.c index b197171..204bfaf 100644 --- a/arch/arm/mach-s3c64xx/dma.c +++ b/arch/arm/mach-s3c64xx/dma.c @@ -113,7 +113,7 @@ found: return chan; } -int s3c2410_dma_config(unsigned int channel, int xferunit) +int s3c2410_dma_config(enum dma_ch channel, int xferunit) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -297,7 +297,7 @@ static int s3c64xx_dma_flush(struct s3c2410_dma_chan *chan) return 0; } -int s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op) +int s3c2410_dma_ctrl(enum dma_ch channel, enum s3c2410_chan_op op) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -331,7 +331,7 @@ EXPORT_SYMBOL(s3c2410_dma_ctrl); * */ -int s3c2410_dma_enqueue(unsigned int channel, void *id, +int s3c2410_dma_enqueue(enum dma_ch channel, void *id, dma_addr_t data, int size) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -415,7 +415,7 @@ err_buff: EXPORT_SYMBOL(s3c2410_dma_enqueue); -int s3c2410_dma_devconfig(unsigned int channel, +int s3c2410_dma_devconfig(enum dma_ch channel, enum s3c2410_dmasrc source, unsigned long devaddr) { @@ -463,7 +463,7 @@ int s3c2410_dma_devconfig(unsigned int channel, EXPORT_SYMBOL(s3c2410_dma_devconfig); -int s3c2410_dma_getposition(unsigned int channel, +int s3c2410_dma_getposition(enum dma_ch channel, dma_addr_t *src, dma_addr_t *dst) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -487,7 +487,7 @@ EXPORT_SYMBOL(s3c2410_dma_getposition); * get control of an dma channel */ -int s3c2410_dma_request(unsigned int channel, +int s3c2410_dma_request(enum dma_ch channel, struct s3c2410_dma_client *client, void *dev) { @@ -533,7 +533,7 @@ EXPORT_SYMBOL(s3c2410_dma_request); * allowed to go through. */ -int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *client) +int s3c2410_dma_free(enum dma_ch channel, struct s3c2410_dma_client *client) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); unsigned long flags; diff --git a/arch/arm/mach-s5p64x0/dev-spi.c b/arch/arm/mach-s5p64x0/dev-spi.c index e78ee18..ac825e8 100644 --- a/arch/arm/mach-s5p64x0/dev-spi.c +++ b/arch/arm/mach-s5p64x0/dev-spi.c @@ -112,12 +112,14 @@ static struct s3c64xx_spi_info s5p6440_spi0_pdata = { .cfg_gpio = s5p6440_spi_cfg_gpio, .fifo_lvl_mask = 0x1ff, .rx_lvl_offset = 15, + .tx_st_done = 25, }; static struct s3c64xx_spi_info s5p6450_spi0_pdata = { .cfg_gpio = s5p6450_spi_cfg_gpio, .fifo_lvl_mask = 0x1ff, .rx_lvl_offset = 15, + .tx_st_done = 25, }; static u64 spi_dmamask = DMA_BIT_MASK(32); @@ -160,12 +162,14 @@ static struct s3c64xx_spi_info s5p6440_spi1_pdata = { .cfg_gpio = s5p6440_spi_cfg_gpio, .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 15, + .tx_st_done = 25, }; static struct s3c64xx_spi_info s5p6450_spi1_pdata = { .cfg_gpio = s5p6450_spi_cfg_gpio, .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 15, + .tx_st_done = 25, }; struct platform_device s5p64x0_device_spi1 = { diff --git a/arch/arm/mach-s5pc100/dev-spi.c b/arch/arm/mach-s5pc100/dev-spi.c index 57b1979..e5d6c4d 100644 --- a/arch/arm/mach-s5pc100/dev-spi.c +++ b/arch/arm/mach-s5pc100/dev-spi.c @@ -15,6 +15,7 @@ #include <mach/dma.h> #include <mach/map.h> #include <mach/spi-clocks.h> +#include <mach/irqs.h> #include <plat/s3c64xx-spi.h> #include <plat/gpio-cfg.h> @@ -90,6 +91,7 @@ static struct s3c64xx_spi_info s5pc100_spi0_pdata = { .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 13, .high_speed = 1, + .tx_st_done = 21, }; static u64 spi_dmamask = DMA_BIT_MASK(32); @@ -134,6 +136,7 @@ static struct s3c64xx_spi_info s5pc100_spi1_pdata = { .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 13, .high_speed = 1, + .tx_st_done = 21, }; struct platform_device s5pc100_device_spi1 = { @@ -176,6 +179,7 @@ static struct s3c64xx_spi_info s5pc100_spi2_pdata = { .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 13, .high_speed = 1, + .tx_st_done = 21, }; struct platform_device s5pc100_device_spi2 = { diff --git a/arch/arm/mach-s5pv210/dev-spi.c b/arch/arm/mach-s5pv210/dev-spi.c index e3249a4..eaf9a7b 100644 --- a/arch/arm/mach-s5pv210/dev-spi.c +++ b/arch/arm/mach-s5pv210/dev-spi.c @@ -85,6 +85,7 @@ static struct s3c64xx_spi_info s5pv210_spi0_pdata = { .fifo_lvl_mask = 0x1ff, .rx_lvl_offset = 15, .high_speed = 1, + .tx_st_done = 25, }; static u64 spi_dmamask = DMA_BIT_MASK(32); @@ -129,6 +130,7 @@ static struct s3c64xx_spi_info s5pv210_spi1_pdata = { .fifo_lvl_mask = 0x7f, .rx_lvl_offset = 15, .high_speed = 1, + .tx_st_done = 25, }; struct platform_device s5pv210_device_spi1 = { diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c index 1e2aba2..ce5c251 100644 --- a/arch/arm/mach-shmobile/board-ag5evm.c +++ b/arch/arm/mach-shmobile/board-ag5evm.c @@ -381,7 +381,7 @@ void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state) gpio_set_value(GPIO_PORT114, state); } -static struct sh_mobile_sdhi_info sh_sdhi1_platdata = { +static struct sh_mobile_sdhi_info sh_sdhi1_info = { .tmio_flags = TMIO_MMC_WRPROTECT_DISABLE, .tmio_caps = MMC_CAP_NONREMOVABLE | MMC_CAP_SDIO_IRQ, .tmio_ocr_mask = MMC_VDD_32_33 | MMC_VDD_33_34, @@ -413,7 +413,7 @@ static struct platform_device sdhi1_device = { .name = "sh_mobile_sdhi", .id = 1, .dev = { - .platform_data = &sh_sdhi1_platdata, + .platform_data = &sh_sdhi1_info, }, .num_resources = ARRAY_SIZE(sdhi1_resources), .resource = sdhi1_resources, diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c index f6b687f..803bc6e 100644 --- a/arch/arm/mach-shmobile/board-ap4evb.c +++ b/arch/arm/mach-shmobile/board-ap4evb.c @@ -913,7 +913,7 @@ static struct i2c_board_info imx074_info = { I2C_BOARD_INFO("imx074", 0x1a), }; -struct soc_camera_link imx074_link = { +static struct soc_camera_link imx074_link = { .bus_id = 0, .board_info = &imx074_info, .i2c_adapter_id = 0, diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c index 7e1d375..3802f2a 100644 --- a/arch/arm/mach-shmobile/board-mackerel.c +++ b/arch/arm/mach-shmobile/board-mackerel.c @@ -1287,9 +1287,9 @@ static struct platform_device *mackerel_devices[] __initdata = { &nor_flash_device, &smc911x_device, &lcdc_device, - &usbhs0_device, &usb1_host_device, &usbhs1_device, + &usbhs0_device, &leds_device, &fsi_device, &fsi_ak4643_device, diff --git a/arch/arm/mach-ux500/board-mop500-pins.c b/arch/arm/mach-ux500/board-mop500-pins.c index fd4cf1c..70cdbd6 100644 --- a/arch/arm/mach-ux500/board-mop500-pins.c +++ b/arch/arm/mach-ux500/board-mop500-pins.c @@ -110,10 +110,18 @@ static pin_cfg_t mop500_pins_common[] = { GPIO168_KP_O0, /* UART */ - GPIO0_U0_CTSn | PIN_INPUT_PULLUP, - GPIO1_U0_RTSn | PIN_OUTPUT_HIGH, - GPIO2_U0_RXD | PIN_INPUT_PULLUP, - GPIO3_U0_TXD | PIN_OUTPUT_HIGH, + /* uart-0 pins gpio configuration should be + * kept intact to prevent glitch in tx line + * when tty dev is opened. Later these pins + * are configured to uart mop500_pins_uart0 + * + * It will be replaced with uart configuration + * once the issue is solved. + */ + GPIO0_GPIO | PIN_INPUT_PULLUP, + GPIO1_GPIO | PIN_OUTPUT_HIGH, + GPIO2_GPIO | PIN_INPUT_PULLUP, + GPIO3_GPIO | PIN_OUTPUT_HIGH, GPIO29_U2_RXD | PIN_INPUT_PULLUP, GPIO30_U2_TXD | PIN_OUTPUT_HIGH, diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index bb26f40..2a08c07 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -27,18 +27,21 @@ #include <linux/leds-lp5521.h> #include <linux/input.h> #include <linux/gpio_keys.h> +#include <linux/delay.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> #include <plat/i2c.h> #include <plat/ste_dma40.h> +#include <plat/pincfg.h> #include <mach/hardware.h> #include <mach/setup.h> #include <mach/devices.h> #include <mach/irqs.h> +#include "pins-db8500.h" #include "ste-dma40-db8500.h" #include "devices-db8500.h" #include "board-mop500.h" @@ -393,12 +396,63 @@ static struct stedma40_chan_cfg uart2_dma_cfg_tx = { }; #endif + +static pin_cfg_t mop500_pins_uart0[] = { + GPIO0_U0_CTSn | PIN_INPUT_PULLUP, + GPIO1_U0_RTSn | PIN_OUTPUT_HIGH, + GPIO2_U0_RXD | PIN_INPUT_PULLUP, + GPIO3_U0_TXD | PIN_OUTPUT_HIGH, +}; + +#define PRCC_K_SOFTRST_SET 0x18 +#define PRCC_K_SOFTRST_CLEAR 0x1C +static void ux500_uart0_reset(void) +{ + void __iomem *prcc_rst_set, *prcc_rst_clr; + + prcc_rst_set = (void __iomem *)IO_ADDRESS(U8500_CLKRST1_BASE + + PRCC_K_SOFTRST_SET); + prcc_rst_clr = (void __iomem *)IO_ADDRESS(U8500_CLKRST1_BASE + + PRCC_K_SOFTRST_CLEAR); + + /* Activate soft reset PRCC_K_SOFTRST_CLEAR */ + writel((readl(prcc_rst_clr) | 0x1), prcc_rst_clr); + udelay(1); + + /* Release soft reset PRCC_K_SOFTRST_SET */ + writel((readl(prcc_rst_set) | 0x1), prcc_rst_set); + udelay(1); +} + +static void ux500_uart0_init(void) +{ + int ret; + + ret = nmk_config_pins(mop500_pins_uart0, + ARRAY_SIZE(mop500_pins_uart0)); + if (ret < 0) + pr_err("pl011: uart pins_enable failed\n"); +} + +static void ux500_uart0_exit(void) +{ + int ret; + + ret = nmk_config_pins_sleep(mop500_pins_uart0, + ARRAY_SIZE(mop500_pins_uart0)); + if (ret < 0) + pr_err("pl011: uart pins_disable failed\n"); +} + static struct amba_pl011_data uart0_plat = { #ifdef CONFIG_STE_DMA40 .dma_filter = stedma40_filter, .dma_rx_param = &uart0_dma_cfg_rx, .dma_tx_param = &uart0_dma_cfg_tx, #endif + .init = ux500_uart0_init, + .exit = ux500_uart0_exit, + .reset = ux500_uart0_reset, }; static struct amba_pl011_data uart1_plat = { diff --git a/arch/arm/mach-vt8500/irq.c b/arch/arm/mach-vt8500/irq.c index 245140c..642de04 100644 --- a/arch/arm/mach-vt8500/irq.c +++ b/arch/arm/mach-vt8500/irq.c @@ -39,9 +39,10 @@ static void __iomem *ic_regbase; static void __iomem *sic_regbase; -static void vt8500_irq_mask(unsigned int irq) +static void vt8500_irq_mask(struct irq_data *d) { void __iomem *base = ic_regbase; + unsigned irq = d->irq; u8 edge; if (irq >= 64) { @@ -64,9 +65,10 @@ static void vt8500_irq_mask(unsigned int irq) } } -static void vt8500_irq_unmask(unsigned int irq) +static void vt8500_irq_unmask(struct irq_data *d) { void __iomem *base = ic_regbase; + unsigned irq = d->irq; u8 dctr; if (irq >= 64) { @@ -78,10 +80,11 @@ static void vt8500_irq_unmask(unsigned int irq) writeb(dctr, base + VT8500_IC_DCTR + irq); } -static int vt8500_irq_set_type(unsigned int irq, unsigned int flow_type) +static int vt8500_irq_set_type(struct irq_data *d, unsigned int flow_type) { void __iomem *base = ic_regbase; - unsigned int orig_irq = irq; + unsigned irq = d->irq; + unsigned orig_irq = irq; u8 dctr; if (irq >= 64) { @@ -114,11 +117,11 @@ static int vt8500_irq_set_type(unsigned int irq, unsigned int flow_type) } static struct irq_chip vt8500_irq_chip = { - .name = "vt8500", - .ack = vt8500_irq_mask, - .mask = vt8500_irq_mask, - .unmask = vt8500_irq_unmask, - .set_type = vt8500_irq_set_type, + .name = "vt8500", + .irq_ack = vt8500_irq_mask, + .irq_mask = vt8500_irq_mask, + .irq_unmask = vt8500_irq_unmask, + .irq_set_type = vt8500_irq_set_type, }; void __init vt8500_init_irq(void) diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index ef59099..44c0867 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -120,17 +120,22 @@ static void l2x0_cache_sync(void) spin_unlock_irqrestore(&l2x0_lock, flags); } -static void l2x0_flush_all(void) +static void __l2x0_flush_all(void) { - unsigned long flags; - - /* clean all ways */ - spin_lock_irqsave(&l2x0_lock, flags); debug_writel(0x03); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY); cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask); cache_sync(); debug_writel(0x00); +} + +static void l2x0_flush_all(void) +{ + unsigned long flags; + + /* clean all ways */ + spin_lock_irqsave(&l2x0_lock, flags); + __l2x0_flush_all(); spin_unlock_irqrestore(&l2x0_lock, flags); } @@ -266,7 +271,9 @@ static void l2x0_disable(void) unsigned long flags; spin_lock_irqsave(&l2x0_lock, flags); - writel(0, l2x0_base + L2X0_CTRL); + __l2x0_flush_all(); + writel_relaxed(0, l2x0_base + L2X0_CTRL); + dsb(); spin_unlock_irqrestore(&l2x0_lock, flags); } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 9d9e736..594d677 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -759,7 +759,7 @@ early_param("vmalloc", early_vmalloc); static phys_addr_t lowmem_limit __initdata = 0; -static void __init sanity_check_meminfo(void) +void __init sanity_check_meminfo(void) { int i, j, highmem = 0; @@ -1032,8 +1032,9 @@ void __init paging_init(struct machine_desc *mdesc) { void *zero_page; + memblock_set_current_limit(lowmem_limit); + build_mem_type_table(); - sanity_check_meminfo(); prepare_page_table(); map_lowmem(); devicemaps_init(mdesc); diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 687d023..941a98c 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -27,6 +27,10 @@ void __init arm_mm_memblock_reserve(void) memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE); } +void __init sanity_check_meminfo(void) +{ +} + /* * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 3c38678..089c0b5 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -210,19 +210,21 @@ cpu_v7_name: /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */ .globl cpu_v7_suspend_size -.equ cpu_v7_suspend_size, 4 * 8 +.equ cpu_v7_suspend_size, 4 * 9 #ifdef CONFIG_PM_SLEEP ENTRY(cpu_v7_do_suspend) stmfd sp!, {r4 - r11, lr} mrc p15, 0, r4, c13, c0, 0 @ FCSE/PID mrc p15, 0, r5, c13, c0, 1 @ Context ID + mrc p15, 0, r6, c13, c0, 3 @ User r/o thread ID + stmia r0!, {r4 - r6} mrc p15, 0, r6, c3, c0, 0 @ Domain ID mrc p15, 0, r7, c2, c0, 0 @ TTB 0 mrc p15, 0, r8, c2, c0, 1 @ TTB 1 mrc p15, 0, r9, c1, c0, 0 @ Control register mrc p15, 0, r10, c1, c0, 1 @ Auxiliary control register mrc p15, 0, r11, c1, c0, 2 @ Co-processor access control - stmia r0, {r4 - r11} + stmia r0, {r6 - r11} ldmfd sp!, {r4 - r11, pc} ENDPROC(cpu_v7_do_suspend) @@ -230,9 +232,11 @@ ENTRY(cpu_v7_do_resume) mov ip, #0 mcr p15, 0, ip, c8, c7, 0 @ invalidate TLBs mcr p15, 0, ip, c7, c5, 0 @ invalidate I cache - ldmia r0, {r4 - r11} + ldmia r0!, {r4 - r6} mcr p15, 0, r4, c13, c0, 0 @ FCSE/PID mcr p15, 0, r5, c13, c0, 1 @ Context ID + mcr p15, 0, r6, c13, c0, 3 @ User r/o thread ID + ldmia r0, {r6 - r11} mcr p15, 0, r6, c3, c0, 0 @ Domain ID mcr p15, 0, r7, c2, c0, 0 @ TTB 0 mcr p15, 0, r8, c2, c0, 1 @ TTB 1 @@ -418,9 +422,9 @@ ENTRY(v7_processor_functions) .word cpu_v7_dcache_clean_area .word cpu_v7_switch_mm .word cpu_v7_set_pte_ext - .word 0 - .word 0 - .word 0 + .word cpu_v7_suspend_size + .word cpu_v7_do_suspend + .word cpu_v7_do_resume .size v7_processor_functions, . - v7_processor_functions .section ".rodata" diff --git a/arch/arm/plat-iop/cp6.c b/arch/arm/plat-iop/cp6.c index 9612a87..bab73e2 100644 --- a/arch/arm/plat-iop/cp6.c +++ b/arch/arm/plat-iop/cp6.c @@ -18,6 +18,7 @@ */ #include <linux/init.h> #include <asm/traps.h> +#include <asm/ptrace.h> static int cp6_trap(struct pt_regs *regs, unsigned int instr) { diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c index 5b4fffa..41ab97e 100644 --- a/arch/arm/plat-orion/gpio.c +++ b/arch/arm/plat-orion/gpio.c @@ -432,7 +432,7 @@ void __init orion_gpio_init(int gpio_base, int ngpio, ct->regs.mask = ochip->mask_offset + GPIO_EDGE_MASK_OFF; ct->regs.ack = GPIO_EDGE_CAUSE_OFF; ct->type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING; - ct->chip.irq_ack = irq_gc_ack; + ct->chip.irq_ack = irq_gc_ack_clr_bit; ct->chip.irq_mask = irq_gc_mask_clr_bit; ct->chip.irq_unmask = irq_gc_mask_set_bit; ct->chip.irq_set_type = gpio_irq_set_type; diff --git a/arch/arm/plat-pxa/gpio.c b/arch/arm/plat-pxa/gpio.c index 48ebb94..a11dc36 100644 --- a/arch/arm/plat-pxa/gpio.c +++ b/arch/arm/plat-pxa/gpio.c @@ -50,7 +50,7 @@ static inline void __iomem *gpio_chip_base(struct gpio_chip *c) return container_of(c, struct pxa_gpio_chip, chip)->regbase; } -static inline struct pxa_gpio_chip *gpio_to_chip(unsigned gpio) +static inline struct pxa_gpio_chip *gpio_to_pxachip(unsigned gpio) { return &pxa_gpio_chips[gpio_to_bank(gpio)]; } @@ -161,7 +161,7 @@ static int pxa_gpio_irq_type(struct irq_data *d, unsigned int type) int gpio = irq_to_gpio(d->irq); unsigned long gpdr, mask = GPIO_bit(gpio); - c = gpio_to_chip(gpio); + c = gpio_to_pxachip(gpio); if (type == IRQ_TYPE_PROBE) { /* Don't mess with enabled GPIOs using preconfigured edges or @@ -230,7 +230,7 @@ static void pxa_gpio_demux_handler(unsigned int irq, struct irq_desc *desc) static void pxa_ack_muxed_gpio(struct irq_data *d) { int gpio = irq_to_gpio(d->irq); - struct pxa_gpio_chip *c = gpio_to_chip(gpio); + struct pxa_gpio_chip *c = gpio_to_pxachip(gpio); __raw_writel(GPIO_bit(gpio), c->regbase + GEDR_OFFSET); } @@ -238,7 +238,7 @@ static void pxa_ack_muxed_gpio(struct irq_data *d) static void pxa_mask_muxed_gpio(struct irq_data *d) { int gpio = irq_to_gpio(d->irq); - struct pxa_gpio_chip *c = gpio_to_chip(gpio); + struct pxa_gpio_chip *c = gpio_to_pxachip(gpio); uint32_t grer, gfer; c->irq_mask &= ~GPIO_bit(gpio); @@ -252,7 +252,7 @@ static void pxa_mask_muxed_gpio(struct irq_data *d) static void pxa_unmask_muxed_gpio(struct irq_data *d) { int gpio = irq_to_gpio(d->irq); - struct pxa_gpio_chip *c = gpio_to_chip(gpio); + struct pxa_gpio_chip *c = gpio_to_pxachip(gpio); c->irq_mask |= GPIO_bit(gpio); update_edge_detect(c); diff --git a/arch/arm/plat-pxa/include/plat/sdhci.h b/arch/arm/plat-pxa/include/plat/sdhci.h deleted file mode 100644 index 1ab332e..0000000 --- a/arch/arm/plat-pxa/include/plat/sdhci.h +++ /dev/null @@ -1,35 +0,0 @@ -/* linux/arch/arm/plat-pxa/include/plat/sdhci.h - * - * Copyright 2010 Marvell - * Zhangfei Gao <zhangfei.gao@marvell.com> - * - * PXA Platform - SDHCI platform data definitions - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#ifndef __PLAT_PXA_SDHCI_H -#define __PLAT_PXA_SDHCI_H - -/* pxa specific flag */ -/* Require clock free running */ -#define PXA_FLAG_DISABLE_CLOCK_GATING (1<<0) - -/* Board design supports 8-bit data on SD/SDIO BUS */ -#define PXA_FLAG_SD_8_BIT_CAPABLE_SLOT (1<<2) - -/* - * struct pxa_sdhci_platdata() - Platform device data for PXA SDHCI - * @max_speed: the maximum speed supported - * @quirks: quirks of specific device - * @flags: flags for platform requirement - */ -struct sdhci_pxa_platdata { - unsigned int max_speed; - unsigned int quirks; - unsigned int flags; -}; - -#endif /* __PLAT_PXA_SDHCI_H */ diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c index 2abf966..539bd0e 100644 --- a/arch/arm/plat-s3c24xx/dma.c +++ b/arch/arm/plat-s3c24xx/dma.c @@ -712,7 +712,7 @@ static struct s3c2410_dma_chan *s3c2410_dma_map_channel(int channel); * get control of an dma channel */ -int s3c2410_dma_request(unsigned int channel, +int s3c2410_dma_request(enum dma_ch channel, struct s3c2410_dma_client *client, void *dev) { @@ -783,7 +783,7 @@ EXPORT_SYMBOL(s3c2410_dma_request); * allowed to go through. */ -int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *client) +int s3c2410_dma_free(enum dma_ch channel, struct s3c2410_dma_client *client) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); unsigned long flags; @@ -974,7 +974,7 @@ static int s3c2410_dma_started(struct s3c2410_dma_chan *chan) } int -s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op) +s3c2410_dma_ctrl(enum dma_ch channel, enum s3c2410_chan_op op) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -1021,23 +1021,19 @@ EXPORT_SYMBOL(s3c2410_dma_ctrl); * xfersize: size of unit in bytes (1,2,4) */ -int s3c2410_dma_config(unsigned int channel, +int s3c2410_dma_config(enum dma_ch channel, int xferunit) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); unsigned int dcon; - pr_debug("%s: chan=%d, xfer_unit=%d, dcon=%08x\n", - __func__, channel, xferunit, dcon); + pr_debug("%s: chan=%d, xfer_unit=%d\n", __func__, channel, xferunit); if (chan == NULL) return -EINVAL; - pr_debug("%s: Initial dcon is %08x\n", __func__, dcon); - dcon = chan->dcon & dma_sel.dcon_mask; - - pr_debug("%s: New dcon is %08x\n", __func__, dcon); + pr_debug("%s: dcon is %08x\n", __func__, dcon); switch (chan->req_ch) { case DMACH_I2S_IN: @@ -1104,7 +1100,7 @@ EXPORT_SYMBOL(s3c2410_dma_config); * devaddr: physical address of the source */ -int s3c2410_dma_devconfig(unsigned int channel, +int s3c2410_dma_devconfig(enum dma_ch channel, enum s3c2410_dmasrc source, unsigned long devaddr) { @@ -1177,7 +1173,7 @@ EXPORT_SYMBOL(s3c2410_dma_devconfig); * returns the current transfer points for the dma source and destination */ -int s3c2410_dma_getposition(unsigned int channel, dma_addr_t *src, dma_addr_t *dst) +int s3c2410_dma_getposition(enum dma_ch channel, dma_addr_t *src, dma_addr_t *dst) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -1235,7 +1231,7 @@ static void s3c2410_dma_resume_chan(struct s3c2410_dma_chan *cp) /* restore channel's hardware configuration */ if (!cp->in_use) - return 0; + return; printk(KERN_INFO "dma%d: restoring configuration\n", cp->number); @@ -1246,8 +1242,6 @@ static void s3c2410_dma_resume_chan(struct s3c2410_dma_chan *cp) if (cp->map != NULL) dma_sel.select(cp, cp->map); - - return 0; } static void s3c2410_dma_resume(void) diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c index 135abda..327ab9f 100644 --- a/arch/arm/plat-s5p/irq-gpioint.c +++ b/arch/arm/plat-s5p/irq-gpioint.c @@ -152,7 +152,7 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip) if (!gc) return -ENOMEM; ct = gc->chip_types; - ct->chip.irq_ack = irq_gc_ack; + ct->chip.irq_ack = irq_gc_ack_set_bit; ct->chip.irq_mask = irq_gc_mask_set_bit; ct->chip.irq_unmask = irq_gc_mask_clr_bit; ct->chip.irq_set_type = s5p_gpioint_set_type, diff --git a/arch/arm/plat-s5p/s5p-time.c b/arch/arm/plat-s5p/s5p-time.c index 899a8cc..612934c 100644 --- a/arch/arm/plat-s5p/s5p-time.c +++ b/arch/arm/plat-s5p/s5p-time.c @@ -370,11 +370,11 @@ static void __init s5p_clocksource_init(void) clock_rate = clk_get_rate(tin_source); - init_sched_clock(&cd, s5p_update_sched_clock, 32, clock_rate); - s5p_time_setup(timer_source.source_id, TCNT_MAX); s5p_time_start(timer_source.source_id, PERIODIC); + init_sched_clock(&cd, s5p_update_sched_clock, 32, clock_rate); + if (clocksource_register_hz(&time_clocksource, clock_rate)) panic("%s: can't register clocksource\n", time_clocksource.name); } diff --git a/arch/arm/plat-samsung/dma.c b/arch/arm/plat-samsung/dma.c index cb459dd..6143aa1 100644 --- a/arch/arm/plat-samsung/dma.c +++ b/arch/arm/plat-samsung/dma.c @@ -41,7 +41,7 @@ struct s3c2410_dma_chan *s3c_dma_lookup_channel(unsigned int channel) * irq? */ -int s3c2410_dma_set_opfn(unsigned int channel, s3c2410_dma_opfn_t rtn) +int s3c2410_dma_set_opfn(enum dma_ch channel, s3c2410_dma_opfn_t rtn) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -56,7 +56,7 @@ int s3c2410_dma_set_opfn(unsigned int channel, s3c2410_dma_opfn_t rtn) } EXPORT_SYMBOL(s3c2410_dma_set_opfn); -int s3c2410_dma_set_buffdone_fn(unsigned int channel, s3c2410_dma_cbfn_t rtn) +int s3c2410_dma_set_buffdone_fn(enum dma_ch channel, s3c2410_dma_cbfn_t rtn) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); @@ -71,7 +71,7 @@ int s3c2410_dma_set_buffdone_fn(unsigned int channel, s3c2410_dma_cbfn_t rtn) } EXPORT_SYMBOL(s3c2410_dma_set_buffdone_fn); -int s3c2410_dma_setflags(unsigned int channel, unsigned int flags) +int s3c2410_dma_setflags(enum dma_ch channel, unsigned int flags) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); diff --git a/arch/arm/plat-samsung/include/plat/devs.h b/arch/arm/plat-samsung/include/plat/devs.h index 4af108f..e3b31c2 100644 --- a/arch/arm/plat-samsung/include/plat/devs.h +++ b/arch/arm/plat-samsung/include/plat/devs.h @@ -12,6 +12,10 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#ifndef __PLAT_DEVS_H +#define __PLAT_DEVS_H __FILE__ + #include <linux/platform_device.h> struct s3c24xx_uart_resources { @@ -159,3 +163,5 @@ extern struct platform_device s3c_device_ac97; */ extern void *s3c_set_platdata(void *pd, size_t pdsize, struct platform_device *pdev); + +#endif /* __PLAT_DEVS_H */ diff --git a/arch/arm/plat-samsung/include/plat/dma.h b/arch/arm/plat-samsung/include/plat/dma.h index 2e8f8c6..8c273b7 100644 --- a/arch/arm/plat-samsung/include/plat/dma.h +++ b/arch/arm/plat-samsung/include/plat/dma.h @@ -42,6 +42,7 @@ struct s3c2410_dma_client { }; struct s3c2410_dma_chan; +enum dma_ch; /* s3c2410_dma_cbfn_t * @@ -62,7 +63,7 @@ typedef int (*s3c2410_dma_opfn_t)(struct s3c2410_dma_chan *, * request a dma channel exclusivley */ -extern int s3c2410_dma_request(unsigned int channel, +extern int s3c2410_dma_request(enum dma_ch channel, struct s3c2410_dma_client *, void *dev); @@ -71,14 +72,14 @@ extern int s3c2410_dma_request(unsigned int channel, * change the state of the dma channel */ -extern int s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op); +extern int s3c2410_dma_ctrl(enum dma_ch channel, enum s3c2410_chan_op op); /* s3c2410_dma_setflags * * set the channel's flags to a given state */ -extern int s3c2410_dma_setflags(unsigned int channel, +extern int s3c2410_dma_setflags(enum dma_ch channel, unsigned int flags); /* s3c2410_dma_free @@ -86,7 +87,7 @@ extern int s3c2410_dma_setflags(unsigned int channel, * free the dma channel (will also abort any outstanding operations) */ -extern int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *); +extern int s3c2410_dma_free(enum dma_ch channel, struct s3c2410_dma_client *); /* s3c2410_dma_enqueue * @@ -95,7 +96,7 @@ extern int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *); * drained before the buffer is given to the DMA system. */ -extern int s3c2410_dma_enqueue(unsigned int channel, void *id, +extern int s3c2410_dma_enqueue(enum dma_ch channel, void *id, dma_addr_t data, int size); /* s3c2410_dma_config @@ -103,14 +104,14 @@ extern int s3c2410_dma_enqueue(unsigned int channel, void *id, * configure the dma channel */ -extern int s3c2410_dma_config(unsigned int channel, int xferunit); +extern int s3c2410_dma_config(enum dma_ch channel, int xferunit); /* s3c2410_dma_devconfig * * configure the device we're talking to */ -extern int s3c2410_dma_devconfig(unsigned int channel, +extern int s3c2410_dma_devconfig(enum dma_ch channel, enum s3c2410_dmasrc source, unsigned long devaddr); /* s3c2410_dma_getposition @@ -118,10 +119,10 @@ extern int s3c2410_dma_devconfig(unsigned int channel, * get the position that the dma transfer is currently at */ -extern int s3c2410_dma_getposition(unsigned int channel, +extern int s3c2410_dma_getposition(enum dma_ch channel, dma_addr_t *src, dma_addr_t *dest); -extern int s3c2410_dma_set_opfn(unsigned int, s3c2410_dma_opfn_t rtn); -extern int s3c2410_dma_set_buffdone_fn(unsigned int, s3c2410_dma_cbfn_t rtn); +extern int s3c2410_dma_set_opfn(enum dma_ch, s3c2410_dma_opfn_t rtn); +extern int s3c2410_dma_set_buffdone_fn(enum dma_ch, s3c2410_dma_cbfn_t rtn); diff --git a/arch/arm/plat-samsung/include/plat/regs-serial.h b/arch/arm/plat-samsung/include/plat/regs-serial.h index c151c5f..116edfe 100644 --- a/arch/arm/plat-samsung/include/plat/regs-serial.h +++ b/arch/arm/plat-samsung/include/plat/regs-serial.h @@ -224,6 +224,8 @@ #define S5PV210_UFSTAT_RXMASK (255<<0) #define S5PV210_UFSTAT_RXSHIFT (0) +#define NO_NEED_CHECK_CLKSRC 1 + #ifndef __ASSEMBLY__ /* struct s3c24xx_uart_clksrc diff --git a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h index 0ffe34a..4c16fa3 100644 --- a/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h +++ b/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h @@ -39,6 +39,7 @@ struct s3c64xx_spi_csinfo { * @fifo_lvl_mask: All tx fifo_lvl fields start at offset-6 * @rx_lvl_offset: Depends on tx fifo_lvl field and bus number * @high_speed: If the controller supports HIGH_SPEED_EN bit + * @tx_st_done: Depends on tx fifo_lvl field */ struct s3c64xx_spi_info { int src_clk_nr; @@ -53,6 +54,7 @@ struct s3c64xx_spi_info { int fifo_lvl_mask; int rx_lvl_offset; int high_speed; + int tx_st_done; }; /** diff --git a/arch/arm/plat-samsung/irq-uart.c b/arch/arm/plat-samsung/irq-uart.c index 32582c0..657405c 100644 --- a/arch/arm/plat-samsung/irq-uart.c +++ b/arch/arm/plat-samsung/irq-uart.c @@ -54,8 +54,15 @@ static void __init s3c_init_uart_irq(struct s3c_uart_irq *uirq) gc = irq_alloc_generic_chip("s3c-uart", 1, uirq->base_irq, reg_base, handle_level_irq); + + if (!gc) { + pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n", + __func__, uirq->base_irq); + return; + } + ct = gc->chip_types; - ct->chip.irq_ack = irq_gc_ack; + ct->chip.irq_ack = irq_gc_ack_set_bit; ct->chip.irq_mask = irq_gc_mask_set_bit; ct->chip.irq_unmask = irq_gc_mask_clr_bit; ct->regs.ack = S3C64XX_UINTP; diff --git a/arch/arm/plat-samsung/irq-vic-timer.c b/arch/arm/plat-samsung/irq-vic-timer.c index a607546..f714d06 100644 --- a/arch/arm/plat-samsung/irq-vic-timer.c +++ b/arch/arm/plat-samsung/irq-vic-timer.c @@ -54,6 +54,13 @@ void __init s3c_init_vic_timer_irq(unsigned int num, unsigned int timer_irq) s3c_tgc = irq_alloc_generic_chip("s3c-timer", 1, timer_irq, S3C64XX_TINT_CSTAT, handle_level_irq); + + if (!s3c_tgc) { + pr_err("%s: irq_alloc_generic_chip for IRQ %d failed\n", + __func__, timer_irq); + return; + } + ct = s3c_tgc->chip_types; ct->chip.irq_mask = irq_gc_mask_clr_bit; ct->chip.irq_unmask = irq_gc_mask_set_bit; diff --git a/arch/m32r/include/asm/mmzone.h b/arch/m32r/include/asm/mmzone.h index 9f3b5ac..115ced3 100644 --- a/arch/m32r/include/asm/mmzone.h +++ b/arch/m32r/include/asm/mmzone.h @@ -14,12 +14,6 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) #define node_localnr(pfn, nid) ((pfn) - NODE_DATA(nid)->node_start_pfn) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages - 1; \ -}) #define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) /* @@ -44,7 +38,7 @@ static __inline__ int pfn_to_nid(unsigned long pfn) int node; for (node = 0 ; node < MAX_NUMNODES ; node++) - if (pfn >= node_start_pfn(node) && pfn <= node_end_pfn(node)) + if (pfn >= node_start_pfn(node) && pfn < node_end_pfn(node)) break; return node; diff --git a/arch/mips/kernel/i8259.c b/arch/mips/kernel/i8259.c index c018696..5c74eb7 100644 --- a/arch/mips/kernel/i8259.c +++ b/arch/mips/kernel/i8259.c @@ -14,7 +14,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/spinlock.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/irq.h> #include <asm/i8259.h> @@ -215,14 +215,13 @@ spurious_8259A_irq: } } -static int i8259A_resume(struct sys_device *dev) +static void i8259A_resume(void) { if (i8259A_auto_eoi >= 0) init_8259A(i8259A_auto_eoi); - return 0; } -static int i8259A_shutdown(struct sys_device *dev) +static void i8259A_shutdown(void) { /* Put the i8259A into a quiescent state that * the kernel initialization code can get it @@ -232,26 +231,17 @@ static int i8259A_shutdown(struct sys_device *dev) outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */ } - return 0; } -static struct sysdev_class i8259_sysdev_class = { - .name = "i8259", +static struct syscore_ops i8259_syscore_ops = { .resume = i8259A_resume, .shutdown = i8259A_shutdown, }; -static struct sys_device device_i8259A = { - .id = 0, - .cls = &i8259_sysdev_class, -}; - static int __init i8259A_init_sysfs(void) { - int error = sysdev_class_register(&i8259_sysdev_class); - if (!error) - error = sysdev_register(&device_i8259A); - return error; + register_syscore_ops(&i8259_syscore_ops); + return 0; } device_initcall(i8259A_init_sysfs); diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h index 3d6e60d..780560b 100644 --- a/arch/mn10300/include/asm/uaccess.h +++ b/arch/mn10300/include/asm/uaccess.h @@ -15,6 +15,7 @@ * User space memory access functions */ #include <linux/thread_info.h> +#include <linux/kernel.h> #include <asm/page.h> #include <asm/errno.h> diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h index 9608d2c..e67eb9c 100644 --- a/arch/parisc/include/asm/mmzone.h +++ b/arch/parisc/include/asm/mmzone.h @@ -14,13 +14,6 @@ extern struct node_map_data node_data[]; #define NODE_DATA(nid) (&node_data[nid].pg_data) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - /* We have these possible memory map layouts: * Astro: 0-3.75, 67.75-68, 4-64 * zx1: 0-1, 257-260, 4-256 diff --git a/arch/powerpc/boot/dts/p1022ds.dts b/arch/powerpc/boot/dts/p1022ds.dts index 4f685a7..98d9426 100644 --- a/arch/powerpc/boot/dts/p1022ds.dts +++ b/arch/powerpc/boot/dts/p1022ds.dts @@ -209,8 +209,10 @@ wm8776:codec@1a { compatible = "wlf,wm8776"; reg = <0x1a>; - /* MCLK source is a stand-alone oscillator */ - clock-frequency = <12288000>; + /* + * clock-frequency will be set by U-Boot if + * the clock is enabled. + */ }; }; @@ -280,7 +282,8 @@ codec-handle = <&wm8776>; fsl,playback-dma = <&dma00>; fsl,capture-dma = <&dma01>; - fsl,fifo-depth = <16>; + fsl,fifo-depth = <15>; + fsl,ssi-asynchronous; }; dma@c300 { diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index c9f212b..80bc5de 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -148,7 +148,6 @@ CONFIG_SCSI_SAS_ATTRS=m CONFIG_SCSI_CXGB3_ISCSI=m CONFIG_SCSI_CXGB4_ISCSI=m CONFIG_SCSI_BNX2_ISCSI=m -CONFIG_SCSI_BNX2_ISCSI=m CONFIG_BE2ISCSI=m CONFIG_SCSI_IBMVSCSI=y CONFIG_SCSI_IBMVFC=m diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index fd3fd58..7b58917 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -38,13 +38,6 @@ u64 memory_hotplug_max(void); #define memory_hotplug_max() memblock_end_of_DRAM() #endif -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) - #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ diff --git a/arch/powerpc/kernel/rtas-rtc.c b/arch/powerpc/kernel/rtas-rtc.c index 77578c0..c57c193 100644 --- a/arch/powerpc/kernel/rtas-rtc.c +++ b/arch/powerpc/kernel/rtas-rtc.c @@ -4,6 +4,7 @@ #include <linux/init.h> #include <linux/rtc.h> #include <linux/delay.h> +#include <linux/ratelimit.h> #include <asm/prom.h> #include <asm/rtas.h> #include <asm/time.h> @@ -29,9 +30,10 @@ unsigned long __init rtas_get_boot_time(void) } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) { - printk(KERN_WARNING "error: reading the clock failed (%d)\n", - error); + if (error != 0) { + printk_ratelimited(KERN_WARNING + "error: reading the clock failed (%d)\n", + error); return 0; } @@ -55,19 +57,21 @@ void rtas_get_rtc_time(struct rtc_time *rtc_tm) wait_time = rtas_busy_delay_time(error); if (wait_time) { - if (in_interrupt() && printk_ratelimit()) { + if (in_interrupt()) { memset(rtc_tm, 0, sizeof(struct rtc_time)); - printk(KERN_WARNING "error: reading clock" - " would delay interrupt\n"); + printk_ratelimited(KERN_WARNING + "error: reading clock " + "would delay interrupt\n"); return; /* delay not allowed */ } msleep(wait_time); } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) { - printk(KERN_WARNING "error: reading the clock failed (%d)\n", - error); + if (error != 0) { + printk_ratelimited(KERN_WARNING + "error: reading the clock failed (%d)\n", + error); return; } @@ -99,9 +103,10 @@ int rtas_set_rtc_time(struct rtc_time *tm) } } while (wait_time && (get_tb() < max_wait_tb)); - if (error != 0 && printk_ratelimit()) - printk(KERN_WARNING "error: setting the clock failed (%d)\n", - error); + if (error != 0) + printk_ratelimited(KERN_WARNING + "error: setting the clock failed (%d)\n", + error); return 0; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index b96a3a0..78b76dc 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -25,6 +25,7 @@ #include <linux/errno.h> #include <linux/elf.h> #include <linux/ptrace.h> +#include <linux/ratelimit.h> #ifdef CONFIG_PPC64 #include <linux/syscalls.h> #include <linux/compat.h> @@ -892,11 +893,12 @@ badframe: printk("badframe in handle_rt_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in handle_rt_signal32: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - addr, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in handle_rt_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); force_sigsegv(sig, current); return 0; @@ -1058,11 +1060,12 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; bad: - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in sys_rt_sigreturn: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - rt_sf, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in sys_rt_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + rt_sf, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; @@ -1149,12 +1152,12 @@ int sys_debug_setcontext(struct ucontext __user *ctx, * We kill the task with a SIGSEGV in this situation. */ if (do_setcontext(ctx, regs, 1)) { - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in " - "sys_debug_setcontext: %p nip %08lx " - "lr %08lx\n", - current->comm, current->pid, - ctx, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO "%s[%d]: bad frame in " + "sys_debug_setcontext: %p nip %08lx " + "lr %08lx\n", + current->comm, current->pid, + ctx, regs->nip, regs->link); force_sig(SIGSEGV, current); goto out; @@ -1236,11 +1239,12 @@ badframe: printk("badframe in handle_signal, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in handle_signal32: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - frame, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in handle_signal32: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + frame, regs->nip, regs->link); force_sigsegv(sig, current); return 0; @@ -1288,11 +1292,12 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8, return 0; badframe: - if (show_unhandled_signals && printk_ratelimit()) - printk(KERN_INFO "%s[%d]: bad frame in sys_sigreturn: " - "%p nip %08lx lr %08lx\n", - current->comm, current->pid, - addr, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(KERN_INFO + "%s[%d]: bad frame in sys_sigreturn: " + "%p nip %08lx lr %08lx\n", + current->comm, current->pid, + addr, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index da989ff..e91c736 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -24,6 +24,7 @@ #include <linux/elf.h> #include <linux/ptrace.h> #include <linux/module.h> +#include <linux/ratelimit.h> #include <asm/sigcontext.h> #include <asm/ucontext.h> @@ -380,10 +381,10 @@ badframe: printk("badframe in sys_rt_sigreturn, regs=%p uc=%p &uc->uc_mcontext=%p\n", regs, uc, &uc->uc_mcontext); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, "rt_sigreturn", - (long)uc, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, "rt_sigreturn", + (long)uc, regs->nip, regs->link); force_sig(SIGSEGV, current); return 0; @@ -468,10 +469,10 @@ badframe: printk("badframe in setup_rt_frame, regs=%p frame=%p newsp=%lx\n", regs, frame, newsp); #endif - if (show_unhandled_signals && printk_ratelimit()) - printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, "setup_rt_frame", - (long)frame, regs->nip, regs->link); + if (show_unhandled_signals) + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, "setup_rt_frame", + (long)frame, regs->nip, regs->link); force_sigsegv(signr, current); return 0; diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0ff4ab9..1a01414 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -34,6 +34,7 @@ #include <linux/bug.h> #include <linux/kdebug.h> #include <linux/debugfs.h> +#include <linux/ratelimit.h> #include <asm/emulated_ops.h> #include <asm/pgtable.h> @@ -197,12 +198,11 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr) if (die("Exception in kernel mode", regs, signr)) return; } else if (show_unhandled_signals && - unhandled_signal(current, signr) && - printk_ratelimit()) { - printk(regs->msr & MSR_64BIT ? fmt64 : fmt32, - current->comm, current->pid, signr, - addr, regs->nip, regs->link, code); - } + unhandled_signal(current, signr)) { + printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32, + current->comm, current->pid, signr, + addr, regs->nip, regs->link, code); + } memset(&info, 0, sizeof(info)); info.si_signo = signr; @@ -425,7 +425,7 @@ int machine_check_e500mc(struct pt_regs *regs) unsigned long reason = mcsr; int recoverable = 1; - if (reason & MCSR_BUS_RBERR) { + if (reason & MCSR_LD) { recoverable = fsl_rio_mcheck_exception(regs); if (recoverable == 1) goto silent_out; @@ -1342,9 +1342,8 @@ void altivec_assist_exception(struct pt_regs *regs) } else { /* didn't recognize the instruction */ /* XXX quick hack for now: set the non-Java bit in the VSCR */ - if (printk_ratelimit()) - printk(KERN_ERR "Unrecognized altivec instruction " - "in %s at %lx\n", current->comm, regs->nip); + printk_ratelimited(KERN_ERR "Unrecognized altivec instruction " + "in %s at %lx\n", current->comm, regs->nip); current->thread.vscr.u[3] |= 0x10000; } } @@ -1548,9 +1547,8 @@ u32 ppc_warn_emulated; void ppc_warn_emulated_print(const char *type) { - if (printk_ratelimit()) - pr_warning("%s used emulated %s instruction\n", current->comm, - type); + pr_warn_ratelimited("%s used emulated %s instruction\n", current->comm, + type); } static int __init ppc_warn_emulated_init(void) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 54f4fb9..ad35f66 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -31,6 +31,7 @@ #include <linux/kdebug.h> #include <linux/perf_event.h> #include <linux/magic.h> +#include <linux/ratelimit.h> #include <asm/firmware.h> #include <asm/page.h> @@ -346,11 +347,10 @@ bad_area_nosemaphore: return 0; } - if (is_exec && (error_code & DSISR_PROTFAULT) - && printk_ratelimit()) - printk(KERN_CRIT "kernel tried to execute NX-protected" - " page (%lx) - exploit attempt? (uid: %d)\n", - address, current_uid()); + if (is_exec && (error_code & DSISR_PROTFAULT)) + printk_ratelimited(KERN_CRIT "kernel tried to execute NX-protected" + " page (%lx) - exploit attempt? (uid: %d)\n", + address, current_uid()); return SIGSEGV; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 33867ec..9d6a8ef 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -12,6 +12,8 @@ #include <linux/of.h> #include <linux/memblock.h> #include <linux/vmalloc.h> +#include <linux/memory.h> + #include <asm/firmware.h> #include <asm/machdep.h> #include <asm/pSeries_reconfig.h> @@ -20,24 +22,25 @@ static unsigned long get_memblock_size(void) { struct device_node *np; - unsigned int memblock_size = 0; + unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (np) { - const unsigned long *size; + const __be64 *size; size = of_get_property(np, "ibm,lmb-size", NULL); - memblock_size = size ? *size : 0; - + if (size) + memblock_size = be64_to_cpup(size); of_node_put(np); - } else { + } else if (machine_is(pseries)) { + /* This fallback really only applies to pseries */ unsigned int memzero_size = 0; - const unsigned int *regs; np = of_find_node_by_path("/memory@0"); if (np) { - regs = of_get_property(np, "reg", NULL); - memzero_size = regs ? regs[3] : 0; + if (!of_address_to_resource(np, 0, &r)) + memzero_size = resource_size(&r); of_node_put(np); } @@ -50,16 +53,21 @@ static unsigned long get_memblock_size(void) sprintf(buf, "/memory@%x", memzero_size); np = of_find_node_by_path(buf); if (np) { - regs = of_get_property(np, "reg", NULL); - memblock_size = regs ? regs[3] : 0; + if (!of_address_to_resource(np, 0, &r)) + memblock_size = resource_size(&r); of_node_put(np); } } } - return memblock_size; } +/* WARNING: This is going to override the generic definition whenever + * pseries is built-in regardless of what platform is active at boot + * time. This is fine for now as this is the only "option" and it + * should work everywhere. If not, we'll have to turn this into a + * ppc_md. callback + */ unsigned long memory_block_size_bytes(void) { return get_memblock_size(); diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 5b206a2..b3fd081 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -283,23 +283,24 @@ static void __iomem *rio_regs_win; #ifdef CONFIG_E500 int fsl_rio_mcheck_exception(struct pt_regs *regs) { - const struct exception_table_entry *entry = NULL; - unsigned long reason = mfspr(SPRN_MCSR); - - if (reason & MCSR_BUS_RBERR) { - reason = in_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR)); - if (reason & (RIO_LTLEDCSR_IER | RIO_LTLEDCSR_PRT)) { - /* Check if we are prepared to handle this fault */ - entry = search_exception_tables(regs->nip); - if (entry) { - pr_debug("RIO: %s - MC Exception handled\n", - __func__); - out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), - 0); - regs->msr |= MSR_RI; - regs->nip = entry->fixup; - return 1; - } + const struct exception_table_entry *entry; + unsigned long reason; + + if (!rio_regs_win) + return 0; + + reason = in_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR)); + if (reason & (RIO_LTLEDCSR_IER | RIO_LTLEDCSR_PRT)) { + /* Check if we are prepared to handle this fault */ + entry = search_exception_tables(regs->nip); + if (entry) { + pr_debug("RIO: %s - MC Exception handled\n", + __func__); + out_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR), + 0); + regs->msr |= MSR_RI; + regs->nip = entry->fixup; + return 1; } } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 3a8de5b..58d7a53 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -29,6 +29,7 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/syscore_ops.h> +#include <linux/ratelimit.h> #include <asm/ptrace.h> #include <asm/signal.h> @@ -1648,9 +1649,8 @@ static unsigned int _mpic_get_one_irq(struct mpic *mpic, int reg) return NO_IRQ; } if (unlikely(mpic->protected && test_bit(src, mpic->protected))) { - if (printk_ratelimit()) - printk(KERN_WARNING "%s: Got protected source %d !\n", - mpic->name, (int)src); + printk_ratelimited(KERN_WARNING "%s: Got protected source %d !\n", + mpic->name, (int)src); mpic_eoi(mpic); return NO_IRQ; } @@ -1688,9 +1688,8 @@ unsigned int mpic_get_coreint_irq(void) return NO_IRQ; } if (unlikely(mpic->protected && test_bit(src, mpic->protected))) { - if (printk_ratelimit()) - printk(KERN_WARNING "%s: Got protected source %d !\n", - mpic->name, (int)src); + printk_ratelimited(KERN_WARNING "%s: Got protected source %d !\n", + mpic->name, (int)src); return NO_IRQ; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 90d77bd..c03fef7 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -579,6 +579,7 @@ config S390_GUEST def_bool y prompt "s390 guest support for KVM (EXPERIMENTAL)" depends on 64BIT && EXPERIMENTAL + select VIRTUALIZATION select VIRTIO select VIRTIO_RING select VIRTIO_CONSOLE diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 52420d2..1d55c95 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -262,7 +262,7 @@ void smp_ctl_set_bit(int cr, int bit) memset(&parms.orvals, 0, sizeof(parms.orvals)); memset(&parms.andvals, 0xff, sizeof(parms.andvals)); - parms.orvals[cr] = 1 << bit; + parms.orvals[cr] = 1UL << bit; on_each_cpu(smp_ctl_bit_callback, &parms, 1); } EXPORT_SYMBOL(smp_ctl_set_bit); @@ -276,7 +276,7 @@ void smp_ctl_clear_bit(int cr, int bit) memset(&parms.orvals, 0, sizeof(parms.orvals)); memset(&parms.andvals, 0xff, sizeof(parms.andvals)); - parms.andvals[cr] = ~(1L << bit); + parms.andvals[cr] = ~(1UL << bit); on_each_cpu(smp_ctl_bit_callback, &parms, 1); } EXPORT_SYMBOL(smp_ctl_clear_bit); diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 5995e9b..0e358c2 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -25,7 +25,7 @@ extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth); #include "hwsampler.h" -#define DEFAULT_INTERVAL 4096 +#define DEFAULT_INTERVAL 4127518 #define DEFAULT_SDBT_BLOCKS 1 #define DEFAULT_SDB_BLOCKS 511 @@ -151,6 +151,12 @@ static int oprofile_hwsampler_init(struct oprofile_operations *ops) if (oprofile_max_interval == 0) return -ENODEV; + /* The initial value should be sane */ + if (oprofile_hw_interval < oprofile_min_interval) + oprofile_hw_interval = oprofile_min_interval; + if (oprofile_hw_interval > oprofile_max_interval) + oprofile_hw_interval = oprofile_max_interval; + if (oprofile_timer_init(ops)) return -ENODEV; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index f03338c..bbdeb48 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -348,6 +348,7 @@ config CPU_SUBTYPE_SH7720 select SYS_SUPPORTS_CMT select ARCH_WANT_OPTIONAL_GPIOLIB select USB_ARCH_HAS_OHCI + select USB_OHCI_SH if USB_OHCI_HCD help Select SH7720 if you have a SH3-DSP SH7720 CPU. @@ -357,6 +358,7 @@ config CPU_SUBTYPE_SH7721 select CPU_HAS_DSP select SYS_SUPPORTS_CMT select USB_ARCH_HAS_OHCI + select USB_OHCI_SH if USB_OHCI_HCD help Select SH7721 if you have a SH3-DSP SH7721 CPU. @@ -440,6 +442,7 @@ config CPU_SUBTYPE_SH7763 bool "Support SH7763 processor" select CPU_SH4A select USB_ARCH_HAS_OHCI + select USB_OHCI_SH if USB_OHCI_HCD help Select SH7763 if you have a SH4A SH7763(R5S77631) CPU. @@ -467,7 +470,9 @@ config CPU_SUBTYPE_SH7786 select GENERIC_CLOCKEVENTS_BROADCAST if SMP select ARCH_WANT_OPTIONAL_GPIOLIB select USB_ARCH_HAS_OHCI + select USB_OHCI_SH if USB_OHCI_HCD select USB_ARCH_HAS_EHCI + select USB_EHCI_SH if USB_EHCI_HCD config CPU_SUBTYPE_SHX3 bool "Support SH-X3 processor" diff --git a/arch/sh/configs/sh7757lcr_defconfig b/arch/sh/configs/sh7757lcr_defconfig index 33ddb13..cfde98d 100644 --- a/arch/sh/configs/sh7757lcr_defconfig +++ b/arch/sh/configs/sh7757lcr_defconfig @@ -9,7 +9,6 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set # CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_ALL=y CONFIG_SLAB=y @@ -39,8 +38,6 @@ CONFIG_IPV6=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_CONCAT=y -CONFIG_MTD_PARTITIONS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_M25P80=y @@ -56,18 +53,19 @@ CONFIG_SH_ETH=y # CONFIG_KEYBOARD_ATKBD is not set # CONFIG_MOUSE_PS2 is not set # CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_SH_SCI=y CONFIG_SERIAL_SH_SCI_NR_UARTS=3 CONFIG_SERIAL_SH_SCI_CONSOLE=y -# CONFIG_LEGACY_PTYS is not set # CONFIG_HW_RANDOM is not set CONFIG_SPI=y CONFIG_SPI_SH=y # CONFIG_HWMON is not set -CONFIG_MFD_SH_MOBILE_SDHI=y CONFIG_USB=y CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_SH=y CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_SH=y CONFIG_USB_STORAGE=y CONFIG_MMC=y CONFIG_MMC_SDHI=y diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h index 8887baf..15a8496 100644 --- a/arch/sh/include/asm/mmzone.h +++ b/arch/sh/include/asm/mmzone.h @@ -9,10 +9,6 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ - NODE_DATA(nid)->node_spanned_pages) - static inline int pfn_to_nid(unsigned long pfn) { int nid; diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c index 423dabf..e915dea 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7757.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7757.c @@ -183,7 +183,7 @@ static const struct sh_dmae_slave_config sh7757_dmae1_slaves[] = { { .slave_id = SHDMA_SLAVE_SCIF2_RX, .addr = 0x1f4b0014, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x22, }, @@ -197,7 +197,7 @@ static const struct sh_dmae_slave_config sh7757_dmae1_slaves[] = { { .slave_id = SHDMA_SLAVE_SCIF3_RX, .addr = 0x1f4c0014, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x2a, }, @@ -211,7 +211,7 @@ static const struct sh_dmae_slave_config sh7757_dmae1_slaves[] = { { .slave_id = SHDMA_SLAVE_SCIF4_RX, .addr = 0x1f4d0014, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x42, }, @@ -228,7 +228,7 @@ static const struct sh_dmae_slave_config sh7757_dmae2_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC0_RX, .addr = 0x1e500013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x22, }, @@ -242,7 +242,7 @@ static const struct sh_dmae_slave_config sh7757_dmae2_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC1_RX, .addr = 0x1e510013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x2a, }, @@ -256,7 +256,7 @@ static const struct sh_dmae_slave_config sh7757_dmae2_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC2_RX, .addr = 0x1e520013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0xa2, }, @@ -265,12 +265,12 @@ static const struct sh_dmae_slave_config sh7757_dmae2_slaves[] = { .addr = 0x1e530012, .chcr = SM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), - .mid_rid = 0xab, + .mid_rid = 0xa9, }, { .slave_id = SHDMA_SLAVE_RIIC3_RX, .addr = 0x1e530013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0xaf, }, @@ -279,14 +279,14 @@ static const struct sh_dmae_slave_config sh7757_dmae2_slaves[] = { .addr = 0x1e540012, .chcr = SM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), - .mid_rid = 0xc1, + .mid_rid = 0xc5, }, { .slave_id = SHDMA_SLAVE_RIIC4_RX, .addr = 0x1e540013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), - .mid_rid = 0xc2, + .mid_rid = 0xc6, }, }; @@ -301,7 +301,7 @@ static const struct sh_dmae_slave_config sh7757_dmae3_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC5_RX, .addr = 0x1e550013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x22, }, @@ -315,7 +315,7 @@ static const struct sh_dmae_slave_config sh7757_dmae3_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC6_RX, .addr = 0x1e560013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x2a, }, @@ -329,7 +329,7 @@ static const struct sh_dmae_slave_config sh7757_dmae3_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC7_RX, .addr = 0x1e570013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x42, }, @@ -343,7 +343,7 @@ static const struct sh_dmae_slave_config sh7757_dmae3_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC8_RX, .addr = 0x1e580013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x46, }, @@ -357,7 +357,7 @@ static const struct sh_dmae_slave_config sh7757_dmae3_slaves[] = { { .slave_id = SHDMA_SLAVE_RIIC9_RX, .addr = 0x1e590013, - .chcr = SM_INC | 0x800 | 0x40000000 | + .chcr = DM_INC | 0x800 | 0x40000000 | TS_INDEX2VAL(XMIT_SZ_8BIT), .mid_rid = 0x52, }, @@ -659,6 +659,54 @@ static struct platform_device spi0_device = { .resource = spi0_resources, }; +static struct resource usb_ehci_resources[] = { + [0] = { + .start = 0xfe4f1000, + .end = 0xfe4f10ff, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = 57, + .end = 57, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usb_ehci_device = { + .name = "sh_ehci", + .id = -1, + .dev = { + .dma_mask = &usb_ehci_device.dev.coherent_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + }, + .num_resources = ARRAY_SIZE(usb_ehci_resources), + .resource = usb_ehci_resources, +}; + +static struct resource usb_ohci_resources[] = { + [0] = { + .start = 0xfe4f1800, + .end = 0xfe4f18ff, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = 57, + .end = 57, + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device usb_ohci_device = { + .name = "sh_ohci", + .id = -1, + .dev = { + .dma_mask = &usb_ohci_device.dev.coherent_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + }, + .num_resources = ARRAY_SIZE(usb_ohci_resources), + .resource = usb_ohci_resources, +}; + static struct platform_device *sh7757_devices[] __initdata = { &scif2_device, &scif3_device, @@ -670,6 +718,8 @@ static struct platform_device *sh7757_devices[] __initdata = { &dma2_device, &dma3_device, &spi0_device, + &usb_ehci_device, + &usb_ohci_device, }; static int __init sh7757_devices_setup(void) @@ -1039,13 +1089,13 @@ static DECLARE_INTC_DESC(intc_desc, "sh7757", vectors, groups, /* Support for external interrupt pins in IRQ mode */ static struct intc_vect vectors_irq0123[] __initdata = { - INTC_VECT(IRQ0, 0x240), INTC_VECT(IRQ1, 0x280), - INTC_VECT(IRQ2, 0x2c0), INTC_VECT(IRQ3, 0x300), + INTC_VECT(IRQ0, 0x200), INTC_VECT(IRQ1, 0x240), + INTC_VECT(IRQ2, 0x280), INTC_VECT(IRQ3, 0x2c0), }; static struct intc_vect vectors_irq4567[] __initdata = { - INTC_VECT(IRQ4, 0x340), INTC_VECT(IRQ5, 0x380), - INTC_VECT(IRQ6, 0x3c0), INTC_VECT(IRQ7, 0x200), + INTC_VECT(IRQ4, 0x300), INTC_VECT(IRQ5, 0x340), + INTC_VECT(IRQ6, 0x380), INTC_VECT(IRQ7, 0x3c0), }; static struct intc_sense_reg sense_registers[] __initdata = { @@ -1079,14 +1129,14 @@ static struct intc_vect vectors_irl0123[] __initdata = { }; static struct intc_vect vectors_irl4567[] __initdata = { - INTC_VECT(IRL4_LLLL, 0xb00), INTC_VECT(IRL4_LLLH, 0xb20), - INTC_VECT(IRL4_LLHL, 0xb40), INTC_VECT(IRL4_LLHH, 0xb60), - INTC_VECT(IRL4_LHLL, 0xb80), INTC_VECT(IRL4_LHLH, 0xba0), - INTC_VECT(IRL4_LHHL, 0xbc0), INTC_VECT(IRL4_LHHH, 0xbe0), - INTC_VECT(IRL4_HLLL, 0xc00), INTC_VECT(IRL4_HLLH, 0xc20), - INTC_VECT(IRL4_HLHL, 0xc40), INTC_VECT(IRL4_HLHH, 0xc60), - INTC_VECT(IRL4_HHLL, 0xc80), INTC_VECT(IRL4_HHLH, 0xca0), - INTC_VECT(IRL4_HHHL, 0xcc0), + INTC_VECT(IRL4_LLLL, 0x200), INTC_VECT(IRL4_LLLH, 0x220), + INTC_VECT(IRL4_LLHL, 0x240), INTC_VECT(IRL4_LLHH, 0x260), + INTC_VECT(IRL4_LHLL, 0x280), INTC_VECT(IRL4_LHLH, 0x2a0), + INTC_VECT(IRL4_LHHL, 0x2c0), INTC_VECT(IRL4_LHHH, 0x2e0), + INTC_VECT(IRL4_HLLL, 0x300), INTC_VECT(IRL4_HLLH, 0x320), + INTC_VECT(IRL4_HLHL, 0x340), INTC_VECT(IRL4_HLHH, 0x360), + INTC_VECT(IRL4_HHLL, 0x380), INTC_VECT(IRL4_HHLH, 0x3a0), + INTC_VECT(IRL4_HHHL, 0x3c0), }; static DECLARE_INTC_DESC(intc_desc_irl0123, "sh7757-irl0123", vectors_irl0123, diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index 9197110..a3ee919 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -13,6 +13,7 @@ #include <linux/seq_file.h> #include <linux/ftrace.h> #include <linux/delay.h> +#include <linux/ratelimit.h> #include <asm/processor.h> #include <asm/machvec.h> #include <asm/uaccess.h> @@ -268,9 +269,8 @@ void migrate_irqs(void) unsigned int newcpu = cpumask_any_and(data->affinity, cpu_online_mask); if (newcpu >= nr_cpu_ids) { - if (printk_ratelimit()) - printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n", - irq, cpu); + pr_info_ratelimited("IRQ%u no longer affine to CPU%u\n", + irq, cpu); cpumask_setall(data->affinity); newcpu = cpumask_any_and(data->affinity, diff --git a/arch/sh/mm/alignment.c b/arch/sh/mm/alignment.c index b2595b8..620fa7f 100644 --- a/arch/sh/mm/alignment.c +++ b/arch/sh/mm/alignment.c @@ -13,6 +13,7 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/uaccess.h> +#include <linux/ratelimit.h> #include <asm/alignment.h> #include <asm/processor.h> @@ -95,13 +96,13 @@ int set_unalign_ctl(struct task_struct *tsk, unsigned int val) void unaligned_fixups_notify(struct task_struct *tsk, insn_size_t insn, struct pt_regs *regs) { - if (user_mode(regs) && (se_usermode & UM_WARN) && printk_ratelimit()) - pr_notice("Fixing up unaligned userspace access " + if (user_mode(regs) && (se_usermode & UM_WARN)) + pr_notice_ratelimited("Fixing up unaligned userspace access " "in \"%s\" pid=%d pc=0x%p ins=0x%04hx\n", tsk->comm, task_pid_nr(tsk), (void *)instruction_pointer(regs), insn); - else if (se_kernmode_warn && printk_ratelimit()) - pr_notice("Fixing up unaligned kernel access " + else if (se_kernmode_warn) + pr_notice_ratelimited("Fixing up unaligned kernel access " "in \"%s\" pid=%d pc=0x%p ins=0x%04hx\n", tsk->comm, task_pid_nr(tsk), (void *)instruction_pointer(regs), insn); diff --git a/arch/sparc/include/asm/irqflags_32.h b/arch/sparc/include/asm/irqflags_32.h index d4d0711..1484890 100644 --- a/arch/sparc/include/asm/irqflags_32.h +++ b/arch/sparc/include/asm/irqflags_32.h @@ -18,7 +18,7 @@ extern void arch_local_irq_restore(unsigned long); extern unsigned long arch_local_irq_save(void); extern void arch_local_irq_enable(void); -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { unsigned long flags; @@ -26,17 +26,17 @@ static inline unsigned long arch_local_save_flags(void) return flags; } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { arch_local_irq_save(); } -static inline bool arch_irqs_disabled_flags(unsigned long flags) +static inline notrace bool arch_irqs_disabled_flags(unsigned long flags) { return (flags & PSR_PIL) != 0; } -static inline bool arch_irqs_disabled(void) +static inline notrace bool arch_irqs_disabled(void) { return arch_irqs_disabled_flags(arch_local_save_flags()); } diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h index aab969c..23cd27f 100644 --- a/arch/sparc/include/asm/irqflags_64.h +++ b/arch/sparc/include/asm/irqflags_64.h @@ -14,7 +14,7 @@ #ifndef __ASSEMBLY__ -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { unsigned long flags; @@ -26,7 +26,7 @@ static inline unsigned long arch_local_save_flags(void) return flags; } -static inline void arch_local_irq_restore(unsigned long flags) +static inline notrace void arch_local_irq_restore(unsigned long flags) { __asm__ __volatile__( "wrpr %0, %%pil" @@ -36,7 +36,7 @@ static inline void arch_local_irq_restore(unsigned long flags) ); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { __asm__ __volatile__( "wrpr %0, %%pil" @@ -46,7 +46,7 @@ static inline void arch_local_irq_disable(void) ); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { __asm__ __volatile__( "wrpr 0, %%pil" @@ -56,17 +56,17 @@ static inline void arch_local_irq_enable(void) ); } -static inline int arch_irqs_disabled_flags(unsigned long flags) +static inline notrace int arch_irqs_disabled_flags(unsigned long flags) { return (flags > 0); } -static inline int arch_irqs_disabled(void) +static inline notrace int arch_irqs_disabled(void) { return arch_irqs_disabled_flags(arch_local_save_flags()); } -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { unsigned long flags, tmp; diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h index e8c6487..99d9b9f 100644 --- a/arch/sparc/include/asm/mmzone.h +++ b/arch/sparc/include/asm/mmzone.h @@ -8,8 +8,6 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_end_pfn) extern int numa_cpu_lookup_table[]; extern cpumask_t numa_cpumask_lookup_table[]; diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index c7ad3fe..b928b31 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -205,6 +205,7 @@ do { current_thread_info()->syscall_noerror = 1; \ } while (0) #define user_mode(regs) (!((regs)->tstate & TSTATE_PRIV)) #define instruction_pointer(regs) ((regs)->tpc) +#define instruction_pointer_set(regs, val) ((regs)->tpc = (val)) #define user_stack_pointer(regs) ((regs)->u_regs[UREG_FP]) #define regs_return_value(regs) ((regs)->u_regs[UREG_I0]) #ifdef CONFIG_SMP diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 9fe08a1..f445e98 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -293,7 +293,7 @@ maybe_smp4m_msg: WRITE_PAUSE wr %l4, PSR_ET, %psr WRITE_PAUSE - sll %o3, 28, %o2 ! shift for simpler checks below + srl %o3, 28, %o2 ! shift for simpler checks below maybe_smp4m_msg_check_single: andcc %o2, 0x1, %g0 beq,a maybe_smp4m_msg_check_mask diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c index c0e0129..e485a68 100644 --- a/arch/sparc/mm/leon_mm.c +++ b/arch/sparc/mm/leon_mm.c @@ -226,7 +226,7 @@ void leon3_getCacheRegs(struct leon3_cacheregs *regs) * Leon2 and Leon3 differ in their way of telling cache information * */ -int leon_flush_needed(void) +int __init leon_flush_needed(void) { int flush_needed = -1; unsigned int ssize, sets; diff --git a/arch/tile/include/asm/mmzone.h b/arch/tile/include/asm/mmzone.h index c6344c4..9d3dbce 100644 --- a/arch/tile/include/asm/mmzone.h +++ b/arch/tile/include/asm/mmzone.h @@ -40,17 +40,6 @@ static inline int pfn_to_nid(unsigned long pfn) return highbits_to_node[__pfn_to_highbits(pfn)]; } -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - #define kern_addr_valid(kaddr) virt_addr_valid((void *)kaddr) static inline int pfn_valid(int pfn) diff --git a/arch/um/include/asm/percpu.h b/arch/um/include/asm/percpu.h new file mode 100644 index 0000000..efe7508 --- /dev/null +++ b/arch/um/include/asm/percpu.h @@ -0,0 +1,6 @@ +#ifndef __UM_PERCPU_H +#define __UM_PERCPU_H + +#include <asm-generic/percpu.h> + +#endif /* __UM_PERCPU_H */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index da34972..37357a5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1170,7 +1170,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" config AMD_NUMA def_bool y prompt "Old style AMD Opteron NUMA detection" - depends on NUMA && PCI + depends on X86_64 && NUMA && PCI ---help--- Enable AMD NUMA node topology detection. You should say Y here if you have a multi processor AMD system. This uses an old method to diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index 2fefa50..af60d8a 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -62,7 +62,7 @@ extern int sfi_mtimer_num; #else /* CONFIG_APB_TIMER */ static inline unsigned long apbt_quick_calibrate(void) {return 0; } -static inline void apbt_time_init(void) {return 0; } +static inline void apbt_time_init(void) { } #endif #endif /* ASM_X86_APBT_H */ diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 5e83a41..ffa037f 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn) #endif } -/* - * Following are macros that each numa implmentation must define. - */ - -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) \ -({ \ - pg_data_t *__pgdat = NODE_DATA(nid); \ - __pgdat->node_start_pfn + __pgdat->node_spanned_pages; \ -}) - static inline int pfn_valid(int pfn) { int nid = pfn_to_nid(pfn); @@ -68,6 +57,8 @@ static inline int pfn_valid(int pfn) return 0; } +#define early_pfn_valid(pfn) pfn_valid((pfn)) + #endif /* CONFIG_DISCONTIGMEM */ #ifdef CONFIG_NEED_MULTIPLE_NODES diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index b3f88d7..129d9aa 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -13,8 +13,5 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) -#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) -#define node_end_pfn(nid) (NODE_DATA(nid)->node_start_pfn + \ - NODE_DATA(nid)->node_spanned_pages) #endif #endif /* _ASM_X86_MMZONE_64_H */ diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 4fbda9a..968d57d 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -14,13 +14,14 @@ static inline int pci_xen_hvm_init(void) } #endif #if defined(CONFIG_XEN_DOM0) -void __init xen_setup_pirqs(void); +int __init pci_xen_initial_domain(void); int xen_find_device_domain_owner(struct pci_dev *dev); int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain); int xen_unregister_device_domain_owner(struct pci_dev *dev); #else -static inline void __init xen_setup_pirqs(void) +static inline int __init pci_xen_initial_domain(void) { + return -1; } static inline int xen_find_device_domain_owner(struct pci_dev *dev) { diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S index ead21b6..b4fd836 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.S +++ b/arch/x86/kernel/acpi/realmode/wakeup.S @@ -28,6 +28,8 @@ pmode_cr3: .long 0 /* Saved %cr3 */ pmode_cr4: .long 0 /* Saved %cr4 */ pmode_efer: .quad 0 /* Saved EFER */ pmode_gdt: .quad 0 +pmode_misc_en: .quad 0 /* Saved MISC_ENABLE MSR */ +pmode_behavior: .long 0 /* Wakeup behavior flags */ realmode_flags: .long 0 real_magic: .long 0 trampoline_segment: .word 0 @@ -91,6 +93,18 @@ wakeup_code: /* Call the C code */ calll main + /* Restore MISC_ENABLE before entering protected mode, in case + BIOS decided to clear XD_DISABLE during S3. */ + movl pmode_behavior, %eax + btl $WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %eax + jnc 1f + + movl pmode_misc_en, %eax + movl pmode_misc_en + 4, %edx + movl $MSR_IA32_MISC_ENABLE, %ecx + wrmsr +1: + /* Do any other stuff... */ #ifndef CONFIG_64BIT diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h index e1828c0..97a29e1 100644 --- a/arch/x86/kernel/acpi/realmode/wakeup.h +++ b/arch/x86/kernel/acpi/realmode/wakeup.h @@ -21,6 +21,9 @@ struct wakeup_header { u32 pmode_efer_low; /* Protected mode EFER */ u32 pmode_efer_high; u64 pmode_gdt; + u32 pmode_misc_en_low; /* Protected mode MISC_ENABLE */ + u32 pmode_misc_en_high; + u32 pmode_behavior; /* Wakeup routine behavior flags */ u32 realmode_flags; u32 real_magic; u16 trampoline_segment; /* segment with trampoline code, 64-bit only */ @@ -39,4 +42,7 @@ extern struct wakeup_header wakeup_header; #define WAKEUP_HEADER_SIGNATURE 0x51ee1111 #define WAKEUP_END_SIGNATURE 0x65a22c82 +/* Wakeup behavior bits */ +#define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE 0 + #endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 18a857b..103b6ab 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -77,6 +77,12 @@ int acpi_suspend_lowlevel(void) header->pmode_cr0 = read_cr0(); header->pmode_cr4 = read_cr4_safe(); + header->pmode_behavior = 0; + if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, + &header->pmode_misc_en_low, + &header->pmode_misc_en_high)) + header->pmode_behavior |= + (1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE); header->realmode_flags = acpi_realmode_flags; header->real_magic = 0x12345678; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0c016f7..9242436 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -294,6 +294,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"), }, }, + { /* Handle reboot issue on Acer Aspire one */ + .callback = set_bios_reboot, + .ident = "Acer Aspire One A110", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), + }, + }, { } }; @@ -411,6 +419,30 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the Latitude E6320. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6320", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"), + }, + }, + { /* Handle problems with rebooting on the Latitude E5420. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E5420", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"), + }, + }, + { /* Handle problems with rebooting on the Latitude E6420. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6420", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"), + }, + }, { } }; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 6df88c7..adc9867 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3372,7 +3372,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) int def_op_bytes, def_ad_bytes, goffset, simd_prefix; bool op_prefix = false; struct opcode opcode; - struct operand memop = { .type = OP_NONE }; + struct operand memop = { .type = OP_NONE }, *memopp = NULL; c->eip = ctxt->eip; c->fetch.start = c->eip; @@ -3547,9 +3547,6 @@ done_prefixes: if (memop.type == OP_MEM && c->ad_bytes != 8) memop.addr.mem.ea = (u32)memop.addr.mem.ea; - if (memop.type == OP_MEM && c->rip_relative) - memop.addr.mem.ea += c->eip; - /* * Decode and fetch the source operand: register, memory * or immediate. @@ -3571,6 +3568,7 @@ done_prefixes: c->op_bytes; srcmem_common: c->src = memop; + memopp = &c->src; break; case SrcImmU16: rc = decode_imm(ctxt, &c->src, 2, false); @@ -3667,6 +3665,7 @@ done_prefixes: case DstMem: case DstMem64: c->dst = memop; + memopp = &c->dst; if ((c->d & DstMask) == DstMem64) c->dst.bytes = 8; else @@ -3700,10 +3699,13 @@ done_prefixes: /* Special instructions do their own operand decoding. */ default: c->dst.type = OP_NONE; /* Disable writeback. */ - return 0; + break; } done: + if (memopp && memopp->type == OP_MEM && c->rip_relative) + memopp->addr.mem.ea += c->eip; + return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index d865c4a..bbaaa00 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -28,6 +28,7 @@ #include <linux/poison.h> #include <linux/dma-mapping.h> #include <linux/module.h> +#include <linux/memory.h> #include <linux/memory_hotplug.h> #include <linux/nmi.h> #include <linux/gfp.h> @@ -895,8 +896,6 @@ const char *arch_vma_name(struct vm_area_struct *vma) } #ifdef CONFIG_X86_UV -#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) - unsigned long memory_block_size_bytes(void) { if (is_uv_system()) { diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index cf97500..68894fd 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy) static int nmi_start(void) { get_online_cpus(); - on_each_cpu(nmi_cpu_start, NULL, 1); ctr_running = 1; + /* make ctr_running visible to the nmi handler: */ + smp_mb(); + on_each_cpu(nmi_cpu_start, NULL, 1); put_online_cpus(); return 0; } @@ -504,15 +506,18 @@ static int nmi_setup(void) nmi_enabled = 0; ctr_running = 0; - barrier(); + /* make variables visible to the nmi handler: */ + smp_mb(); err = register_die_notifier(&profile_exceptions_nb); if (err) goto fail; get_online_cpus(); register_cpu_notifier(&oprofile_cpu_nb); - on_each_cpu(nmi_cpu_setup, NULL, 1); nmi_enabled = 1; + /* make nmi_enabled visible to the nmi handler: */ + smp_mb(); + on_each_cpu(nmi_cpu_setup, NULL, 1); put_online_cpus(); return 0; @@ -531,7 +536,8 @@ static void nmi_shutdown(void) nmi_enabled = 0; ctr_running = 0; put_online_cpus(); - barrier(); + /* make variables visible to the nmi handler: */ + smp_mb(); unregister_die_notifier(&profile_exceptions_nb); msrs = &get_cpu_var(cpu_msrs); model->shutdown(msrs); diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 0972315..68c3c13 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point) return false; } -static void coalesce_windows(struct pci_root_info *info, int type) +static void coalesce_windows(struct pci_root_info *info, unsigned long type) { int i, j; struct resource *res1, *res2; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 8214724..1017c7b 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -1,8 +1,13 @@ /* - * Xen PCI Frontend Stub - puts some "dummy" functions in to the Linux - * x86 PCI core to support the Xen PCI Frontend + * Xen PCI - handle PCI (INTx) and MSI infrastructure calls for PV, HVM and + * initial domain support. We also handle the DSDT _PRT callbacks for GSI's + * used in HVM and initial domain mode (PV does not parse ACPI, so it has no + * concept of GSIs). Under PV we hook under the pnbbios API for IRQs and + * 0xcf8 PCI configuration read/write. * * Author: Ryan Wilson <hap9@epoch.ncsc.mil> + * Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> + * Stefano Stabellini <stefano.stabellini@eu.citrix.com> */ #include <linux/module.h> #include <linux/init.h> @@ -19,22 +24,53 @@ #include <xen/events.h> #include <asm/xen/pci.h> +static int xen_pcifront_enable_irq(struct pci_dev *dev) +{ + int rc; + int share = 1; + int pirq; + u8 gsi; + + rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", + rc); + return rc; + } + /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ + pirq = gsi; + + if (gsi < NR_IRQS_LEGACY) + share = 0; + + rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront"); + if (rc < 0) { + dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n", + gsi, pirq, rc); + return rc; + } + + dev->irq = rc; + dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq); + return 0; +} + #ifdef CONFIG_ACPI -static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, - int trigger, int polarity) +static int xen_register_pirq(u32 gsi, int gsi_override, int triggering, + bool set_pirq) { - int rc, irq; + int rc, pirq = -1, irq = -1; struct physdev_map_pirq map_irq; int shareable = 0; char *name; - if (!xen_hvm_domain()) - return -1; + if (set_pirq) + pirq = gsi; map_irq.domid = DOMID_SELF; map_irq.type = MAP_PIRQ_TYPE_GSI; map_irq.index = gsi; - map_irq.pirq = -1; + map_irq.pirq = pirq; rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); if (rc) { @@ -42,7 +78,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, return -1; } - if (trigger == ACPI_EDGE_SENSITIVE) { + if (triggering == ACPI_EDGE_SENSITIVE) { shareable = 0; name = "ioapic-edge"; } else { @@ -50,12 +86,63 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, name = "ioapic-level"; } + if (gsi_override >= 0) + gsi = gsi_override; + irq = xen_bind_pirq_gsi_to_irq(gsi, map_irq.pirq, shareable, name); + if (irq < 0) + goto out; - printk(KERN_DEBUG "xen: --> irq=%d, pirq=%d\n", irq, map_irq.pirq); + printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d (gsi=%d)\n", map_irq.pirq, irq, gsi); +out: + return irq; +} + +static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, + int trigger, int polarity) +{ + if (!xen_hvm_domain()) + return -1; + + return xen_register_pirq(gsi, -1 /* no GSI override */, trigger, + false /* no mapping of GSI to PIRQ */); +} + +#ifdef CONFIG_XEN_DOM0 +static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polarity) +{ + int rc, irq; + struct physdev_setup_gsi setup_gsi; + + if (!xen_pv_domain()) + return -1; + + printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n", + gsi, triggering, polarity); + + irq = xen_register_pirq(gsi, gsi_override, triggering, true); + + setup_gsi.gsi = gsi; + setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1); + setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); + + rc = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); + if (rc == -EEXIST) + printk(KERN_INFO "Already setup the GSI :%d\n", gsi); + else if (rc) { + printk(KERN_ERR "Failed to setup GSI :%d, err_code:%d\n", + gsi, rc); + } return irq; } + +static int acpi_register_gsi_xen(struct device *dev, u32 gsi, + int trigger, int polarity) +{ + return xen_register_gsi(gsi, -1 /* no GSI override */, trigger, polarity); +} +#endif #endif #if defined(CONFIG_PCI_MSI) @@ -65,6 +152,43 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi, struct xen_pci_frontend_ops *xen_pci_frontend; EXPORT_SYMBOL_GPL(xen_pci_frontend); +static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + int irq, ret, i; + struct msi_desc *msidesc; + int *v; + + v = kzalloc(sizeof(int) * max(1, nvec), GFP_KERNEL); + if (!v) + return -ENOMEM; + + if (type == PCI_CAP_ID_MSIX) + ret = xen_pci_frontend_enable_msix(dev, v, nvec); + else + ret = xen_pci_frontend_enable_msi(dev, v); + if (ret) + goto error; + i = 0; + list_for_each_entry(msidesc, &dev->msi_list, list) { + irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, + (type == PCI_CAP_ID_MSIX) ? + "pcifront-msi-x" : + "pcifront-msi", + DOMID_SELF); + if (irq < 0) + goto free; + i++; + } + kfree(v); + return 0; + +error: + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); +free: + kfree(v); + return ret; +} + #define XEN_PIRQ_MSI_DATA (MSI_DATA_TRIGGER_EDGE | \ MSI_DATA_LEVEL_ASSERT | (3 << 8) | MSI_DATA_VECTOR(0)) @@ -123,67 +247,6 @@ error: return -ENODEV; } -/* - * For MSI interrupts we have to use drivers/xen/event.s functions to - * allocate an irq_desc and setup the right */ - - -static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - int irq, ret, i; - struct msi_desc *msidesc; - int *v; - - v = kzalloc(sizeof(int) * max(1, nvec), GFP_KERNEL); - if (!v) - return -ENOMEM; - - if (type == PCI_CAP_ID_MSIX) - ret = xen_pci_frontend_enable_msix(dev, v, nvec); - else - ret = xen_pci_frontend_enable_msi(dev, v); - if (ret) - goto error; - i = 0; - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], 0, - (type == PCI_CAP_ID_MSIX) ? - "pcifront-msi-x" : - "pcifront-msi", - DOMID_SELF); - if (irq < 0) - goto free; - i++; - } - kfree(v); - return 0; - -error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); -free: - kfree(v); - return ret; -} - -static void xen_teardown_msi_irqs(struct pci_dev *dev) -{ - struct msi_desc *msidesc; - - msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); - if (msidesc->msi_attrib.is_msix) - xen_pci_frontend_disable_msix(dev); - else - xen_pci_frontend_disable_msi(dev); - - /* Free the IRQ's and the msidesc using the generic code. */ - default_teardown_msi_irqs(dev); -} - -static void xen_teardown_msi_irq(unsigned int irq) -{ - xen_destroy_irq(irq); -} - #ifdef CONFIG_XEN_DOM0 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { @@ -242,45 +305,28 @@ out: return ret; } #endif -#endif -static int xen_pcifront_enable_irq(struct pci_dev *dev) +static void xen_teardown_msi_irqs(struct pci_dev *dev) { - int rc; - int share = 1; - int pirq; - u8 gsi; - - rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", - rc); - return rc; - } - - rc = xen_allocate_pirq_gsi(gsi); - if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI: failed to allocate a PIRQ for GSI%d: %d\n", - gsi, rc); - return rc; - } - pirq = rc; + struct msi_desc *msidesc; - if (gsi < NR_IRQS_LEGACY) - share = 0; + msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + if (msidesc->msi_attrib.is_msix) + xen_pci_frontend_disable_msix(dev); + else + xen_pci_frontend_disable_msi(dev); - rc = xen_bind_pirq_gsi_to_irq(gsi, pirq, share, "pcifront"); - if (rc < 0) { - dev_warn(&dev->dev, "Xen PCI: failed to bind GSI%d (PIRQ%d) to IRQ: %d\n", - gsi, pirq, rc); - return rc; - } + /* Free the IRQ's and the msidesc using the generic code. */ + default_teardown_msi_irqs(dev); +} - dev->irq = rc; - dev_info(&dev->dev, "Xen PCI mapped GSI%d to IRQ%d\n", gsi, dev->irq); - return 0; +static void xen_teardown_msi_irq(unsigned int irq) +{ + xen_destroy_irq(irq); } +#endif + int __init pci_xen_init(void) { if (!xen_pv_domain() || xen_initial_domain()) @@ -327,82 +373,13 @@ int __init pci_xen_hvm_init(void) } #ifdef CONFIG_XEN_DOM0 -static int xen_register_pirq(u32 gsi, int triggering) -{ - int rc, pirq, irq = -1; - struct physdev_map_pirq map_irq; - int shareable = 0; - char *name; - - if (!xen_pv_domain()) - return -1; - - if (triggering == ACPI_EDGE_SENSITIVE) { - shareable = 0; - name = "ioapic-edge"; - } else { - shareable = 1; - name = "ioapic-level"; - } - - pirq = xen_allocate_pirq_gsi(gsi); - if (pirq < 0) - goto out; - - irq = xen_bind_pirq_gsi_to_irq(gsi, pirq, shareable, name); - if (irq < 0) - goto out; - - printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d\n", pirq, irq); - - map_irq.domid = DOMID_SELF; - map_irq.type = MAP_PIRQ_TYPE_GSI; - map_irq.index = gsi; - map_irq.pirq = pirq; - - rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); - if (rc) { - printk(KERN_WARNING "xen map irq failed %d\n", rc); - return -1; - } - -out: - return irq; -} - -static int xen_register_gsi(u32 gsi, int triggering, int polarity) -{ - int rc, irq; - struct physdev_setup_gsi setup_gsi; - - if (!xen_pv_domain()) - return -1; - - printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n", - gsi, triggering, polarity); - - irq = xen_register_pirq(gsi, triggering); - - setup_gsi.gsi = gsi; - setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1); - setup_gsi.polarity = (polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - - rc = HYPERVISOR_physdev_op(PHYSDEVOP_setup_gsi, &setup_gsi); - if (rc == -EEXIST) - printk(KERN_INFO "Already setup the GSI :%d\n", gsi); - else if (rc) { - printk(KERN_ERR "Failed to setup GSI :%d, err_code:%d\n", - gsi, rc); - } - - return irq; -} - static __init void xen_setup_acpi_sci(void) { int rc; int trigger, polarity; int gsi = acpi_sci_override_gsi; + int irq = -1; + int gsi_override = -1; if (!gsi) return; @@ -415,51 +392,43 @@ static __init void xen_setup_acpi_sci(void) } trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE; polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH; - + printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d " "polarity=%d\n", gsi, trigger, polarity); - gsi = xen_register_gsi(gsi, trigger, polarity); + /* Before we bind the GSI to a Linux IRQ, check whether + * we need to override it with bus_irq (IRQ) value. Usually for + * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so: + * ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level) + * but there are oddballs where the IRQ != GSI: + * ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level) + * which ends up being: gsi_to_irq[9] == 20 + * (which is what acpi_gsi_to_irq ends up calling when starting the + * the ACPI interpreter and keels over since IRQ 9 has not been + * setup as we had setup IRQ 20 for it). + */ + if (acpi_gsi_to_irq(gsi, &irq) == 0) { + /* Use the provided value if it's valid. */ + if (irq >= 0) + gsi_override = irq; + } + + gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity); printk(KERN_INFO "xen: acpi sci %d\n", gsi); return; } -static int acpi_register_gsi_xen(struct device *dev, u32 gsi, - int trigger, int polarity) +int __init pci_xen_initial_domain(void) { - return xen_register_gsi(gsi, trigger, polarity); -} + int irq; -static int __init pci_xen_initial_domain(void) -{ #ifdef CONFIG_PCI_MSI x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; - - return 0; -} - -void __init xen_setup_pirqs(void) -{ - int pirq, irq; - - pci_xen_initial_domain(); - - if (0 == nr_ioapics) { - for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { - pirq = xen_allocate_pirq_gsi(irq); - if (WARN(pirq < 0, - "Could not allocate PIRQ for legacy interrupt\n")) - break; - irq = xen_bind_pirq_gsi_to_irq(irq, pirq, 0, "xt-pic"); - } - return; - } - /* Pre-allocate legacy irqs */ for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { int trigger, polarity; @@ -467,13 +436,17 @@ void __init xen_setup_pirqs(void) if (acpi_get_override_irq(irq, &trigger, &polarity) == -1) continue; - xen_register_pirq(irq, - trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE); + xen_register_pirq(irq, -1 /* no GSI override */, + trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE, + true /* Map GSI to PIRQ */); } + if (0 == nr_ioapics) { + for (irq = 0; irq < NR_IRQS_LEGACY; irq++) + xen_bind_pirq_gsi_to_irq(irq, irq, 0, "xt-pic"); + } + return 0; } -#endif -#ifdef CONFIG_XEN_DOM0 struct xen_device_domain_owner { domid_t domain; struct pci_dev *dev; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 474356b..899e393 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -504,9 +504,6 @@ void __init efi_init(void) x86_platform.set_wallclock = efi_set_rtc_mmss; #endif - /* Setup for EFI runtime service */ - reboot_type = BOOT_EFI; - #if EFI_DEBUG print_efi_memmap(); #endif diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 673e968..0ccccb6 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1232,7 +1232,11 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; +#ifdef CONFIG_SMP DECLARE_BITMAP(mask, num_processors); +#else + DECLARE_BITMAP(mask, NR_CPUS); +#endif } *args; struct multicall_space mcs; diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c index 25c52f9..ffcf261 100644 --- a/arch/x86/xen/platform-pci-unplug.c +++ b/arch/x86/xen/platform-pci-unplug.c @@ -35,7 +35,7 @@ EXPORT_SYMBOL_GPL(xen_platform_pci_unplug); #ifdef CONFIG_XEN_PVHVM static int xen_emul_unplug; -static int __init check_platform_magic(void) +static int check_platform_magic(void) { short magic; char protocol; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a62be8d..3689f83 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -927,7 +927,7 @@ static int throtl_dispatch(struct request_queue *q) bio_list_init(&bio_list_on_stack); - throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u", + throtl_log(td, "dispatch nr_queued=%d read=%u write=%u", total_nr_queued(td), td->nr_queued[READ], td->nr_queued[WRITE]); @@ -1204,7 +1204,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop) } queue_bio: - throtl_log_tg(td, tg, "[%c] bio. bdisp=%u sz=%u bps=%llu" + throtl_log_tg(td, tg, "[%c] bio. bdisp=%llu sz=%u bps=%llu" " iodisp=%u iops=%u queued=%d/%d", rw == READ ? 'R' : 'W', tg->bytes_disp[rw], bio->bi_size, tg->bps[rw], diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 3c7b537..ae21919 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -988,9 +988,10 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg, cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime, st->min_vdisktime); - cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u" - " sect=%u", used_sl, cfqq->slice_dispatch, charge, - iops_mode(cfqd), cfqq->nr_sectors); + cfq_log_cfqq(cfqq->cfqd, cfqq, + "sl_used=%u disp=%u charge=%u iops=%u sect=%lu", + used_sl, cfqq->slice_dispatch, charge, + iops_mode(cfqd), cfqq->nr_sectors); cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl, unaccounted_sl); cfq_blkiocg_set_start_empty_time(&cfqg->blkg); @@ -2023,8 +2024,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) */ if (sample_valid(cic->ttime_samples) && (cfqq->slice_end - jiffies < cic->ttime_mean)) { - cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d", - cic->ttime_mean); + cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%lu", + cic->ttime_mean); return; } @@ -2772,8 +2773,14 @@ static void __cfq_exit_single_io_context(struct cfq_data *cfqd, smp_wmb(); cic->key = cfqd_dead_key(cfqd); - if (ioc->ioc_data == cic) + rcu_read_lock(); + if (rcu_dereference(ioc->ioc_data) == cic) { + rcu_read_unlock(); + spin_lock(&ioc->lock); rcu_assign_pointer(ioc->ioc_data, NULL); + spin_unlock(&ioc->lock); + } else + rcu_read_unlock(); if (cic->cfqq[BLK_RW_ASYNC]) { cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]); @@ -3080,7 +3087,8 @@ cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc, spin_lock_irqsave(&ioc->lock, flags); - BUG_ON(ioc->ioc_data == cic); + BUG_ON(rcu_dereference_check(ioc->ioc_data, + lockdep_is_held(&ioc->lock)) == cic); radix_tree_delete(&ioc->radix_root, cfqd->cic_index); hlist_del_rcu(&cic->cic_list); diff --git a/block/genhd.c b/block/genhd.c index 95822ae..3608289 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1371,6 +1371,7 @@ struct disk_events { struct gendisk *disk; /* the associated disk */ spinlock_t lock; + struct mutex block_mutex; /* protects blocking */ int block; /* event blocking depth */ unsigned int pending; /* events already sent out */ unsigned int clearing; /* events being cleared */ @@ -1414,22 +1415,44 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk) return msecs_to_jiffies(intv_msecs); } -static void __disk_block_events(struct gendisk *disk, bool sync) +/** + * disk_block_events - block and flush disk event checking + * @disk: disk to block events for + * + * On return from this function, it is guaranteed that event checking + * isn't in progress and won't happen until unblocked by + * disk_unblock_events(). Events blocking is counted and the actual + * unblocking happens after the matching number of unblocks are done. + * + * Note that this intentionally does not block event checking from + * disk_clear_events(). + * + * CONTEXT: + * Might sleep. + */ +void disk_block_events(struct gendisk *disk) { struct disk_events *ev = disk->ev; unsigned long flags; bool cancel; + if (!ev) + return; + + /* + * Outer mutex ensures that the first blocker completes canceling + * the event work before further blockers are allowed to finish. + */ + mutex_lock(&ev->block_mutex); + spin_lock_irqsave(&ev->lock, flags); cancel = !ev->block++; spin_unlock_irqrestore(&ev->lock, flags); - if (cancel) { - if (sync) - cancel_delayed_work_sync(&disk->ev->dwork); - else - cancel_delayed_work(&disk->ev->dwork); - } + if (cancel) + cancel_delayed_work_sync(&disk->ev->dwork); + + mutex_unlock(&ev->block_mutex); } static void __disk_unblock_events(struct gendisk *disk, bool check_now) @@ -1461,27 +1484,6 @@ out_unlock: } /** - * disk_block_events - block and flush disk event checking - * @disk: disk to block events for - * - * On return from this function, it is guaranteed that event checking - * isn't in progress and won't happen until unblocked by - * disk_unblock_events(). Events blocking is counted and the actual - * unblocking happens after the matching number of unblocks are done. - * - * Note that this intentionally does not block event checking from - * disk_clear_events(). - * - * CONTEXT: - * Might sleep. - */ -void disk_block_events(struct gendisk *disk) -{ - if (disk->ev) - __disk_block_events(disk, true); -} - -/** * disk_unblock_events - unblock disk event checking * @disk: disk to unblock events for * @@ -1508,10 +1510,18 @@ void disk_unblock_events(struct gendisk *disk) */ void disk_check_events(struct gendisk *disk) { - if (disk->ev) { - __disk_block_events(disk, false); - __disk_unblock_events(disk, true); + struct disk_events *ev = disk->ev; + unsigned long flags; + + if (!ev) + return; + + spin_lock_irqsave(&ev->lock, flags); + if (!ev->block) { + cancel_delayed_work(&ev->dwork); + queue_delayed_work(system_nrt_wq, &ev->dwork, 0); } + spin_unlock_irqrestore(&ev->lock, flags); } EXPORT_SYMBOL_GPL(disk_check_events); @@ -1546,7 +1556,7 @@ unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) spin_unlock_irq(&ev->lock); /* uncondtionally schedule event check and wait for it to finish */ - __disk_block_events(disk, true); + disk_block_events(disk); queue_delayed_work(system_nrt_wq, &ev->dwork, 0); flush_delayed_work(&ev->dwork); __disk_unblock_events(disk, false); @@ -1664,7 +1674,7 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev, if (intv < 0 && intv != -1) return -EINVAL; - __disk_block_events(disk, true); + disk_block_events(disk); disk->ev->poll_msecs = intv; __disk_unblock_events(disk, true); @@ -1750,6 +1760,7 @@ static void disk_add_events(struct gendisk *disk) INIT_LIST_HEAD(&ev->node); ev->disk = disk; spin_lock_init(&ev->lock); + mutex_init(&ev->block_mutex); ev->block = 1; ev->poll_msecs = -1; INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); @@ -1770,7 +1781,7 @@ static void disk_del_events(struct gendisk *disk) if (!disk->ev) return; - __disk_block_events(disk, true); + disk_block_events(disk); mutex_lock(&disk_events_mutex); list_del_init(&disk->ev->node); diff --git a/crypto/deflate.c b/crypto/deflate.c index b5ccae2..b0165ec 100644 --- a/crypto/deflate.c +++ b/crypto/deflate.c @@ -32,7 +32,6 @@ #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/net.h> -#include <linux/slab.h> #define DEFLATE_DEF_LEVEL Z_DEFAULT_COMPRESSION #define DEFLATE_DEF_WINBITS 11 @@ -73,7 +72,7 @@ static int deflate_decomp_init(struct deflate_ctx *ctx) int ret = 0; struct z_stream_s *stream = &ctx->decomp_stream; - stream->workspace = kzalloc(zlib_inflate_workspacesize(), GFP_KERNEL); + stream->workspace = vzalloc(zlib_inflate_workspacesize()); if (!stream->workspace) { ret = -ENOMEM; goto out; @@ -86,7 +85,7 @@ static int deflate_decomp_init(struct deflate_ctx *ctx) out: return ret; out_free: - kfree(stream->workspace); + vfree(stream->workspace); goto out; } @@ -99,7 +98,7 @@ static void deflate_comp_exit(struct deflate_ctx *ctx) static void deflate_decomp_exit(struct deflate_ctx *ctx) { zlib_inflateEnd(&ctx->decomp_stream); - kfree(ctx->decomp_stream.workspace); + vfree(ctx->decomp_stream.workspace); } static int deflate_init(struct crypto_tfm *tfm) diff --git a/crypto/zlib.c b/crypto/zlib.c index d11d761..06b62e5 100644 --- a/crypto/zlib.c +++ b/crypto/zlib.c @@ -29,7 +29,6 @@ #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/net.h> -#include <linux/slab.h> #include <crypto/internal/compress.h> @@ -60,7 +59,7 @@ static void zlib_decomp_exit(struct zlib_ctx *ctx) if (stream->workspace) { zlib_inflateEnd(stream); - kfree(stream->workspace); + vfree(stream->workspace); stream->workspace = NULL; } } @@ -228,13 +227,13 @@ static int zlib_decompress_setup(struct crypto_pcomp *tfm, void *params, ? nla_get_u32(tb[ZLIB_DECOMP_WINDOWBITS]) : DEF_WBITS; - stream->workspace = kzalloc(zlib_inflate_workspacesize(), GFP_KERNEL); + stream->workspace = vzalloc(zlib_inflate_workspacesize()); if (!stream->workspace) return -ENOMEM; ret = zlib_inflateInit2(stream, ctx->decomp_windowBits); if (ret != Z_OK) { - kfree(stream->workspace); + vfree(stream->workspace); stream->workspace = NULL; return -EINVAL; } diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c index abda378..181bc2f 100644 --- a/drivers/acpi/apei/hest.c +++ b/drivers/acpi/apei/hest.c @@ -139,13 +139,23 @@ static int __init hest_parse_ghes(struct acpi_hest_header *hest_hdr, void *data) { struct platform_device *ghes_dev; struct ghes_arr *ghes_arr = data; - int rc; + int rc, i; if (hest_hdr->type != ACPI_HEST_TYPE_GENERIC_ERROR) return 0; if (!((struct acpi_hest_generic *)hest_hdr)->enabled) return 0; + for (i = 0; i < ghes_arr->count; i++) { + struct acpi_hest_header *hdr; + ghes_dev = ghes_arr->ghes_devs[i]; + hdr = *(struct acpi_hest_header **)ghes_dev->dev.platform_data; + if (hdr->source_id == hest_hdr->source_id) { + pr_warning(FW_WARN HEST_PFX "Duplicated hardware error source ID: %d.\n", + hdr->source_id); + return -EIO; + } + } ghes_dev = platform_device_alloc("GHES", hest_hdr->source_id); if (!ghes_dev) return -ENOMEM; diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 52ca964..372f9b7 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -1333,23 +1333,6 @@ int acpi_resources_are_enforced(void) EXPORT_SYMBOL(acpi_resources_are_enforced); /* - * Create and initialize a spinlock. - */ -acpi_status -acpi_os_create_lock(acpi_spinlock *out_handle) -{ - spinlock_t *lock; - - lock = ACPI_ALLOCATE(sizeof(spinlock_t)); - if (!lock) - return AE_NO_MEMORY; - spin_lock_init(lock); - *out_handle = lock; - - return AE_OK; -} - -/* * Deallocate the memory for a spinlock. */ void acpi_os_delete_lock(acpi_spinlock handle) diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index d38c40f..41223c7 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -452,7 +452,7 @@ void ahci_save_initial_config(struct device *dev, } if (mask_port_map) { - dev_printk(KERN_ERR, dev, "masking port_map 0x%x -> 0x%x\n", + dev_printk(KERN_WARNING, dev, "masking port_map 0x%x -> 0x%x\n", port_map, port_map & mask_port_map); port_map &= mask_port_map; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 736bee5..000d03a 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4143,9 +4143,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { * Devices which choke on SETXFER. Applies only if both the * device and controller are SATA. */ - { "PIONEER DVD-RW DVRTD08", "1.00", ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-212D", "1.28", ATA_HORKAGE_NOSETXFER }, - { "PIONEER DVD-RW DVR-216D", "1.08", ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVRTD08", NULL, ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, + { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* End Marker */ { } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index d51f979..927f968 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3797,6 +3797,12 @@ EXPORT_SYMBOL_GPL(ata_sas_port_alloc); */ int ata_sas_port_start(struct ata_port *ap) { + /* + * the port is marked as frozen at allocation time, but if we don't + * have new eh, we won't thaw it + */ + if (!ap->ops->error_handler) + ap->pflags &= ~ATA_PFLAG_FROZEN; return 0; } EXPORT_SYMBOL_GPL(ata_sas_port_start); diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c index 75a6a0c..5d7f58a 100644 --- a/drivers/ata/pata_marvell.c +++ b/drivers/ata/pata_marvell.c @@ -161,6 +161,9 @@ static const struct pci_device_id marvell_pci_tbl[] = { { PCI_DEVICE(0x11AB, 0x6121), }, { PCI_DEVICE(0x11AB, 0x6123), }, { PCI_DEVICE(0x11AB, 0x6145), }, + { PCI_DEVICE(0x1B4B, 0x91A0), }, + { PCI_DEVICE(0x1B4B, 0x91A4), }, + { } /* terminate list */ }; diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 1c4b3aa..dc88a39 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -389,7 +389,7 @@ static void sata_dwc_tf_dump(struct ata_taskfile *tf) /* * Function: get_burst_length_encode * arguments: datalength: length in bytes of data - * returns value to be programmed in register corrresponding to data length + * returns value to be programmed in register corresponding to data length * This value is effectively the log(base 2) of the length */ static int get_burst_length_encode(int datalength) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 9f9b235..45d7c8f 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -30,7 +30,6 @@ static DEFINE_MUTEX(mem_sysfs_mutex); #define MEMORY_CLASS_NAME "memory" -#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) static int sections_per_block; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1c291af..6040717 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -367,7 +367,7 @@ EXPORT_SYMBOL_GPL(platform_device_unregister); * * Returns &struct platform_device pointer on success, or ERR_PTR() on error. */ -struct platform_device *__init_or_module platform_device_register_resndata( +struct platform_device *platform_device_register_resndata( struct device *parent, const char *name, int id, const struct resource *res, unsigned int num, diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index eaa8a85..ad367c4 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -387,7 +387,7 @@ static int pm_runtime_clk_notify(struct notifier_block *nb, clknb = container_of(nb, struct pm_clk_notifier_block, nb); switch (action) { - case BUS_NOTIFY_ADD_DEVICE: + case BUS_NOTIFY_BIND_DRIVER: if (clknb->con_ids[0]) { for (con_id = clknb->con_ids; *con_id; con_id++) enable_clock(dev, *con_id); @@ -395,7 +395,7 @@ static int pm_runtime_clk_notify(struct notifier_block *nb, enable_clock(dev, NULL); } break; - case BUS_NOTIFY_DEL_DEVICE: + case BUS_NOTIFY_UNBOUND_DRIVER: if (clknb->con_ids[0]) { for (con_id = clknb->con_ids; *con_id; con_id++) disable_clock(dev, *con_id); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index aa632020..06f09bf 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -57,7 +57,8 @@ static int async_error; */ void device_pm_init(struct device *dev) { - dev->power.in_suspend = false; + dev->power.is_prepared = false; + dev->power.is_suspended = false; init_completion(&dev->power.completion); complete_all(&dev->power.completion); dev->power.wakeup = NULL; @@ -91,7 +92,7 @@ void device_pm_add(struct device *dev) pr_debug("PM: Adding info for %s:%s\n", dev->bus ? dev->bus->name : "No Bus", dev_name(dev)); mutex_lock(&dpm_list_mtx); - if (dev->parent && dev->parent->power.in_suspend) + if (dev->parent && dev->parent->power.is_prepared) dev_warn(dev, "parent %s should not be sleeping\n", dev_name(dev->parent)); list_add_tail(&dev->power.entry, &dpm_list); @@ -511,7 +512,14 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) dpm_wait(dev->parent, async); device_lock(dev); - dev->power.in_suspend = false; + /* + * This is a fib. But we'll allow new children to be added below + * a resumed device, even if the device hasn't been completed yet. + */ + dev->power.is_prepared = false; + + if (!dev->power.is_suspended) + goto Unlock; if (dev->pwr_domain) { pm_dev_dbg(dev, state, "power domain "); @@ -548,6 +556,9 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) } End: + dev->power.is_suspended = false; + + Unlock: device_unlock(dev); complete_all(&dev->power.completion); @@ -670,7 +681,7 @@ void dpm_complete(pm_message_t state) struct device *dev = to_device(dpm_prepared_list.prev); get_device(dev); - dev->power.in_suspend = false; + dev->power.is_prepared = false; list_move(&dev->power.entry, &list); mutex_unlock(&dpm_list_mtx); @@ -835,11 +846,11 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) device_lock(dev); if (async_error) - goto End; + goto Unlock; if (pm_wakeup_pending()) { async_error = -EBUSY; - goto End; + goto Unlock; } if (dev->pwr_domain) { @@ -877,6 +888,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) } End: + dev->power.is_suspended = !error; + + Unlock: device_unlock(dev); complete_all(&dev->power.completion); @@ -1042,7 +1056,7 @@ int dpm_prepare(pm_message_t state) put_device(dev); break; } - dev->power.in_suspend = true; + dev->power.is_prepared = true; if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); put_device(dev); diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c index c126db3..e8d11b6 100644 --- a/drivers/base/syscore.c +++ b/drivers/base/syscore.c @@ -9,6 +9,7 @@ #include <linux/syscore_ops.h> #include <linux/mutex.h> #include <linux/module.h> +#include <linux/interrupt.h> static LIST_HEAD(syscore_ops_list); static DEFINE_MUTEX(syscore_ops_lock); @@ -48,6 +49,13 @@ int syscore_suspend(void) struct syscore_ops *ops; int ret = 0; + pr_debug("Checking wakeup interrupts\n"); + + /* Return error code if there are any wakeup interrupts pending. */ + ret = check_wakeup_irqs(); + if (ret) + return ret; + WARN_ONCE(!irqs_disabled(), "Interrupts enabled before system core suspend.\n"); diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index 09ef9a8..cf0e63d 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -79,7 +79,7 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev, md_io.error = 0; if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags)) - rw |= REQ_FUA; + rw |= REQ_FUA | REQ_FLUSH; rw |= REQ_SYNC; bio = bio_alloc(GFP_NOIO, 1); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index f440a02..7b97629 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -112,9 +112,6 @@ struct drbd_bitmap { struct task_struct *bm_task; }; -static int __bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, - unsigned long e, int val, const enum km_type km); - #define bm_print_lock_info(m) __bm_print_lock_info(m, __func__) static void __bm_print_lock_info(struct drbd_conf *mdev, const char *func) { @@ -994,6 +991,9 @@ static void bm_page_io_async(struct bm_aio_ctx *ctx, int page_nr, int rw) __must bio_endio(bio, -EIO); } else { submit_bio(rw, bio); + /* this should not count as user activity and cause the + * resync to throttle -- see drbd_rs_should_slow_down(). */ + atomic_add(len >> 9, &mdev->rs_sect_ev); } } @@ -1256,7 +1256,7 @@ unsigned long _drbd_bm_find_next_zero(struct drbd_conf *mdev, unsigned long bm_f * expected to be called for only a few bits (e - s about BITS_PER_LONG). * Must hold bitmap lock already. */ static int __bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, - unsigned long e, int val, const enum km_type km) + unsigned long e, int val) { struct drbd_bitmap *b = mdev->bitmap; unsigned long *p_addr = NULL; @@ -1274,14 +1274,14 @@ static int __bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, unsigned int page_nr = bm_bit_to_page_idx(b, bitnr); if (page_nr != last_page_nr) { if (p_addr) - __bm_unmap(p_addr, km); + __bm_unmap(p_addr, KM_IRQ1); if (c < 0) bm_set_page_lazy_writeout(b->bm_pages[last_page_nr]); else if (c > 0) bm_set_page_need_writeout(b->bm_pages[last_page_nr]); changed_total += c; c = 0; - p_addr = __bm_map_pidx(b, page_nr, km); + p_addr = __bm_map_pidx(b, page_nr, KM_IRQ1); last_page_nr = page_nr; } if (val) @@ -1290,7 +1290,7 @@ static int __bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, c -= (0 != __test_and_clear_bit_le(bitnr & BITS_PER_PAGE_MASK, p_addr)); } if (p_addr) - __bm_unmap(p_addr, km); + __bm_unmap(p_addr, KM_IRQ1); if (c < 0) bm_set_page_lazy_writeout(b->bm_pages[last_page_nr]); else if (c > 0) @@ -1318,7 +1318,7 @@ static int bm_change_bits_to(struct drbd_conf *mdev, const unsigned long s, if ((val ? BM_DONT_SET : BM_DONT_CLEAR) & b->bm_flags) bm_print_lock_info(mdev); - c = __bm_change_bits_to(mdev, s, e, val, KM_IRQ1); + c = __bm_change_bits_to(mdev, s, e, val); spin_unlock_irqrestore(&b->bm_lock, flags); return c; @@ -1343,16 +1343,17 @@ static inline void bm_set_full_words_within_one_page(struct drbd_bitmap *b, { int i; int bits; - unsigned long *paddr = kmap_atomic(b->bm_pages[page_nr], KM_USER0); + unsigned long *paddr = kmap_atomic(b->bm_pages[page_nr], KM_IRQ1); for (i = first_word; i < last_word; i++) { bits = hweight_long(paddr[i]); paddr[i] = ~0UL; b->bm_set += BITS_PER_LONG - bits; } - kunmap_atomic(paddr, KM_USER0); + kunmap_atomic(paddr, KM_IRQ1); } -/* Same thing as drbd_bm_set_bits, but without taking the spin_lock_irqsave. +/* Same thing as drbd_bm_set_bits, + * but more efficient for a large bit range. * You must first drbd_bm_lock(). * Can be called to set the whole bitmap in one go. * Sets bits from s to e _inclusive_. */ @@ -1366,6 +1367,7 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi * Do not use memset, because we must account for changes, * so we need to loop over the words with hweight() anyways. */ + struct drbd_bitmap *b = mdev->bitmap; unsigned long sl = ALIGN(s,BITS_PER_LONG); unsigned long el = (e+1) & ~((unsigned long)BITS_PER_LONG-1); int first_page; @@ -1376,15 +1378,19 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi if (e - s <= 3*BITS_PER_LONG) { /* don't bother; el and sl may even be wrong. */ - __bm_change_bits_to(mdev, s, e, 1, KM_USER0); + spin_lock_irq(&b->bm_lock); + __bm_change_bits_to(mdev, s, e, 1); + spin_unlock_irq(&b->bm_lock); return; } /* difference is large enough that we can trust sl and el */ + spin_lock_irq(&b->bm_lock); + /* bits filling the current long */ if (sl) - __bm_change_bits_to(mdev, s, sl-1, 1, KM_USER0); + __bm_change_bits_to(mdev, s, sl-1, 1); first_page = sl >> (3 + PAGE_SHIFT); last_page = el >> (3 + PAGE_SHIFT); @@ -1397,8 +1403,10 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi /* first and full pages, unless first page == last page */ for (page_nr = first_page; page_nr < last_page; page_nr++) { bm_set_full_words_within_one_page(mdev->bitmap, page_nr, first_word, last_word); + spin_unlock_irq(&b->bm_lock); cond_resched(); first_word = 0; + spin_lock_irq(&b->bm_lock); } /* last page (respectively only page, for first page == last page) */ @@ -1411,7 +1419,8 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi * it would trigger an assert in __bm_change_bits_to() */ if (el <= e) - __bm_change_bits_to(mdev, el, e, 1, KM_USER0); + __bm_change_bits_to(mdev, el, e, 1); + spin_unlock_irq(&b->bm_lock); } /* returns bit state diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 25d32c5..43beaca 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -4602,6 +4602,11 @@ int drbd_asender(struct drbd_thread *thi) dev_err(DEV, "meta connection shut down by peer.\n"); goto reconnect; } else if (rv == -EAGAIN) { + /* If the data socket received something meanwhile, + * that is good enough: peer is still alive. */ + if (time_after(mdev->last_received, + jiffies - mdev->meta.socket->sk->sk_rcvtimeo)) + continue; if (ping_timeout_active) { dev_err(DEV, "PingAck did not arrive in time.\n"); goto reconnect; @@ -4637,6 +4642,7 @@ int drbd_asender(struct drbd_thread *thi) goto reconnect; } if (received == expect) { + mdev->last_received = jiffies; D_ASSERT(cmd != NULL); if (!cmd->process(mdev, h)) goto reconnect; diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 4d76b06..4d3e6f6 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -536,12 +536,7 @@ static int w_make_resync_request(struct drbd_conf *mdev, return 1; } - /* starting with drbd 8.3.8, we can handle multi-bio EEs, - * if it should be necessary */ - max_bio_size = - mdev->agreed_pro_version < 94 ? queue_max_hw_sectors(mdev->rq_queue) << 9 : - mdev->agreed_pro_version < 95 ? DRBD_MAX_SIZE_H80_PACKET : DRBD_MAX_BIO_SIZE; - + max_bio_size = queue_max_hw_sectors(mdev->rq_queue) << 9; number = drbd_rs_number_requests(mdev); if (number == 0) goto requeue; diff --git a/drivers/char/agp/intel-agp.h b/drivers/char/agp/intel-agp.h index 999803c..5da67f1 100644 --- a/drivers/char/agp/intel-agp.h +++ b/drivers/char/agp/intel-agp.h @@ -90,9 +90,10 @@ #define G4x_GMCH_SIZE_MASK (0xf << 8) #define G4x_GMCH_SIZE_1M (0x1 << 8) #define G4x_GMCH_SIZE_2M (0x3 << 8) -#define G4x_GMCH_SIZE_VT_1M (0x9 << 8) -#define G4x_GMCH_SIZE_VT_1_5M (0xa << 8) -#define G4x_GMCH_SIZE_VT_2M (0xc << 8) +#define G4x_GMCH_SIZE_VT_EN (0x8 << 8) +#define G4x_GMCH_SIZE_VT_1M (G4x_GMCH_SIZE_1M | G4x_GMCH_SIZE_VT_EN) +#define G4x_GMCH_SIZE_VT_1_5M ((0x2 << 8) | G4x_GMCH_SIZE_VT_EN) +#define G4x_GMCH_SIZE_VT_2M (G4x_GMCH_SIZE_2M | G4x_GMCH_SIZE_VT_EN) #define GFX_FLSH_CNTL 0x2170 /* 915+ */ diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 219d88a..dde6a0f 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -139,6 +139,7 @@ static int cn_call_callback(struct sk_buff *skb) spin_unlock_bh(&dev->cbdev->queue_lock); if (cbq != NULL) { + err = 0; cbq->callback(msg, nsp); kfree_skb(skb); cn_queue_release_callback(cbq); diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 4e04e12..596d5dd 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -759,7 +759,7 @@ static void __exit acpi_cpufreq_exit(void) cpufreq_unregister_driver(&acpi_cpufreq_driver); - free_percpu(acpi_perf_data); + free_acpi_perf_data(); } module_param(acpi_pstate_strict, uint, 0644); diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index d0e65d6..676d957 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -238,9 +238,9 @@ static int build_sh_desc_ipsec(struct caam_ctx *ctx) /* build shared descriptor for this session */ sh_desc = kmalloc(CAAM_CMD_SZ * DESC_AEAD_SHARED_TEXT_LEN + - keys_fit_inline ? - ctx->split_key_pad_len + ctx->enckeylen : - CAAM_PTR_SZ * 2, GFP_DMA | GFP_KERNEL); + (keys_fit_inline ? + ctx->split_key_pad_len + ctx->enckeylen : + CAAM_PTR_SZ * 2), GFP_DMA | GFP_KERNEL); if (!sh_desc) { dev_err(jrdev, "could not allocate shared descriptor\n"); return -ENOMEM; diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 438e6c8..ebb8973 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -264,6 +264,7 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define PCI_DEVICE_ID_AGERE_FW643 0x5901 #define PCI_DEVICE_ID_JMICRON_JMB38X_FW 0x2380 #define PCI_DEVICE_ID_TI_TSB12LV22 0x8009 +#define PCI_VENDOR_ID_PINNACLE_SYSTEMS 0x11bd #define QUIRK_CYCLE_TIMER 1 #define QUIRK_RESET_PACKET 2 @@ -3190,6 +3191,11 @@ static int __devinit pci_probe(struct pci_dev *dev, int i, err; size_t size; + if (dev->vendor == PCI_VENDOR_ID_PINNACLE_SYSTEMS) { + dev_err(&dev->dev, "Pinnacle MovieBoard is not yet supported\n"); + return -ENOSYS; + } + ohci = kzalloc(sizeof(*ohci), GFP_KERNEL); if (ohci == NULL) { err = -ENOMEM; diff --git a/drivers/firmware/google/Kconfig b/drivers/firmware/google/Kconfig index 87096b6..2f21b0b 100644 --- a/drivers/firmware/google/Kconfig +++ b/drivers/firmware/google/Kconfig @@ -13,6 +13,7 @@ menu "Google Firmware Drivers" config GOOGLE_SMI tristate "SMI interface for Google platforms" depends on ACPI && DMI + select EFI select EFI_VARS help Say Y here if you want to enable SMI callbacks for Google diff --git a/drivers/gpio/langwell_gpio.c b/drivers/gpio/langwell_gpio.c index bd6571e..644ba12 100644 --- a/drivers/gpio/langwell_gpio.c +++ b/drivers/gpio/langwell_gpio.c @@ -223,7 +223,7 @@ static void lnw_irq_handler(unsigned irq, struct irq_desc *desc) gedr = gpio_reg(&lnw->chip, base, GEDR); pending = readl(gedr); while (pending) { - gpio = __ffs(pending) - 1; + gpio = __ffs(pending); mask = BIT(gpio); pending &= ~mask; /* Clear before handling so we can't lose an edge */ diff --git a/drivers/gpio/tps65910-gpio.c b/drivers/gpio/tps65910-gpio.c index 8d1ddfd..15097ca 100644 --- a/drivers/gpio/tps65910-gpio.c +++ b/drivers/gpio/tps65910-gpio.c @@ -81,8 +81,10 @@ void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base) switch(tps65910_chip_id(tps65910)) { case TPS65910: tps65910->gpio.ngpio = 6; + break; case TPS65911: tps65910->gpio.ngpio = 9; + break; default: return; } diff --git a/drivers/gpio/wm831x-gpio.c b/drivers/gpio/wm831x-gpio.c index 309644c..2bcfb0b 100644 --- a/drivers/gpio/wm831x-gpio.c +++ b/drivers/gpio/wm831x-gpio.c @@ -180,6 +180,7 @@ static void wm831x_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) break; case WM831X_GPIO_PULL_UP: pull = "pullup"; + break; default: pull = "INVALID PULL"; break; diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 21058e6..82db185 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -886,9 +886,6 @@ int drm_mode_group_init(struct drm_device *dev, struct drm_mode_group *group) total_objects += dev->mode_config.num_connector; total_objects += dev->mode_config.num_encoder; - if (total_objects == 0) - return -EINVAL; - group->id_list = kzalloc(total_objects * sizeof(uint32_t), GFP_KERNEL); if (!group->id_list) return -ENOMEM; diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 74e4ff5..4012fe4 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -34,6 +34,7 @@ #include <linux/module.h> #include <linux/mman.h> #include <linux/pagemap.h> +#include <linux/shmem_fs.h> #include "drmP.h" /** @file drm_gem.c diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 4d46441..0a893f7 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -1207,13 +1207,17 @@ static int i915_context_status(struct seq_file *m, void *unused) if (ret) return ret; - seq_printf(m, "power context "); - describe_obj(m, dev_priv->pwrctx); - seq_printf(m, "\n"); + if (dev_priv->pwrctx) { + seq_printf(m, "power context "); + describe_obj(m, dev_priv->pwrctx); + seq_printf(m, "\n"); + } - seq_printf(m, "render context "); - describe_obj(m, dev_priv->renderctx); - seq_printf(m, "\n"); + if (dev_priv->renderctx) { + seq_printf(m, "render context "); + describe_obj(m, dev_priv->renderctx); + seq_printf(m, "\n"); + } mutex_unlock(&dev->mode_config.mutex); diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 0239e99..296fbd6 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1266,30 +1266,6 @@ static int i915_load_modeset_init(struct drm_device *dev) intel_modeset_gem_init(dev); - if (IS_IVYBRIDGE(dev)) { - /* Share pre & uninstall handlers with ILK/SNB */ - dev->driver->irq_handler = ivybridge_irq_handler; - dev->driver->irq_preinstall = ironlake_irq_preinstall; - dev->driver->irq_postinstall = ivybridge_irq_postinstall; - dev->driver->irq_uninstall = ironlake_irq_uninstall; - dev->driver->enable_vblank = ivybridge_enable_vblank; - dev->driver->disable_vblank = ivybridge_disable_vblank; - } else if (HAS_PCH_SPLIT(dev)) { - dev->driver->irq_handler = ironlake_irq_handler; - dev->driver->irq_preinstall = ironlake_irq_preinstall; - dev->driver->irq_postinstall = ironlake_irq_postinstall; - dev->driver->irq_uninstall = ironlake_irq_uninstall; - dev->driver->enable_vblank = ironlake_enable_vblank; - dev->driver->disable_vblank = ironlake_disable_vblank; - } else { - dev->driver->irq_preinstall = i915_driver_irq_preinstall; - dev->driver->irq_postinstall = i915_driver_irq_postinstall; - dev->driver->irq_uninstall = i915_driver_irq_uninstall; - dev->driver->irq_handler = i915_driver_irq_handler; - dev->driver->enable_vblank = i915_enable_vblank; - dev->driver->disable_vblank = i915_disable_vblank; - } - ret = drm_irq_install(dev); if (ret) goto cleanup_gem; @@ -1967,7 +1943,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (!dev_priv->mm.gtt) { DRM_ERROR("Failed to initialize GTT\n"); ret = -ENODEV; - goto out_iomapfree; + goto out_rmmap; } agp_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT; @@ -2011,18 +1987,13 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (dev_priv->wq == NULL) { DRM_ERROR("Failed to create our workqueue.\n"); ret = -ENOMEM; - goto out_iomapfree; + goto out_mtrrfree; } /* enable GEM by default */ dev_priv->has_gem = 1; - dev->driver->get_vblank_counter = i915_get_vblank_counter; - dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */ - if (IS_G4X(dev) || IS_GEN5(dev) || IS_GEN6(dev) || IS_IVYBRIDGE(dev)) { - dev->max_vblank_count = 0xffffffff; /* full 32 bit counter */ - dev->driver->get_vblank_counter = gm45_get_vblank_counter; - } + intel_irq_init(dev); /* Try to make sure MCHBAR is enabled before poking at it */ intel_setup_mchbar(dev); @@ -2103,13 +2074,21 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) return 0; out_gem_unload: + if (dev_priv->mm.inactive_shrinker.shrink) + unregister_shrinker(&dev_priv->mm.inactive_shrinker); + if (dev->pdev->msi_enabled) pci_disable_msi(dev->pdev); intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); destroy_workqueue(dev_priv->wq); -out_iomapfree: +out_mtrrfree: + if (dev_priv->mm.gtt_mtrr >= 0) { + mtrr_del(dev_priv->mm.gtt_mtrr, dev->agp->base, + dev->agp->agp_info.aper_size * 1024 * 1024); + dev_priv->mm.gtt_mtrr = -1; + } io_mapping_free(dev_priv->mm.gtt_mapping); out_rmmap: pci_iounmap(dev->pdev, dev_priv->regs); @@ -2182,9 +2161,8 @@ int i915_driver_unload(struct drm_device *dev) /* Flush any outstanding unpin_work. */ flush_workqueue(dev_priv->wq); - i915_gem_free_all_phys_object(dev); - mutex_lock(&dev->struct_mutex); + i915_gem_free_all_phys_object(dev); i915_gem_cleanup_ringbuffer(dev); mutex_unlock(&dev->struct_mutex); if (I915_HAS_FBC(dev) && i915_powersave) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 0defd42..eb91e2d 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -52,7 +52,7 @@ module_param_named(powersave, i915_powersave, int, 0600); unsigned int i915_semaphores = 0; module_param_named(semaphores, i915_semaphores, int, 0600); -unsigned int i915_enable_rc6 = 1; +unsigned int i915_enable_rc6 = 0; module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600); unsigned int i915_enable_fbc = 0; @@ -577,8 +577,12 @@ int i915_reset(struct drm_device *dev, u8 flags) if (get_seconds() - dev_priv->last_gpu_reset < 5) { DRM_ERROR("GPU hanging too fast, declaring wedged!\n"); } else switch (INTEL_INFO(dev)->gen) { + case 7: case 6: ret = gen6_do_reset(dev, flags); + /* If reset with a user forcewake, try to restore */ + if (atomic_read(&dev_priv->forcewake_count)) + __gen6_gt_force_wake_get(dev_priv); break; case 5: ret = ironlake_do_reset(dev, flags); @@ -762,14 +766,6 @@ static struct drm_driver driver = { .resume = i915_resume, .device_is_agp = i915_driver_device_is_agp, - .enable_vblank = i915_enable_vblank, - .disable_vblank = i915_disable_vblank, - .get_vblank_timestamp = i915_get_vblank_timestamp, - .get_scanout_position = i915_get_crtc_scanoutpos, - .irq_preinstall = i915_driver_irq_preinstall, - .irq_postinstall = i915_driver_irq_postinstall, - .irq_uninstall = i915_driver_irq_uninstall, - .irq_handler = i915_driver_irq_handler, .reclaim_buffers = drm_core_reclaim_buffers, .master_create = i915_master_create, .master_destroy = i915_master_destroy, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index f63ee16..ce7914c 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -211,6 +211,9 @@ struct drm_i915_display_funcs { void (*fdi_link_train)(struct drm_crtc *crtc); void (*init_clock_gating)(struct drm_device *dev); void (*init_pch_clock_gating)(struct drm_device *dev); + int (*queue_flip)(struct drm_device *dev, struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj); /* clock updates for mode set */ /* cursor updates */ /* render clock increase/decrease */ @@ -259,6 +262,7 @@ enum intel_pch { }; #define QUIRK_PIPEA_FORCE (1<<0) +#define QUIRK_LVDS_SSC_DISABLE (1<<1) struct intel_fbdev; @@ -994,8 +998,6 @@ extern unsigned int i915_enable_fbc; extern int i915_suspend(struct drm_device *dev, pm_message_t state); extern int i915_resume(struct drm_device *dev); -extern void i915_save_display(struct drm_device *dev); -extern void i915_restore_display(struct drm_device *dev); extern int i915_master_create(struct drm_device *dev, struct drm_master *master); extern void i915_master_destroy(struct drm_device *dev, struct drm_master *master); @@ -1030,33 +1032,12 @@ extern int i915_irq_emit(struct drm_device *dev, void *data, extern int i915_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_priv); -extern irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS); -extern void i915_driver_irq_preinstall(struct drm_device * dev); -extern int i915_driver_irq_postinstall(struct drm_device *dev); -extern void i915_driver_irq_uninstall(struct drm_device * dev); - -extern irqreturn_t ironlake_irq_handler(DRM_IRQ_ARGS); -extern void ironlake_irq_preinstall(struct drm_device *dev); -extern int ironlake_irq_postinstall(struct drm_device *dev); -extern void ironlake_irq_uninstall(struct drm_device *dev); - -extern irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS); -extern void ivybridge_irq_preinstall(struct drm_device *dev); -extern int ivybridge_irq_postinstall(struct drm_device *dev); -extern void ivybridge_irq_uninstall(struct drm_device *dev); +extern void intel_irq_init(struct drm_device *dev); extern int i915_vblank_pipe_set(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int i915_vblank_pipe_get(struct drm_device *dev, void *data, struct drm_file *file_priv); -extern int i915_enable_vblank(struct drm_device *dev, int crtc); -extern void i915_disable_vblank(struct drm_device *dev, int crtc); -extern int ironlake_enable_vblank(struct drm_device *dev, int crtc); -extern void ironlake_disable_vblank(struct drm_device *dev, int crtc); -extern int ivybridge_enable_vblank(struct drm_device *dev, int crtc); -extern void ivybridge_disable_vblank(struct drm_device *dev, int crtc); -extern u32 i915_get_vblank_counter(struct drm_device *dev, int crtc); -extern u32 gm45_get_vblank_counter(struct drm_device *dev, int crtc); extern int i915_vblank_swap(struct drm_device *dev, void *data, struct drm_file *file_priv); @@ -1067,13 +1048,6 @@ void i915_disable_pipestat(drm_i915_private_t *dev_priv, int pipe, u32 mask); void intel_enable_asle (struct drm_device *dev); -int i915_get_vblank_timestamp(struct drm_device *dev, int crtc, - int *max_error, - struct timeval *vblank_time, - unsigned flags); - -int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, - int *vpos, int *hpos); #ifdef CONFIG_DEBUG_FS extern void i915_destroy_error_state(struct drm_device *dev); @@ -1221,7 +1195,9 @@ void i915_gem_free_all_phys_object(struct drm_device *dev); void i915_gem_release(struct drm_device *dev, struct drm_file *file); uint32_t -i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj); +i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev, + uint32_t size, + int tiling_mode); /* i915_gem_gtt.c */ void i915_gem_restore_gtt_mappings(struct drm_device *dev); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 94c84d7..a087e1b 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -31,6 +31,7 @@ #include "i915_drv.h" #include "i915_trace.h" #include "intel_drv.h" +#include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/pci.h> @@ -359,8 +360,7 @@ i915_gem_shmem_pread_fast(struct drm_device *dev, if ((page_offset + remain) > PAGE_SIZE) page_length = PAGE_SIZE - page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); @@ -463,8 +463,7 @@ i915_gem_shmem_pread_slow(struct drm_device *dev, if ((data_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - data_page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; @@ -797,8 +796,7 @@ i915_gem_shmem_pwrite_fast(struct drm_device *dev, if ((page_offset + remain) > PAGE_SIZE) page_length = PAGE_SIZE - page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); @@ -907,8 +905,7 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev, if ((data_page_offset + page_length) > PAGE_SIZE) page_length = PAGE_SIZE - data_page_offset; - page = read_cache_page_gfp(mapping, offset >> PAGE_SHIFT, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; @@ -1219,11 +1216,11 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ret = i915_gem_object_bind_to_gtt(obj, 0, true); if (ret) goto unlock; - } - ret = i915_gem_object_set_to_gtt_domain(obj, write); - if (ret) - goto unlock; + ret = i915_gem_object_set_to_gtt_domain(obj, write); + if (ret) + goto unlock; + } if (obj->tiling_mode == I915_TILING_NONE) ret = i915_gem_object_put_fence(obj); @@ -1377,25 +1374,24 @@ i915_gem_free_mmap_offset(struct drm_i915_gem_object *obj) } static uint32_t -i915_gem_get_gtt_size(struct drm_i915_gem_object *obj) +i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode) { - struct drm_device *dev = obj->base.dev; - uint32_t size; + uint32_t gtt_size; if (INTEL_INFO(dev)->gen >= 4 || - obj->tiling_mode == I915_TILING_NONE) - return obj->base.size; + tiling_mode == I915_TILING_NONE) + return size; /* Previous chips need a power-of-two fence region when tiling */ if (INTEL_INFO(dev)->gen == 3) - size = 1024*1024; + gtt_size = 1024*1024; else - size = 512*1024; + gtt_size = 512*1024; - while (size < obj->base.size) - size <<= 1; + while (gtt_size < size) + gtt_size <<= 1; - return size; + return gtt_size; } /** @@ -1406,59 +1402,52 @@ i915_gem_get_gtt_size(struct drm_i915_gem_object *obj) * potential fence register mapping. */ static uint32_t -i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj) +i915_gem_get_gtt_alignment(struct drm_device *dev, + uint32_t size, + int tiling_mode) { - struct drm_device *dev = obj->base.dev; - /* * Minimum alignment is 4k (GTT page size), but might be greater * if a fence register is needed for the object. */ if (INTEL_INFO(dev)->gen >= 4 || - obj->tiling_mode == I915_TILING_NONE) + tiling_mode == I915_TILING_NONE) return 4096; /* * Previous chips need to be aligned to the size of the smallest * fence register that can contain the object. */ - return i915_gem_get_gtt_size(obj); + return i915_gem_get_gtt_size(dev, size, tiling_mode); } /** * i915_gem_get_unfenced_gtt_alignment - return required GTT alignment for an * unfenced object - * @obj: object to check + * @dev: the device + * @size: size of the object + * @tiling_mode: tiling mode of the object * * Return the required GTT alignment for an object, only taking into account * unfenced tiled surface requirements. */ uint32_t -i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj) +i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev, + uint32_t size, + int tiling_mode) { - struct drm_device *dev = obj->base.dev; - int tile_height; - /* * Minimum alignment is 4k (GTT page size) for sane hw. */ if (INTEL_INFO(dev)->gen >= 4 || IS_G33(dev) || - obj->tiling_mode == I915_TILING_NONE) + tiling_mode == I915_TILING_NONE) return 4096; - /* - * Older chips need unfenced tiled buffers to be aligned to the left - * edge of an even tile row (where tile rows are counted as if the bo is - * placed in a fenced gtt region). + /* Previous hardware however needs to be aligned to a power-of-two + * tile height. The simplest method for determining this is to reuse + * the power-of-tile object size. */ - if (IS_GEN2(dev)) - tile_height = 16; - else if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)) - tile_height = 32; - else - tile_height = 8; - - return tile_height * obj->stride * 2; + return i915_gem_get_gtt_size(dev, size, tiling_mode); } int @@ -1558,12 +1547,10 @@ i915_gem_object_get_pages_gtt(struct drm_i915_gem_object *obj, inode = obj->base.filp->f_path.dentry->d_inode; mapping = inode->i_mapping; + gfpmask |= mapping_gfp_mask(mapping); + for (i = 0; i < page_count; i++) { - page = read_cache_page_gfp(mapping, i, - GFP_HIGHUSER | - __GFP_COLD | - __GFP_RECLAIMABLE | - gfpmask); + page = shmem_read_mapping_page_gfp(mapping, i, gfpmask); if (IS_ERR(page)) goto err_pages; @@ -1701,13 +1688,10 @@ i915_gem_object_truncate(struct drm_i915_gem_object *obj) /* Our goal here is to return as much of the memory as * is possible back to the system as we are called from OOM. * To do this we must instruct the shmfs to drop all of its - * backing pages, *now*. Here we mirror the actions taken - * when by shmem_delete_inode() to release the backing store. + * backing pages, *now*. */ inode = obj->base.filp->f_path.dentry->d_inode; - truncate_inode_pages(inode->i_mapping, 0); - if (inode->i_op->truncate_range) - inode->i_op->truncate_range(inode, 0, (loff_t)-1); + shmem_truncate_range(inode, 0, (loff_t)-1); obj->madv = __I915_MADV_PURGED; } @@ -2080,8 +2064,8 @@ i915_wait_request(struct intel_ring_buffer *ring, if (!ier) { DRM_ERROR("something (likely vbetool) disabled " "interrupts, re-enabling\n"); - i915_driver_irq_preinstall(ring->dev); - i915_driver_irq_postinstall(ring->dev); + ring->dev->driver->irq_preinstall(ring->dev); + ring->dev->driver->irq_postinstall(ring->dev); } trace_i915_gem_request_wait_begin(ring, seqno); @@ -2752,9 +2736,16 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj, return -EINVAL; } - fence_size = i915_gem_get_gtt_size(obj); - fence_alignment = i915_gem_get_gtt_alignment(obj); - unfenced_alignment = i915_gem_get_unfenced_gtt_alignment(obj); + fence_size = i915_gem_get_gtt_size(dev, + obj->base.size, + obj->tiling_mode); + fence_alignment = i915_gem_get_gtt_alignment(dev, + obj->base.size, + obj->tiling_mode); + unfenced_alignment = + i915_gem_get_unfenced_gtt_alignment(dev, + obj->base.size, + obj->tiling_mode); if (alignment == 0) alignment = map_and_fenceable ? fence_alignment : @@ -2926,8 +2917,6 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj) */ wmb(); - i915_gem_release_mmap(obj); - old_write_domain = obj->base.write_domain; obj->base.write_domain = 0; @@ -3567,6 +3556,7 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, { struct drm_i915_private *dev_priv = dev->dev_private; struct drm_i915_gem_object *obj; + struct address_space *mapping; obj = kzalloc(sizeof(*obj), GFP_KERNEL); if (obj == NULL) @@ -3577,6 +3567,9 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev, return NULL; } + mapping = obj->base.filp->f_path.dentry->d_inode->i_mapping; + mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE); + i915_gem_info_add_obj(dev_priv, size); obj->base.write_domain = I915_GEM_DOMAIN_CPU; @@ -3952,8 +3945,7 @@ void i915_gem_detach_phys_object(struct drm_device *dev, page_count = obj->base.size / PAGE_SIZE; for (i = 0; i < page_count; i++) { - struct page *page = read_cache_page_gfp(mapping, i, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + struct page *page = shmem_read_mapping_page(mapping, i); if (!IS_ERR(page)) { char *dst = kmap_atomic(page); memcpy(dst, vaddr + i*PAGE_SIZE, PAGE_SIZE); @@ -4014,8 +4006,7 @@ i915_gem_attach_phys_object(struct drm_device *dev, struct page *page; char *dst, *src; - page = read_cache_page_gfp(mapping, i, - GFP_HIGHUSER | __GFP_RECLAIMABLE); + page = shmem_read_mapping_page(mapping, i); if (IS_ERR(page)) return PTR_ERR(page); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 20a4cc5..4934cf8 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -187,10 +187,6 @@ i915_gem_object_set_to_gpu_domain(struct drm_i915_gem_object *obj, if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_CPU) i915_gem_clflush_object(obj); - /* blow away mappings if mapped through GTT */ - if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_GTT) - i915_gem_release_mmap(obj); - if (obj->base.pending_write_domain) cd->flips |= atomic_read(&obj->pending_flip); diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 82d70fd..99c4faa 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -348,7 +348,9 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, /* Rebind if we need a change of alignment */ if (!obj->map_and_fenceable) { u32 unfenced_alignment = - i915_gem_get_unfenced_gtt_alignment(obj); + i915_gem_get_unfenced_gtt_alignment(dev, + obj->base.size, + args->tiling_mode); if (obj->gtt_offset & (unfenced_alignment - 1)) ret = i915_gem_object_unbind(obj); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 9e34a1a..3b03f85 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -152,7 +152,7 @@ i915_pipe_enabled(struct drm_device *dev, int pipe) /* Called from drm generic code, passed a 'crtc', which * we use as a pipe index */ -u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) +static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long high_frame; @@ -184,7 +184,7 @@ u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) return (high1 << 8) | low; } -u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) +static u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; int reg = PIPE_FRMCOUNT_GM45(pipe); @@ -198,7 +198,7 @@ u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) return I915_READ(reg); } -int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, +static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, int *vpos, int *hpos) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -264,7 +264,7 @@ int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe, return ret; } -int i915_get_vblank_timestamp(struct drm_device *dev, int pipe, +static int i915_get_vblank_timestamp(struct drm_device *dev, int pipe, int *max_error, struct timeval *vblank_time, unsigned flags) @@ -462,7 +462,7 @@ static void pch_irq_handler(struct drm_device *dev) DRM_DEBUG_DRIVER("PCH transcoder A underrun interrupt\n"); } -irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS) +static irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS) { struct drm_device *dev = (struct drm_device *) arg; drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -550,7 +550,7 @@ done: return ret; } -irqreturn_t ironlake_irq_handler(DRM_IRQ_ARGS) +static irqreturn_t ironlake_irq_handler(DRM_IRQ_ARGS) { struct drm_device *dev = (struct drm_device *) arg; drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -1209,7 +1209,7 @@ static void i915_pageflip_stall_check(struct drm_device *dev, int pipe) } } -irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) +static irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) { struct drm_device *dev = (struct drm_device *) arg; drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -1454,7 +1454,7 @@ int i915_irq_wait(struct drm_device *dev, void *data, /* Called from drm generic code, passed 'crtc' which * we use as a pipe index */ -int i915_enable_vblank(struct drm_device *dev, int pipe) +static int i915_enable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; @@ -1478,7 +1478,7 @@ int i915_enable_vblank(struct drm_device *dev, int pipe) return 0; } -int ironlake_enable_vblank(struct drm_device *dev, int pipe) +static int ironlake_enable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; @@ -1494,7 +1494,7 @@ int ironlake_enable_vblank(struct drm_device *dev, int pipe) return 0; } -int ivybridge_enable_vblank(struct drm_device *dev, int pipe) +static int ivybridge_enable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; @@ -1513,7 +1513,7 @@ int ivybridge_enable_vblank(struct drm_device *dev, int pipe) /* Called from drm generic code, passed 'crtc' which * we use as a pipe index */ -void i915_disable_vblank(struct drm_device *dev, int pipe) +static void i915_disable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; @@ -1529,7 +1529,7 @@ void i915_disable_vblank(struct drm_device *dev, int pipe) spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); } -void ironlake_disable_vblank(struct drm_device *dev, int pipe) +static void ironlake_disable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; @@ -1540,7 +1540,7 @@ void ironlake_disable_vblank(struct drm_device *dev, int pipe) spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags); } -void ivybridge_disable_vblank(struct drm_device *dev, int pipe) +static void ivybridge_disable_vblank(struct drm_device *dev, int pipe) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; unsigned long irqflags; @@ -1728,7 +1728,7 @@ repeat: /* drm_dma.h hooks */ -void ironlake_irq_preinstall(struct drm_device *dev) +static void ironlake_irq_preinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -1740,7 +1740,7 @@ void ironlake_irq_preinstall(struct drm_device *dev) INIT_WORK(&dev_priv->rps_work, gen6_pm_rps_work); I915_WRITE(HWSTAM, 0xeffe); - if (IS_GEN6(dev)) { + if (IS_GEN6(dev) || IS_GEN7(dev)) { /* Workaround stalls observed on Sandy Bridge GPUs by * making the blitter command streamer generate a * write to the Hardware Status Page for @@ -1749,6 +1749,7 @@ void ironlake_irq_preinstall(struct drm_device *dev) * happens. */ I915_WRITE(GEN6_BLITTER_HWSTAM, ~GEN6_BLITTER_USER_INTERRUPT); + I915_WRITE(GEN6_BSD_HWSTAM, ~GEN6_BSD_USER_INTERRUPT); } /* XXX hotplug from PCH */ @@ -1768,7 +1769,7 @@ void ironlake_irq_preinstall(struct drm_device *dev) POSTING_READ(SDEIER); } -int ironlake_irq_postinstall(struct drm_device *dev) +static int ironlake_irq_postinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; /* enable kind of interrupts always enabled */ @@ -1840,7 +1841,7 @@ int ironlake_irq_postinstall(struct drm_device *dev) return 0; } -int ivybridge_irq_postinstall(struct drm_device *dev) +static int ivybridge_irq_postinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; /* enable kind of interrupts always enabled */ @@ -1890,7 +1891,7 @@ int ivybridge_irq_postinstall(struct drm_device *dev) return 0; } -void i915_driver_irq_preinstall(struct drm_device * dev) +static void i915_driver_irq_preinstall(struct drm_device * dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; int pipe; @@ -1917,7 +1918,7 @@ void i915_driver_irq_preinstall(struct drm_device * dev) * Must be called after intel_modeset_init or hotplug interrupts won't be * enabled correctly. */ -int i915_driver_irq_postinstall(struct drm_device *dev) +static int i915_driver_irq_postinstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; u32 enable_mask = I915_INTERRUPT_ENABLE_FIX | I915_INTERRUPT_ENABLE_VAR; @@ -1993,7 +1994,7 @@ int i915_driver_irq_postinstall(struct drm_device *dev) return 0; } -void ironlake_irq_uninstall(struct drm_device *dev) +static void ironlake_irq_uninstall(struct drm_device *dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; @@ -2013,7 +2014,7 @@ void ironlake_irq_uninstall(struct drm_device *dev) I915_WRITE(GTIIR, I915_READ(GTIIR)); } -void i915_driver_irq_uninstall(struct drm_device * dev) +static void i915_driver_irq_uninstall(struct drm_device * dev) { drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private; int pipe; @@ -2039,3 +2040,41 @@ void i915_driver_irq_uninstall(struct drm_device * dev) I915_READ(PIPESTAT(pipe)) & 0x8000ffff); I915_WRITE(IIR, I915_READ(IIR)); } + +void intel_irq_init(struct drm_device *dev) +{ + dev->driver->get_vblank_counter = i915_get_vblank_counter; + dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */ + if (IS_G4X(dev) || IS_GEN5(dev) || IS_GEN6(dev) || IS_IVYBRIDGE(dev)) { + dev->max_vblank_count = 0xffffffff; /* full 32 bit counter */ + dev->driver->get_vblank_counter = gm45_get_vblank_counter; + } + + + dev->driver->get_vblank_timestamp = i915_get_vblank_timestamp; + dev->driver->get_scanout_position = i915_get_crtc_scanoutpos; + + if (IS_IVYBRIDGE(dev)) { + /* Share pre & uninstall handlers with ILK/SNB */ + dev->driver->irq_handler = ivybridge_irq_handler; + dev->driver->irq_preinstall = ironlake_irq_preinstall; + dev->driver->irq_postinstall = ivybridge_irq_postinstall; + dev->driver->irq_uninstall = ironlake_irq_uninstall; + dev->driver->enable_vblank = ivybridge_enable_vblank; + dev->driver->disable_vblank = ivybridge_disable_vblank; + } else if (HAS_PCH_SPLIT(dev)) { + dev->driver->irq_handler = ironlake_irq_handler; + dev->driver->irq_preinstall = ironlake_irq_preinstall; + dev->driver->irq_postinstall = ironlake_irq_postinstall; + dev->driver->irq_uninstall = ironlake_irq_uninstall; + dev->driver->enable_vblank = ironlake_enable_vblank; + dev->driver->disable_vblank = ironlake_disable_vblank; + } else { + dev->driver->irq_preinstall = i915_driver_irq_preinstall; + dev->driver->irq_postinstall = i915_driver_irq_postinstall; + dev->driver->irq_uninstall = i915_driver_irq_uninstall; + dev->driver->irq_handler = i915_driver_irq_handler; + dev->driver->enable_vblank = i915_enable_vblank; + dev->driver->disable_vblank = i915_disable_vblank; + } +} diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2f967af..5d5def7 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -531,6 +531,7 @@ #define GEN6_BSD_SLEEP_PSMI_CONTROL_RC_ILDL_MESSAGE_ENABLE 0 #define GEN6_BSD_SLEEP_PSMI_CONTROL_IDLE_INDICATOR (1 << 3) +#define GEN6_BSD_HWSTAM 0x12098 #define GEN6_BSD_IMR 0x120a8 #define GEN6_BSD_USER_INTERRUPT (1 << 12) diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 60a94d2..5257cfc 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -597,7 +597,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev) return; } -void i915_save_display(struct drm_device *dev) +static void i915_save_display(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -689,7 +689,7 @@ void i915_save_display(struct drm_device *dev) i915_save_vga(dev); } -void i915_restore_display(struct drm_device *dev) +static void i915_restore_display(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -780,6 +780,7 @@ void i915_restore_display(struct drm_device *dev) I915_WRITE(CPU_VGACNTRL, dev_priv->saveVGACNTRL); else I915_WRITE(VGACNTRL, dev_priv->saveVGACNTRL); + I915_WRITE(VGA0, dev_priv->saveVGA0); I915_WRITE(VGA1, dev_priv->saveVGA1); I915_WRITE(VGA_PD, dev_priv->saveVGA_PD); @@ -796,6 +797,8 @@ int i915_save_state(struct drm_device *dev) pci_read_config_byte(dev->pdev, LBB, &dev_priv->saveLBB); + mutex_lock(&dev->struct_mutex); + /* Hardware status page */ dev_priv->saveHWS = I915_READ(HWS_PGA); @@ -835,6 +838,8 @@ int i915_save_state(struct drm_device *dev) for (i = 0; i < 3; i++) dev_priv->saveSWF2[i] = I915_READ(SWF30 + (i << 2)); + mutex_unlock(&dev->struct_mutex); + return 0; } @@ -845,6 +850,8 @@ int i915_restore_state(struct drm_device *dev) pci_write_config_byte(dev->pdev, LBB, dev_priv->saveLBB); + mutex_lock(&dev->struct_mutex); + /* Hardware status page */ I915_WRITE(HWS_PGA, dev_priv->saveHWS); @@ -862,6 +869,7 @@ int i915_restore_state(struct drm_device *dev) I915_WRITE(IER, dev_priv->saveIER); I915_WRITE(IMR, dev_priv->saveIMR); } + mutex_unlock(&dev->struct_mutex); intel_init_clock_gating(dev); @@ -873,6 +881,8 @@ int i915_restore_state(struct drm_device *dev) if (IS_GEN6(dev)) gen6_enable_rps(dev_priv); + mutex_lock(&dev->struct_mutex); + /* Cache mode state */ I915_WRITE (CACHE_MODE_0, dev_priv->saveCACHE_MODE_0 | 0xffff0000); @@ -886,6 +896,8 @@ int i915_restore_state(struct drm_device *dev) for (i = 0; i < 3; i++) I915_WRITE(SWF30 + (i << 2), dev_priv->saveSWF2[i]); + mutex_unlock(&dev->struct_mutex); + intel_i2c_reset(dev); return 0; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 81a9059..0f1c799 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4305,7 +4305,8 @@ static void intel_update_watermarks(struct drm_device *dev) static inline bool intel_panel_use_ssc(struct drm_i915_private *dev_priv) { - return dev_priv->lvds_use_ssc && i915_panel_use_ssc; + return dev_priv->lvds_use_ssc && i915_panel_use_ssc + && !(dev_priv->quirks & QUIRK_LVDS_SSC_DISABLE); } static int i9xx_crtc_mode_set(struct drm_crtc *crtc, @@ -4687,6 +4688,7 @@ static int i9xx_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(DSPCNTR(plane), dspcntr); POSTING_READ(DSPCNTR(plane)); + intel_enable_plane(dev_priv, plane, pipe); ret = intel_pipe_set_base(crtc, x, y, old_fb); @@ -5217,8 +5219,6 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(DSPCNTR(plane), dspcntr); POSTING_READ(DSPCNTR(plane)); - if (!HAS_PCH_SPLIT(dev)) - intel_enable_plane(dev_priv, plane, pipe); ret = intel_pipe_set_base(crtc, x, y, old_fb); @@ -6262,6 +6262,197 @@ void intel_prepare_page_flip(struct drm_device *dev, int plane) spin_unlock_irqrestore(&dev->event_lock, flags); } +static int intel_gen2_queue_flip(struct drm_device *dev, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + unsigned long offset; + u32 flip_mask; + int ret; + + ret = intel_pin_and_fence_fb_obj(dev, obj, LP_RING(dev_priv)); + if (ret) + goto out; + + /* Offset into the new buffer for cases of shared fbs between CRTCs */ + offset = crtc->y * fb->pitch + crtc->x * fb->bits_per_pixel/8; + + ret = BEGIN_LP_RING(6); + if (ret) + goto out; + + /* Can't queue multiple flips, so wait for the previous + * one to finish before executing the next. + */ + if (intel_crtc->plane) + flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; + else + flip_mask = MI_WAIT_FOR_PLANE_A_FLIP; + OUT_RING(MI_WAIT_FOR_EVENT | flip_mask); + OUT_RING(MI_NOOP); + OUT_RING(MI_DISPLAY_FLIP | + MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); + OUT_RING(fb->pitch); + OUT_RING(obj->gtt_offset + offset); + OUT_RING(MI_NOOP); + ADVANCE_LP_RING(); +out: + return ret; +} + +static int intel_gen3_queue_flip(struct drm_device *dev, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + unsigned long offset; + u32 flip_mask; + int ret; + + ret = intel_pin_and_fence_fb_obj(dev, obj, LP_RING(dev_priv)); + if (ret) + goto out; + + /* Offset into the new buffer for cases of shared fbs between CRTCs */ + offset = crtc->y * fb->pitch + crtc->x * fb->bits_per_pixel/8; + + ret = BEGIN_LP_RING(6); + if (ret) + goto out; + + if (intel_crtc->plane) + flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; + else + flip_mask = MI_WAIT_FOR_PLANE_A_FLIP; + OUT_RING(MI_WAIT_FOR_EVENT | flip_mask); + OUT_RING(MI_NOOP); + OUT_RING(MI_DISPLAY_FLIP_I915 | + MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); + OUT_RING(fb->pitch); + OUT_RING(obj->gtt_offset + offset); + OUT_RING(MI_NOOP); + + ADVANCE_LP_RING(); +out: + return ret; +} + +static int intel_gen4_queue_flip(struct drm_device *dev, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + uint32_t pf, pipesrc; + int ret; + + ret = intel_pin_and_fence_fb_obj(dev, obj, LP_RING(dev_priv)); + if (ret) + goto out; + + ret = BEGIN_LP_RING(4); + if (ret) + goto out; + + /* i965+ uses the linear or tiled offsets from the + * Display Registers (which do not change across a page-flip) + * so we need only reprogram the base address. + */ + OUT_RING(MI_DISPLAY_FLIP | + MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); + OUT_RING(fb->pitch); + OUT_RING(obj->gtt_offset | obj->tiling_mode); + + /* XXX Enabling the panel-fitter across page-flip is so far + * untested on non-native modes, so ignore it for now. + * pf = I915_READ(pipe == 0 ? PFA_CTL_1 : PFB_CTL_1) & PF_ENABLE; + */ + pf = 0; + pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff; + OUT_RING(pf | pipesrc); + ADVANCE_LP_RING(); +out: + return ret; +} + +static int intel_gen6_queue_flip(struct drm_device *dev, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + uint32_t pf, pipesrc; + int ret; + + ret = intel_pin_and_fence_fb_obj(dev, obj, LP_RING(dev_priv)); + if (ret) + goto out; + + ret = BEGIN_LP_RING(4); + if (ret) + goto out; + + OUT_RING(MI_DISPLAY_FLIP | + MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); + OUT_RING(fb->pitch | obj->tiling_mode); + OUT_RING(obj->gtt_offset); + + pf = I915_READ(PF_CTL(intel_crtc->pipe)) & PF_ENABLE; + pipesrc = I915_READ(PIPESRC(intel_crtc->pipe)) & 0x0fff0fff; + OUT_RING(pf | pipesrc); + ADVANCE_LP_RING(); +out: + return ret; +} + +/* + * On gen7 we currently use the blit ring because (in early silicon at least) + * the render ring doesn't give us interrpts for page flip completion, which + * means clients will hang after the first flip is queued. Fortunately the + * blit ring generates interrupts properly, so use it instead. + */ +static int intel_gen7_queue_flip(struct drm_device *dev, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + struct intel_crtc *intel_crtc = to_intel_crtc(crtc); + struct intel_ring_buffer *ring = &dev_priv->ring[BCS]; + int ret; + + ret = intel_pin_and_fence_fb_obj(dev, obj, ring); + if (ret) + goto out; + + ret = intel_ring_begin(ring, 4); + if (ret) + goto out; + + intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | (intel_crtc->plane << 19)); + intel_ring_emit(ring, (fb->pitch | obj->tiling_mode)); + intel_ring_emit(ring, (obj->gtt_offset)); + intel_ring_emit(ring, (MI_NOOP)); + intel_ring_advance(ring); +out: + return ret; +} + +static int intel_default_queue_flip(struct drm_device *dev, + struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_i915_gem_object *obj) +{ + return -ENODEV; +} + static int intel_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_pending_vblank_event *event) @@ -6272,9 +6463,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, struct drm_i915_gem_object *obj; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_unpin_work *work; - unsigned long flags, offset; - int pipe = intel_crtc->pipe; - u32 pf, pipesrc; + unsigned long flags; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); @@ -6303,9 +6492,6 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, obj = intel_fb->obj; mutex_lock(&dev->struct_mutex); - ret = intel_pin_and_fence_fb_obj(dev, obj, LP_RING(dev_priv)); - if (ret) - goto cleanup_work; /* Reference the objects for the scheduled work. */ drm_gem_object_reference(&work->old_fb_obj->base); @@ -6317,91 +6503,18 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, if (ret) goto cleanup_objs; - if (IS_GEN3(dev) || IS_GEN2(dev)) { - u32 flip_mask; - - /* Can't queue multiple flips, so wait for the previous - * one to finish before executing the next. - */ - ret = BEGIN_LP_RING(2); - if (ret) - goto cleanup_objs; - - if (intel_crtc->plane) - flip_mask = MI_WAIT_FOR_PLANE_B_FLIP; - else - flip_mask = MI_WAIT_FOR_PLANE_A_FLIP; - OUT_RING(MI_WAIT_FOR_EVENT | flip_mask); - OUT_RING(MI_NOOP); - ADVANCE_LP_RING(); - } - work->pending_flip_obj = obj; work->enable_stall_check = true; - /* Offset into the new buffer for cases of shared fbs between CRTCs */ - offset = crtc->y * fb->pitch + crtc->x * fb->bits_per_pixel/8; - - ret = BEGIN_LP_RING(4); - if (ret) - goto cleanup_objs; - /* Block clients from rendering to the new back buffer until * the flip occurs and the object is no longer visible. */ atomic_add(1 << intel_crtc->plane, &work->old_fb_obj->pending_flip); - switch (INTEL_INFO(dev)->gen) { - case 2: - OUT_RING(MI_DISPLAY_FLIP | - MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); - OUT_RING(fb->pitch); - OUT_RING(obj->gtt_offset + offset); - OUT_RING(MI_NOOP); - break; - - case 3: - OUT_RING(MI_DISPLAY_FLIP_I915 | - MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); - OUT_RING(fb->pitch); - OUT_RING(obj->gtt_offset + offset); - OUT_RING(MI_NOOP); - break; - - case 4: - case 5: - /* i965+ uses the linear or tiled offsets from the - * Display Registers (which do not change across a page-flip) - * so we need only reprogram the base address. - */ - OUT_RING(MI_DISPLAY_FLIP | - MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); - OUT_RING(fb->pitch); - OUT_RING(obj->gtt_offset | obj->tiling_mode); - - /* XXX Enabling the panel-fitter across page-flip is so far - * untested on non-native modes, so ignore it for now. - * pf = I915_READ(pipe == 0 ? PFA_CTL_1 : PFB_CTL_1) & PF_ENABLE; - */ - pf = 0; - pipesrc = I915_READ(PIPESRC(pipe)) & 0x0fff0fff; - OUT_RING(pf | pipesrc); - break; - - case 6: - case 7: - OUT_RING(MI_DISPLAY_FLIP | - MI_DISPLAY_FLIP_PLANE(intel_crtc->plane)); - OUT_RING(fb->pitch | obj->tiling_mode); - OUT_RING(obj->gtt_offset); - - pf = I915_READ(PF_CTL(pipe)) & PF_ENABLE; - pipesrc = I915_READ(PIPESRC(pipe)) & 0x0fff0fff; - OUT_RING(pf | pipesrc); - break; - } - ADVANCE_LP_RING(); + ret = dev_priv->display.queue_flip(dev, crtc, fb, obj); + if (ret) + goto cleanup_pending; mutex_unlock(&dev->struct_mutex); @@ -6409,10 +6522,11 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc, return 0; +cleanup_pending: + atomic_sub(1 << intel_crtc->plane, &work->old_fb_obj->pending_flip); cleanup_objs: drm_gem_object_unreference(&work->old_fb_obj->base); drm_gem_object_unreference(&obj->base); -cleanup_work: mutex_unlock(&dev->struct_mutex); spin_lock_irqsave(&dev->event_lock, flags); @@ -7657,6 +7771,31 @@ static void intel_init_display(struct drm_device *dev) else dev_priv->display.get_fifo_size = i830_get_fifo_size; } + + /* Default just returns -ENODEV to indicate unsupported */ + dev_priv->display.queue_flip = intel_default_queue_flip; + + switch (INTEL_INFO(dev)->gen) { + case 2: + dev_priv->display.queue_flip = intel_gen2_queue_flip; + break; + + case 3: + dev_priv->display.queue_flip = intel_gen3_queue_flip; + break; + + case 4: + case 5: + dev_priv->display.queue_flip = intel_gen4_queue_flip; + break; + + case 6: + dev_priv->display.queue_flip = intel_gen6_queue_flip; + break; + case 7: + dev_priv->display.queue_flip = intel_gen7_queue_flip; + break; + } } /* @@ -7672,6 +7811,15 @@ static void quirk_pipea_force (struct drm_device *dev) DRM_DEBUG_DRIVER("applying pipe a force quirk\n"); } +/* + * Some machines (Lenovo U160) do not work with SSC on LVDS for some reason + */ +static void quirk_ssc_force_disable(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + dev_priv->quirks |= QUIRK_LVDS_SSC_DISABLE; +} + struct intel_quirk { int device; int subsystem_vendor; @@ -7700,6 +7848,9 @@ struct intel_quirk intel_quirks[] = { /* 855 & before need to leave pipe A & dpll A up */ { 0x3582, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force }, { 0x2562, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force }, + + /* Lenovo U160 cannot use SSC on LVDS */ + { 0x0046, 0x17aa, 0x3920, quirk_ssc_force_disable }, }; static void intel_init_quirks(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 391b55f..e2aced6 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -50,7 +50,6 @@ struct intel_dp { bool has_audio; int force_audio; uint32_t color_range; - int dpms_mode; uint8_t link_bw; uint8_t lane_count; uint8_t dpcd[4]; @@ -138,8 +137,8 @@ intel_dp_max_lane_count(struct intel_dp *intel_dp) { int max_lane_count = 4; - if (intel_dp->dpcd[0] >= 0x11) { - max_lane_count = intel_dp->dpcd[2] & 0x1f; + if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11) { + max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f; switch (max_lane_count) { case 1: case 2: case 4: break; @@ -153,7 +152,7 @@ intel_dp_max_lane_count(struct intel_dp *intel_dp) static int intel_dp_max_link_bw(struct intel_dp *intel_dp) { - int max_link_bw = intel_dp->dpcd[1]; + int max_link_bw = intel_dp->dpcd[DP_MAX_LINK_RATE]; switch (max_link_bw) { case DP_LINK_BW_1_62: @@ -774,7 +773,8 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, /* * Check for DPCD version > 1.1 and enhanced framing support */ - if (intel_dp->dpcd[0] >= 0x11 && (intel_dp->dpcd[2] & DP_ENHANCED_FRAME_CAP)) { + if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 && + (intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP)) { intel_dp->link_configuration[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; intel_dp->DP |= DP_ENHANCED_FRAMING; } @@ -942,11 +942,44 @@ static void ironlake_edp_pll_off(struct drm_encoder *encoder) udelay(200); } +/* If the sink supports it, try to set the power state appropriately */ +static void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode) +{ + int ret, i; + + /* Should have a valid DPCD by this point */ + if (intel_dp->dpcd[DP_DPCD_REV] < 0x11) + return; + + if (mode != DRM_MODE_DPMS_ON) { + ret = intel_dp_aux_native_write_1(intel_dp, DP_SET_POWER, + DP_SET_POWER_D3); + if (ret != 1) + DRM_DEBUG_DRIVER("failed to write sink power state\n"); + } else { + /* + * When turning on, we need to retry for 1ms to give the sink + * time to wake up. + */ + for (i = 0; i < 3; i++) { + ret = intel_dp_aux_native_write_1(intel_dp, + DP_SET_POWER, + DP_SET_POWER_D0); + if (ret == 1) + break; + msleep(1); + } + } +} + static void intel_dp_prepare(struct drm_encoder *encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct drm_device *dev = encoder->dev; + /* Wake up the sink first */ + intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); + if (is_edp(intel_dp)) { ironlake_edp_backlight_off(dev); ironlake_edp_panel_off(dev); @@ -990,6 +1023,7 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) if (mode != DRM_MODE_DPMS_ON) { if (is_edp(intel_dp)) ironlake_edp_backlight_off(dev); + intel_dp_sink_dpms(intel_dp, mode); intel_dp_link_down(intel_dp); if (is_edp(intel_dp)) ironlake_edp_panel_off(dev); @@ -998,6 +1032,7 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) } else { if (is_edp(intel_dp)) ironlake_edp_panel_vdd_on(intel_dp); + intel_dp_sink_dpms(intel_dp, mode); if (!(dp_reg & DP_PORT_EN)) { intel_dp_start_link_train(intel_dp); if (is_edp(intel_dp)) { @@ -1009,7 +1044,31 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) if (is_edp(intel_dp)) ironlake_edp_backlight_on(dev); } - intel_dp->dpms_mode = mode; +} + +/* + * Native read with retry for link status and receiver capability reads for + * cases where the sink may still be asleep. + */ +static bool +intel_dp_aux_native_read_retry(struct intel_dp *intel_dp, uint16_t address, + uint8_t *recv, int recv_bytes) +{ + int ret, i; + + /* + * Sinks are *supposed* to come up within 1ms from an off state, + * but we're also supposed to retry 3 times per the spec. + */ + for (i = 0; i < 3; i++) { + ret = intel_dp_aux_native_read(intel_dp, address, recv, + recv_bytes); + if (ret == recv_bytes) + return true; + msleep(1); + } + + return false; } /* @@ -1019,14 +1078,10 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) static bool intel_dp_get_link_status(struct intel_dp *intel_dp) { - int ret; - - ret = intel_dp_aux_native_read(intel_dp, - DP_LANE0_1_STATUS, - intel_dp->link_status, DP_LINK_STATUS_SIZE); - if (ret != DP_LINK_STATUS_SIZE) - return false; - return true; + return intel_dp_aux_native_read_retry(intel_dp, + DP_LANE0_1_STATUS, + intel_dp->link_status, + DP_LINK_STATUS_SIZE); } static uint8_t @@ -1515,6 +1570,8 @@ intel_dp_link_down(struct intel_dp *intel_dp) static void intel_dp_check_link_status(struct intel_dp *intel_dp) { + int ret; + if (!intel_dp->base.base.crtc) return; @@ -1523,6 +1580,15 @@ intel_dp_check_link_status(struct intel_dp *intel_dp) return; } + /* Try to read receiver status if the link appears to be up */ + ret = intel_dp_aux_native_read(intel_dp, + 0x000, intel_dp->dpcd, + sizeof (intel_dp->dpcd)); + if (ret != sizeof(intel_dp->dpcd)) { + intel_dp_link_down(intel_dp); + return; + } + if (!intel_channel_eq_ok(intel_dp)) { intel_dp_start_link_train(intel_dp); intel_dp_complete_link_train(intel_dp); @@ -1533,6 +1599,7 @@ static enum drm_connector_status ironlake_dp_detect(struct intel_dp *intel_dp) { enum drm_connector_status status; + bool ret; /* Can't disconnect eDP, but you can close the lid... */ if (is_edp(intel_dp)) { @@ -1543,13 +1610,11 @@ ironlake_dp_detect(struct intel_dp *intel_dp) } status = connector_status_disconnected; - if (intel_dp_aux_native_read(intel_dp, - 0x000, intel_dp->dpcd, - sizeof (intel_dp->dpcd)) - == sizeof(intel_dp->dpcd)) { - if (intel_dp->dpcd[0] != 0) - status = connector_status_connected; - } + ret = intel_dp_aux_native_read_retry(intel_dp, + 0x000, intel_dp->dpcd, + sizeof (intel_dp->dpcd)); + if (ret && intel_dp->dpcd[DP_DPCD_REV] != 0) + status = connector_status_connected; DRM_DEBUG_KMS("DPCD: %hx%hx%hx%hx\n", intel_dp->dpcd[0], intel_dp->dpcd[1], intel_dp->dpcd[2], intel_dp->dpcd[3]); return status; @@ -1586,7 +1651,7 @@ g4x_dp_detect(struct intel_dp *intel_dp) if (intel_dp_aux_native_read(intel_dp, 0x000, intel_dp->dpcd, sizeof (intel_dp->dpcd)) == sizeof (intel_dp->dpcd)) { - if (intel_dp->dpcd[0] != 0) + if (intel_dp->dpcd[DP_DPCD_REV] != 0) status = connector_status_connected; } @@ -1790,8 +1855,7 @@ intel_dp_hot_plug(struct intel_encoder *intel_encoder) { struct intel_dp *intel_dp = container_of(intel_encoder, struct intel_dp, base); - if (intel_dp->dpms_mode == DRM_MODE_DPMS_ON) - intel_dp_check_link_status(intel_dp); + intel_dp_check_link_status(intel_dp); } /* Return which DP Port should be selected for Transcoder DP control */ @@ -1859,7 +1923,6 @@ intel_dp_init(struct drm_device *dev, int output_reg) return; intel_dp->output_reg = output_reg; - intel_dp->dpms_mode = -1; intel_connector = kzalloc(sizeof(struct intel_connector), GFP_KERNEL); if (!intel_connector) { @@ -1954,8 +2017,9 @@ intel_dp_init(struct drm_device *dev, int output_reg) sizeof(intel_dp->dpcd)); ironlake_edp_panel_vdd_off(intel_dp); if (ret == sizeof(intel_dp->dpcd)) { - if (intel_dp->dpcd[0] >= 0x11) - dev_priv->no_aux_handshake = intel_dp->dpcd[3] & + if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11) + dev_priv->no_aux_handshake = + intel_dp->dpcd[DP_MAX_DOWNSPREAD] & DP_NO_AUX_HANDSHAKE_LINK_TRAINING; } else { /* if this fails, presume the device is a ghost */ diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index a670c00..9e2959b 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -1409,6 +1409,11 @@ void intel_setup_overlay(struct drm_device *dev) overlay = kzalloc(sizeof(struct intel_overlay), GFP_KERNEL); if (!overlay) return; + + mutex_lock(&dev->struct_mutex); + if (WARN_ON(dev_priv->overlay)) + goto out_free; + overlay->dev = dev; reg_bo = i915_gem_alloc_object(dev, PAGE_SIZE); @@ -1448,7 +1453,7 @@ void intel_setup_overlay(struct drm_device *dev) regs = intel_overlay_map_regs(overlay); if (!regs) - goto out_free_bo; + goto out_unpin_bo; memset(regs, 0, sizeof(struct overlay_registers)); update_polyphase_filter(regs); @@ -1457,14 +1462,17 @@ void intel_setup_overlay(struct drm_device *dev) intel_overlay_unmap_regs(overlay, regs); dev_priv->overlay = overlay; + mutex_unlock(&dev->struct_mutex); DRM_INFO("initialized overlay support\n"); return; out_unpin_bo: - i915_gem_object_unpin(reg_bo); + if (!OVERLAY_NEEDS_PHYSICAL(dev)) + i915_gem_object_unpin(reg_bo); out_free_bo: drm_gem_object_unreference(®_bo->base); out_free: + mutex_unlock(&dev->struct_mutex); kfree(overlay); return; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index c0e0ee6..39ac2b6 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -165,7 +165,7 @@ void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring); int __must_check intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n); static inline int intel_wait_ring_idle(struct intel_ring_buffer *ring) { - return intel_wait_ring_buffer(ring, ring->space - 8); + return intel_wait_ring_buffer(ring, ring->size - 8); } int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n); diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c index 144f79a..731acea 100644 --- a/drivers/gpu/drm/nouveau/nouveau_state.c +++ b/drivers/gpu/drm/nouveau/nouveau_state.c @@ -371,7 +371,6 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev) engine->vram.flags_valid = nv50_vram_flags_valid; break; case 0xC0: - case 0xD0: engine->instmem.init = nvc0_instmem_init; engine->instmem.takedown = nvc0_instmem_takedown; engine->instmem.suspend = nvc0_instmem_suspend; @@ -923,7 +922,6 @@ int nouveau_load(struct drm_device *dev, unsigned long flags) dev_priv->card_type = NV_50; break; case 0xc0: - case 0xd0: dev_priv->card_type = NV_C0; break; default: diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 445af79..15bd047 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -985,17 +985,19 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav { save->vga_control[0] = RREG32(D1VGA_CONTROL); save->vga_control[1] = RREG32(D2VGA_CONTROL); - save->vga_control[2] = RREG32(EVERGREEN_D3VGA_CONTROL); - save->vga_control[3] = RREG32(EVERGREEN_D4VGA_CONTROL); - save->vga_control[4] = RREG32(EVERGREEN_D5VGA_CONTROL); - save->vga_control[5] = RREG32(EVERGREEN_D6VGA_CONTROL); save->vga_render_control = RREG32(VGA_RENDER_CONTROL); save->vga_hdp_control = RREG32(VGA_HDP_CONTROL); save->crtc_control[0] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET); save->crtc_control[1] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { + save->vga_control[2] = RREG32(EVERGREEN_D3VGA_CONTROL); + save->vga_control[3] = RREG32(EVERGREEN_D4VGA_CONTROL); save->crtc_control[2] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET); save->crtc_control[3] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET); + } + if (rdev->num_crtc >= 6) { + save->vga_control[4] = RREG32(EVERGREEN_D5VGA_CONTROL); + save->vga_control[5] = RREG32(EVERGREEN_D6VGA_CONTROL); save->crtc_control[4] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET); save->crtc_control[5] = RREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET); } @@ -1004,35 +1006,45 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav WREG32(VGA_RENDER_CONTROL, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 1); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 1); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 1); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 1); + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 1); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 1); } WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } WREG32(D1VGA_CONTROL, 0); WREG32(D2VGA_CONTROL, 0); - WREG32(EVERGREEN_D3VGA_CONTROL, 0); - WREG32(EVERGREEN_D4VGA_CONTROL, 0); - WREG32(EVERGREEN_D5VGA_CONTROL, 0); - WREG32(EVERGREEN_D6VGA_CONTROL, 0); + if (rdev->num_crtc >= 4) { + WREG32(EVERGREEN_D3VGA_CONTROL, 0); + WREG32(EVERGREEN_D4VGA_CONTROL, 0); + } + if (rdev->num_crtc >= 6) { + WREG32(EVERGREEN_D5VGA_CONTROL, 0); + WREG32(EVERGREEN_D6VGA_CONTROL, 0); + } } void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *save) @@ -1055,7 +1067,7 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC1_REGISTER_OFFSET, (u32)rdev->mc.vram_start); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC2_REGISTER_OFFSET, upper_32_bits(rdev->mc.vram_start)); WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC2_REGISTER_OFFSET, @@ -1073,7 +1085,8 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s (u32)rdev->mc.vram_start); WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS + EVERGREEN_CRTC3_REGISTER_OFFSET, (u32)rdev->mc.vram_start); - + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_GRPH_PRIMARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC4_REGISTER_OFFSET, upper_32_bits(rdev->mc.vram_start)); WREG32(EVERGREEN_GRPH_SECONDARY_SURFACE_ADDRESS_HIGH + EVERGREEN_CRTC4_REGISTER_OFFSET, @@ -1101,31 +1114,41 @@ void evergreen_mc_resume(struct radeon_device *rdev, struct evergreen_mc_save *s /* Restore video state */ WREG32(D1VGA_CONTROL, save->vga_control[0]); WREG32(D2VGA_CONTROL, save->vga_control[1]); - WREG32(EVERGREEN_D3VGA_CONTROL, save->vga_control[2]); - WREG32(EVERGREEN_D4VGA_CONTROL, save->vga_control[3]); - WREG32(EVERGREEN_D5VGA_CONTROL, save->vga_control[4]); - WREG32(EVERGREEN_D6VGA_CONTROL, save->vga_control[5]); + if (rdev->num_crtc >= 4) { + WREG32(EVERGREEN_D3VGA_CONTROL, save->vga_control[2]); + WREG32(EVERGREEN_D4VGA_CONTROL, save->vga_control[3]); + } + if (rdev->num_crtc >= 6) { + WREG32(EVERGREEN_D5VGA_CONTROL, save->vga_control[4]); + WREG32(EVERGREEN_D6VGA_CONTROL, save->vga_control[5]); + } WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 1); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 1); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 1); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 1); + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 1); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 1); } WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, save->crtc_control[0]); WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, save->crtc_control[1]); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, save->crtc_control[2]); WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, save->crtc_control[3]); + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, save->crtc_control[4]); WREG32(EVERGREEN_CRTC_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, save->crtc_control[5]); } WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 6) { WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); WREG32(EVERGREEN_CRTC_UPDATE_LOCK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } @@ -1977,7 +2000,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev) gb_backend_map = 0x66442200; break; case CHIP_JUNIPER: - gb_backend_map = 0x00006420; + gb_backend_map = 0x00002200; break; default: gb_backend_map = @@ -2013,9 +2036,9 @@ static void evergreen_gpu_init(struct radeon_device *rdev) rdev->config.evergreen.tile_config |= (3 << 0); break; } - /* num banks is 8 on all fusion asics */ + /* num banks is 8 on all fusion asics. 0 = 4, 1 = 8, 2 = 16 */ if (rdev->flags & RADEON_IS_IGP) - rdev->config.evergreen.tile_config |= 8 << 4; + rdev->config.evergreen.tile_config |= 1 << 4; else rdev->config.evergreen.tile_config |= ((mc_arb_ramcfg & NOOFBANK_MASK) >> NOOFBANK_SHIFT) << 4; @@ -2248,7 +2271,10 @@ int evergreen_mc_init(struct radeon_device *rdev) /* Get VRAM informations */ rdev->mc.vram_is_ddr = true; - tmp = RREG32(MC_ARB_RAMCFG); + if (rdev->flags & RADEON_IS_IGP) + tmp = RREG32(FUS_MC_ARB_RAMCFG); + else + tmp = RREG32(MC_ARB_RAMCFG); if (tmp & CHANSIZE_OVERRIDE) { chansize = 16; } else if (tmp & CHANSIZE_MASK) { @@ -2414,18 +2440,22 @@ void evergreen_disable_interrupt_state(struct radeon_device *rdev) WREG32(GRBM_INT_CNTL, 0); WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(INT_MASK + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); WREG32(INT_MASK + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 6) { WREG32(INT_MASK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); WREG32(INT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0); WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0); + } + if (rdev->num_crtc >= 6) { WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0); WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0); } @@ -2544,19 +2574,25 @@ int evergreen_irq_set(struct radeon_device *rdev) WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, crtc1); WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, crtc2); - if (!(rdev->flags & RADEON_IS_IGP)) { + if (rdev->num_crtc >= 4) { WREG32(INT_MASK + EVERGREEN_CRTC2_REGISTER_OFFSET, crtc3); WREG32(INT_MASK + EVERGREEN_CRTC3_REGISTER_OFFSET, crtc4); + } + if (rdev->num_crtc >= 6) { WREG32(INT_MASK + EVERGREEN_CRTC4_REGISTER_OFFSET, crtc5); WREG32(INT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6); } WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1); WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5); - WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6); + if (rdev->num_crtc >= 4) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4); + } + if (rdev->num_crtc >= 6) { + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5); + WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6); + } WREG32(DC_HPD1_INT_CONTROL, hpd1); WREG32(DC_HPD2_INT_CONTROL, hpd2); @@ -2580,53 +2616,57 @@ static inline void evergreen_irq_ack(struct radeon_device *rdev) rdev->irq.stat_regs.evergreen.disp_int_cont5 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE5); rdev->irq.stat_regs.evergreen.d1grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET); rdev->irq.stat_regs.evergreen.d2grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET); - rdev->irq.stat_regs.evergreen.d3grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET); - rdev->irq.stat_regs.evergreen.d4grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET); - rdev->irq.stat_regs.evergreen.d5grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET); - rdev->irq.stat_regs.evergreen.d6grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET); + if (rdev->num_crtc >= 4) { + rdev->irq.stat_regs.evergreen.d3grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET); + rdev->irq.stat_regs.evergreen.d4grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET); + } + if (rdev->num_crtc >= 6) { + rdev->irq.stat_regs.evergreen.d5grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET); + rdev->irq.stat_regs.evergreen.d6grph_int = RREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET); + } if (rdev->irq.stat_regs.evergreen.d1grph_int & GRPH_PFLIP_INT_OCCURRED) WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); if (rdev->irq.stat_regs.evergreen.d2grph_int & GRPH_PFLIP_INT_OCCURRED) WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); - if (rdev->irq.stat_regs.evergreen.d3grph_int & GRPH_PFLIP_INT_OCCURRED) - WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); - if (rdev->irq.stat_regs.evergreen.d4grph_int & GRPH_PFLIP_INT_OCCURRED) - WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); - if (rdev->irq.stat_regs.evergreen.d5grph_int & GRPH_PFLIP_INT_OCCURRED) - WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); - if (rdev->irq.stat_regs.evergreen.d6grph_int & GRPH_PFLIP_INT_OCCURRED) - WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); - if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT) WREG32(VBLANK_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, VBLANK_ACK); if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT) WREG32(VLINE_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, VLINE_ACK); - if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT) WREG32(VBLANK_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, VBLANK_ACK); if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT) WREG32(VLINE_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, VLINE_ACK); - if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) - WREG32(VBLANK_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VBLANK_ACK); - if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) - WREG32(VLINE_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VLINE_ACK); - - if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) - WREG32(VBLANK_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, VBLANK_ACK); - if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) - WREG32(VLINE_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, VLINE_ACK); - - if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) - WREG32(VBLANK_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VBLANK_ACK); - if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) - WREG32(VLINE_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VLINE_ACK); - - if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) - WREG32(VBLANK_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, VBLANK_ACK); - if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) - WREG32(VLINE_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, VLINE_ACK); + if (rdev->num_crtc >= 4) { + if (rdev->irq.stat_regs.evergreen.d3grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.evergreen.d4grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) + WREG32(VBLANK_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VBLANK_ACK); + if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) + WREG32(VLINE_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VLINE_ACK); + if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) + WREG32(VBLANK_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, VBLANK_ACK); + if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) + WREG32(VLINE_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET, VLINE_ACK); + } + + if (rdev->num_crtc >= 6) { + if (rdev->irq.stat_regs.evergreen.d5grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.evergreen.d6grph_int & GRPH_PFLIP_INT_OCCURRED) + WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, GRPH_PFLIP_INT_CLEAR); + if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) + WREG32(VBLANK_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VBLANK_ACK); + if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) + WREG32(VLINE_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VLINE_ACK); + if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) + WREG32(VBLANK_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, VBLANK_ACK); + if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) + WREG32(VLINE_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET, VLINE_ACK); + } if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT) { tmp = RREG32(DC_HPD1_INT_CONTROL); @@ -3234,6 +3274,7 @@ void evergreen_fini(struct radeon_device *rdev) r700_cp_fini(rdev); r600_irq_fini(rdev); radeon_wb_fini(rdev); + radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); evergreen_pcie_gart_fini(rdev); radeon_gem_fini(rdev); diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c index 57f3bc1..2eb2518 100644 --- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c +++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c @@ -252,7 +252,7 @@ draw_auto(struct radeon_device *rdev) } -/* emits 36 */ +/* emits 39 */ static void set_default_state(struct radeon_device *rdev) { @@ -531,6 +531,11 @@ set_default_state(struct radeon_device *rdev) radeon_ring_write(rdev, (SQ_DYN_GPR_CNTL_PS_FLUSH_REQ - PACKET3_SET_CONFIG_REG_START) >> 2); radeon_ring_write(rdev, 0); + /* setup LDS */ + radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 1)); + radeon_ring_write(rdev, (SQ_LDS_RESOURCE_MGMT - PACKET3_SET_CONFIG_REG_START) >> 2); + radeon_ring_write(rdev, 0x10001000); + /* SQ config */ radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 11)); radeon_ring_write(rdev, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_START) >> 2); @@ -773,7 +778,7 @@ int evergreen_blit_prepare_copy(struct radeon_device *rdev, int size_bytes) /* calculate number of loops correctly */ ring_size = num_loops * dwords_per_loop; /* set default + shaders */ - ring_size += 52; /* shaders + def state */ + ring_size += 55; /* shaders + def state */ ring_size += 10; /* fence emit for VB IB */ ring_size += 5; /* done copy */ ring_size += 10; /* fence emit for done copy */ diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index 1636e34..b7b2714 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -466,7 +466,7 @@ #define IH_RB_WPTR_ADDR_LO 0x3e14 #define IH_CNTL 0x3e18 # define ENABLE_INTR (1 << 0) -# define IH_MC_SWAP(x) ((x) << 2) +# define IH_MC_SWAP(x) ((x) << 1) # define IH_MC_SWAP_NONE 0 # define IH_MC_SWAP_16BIT 1 # define IH_MC_SWAP_32BIT 2 @@ -547,7 +547,7 @@ # define LB_D5_VBLANK_INTERRUPT (1 << 3) # define DC_HPD5_INTERRUPT (1 << 17) # define DC_HPD5_RX_INTERRUPT (1 << 18) -#define DISP_INTERRUPT_STATUS_CONTINUE5 0x6050 +#define DISP_INTERRUPT_STATUS_CONTINUE5 0x6150 # define LB_D6_VLINE_INTERRUPT (1 << 2) # define LB_D6_VBLANK_INTERRUPT (1 << 3) # define DC_HPD6_INTERRUPT (1 << 17) diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 16caafe..559dbd4 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1581,6 +1581,7 @@ void cayman_fini(struct radeon_device *rdev) cayman_cp_fini(rdev); r600_irq_fini(rdev); radeon_wb_fini(rdev); + radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); cayman_pcie_gart_fini(rdev); radeon_gem_fini(rdev); diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h index 9736746..4672869 100644 --- a/drivers/gpu/drm/radeon/nid.h +++ b/drivers/gpu/drm/radeon/nid.h @@ -320,7 +320,7 @@ #define CGTS_USER_TCC_DISABLE 0x914C #define TCC_DISABLE_MASK 0xFFFF0000 #define TCC_DISABLE_SHIFT 16 -#define CGTS_SM_CTRL_REG 0x915C +#define CGTS_SM_CTRL_REG 0x9150 #define OVERRIDE (1 << 21) #define TA_CNTL_AUX 0x9508 diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index f79d2cc..bc54b26 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -2628,6 +2628,7 @@ void r600_fini(struct radeon_device *rdev) r600_cp_fini(rdev); r600_irq_fini(rdev); radeon_wb_fini(rdev); + radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); r600_pcie_gart_fini(rdev); radeon_agp_fini(rdev); diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h index f140a0d..0245ae6 100644 --- a/drivers/gpu/drm/radeon/r600d.h +++ b/drivers/gpu/drm/radeon/r600d.h @@ -536,7 +536,7 @@ #define IH_RB_WPTR_ADDR_LO 0x3e14 #define IH_CNTL 0x3e18 # define ENABLE_INTR (1 << 0) -# define IH_MC_SWAP(x) ((x) << 2) +# define IH_MC_SWAP(x) ((x) << 1) # define IH_MC_SWAP_NONE 0 # define IH_MC_SWAP_16BIT 1 # define IH_MC_SWAP_32BIT 2 diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 27f4557..ef0e0e0 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -179,6 +179,7 @@ void radeon_pm_resume(struct radeon_device *rdev); void radeon_combios_get_power_modes(struct radeon_device *rdev); void radeon_atombios_get_power_modes(struct radeon_device *rdev); void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 voltage_type); +int radeon_atom_get_max_vddc(struct radeon_device *rdev, u16 *voltage); void rs690_pm_info(struct radeon_device *rdev); extern int rv6xx_get_temp(struct radeon_device *rdev); extern int rv770_get_temp(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 1e725d9..bf2b615 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -2320,6 +2320,14 @@ static bool radeon_atombios_parse_pplib_clock_info(struct radeon_device *rdev, le16_to_cpu(clock_info->r600.usVDDC); } + /* patch up vddc if necessary */ + if (rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage == 0xff01) { + u16 vddc; + + if (radeon_atom_get_max_vddc(rdev, &vddc) == 0) + rdev->pm.power_state[state_index].clock_info[mode_index].voltage.voltage = vddc; + } + if (rdev->flags & RADEON_IS_IGP) { /* skip invalid modes */ if (rdev->pm.power_state[state_index].clock_info[mode_index].sclk == 0) @@ -2630,7 +2638,35 @@ void radeon_atom_set_voltage(struct radeon_device *rdev, u16 voltage_level, u8 v atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); } +int radeon_atom_get_max_vddc(struct radeon_device *rdev, + u16 *voltage) +{ + union set_voltage args; + int index = GetIndexIntoMasterTable(COMMAND, SetVoltage); + u8 frev, crev; + + if (!atom_parse_cmd_header(rdev->mode_info.atom_context, index, &frev, &crev)) + return -EINVAL; + + switch (crev) { + case 1: + return -EINVAL; + case 2: + args.v2.ucVoltageType = SET_VOLTAGE_GET_MAX_VOLTAGE; + args.v2.ucVoltageMode = 0; + args.v2.usVoltageLevel = 0; + + atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args); + + *voltage = le16_to_cpu(args.v2.usVoltageLevel); + break; + default: + DRM_ERROR("Unknown table version %d, %d\n", frev, crev); + return -EINVAL; + } + return 0; +} void radeon_atom_initialize_bios_scratch_regs(struct drm_device *dev) { diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 1aba85c..229a20f 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -104,7 +104,7 @@ static bool radeon_read_bios(struct radeon_device *rdev) static bool radeon_atrm_get_bios(struct radeon_device *rdev) { int ret; - int size = 64 * 1024; + int size = 256 * 1024; int i; if (!radeon_atrm_supported(rdev->pdev)) @@ -331,7 +331,7 @@ static bool avivo_read_disabled_bios(struct radeon_device *rdev) seprom_cntl1 = RREG32(RADEON_SEPROM_CNTL1); viph_control = RREG32(RADEON_VIPH_CONTROL); - bus_cntl = RREG32(RADEON_BUS_CNTL); + bus_cntl = RREG32(RV370_BUS_CNTL); d1vga_control = RREG32(AVIVO_D1VGA_CONTROL); d2vga_control = RREG32(AVIVO_D2VGA_CONTROL); vga_render_control = RREG32(AVIVO_VGA_RENDER_CONTROL); @@ -350,7 +350,7 @@ static bool avivo_read_disabled_bios(struct radeon_device *rdev) WREG32(RADEON_VIPH_CONTROL, (viph_control & ~RADEON_VIPH_EN)); /* enable the rom */ - WREG32(RADEON_BUS_CNTL, (bus_cntl & ~RADEON_BUS_BIOS_DIS_ROM)); + WREG32(RV370_BUS_CNTL, (bus_cntl & ~RV370_BUS_BIOS_DIS_ROM)); /* Disable VGA mode */ WREG32(AVIVO_D1VGA_CONTROL, @@ -367,7 +367,7 @@ static bool avivo_read_disabled_bios(struct radeon_device *rdev) /* restore regs */ WREG32(RADEON_SEPROM_CNTL1, seprom_cntl1); WREG32(RADEON_VIPH_CONTROL, viph_control); - WREG32(RADEON_BUS_CNTL, bus_cntl); + WREG32(RV370_BUS_CNTL, bus_cntl); WREG32(AVIVO_D1VGA_CONTROL, d1vga_control); WREG32(AVIVO_D2VGA_CONTROL, d2vga_control); WREG32(AVIVO_VGA_RENDER_CONTROL, vga_render_control); @@ -390,7 +390,10 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev) seprom_cntl1 = RREG32(RADEON_SEPROM_CNTL1); viph_control = RREG32(RADEON_VIPH_CONTROL); - bus_cntl = RREG32(RADEON_BUS_CNTL); + if (rdev->flags & RADEON_IS_PCIE) + bus_cntl = RREG32(RV370_BUS_CNTL); + else + bus_cntl = RREG32(RADEON_BUS_CNTL); crtc_gen_cntl = RREG32(RADEON_CRTC_GEN_CNTL); crtc2_gen_cntl = 0; crtc_ext_cntl = RREG32(RADEON_CRTC_EXT_CNTL); @@ -412,7 +415,10 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev) WREG32(RADEON_VIPH_CONTROL, (viph_control & ~RADEON_VIPH_EN)); /* enable the rom */ - WREG32(RADEON_BUS_CNTL, (bus_cntl & ~RADEON_BUS_BIOS_DIS_ROM)); + if (rdev->flags & RADEON_IS_PCIE) + WREG32(RV370_BUS_CNTL, (bus_cntl & ~RV370_BUS_BIOS_DIS_ROM)); + else + WREG32(RADEON_BUS_CNTL, (bus_cntl & ~RADEON_BUS_BIOS_DIS_ROM)); /* Turn off mem requests and CRTC for both controllers */ WREG32(RADEON_CRTC_GEN_CNTL, @@ -439,7 +445,10 @@ static bool legacy_read_disabled_bios(struct radeon_device *rdev) /* restore regs */ WREG32(RADEON_SEPROM_CNTL1, seprom_cntl1); WREG32(RADEON_VIPH_CONTROL, viph_control); - WREG32(RADEON_BUS_CNTL, bus_cntl); + if (rdev->flags & RADEON_IS_PCIE) + WREG32(RV370_BUS_CNTL, bus_cntl); + else + WREG32(RADEON_BUS_CNTL, bus_cntl); WREG32(RADEON_CRTC_GEN_CNTL, crtc_gen_cntl); if (!(rdev->flags & RADEON_SINGLE_CRTC)) { WREG32(RADEON_CRTC2_GEN_CNTL, crtc2_gen_cntl); diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index cbfca3a..9792d4f 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -52,6 +52,12 @@ void radeon_connector_hotplug(struct drm_connector *connector) struct radeon_device *rdev = dev->dev_private; struct radeon_connector *radeon_connector = to_radeon_connector(connector); + /* bail if the connector does not have hpd pin, e.g., + * VGA, TV, etc. + */ + if (radeon_connector->hpd.hpd == RADEON_HPD_NONE) + return; + radeon_hpd_set_polarity(rdev, radeon_connector->hpd.hpd); /* powering up/down the eDP panel generates hpd events which diff --git a/drivers/gpu/drm/radeon/radeon_reg.h b/drivers/gpu/drm/radeon/radeon_reg.h index ec93a75..bc44a3d 100644 --- a/drivers/gpu/drm/radeon/radeon_reg.h +++ b/drivers/gpu/drm/radeon/radeon_reg.h @@ -300,6 +300,8 @@ # define RADEON_BUS_READ_BURST (1 << 30) #define RADEON_BUS_CNTL1 0x0034 # define RADEON_BUS_WAIT_ON_LOCK_EN (1 << 4) +#define RV370_BUS_CNTL 0x004c +# define RV370_BUS_BIOS_DIS_ROM (1 << 2) /* rv370/rv380, rv410, r423/r430/r480, r5xx */ #define RADEON_MSI_REARM_EN 0x0160 # define RV370_MSI_REARM_EN (1 << 0) diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c index 6e3b11e..1f5850e 100644 --- a/drivers/gpu/drm/radeon/rs600.c +++ b/drivers/gpu/drm/radeon/rs600.c @@ -426,7 +426,7 @@ int rs600_gart_init(struct radeon_device *rdev) return radeon_gart_table_vram_alloc(rdev); } -int rs600_gart_enable(struct radeon_device *rdev) +static int rs600_gart_enable(struct radeon_device *rdev) { u32 tmp; int r, i; @@ -440,8 +440,8 @@ int rs600_gart_enable(struct radeon_device *rdev) return r; radeon_gart_restore(rdev); /* Enable bus master */ - tmp = RREG32(R_00004C_BUS_CNTL) & C_00004C_BUS_MASTER_DIS; - WREG32(R_00004C_BUS_CNTL, tmp); + tmp = RREG32(RADEON_BUS_CNTL) & ~RS600_BUS_MASTER_DIS; + WREG32(RADEON_BUS_CNTL, tmp); /* FIXME: setup default page */ WREG32_MC(R_000100_MC_PT0_CNTL, (S_000100_EFFECTIVE_L2_CACHE_SIZE(6) | diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index 6f508ff..4de5189 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -575,6 +575,12 @@ static void rv770_program_channel_remap(struct radeon_device *rdev) else tcp_chan_steer = 0x00fac688; + /* RV770 CE has special chremap setup */ + if (rdev->pdev->device == 0x944e) { + tcp_chan_steer = 0x00b08b08; + mc_shared_chremap = 0x00b08b08; + } + WREG32(TCP_CHAN_STEER, tcp_chan_steer); WREG32(MC_SHARED_CHREMAP, mc_shared_chremap); } @@ -1362,6 +1368,7 @@ void rv770_fini(struct radeon_device *rdev) r700_cp_fini(rdev); r600_irq_fini(rdev); radeon_wb_fini(rdev); + radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); rv770_pcie_gart_fini(rdev); rv770_vram_scratch_fini(rdev); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 90e23e0..58c271e 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -31,6 +31,7 @@ #include <linux/sched.h> #include <linux/highmem.h> #include <linux/pagemap.h> +#include <linux/shmem_fs.h> #include <linux/file.h> #include <linux/swap.h> #include <linux/slab.h> @@ -484,7 +485,7 @@ static int ttm_tt_swapin(struct ttm_tt *ttm) swap_space = swap_storage->f_path.dentry->d_inode->i_mapping; for (i = 0; i < ttm->num_pages; ++i) { - from_page = read_mapping_page(swap_space, i, NULL); + from_page = shmem_read_mapping_page(swap_space, i); if (IS_ERR(from_page)) { ret = PTR_ERR(from_page); goto out_err; @@ -557,7 +558,7 @@ int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage) from_page = ttm->pages[i]; if (unlikely(from_page == NULL)) continue; - to_page = read_mapping_page(swap_space, i, NULL); + to_page = shmem_read_mapping_page(swap_space, i); if (unlikely(IS_ERR(to_page))) { ret = PTR_ERR(to_page); goto out_err; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index f7440e8..6f3289a 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1423,6 +1423,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACETRAVELLER) }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACENAVIGATOR) }, { HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH_DUAL) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICOLCD) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROCHIP, USB_DEVICE_ID_PICOLCD_BOOTLOADER) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_SIDEWINDER_GV) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index aecb5a4..a756ee6 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -449,6 +449,7 @@ #define USB_VENDOR_ID_LUMIO 0x202e #define USB_DEVICE_ID_CRYSTALTOUCH 0x0006 +#define USB_DEVICE_ID_CRYSTALTOUCH_DUAL 0x0007 #define USB_VENDOR_ID_MCC 0x09db #define USB_DEVICE_ID_MCC_PMD1024LS 0x0076 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 0b2dcd0..62cac4d 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -271,6 +271,8 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi, } return 1; case HID_DG_CONTACTID: + if (!td->maxcontacts) + td->maxcontacts = MT_DEFAULT_MAXCONTACT; input_mt_init_slots(hi->input, td->maxcontacts); td->last_slot_field = usage->hid; td->last_field_index = field->index; @@ -547,9 +549,6 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) goto fail; - if (!td->maxcontacts) - td->maxcontacts = MT_DEFAULT_MAXCONTACT; - td->slots = kzalloc(td->maxcontacts * sizeof(struct mt_slot), GFP_KERNEL); if (!td->slots) { @@ -677,6 +676,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, USB_DEVICE_ID_CRYSTALTOUCH) }, + { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, + HID_USB_DEVICE(USB_VENDOR_ID_LUMIO, + USB_DEVICE_ID_CRYSTALTOUCH_DUAL) }, /* MosArt panels */ { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, @@ -707,10 +709,10 @@ static const struct hid_device_id mt_devices[] = { HID_USB_DEVICE(USB_VENDOR_ID_STANTUM, USB_DEVICE_ID_MTP)}, { .driver_data = MT_CLS_CONFIDENCE, - HID_USB_DEVICE(USB_VENDOR_ID_STANTUM, + HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_STM, USB_DEVICE_ID_MTP_STM)}, { .driver_data = MT_CLS_CONFIDENCE, - HID_USB_DEVICE(USB_VENDOR_ID_STANTUM, + HID_USB_DEVICE(USB_VENDOR_ID_STANTUM_SITRONIX, USB_DEVICE_ID_MTP_SITRONIX)}, /* Touch International panels */ diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index 16db83c..5f888f7 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -333,7 +333,7 @@ config SENSORS_F71882FG F71858FG F71862FG F71863FG - F71869F/E + F71869F/E/A F71882FG F71883FG F71889FG/ED/A diff --git a/drivers/hwmon/adm1275.c b/drivers/hwmon/adm1275.c index c2ee204..8bc1bd6 100644 --- a/drivers/hwmon/adm1275.c +++ b/drivers/hwmon/adm1275.c @@ -32,6 +32,7 @@ static int adm1275_probe(struct i2c_client *client, const struct i2c_device_id *id) { int config; + int ret; struct pmbus_driver_info *info; if (!i2c_check_functionality(client->adapter, @@ -43,30 +44,32 @@ static int adm1275_probe(struct i2c_client *client, return -ENOMEM; config = i2c_smbus_read_byte_data(client, ADM1275_PMON_CONFIG); - if (config < 0) - return config; + if (config < 0) { + ret = config; + goto err_mem; + } info->pages = 1; info->direct[PSC_VOLTAGE_IN] = true; info->direct[PSC_VOLTAGE_OUT] = true; info->direct[PSC_CURRENT_OUT] = true; - info->m[PSC_CURRENT_OUT] = 800; + info->m[PSC_CURRENT_OUT] = 807; info->b[PSC_CURRENT_OUT] = 20475; info->R[PSC_CURRENT_OUT] = -1; info->func[0] = PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT; if (config & ADM1275_VRANGE) { - info->m[PSC_VOLTAGE_IN] = 19045; + info->m[PSC_VOLTAGE_IN] = 19199; info->b[PSC_VOLTAGE_IN] = 0; info->R[PSC_VOLTAGE_IN] = -2; - info->m[PSC_VOLTAGE_OUT] = 19045; + info->m[PSC_VOLTAGE_OUT] = 19199; info->b[PSC_VOLTAGE_OUT] = 0; info->R[PSC_VOLTAGE_OUT] = -2; } else { - info->m[PSC_VOLTAGE_IN] = 6666; + info->m[PSC_VOLTAGE_IN] = 6720; info->b[PSC_VOLTAGE_IN] = 0; info->R[PSC_VOLTAGE_IN] = -1; - info->m[PSC_VOLTAGE_OUT] = 6666; + info->m[PSC_VOLTAGE_OUT] = 6720; info->b[PSC_VOLTAGE_OUT] = 0; info->R[PSC_VOLTAGE_OUT] = -1; } @@ -76,7 +79,14 @@ static int adm1275_probe(struct i2c_client *client, else info->func[0] |= PMBUS_HAVE_VIN | PMBUS_HAVE_STATUS_INPUT; - return pmbus_do_probe(client, id, info); + ret = pmbus_do_probe(client, id, info); + if (ret) + goto err_mem; + return 0; + +err_mem: + kfree(info); + return ret; } static int adm1275_remove(struct i2c_client *client) diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index dcb78a7..00e9851 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -674,6 +674,7 @@ static int atk_debugfs_gitm_get(void *p, u64 *val) else err = -EIO; + ACPI_FREE(ret); return err; } diff --git a/drivers/hwmon/emc6w201.c b/drivers/hwmon/emc6w201.c index e0ef323..0064432 100644 --- a/drivers/hwmon/emc6w201.c +++ b/drivers/hwmon/emc6w201.c @@ -78,8 +78,9 @@ static u16 emc6w201_read16(struct i2c_client *client, u8 reg) lsb = i2c_smbus_read_byte_data(client, reg); msb = i2c_smbus_read_byte_data(client, reg + 1); - if (lsb < 0 || msb < 0) { - dev_err(&client->dev, "16-bit read failed at 0x%02x\n", reg); + if (unlikely(lsb < 0 || msb < 0)) { + dev_err(&client->dev, "%d-bit %s failed at 0x%02x\n", + 16, "read", reg); return 0xFFFF; /* Arbitrary value */ } @@ -95,10 +96,39 @@ static int emc6w201_write16(struct i2c_client *client, u8 reg, u16 val) int err; err = i2c_smbus_write_byte_data(client, reg, val & 0xff); - if (!err) + if (likely(!err)) err = i2c_smbus_write_byte_data(client, reg + 1, val >> 8); - if (err < 0) - dev_err(&client->dev, "16-bit write failed at 0x%02x\n", reg); + if (unlikely(err < 0)) + dev_err(&client->dev, "%d-bit %s failed at 0x%02x\n", + 16, "write", reg); + + return err; +} + +/* Read 8-bit value from register */ +static u8 emc6w201_read8(struct i2c_client *client, u8 reg) +{ + int val; + + val = i2c_smbus_read_byte_data(client, reg); + if (unlikely(val < 0)) { + dev_err(&client->dev, "%d-bit %s failed at 0x%02x\n", + 8, "read", reg); + return 0x00; /* Arbitrary value */ + } + + return val; +} + +/* Write 8-bit value to register */ +static int emc6w201_write8(struct i2c_client *client, u8 reg, u8 val) +{ + int err; + + err = i2c_smbus_write_byte_data(client, reg, val); + if (unlikely(err < 0)) + dev_err(&client->dev, "%d-bit %s failed at 0x%02x\n", + 8, "write", reg); return err; } @@ -114,25 +144,25 @@ static struct emc6w201_data *emc6w201_update_device(struct device *dev) if (time_after(jiffies, data->last_updated + HZ) || !data->valid) { for (nr = 0; nr < 6; nr++) { data->in[input][nr] = - i2c_smbus_read_byte_data(client, + emc6w201_read8(client, EMC6W201_REG_IN(nr)); data->in[min][nr] = - i2c_smbus_read_byte_data(client, + emc6w201_read8(client, EMC6W201_REG_IN_LOW(nr)); data->in[max][nr] = - i2c_smbus_read_byte_data(client, + emc6w201_read8(client, EMC6W201_REG_IN_HIGH(nr)); } for (nr = 0; nr < 6; nr++) { data->temp[input][nr] = - i2c_smbus_read_byte_data(client, + emc6w201_read8(client, EMC6W201_REG_TEMP(nr)); data->temp[min][nr] = - i2c_smbus_read_byte_data(client, + emc6w201_read8(client, EMC6W201_REG_TEMP_LOW(nr)); data->temp[max][nr] = - i2c_smbus_read_byte_data(client, + emc6w201_read8(client, EMC6W201_REG_TEMP_HIGH(nr)); } @@ -192,7 +222,7 @@ static ssize_t set_in(struct device *dev, struct device_attribute *devattr, mutex_lock(&data->update_lock); data->in[sf][nr] = SENSORS_LIMIT(val, 0, 255); - err = i2c_smbus_write_byte_data(client, reg, data->in[sf][nr]); + err = emc6w201_write8(client, reg, data->in[sf][nr]); mutex_unlock(&data->update_lock); return err < 0 ? err : count; @@ -229,7 +259,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr, mutex_lock(&data->update_lock); data->temp[sf][nr] = SENSORS_LIMIT(val, -127, 128); - err = i2c_smbus_write_byte_data(client, reg, data->temp[sf][nr]); + err = emc6w201_write8(client, reg, data->temp[sf][nr]); mutex_unlock(&data->update_lock); return err < 0 ? err : count; @@ -444,7 +474,7 @@ static int emc6w201_detect(struct i2c_client *client, /* Check configuration */ config = i2c_smbus_read_byte_data(client, EMC6W201_REG_CONFIG); - if ((config & 0xF4) != 0x04) + if (config < 0 || (config & 0xF4) != 0x04) return -ENODEV; if (!(config & 0x01)) { dev_err(&client->dev, "Monitoring not enabled\n"); diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c index a4a94a0..2d96ed2 100644 --- a/drivers/hwmon/f71882fg.c +++ b/drivers/hwmon/f71882fg.c @@ -52,6 +52,7 @@ #define SIO_F71858_ID 0x0507 /* Chipset ID */ #define SIO_F71862_ID 0x0601 /* Chipset ID */ #define SIO_F71869_ID 0x0814 /* Chipset ID */ +#define SIO_F71869A_ID 0x1007 /* Chipset ID */ #define SIO_F71882_ID 0x0541 /* Chipset ID */ #define SIO_F71889_ID 0x0723 /* Chipset ID */ #define SIO_F71889E_ID 0x0909 /* Chipset ID */ @@ -108,8 +109,8 @@ static unsigned short force_id; module_param(force_id, ushort, 0); MODULE_PARM_DESC(force_id, "Override the detected device ID"); -enum chips { f71808e, f71808a, f71858fg, f71862fg, f71869, f71882fg, f71889fg, - f71889ed, f71889a, f8000, f81865f }; +enum chips { f71808e, f71808a, f71858fg, f71862fg, f71869, f71869a, f71882fg, + f71889fg, f71889ed, f71889a, f8000, f81865f }; static const char *f71882fg_names[] = { "f71808e", @@ -117,6 +118,7 @@ static const char *f71882fg_names[] = { "f71858fg", "f71862fg", "f71869", /* Both f71869f and f71869e, reg. compatible and same id */ + "f71869a", "f71882fg", "f71889fg", /* f81801u too, same id */ "f71889ed", @@ -131,6 +133,7 @@ static const char f71882fg_has_in[][F71882FG_MAX_INS] = { [f71858fg] = { 1, 1, 1, 0, 0, 0, 0, 0, 0 }, [f71862fg] = { 1, 1, 1, 1, 1, 1, 1, 1, 1 }, [f71869] = { 1, 1, 1, 1, 1, 1, 1, 1, 1 }, + [f71869a] = { 1, 1, 1, 1, 1, 1, 1, 1, 1 }, [f71882fg] = { 1, 1, 1, 1, 1, 1, 1, 1, 1 }, [f71889fg] = { 1, 1, 1, 1, 1, 1, 1, 1, 1 }, [f71889ed] = { 1, 1, 1, 1, 1, 1, 1, 1, 1 }, @@ -145,6 +148,7 @@ static const char f71882fg_has_in1_alarm[] = { [f71858fg] = 0, [f71862fg] = 0, [f71869] = 0, + [f71869a] = 0, [f71882fg] = 1, [f71889fg] = 1, [f71889ed] = 1, @@ -159,6 +163,7 @@ static const char f71882fg_fan_has_beep[] = { [f71858fg] = 0, [f71862fg] = 1, [f71869] = 1, + [f71869a] = 1, [f71882fg] = 1, [f71889fg] = 1, [f71889ed] = 1, @@ -173,6 +178,7 @@ static const char f71882fg_nr_fans[] = { [f71858fg] = 3, [f71862fg] = 3, [f71869] = 3, + [f71869a] = 3, [f71882fg] = 4, [f71889fg] = 3, [f71889ed] = 3, @@ -187,6 +193,7 @@ static const char f71882fg_temp_has_beep[] = { [f71858fg] = 0, [f71862fg] = 1, [f71869] = 1, + [f71869a] = 1, [f71882fg] = 1, [f71889fg] = 1, [f71889ed] = 1, @@ -201,6 +208,7 @@ static const char f71882fg_nr_temps[] = { [f71858fg] = 3, [f71862fg] = 3, [f71869] = 3, + [f71869a] = 3, [f71882fg] = 3, [f71889fg] = 3, [f71889ed] = 3, @@ -2243,6 +2251,7 @@ static int __devinit f71882fg_probe(struct platform_device *pdev) case f71808e: case f71808a: case f71869: + case f71869a: /* These always have signed auto point temps */ data->auto_point_temp_signed = 1; /* Fall through to select correct fan/pwm reg bank! */ @@ -2305,6 +2314,7 @@ static int __devinit f71882fg_probe(struct platform_device *pdev) case f71808e: case f71808a: case f71869: + case f71869a: case f71889fg: case f71889ed: case f71889a: @@ -2528,6 +2538,9 @@ static int __init f71882fg_find(int sioaddr, unsigned short *address, case SIO_F71869_ID: sio_data->type = f71869; break; + case SIO_F71869A_ID: + sio_data->type = f71869a; + break; case SIO_F71882_ID: sio_data->type = f71882fg; break; @@ -2662,7 +2675,7 @@ static void __exit f71882fg_exit(void) } MODULE_DESCRIPTION("F71882FG Hardware Monitoring Driver"); -MODULE_AUTHOR("Hans Edgington, Hans de Goede (hdegoede@redhat.com)"); +MODULE_AUTHOR("Hans Edgington, Hans de Goede <hdegoede@redhat.com>"); MODULE_LICENSE("GPL"); module_init(f71882fg_init); diff --git a/drivers/hwmon/hwmon-vid.c b/drivers/hwmon/hwmon-vid.c index 2582bfe..c8195a0 100644 --- a/drivers/hwmon/hwmon-vid.c +++ b/drivers/hwmon/hwmon-vid.c @@ -202,7 +202,7 @@ static struct vrm_model vrm_models[] = { {X86_VENDOR_CENTAUR, 0x6, 0x7, ANY, 85}, /* Eden ESP/Ezra */ {X86_VENDOR_CENTAUR, 0x6, 0x8, 0x7, 85}, /* Ezra T */ - {X86_VENDOR_CENTAUR, 0x6, 0x9, 0x7, 85}, /* Nemiah */ + {X86_VENDOR_CENTAUR, 0x6, 0x9, 0x7, 85}, /* Nehemiah */ {X86_VENDOR_CENTAUR, 0x6, 0x9, ANY, 17}, /* C3-M, Eden-N */ {X86_VENDOR_CENTAUR, 0x6, 0xA, 0x7, 0}, /* No information */ {X86_VENDOR_CENTAUR, 0x6, 0xA, ANY, 13}, /* C7, Esther */ diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index bb6405b..5f52477 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -1538,7 +1538,7 @@ static struct attribute *it87_attributes_label[] = { }; static const struct attribute_group it87_group_label = { - .attrs = it87_attributes_vid, + .attrs = it87_attributes_label, }; /* SuperIO detection - will change isa_address if a chip is found */ diff --git a/drivers/hwmon/lm95241.c b/drivers/hwmon/lm95241.c index 1a6dfb6..d3b464b 100644 --- a/drivers/hwmon/lm95241.c +++ b/drivers/hwmon/lm95241.c @@ -98,11 +98,16 @@ struct lm95241_data { }; /* Conversions */ -static int TempFromReg(u8 val_h, u8 val_l) +static int temp_from_reg_signed(u8 val_h, u8 val_l) { - if (val_h & 0x80) - return val_h - 0x100; - return val_h * 1000 + val_l * 1000 / 256; + s16 val_hl = (val_h << 8) | val_l; + return val_hl * 1000 / 256; +} + +static int temp_from_reg_unsigned(u8 val_h, u8 val_l) +{ + u16 val_hl = (val_h << 8) | val_l; + return val_hl * 1000 / 256; } static struct lm95241_data *lm95241_update_device(struct device *dev) @@ -135,10 +140,13 @@ static ssize_t show_input(struct device *dev, struct device_attribute *attr, char *buf) { struct lm95241_data *data = lm95241_update_device(dev); + int index = to_sensor_dev_attr(attr)->index; return snprintf(buf, PAGE_SIZE - 1, "%d\n", - TempFromReg(data->temp[to_sensor_dev_attr(attr)->index], - data->temp[to_sensor_dev_attr(attr)->index + 1])); + index == 0 || (data->config & (1 << (index / 2))) ? + temp_from_reg_signed(data->temp[index], data->temp[index + 1]) : + temp_from_reg_unsigned(data->temp[index], + data->temp[index + 1])); } static ssize_t show_type(struct device *dev, struct device_attribute *attr, @@ -339,7 +347,7 @@ static int lm95241_detect(struct i2c_client *new_client, if ((i2c_smbus_read_byte_data(new_client, LM95241_REG_R_MAN_ID) == MANUFACTURER_ID) && (i2c_smbus_read_byte_data(new_client, LM95241_REG_R_CHIP_ID) - >= DEFAULT_REVISION)) { + == DEFAULT_REVISION)) { name = DEVNAME; } else { dev_dbg(&adapter->dev, "LM95241 detection failed at 0x%02x\n", diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c index 12a54aa..14335bb 100644 --- a/drivers/hwmon/max1111.c +++ b/drivers/hwmon/max1111.c @@ -40,6 +40,8 @@ struct max1111_data { struct spi_transfer xfer[2]; uint8_t *tx_buf; uint8_t *rx_buf; + struct mutex drvdata_lock; + /* protect msg, xfer and buffers from multiple access */ }; static int max1111_read(struct device *dev, int channel) @@ -48,6 +50,9 @@ static int max1111_read(struct device *dev, int channel) uint8_t v1, v2; int err; + /* writing to drvdata struct is not thread safe, wait on mutex */ + mutex_lock(&data->drvdata_lock); + data->tx_buf[0] = (channel << MAX1111_CTRL_SEL_SH) | MAX1111_CTRL_PD0 | MAX1111_CTRL_PD1 | MAX1111_CTRL_SGL | MAX1111_CTRL_UNI | MAX1111_CTRL_STR; @@ -55,12 +60,15 @@ static int max1111_read(struct device *dev, int channel) err = spi_sync(data->spi, &data->msg); if (err < 0) { dev_err(dev, "spi_sync failed with %d\n", err); + mutex_unlock(&data->drvdata_lock); return err; } v1 = data->rx_buf[0]; v2 = data->rx_buf[1]; + mutex_unlock(&data->drvdata_lock); + if ((v1 & 0xc0) || (v2 & 0x3f)) return -EINVAL; @@ -176,6 +184,8 @@ static int __devinit max1111_probe(struct spi_device *spi) if (err) goto err_free_data; + mutex_init(&data->drvdata_lock); + data->spi = spi; spi_set_drvdata(spi, data); @@ -213,6 +223,7 @@ static int __devexit max1111_remove(struct spi_device *spi) hwmon_device_unregister(data->hwmon_dev); sysfs_remove_group(&spi->dev.kobj, &max1111_attr_group); + mutex_destroy(&data->drvdata_lock); kfree(data->rx_buf); kfree(data->tx_buf); kfree(data); diff --git a/drivers/hwmon/pmbus.c b/drivers/hwmon/pmbus.c index 98e2e28..9b1f0c3 100644 --- a/drivers/hwmon/pmbus.c +++ b/drivers/hwmon/pmbus.c @@ -47,22 +47,29 @@ static void pmbus_find_sensor_groups(struct i2c_client *client, if (info->func[0] && pmbus_check_byte_register(client, 0, PMBUS_STATUS_INPUT)) info->func[0] |= PMBUS_HAVE_STATUS_INPUT; - if (pmbus_check_word_register(client, 0, PMBUS_READ_FAN_SPEED_1)) { + if (pmbus_check_byte_register(client, 0, PMBUS_FAN_CONFIG_12) && + pmbus_check_word_register(client, 0, PMBUS_READ_FAN_SPEED_1)) { info->func[0] |= PMBUS_HAVE_FAN12; if (pmbus_check_byte_register(client, 0, PMBUS_STATUS_FAN_12)) info->func[0] |= PMBUS_HAVE_STATUS_FAN12; } - if (pmbus_check_word_register(client, 0, PMBUS_READ_FAN_SPEED_3)) { + if (pmbus_check_byte_register(client, 0, PMBUS_FAN_CONFIG_34) && + pmbus_check_word_register(client, 0, PMBUS_READ_FAN_SPEED_3)) { info->func[0] |= PMBUS_HAVE_FAN34; if (pmbus_check_byte_register(client, 0, PMBUS_STATUS_FAN_34)) info->func[0] |= PMBUS_HAVE_STATUS_FAN34; } - if (pmbus_check_word_register(client, 0, PMBUS_READ_TEMPERATURE_1)) { + if (pmbus_check_word_register(client, 0, PMBUS_READ_TEMPERATURE_1)) info->func[0] |= PMBUS_HAVE_TEMP; - if (pmbus_check_byte_register(client, 0, - PMBUS_STATUS_TEMPERATURE)) + if (pmbus_check_word_register(client, 0, PMBUS_READ_TEMPERATURE_2)) + info->func[0] |= PMBUS_HAVE_TEMP2; + if (pmbus_check_word_register(client, 0, PMBUS_READ_TEMPERATURE_3)) + info->func[0] |= PMBUS_HAVE_TEMP3; + if (info->func[0] & (PMBUS_HAVE_TEMP | PMBUS_HAVE_TEMP2 + | PMBUS_HAVE_TEMP3) + && pmbus_check_byte_register(client, 0, + PMBUS_STATUS_TEMPERATURE)) info->func[0] |= PMBUS_HAVE_STATUS_TEMP; - } /* Sensors detected on all pages */ for (page = 0; page < info->pages; page++) { diff --git a/drivers/hwmon/pmbus_core.c b/drivers/hwmon/pmbus_core.c index 354770e..8e31a8e 100644 --- a/drivers/hwmon/pmbus_core.c +++ b/drivers/hwmon/pmbus_core.c @@ -362,8 +362,8 @@ static struct pmbus_data *pmbus_update_device(struct device *dev) * Convert linear sensor values to milli- or micro-units * depending on sensor type. */ -static int pmbus_reg2data_linear(struct pmbus_data *data, - struct pmbus_sensor *sensor) +static long pmbus_reg2data_linear(struct pmbus_data *data, + struct pmbus_sensor *sensor) { s16 exponent; s32 mantissa; @@ -397,15 +397,15 @@ static int pmbus_reg2data_linear(struct pmbus_data *data, else val >>= -exponent; - return (int)val; + return val; } /* * Convert direct sensor values to milli- or micro-units * depending on sensor type. */ -static int pmbus_reg2data_direct(struct pmbus_data *data, - struct pmbus_sensor *sensor) +static long pmbus_reg2data_direct(struct pmbus_data *data, + struct pmbus_sensor *sensor) { long val = (s16) sensor->data; long m, b, R; @@ -440,12 +440,12 @@ static int pmbus_reg2data_direct(struct pmbus_data *data, R++; } - return (int)((val - b) / m); + return (val - b) / m; } -static int pmbus_reg2data(struct pmbus_data *data, struct pmbus_sensor *sensor) +static long pmbus_reg2data(struct pmbus_data *data, struct pmbus_sensor *sensor) { - int val; + long val; if (data->info->direct[sensor->class]) val = pmbus_reg2data_direct(data, sensor); @@ -619,7 +619,7 @@ static int pmbus_get_boolean(struct pmbus_data *data, int index, int *val) if (!s1 && !s2) *val = !!regval; else { - int v1, v2; + long v1, v2; struct pmbus_sensor *sensor1, *sensor2; sensor1 = &data->sensors[s1]; @@ -661,7 +661,7 @@ static ssize_t pmbus_show_sensor(struct device *dev, if (sensor->data < 0) return sensor->data; - return snprintf(buf, PAGE_SIZE, "%d\n", pmbus_reg2data(data, sensor)); + return snprintf(buf, PAGE_SIZE, "%ld\n", pmbus_reg2data(data, sensor)); } static ssize_t pmbus_set_sensor(struct device *dev, @@ -1430,14 +1430,9 @@ int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id, i2c_set_clientdata(client, data); mutex_init(&data->update_lock); - /* - * Bail out if status register or PMBus revision register - * does not exist. - */ - if (i2c_smbus_read_byte_data(client, PMBUS_STATUS_BYTE) < 0 - || i2c_smbus_read_byte_data(client, PMBUS_REVISION) < 0) { - dev_err(&client->dev, - "Status or revision register not found\n"); + /* Bail out if PMBus status register does not exist. */ + if (i2c_smbus_read_byte_data(client, PMBUS_STATUS_BYTE) < 0) { + dev_err(&client->dev, "PMBus status register not found\n"); ret = -ENODEV; goto out_data; } diff --git a/drivers/hwmon/sch5627.c b/drivers/hwmon/sch5627.c index 020c872..3494a4c 100644 --- a/drivers/hwmon/sch5627.c +++ b/drivers/hwmon/sch5627.c @@ -887,7 +887,7 @@ static void __exit sch5627_exit(void) } MODULE_DESCRIPTION("SMSC SCH5627 Hardware Monitoring Driver"); -MODULE_AUTHOR("Hans de Goede (hdegoede@redhat.com)"); +MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>"); MODULE_LICENSE("GPL"); module_init(sch5627_init); diff --git a/drivers/i2c/busses/i2c-bfin-twi.c b/drivers/i2c/busses/i2c-bfin-twi.c index 52b545a..cbc98ae 100644 --- a/drivers/i2c/busses/i2c-bfin-twi.c +++ b/drivers/i2c/busses/i2c-bfin-twi.c @@ -193,7 +193,13 @@ static void bfin_twi_handle_interrupt(struct bfin_twi_iface *iface, return; } if (twi_int_status & MCOMP) { - if (iface->cur_mode == TWI_I2C_MODE_COMBINED) { + if ((read_MASTER_CTL(iface) & MEN) == 0 && + (iface->cur_mode == TWI_I2C_MODE_REPEAT || + iface->cur_mode == TWI_I2C_MODE_COMBINED)) { + iface->result = -1; + write_INT_MASK(iface, 0); + write_MASTER_CTL(iface, 0); + } else if (iface->cur_mode == TWI_I2C_MODE_COMBINED) { if (iface->readNum == 0) { /* set the read number to 1 and ask for manual * stop in block combine mode diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 6c00c10..f84a63c 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -248,12 +248,12 @@ static inline int is_msgend(struct s3c24xx_i2c *i2c) return i2c->msg_ptr >= i2c->msg->len; } -/* i2s_s3c_irq_nextbyte +/* i2c_s3c_irq_nextbyte * * process an interrupt and work out what to do */ -static int i2s_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) +static int i2c_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) { unsigned long tmp; unsigned char byte; @@ -264,7 +264,6 @@ static int i2s_s3c_irq_nextbyte(struct s3c24xx_i2c *i2c, unsigned long iicstat) case STATE_IDLE: dev_err(i2c->dev, "%s: called in STATE_IDLE\n", __func__); goto out; - break; case STATE_STOP: dev_err(i2c->dev, "%s: called in STATE_STOP\n", __func__); @@ -444,7 +443,7 @@ static irqreturn_t s3c24xx_i2c_irq(int irqno, void *dev_id) /* pretty much this leaves us with the fact that we've * transmitted or received whatever byte we last sent */ - i2s_s3c_irq_nextbyte(i2c, status); + i2c_s3c_irq_nextbyte(i2c, status); out: return IRQ_HANDLED; diff --git a/drivers/i2c/busses/i2c-taos-evm.c b/drivers/i2c/busses/i2c-taos-evm.c index dd39c1e..26c352a 100644 --- a/drivers/i2c/busses/i2c-taos-evm.c +++ b/drivers/i2c/busses/i2c-taos-evm.c @@ -234,7 +234,7 @@ static int taos_connect(struct serio *serio, struct serio_driver *drv) if (taos->state != TAOS_STATE_IDLE) { err = -ENODEV; - dev_dbg(&serio->dev, "TAOS EVM reset failed (state=%d, " + dev_err(&serio->dev, "TAOS EVM reset failed (state=%d, " "pos=%d)\n", taos->state, taos->pos); goto exit_close; } @@ -255,7 +255,7 @@ static int taos_connect(struct serio *serio, struct serio_driver *drv) msecs_to_jiffies(250)); if (taos->state != TAOS_STATE_IDLE) { err = -ENODEV; - dev_err(&adapter->dev, "Echo off failed " + dev_err(&serio->dev, "TAOS EVM echo off failed " "(state=%d)\n", taos->state); goto exit_close; } @@ -263,7 +263,7 @@ static int taos_connect(struct serio *serio, struct serio_driver *drv) err = i2c_add_adapter(adapter); if (err) goto exit_close; - dev_dbg(&serio->dev, "Connected to TAOS EVM\n"); + dev_info(&serio->dev, "Connected to TAOS EVM\n"); taos->client = taos_instantiate_device(adapter); return 0; @@ -288,7 +288,7 @@ static void taos_disconnect(struct serio *serio) serio_set_drvdata(serio, NULL); kfree(taos); - dev_dbg(&serio->dev, "Disconnected from TAOS EVM\n"); + dev_info(&serio->dev, "Disconnected from TAOS EVM\n"); } static struct serio_device_id taos_serio_ids[] = { diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 4d93196..fb3b4f8 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -40,8 +40,10 @@ #define I2C_CNFG_NEW_MASTER_FSM (1<<11) #define I2C_STATUS 0x01C #define I2C_SL_CNFG 0x020 +#define I2C_SL_CNFG_NACK (1<<1) #define I2C_SL_CNFG_NEWSL (1<<2) #define I2C_SL_ADDR1 0x02c +#define I2C_SL_ADDR2 0x030 #define I2C_TX_FIFO 0x050 #define I2C_RX_FIFO 0x054 #define I2C_PACKET_TRANSFER_STATUS 0x058 @@ -337,7 +339,11 @@ static int tegra_i2c_init(struct tegra_i2c_dev *i2c_dev) if (!i2c_dev->is_dvc) { u32 sl_cfg = i2c_readl(i2c_dev, I2C_SL_CNFG); - i2c_writel(i2c_dev, sl_cfg | I2C_SL_CNFG_NEWSL, I2C_SL_CNFG); + sl_cfg |= I2C_SL_CNFG_NACK | I2C_SL_CNFG_NEWSL; + i2c_writel(i2c_dev, sl_cfg, I2C_SL_CNFG); + i2c_writel(i2c_dev, 0xfc, I2C_SL_ADDR1); + i2c_writel(i2c_dev, 0x00, I2C_SL_ADDR2); + } val = 7 << I2C_FIFO_CONTROL_TX_TRIG_SHIFT | diff --git a/drivers/i2c/muxes/pca954x.c b/drivers/i2c/muxes/pca954x.c index 54e1ce7..6f89536 100644 --- a/drivers/i2c/muxes/pca954x.c +++ b/drivers/i2c/muxes/pca954x.c @@ -201,10 +201,11 @@ static int pca954x_probe(struct i2c_client *client, i2c_set_clientdata(client, data); - /* Read the mux register at addr to verify - * that the mux is in fact present. + /* Write the mux register at addr to verify + * that the mux is in fact present. This also + * initializes the mux to disconnected state. */ - if (i2c_smbus_read_byte(client) < 0) { + if (i2c_smbus_write_byte(client, 0) < 0) { dev_warn(&client->dev, "probe failed\n"); goto exit_free; } diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index f62f52f..fc0f2bd 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3641,7 +3641,8 @@ static struct kobj_type cm_port_obj_type = { static char *cm_devnode(struct device *dev, mode_t *mode) { - *mode = 0666; + if (mode) + *mode = 0666; return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index e49a85f..56898b6 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -826,7 +826,8 @@ static void ib_uverbs_remove_one(struct ib_device *device) static char *uverbs_devnode(struct device *dev, mode_t *mode) { - *mode = 0666; + if (mode) + *mode = 0666; return kasprintf(GFP_KERNEL, "infiniband/%s", dev_name(dev)); } diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index f660cd0..31fb440 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1463,9 +1463,9 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) struct c4iw_qp_attributes attrs; int disconnect = 1; int release = 0; - int abort = 0; struct tid_info *t = dev->rdev.lldi.tids; unsigned int tid = GET_TID(hdr); + int ret; ep = lookup_tid(t, tid); PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid); @@ -1501,10 +1501,12 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb) start_ep_timer(ep); __state_set(&ep->com, CLOSING); attrs.next_state = C4IW_QP_STATE_CLOSING; - abort = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, + ret = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 1); - peer_close_upcall(ep); - disconnect = 1; + if (ret != -ECONNRESET) { + peer_close_upcall(ep); + disconnect = 1; + } break; case ABORTING: disconnect = 0; @@ -2109,15 +2111,16 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp) break; } - mutex_unlock(&ep->com.mutex); if (close) { - if (abrupt) - ret = abort_connection(ep, NULL, gfp); - else + if (abrupt) { + close_complete_upcall(ep); + ret = send_abort(ep, NULL, gfp); + } else ret = send_halfclose(ep, gfp); if (ret) fatal = 1; } + mutex_unlock(&ep->com.mutex); if (fatal) release_ep_resources(ep); return ret; @@ -2301,6 +2304,31 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb) return 0; } +static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb) +{ + struct cpl_abort_req_rss *req = cplhdr(skb); + struct c4iw_ep *ep; + struct tid_info *t = dev->rdev.lldi.tids; + unsigned int tid = GET_TID(req); + + ep = lookup_tid(t, tid); + if (is_neg_adv_abort(req->status)) { + PDBG("%s neg_adv_abort ep %p tid %u\n", __func__, ep, + ep->hwtid); + kfree_skb(skb); + return 0; + } + PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid, + ep->com.state); + + /* + * Wake up any threads in rdma_init() or rdma_fini(). + */ + c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET); + sched(dev, skb); + return 0; +} + /* * Most upcalls from the T4 Core go to sched() to * schedule the processing on a work queue. @@ -2317,7 +2345,7 @@ c4iw_handler_func c4iw_handlers[NUM_CPL_CMDS] = { [CPL_PASS_ESTABLISH] = sched, [CPL_PEER_CLOSE] = sched, [CPL_CLOSE_CON_RPL] = sched, - [CPL_ABORT_REQ_RSS] = sched, + [CPL_ABORT_REQ_RSS] = peer_abort_intr, [CPL_RDMA_TERMINATE] = sched, [CPL_FW4_ACK] = sched, [CPL_SET_TCB_RPL] = set_tcb_rpl, diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 8d8f8ad..1720dc7 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -801,6 +801,10 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries, if (ucontext) { memsize = roundup(memsize, PAGE_SIZE); hwentries = memsize / sizeof *chp->cq.queue; + while (hwentries > T4_MAX_IQ_SIZE) { + memsize -= PAGE_SIZE; + hwentries = memsize / sizeof *chp->cq.queue; + } } chp->cq.size = hwentries; chp->cq.memsize = memsize; diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 273ffe4..0347eed 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -625,7 +625,7 @@ pbl_done: mhp->attr.perms = c4iw_ib_to_tpt_access(acc); mhp->attr.va_fbo = virt; mhp->attr.page_size = shift - 12; - mhp->attr.len = (u32) length; + mhp->attr.len = length; err = register_mem(rhp, php, mhp, shift); if (err) diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 3b773b0..a41578e 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1207,11 +1207,8 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp, c4iw_get_ep(&qhp->ep->com); } ret = rdma_fini(rhp, qhp, ep); - if (ret) { - if (internal) - c4iw_get_ep(&qhp->ep->com); + if (ret) goto err; - } break; case C4IW_QP_STATE_TERMINATE: set_state(qhp, C4IW_QP_STATE_TERMINATE); diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 9f53e68..8ec5237 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -469,6 +469,8 @@ static u8 ib_rate_to_delay[IB_RATE_120_GBPS + 1] = { #define IB_7322_LT_STATE_RECOVERIDLE 0x0f #define IB_7322_LT_STATE_CFGENH 0x10 #define IB_7322_LT_STATE_CFGTEST 0x11 +#define IB_7322_LT_STATE_CFGWAITRMTTEST 0x12 +#define IB_7322_LT_STATE_CFGWAITENH 0x13 /* link state machine states from IBC */ #define IB_7322_L_STATE_DOWN 0x0 @@ -498,8 +500,10 @@ static const u8 qib_7322_physportstate[0x20] = { IB_PHYSPORTSTATE_LINK_ERR_RECOVER, [IB_7322_LT_STATE_CFGENH] = IB_PHYSPORTSTATE_CFG_ENH, [IB_7322_LT_STATE_CFGTEST] = IB_PHYSPORTSTATE_CFG_TRAIN, - [0x12] = IB_PHYSPORTSTATE_CFG_TRAIN, - [0x13] = IB_PHYSPORTSTATE_CFG_WAIT_ENH, + [IB_7322_LT_STATE_CFGWAITRMTTEST] = + IB_PHYSPORTSTATE_CFG_TRAIN, + [IB_7322_LT_STATE_CFGWAITENH] = + IB_PHYSPORTSTATE_CFG_WAIT_ENH, [0x14] = IB_PHYSPORTSTATE_CFG_TRAIN, [0x15] = IB_PHYSPORTSTATE_CFG_TRAIN, [0x16] = IB_PHYSPORTSTATE_CFG_TRAIN, @@ -1692,7 +1696,9 @@ static void handle_serdes_issues(struct qib_pportdata *ppd, u64 ibcst) break; } - if (ibclt == IB_7322_LT_STATE_CFGTEST && + if (((ibclt >= IB_7322_LT_STATE_CFGTEST && + ibclt <= IB_7322_LT_STATE_CFGWAITENH) || + ibclt == IB_7322_LT_STATE_LINKUP) && (ibcst & SYM_MASK(IBCStatusA_0, LinkSpeedQDR))) { force_h1(ppd); ppd->cpspec->qdr_reforce = 1; @@ -7301,12 +7307,17 @@ static void ibsd_wr_allchans(struct qib_pportdata *ppd, int addr, unsigned data, static void serdes_7322_los_enable(struct qib_pportdata *ppd, int enable) { u64 data = qib_read_kreg_port(ppd, krp_serdesctrl); - printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS %s\n", - ppd->dd->unit, ppd->port, (enable ? "on" : "off")); - if (enable) + u8 state = SYM_FIELD(data, IBSerdesCtrl_0, RXLOSEN); + + if (enable && !state) { + printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS on\n", + ppd->dd->unit, ppd->port); data |= SYM_MASK(IBSerdesCtrl_0, RXLOSEN); - else + } else if (!enable && state) { + printk(KERN_INFO QIB_DRV_NAME " IB%u:%u Turning LOS off\n", + ppd->dd->unit, ppd->port); data &= ~SYM_MASK(IBSerdesCtrl_0, RXLOSEN); + } qib_write_kreg_port(ppd, krp_serdesctrl, data); } diff --git a/drivers/infiniband/hw/qib/qib_intr.c b/drivers/infiniband/hw/qib/qib_intr.c index a693c56..6ae57d2 100644 --- a/drivers/infiniband/hw/qib/qib_intr.c +++ b/drivers/infiniband/hw/qib/qib_intr.c @@ -96,8 +96,12 @@ void qib_handle_e_ibstatuschanged(struct qib_pportdata *ppd, u64 ibcs) * states, or if it transitions from any of the up (INIT or better) * states into any of the down states (except link recovery), then * call the chip-specific code to take appropriate actions. + * + * ppd->lflags could be 0 if this is the first time the interrupt + * handlers has been called but the link is already up. */ - if (lstate >= IB_PORT_INIT && (ppd->lflags & QIBL_LINKDOWN) && + if (lstate >= IB_PORT_INIT && + (!ppd->lflags || (ppd->lflags & QIBL_LINKDOWN)) && ltstate == IB_PHYSPORTSTATE_LINKUP) { /* transitioned to UP */ if (dd->f_ib_updown(ppd, 1, ibcs)) diff --git a/drivers/input/keyboard/pmic8xxx-keypad.c b/drivers/input/keyboard/pmic8xxx-keypad.c index 40b02ae..6229c3e 100644 --- a/drivers/input/keyboard/pmic8xxx-keypad.c +++ b/drivers/input/keyboard/pmic8xxx-keypad.c @@ -520,7 +520,8 @@ static void pmic8xxx_kp_close(struct input_dev *dev) */ static int __devinit pmic8xxx_kp_probe(struct platform_device *pdev) { - const struct pm8xxx_keypad_platform_data *pdata = mfd_get_data(pdev); + const struct pm8xxx_keypad_platform_data *pdata = + dev_get_platdata(&pdev->dev); const struct matrix_keymap_data *keymap_data; struct pmic8xxx_kp *kp; int rc; diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c index 97e07e7..b3cfb9c 100644 --- a/drivers/input/misc/pmic8xxx-pwrkey.c +++ b/drivers/input/misc/pmic8xxx-pwrkey.c @@ -90,7 +90,8 @@ static int __devinit pmic8xxx_pwrkey_probe(struct platform_device *pdev) unsigned int delay; u8 pon_cntl; struct pmic8xxx_pwrkey *pwrkey; - const struct pm8xxx_pwrkey_platform_data *pdata = mfd_get_data(pdev); + const struct pm8xxx_pwrkey_platform_data *pdata = + dev_get_platdata(&pdev->dev); if (!pdata) { dev_err(&pdev->dev, "power key platform data not supplied\n"); diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c index c0cff64..cc1dc48 100644 --- a/drivers/leds/leds-lp5521.c +++ b/drivers/leds/leds-lp5521.c @@ -593,7 +593,7 @@ static void lp5521_unregister_sysfs(struct i2c_client *client) &lp5521_led_attribute_group); } -static int __init lp5521_init_led(struct lp5521_led *led, +static int __devinit lp5521_init_led(struct lp5521_led *led, struct i2c_client *client, int chan, struct lp5521_platform_data *pdata) { @@ -637,7 +637,7 @@ static int __init lp5521_init_led(struct lp5521_led *led, return 0; } -static int lp5521_probe(struct i2c_client *client, +static int __devinit lp5521_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct lp5521_chip *chip; diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c index e19fed2..5971e309 100644 --- a/drivers/leds/leds-lp5523.c +++ b/drivers/leds/leds-lp5523.c @@ -826,7 +826,7 @@ static int __init lp5523_init_engine(struct lp5523_engine *engine, int id) return 0; } -static int __init lp5523_init_led(struct lp5523_led *led, struct device *dev, +static int __devinit lp5523_init_led(struct lp5523_led *led, struct device *dev, int chan, struct lp5523_platform_data *pdata) { char name[32]; @@ -872,7 +872,7 @@ static int __init lp5523_init_led(struct lp5523_led *led, struct device *dev, static struct i2c_driver lp5523_driver; -static int lp5523_probe(struct i2c_client *client, +static int __devinit lp5523_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct lp5523_chip *chip; diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c index d8d3a1e..a2c8746 100644 --- a/drivers/leds/leds-pca9532.c +++ b/drivers/leds/leds-pca9532.c @@ -88,7 +88,7 @@ static const struct pca9532_chip_info pca9532_chip_info_tbl[] = { static struct i2c_driver pca9532_driver = { .driver = { - .name = "pca953x", + .name = "leds-pca953x", }, .probe = pca9532_probe, .remove = pca9532_remove, diff --git a/drivers/md/md.c b/drivers/md/md.c index 4332fc2..91e31e2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7088,6 +7088,7 @@ static int remove_and_add_spares(mddev_t *mddev) list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->raid_disk >= 0 && !test_bit(In_sync, &rdev->flags) && + !test_bit(Faulty, &rdev->flags) && !test_bit(Blocked, &rdev->flags)) spares++; if (rdev->raid_disk < 0 diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c index 9827804..5b6b451 100644 --- a/drivers/media/dvb/dvb-core/dvb_frontend.c +++ b/drivers/media/dvb/dvb-core/dvb_frontend.c @@ -1988,6 +1988,14 @@ static int dvb_frontend_open(struct inode *inode, struct file *file) if (dvbdev->users == -1 && fe->ops.ts_bus_ctrl) { if ((ret = fe->ops.ts_bus_ctrl(fe, 1)) < 0) goto err0; + + /* If we took control of the bus, we need to force + reinitialization. This is because many ts_bus_ctrl() + functions strobe the RESET pin on the demod, and if the + frontend thread already exists then the dvb_init() routine + won't get called (which is what usually does initial + register configuration). */ + fepriv->reinitialise = 1; } if ((ret = dvb_generic_open (inode, file)) < 0) diff --git a/drivers/media/radio/Kconfig b/drivers/media/radio/Kconfig index e4c97fd..52798a1 100644 --- a/drivers/media/radio/Kconfig +++ b/drivers/media/radio/Kconfig @@ -168,7 +168,7 @@ config RADIO_MAXIRADIO config RADIO_MIROPCM20 tristate "miroSOUND PCM20 radio" - depends on ISA && VIDEO_V4L2 && SND + depends on ISA && ISA_DMA_API && VIDEO_V4L2 && SND select SND_ISA select SND_MIRO ---help--- @@ -201,7 +201,7 @@ config RADIO_SF16FMI config RADIO_SF16FMR2 tristate "SF16FMR2 Radio" - depends on ISA && VIDEO_V4L2 + depends on ISA && VIDEO_V4L2 && SND ---help--- Choose Y here if you have one of these FM radio cards. diff --git a/drivers/media/radio/si4713-i2c.c b/drivers/media/radio/si4713-i2c.c index deca2e0..c9f4a8e 100644 --- a/drivers/media/radio/si4713-i2c.c +++ b/drivers/media/radio/si4713-i2c.c @@ -1033,7 +1033,7 @@ static int si4713_write_econtrol_string(struct si4713_device *sdev, char ps_name[MAX_RDS_PS_NAME + 1]; len = control->size - 1; - if (len > MAX_RDS_PS_NAME) { + if (len < 0 || len > MAX_RDS_PS_NAME) { rval = -ERANGE; goto exit; } @@ -1057,7 +1057,7 @@ static int si4713_write_econtrol_string(struct si4713_device *sdev, char radio_text[MAX_RDS_RADIO_TEXT + 1]; len = control->size - 1; - if (len > MAX_RDS_RADIO_TEXT) { + if (len < 0 || len > MAX_RDS_RADIO_TEXT) { rval = -ERANGE; goto exit; } diff --git a/drivers/media/rc/fintek-cir.c b/drivers/media/rc/fintek-cir.c index 8fa539d..7f7079b 100644 --- a/drivers/media/rc/fintek-cir.c +++ b/drivers/media/rc/fintek-cir.c @@ -597,12 +597,17 @@ static void __devexit fintek_remove(struct pnp_dev *pdev) static int fintek_suspend(struct pnp_dev *pdev, pm_message_t state) { struct fintek_dev *fintek = pnp_get_drvdata(pdev); + unsigned long flags; fit_dbg("%s called", __func__); + spin_lock_irqsave(&fintek->fintek_lock, flags); + /* disable all CIR interrupts */ fintek_cir_reg_write(fintek, CIR_STATUS_IRQ_MASK, CIR_STATUS); + spin_unlock_irqrestore(&fintek->fintek_lock, flags); + fintek_config_mode_enable(fintek); /* disable cir logical dev */ diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index 3f3c707..6bc35ee 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -307,6 +307,14 @@ static const struct { /* 0xffdc iMON MCE VFD */ { 0x00010000ffffffeell, KEY_VOLUMEUP }, { 0x01000000ffffffeell, KEY_VOLUMEDOWN }, + { 0x00000001ffffffeell, KEY_MUTE }, + { 0x0000000fffffffeell, KEY_MEDIA }, + { 0x00000012ffffffeell, KEY_UP }, + { 0x00000013ffffffeell, KEY_DOWN }, + { 0x00000014ffffffeell, KEY_LEFT }, + { 0x00000015ffffffeell, KEY_RIGHT }, + { 0x00000016ffffffeell, KEY_ENTER }, + { 0x00000017ffffffeell, KEY_ESC }, /* iMON Knob values */ { 0x000100ffffffffeell, KEY_VOLUMEUP }, { 0x010000ffffffffeell, KEY_VOLUMEDOWN }, @@ -1582,16 +1590,16 @@ static void imon_incoming_packet(struct imon_context *ictx, /* Only panel type events left to process now */ spin_lock_irqsave(&ictx->kc_lock, flags); + do_gettimeofday(&t); /* KEY_MUTE repeats from knob need to be suppressed */ if (ictx->kc == KEY_MUTE && ictx->kc == ictx->last_keycode) { - do_gettimeofday(&t); msec = tv2int(&t, &prev_time); - prev_time = t; if (msec < ictx->idev->rep[REP_DELAY]) { spin_unlock_irqrestore(&ictx->kc_lock, flags); return; } } + prev_time = t; kc = ictx->kc; spin_unlock_irqrestore(&ictx->kc_lock, flags); @@ -1603,7 +1611,9 @@ static void imon_incoming_packet(struct imon_context *ictx, input_report_key(ictx->idev, kc, 0); input_sync(ictx->idev); + spin_lock_irqsave(&ictx->kc_lock, flags); ictx->last_keycode = kc; + spin_unlock_irqrestore(&ictx->kc_lock, flags); return; @@ -1740,6 +1750,8 @@ static void imon_get_ffdc_type(struct imon_context *ictx) detected_display_type = IMON_DISPLAY_TYPE_VFD; break; /* iMON VFD, MCE IR */ + case 0x46: + case 0x7e: case 0x9e: dev_info(ictx->dev, "0xffdc iMON VFD, MCE IR"); detected_display_type = IMON_DISPLAY_TYPE_VFD; @@ -1755,6 +1767,9 @@ static void imon_get_ffdc_type(struct imon_context *ictx) dev_info(ictx->dev, "Unknown 0xffdc device, " "defaulting to VFD and iMON IR"); detected_display_type = IMON_DISPLAY_TYPE_VFD; + /* We don't know which one it is, allow user to set the + * RC6 one from userspace if OTHER wasn't correct. */ + allowed_protos |= RC_TYPE_RC6; break; } diff --git a/drivers/media/rc/ir-raw.c b/drivers/media/rc/ir-raw.c index 11c19d8..423ed45 100644 --- a/drivers/media/rc/ir-raw.c +++ b/drivers/media/rc/ir-raw.c @@ -114,18 +114,20 @@ int ir_raw_event_store_edge(struct rc_dev *dev, enum raw_event_type type) s64 delta; /* ns */ DEFINE_IR_RAW_EVENT(ev); int rc = 0; + int delay; if (!dev->raw) return -EINVAL; now = ktime_get(); delta = ktime_to_ns(ktime_sub(now, dev->raw->last_event)); + delay = MS_TO_NS(dev->input_dev->rep[REP_DELAY]); /* Check for a long duration since last event or if we're * being called for the first time, note that delta can't * possibly be negative. */ - if (delta > IR_MAX_DURATION || !dev->raw->last_type) + if (delta > delay || !dev->raw->last_type) type |= IR_START_EVENT; else ev.duration = delta; diff --git a/drivers/media/rc/ite-cir.c b/drivers/media/rc/ite-cir.c index e716b93..ecd3d02 100644 --- a/drivers/media/rc/ite-cir.c +++ b/drivers/media/rc/ite-cir.c @@ -1347,6 +1347,7 @@ static const struct ite_dev_params ite_dev_descs[] = { { /* 0: ITE8704 */ .model = "ITE8704 CIR transceiver", .io_region_size = IT87_IOREG_LENGTH, + .io_rsrc_no = 0, .hw_tx_capable = true, .sample_period = (u32) (1000000000ULL / 115200), .tx_carrier_freq = 38000, @@ -1371,6 +1372,7 @@ static const struct ite_dev_params ite_dev_descs[] = { { /* 1: ITE8713 */ .model = "ITE8713 CIR transceiver", .io_region_size = IT87_IOREG_LENGTH, + .io_rsrc_no = 0, .hw_tx_capable = true, .sample_period = (u32) (1000000000ULL / 115200), .tx_carrier_freq = 38000, @@ -1395,6 +1397,7 @@ static const struct ite_dev_params ite_dev_descs[] = { { /* 2: ITE8708 */ .model = "ITE8708 CIR transceiver", .io_region_size = IT8708_IOREG_LENGTH, + .io_rsrc_no = 0, .hw_tx_capable = true, .sample_period = (u32) (1000000000ULL / 115200), .tx_carrier_freq = 38000, @@ -1420,6 +1423,7 @@ static const struct ite_dev_params ite_dev_descs[] = { { /* 3: ITE8709 */ .model = "ITE8709 CIR transceiver", .io_region_size = IT8709_IOREG_LENGTH, + .io_rsrc_no = 2, .hw_tx_capable = true, .sample_period = (u32) (1000000000ULL / 115200), .tx_carrier_freq = 38000, @@ -1461,6 +1465,7 @@ static int ite_probe(struct pnp_dev *pdev, const struct pnp_device_id struct rc_dev *rdev = NULL; int ret = -ENOMEM; int model_no; + int io_rsrc_no; ite_dbg("%s called", __func__); @@ -1490,10 +1495,11 @@ static int ite_probe(struct pnp_dev *pdev, const struct pnp_device_id /* get the description for the device */ dev_desc = &ite_dev_descs[model_no]; + io_rsrc_no = dev_desc->io_rsrc_no; /* validate pnp resources */ - if (!pnp_port_valid(pdev, 0) || - pnp_port_len(pdev, 0) != dev_desc->io_region_size) { + if (!pnp_port_valid(pdev, io_rsrc_no) || + pnp_port_len(pdev, io_rsrc_no) != dev_desc->io_region_size) { dev_err(&pdev->dev, "IR PNP Port not valid!\n"); goto failure; } @@ -1504,7 +1510,7 @@ static int ite_probe(struct pnp_dev *pdev, const struct pnp_device_id } /* store resource values */ - itdev->cir_addr = pnp_port_start(pdev, 0); + itdev->cir_addr = pnp_port_start(pdev, io_rsrc_no); itdev->cir_irq = pnp_irq(pdev, 0); /* initialize spinlocks */ diff --git a/drivers/media/rc/ite-cir.h b/drivers/media/rc/ite-cir.h index 16a19f5..aa899a0 100644 --- a/drivers/media/rc/ite-cir.h +++ b/drivers/media/rc/ite-cir.h @@ -57,6 +57,9 @@ struct ite_dev_params { /* size of the I/O region */ int io_region_size; + /* IR pnp I/O resource number */ + int io_rsrc_no; + /* true if the hardware supports transmission */ bool hw_tx_capable; diff --git a/drivers/media/rc/keymaps/rc-pinnacle-pctv-hd.c b/drivers/media/rc/keymaps/rc-pinnacle-pctv-hd.c index bb10ffe..8d558ae 100644 --- a/drivers/media/rc/keymaps/rc-pinnacle-pctv-hd.c +++ b/drivers/media/rc/keymaps/rc-pinnacle-pctv-hd.c @@ -15,43 +15,39 @@ /* Pinnacle PCTV HD 800i mini remote */ static struct rc_map_table pinnacle_pctv_hd[] = { - - { 0x0f, KEY_1 }, - { 0x15, KEY_2 }, - { 0x10, KEY_3 }, - { 0x18, KEY_4 }, - { 0x1b, KEY_5 }, - { 0x1e, KEY_6 }, - { 0x11, KEY_7 }, - { 0x21, KEY_8 }, - { 0x12, KEY_9 }, - { 0x27, KEY_0 }, - - { 0x24, KEY_ZOOM }, - { 0x2a, KEY_SUBTITLE }, - - { 0x00, KEY_MUTE }, - { 0x01, KEY_ENTER }, /* Pinnacle Logo */ - { 0x39, KEY_POWER }, - - { 0x03, KEY_VOLUMEUP }, - { 0x09, KEY_VOLUMEDOWN }, - { 0x06, KEY_CHANNELUP }, - { 0x0c, KEY_CHANNELDOWN }, - - { 0x2d, KEY_REWIND }, - { 0x30, KEY_PLAYPAUSE }, - { 0x33, KEY_FASTFORWARD }, - { 0x3c, KEY_STOP }, - { 0x36, KEY_RECORD }, - { 0x3f, KEY_EPG }, /* Labeled "?" */ + /* Key codes for the tiny Pinnacle remote*/ + { 0x0700, KEY_MUTE }, + { 0x0701, KEY_MENU }, /* Pinnacle logo */ + { 0x0739, KEY_POWER }, + { 0x0703, KEY_VOLUMEUP }, + { 0x0709, KEY_VOLUMEDOWN }, + { 0x0706, KEY_CHANNELUP }, + { 0x070c, KEY_CHANNELDOWN }, + { 0x070f, KEY_1 }, + { 0x0715, KEY_2 }, + { 0x0710, KEY_3 }, + { 0x0718, KEY_4 }, + { 0x071b, KEY_5 }, + { 0x071e, KEY_6 }, + { 0x0711, KEY_7 }, + { 0x0721, KEY_8 }, + { 0x0712, KEY_9 }, + { 0x0727, KEY_0 }, + { 0x0724, KEY_ZOOM }, /* 'Square' key */ + { 0x072a, KEY_SUBTITLE }, /* 'T' key */ + { 0x072d, KEY_REWIND }, + { 0x0730, KEY_PLAYPAUSE }, + { 0x0733, KEY_FASTFORWARD }, + { 0x0736, KEY_RECORD }, + { 0x073c, KEY_STOP }, + { 0x073f, KEY_HELP }, /* '?' key */ }; static struct rc_map_list pinnacle_pctv_hd_map = { .map = { .scan = pinnacle_pctv_hd, .size = ARRAY_SIZE(pinnacle_pctv_hd), - .rc_type = RC_TYPE_UNKNOWN, /* Legacy IR type */ + .rc_type = RC_TYPE_RC5, .name = RC_MAP_PINNACLE_PCTV_HD, } }; diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index fd237ab..27997a9 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -55,6 +55,8 @@ struct irctl { struct lirc_buffer *buf; unsigned int chunk_size; + struct cdev *cdev; + struct task_struct *task; long jiffies_to_wait; }; @@ -62,7 +64,6 @@ struct irctl { static DEFINE_MUTEX(lirc_dev_lock); static struct irctl *irctls[MAX_IRCTL_DEVICES]; -static struct cdev cdevs[MAX_IRCTL_DEVICES]; /* Only used for sysfs but defined to void otherwise */ static struct class *lirc_class; @@ -167,9 +168,13 @@ static struct file_operations lirc_dev_fops = { static int lirc_cdev_add(struct irctl *ir) { - int retval; + int retval = -ENOMEM; struct lirc_driver *d = &ir->d; - struct cdev *cdev = &cdevs[d->minor]; + struct cdev *cdev; + + cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); + if (!cdev) + goto err_out; if (d->fops) { cdev_init(cdev, d->fops); @@ -180,12 +185,20 @@ static int lirc_cdev_add(struct irctl *ir) } retval = kobject_set_name(&cdev->kobj, "lirc%d", d->minor); if (retval) - return retval; + goto err_out; retval = cdev_add(cdev, MKDEV(MAJOR(lirc_base_dev), d->minor), 1); - if (retval) + if (retval) { kobject_put(&cdev->kobj); + goto err_out; + } + + ir->cdev = cdev; + + return 0; +err_out: + kfree(cdev); return retval; } @@ -214,7 +227,7 @@ int lirc_register_driver(struct lirc_driver *d) if (MAX_IRCTL_DEVICES <= d->minor) { dev_err(d->dev, "lirc_dev: lirc_register_driver: " "\"minor\" must be between 0 and %d (%d)!\n", - MAX_IRCTL_DEVICES-1, d->minor); + MAX_IRCTL_DEVICES - 1, d->minor); err = -EBADRQC; goto out; } @@ -369,7 +382,7 @@ int lirc_unregister_driver(int minor) if (minor < 0 || minor >= MAX_IRCTL_DEVICES) { printk(KERN_ERR "lirc_dev: %s: minor (%d) must be between " - "0 and %d!\n", __func__, minor, MAX_IRCTL_DEVICES-1); + "0 and %d!\n", __func__, minor, MAX_IRCTL_DEVICES - 1); return -EBADRQC; } @@ -380,7 +393,7 @@ int lirc_unregister_driver(int minor) return -ENOENT; } - cdev = &cdevs[minor]; + cdev = ir->cdev; mutex_lock(&lirc_dev_lock); @@ -410,6 +423,7 @@ int lirc_unregister_driver(int minor) } else { lirc_irctl_cleanup(ir); cdev_del(cdev); + kfree(cdev); kfree(ir); irctls[minor] = NULL; } @@ -453,7 +467,7 @@ int lirc_dev_fop_open(struct inode *inode, struct file *file) goto error; } - cdev = &cdevs[iminor(inode)]; + cdev = ir->cdev; if (try_module_get(cdev->owner)) { ir->open++; retval = ir->d.set_use_inc(ir->d.data); @@ -484,13 +498,15 @@ EXPORT_SYMBOL(lirc_dev_fop_open); int lirc_dev_fop_close(struct inode *inode, struct file *file) { struct irctl *ir = irctls[iminor(inode)]; - struct cdev *cdev = &cdevs[iminor(inode)]; + struct cdev *cdev; if (!ir) { printk(KERN_ERR "%s: called with invalid irctl\n", __func__); return -EINVAL; } + cdev = ir->cdev; + dev_dbg(ir->d.dev, LOGHEAD "close called\n", ir->d.name, ir->d.minor); WARN_ON(mutex_lock_killable(&lirc_dev_lock)); @@ -503,6 +519,7 @@ int lirc_dev_fop_close(struct inode *inode, struct file *file) lirc_irctl_cleanup(ir); cdev_del(cdev); irctls[ir->d.minor] = NULL; + kfree(cdev); kfree(ir); } diff --git a/drivers/media/rc/mceusb.c b/drivers/media/rc/mceusb.c index ad927fc..ec972dc 100644 --- a/drivers/media/rc/mceusb.c +++ b/drivers/media/rc/mceusb.c @@ -108,6 +108,12 @@ static int debug = 1; static int debug; #endif +#define mce_dbg(dev, fmt, ...) \ + do { \ + if (debug) \ + dev_info(dev, fmt, ## __VA_ARGS__); \ + } while (0) + /* general constants */ #define SEND_FLAG_IN_PROGRESS 1 #define SEND_FLAG_COMPLETE 2 @@ -246,6 +252,9 @@ static struct usb_device_id mceusb_dev_table[] = { .driver_info = MCE_GEN2_TX_INV }, /* SMK eHome Infrared Transceiver */ { USB_DEVICE(VENDOR_SMK, 0x0338) }, + /* SMK/I-O Data GV-MC7/RCKIT Receiver */ + { USB_DEVICE(VENDOR_SMK, 0x0353), + .driver_info = MCE_GEN2_NO_TX }, /* Tatung eHome Infrared Transceiver */ { USB_DEVICE(VENDOR_TATUNG, 0x9150) }, /* Shuttle eHome Infrared Transceiver */ @@ -549,9 +558,10 @@ static void mceusb_dev_printdata(struct mceusb_dev *ir, char *buf, inout, data1); break; case MCE_CMD_S_TIMEOUT: - /* value is in units of 50us, so x*50/100 or x/2 ms */ + /* value is in units of 50us, so x*50/1000 ms */ dev_info(dev, "%s receive timeout of %d ms\n", - inout, ((data1 << 8) | data2) / 2); + inout, + ((data1 << 8) | data2) * MCE_TIME_UNIT / 1000); break; case MCE_CMD_G_TIMEOUT: dev_info(dev, "Get receive timeout\n"); @@ -606,12 +616,15 @@ static void mce_async_callback(struct urb *urb, struct pt_regs *regs) if (ir) { len = urb->actual_length; - dev_dbg(ir->dev, "callback called (status=%d len=%d)\n", + mce_dbg(ir->dev, "callback called (status=%d len=%d)\n", urb->status, len); mceusb_dev_printdata(ir, urb->transfer_buffer, 0, len, true); } + /* the transfer buffer and urb were allocated in mce_request_packet */ + kfree(urb->transfer_buffer); + usb_free_urb(urb); } /* request incoming or send outgoing usb packet - used to initialize remote */ @@ -655,17 +668,17 @@ static void mce_request_packet(struct mceusb_dev *ir, unsigned char *data, return; } - dev_dbg(dev, "receive request called (size=%#x)\n", size); + mce_dbg(dev, "receive request called (size=%#x)\n", size); async_urb->transfer_buffer_length = size; async_urb->dev = ir->usbdev; res = usb_submit_urb(async_urb, GFP_ATOMIC); if (res) { - dev_dbg(dev, "receive request FAILED! (res=%d)\n", res); + mce_dbg(dev, "receive request FAILED! (res=%d)\n", res); return; } - dev_dbg(dev, "receive request complete (res=%d)\n", res); + mce_dbg(dev, "receive request complete (res=%d)\n", res); } static void mce_async_out(struct mceusb_dev *ir, unsigned char *data, int size) @@ -673,9 +686,9 @@ static void mce_async_out(struct mceusb_dev *ir, unsigned char *data, int size) mce_request_packet(ir, data, size, MCEUSB_TX); } -static void mce_sync_in(struct mceusb_dev *ir, unsigned char *data, int size) +static void mce_flush_rx_buffer(struct mceusb_dev *ir, int size) { - mce_request_packet(ir, data, size, MCEUSB_RX); + mce_request_packet(ir, NULL, size, MCEUSB_RX); } /* Send data out the IR blaster port(s) */ @@ -794,7 +807,7 @@ static int mceusb_set_tx_carrier(struct rc_dev *dev, u32 carrier) ir->carrier = carrier; cmdbuf[2] = MCE_CMD_SIG_END; cmdbuf[3] = MCE_IRDATA_TRAILER; - dev_dbg(ir->dev, "%s: disabling carrier " + mce_dbg(ir->dev, "%s: disabling carrier " "modulation\n", __func__); mce_async_out(ir, cmdbuf, sizeof(cmdbuf)); return carrier; @@ -806,7 +819,7 @@ static int mceusb_set_tx_carrier(struct rc_dev *dev, u32 carrier) ir->carrier = carrier; cmdbuf[2] = prescaler; cmdbuf[3] = divisor; - dev_dbg(ir->dev, "%s: requesting %u HZ " + mce_dbg(ir->dev, "%s: requesting %u HZ " "carrier\n", __func__, carrier); /* Transmit new carrier to mce device */ @@ -835,7 +848,7 @@ static void mceusb_handle_command(struct mceusb_dev *ir, int index) switch (ir->buf_in[index]) { /* 2-byte return value commands */ case MCE_CMD_S_TIMEOUT: - ir->rc->timeout = US_TO_NS((hi << 8 | lo) / 2); + ir->rc->timeout = US_TO_NS((hi << 8 | lo) * MCE_TIME_UNIT); break; /* 1-byte return value commands */ @@ -879,7 +892,7 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) rawir.duration = (ir->buf_in[i] & MCE_PULSE_MASK) * US_TO_NS(MCE_TIME_UNIT); - dev_dbg(ir->dev, "Storing %s with duration %d\n", + mce_dbg(ir->dev, "Storing %s with duration %d\n", rawir.pulse ? "pulse" : "space", rawir.duration); @@ -911,7 +924,7 @@ static void mceusb_process_ir_data(struct mceusb_dev *ir, int buf_len) if (ir->parser_state != CMD_HEADER && !ir->rem) ir->parser_state = CMD_HEADER; } - dev_dbg(ir->dev, "processed IR data, calling ir_raw_event_handle\n"); + mce_dbg(ir->dev, "processed IR data, calling ir_raw_event_handle\n"); ir_raw_event_handle(ir->rc); } @@ -933,7 +946,7 @@ static void mceusb_dev_recv(struct urb *urb, struct pt_regs *regs) if (ir->send_flags == RECV_FLAG_IN_PROGRESS) { ir->send_flags = SEND_FLAG_COMPLETE; - dev_dbg(ir->dev, "setup answer received %d bytes\n", + mce_dbg(ir->dev, "setup answer received %d bytes\n", buf_len); } @@ -951,7 +964,7 @@ static void mceusb_dev_recv(struct urb *urb, struct pt_regs *regs) case -EPIPE: default: - dev_dbg(ir->dev, "Error: urb status = %d\n", urb->status); + mce_dbg(ir->dev, "Error: urb status = %d\n", urb->status); break; } @@ -961,7 +974,6 @@ static void mceusb_dev_recv(struct urb *urb, struct pt_regs *regs) static void mceusb_gen1_init(struct mceusb_dev *ir) { int ret; - int maxp = ir->len_in; struct device *dev = ir->dev; char *data; @@ -978,8 +990,8 @@ static void mceusb_gen1_init(struct mceusb_dev *ir) ret = usb_control_msg(ir->usbdev, usb_rcvctrlpipe(ir->usbdev, 0), USB_REQ_SET_ADDRESS, USB_TYPE_VENDOR, 0, 0, data, USB_CTRL_MSG_SZ, HZ * 3); - dev_dbg(dev, "%s - ret = %d\n", __func__, ret); - dev_dbg(dev, "%s - data[0] = %d, data[1] = %d\n", + mce_dbg(dev, "%s - ret = %d\n", __func__, ret); + mce_dbg(dev, "%s - data[0] = %d, data[1] = %d\n", __func__, data[0], data[1]); /* set feature: bit rate 38400 bps */ @@ -987,71 +999,56 @@ static void mceusb_gen1_init(struct mceusb_dev *ir) USB_REQ_SET_FEATURE, USB_TYPE_VENDOR, 0xc04e, 0x0000, NULL, 0, HZ * 3); - dev_dbg(dev, "%s - ret = %d\n", __func__, ret); + mce_dbg(dev, "%s - ret = %d\n", __func__, ret); /* bRequest 4: set char length to 8 bits */ ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0), 4, USB_TYPE_VENDOR, 0x0808, 0x0000, NULL, 0, HZ * 3); - dev_dbg(dev, "%s - retB = %d\n", __func__, ret); + mce_dbg(dev, "%s - retB = %d\n", __func__, ret); /* bRequest 2: set handshaking to use DTR/DSR */ ret = usb_control_msg(ir->usbdev, usb_sndctrlpipe(ir->usbdev, 0), 2, USB_TYPE_VENDOR, 0x0000, 0x0100, NULL, 0, HZ * 3); - dev_dbg(dev, "%s - retC = %d\n", __func__, ret); + mce_dbg(dev, "%s - retC = %d\n", __func__, ret); /* device reset */ mce_async_out(ir, DEVICE_RESET, sizeof(DEVICE_RESET)); - mce_sync_in(ir, NULL, maxp); /* get hw/sw revision? */ mce_async_out(ir, GET_REVISION, sizeof(GET_REVISION)); - mce_sync_in(ir, NULL, maxp); kfree(data); }; static void mceusb_gen2_init(struct mceusb_dev *ir) { - int maxp = ir->len_in; - /* device reset */ mce_async_out(ir, DEVICE_RESET, sizeof(DEVICE_RESET)); - mce_sync_in(ir, NULL, maxp); /* get hw/sw revision? */ mce_async_out(ir, GET_REVISION, sizeof(GET_REVISION)); - mce_sync_in(ir, NULL, maxp); /* unknown what the next two actually return... */ mce_async_out(ir, GET_UNKNOWN, sizeof(GET_UNKNOWN)); - mce_sync_in(ir, NULL, maxp); mce_async_out(ir, GET_UNKNOWN2, sizeof(GET_UNKNOWN2)); - mce_sync_in(ir, NULL, maxp); } static void mceusb_get_parameters(struct mceusb_dev *ir) { - int maxp = ir->len_in; - /* get the carrier and frequency */ mce_async_out(ir, GET_CARRIER_FREQ, sizeof(GET_CARRIER_FREQ)); - mce_sync_in(ir, NULL, maxp); - if (!ir->flags.no_tx) { + if (!ir->flags.no_tx) /* get the transmitter bitmask */ mce_async_out(ir, GET_TX_BITMASK, sizeof(GET_TX_BITMASK)); - mce_sync_in(ir, NULL, maxp); - } /* get receiver timeout value */ mce_async_out(ir, GET_RX_TIMEOUT, sizeof(GET_RX_TIMEOUT)); - mce_sync_in(ir, NULL, maxp); /* get receiver sensor setting */ mce_async_out(ir, GET_RX_SENSOR, sizeof(GET_RX_SENSOR)); - mce_sync_in(ir, NULL, maxp); } static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir) @@ -1082,7 +1079,7 @@ static struct rc_dev *mceusb_init_rc_dev(struct mceusb_dev *ir) rc->priv = ir; rc->driver_type = RC_DRIVER_IR_RAW; rc->allowed_protos = RC_TYPE_ALL; - rc->timeout = US_TO_NS(1000); + rc->timeout = MS_TO_NS(100); if (!ir->flags.no_tx) { rc->s_tx_mask = mceusb_set_tx_mask; rc->s_tx_carrier = mceusb_set_tx_carrier; @@ -1122,7 +1119,7 @@ static int __devinit mceusb_dev_probe(struct usb_interface *intf, bool tx_mask_normal; int ir_intfnum; - dev_dbg(&intf->dev, "%s called\n", __func__); + mce_dbg(&intf->dev, "%s called\n", __func__); idesc = intf->cur_altsetting; @@ -1150,7 +1147,7 @@ static int __devinit mceusb_dev_probe(struct usb_interface *intf, ep_in = ep; ep_in->bmAttributes = USB_ENDPOINT_XFER_INT; ep_in->bInterval = 1; - dev_dbg(&intf->dev, "acceptable inbound endpoint " + mce_dbg(&intf->dev, "acceptable inbound endpoint " "found\n"); } @@ -1165,12 +1162,12 @@ static int __devinit mceusb_dev_probe(struct usb_interface *intf, ep_out = ep; ep_out->bmAttributes = USB_ENDPOINT_XFER_INT; ep_out->bInterval = 1; - dev_dbg(&intf->dev, "acceptable outbound endpoint " + mce_dbg(&intf->dev, "acceptable outbound endpoint " "found\n"); } } if (ep_in == NULL) { - dev_dbg(&intf->dev, "inbound and/or endpoint not found\n"); + mce_dbg(&intf->dev, "inbound and/or endpoint not found\n"); return -ENODEV; } @@ -1215,16 +1212,16 @@ static int __devinit mceusb_dev_probe(struct usb_interface *intf, if (!ir->rc) goto rc_dev_fail; - /* flush buffers on the device */ - mce_sync_in(ir, NULL, maxp); - mce_sync_in(ir, NULL, maxp); - /* wire up inbound data handler */ usb_fill_int_urb(ir->urb_in, dev, pipe, ir->buf_in, maxp, (usb_complete_t) mceusb_dev_recv, ir, ep_in->bInterval); ir->urb_in->transfer_dma = ir->dma_in; ir->urb_in->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; + /* flush buffers on the device */ + mce_dbg(&intf->dev, "Flushing receive buffers\n"); + mce_flush_rx_buffer(ir, maxp); + /* initialize device */ if (ir->flags.microsoft_gen1) mceusb_gen1_init(ir); diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c index bf3060e..ce595f9 100644 --- a/drivers/media/rc/nuvoton-cir.c +++ b/drivers/media/rc/nuvoton-cir.c @@ -991,7 +991,6 @@ static int nvt_open(struct rc_dev *dev) unsigned long flags; spin_lock_irqsave(&nvt->nvt_lock, flags); - nvt->in_use = true; nvt_enable_cir(nvt); spin_unlock_irqrestore(&nvt->nvt_lock, flags); @@ -1004,7 +1003,6 @@ static void nvt_close(struct rc_dev *dev) unsigned long flags; spin_lock_irqsave(&nvt->nvt_lock, flags); - nvt->in_use = false; nvt_disable_cir(nvt); spin_unlock_irqrestore(&nvt->nvt_lock, flags); } @@ -1112,7 +1110,7 @@ static int nvt_probe(struct pnp_dev *pdev, const struct pnp_device_id *dev_id) rdev->dev.parent = &pdev->dev; rdev->driver_name = NVT_DRIVER_NAME; rdev->map_name = RC_MAP_RC6_MCE; - rdev->timeout = US_TO_NS(1000); + rdev->timeout = MS_TO_NS(100); /* rx resolution is hardwired to 50us atm, 1, 25, 100 also possible */ rdev->rx_resolution = US_TO_NS(CIR_SAMPLE_PERIOD); #if 0 diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h index 379795d..1241fc8 100644 --- a/drivers/media/rc/nuvoton-cir.h +++ b/drivers/media/rc/nuvoton-cir.h @@ -70,7 +70,6 @@ struct nvt_dev { struct ir_raw_event rawir; spinlock_t nvt_lock; - bool in_use; /* for rx */ u8 buf[RX_BUF_LEN]; diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index f57cd56..3186ac7 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -522,18 +522,20 @@ EXPORT_SYMBOL_GPL(rc_g_keycode_from_table); /** * ir_do_keyup() - internal function to signal the release of a keypress * @dev: the struct rc_dev descriptor of the device + * @sync: whether or not to call input_sync * * This function is used internally to release a keypress, it must be * called with keylock held. */ -static void ir_do_keyup(struct rc_dev *dev) +static void ir_do_keyup(struct rc_dev *dev, bool sync) { if (!dev->keypressed) return; IR_dprintk(1, "keyup key 0x%04x\n", dev->last_keycode); input_report_key(dev->input_dev, dev->last_keycode, 0); - input_sync(dev->input_dev); + if (sync) + input_sync(dev->input_dev); dev->keypressed = false; } @@ -549,7 +551,7 @@ void rc_keyup(struct rc_dev *dev) unsigned long flags; spin_lock_irqsave(&dev->keylock, flags); - ir_do_keyup(dev); + ir_do_keyup(dev, true); spin_unlock_irqrestore(&dev->keylock, flags); } EXPORT_SYMBOL_GPL(rc_keyup); @@ -578,7 +580,7 @@ static void ir_timer_keyup(unsigned long cookie) */ spin_lock_irqsave(&dev->keylock, flags); if (time_is_before_eq_jiffies(dev->keyup_jiffies)) - ir_do_keyup(dev); + ir_do_keyup(dev, true); spin_unlock_irqrestore(&dev->keylock, flags); } @@ -597,6 +599,7 @@ void rc_repeat(struct rc_dev *dev) spin_lock_irqsave(&dev->keylock, flags); input_event(dev->input_dev, EV_MSC, MSC_SCAN, dev->last_scancode); + input_sync(dev->input_dev); if (!dev->keypressed) goto out; @@ -622,29 +625,28 @@ EXPORT_SYMBOL_GPL(rc_repeat); static void ir_do_keydown(struct rc_dev *dev, int scancode, u32 keycode, u8 toggle) { - input_event(dev->input_dev, EV_MSC, MSC_SCAN, scancode); - - /* Repeat event? */ - if (dev->keypressed && - dev->last_scancode == scancode && - dev->last_toggle == toggle) - return; + bool new_event = !dev->keypressed || + dev->last_scancode != scancode || + dev->last_toggle != toggle; - /* Release old keypress */ - ir_do_keyup(dev); + if (new_event && dev->keypressed) + ir_do_keyup(dev, false); - dev->last_scancode = scancode; - dev->last_toggle = toggle; - dev->last_keycode = keycode; + input_event(dev->input_dev, EV_MSC, MSC_SCAN, scancode); - if (keycode == KEY_RESERVED) - return; + if (new_event && keycode != KEY_RESERVED) { + /* Register a keypress */ + dev->keypressed = true; + dev->last_scancode = scancode; + dev->last_toggle = toggle; + dev->last_keycode = keycode; + + IR_dprintk(1, "%s: key down event, " + "key 0x%04x, scancode 0x%04x\n", + dev->input_name, keycode, scancode); + input_report_key(dev->input_dev, keycode, 1); + } - /* Register a keypress */ - dev->keypressed = true; - IR_dprintk(1, "%s: key down event, key 0x%04x, scancode 0x%04x\n", - dev->input_name, keycode, scancode); - input_report_key(dev->input_dev, dev->last_keycode, 1); input_sync(dev->input_dev); } diff --git a/drivers/media/video/bt8xx/bttv-driver.c b/drivers/media/video/bt8xx/bttv-driver.c index a97cf27..834a483 100644 --- a/drivers/media/video/bt8xx/bttv-driver.c +++ b/drivers/media/video/bt8xx/bttv-driver.c @@ -3474,7 +3474,7 @@ static int radio_s_tuner(struct file *file, void *priv, if (0 != t->index) return -EINVAL; - bttv_call_all(btv, tuner, g_tuner, t); + bttv_call_all(btv, tuner, s_tuner, t); return 0; } diff --git a/drivers/media/video/cx18/cx18-ioctl.c b/drivers/media/video/cx18/cx18-ioctl.c index 1933d4d..e80134f 100644 --- a/drivers/media/video/cx18/cx18-ioctl.c +++ b/drivers/media/video/cx18/cx18-ioctl.c @@ -695,14 +695,10 @@ static int cx18_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt) cx18_call_all(cx, tuner, g_tuner, vt); - if (test_bit(CX18_F_I_RADIO_USER, &cx->i_flags)) { + if (vt->type == V4L2_TUNER_RADIO) strlcpy(vt->name, "cx18 Radio Tuner", sizeof(vt->name)); - vt->type = V4L2_TUNER_RADIO; - } else { + else strlcpy(vt->name, "cx18 TV Tuner", sizeof(vt->name)); - vt->type = V4L2_TUNER_ANALOG_TV; - } - return 0; } diff --git a/drivers/media/video/cx23885/cx23885-core.c b/drivers/media/video/cx23885/cx23885-core.c index 64d9b21..419777a 100644 --- a/drivers/media/video/cx23885/cx23885-core.c +++ b/drivers/media/video/cx23885/cx23885-core.c @@ -2060,12 +2060,8 @@ static int __devinit cx23885_initdev(struct pci_dev *pci_dev, goto fail_irq; } - if (!pci_enable_msi(pci_dev)) - err = request_irq(pci_dev->irq, cx23885_irq, - IRQF_DISABLED, dev->name, dev); - else - err = request_irq(pci_dev->irq, cx23885_irq, - IRQF_SHARED | IRQF_DISABLED, dev->name, dev); + err = request_irq(pci_dev->irq, cx23885_irq, + IRQF_SHARED | IRQF_DISABLED, dev->name, dev); if (err < 0) { printk(KERN_ERR "%s: can't get IRQ %d\n", dev->name, pci_dev->irq); @@ -2114,7 +2110,6 @@ static void __devexit cx23885_finidev(struct pci_dev *pci_dev) /* unregister stuff */ free_irq(pci_dev->irq, dev); - pci_disable_msi(pci_dev); cx23885_dev_unregister(dev); v4l2_device_unregister(v4l2_dev); diff --git a/drivers/media/video/ivtv/ivtv-ioctl.c b/drivers/media/video/ivtv/ivtv-ioctl.c index f9e347d..120c7d8 100644 --- a/drivers/media/video/ivtv/ivtv-ioctl.c +++ b/drivers/media/video/ivtv/ivtv-ioctl.c @@ -1184,14 +1184,10 @@ static int ivtv_g_tuner(struct file *file, void *fh, struct v4l2_tuner *vt) ivtv_call_all(itv, tuner, g_tuner, vt); - if (test_bit(IVTV_F_I_RADIO_USER, &itv->i_flags)) { + if (vt->type == V4L2_TUNER_RADIO) strlcpy(vt->name, "ivtv Radio Tuner", sizeof(vt->name)); - vt->type = V4L2_TUNER_RADIO; - } else { + else strlcpy(vt->name, "ivtv TV Tuner", sizeof(vt->name)); - vt->type = V4L2_TUNER_ANALOG_TV; - } - return 0; } diff --git a/drivers/media/video/m5mols/m5mols.h b/drivers/media/video/m5mols/m5mols.h index 10b55c8..89d09a8 100644 --- a/drivers/media/video/m5mols/m5mols.h +++ b/drivers/media/video/m5mols/m5mols.h @@ -2,10 +2,10 @@ * Header for M-5MOLS 8M Pixel camera sensor with ISP * * Copyright (C) 2011 Samsung Electronics Co., Ltd. - * Author: HeungJun Kim, riverful.kim@samsung.com + * Author: HeungJun Kim <riverful.kim@samsung.com> * * Copyright (C) 2009 Samsung Electronics Co., Ltd. - * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.com + * Author: Dongsoo Nathaniel Kim <dongsoo45.kim@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -106,23 +106,23 @@ struct m5mols_capture { * The each value according to each scenemode is recommended in the documents. */ struct m5mols_scenemode { - u32 metering; - u32 ev_bias; - u32 wb_mode; - u32 wb_preset; - u32 chroma_en; - u32 chroma_lvl; - u32 edge_en; - u32 edge_lvl; - u32 af_range; - u32 fd_mode; - u32 mcc; - u32 light; - u32 flash; - u32 tone; - u32 iso; - u32 capt_mode; - u32 wdr; + u8 metering; + u8 ev_bias; + u8 wb_mode; + u8 wb_preset; + u8 chroma_en; + u8 chroma_lvl; + u8 edge_en; + u8 edge_lvl; + u8 af_range; + u8 fd_mode; + u8 mcc; + u8 light; + u8 flash; + u8 tone; + u8 iso; + u8 capt_mode; + u8 wdr; }; /** @@ -154,7 +154,6 @@ struct m5mols_version { u8 str[VERSION_STRING_SIZE]; u8 af; }; -#define VERSION_SIZE sizeof(struct m5mols_version) /** * struct m5mols_info - M-5MOLS driver data structure @@ -216,9 +215,9 @@ struct m5mols_info { bool lock_ae; bool lock_awb; u8 resolution; - u32 interrupt; - u32 mode; - u32 mode_save; + u8 interrupt; + u8 mode; + u8 mode_save; int (*set_power)(struct device *dev, int on); }; @@ -256,9 +255,11 @@ struct m5mols_info { * +-------+---+----------+-----+------+------+------+------+ * - d[0..3]: according to size1 */ -int m5mols_read(struct v4l2_subdev *sd, u32 reg_comb, u32 *val); +int m5mols_read_u8(struct v4l2_subdev *sd, u32 reg_comb, u8 *val); +int m5mols_read_u16(struct v4l2_subdev *sd, u32 reg_comb, u16 *val); +int m5mols_read_u32(struct v4l2_subdev *sd, u32 reg_comb, u32 *val); int m5mols_write(struct v4l2_subdev *sd, u32 reg_comb, u32 val); -int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u32 value); +int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u8 value); /* * Mode operation of the M-5MOLS @@ -280,12 +281,12 @@ int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u32 value); * The available executing order between each modes are as follows: * PARAMETER <---> MONITOR <---> CAPTURE */ -int m5mols_mode(struct m5mols_info *info, u32 mode); +int m5mols_mode(struct m5mols_info *info, u8 mode); -int m5mols_enable_interrupt(struct v4l2_subdev *sd, u32 reg); +int m5mols_enable_interrupt(struct v4l2_subdev *sd, u8 reg); int m5mols_sync_controls(struct m5mols_info *info); int m5mols_start_capture(struct m5mols_info *info); -int m5mols_do_scenemode(struct m5mols_info *info, u32 mode); +int m5mols_do_scenemode(struct m5mols_info *info, u8 mode); int m5mols_lock_3a(struct m5mols_info *info, bool lock); int m5mols_set_ctrl(struct v4l2_ctrl *ctrl); diff --git a/drivers/media/video/m5mols/m5mols_capture.c b/drivers/media/video/m5mols/m5mols_capture.c index d71a390..d947192 100644 --- a/drivers/media/video/m5mols/m5mols_capture.c +++ b/drivers/media/video/m5mols/m5mols_capture.c @@ -2,10 +2,10 @@ * The Capture code for Fujitsu M-5MOLS ISP * * Copyright (C) 2011 Samsung Electronics Co., Ltd. - * Author: HeungJun Kim, riverful.kim@samsung.com + * Author: HeungJun Kim <riverful.kim@samsung.com> * * Copyright (C) 2009 Samsung Electronics Co., Ltd. - * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.com + * Author: Dongsoo Nathaniel Kim <dongsoo45.kim@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -58,9 +58,9 @@ static int m5mols_read_rational(struct v4l2_subdev *sd, u32 addr_num, { u32 num, den; - int ret = m5mols_read(sd, addr_num, &num); + int ret = m5mols_read_u32(sd, addr_num, &num); if (!ret) - ret = m5mols_read(sd, addr_den, &den); + ret = m5mols_read_u32(sd, addr_den, &den); if (ret) return ret; *val = den == 0 ? 0 : num / den; @@ -99,20 +99,20 @@ static int m5mols_capture_info(struct m5mols_info *info) if (ret) return ret; - ret = m5mols_read(sd, EXIF_INFO_ISO, (u32 *)&exif->iso_speed); + ret = m5mols_read_u16(sd, EXIF_INFO_ISO, &exif->iso_speed); if (!ret) - ret = m5mols_read(sd, EXIF_INFO_FLASH, (u32 *)&exif->flash); + ret = m5mols_read_u16(sd, EXIF_INFO_FLASH, &exif->flash); if (!ret) - ret = m5mols_read(sd, EXIF_INFO_SDR, (u32 *)&exif->sdr); + ret = m5mols_read_u16(sd, EXIF_INFO_SDR, &exif->sdr); if (!ret) - ret = m5mols_read(sd, EXIF_INFO_QVAL, (u32 *)&exif->qval); + ret = m5mols_read_u16(sd, EXIF_INFO_QVAL, &exif->qval); if (ret) return ret; if (!ret) - ret = m5mols_read(sd, CAPC_IMAGE_SIZE, &info->cap.main); + ret = m5mols_read_u32(sd, CAPC_IMAGE_SIZE, &info->cap.main); if (!ret) - ret = m5mols_read(sd, CAPC_THUMB_SIZE, &info->cap.thumb); + ret = m5mols_read_u32(sd, CAPC_THUMB_SIZE, &info->cap.thumb); if (!ret) info->cap.total = info->cap.main + info->cap.thumb; @@ -122,7 +122,7 @@ static int m5mols_capture_info(struct m5mols_info *info) int m5mols_start_capture(struct m5mols_info *info) { struct v4l2_subdev *sd = &info->sd; - u32 resolution = info->resolution; + u8 resolution = info->resolution; int timeout; int ret; diff --git a/drivers/media/video/m5mols/m5mols_controls.c b/drivers/media/video/m5mols/m5mols_controls.c index 817c16f..d135d20 100644 --- a/drivers/media/video/m5mols/m5mols_controls.c +++ b/drivers/media/video/m5mols/m5mols_controls.c @@ -2,10 +2,10 @@ * Controls for M-5MOLS 8M Pixel camera sensor with ISP * * Copyright (C) 2011 Samsung Electronics Co., Ltd. - * Author: HeungJun Kim, riverful.kim@samsung.com + * Author: HeungJun Kim <riverful.kim@samsung.com> * * Copyright (C) 2009 Samsung Electronics Co., Ltd. - * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.com + * Author: Dongsoo Nathaniel Kim <dongsoo45.kim@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -130,7 +130,7 @@ static struct m5mols_scenemode m5mols_default_scenemode[] = { * * WARNING: The execution order is important. Do not change the order. */ -int m5mols_do_scenemode(struct m5mols_info *info, u32 mode) +int m5mols_do_scenemode(struct m5mols_info *info, u8 mode) { struct v4l2_subdev *sd = &info->sd; struct m5mols_scenemode scenemode = m5mols_default_scenemode[mode]; diff --git a/drivers/media/video/m5mols/m5mols_core.c b/drivers/media/video/m5mols/m5mols_core.c index 76eac26..43c68f5 100644 --- a/drivers/media/video/m5mols/m5mols_core.c +++ b/drivers/media/video/m5mols/m5mols_core.c @@ -2,10 +2,10 @@ * Driver for M-5MOLS 8M Pixel camera sensor with ISP * * Copyright (C) 2011 Samsung Electronics Co., Ltd. - * Author: HeungJun Kim, riverful.kim@samsung.com + * Author: HeungJun Kim <riverful.kim@samsung.com> * * Copyright (C) 2009 Samsung Electronics Co., Ltd. - * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.com + * Author: Dongsoo Nathaniel Kim <dongsoo45.kim@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -133,13 +133,13 @@ static u32 m5mols_swap_byte(u8 *data, u8 length) /** * m5mols_read - I2C read function * @reg: combination of size, category and command for the I2C packet + * @size: desired size of I2C packet * @val: read value */ -int m5mols_read(struct v4l2_subdev *sd, u32 reg, u32 *val) +static int m5mols_read(struct v4l2_subdev *sd, u32 size, u32 reg, u32 *val) { struct i2c_client *client = v4l2_get_subdevdata(sd); u8 rbuf[M5MOLS_I2C_MAX_SIZE + 1]; - u8 size = I2C_SIZE(reg); u8 category = I2C_CATEGORY(reg); u8 cmd = I2C_COMMAND(reg); struct i2c_msg msg[2]; @@ -149,11 +149,6 @@ int m5mols_read(struct v4l2_subdev *sd, u32 reg, u32 *val) if (!client->adapter) return -ENODEV; - if (size != 1 && size != 2 && size != 4) { - v4l2_err(sd, "Wrong data size\n"); - return -EINVAL; - } - msg[0].addr = client->addr; msg[0].flags = 0; msg[0].len = 5; @@ -184,6 +179,52 @@ int m5mols_read(struct v4l2_subdev *sd, u32 reg, u32 *val) return 0; } +int m5mols_read_u8(struct v4l2_subdev *sd, u32 reg, u8 *val) +{ + u32 val_32; + int ret; + + if (I2C_SIZE(reg) != 1) { + v4l2_err(sd, "Wrong data size\n"); + return -EINVAL; + } + + ret = m5mols_read(sd, I2C_SIZE(reg), reg, &val_32); + if (ret) + return ret; + + *val = (u8)val_32; + return ret; +} + +int m5mols_read_u16(struct v4l2_subdev *sd, u32 reg, u16 *val) +{ + u32 val_32; + int ret; + + if (I2C_SIZE(reg) != 2) { + v4l2_err(sd, "Wrong data size\n"); + return -EINVAL; + } + + ret = m5mols_read(sd, I2C_SIZE(reg), reg, &val_32); + if (ret) + return ret; + + *val = (u16)val_32; + return ret; +} + +int m5mols_read_u32(struct v4l2_subdev *sd, u32 reg, u32 *val) +{ + if (I2C_SIZE(reg) != 4) { + v4l2_err(sd, "Wrong data size\n"); + return -EINVAL; + } + + return m5mols_read(sd, I2C_SIZE(reg), reg, val); +} + /** * m5mols_write - I2C command write function * @reg: combination of size, category and command for the I2C packet @@ -231,13 +272,14 @@ int m5mols_write(struct v4l2_subdev *sd, u32 reg, u32 val) return 0; } -int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u32 mask) +int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u8 mask) { - u32 busy, i; + u8 busy; + int i; int ret; for (i = 0; i < M5MOLS_I2C_CHECK_RETRY; i++) { - ret = m5mols_read(sd, I2C_REG(category, cmd, 1), &busy); + ret = m5mols_read_u8(sd, I2C_REG(category, cmd, 1), &busy); if (ret < 0) return ret; if ((busy & mask) == mask) @@ -252,14 +294,14 @@ int m5mols_busy(struct v4l2_subdev *sd, u8 category, u8 cmd, u32 mask) * Before writing desired interrupt value the INT_FACTOR register should * be read to clear pending interrupts. */ -int m5mols_enable_interrupt(struct v4l2_subdev *sd, u32 reg) +int m5mols_enable_interrupt(struct v4l2_subdev *sd, u8 reg) { struct m5mols_info *info = to_m5mols(sd); - u32 mask = is_available_af(info) ? REG_INT_AF : 0; - u32 dummy; + u8 mask = is_available_af(info) ? REG_INT_AF : 0; + u8 dummy; int ret; - ret = m5mols_read(sd, SYSTEM_INT_FACTOR, &dummy); + ret = m5mols_read_u8(sd, SYSTEM_INT_FACTOR, &dummy); if (!ret) ret = m5mols_write(sd, SYSTEM_INT_ENABLE, reg & ~mask); return ret; @@ -271,7 +313,7 @@ int m5mols_enable_interrupt(struct v4l2_subdev *sd, u32 reg) * It always accompanies a little delay changing the M-5MOLS mode, so it is * needed checking current busy status to guarantee right mode. */ -static int m5mols_reg_mode(struct v4l2_subdev *sd, u32 mode) +static int m5mols_reg_mode(struct v4l2_subdev *sd, u8 mode) { int ret = m5mols_write(sd, SYSTEM_SYSMODE, mode); @@ -286,16 +328,16 @@ static int m5mols_reg_mode(struct v4l2_subdev *sd, u32 mode) * can be guaranteed only when the sensor is operating in mode which which * a command belongs to. */ -int m5mols_mode(struct m5mols_info *info, u32 mode) +int m5mols_mode(struct m5mols_info *info, u8 mode) { struct v4l2_subdev *sd = &info->sd; int ret = -EINVAL; - u32 reg; + u8 reg; if (mode < REG_PARAMETER && mode > REG_CAPTURE) return ret; - ret = m5mols_read(sd, SYSTEM_SYSMODE, ®); + ret = m5mols_read_u8(sd, SYSTEM_SYSMODE, ®); if ((!ret && reg == mode) || ret) return ret; @@ -344,41 +386,37 @@ int m5mols_mode(struct m5mols_info *info, u32 mode) static int m5mols_get_version(struct v4l2_subdev *sd) { struct m5mols_info *info = to_m5mols(sd); - union { - struct m5mols_version ver; - u8 bytes[VERSION_SIZE]; - } version; - u32 *value; - u8 cmd = CAT0_VER_CUSTOMER; + struct m5mols_version *ver = &info->ver; + u8 *str = ver->str; + int i; int ret; - do { - value = (u32 *)&version.bytes[cmd]; - ret = m5mols_read(sd, SYSTEM_CMD(cmd), value); - if (ret) - return ret; - } while (cmd++ != CAT0_VER_AWB); + ret = m5mols_read_u8(sd, SYSTEM_VER_CUSTOMER, &ver->customer); + if (!ret) + ret = m5mols_read_u8(sd, SYSTEM_VER_PROJECT, &ver->project); + if (!ret) + ret = m5mols_read_u16(sd, SYSTEM_VER_FIRMWARE, &ver->fw); + if (!ret) + ret = m5mols_read_u16(sd, SYSTEM_VER_HARDWARE, &ver->hw); + if (!ret) + ret = m5mols_read_u16(sd, SYSTEM_VER_PARAMETER, &ver->param); + if (!ret) + ret = m5mols_read_u16(sd, SYSTEM_VER_AWB, &ver->awb); + if (!ret) + ret = m5mols_read_u8(sd, AF_VERSION, &ver->af); + if (ret) + return ret; - do { - value = (u32 *)&version.bytes[cmd]; - ret = m5mols_read(sd, SYSTEM_VER_STRING, value); + for (i = 0; i < VERSION_STRING_SIZE; i++) { + ret = m5mols_read_u8(sd, SYSTEM_VER_STRING, &str[i]); if (ret) return ret; - if (cmd >= VERSION_SIZE - 1) - return -EINVAL; - } while (version.bytes[cmd++]); - - value = (u32 *)&version.bytes[cmd]; - ret = m5mols_read(sd, AF_VERSION, value); - if (ret) - return ret; + } - /* store version information swapped for being readable */ - info->ver = version.ver; - info->ver.fw = be16_to_cpu(info->ver.fw); - info->ver.hw = be16_to_cpu(info->ver.hw); - info->ver.param = be16_to_cpu(info->ver.param); - info->ver.awb = be16_to_cpu(info->ver.awb); + ver->fw = be16_to_cpu(ver->fw); + ver->hw = be16_to_cpu(ver->hw); + ver->param = be16_to_cpu(ver->param); + ver->awb = be16_to_cpu(ver->awb); v4l2_info(sd, "Manufacturer\t[%s]\n", is_manufacturer(info, REG_SAMSUNG_ELECTRO) ? @@ -722,7 +760,7 @@ static int m5mols_init_controls(struct m5mols_info *info) int ret; /* Determine value's range & step of controls for various FW version */ - ret = m5mols_read(sd, AE_MAX_GAIN_MON, (u32 *)&max_exposure); + ret = m5mols_read_u16(sd, AE_MAX_GAIN_MON, &max_exposure); if (!ret) step_zoom = is_manufacturer(info, REG_SAMSUNG_OPTICS) ? 31 : 1; if (ret) @@ -842,18 +880,18 @@ static void m5mols_irq_work(struct work_struct *work) struct m5mols_info *info = container_of(work, struct m5mols_info, work_irq); struct v4l2_subdev *sd = &info->sd; - u32 reg; + u8 reg; int ret; if (!is_powered(info) || - m5mols_read(sd, SYSTEM_INT_FACTOR, &info->interrupt)) + m5mols_read_u8(sd, SYSTEM_INT_FACTOR, &info->interrupt)) return; switch (info->interrupt & REG_INT_MASK) { case REG_INT_AF: if (!is_available_af(info)) break; - ret = m5mols_read(sd, AF_STATUS, ®); + ret = m5mols_read_u8(sd, AF_STATUS, ®); v4l2_dbg(2, m5mols_debug, sd, "AF %s\n", reg == REG_AF_FAIL ? "Failed" : reg == REG_AF_SUCCESS ? "Success" : diff --git a/drivers/media/video/m5mols/m5mols_reg.h b/drivers/media/video/m5mols/m5mols_reg.h index b83e36f..c755bd6 100644 --- a/drivers/media/video/m5mols/m5mols_reg.h +++ b/drivers/media/video/m5mols/m5mols_reg.h @@ -2,10 +2,10 @@ * Register map for M-5MOLS 8M Pixel camera sensor with ISP * * Copyright (C) 2011 Samsung Electronics Co., Ltd. - * Author: HeungJun Kim, riverful.kim@samsung.com + * Author: HeungJun Kim <riverful.kim@samsung.com> * * Copyright (C) 2009 Samsung Electronics Co., Ltd. - * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.com + * Author: Dongsoo Nathaniel Kim <dongsoo45.kim@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -56,13 +56,24 @@ * more specific contents, see definition if file m5mols.h. */ #define CAT0_VER_CUSTOMER 0x00 /* customer version */ -#define CAT0_VER_AWB 0x09 /* Auto WB version */ +#define CAT0_VER_PROJECT 0x01 /* project version */ +#define CAT0_VER_FIRMWARE 0x02 /* Firmware version */ +#define CAT0_VER_HARDWARE 0x04 /* Hardware version */ +#define CAT0_VER_PARAMETER 0x06 /* Parameter version */ +#define CAT0_VER_AWB 0x08 /* Auto WB version */ #define CAT0_VER_STRING 0x0a /* string including M-5MOLS */ #define CAT0_SYSMODE 0x0b /* SYSTEM mode register */ #define CAT0_STATUS 0x0c /* SYSTEM mode status register */ #define CAT0_INT_FACTOR 0x10 /* interrupt pending register */ #define CAT0_INT_ENABLE 0x11 /* interrupt enable register */ +#define SYSTEM_VER_CUSTOMER I2C_REG(CAT_SYSTEM, CAT0_VER_CUSTOMER, 1) +#define SYSTEM_VER_PROJECT I2C_REG(CAT_SYSTEM, CAT0_VER_PROJECT, 1) +#define SYSTEM_VER_FIRMWARE I2C_REG(CAT_SYSTEM, CAT0_VER_FIRMWARE, 2) +#define SYSTEM_VER_HARDWARE I2C_REG(CAT_SYSTEM, CAT0_VER_HARDWARE, 2) +#define SYSTEM_VER_PARAMETER I2C_REG(CAT_SYSTEM, CAT0_VER_PARAMETER, 2) +#define SYSTEM_VER_AWB I2C_REG(CAT_SYSTEM, CAT0_VER_AWB, 2) + #define SYSTEM_SYSMODE I2C_REG(CAT_SYSTEM, CAT0_SYSMODE, 1) #define REG_SYSINIT 0x00 /* SYSTEM mode */ #define REG_PARAMETER 0x01 /* PARAMETER mode */ @@ -382,8 +393,8 @@ #define REG_CAP_START_MAIN 0x01 #define REG_CAP_START_THUMB 0x03 -#define CAPC_IMAGE_SIZE I2C_REG(CAT_CAPT_CTRL, CATC_CAP_IMAGE_SIZE, 1) -#define CAPC_THUMB_SIZE I2C_REG(CAT_CAPT_CTRL, CATC_CAP_THUMB_SIZE, 1) +#define CAPC_IMAGE_SIZE I2C_REG(CAT_CAPT_CTRL, CATC_CAP_IMAGE_SIZE, 4) +#define CAPC_THUMB_SIZE I2C_REG(CAT_CAPT_CTRL, CATC_CAP_THUMB_SIZE, 4) /* * Category F - Flash diff --git a/drivers/media/video/msp3400-driver.c b/drivers/media/video/msp3400-driver.c index de5d481..c43c81f 100644 --- a/drivers/media/video/msp3400-driver.c +++ b/drivers/media/video/msp3400-driver.c @@ -480,12 +480,14 @@ static int msp_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *vt) struct msp_state *state = to_state(sd); struct i2c_client *client = v4l2_get_subdevdata(sd); - if (state->radio) + if (vt->type != V4L2_TUNER_ANALOG_TV) return 0; - if (state->opmode == OPMODE_AUTOSELECT) - msp_detect_stereo(client); - vt->audmode = state->audmode; - vt->rxsubchans = state->rxsubchans; + if (!state->radio) { + if (state->opmode == OPMODE_AUTOSELECT) + msp_detect_stereo(client); + vt->rxsubchans = state->rxsubchans; + } + vt->audmode = state->audmode; vt->capability |= V4L2_TUNER_CAP_STEREO | V4L2_TUNER_CAP_LANG1 | V4L2_TUNER_CAP_LANG2; return 0; diff --git a/drivers/media/video/mx1_camera.c b/drivers/media/video/mx1_camera.c index bc0c23a..63f8a0c 100644 --- a/drivers/media/video/mx1_camera.c +++ b/drivers/media/video/mx1_camera.c @@ -444,12 +444,9 @@ static int mx1_camera_add_device(struct soc_camera_device *icd) { struct soc_camera_host *ici = to_soc_camera_host(icd->dev.parent); struct mx1_camera_dev *pcdev = ici->priv; - int ret; - if (pcdev->icd) { - ret = -EBUSY; - goto ebusy; - } + if (pcdev->icd) + return -EBUSY; dev_info(icd->dev.parent, "MX1 Camera driver attached to camera %d\n", icd->devnum); @@ -458,8 +455,7 @@ static int mx1_camera_add_device(struct soc_camera_device *icd) pcdev->icd = icd; -ebusy: - return ret; + return 0; } static void mx1_camera_remove_device(struct soc_camera_device *icd) diff --git a/drivers/media/video/omap/omap_vout.c b/drivers/media/video/omap/omap_vout.c index 4ada9be..4d07c58 100644 --- a/drivers/media/video/omap/omap_vout.c +++ b/drivers/media/video/omap/omap_vout.c @@ -982,6 +982,14 @@ static int omap_vout_buffer_setup(struct videobuf_queue *q, unsigned int *count, startindex = (vout->vid == OMAP_VIDEO1) ? video1_numbuffers : video2_numbuffers; + /* Check the size of the buffer */ + if (*size > vout->buffer_size) { + v4l2_err(&vout->vid_dev->v4l2_dev, + "buffer allocation mismatch [%u] [%u]\n", + *size, vout->buffer_size); + return -ENOMEM; + } + for (i = startindex; i < *count; i++) { vout->buffer_size = *size; @@ -1228,6 +1236,14 @@ static int omap_vout_mmap(struct file *file, struct vm_area_struct *vma) (vma->vm_pgoff << PAGE_SHIFT)); return -EINVAL; } + /* Check the size of the buffer */ + if (size > vout->buffer_size) { + v4l2_err(&vout->vid_dev->v4l2_dev, + "insufficient memory [%lu] [%u]\n", + size, vout->buffer_size); + return -ENOMEM; + } + q->bufs[i]->baddr = vma->vm_start; vma->vm_flags |= VM_RESERVED; @@ -2391,7 +2407,7 @@ static int __init omap_vout_create_video_devices(struct platform_device *pdev) /* Register the Video device with V4L2 */ vfd = vout->vfd; - if (video_register_device(vfd, VFL_TYPE_GRABBER, k + 1) < 0) { + if (video_register_device(vfd, VFL_TYPE_GRABBER, -1) < 0) { dev_err(&pdev->dev, ": Could not register " "Video for Linux device\n"); vfd->minor = -1; diff --git a/drivers/media/video/omap/omap_voutlib.c b/drivers/media/video/omap/omap_voutlib.c index 2aa6a76..8ae7481 100644 --- a/drivers/media/video/omap/omap_voutlib.c +++ b/drivers/media/video/omap/omap_voutlib.c @@ -193,7 +193,7 @@ int omap_vout_new_crop(struct v4l2_pix_format *pix, return -EINVAL; if (cpu_is_omap24xx()) { - if (crop->height != win->w.height) { + if (try_crop.height != win->w.height) { /* If we're resizing vertically, we can't support a * crop width wider than 768 pixels. */ @@ -202,7 +202,7 @@ int omap_vout_new_crop(struct v4l2_pix_format *pix, } } /* vertical resizing */ - vresize = (1024 * crop->height) / win->w.height; + vresize = (1024 * try_crop.height) / win->w.height; if (cpu_is_omap24xx() && (vresize > 2048)) vresize = 2048; else if (cpu_is_omap34xx() && (vresize > 4096)) @@ -221,7 +221,7 @@ int omap_vout_new_crop(struct v4l2_pix_format *pix, try_crop.height = 2; } /* horizontal resizing */ - hresize = (1024 * crop->width) / win->w.width; + hresize = (1024 * try_crop.width) / win->w.width; if (cpu_is_omap24xx() && (hresize > 2048)) hresize = 2048; else if (cpu_is_omap34xx() && (hresize > 4096)) diff --git a/drivers/media/video/omap3isp/isp.c b/drivers/media/video/omap3isp/isp.c index c9fd04e..94b6ed8 100644 --- a/drivers/media/video/omap3isp/isp.c +++ b/drivers/media/video/omap3isp/isp.c @@ -1748,7 +1748,7 @@ static int isp_register_entities(struct isp_device *isp) goto done; /* Register external entities */ - for (subdevs = pdata->subdevs; subdevs->subdevs; ++subdevs) { + for (subdevs = pdata->subdevs; subdevs && subdevs->subdevs; ++subdevs) { struct v4l2_subdev *sensor; struct media_entity *input; unsigned int flags; diff --git a/drivers/media/video/pvrusb2/pvrusb2-hdw.c b/drivers/media/video/pvrusb2/pvrusb2-hdw.c index 9d0dd08..e98d382 100644 --- a/drivers/media/video/pvrusb2/pvrusb2-hdw.c +++ b/drivers/media/video/pvrusb2/pvrusb2-hdw.c @@ -3046,6 +3046,8 @@ static void pvr2_subdev_update(struct pvr2_hdw *hdw) if (hdw->input_dirty || hdw->audiomode_dirty || hdw->force_dirty) { struct v4l2_tuner vt; memset(&vt, 0, sizeof(vt)); + vt.type = (hdw->input_val == PVR2_CVAL_INPUT_RADIO) ? + V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; vt.audmode = hdw->audiomode_val; v4l2_device_call_all(&hdw->v4l2_dev, 0, tuner, s_tuner, &vt); } @@ -5171,6 +5173,8 @@ void pvr2_hdw_status_poll(struct pvr2_hdw *hdw) { struct v4l2_tuner *vtp = &hdw->tuner_signal_info; memset(vtp, 0, sizeof(*vtp)); + vtp->type = (hdw->input_val == PVR2_CVAL_INPUT_RADIO) ? + V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; hdw->tuner_signal_stale = 0; /* Note: There apparently is no replacement for VIDIOC_CROPCAP using v4l2-subdev - therefore we can't support that AT ALL right diff --git a/drivers/media/video/pwc/pwc-ctrl.c b/drivers/media/video/pwc/pwc-ctrl.c index 1593f8d..760b4de 100644 --- a/drivers/media/video/pwc/pwc-ctrl.c +++ b/drivers/media/video/pwc/pwc-ctrl.c @@ -1414,7 +1414,7 @@ long pwc_ioctl(struct pwc_device *pdev, unsigned int cmd, void *arg) { ARG_DEF(struct pwc_probe, probe) - strcpy(ARGR(probe).name, pdev->vdev->name); + strcpy(ARGR(probe).name, pdev->vdev.name); ARGR(probe).type = pdev->type; ARG_OUT(probe) break; diff --git a/drivers/media/video/pwc/pwc-if.c b/drivers/media/video/pwc/pwc-if.c index 356cd42..b0bde5a 100644 --- a/drivers/media/video/pwc/pwc-if.c +++ b/drivers/media/video/pwc/pwc-if.c @@ -40,7 +40,7 @@ Oh yes, convention: to disctinguish between all the various pointers to device-structures, I use these names for the pointer variables: udev: struct usb_device * - vdev: struct video_device * + vdev: struct video_device (member of pwc_dev) pdev: struct pwc_devive * */ @@ -152,6 +152,7 @@ static ssize_t pwc_video_read(struct file *file, char __user *buf, size_t count, loff_t *ppos); static unsigned int pwc_video_poll(struct file *file, poll_table *wait); static int pwc_video_mmap(struct file *file, struct vm_area_struct *vma); +static void pwc_video_release(struct video_device *vfd); static const struct v4l2_file_operations pwc_fops = { .owner = THIS_MODULE, @@ -164,42 +165,12 @@ static const struct v4l2_file_operations pwc_fops = { }; static struct video_device pwc_template = { .name = "Philips Webcam", /* Filled in later */ - .release = video_device_release, + .release = pwc_video_release, .fops = &pwc_fops, + .ioctl_ops = &pwc_ioctl_ops, }; /***************************************************************************/ - -/* Okay, this is some magic that I worked out and the reasoning behind it... - - The biggest problem with any USB device is of course: "what to do - when the user unplugs the device while it is in use by an application?" - We have several options: - 1) Curse them with the 7 plagues when they do (requires divine intervention) - 2) Tell them not to (won't work: they'll do it anyway) - 3) Oops the kernel (this will have a negative effect on a user's uptime) - 4) Do something sensible. - - Of course, we go for option 4. - - It happens that this device will be linked to two times, once from - usb_device and once from the video_device in their respective 'private' - pointers. This is done when the device is probed() and all initialization - succeeded. The pwc_device struct links back to both structures. - - When a device is unplugged while in use it will be removed from the - list of known USB devices; I also de-register it as a V4L device, but - unfortunately I can't free the memory since the struct is still in use - by the file descriptor. This free-ing is then deferend until the first - opportunity. Crude, but it works. - - A small 'advantage' is that if a user unplugs the cam and plugs it back - in, it should get assigned the same video device minor, but unfortunately - it's non-trivial to re-link the cam back to the video device... (that - would surely be magic! :)) -*/ - -/***************************************************************************/ /* Private functions */ /* Here we want the physical address of the memory. @@ -1016,16 +987,15 @@ static ssize_t show_snapshot_button_status(struct device *class_dev, static DEVICE_ATTR(button, S_IRUGO | S_IWUSR, show_snapshot_button_status, NULL); -static int pwc_create_sysfs_files(struct video_device *vdev) +static int pwc_create_sysfs_files(struct pwc_device *pdev) { - struct pwc_device *pdev = video_get_drvdata(vdev); int rc; - rc = device_create_file(&vdev->dev, &dev_attr_button); + rc = device_create_file(&pdev->vdev.dev, &dev_attr_button); if (rc) goto err; if (pdev->features & FEATURE_MOTOR_PANTILT) { - rc = device_create_file(&vdev->dev, &dev_attr_pan_tilt); + rc = device_create_file(&pdev->vdev.dev, &dev_attr_pan_tilt); if (rc) goto err_button; } @@ -1033,19 +1003,17 @@ static int pwc_create_sysfs_files(struct video_device *vdev) return 0; err_button: - device_remove_file(&vdev->dev, &dev_attr_button); + device_remove_file(&pdev->vdev.dev, &dev_attr_button); err: PWC_ERROR("Could not create sysfs files.\n"); return rc; } -static void pwc_remove_sysfs_files(struct video_device *vdev) +static void pwc_remove_sysfs_files(struct pwc_device *pdev) { - struct pwc_device *pdev = video_get_drvdata(vdev); - if (pdev->features & FEATURE_MOTOR_PANTILT) - device_remove_file(&vdev->dev, &dev_attr_pan_tilt); - device_remove_file(&vdev->dev, &dev_attr_button); + device_remove_file(&pdev->vdev.dev, &dev_attr_pan_tilt); + device_remove_file(&pdev->vdev.dev, &dev_attr_button); } #ifdef CONFIG_USB_PWC_DEBUG @@ -1106,7 +1074,7 @@ static int pwc_video_open(struct file *file) if (ret >= 0) { PWC_DEBUG_OPEN("This %s camera is equipped with a %s (%d).\n", - pdev->vdev->name, + pdev->vdev.name, pwc_sensor_type_to_string(i), i); } } @@ -1180,16 +1148,15 @@ static int pwc_video_open(struct file *file) return 0; } - -static void pwc_cleanup(struct pwc_device *pdev) +static void pwc_video_release(struct video_device *vfd) { - pwc_remove_sysfs_files(pdev->vdev); - video_unregister_device(pdev->vdev); + struct pwc_device *pdev = container_of(vfd, struct pwc_device, vdev); + int hint; -#ifdef CONFIG_USB_PWC_INPUT_EVDEV - if (pdev->button_dev) - input_unregister_device(pdev->button_dev); -#endif + /* search device_hint[] table if we occupy a slot, by any chance */ + for (hint = 0; hint < MAX_DEV_HINTS; hint++) + if (device_hint[hint].pdev == pdev) + device_hint[hint].pdev = NULL; kfree(pdev); } @@ -1199,7 +1166,7 @@ static int pwc_video_close(struct file *file) { struct video_device *vdev = file->private_data; struct pwc_device *pdev; - int i, hint; + int i; PWC_DEBUG_OPEN(">> video_close called(vdev = 0x%p).\n", vdev); @@ -1234,12 +1201,6 @@ static int pwc_video_close(struct file *file) } pdev->vopen--; PWC_DEBUG_OPEN("<< video_close() vopen=%d\n", pdev->vopen); - } else { - pwc_cleanup(pdev); - /* search device_hint[] table if we occupy a slot, by any chance */ - for (hint = 0; hint < MAX_DEV_HINTS; hint++) - if (device_hint[hint].pdev == pdev) - device_hint[hint].pdev = NULL; } return 0; @@ -1715,19 +1676,12 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id init_waitqueue_head(&pdev->frameq); pdev->vcompression = pwc_preferred_compression; - /* Allocate video_device structure */ - pdev->vdev = video_device_alloc(); - if (!pdev->vdev) { - PWC_ERROR("Err, cannot allocate video_device struture. Failing probe."); - rc = -ENOMEM; - goto err_free_mem; - } - memcpy(pdev->vdev, &pwc_template, sizeof(pwc_template)); - pdev->vdev->parent = &intf->dev; - pdev->vdev->lock = &pdev->modlock; - pdev->vdev->ioctl_ops = &pwc_ioctl_ops; - strcpy(pdev->vdev->name, name); - video_set_drvdata(pdev->vdev, pdev); + /* Init video_device structure */ + memcpy(&pdev->vdev, &pwc_template, sizeof(pwc_template)); + pdev->vdev.parent = &intf->dev; + pdev->vdev.lock = &pdev->modlock; + strcpy(pdev->vdev.name, name); + video_set_drvdata(&pdev->vdev, pdev); pdev->release = le16_to_cpu(udev->descriptor.bcdDevice); PWC_DEBUG_PROBE("Release: %04x\n", pdev->release); @@ -1746,8 +1700,6 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id } } - pdev->vdev->release = video_device_release; - /* occupy slot */ if (hint < MAX_DEV_HINTS) device_hint[hint].pdev = pdev; @@ -1759,16 +1711,16 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id pwc_set_leds(pdev, 0, 0); pwc_camera_power(pdev, 0); - rc = video_register_device(pdev->vdev, VFL_TYPE_GRABBER, video_nr); + rc = video_register_device(&pdev->vdev, VFL_TYPE_GRABBER, video_nr); if (rc < 0) { PWC_ERROR("Failed to register as video device (%d).\n", rc); - goto err_video_release; + goto err_free_mem; } - rc = pwc_create_sysfs_files(pdev->vdev); + rc = pwc_create_sysfs_files(pdev); if (rc) goto err_video_unreg; - PWC_INFO("Registered as %s.\n", video_device_node_name(pdev->vdev)); + PWC_INFO("Registered as %s.\n", video_device_node_name(&pdev->vdev)); #ifdef CONFIG_USB_PWC_INPUT_EVDEV /* register webcam snapshot button input device */ @@ -1776,7 +1728,7 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id if (!pdev->button_dev) { PWC_ERROR("Err, insufficient memory for webcam snapshot button device."); rc = -ENOMEM; - pwc_remove_sysfs_files(pdev->vdev); + pwc_remove_sysfs_files(pdev); goto err_video_unreg; } @@ -1794,7 +1746,7 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id if (rc) { input_free_device(pdev->button_dev); pdev->button_dev = NULL; - pwc_remove_sysfs_files(pdev->vdev); + pwc_remove_sysfs_files(pdev); goto err_video_unreg; } #endif @@ -1804,10 +1756,7 @@ static int usb_pwc_probe(struct usb_interface *intf, const struct usb_device_id err_video_unreg: if (hint < MAX_DEV_HINTS) device_hint[hint].pdev = NULL; - video_unregister_device(pdev->vdev); - pdev->vdev = NULL; /* So we don't try to release it below */ -err_video_release: - video_device_release(pdev->vdev); + video_unregister_device(&pdev->vdev); err_free_mem: kfree(pdev); return rc; @@ -1816,10 +1765,8 @@ err_free_mem: /* The user yanked out the cable... */ static void usb_pwc_disconnect(struct usb_interface *intf) { - struct pwc_device *pdev; - int hint; + struct pwc_device *pdev = usb_get_intfdata(intf); - pdev = usb_get_intfdata (intf); mutex_lock(&pdev->modlock); usb_set_intfdata (intf, NULL); if (pdev == NULL) { @@ -1836,30 +1783,25 @@ static void usb_pwc_disconnect(struct usb_interface *intf) } /* We got unplugged; this is signalled by an EPIPE error code */ - if (pdev->vopen) { - PWC_INFO("Disconnected while webcam is in use!\n"); - pdev->error_status = EPIPE; - } + pdev->error_status = EPIPE; + pdev->unplugged = 1; /* Alert waiting processes */ wake_up_interruptible(&pdev->frameq); - /* Wait until device is closed */ - if (pdev->vopen) { - pdev->unplugged = 1; - pwc_iso_stop(pdev); - } else { - /* Device is closed, so we can safely unregister it */ - PWC_DEBUG_PROBE("Unregistering video device in disconnect().\n"); -disconnect_out: - /* search device_hint[] table if we occupy a slot, by any chance */ - for (hint = 0; hint < MAX_DEV_HINTS; hint++) - if (device_hint[hint].pdev == pdev) - device_hint[hint].pdev = NULL; - } + /* No need to keep the urbs around after disconnection */ + pwc_isoc_cleanup(pdev); +disconnect_out: mutex_unlock(&pdev->modlock); - pwc_cleanup(pdev); + + pwc_remove_sysfs_files(pdev); + video_unregister_device(&pdev->vdev); + +#ifdef CONFIG_USB_PWC_INPUT_EVDEV + if (pdev->button_dev) + input_unregister_device(pdev->button_dev); +#endif } diff --git a/drivers/media/video/pwc/pwc.h b/drivers/media/video/pwc/pwc.h index e947766..083f8b1 100644 --- a/drivers/media/video/pwc/pwc.h +++ b/drivers/media/video/pwc/pwc.h @@ -162,9 +162,9 @@ struct pwc_imgbuf struct pwc_device { - struct video_device *vdev; + struct video_device vdev; - /* Pointer to our usb_device */ + /* Pointer to our usb_device, may be NULL after unplug */ struct usb_device *udev; int type; /* type of cam (645, 646, 675, 680, 690, 720, 730, 740, 750) */ diff --git a/drivers/media/video/s5p-fimc/fimc-capture.c b/drivers/media/video/s5p-fimc/fimc-capture.c index d142b40..81b4a82 100644 --- a/drivers/media/video/s5p-fimc/fimc-capture.c +++ b/drivers/media/video/s5p-fimc/fimc-capture.c @@ -1,7 +1,7 @@ /* - * Samsung S5P SoC series camera interface (camera capture) driver + * Samsung S5P/EXYNOS4 SoC series camera interface (camera capture) driver * - * Copyright (c) 2010 Samsung Electronics Co., Ltd + * Copyright (C) 2010 - 2011 Samsung Electronics Co., Ltd. * Author: Sylwester Nawrocki, <s.nawrocki@samsung.com> * * This program is free software; you can redistribute it and/or modify @@ -262,12 +262,7 @@ static unsigned int get_plane_size(struct fimc_frame *fr, unsigned int plane) { if (!fr || plane >= fr->fmt->memplanes) return 0; - - dbg("%s: w: %d. h: %d. depth[%d]: %d", - __func__, fr->width, fr->height, plane, fr->fmt->depth[plane]); - return fr->f_width * fr->f_height * fr->fmt->depth[plane] / 8; - } static int queue_setup(struct vb2_queue *vq, unsigned int *num_buffers, @@ -283,24 +278,14 @@ static int queue_setup(struct vb2_queue *vq, unsigned int *num_buffers, *num_planes = fmt->memplanes; - dbg("%s, buffer count=%d, plane count=%d", - __func__, *num_buffers, *num_planes); - for (i = 0; i < fmt->memplanes; i++) { sizes[i] = get_plane_size(&ctx->d_frame, i); - dbg("plane: %u, plane_size: %lu", i, sizes[i]); allocators[i] = ctx->fimc_dev->alloc_ctx; } return 0; } -static int buffer_init(struct vb2_buffer *vb) -{ - /* TODO: */ - return 0; -} - static int buffer_prepare(struct vb2_buffer *vb) { struct vb2_queue *vq = vb->vb2_queue; @@ -380,7 +365,6 @@ static struct vb2_ops fimc_capture_qops = { .queue_setup = queue_setup, .buf_prepare = buffer_prepare, .buf_queue = buffer_queue, - .buf_init = buffer_init, .wait_prepare = fimc_unlock, .wait_finish = fimc_lock, .start_streaming = start_streaming, @@ -903,6 +887,7 @@ err_vd_reg: err_v4l2_reg: v4l2_device_unregister(v4l2_dev); err_info: + kfree(ctx); dev_err(&fimc->pdev->dev, "failed to install\n"); return ret; } diff --git a/drivers/media/video/s5p-fimc/fimc-core.c b/drivers/media/video/s5p-fimc/fimc-core.c index dc91a85..bdf19ad 100644 --- a/drivers/media/video/s5p-fimc/fimc-core.c +++ b/drivers/media/video/s5p-fimc/fimc-core.c @@ -1,9 +1,8 @@ /* - * S5P camera interface (video postprocessor) driver + * Samsung S5P/EXYNOS4 SoC series camera interface (video postprocessor) driver * - * Copyright (c) 2010 Samsung Electronics Co., Ltd - * - * Sylwester Nawrocki, <s.nawrocki@samsung.com> + * Copyright (C) 2010-2011 Samsung Electronics Co., Ltd. + * Contact: Sylwester Nawrocki, <s.nawrocki@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published @@ -42,7 +41,6 @@ static struct fimc_fmt fimc_formats[] = { .color = S5P_FIMC_RGB565, .memplanes = 1, .colplanes = 1, - .mbus_code = V4L2_MBUS_FMT_RGB565_2X8_BE, .flags = FMT_FLAGS_M2M, }, { .name = "BGR666", @@ -232,11 +230,7 @@ static int fimc_get_scaler_factor(u32 src, u32 tar, u32 *ratio, u32 *shift) return 0; } } - *shift = 0, *ratio = 1; - - dbg("s: %d, t: %d, shift: %d, ratio: %d", - src, tar, *shift, *ratio); return 0; } @@ -268,10 +262,8 @@ int fimc_set_scaler_info(struct fimc_ctx *ctx) err("invalid source size: %d x %d", sx, sy); return -EINVAL; } - sc->real_width = sx; sc->real_height = sy; - dbg("sx= %d, sy= %d, tx= %d, ty= %d", sx, sy, tx, ty); ret = fimc_get_scaler_factor(sx, tx, &sc->pre_hratio, &sc->hfactor); if (ret) @@ -711,22 +703,18 @@ static int fimc_queue_setup(struct vb2_queue *vq, unsigned int *num_buffers, f = ctx_get_frame(ctx, vq->type); if (IS_ERR(f)) return PTR_ERR(f); - /* * Return number of non-contigous planes (plane buffers) * depending on the configured color format. */ - if (f->fmt) - *num_planes = f->fmt->memplanes; + if (!f->fmt) + return -EINVAL; + *num_planes = f->fmt->memplanes; for (i = 0; i < f->fmt->memplanes; i++) { - sizes[i] = (f->width * f->height * f->fmt->depth[i]) >> 3; + sizes[i] = (f->f_width * f->f_height * f->fmt->depth[i]) / 8; allocators[i] = ctx->fimc_dev->alloc_ctx; } - - if (*num_buffers == 0) - *num_buffers = 1; - return 0; } @@ -852,7 +840,7 @@ struct fimc_fmt *find_format(struct v4l2_format *f, unsigned int mask) for (i = 0; i < ARRAY_SIZE(fimc_formats); ++i) { fmt = &fimc_formats[i]; - if (fmt->fourcc == f->fmt.pix.pixelformat && + if (fmt->fourcc == f->fmt.pix_mp.pixelformat && (fmt->flags & mask)) break; } diff --git a/drivers/media/video/s5p-fimc/fimc-core.h b/drivers/media/video/s5p-fimc/fimc-core.h index 3beb1e5..1f70772 100644 --- a/drivers/media/video/s5p-fimc/fimc-core.h +++ b/drivers/media/video/s5p-fimc/fimc-core.h @@ -1,7 +1,5 @@ /* - * Copyright (c) 2010 Samsung Electronics - * - * Sylwester Nawrocki, <s.nawrocki@samsung.com> + * Copyright (C) 2010 - 2011 Samsung Electronics Co., Ltd. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -135,9 +133,10 @@ enum fimc_color_fmt { * @name: format description * @fourcc: the fourcc code for this format, 0 if not applicable * @color: the corresponding fimc_color_fmt - * @depth: per plane driver's private 'number of bits per pixel' * @memplanes: number of physically non-contiguous data planes * @colplanes: number of physically contiguous data planes + * @depth: per plane driver's private 'number of bits per pixel' + * @flags: flags indicating which operation mode format applies to */ struct fimc_fmt { enum v4l2_mbus_pixelcode mbus_code; @@ -171,7 +170,7 @@ struct fimc_dma_offset { }; /** - * struct fimc_effect - the configuration data for the "Arbitrary" image effect + * struct fimc_effect - color effect information * @type: effect type * @pat_cb: cr value when type is "arbitrary" * @pat_cr: cr value when type is "arbitrary" @@ -184,7 +183,6 @@ struct fimc_effect { /** * struct fimc_scaler - the configuration data for FIMC inetrnal scaler - * * @scaleup_h: flag indicating scaling up horizontally * @scaleup_v: flag indicating scaling up vertically * @copy_mode: flag indicating transparent DMA transfer (no scaling @@ -220,7 +218,6 @@ struct fimc_scaler { /** * struct fimc_addr - the FIMC physical address set for DMA - * * @y: luminance plane physical address * @cb: Cb plane physical address * @cr: Cr plane physical address @@ -234,6 +231,7 @@ struct fimc_addr { /** * struct fimc_vid_buffer - the driver's video buffer * @vb: v4l videobuf buffer + * @list: linked list structure for buffer queue * @paddr: precalculated physical address set * @index: buffer index for the output DMA engine */ @@ -254,11 +252,10 @@ struct fimc_vid_buffer { * @offs_v: image vertical pixel offset * @width: image pixel width * @height: image pixel weight - * @paddr: image frame buffer physical addresses - * @buf_cnt: number of buffers depending on a color format * @payload: image size in bytes (w x h x bpp) - * @color: color format + * @paddr: image frame buffer physical addresses * @dma_offset: DMA offset in bytes + * @fmt: fimc color format pointer */ struct fimc_frame { u32 f_width; @@ -390,21 +387,22 @@ struct fimc_ctx; /** * struct fimc_dev - abstraction for FIMC entity - * * @slock: the spinlock protecting this data structure * @lock: the mutex protecting this data structure * @pdev: pointer to the FIMC platform device * @pdata: pointer to the device platform data + * @variant: the IP variant information * @id: FIMC device index (0..FIMC_MAX_DEVS) * @num_clocks: the number of clocks managed by this device instance - * @clock[]: the clocks required for FIMC operation + * @clock: clocks required for FIMC operation * @regs: the mapped hardware registers * @regs_res: the resource claimed for IO registers - * @irq: interrupt number of the FIMC subdevice - * @irq_queue: + * @irq: FIMC interrupt number + * @irq_queue: interrupt handler waitqueue * @m2m: memory-to-memory V4L2 device information * @vid_cap: camera capture device information * @state: flags used to synchronize m2m and capture mode operation + * @alloc_ctx: videobuf2 memory allocator context */ struct fimc_dev { spinlock_t slock; @@ -427,8 +425,7 @@ struct fimc_dev { /** * fimc_ctx - the device context data - * - * @lock: mutex protecting this data structure + * @slock: spinlock protecting this data structure * @s_frame: source frame properties * @d_frame: destination frame properties * @out_order_1p: output 1-plane YCBCR order diff --git a/drivers/media/video/saa7134/saa7134-input.c b/drivers/media/video/saa7134/saa7134-input.c index ff6c0e9..d4ee24b 100644 --- a/drivers/media/video/saa7134/saa7134-input.c +++ b/drivers/media/video/saa7134/saa7134-input.c @@ -963,7 +963,7 @@ static int saa7134_raw_decode_irq(struct saa7134_dev *dev) * to work with other protocols. */ if (!ir->active) { - timeout = jiffies + jiffies_to_msecs(15); + timeout = jiffies + msecs_to_jiffies(15); mod_timer(&ir->timer, timeout); ir->active = true; } diff --git a/drivers/media/video/tuner-core.c b/drivers/media/video/tuner-core.c index 9363ed9..a03945a 100644 --- a/drivers/media/video/tuner-core.c +++ b/drivers/media/video/tuner-core.c @@ -714,29 +714,34 @@ static int tuner_remove(struct i2c_client *client) * returns 0. * This function is needed for boards that have a separate tuner for * radio (like devices with tea5767). + * NOTE: mt20xx uses V4L2_TUNER_DIGITAL_TV and calls set_tv_freq to + * select a TV frequency. So, t_mode = T_ANALOG_TV could actually + * be used to represent a Digital TV too. */ static inline int check_mode(struct tuner *t, enum v4l2_tuner_type mode) { - if ((1 << mode & t->mode_mask) == 0) + int t_mode; + if (mode == V4L2_TUNER_RADIO) + t_mode = T_RADIO; + else + t_mode = T_ANALOG_TV; + + if ((t_mode & t->mode_mask) == 0) return -EINVAL; return 0; } /** - * set_mode_freq - Switch tuner to other mode. - * @client: struct i2c_client pointer + * set_mode - Switch tuner to other mode. * @t: a pointer to the module's internal struct_tuner * @mode: enum v4l2_type (radio or TV) - * @freq: frequency to set (0 means to use the previous one) * * If tuner doesn't support the needed mode (radio or TV), prints a * debug message and returns -EINVAL, changing its state to standby. - * Otherwise, changes the state and sets frequency to the last value, if - * the tuner can sleep or if it supports both Radio and TV. + * Otherwise, changes the mode and returns 0. */ -static int set_mode_freq(struct i2c_client *client, struct tuner *t, - enum v4l2_tuner_type mode, unsigned int freq) +static int set_mode(struct tuner *t, enum v4l2_tuner_type mode) { struct analog_demod_ops *analog_ops = &t->fe.ops.analog_ops; @@ -752,17 +757,27 @@ static int set_mode_freq(struct i2c_client *client, struct tuner *t, t->mode = mode; tuner_dbg("Changing to mode %d\n", mode); } + return 0; +} + +/** + * set_freq - Set the tuner to the desired frequency. + * @t: a pointer to the module's internal struct_tuner + * @freq: frequency to set (0 means to use the current frequency) + */ +static void set_freq(struct tuner *t, unsigned int freq) +{ + struct i2c_client *client = v4l2_get_subdevdata(&t->sd); + if (t->mode == V4L2_TUNER_RADIO) { - if (freq) - t->radio_freq = freq; - set_radio_freq(client, t->radio_freq); + if (!freq) + freq = t->radio_freq; + set_radio_freq(client, freq); } else { - if (freq) - t->tv_freq = freq; - set_tv_freq(client, t->tv_freq); + if (!freq) + freq = t->tv_freq; + set_tv_freq(client, freq); } - - return 0; } /* @@ -817,7 +832,8 @@ static void set_tv_freq(struct i2c_client *c, unsigned int freq) /** * tuner_fixup_std - force a given video standard variant * - * @t: tuner internal struct + * @t: tuner internal struct + * @std: TV standard * * A few devices or drivers have problem to detect some standard variations. * On other operational systems, the drivers generally have a per-country @@ -827,57 +843,39 @@ static void set_tv_freq(struct i2c_client *c, unsigned int freq) * to distinguish all video standard variations, a modprobe parameter can * be used to force a video standard match. */ -static int tuner_fixup_std(struct tuner *t) +static v4l2_std_id tuner_fixup_std(struct tuner *t, v4l2_std_id std) { - if ((t->std & V4L2_STD_PAL) == V4L2_STD_PAL) { + if (pal[0] != '-' && (std & V4L2_STD_PAL) == V4L2_STD_PAL) { switch (pal[0]) { case '6': - tuner_dbg("insmod fixup: PAL => PAL-60\n"); - t->std = V4L2_STD_PAL_60; - break; + return V4L2_STD_PAL_60; case 'b': case 'B': case 'g': case 'G': - tuner_dbg("insmod fixup: PAL => PAL-BG\n"); - t->std = V4L2_STD_PAL_BG; - break; + return V4L2_STD_PAL_BG; case 'i': case 'I': - tuner_dbg("insmod fixup: PAL => PAL-I\n"); - t->std = V4L2_STD_PAL_I; - break; + return V4L2_STD_PAL_I; case 'd': case 'D': case 'k': case 'K': - tuner_dbg("insmod fixup: PAL => PAL-DK\n"); - t->std = V4L2_STD_PAL_DK; - break; + return V4L2_STD_PAL_DK; case 'M': case 'm': - tuner_dbg("insmod fixup: PAL => PAL-M\n"); - t->std = V4L2_STD_PAL_M; - break; + return V4L2_STD_PAL_M; case 'N': case 'n': - if (pal[1] == 'c' || pal[1] == 'C') { - tuner_dbg("insmod fixup: PAL => PAL-Nc\n"); - t->std = V4L2_STD_PAL_Nc; - } else { - tuner_dbg("insmod fixup: PAL => PAL-N\n"); - t->std = V4L2_STD_PAL_N; - } - break; - case '-': - /* default parameter, do nothing */ - break; + if (pal[1] == 'c' || pal[1] == 'C') + return V4L2_STD_PAL_Nc; + return V4L2_STD_PAL_N; default: tuner_warn("pal= argument not recognised\n"); break; } } - if ((t->std & V4L2_STD_SECAM) == V4L2_STD_SECAM) { + if (secam[0] != '-' && (std & V4L2_STD_SECAM) == V4L2_STD_SECAM) { switch (secam[0]) { case 'b': case 'B': @@ -885,63 +883,42 @@ static int tuner_fixup_std(struct tuner *t) case 'G': case 'h': case 'H': - tuner_dbg("insmod fixup: SECAM => SECAM-BGH\n"); - t->std = V4L2_STD_SECAM_B | - V4L2_STD_SECAM_G | - V4L2_STD_SECAM_H; - break; + return V4L2_STD_SECAM_B | + V4L2_STD_SECAM_G | + V4L2_STD_SECAM_H; case 'd': case 'D': case 'k': case 'K': - tuner_dbg("insmod fixup: SECAM => SECAM-DK\n"); - t->std = V4L2_STD_SECAM_DK; - break; + return V4L2_STD_SECAM_DK; case 'l': case 'L': - if ((secam[1] == 'C') || (secam[1] == 'c')) { - tuner_dbg("insmod fixup: SECAM => SECAM-L'\n"); - t->std = V4L2_STD_SECAM_LC; - } else { - tuner_dbg("insmod fixup: SECAM => SECAM-L\n"); - t->std = V4L2_STD_SECAM_L; - } - break; - case '-': - /* default parameter, do nothing */ - break; + if ((secam[1] == 'C') || (secam[1] == 'c')) + return V4L2_STD_SECAM_LC; + return V4L2_STD_SECAM_L; default: tuner_warn("secam= argument not recognised\n"); break; } } - if ((t->std & V4L2_STD_NTSC) == V4L2_STD_NTSC) { + if (ntsc[0] != '-' && (std & V4L2_STD_NTSC) == V4L2_STD_NTSC) { switch (ntsc[0]) { case 'm': case 'M': - tuner_dbg("insmod fixup: NTSC => NTSC-M\n"); - t->std = V4L2_STD_NTSC_M; - break; + return V4L2_STD_NTSC_M; case 'j': case 'J': - tuner_dbg("insmod fixup: NTSC => NTSC_M_JP\n"); - t->std = V4L2_STD_NTSC_M_JP; - break; + return V4L2_STD_NTSC_M_JP; case 'k': case 'K': - tuner_dbg("insmod fixup: NTSC => NTSC_M_KR\n"); - t->std = V4L2_STD_NTSC_M_KR; - break; - case '-': - /* default parameter, do nothing */ - break; + return V4L2_STD_NTSC_M_KR; default: tuner_info("ntsc= argument not recognised\n"); break; } } - return 0; + return std; } /* @@ -1016,7 +993,7 @@ static void tuner_status(struct dvb_frontend *fe) case V4L2_TUNER_RADIO: p = "radio"; break; - case V4L2_TUNER_DIGITAL_TV: + case V4L2_TUNER_DIGITAL_TV: /* Used by mt20xx */ p = "digital TV"; break; case V4L2_TUNER_ANALOG_TV: @@ -1058,10 +1035,9 @@ static void tuner_status(struct dvb_frontend *fe) static int tuner_s_radio(struct v4l2_subdev *sd) { struct tuner *t = to_tuner(sd); - struct i2c_client *client = v4l2_get_subdevdata(sd); - if (set_mode_freq(client, t, V4L2_TUNER_RADIO, 0) == -EINVAL) - return 0; + if (set_mode(t, V4L2_TUNER_RADIO) == 0) + set_freq(t, 0); return 0; } @@ -1072,16 +1048,20 @@ static int tuner_s_radio(struct v4l2_subdev *sd) /** * tuner_s_power - controls the power state of the tuner * @sd: pointer to struct v4l2_subdev - * @on: a zero value puts the tuner to sleep + * @on: a zero value puts the tuner to sleep, non-zero wakes it up */ static int tuner_s_power(struct v4l2_subdev *sd, int on) { struct tuner *t = to_tuner(sd); struct analog_demod_ops *analog_ops = &t->fe.ops.analog_ops; - /* FIXME: Why this function don't wake the tuner if on != 0 ? */ - if (on) + if (on) { + if (t->standby && set_mode(t, t->mode) == 0) { + tuner_dbg("Waking up tuner\n"); + set_freq(t, 0); + } return 0; + } tuner_dbg("Putting tuner to sleep\n"); t->standby = true; @@ -1093,28 +1073,36 @@ static int tuner_s_power(struct v4l2_subdev *sd, int on) static int tuner_s_std(struct v4l2_subdev *sd, v4l2_std_id std) { struct tuner *t = to_tuner(sd); - struct i2c_client *client = v4l2_get_subdevdata(sd); - if (set_mode_freq(client, t, V4L2_TUNER_ANALOG_TV, 0) == -EINVAL) + if (set_mode(t, V4L2_TUNER_ANALOG_TV)) return 0; - t->std = std; - tuner_fixup_std(t); - + t->std = tuner_fixup_std(t, std); + if (t->std != std) + tuner_dbg("Fixup standard %llx to %llx\n", std, t->std); + set_freq(t, 0); return 0; } static int tuner_s_frequency(struct v4l2_subdev *sd, struct v4l2_frequency *f) { struct tuner *t = to_tuner(sd); - struct i2c_client *client = v4l2_get_subdevdata(sd); - - if (set_mode_freq(client, t, f->type, f->frequency) == -EINVAL) - return 0; + if (set_mode(t, f->type) == 0) + set_freq(t, f->frequency); return 0; } +/** + * tuner_g_frequency - Get the tuned frequency for the tuner + * @sd: pointer to struct v4l2_subdev + * @f: pointer to struct v4l2_frequency + * + * At return, the structure f will be filled with tuner frequency + * if the tuner matches the f->type. + * Note: f->type should be initialized before calling it. + * This is done by either video_ioctl2 or by the bridge driver. + */ static int tuner_g_frequency(struct v4l2_subdev *sd, struct v4l2_frequency *f) { struct tuner *t = to_tuner(sd); @@ -1122,8 +1110,7 @@ static int tuner_g_frequency(struct v4l2_subdev *sd, struct v4l2_frequency *f) if (check_mode(t, f->type) == -EINVAL) return 0; - f->type = t->mode; - if (fe_tuner_ops->get_frequency && !t->standby) { + if (f->type == t->mode && fe_tuner_ops->get_frequency && !t->standby) { u32 abs_freq; fe_tuner_ops->get_frequency(&t->fe, &abs_freq); @@ -1131,12 +1118,22 @@ static int tuner_g_frequency(struct v4l2_subdev *sd, struct v4l2_frequency *f) DIV_ROUND_CLOSEST(abs_freq * 2, 125) : DIV_ROUND_CLOSEST(abs_freq, 62500); } else { - f->frequency = (V4L2_TUNER_RADIO == t->mode) ? + f->frequency = (V4L2_TUNER_RADIO == f->type) ? t->radio_freq : t->tv_freq; } return 0; } +/** + * tuner_g_tuner - Fill in tuner information + * @sd: pointer to struct v4l2_subdev + * @vt: pointer to struct v4l2_tuner + * + * At return, the structure vt will be filled with tuner information + * if the tuner matches vt->type. + * Note: vt->type should be initialized before calling it. + * This is done by either video_ioctl2 or by the bridge driver. + */ static int tuner_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *vt) { struct tuner *t = to_tuner(sd); @@ -1145,48 +1142,57 @@ static int tuner_g_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *vt) if (check_mode(t, vt->type) == -EINVAL) return 0; - vt->type = t->mode; - if (analog_ops->get_afc) + if (vt->type == t->mode && analog_ops->get_afc) vt->afc = analog_ops->get_afc(&t->fe); - if (t->mode == V4L2_TUNER_ANALOG_TV) - vt->capability |= V4L2_TUNER_CAP_NORM; if (t->mode != V4L2_TUNER_RADIO) { + vt->capability |= V4L2_TUNER_CAP_NORM; vt->rangelow = tv_range[0] * 16; vt->rangehigh = tv_range[1] * 16; return 0; } /* radio mode */ - vt->rxsubchans = V4L2_TUNER_SUB_MONO | V4L2_TUNER_SUB_STEREO; - if (fe_tuner_ops->get_status) { - u32 tuner_status; - - fe_tuner_ops->get_status(&t->fe, &tuner_status); - vt->rxsubchans = - (tuner_status & TUNER_STATUS_STEREO) ? - V4L2_TUNER_SUB_STEREO : - V4L2_TUNER_SUB_MONO; + if (vt->type == t->mode) { + vt->rxsubchans = V4L2_TUNER_SUB_MONO | V4L2_TUNER_SUB_STEREO; + if (fe_tuner_ops->get_status) { + u32 tuner_status; + + fe_tuner_ops->get_status(&t->fe, &tuner_status); + vt->rxsubchans = + (tuner_status & TUNER_STATUS_STEREO) ? + V4L2_TUNER_SUB_STEREO : + V4L2_TUNER_SUB_MONO; + } + if (analog_ops->has_signal) + vt->signal = analog_ops->has_signal(&t->fe); + vt->audmode = t->audmode; } - if (analog_ops->has_signal) - vt->signal = analog_ops->has_signal(&t->fe); vt->capability |= V4L2_TUNER_CAP_LOW | V4L2_TUNER_CAP_STEREO; - vt->audmode = t->audmode; vt->rangelow = radio_range[0] * 16000; vt->rangehigh = radio_range[1] * 16000; return 0; } +/** + * tuner_s_tuner - Set the tuner's audio mode + * @sd: pointer to struct v4l2_subdev + * @vt: pointer to struct v4l2_tuner + * + * Sets the audio mode if the tuner matches vt->type. + * Note: vt->type should be initialized before calling it. + * This is done by either video_ioctl2 or by the bridge driver. + */ static int tuner_s_tuner(struct v4l2_subdev *sd, struct v4l2_tuner *vt) { struct tuner *t = to_tuner(sd); - struct i2c_client *client = v4l2_get_subdevdata(sd); - if (set_mode_freq(client, t, vt->type, 0) == -EINVAL) + if (set_mode(t, vt->type)) return 0; if (t->mode == V4L2_TUNER_RADIO) t->audmode = vt->audmode; + set_freq(t, 0); return 0; } @@ -1221,7 +1227,8 @@ static int tuner_resume(struct i2c_client *c) tuner_dbg("resume\n"); if (!t->standby) - set_mode_freq(c, t, t->type, 0); + if (set_mode(t, t->mode) == 0) + set_freq(t, 0); return 0; } diff --git a/drivers/media/video/uvc/uvc_entity.c b/drivers/media/video/uvc/uvc_entity.c index c3ab0c8..48fea37 100644 --- a/drivers/media/video/uvc/uvc_entity.c +++ b/drivers/media/video/uvc/uvc_entity.c @@ -27,14 +27,20 @@ static int uvc_mc_register_entity(struct uvc_video_chain *chain, struct uvc_entity *entity) { const u32 flags = MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE; - struct uvc_entity *remote; + struct media_entity *sink; unsigned int i; - u8 remote_pad; - int ret = 0; + int ret; + + sink = (UVC_ENTITY_TYPE(entity) == UVC_TT_STREAMING) + ? (entity->vdev ? &entity->vdev->entity : NULL) + : &entity->subdev.entity; + if (sink == NULL) + return 0; for (i = 0; i < entity->num_pads; ++i) { struct media_entity *source; - struct media_entity *sink; + struct uvc_entity *remote; + u8 remote_pad; if (!(entity->pads[i].flags & MEDIA_PAD_FL_SINK)) continue; @@ -43,10 +49,11 @@ static int uvc_mc_register_entity(struct uvc_video_chain *chain, if (remote == NULL) return -EINVAL; - source = (UVC_ENTITY_TYPE(remote) == UVC_TT_STREAMING) - ? &remote->vdev->entity : &remote->subdev.entity; - sink = (UVC_ENTITY_TYPE(entity) == UVC_TT_STREAMING) - ? &entity->vdev->entity : &entity->subdev.entity; + source = (UVC_ENTITY_TYPE(remote) != UVC_TT_STREAMING) + ? (remote->vdev ? &remote->vdev->entity : NULL) + : &remote->subdev.entity; + if (source == NULL) + continue; remote_pad = remote->num_pads - 1; ret = media_entity_create_link(source, remote_pad, @@ -55,11 +62,10 @@ static int uvc_mc_register_entity(struct uvc_video_chain *chain, return ret; } - if (UVC_ENTITY_TYPE(entity) != UVC_TT_STREAMING) - ret = v4l2_device_register_subdev(&chain->dev->vdev, - &entity->subdev); + if (UVC_ENTITY_TYPE(entity) == UVC_TT_STREAMING) + return 0; - return ret; + return v4l2_device_register_subdev(&chain->dev->vdev, &entity->subdev); } static struct v4l2_subdev_ops uvc_subdev_ops = { @@ -84,9 +90,11 @@ static int uvc_mc_init_entity(struct uvc_entity *entity) ret = media_entity_init(&entity->subdev.entity, entity->num_pads, entity->pads, 0); - } else + } else if (entity->vdev != NULL) { ret = media_entity_init(&entity->vdev->entity, entity->num_pads, entity->pads, 0); + } else + ret = 0; return ret; } diff --git a/drivers/media/video/uvc/uvc_queue.c b/drivers/media/video/uvc/uvc_queue.c index 109a063..f90ce9f 100644 --- a/drivers/media/video/uvc/uvc_queue.c +++ b/drivers/media/video/uvc/uvc_queue.c @@ -104,6 +104,8 @@ static int __uvc_free_buffers(struct uvc_video_queue *queue) } if (queue->count) { + uvc_queue_cancel(queue, 0); + INIT_LIST_HEAD(&queue->mainqueue); vfree(queue->mem); queue->count = 0; } diff --git a/drivers/media/video/uvc/uvc_video.c b/drivers/media/video/uvc/uvc_video.c index fc766b9..4999479 100644 --- a/drivers/media/video/uvc/uvc_video.c +++ b/drivers/media/video/uvc/uvc_video.c @@ -1255,8 +1255,10 @@ int uvc_video_enable(struct uvc_streaming *stream, int enable) /* Commit the streaming parameters. */ ret = uvc_commit_video(stream, &stream->ctrl); - if (ret < 0) + if (ret < 0) { + uvc_queue_enable(&stream->queue, 0); return ret; + } return uvc_init_video(stream, GFP_KERNEL); } diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c index 19d5ae2..06f1400 100644 --- a/drivers/media/video/v4l2-dev.c +++ b/drivers/media/video/v4l2-dev.c @@ -167,6 +167,12 @@ static void v4l2_device_release(struct device *cd) mutex_unlock(&videodev_lock); +#if defined(CONFIG_MEDIA_CONTROLLER) + if (vdev->v4l2_dev && vdev->v4l2_dev->mdev && + vdev->vfl_type != VFL_TYPE_SUBDEV) + media_device_unregister_entity(&vdev->entity); +#endif + /* Release video_device and perform other cleanups as needed. */ vdev->release(vdev); @@ -389,9 +395,6 @@ static int v4l2_mmap(struct file *filp, struct vm_area_struct *vm) static int v4l2_open(struct inode *inode, struct file *filp) { struct video_device *vdev; -#if defined(CONFIG_MEDIA_CONTROLLER) - struct media_entity *entity = NULL; -#endif int ret = 0; /* Check if the video device is available */ @@ -405,17 +408,6 @@ static int v4l2_open(struct inode *inode, struct file *filp) /* and increase the device refcount */ video_get(vdev); mutex_unlock(&videodev_lock); -#if defined(CONFIG_MEDIA_CONTROLLER) - if (vdev->v4l2_dev && vdev->v4l2_dev->mdev && - vdev->vfl_type != VFL_TYPE_SUBDEV) { - entity = media_entity_get(&vdev->entity); - if (!entity) { - ret = -EBUSY; - video_put(vdev); - return ret; - } - } -#endif if (vdev->fops->open) { if (vdev->lock && mutex_lock_interruptible(vdev->lock)) { ret = -ERESTARTSYS; @@ -431,14 +423,8 @@ static int v4l2_open(struct inode *inode, struct file *filp) err: /* decrease the refcount in case of an error */ - if (ret) { -#if defined(CONFIG_MEDIA_CONTROLLER) - if (vdev->v4l2_dev && vdev->v4l2_dev->mdev && - vdev->vfl_type != VFL_TYPE_SUBDEV) - media_entity_put(entity); -#endif + if (ret) video_put(vdev); - } return ret; } @@ -455,11 +441,6 @@ static int v4l2_release(struct inode *inode, struct file *filp) if (vdev->lock) mutex_unlock(vdev->lock); } -#if defined(CONFIG_MEDIA_CONTROLLER) - if (vdev->v4l2_dev && vdev->v4l2_dev->mdev && - vdev->vfl_type != VFL_TYPE_SUBDEV) - media_entity_put(&vdev->entity); -#endif /* decrease the refcount unconditionally since the release() return value is ignored. */ video_put(vdev); @@ -754,12 +735,6 @@ void video_unregister_device(struct video_device *vdev) if (!vdev || !video_is_registered(vdev)) return; -#if defined(CONFIG_MEDIA_CONTROLLER) - if (vdev->v4l2_dev && vdev->v4l2_dev->mdev && - vdev->vfl_type != VFL_TYPE_SUBDEV) - media_device_unregister_entity(&vdev->entity); -#endif - mutex_lock(&videodev_lock); /* This must be in a critical section to prevent a race with v4l2_open. * Once this bit has been cleared video_get may never be called again. diff --git a/drivers/media/video/v4l2-ioctl.c b/drivers/media/video/v4l2-ioctl.c index 506edcc..69e8c6f 100644 --- a/drivers/media/video/v4l2-ioctl.c +++ b/drivers/media/video/v4l2-ioctl.c @@ -1822,6 +1822,8 @@ static long __video_do_ioctl(struct file *file, if (!ops->vidioc_g_tuner) break; + p->type = (vfd->vfl_type == VFL_TYPE_RADIO) ? + V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; ret = ops->vidioc_g_tuner(file, fh, p); if (!ret) dbgarg(cmd, "index=%d, name=%s, type=%d, " @@ -1840,6 +1842,8 @@ static long __video_do_ioctl(struct file *file, if (!ops->vidioc_s_tuner) break; + p->type = (vfd->vfl_type == VFL_TYPE_RADIO) ? + V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; dbgarg(cmd, "index=%d, name=%s, type=%d, " "capability=0x%x, rangelow=%d, " "rangehigh=%d, signal=%d, afc=%d, " @@ -1858,6 +1862,8 @@ static long __video_do_ioctl(struct file *file, if (!ops->vidioc_g_frequency) break; + p->type = (vfd->vfl_type == VFL_TYPE_RADIO) ? + V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; ret = ops->vidioc_g_frequency(file, fh, p); if (!ret) dbgarg(cmd, "tuner=%d, type=%d, frequency=%d\n", @@ -1940,13 +1946,19 @@ static long __video_do_ioctl(struct file *file, case VIDIOC_S_HW_FREQ_SEEK: { struct v4l2_hw_freq_seek *p = arg; + enum v4l2_tuner_type type; if (!ops->vidioc_s_hw_freq_seek) break; + type = (vfd->vfl_type == VFL_TYPE_RADIO) ? + V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; dbgarg(cmd, - "tuner=%d, type=%d, seek_upward=%d, wrap_around=%d\n", - p->tuner, p->type, p->seek_upward, p->wrap_around); - ret = ops->vidioc_s_hw_freq_seek(file, fh, p); + "tuner=%u, type=%u, seek_upward=%u, wrap_around=%u, spacing=%u\n", + p->tuner, p->type, p->seek_upward, p->wrap_around, p->spacing); + if (p->type != type) + ret = -EINVAL; + else + ret = ops->vidioc_s_hw_freq_seek(file, fh, p); break; } case VIDIOC_ENUM_FRAMESIZES: diff --git a/drivers/media/video/videobuf2-core.c b/drivers/media/video/videobuf2-core.c index 6ba1461..3015e60 100644 --- a/drivers/media/video/videobuf2-core.c +++ b/drivers/media/video/videobuf2-core.c @@ -492,13 +492,6 @@ int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) return -EINVAL; } - /* - * If the same number of buffers and memory access method is requested - * then return immediately. - */ - if (q->memory == req->memory && req->count == q->num_buffers) - return 0; - if (req->count == 0 || q->num_buffers != 0 || q->memory != req->memory) { /* * We already have buffers allocated, so first check if they @@ -539,9 +532,9 @@ int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) /* Finally, allocate buffers and video memory */ ret = __vb2_queue_alloc(q, req->memory, num_buffers, num_planes, plane_sizes); - if (ret < 0) { - dprintk(1, "Memory allocation failed with error: %d\n", ret); - return ret; + if (ret == 0) { + dprintk(1, "Memory allocation failed\n"); + return -ENOMEM; } /* @@ -1196,6 +1189,7 @@ static void __vb2_queue_cancel(struct vb2_queue *q) * has not already dequeued before initiating cancel. */ INIT_LIST_HEAD(&q->done_list); + atomic_set(&q->queued_count, 0); wake_up_all(&q->done_wq); /* diff --git a/drivers/media/video/videobuf2-dma-sg.c b/drivers/media/video/videobuf2-dma-sg.c index b2d9485..10a20d9 100644 --- a/drivers/media/video/videobuf2-dma-sg.c +++ b/drivers/media/video/videobuf2-dma-sg.c @@ -62,7 +62,7 @@ static void *vb2_dma_sg_alloc(void *alloc_ctx, unsigned long size) goto fail_pages_array_alloc; for (i = 0; i < buf->sg_desc.num_pages; ++i) { - buf->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); + buf->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN); if (NULL == buf->pages[i]) goto fail_pages_alloc; sg_set_page(&buf->sg_desc.sglist[i], diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 0f09c05..6ca938a 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -728,6 +728,9 @@ config MFD_TPS65910 if you say yes here you get support for the TPS65910 series of Power Management chips. +config TPS65911_COMPARATOR + tristate + endif # MFD_SUPPORT menu "Multimedia Capabilities Port drivers" diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index efe3cc3..d7d47d2 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -94,3 +94,4 @@ obj-$(CONFIG_MFD_OMAP_USB_HOST) += omap-usb-host.o obj-$(CONFIG_MFD_PM8921_CORE) += pm8921-core.o obj-$(CONFIG_MFD_PM8XXX_IRQ) += pm8xxx-irq.o obj-$(CONFIG_MFD_TPS65910) += tps65910.o tps65910-irq.o +obj-$(CONFIG_TPS65911_COMPARATOR) += tps65911-comparator.o diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c index c27fd1f..c71ae09 100644 --- a/drivers/mfd/asic3.c +++ b/drivers/mfd/asic3.c @@ -619,6 +619,7 @@ static void asic3_clk_disable(struct asic3 *asic, struct asic3_clk *clk) /* MFD cells (SPI, PWM, LED, DS1WM, MMC) */ static struct ds1wm_driver_data ds1wm_pdata = { .active_high = 1, + .reset_recover_delay = 1, }; static struct resource ds1wm_resources[] = { diff --git a/drivers/mfd/htc-pasic3.c b/drivers/mfd/htc-pasic3.c index 2808bd1..04c7093 100644 --- a/drivers/mfd/htc-pasic3.c +++ b/drivers/mfd/htc-pasic3.c @@ -99,6 +99,7 @@ static int ds1wm_disable(struct platform_device *pdev) static struct ds1wm_driver_data ds1wm_pdata = { .active_high = 0, + .reset_recover_delay = 1, }; static struct resource ds1wm_resources[] __initdata = { diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index 8552195..1717144 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -26,7 +26,6 @@ #include <linux/spinlock.h> #include <linux/gpio.h> #include <plat/usb.h> -#include <linux/pm_runtime.h> #define USBHS_DRIVER_NAME "usbhs-omap" #define OMAP_EHCI_DEVICE "ehci-omap" @@ -147,6 +146,9 @@ struct usbhs_hcd_omap { + struct clk *usbhost_ick; + struct clk *usbhost_hs_fck; + struct clk *usbhost_fs_fck; struct clk *xclk60mhsp1_ck; struct clk *xclk60mhsp2_ck; struct clk *utmi_p1_fck; @@ -156,6 +158,8 @@ struct usbhs_hcd_omap { struct clk *usbhost_p2_fck; struct clk *usbtll_p2_fck; struct clk *init_60m_fclk; + struct clk *usbtll_fck; + struct clk *usbtll_ick; void __iomem *uhh_base; void __iomem *tll_base; @@ -349,13 +353,46 @@ static int __devinit usbhs_omap_probe(struct platform_device *pdev) omap->platdata.ehci_data = pdata->ehci_data; omap->platdata.ohci_data = pdata->ohci_data; - pm_runtime_enable(&pdev->dev); + omap->usbhost_ick = clk_get(dev, "usbhost_ick"); + if (IS_ERR(omap->usbhost_ick)) { + ret = PTR_ERR(omap->usbhost_ick); + dev_err(dev, "usbhost_ick failed error:%d\n", ret); + goto err_end; + } + + omap->usbhost_hs_fck = clk_get(dev, "hs_fck"); + if (IS_ERR(omap->usbhost_hs_fck)) { + ret = PTR_ERR(omap->usbhost_hs_fck); + dev_err(dev, "usbhost_hs_fck failed error:%d\n", ret); + goto err_usbhost_ick; + } + + omap->usbhost_fs_fck = clk_get(dev, "fs_fck"); + if (IS_ERR(omap->usbhost_fs_fck)) { + ret = PTR_ERR(omap->usbhost_fs_fck); + dev_err(dev, "usbhost_fs_fck failed error:%d\n", ret); + goto err_usbhost_hs_fck; + } + + omap->usbtll_fck = clk_get(dev, "usbtll_fck"); + if (IS_ERR(omap->usbtll_fck)) { + ret = PTR_ERR(omap->usbtll_fck); + dev_err(dev, "usbtll_fck failed error:%d\n", ret); + goto err_usbhost_fs_fck; + } + + omap->usbtll_ick = clk_get(dev, "usbtll_ick"); + if (IS_ERR(omap->usbtll_ick)) { + ret = PTR_ERR(omap->usbtll_ick); + dev_err(dev, "usbtll_ick failed error:%d\n", ret); + goto err_usbtll_fck; + } omap->utmi_p1_fck = clk_get(dev, "utmi_p1_gfclk"); if (IS_ERR(omap->utmi_p1_fck)) { ret = PTR_ERR(omap->utmi_p1_fck); dev_err(dev, "utmi_p1_gfclk failed error:%d\n", ret); - goto err_end; + goto err_usbtll_ick; } omap->xclk60mhsp1_ck = clk_get(dev, "xclk60mhsp1_ck"); @@ -485,8 +522,22 @@ err_xclk60mhsp1_ck: err_utmi_p1_fck: clk_put(omap->utmi_p1_fck); +err_usbtll_ick: + clk_put(omap->usbtll_ick); + +err_usbtll_fck: + clk_put(omap->usbtll_fck); + +err_usbhost_fs_fck: + clk_put(omap->usbhost_fs_fck); + +err_usbhost_hs_fck: + clk_put(omap->usbhost_hs_fck); + +err_usbhost_ick: + clk_put(omap->usbhost_ick); + err_end: - pm_runtime_disable(&pdev->dev); kfree(omap); end_probe: @@ -520,7 +571,11 @@ static int __devexit usbhs_omap_remove(struct platform_device *pdev) clk_put(omap->utmi_p2_fck); clk_put(omap->xclk60mhsp1_ck); clk_put(omap->utmi_p1_fck); - pm_runtime_disable(&pdev->dev); + clk_put(omap->usbtll_ick); + clk_put(omap->usbtll_fck); + clk_put(omap->usbhost_fs_fck); + clk_put(omap->usbhost_hs_fck); + clk_put(omap->usbhost_ick); kfree(omap); return 0; @@ -640,6 +695,7 @@ static int usbhs_enable(struct device *dev) struct usbhs_omap_platform_data *pdata = &omap->platdata; unsigned long flags = 0; int ret = 0; + unsigned long timeout; unsigned reg; dev_dbg(dev, "starting TI HSUSB Controller\n"); @@ -652,7 +708,11 @@ static int usbhs_enable(struct device *dev) if (omap->count > 0) goto end_count; - pm_runtime_get_sync(dev); + clk_enable(omap->usbhost_ick); + clk_enable(omap->usbhost_hs_fck); + clk_enable(omap->usbhost_fs_fck); + clk_enable(omap->usbtll_fck); + clk_enable(omap->usbtll_ick); if (pdata->ehci_data->phy_reset) { if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[0])) { @@ -676,6 +736,50 @@ static int usbhs_enable(struct device *dev) omap->usbhs_rev = usbhs_read(omap->uhh_base, OMAP_UHH_REVISION); dev_dbg(dev, "OMAP UHH_REVISION 0x%x\n", omap->usbhs_rev); + /* perform TLL soft reset, and wait until reset is complete */ + usbhs_write(omap->tll_base, OMAP_USBTLL_SYSCONFIG, + OMAP_USBTLL_SYSCONFIG_SOFTRESET); + + /* Wait for TLL reset to complete */ + timeout = jiffies + msecs_to_jiffies(1000); + while (!(usbhs_read(omap->tll_base, OMAP_USBTLL_SYSSTATUS) + & OMAP_USBTLL_SYSSTATUS_RESETDONE)) { + cpu_relax(); + + if (time_after(jiffies, timeout)) { + dev_dbg(dev, "operation timed out\n"); + ret = -EINVAL; + goto err_tll; + } + } + + dev_dbg(dev, "TLL RESET DONE\n"); + + /* (1<<3) = no idle mode only for initial debugging */ + usbhs_write(omap->tll_base, OMAP_USBTLL_SYSCONFIG, + OMAP_USBTLL_SYSCONFIG_ENAWAKEUP | + OMAP_USBTLL_SYSCONFIG_SIDLEMODE | + OMAP_USBTLL_SYSCONFIG_AUTOIDLE); + + /* Put UHH in NoIdle/NoStandby mode */ + reg = usbhs_read(omap->uhh_base, OMAP_UHH_SYSCONFIG); + if (is_omap_usbhs_rev1(omap)) { + reg |= (OMAP_UHH_SYSCONFIG_ENAWAKEUP + | OMAP_UHH_SYSCONFIG_SIDLEMODE + | OMAP_UHH_SYSCONFIG_CACTIVITY + | OMAP_UHH_SYSCONFIG_MIDLEMODE); + reg &= ~OMAP_UHH_SYSCONFIG_AUTOIDLE; + + + } else if (is_omap_usbhs_rev2(omap)) { + reg &= ~OMAP4_UHH_SYSCONFIG_IDLEMODE_CLEAR; + reg |= OMAP4_UHH_SYSCONFIG_NOIDLE; + reg &= ~OMAP4_UHH_SYSCONFIG_STDBYMODE_CLEAR; + reg |= OMAP4_UHH_SYSCONFIG_NOSTDBY; + } + + usbhs_write(omap->uhh_base, OMAP_UHH_SYSCONFIG, reg); + reg = usbhs_read(omap->uhh_base, OMAP_UHH_HOSTCONFIG); /* setup ULPI bypass and burst configurations */ reg |= (OMAP_UHH_HOSTCONFIG_INCR4_BURST_EN @@ -815,8 +919,6 @@ end_count: return 0; err_tll: - pm_runtime_put_sync(dev); - spin_unlock_irqrestore(&omap->lock, flags); if (pdata->ehci_data->phy_reset) { if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[0])) gpio_free(pdata->ehci_data->reset_gpio_port[0]); @@ -824,6 +926,13 @@ err_tll: if (gpio_is_valid(pdata->ehci_data->reset_gpio_port[1])) gpio_free(pdata->ehci_data->reset_gpio_port[1]); } + + clk_disable(omap->usbtll_ick); + clk_disable(omap->usbtll_fck); + clk_disable(omap->usbhost_fs_fck); + clk_disable(omap->usbhost_hs_fck); + clk_disable(omap->usbhost_ick); + spin_unlock_irqrestore(&omap->lock, flags); return ret; } @@ -896,7 +1005,11 @@ static void usbhs_disable(struct device *dev) clk_disable(omap->utmi_p1_fck); } - pm_runtime_put_sync(dev); + clk_disable(omap->usbtll_ick); + clk_disable(omap->usbtll_fck); + clk_disable(omap->usbhost_fs_fck); + clk_disable(omap->usbhost_hs_fck); + clk_disable(omap->usbhost_ick); /* The gpio_free migh sleep; so unlock the spinlock */ spin_unlock_irqrestore(&omap->lock, flags); diff --git a/drivers/mfd/tps65911-comparator.c b/drivers/mfd/tps65911-comparator.c index 3d2dc56..283ac67 100644 --- a/drivers/mfd/tps65911-comparator.c +++ b/drivers/mfd/tps65911-comparator.c @@ -125,7 +125,7 @@ static DEVICE_ATTR(comp2_threshold, S_IRUGO, comp_threshold_show, NULL); static __devinit int tps65911_comparator_probe(struct platform_device *pdev) { struct tps65910 *tps65910 = dev_get_drvdata(pdev->dev.parent); - struct tps65910_platform_data *pdata = dev_get_platdata(tps65910->dev); + struct tps65910_board *pdata = dev_get_platdata(tps65910->dev); int ret; ret = comp_threshold_set(tps65910, COMP1, pdata->vmbch_threshold); diff --git a/drivers/misc/cb710/sgbuf2.c b/drivers/misc/cb710/sgbuf2.c index d019746..2a40d0e 100644 --- a/drivers/misc/cb710/sgbuf2.c +++ b/drivers/misc/cb710/sgbuf2.c @@ -47,7 +47,7 @@ static uint32_t sg_dwiter_read_buffer(struct sg_mapping_iter *miter) static inline bool needs_unaligned_copy(const void *ptr) { -#ifdef HAVE_EFFICIENT_UNALIGNED_ACCESS +#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS return false; #else return ((ptr - NULL) & 3) != 0; diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c index 668d41e..df03dd3 100644 --- a/drivers/misc/ioc4.c +++ b/drivers/misc/ioc4.c @@ -270,7 +270,7 @@ ioc4_variant(struct ioc4_driver_data *idd) return IOC4_VARIANT_PCI_RT; } -static void __devinit +static void ioc4_load_modules(struct work_struct *work) { request_module("sgiioc4"); diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c index 81d7fa4..150cd70 100644 --- a/drivers/misc/lkdtm.c +++ b/drivers/misc/lkdtm.c @@ -120,6 +120,7 @@ static int recur_count = REC_NUM_DEFAULT; static enum cname cpoint = CN_INVALID; static enum ctype cptype = CT_NONE; static int count = DEFAULT_COUNT; +static DEFINE_SPINLOCK(count_lock); module_param(recur_count, int, 0644); MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test, "\ @@ -230,11 +231,14 @@ static const char *cp_name_to_str(enum cname name) static int lkdtm_parse_commandline(void) { int i; + unsigned long flags; if (cpoint_count < 1 || recur_count < 1) return -EINVAL; + spin_lock_irqsave(&count_lock, flags); count = cpoint_count; + spin_unlock_irqrestore(&count_lock, flags); /* No special parameters */ if (!cpoint_type && !cpoint_name) @@ -349,6 +353,9 @@ static void lkdtm_do_action(enum ctype which) static void lkdtm_handler(void) { + unsigned long flags; + + spin_lock_irqsave(&count_lock, flags); count--; printk(KERN_INFO "lkdtm: Crash point %s of type %s hit, trigger in %d rounds\n", cp_name_to_str(cpoint), cp_type_to_str(cptype), count); @@ -357,6 +364,7 @@ static void lkdtm_handler(void) lkdtm_do_action(cptype); count = cpoint_count; } + spin_unlock_irqrestore(&count_lock, flags); } static int lkdtm_register_cpoint(enum cname which) diff --git a/drivers/misc/pti.c b/drivers/misc/pti.c index bb6f925..374dfcf 100644 --- a/drivers/misc/pti.c +++ b/drivers/misc/pti.c @@ -317,7 +317,8 @@ EXPORT_SYMBOL_GPL(pti_request_masterchannel); * a master, channel ID address * used to write to PTI HW. * - * @mc: master, channel apeture ID address to be released. + * @mc: master, channel apeture ID address to be released. This + * will de-allocate the structure via kfree(). */ void pti_release_masterchannel(struct pti_masterchannel *mc) { @@ -475,8 +476,10 @@ static int pti_tty_install(struct tty_driver *driver, struct tty_struct *tty) else pti_tty_data->mc = pti_request_masterchannel(2); - if (pti_tty_data->mc == NULL) + if (pti_tty_data->mc == NULL) { + kfree(pti_tty_data); return -ENXIO; + } tty->driver_data = pti_tty_data; } @@ -495,7 +498,7 @@ static void pti_tty_cleanup(struct tty_struct *tty) if (pti_tty_data == NULL) return; pti_release_masterchannel(pti_tty_data->mc); - kfree(tty->driver_data); + kfree(pti_tty_data); tty->driver_data = NULL; } @@ -581,7 +584,7 @@ static int pti_char_open(struct inode *inode, struct file *filp) static int pti_char_release(struct inode *inode, struct file *filp) { pti_release_masterchannel(filp->private_data); - kfree(filp->private_data); + filp->private_data = NULL; return 0; } diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c index f91f82e..54c91ff 100644 --- a/drivers/misc/ti-st/st_core.c +++ b/drivers/misc/ti-st/st_core.c @@ -605,7 +605,7 @@ long st_unregister(struct st_proto_s *proto) pr_debug("%s: %d ", __func__, proto->chnl_id); st_kim_ref(&st_gdata, 0); - if (proto->chnl_id >= ST_MAX_CHANNELS) { + if (!st_gdata || proto->chnl_id >= ST_MAX_CHANNELS) { pr_err(" chnl_id %d not supported", proto->chnl_id); return -EPROTONOSUPPORT; } diff --git a/drivers/misc/ti-st/st_kim.c b/drivers/misc/ti-st/st_kim.c index 5da93ee..38fd2f0 100644 --- a/drivers/misc/ti-st/st_kim.c +++ b/drivers/misc/ti-st/st_kim.c @@ -245,9 +245,9 @@ void skip_change_remote_baud(unsigned char **ptr, long *len) pr_err("invalid action after change remote baud command"); } else { *ptr = *ptr + sizeof(struct bts_action) + - ((struct bts_action *)nxt_action)->size; + ((struct bts_action *)cur_action)->size; *len = *len - (sizeof(struct bts_action) + - ((struct bts_action *)nxt_action)->size); + ((struct bts_action *)cur_action)->size); /* warn user on not commenting these in firmware */ pr_warn("skipping the wait event of change remote baud"); } @@ -604,6 +604,10 @@ void st_kim_ref(struct st_data_s **core_data, int id) struct kim_data_s *kim_gdata; /* get kim_gdata reference from platform device */ pdev = st_get_plat_device(id); + if (!pdev) { + *core_data = NULL; + return; + } kim_gdata = dev_get_drvdata(&pdev->dev); *core_data = kim_gdata->core_data; } diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 71da564..1ff5486 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -106,6 +106,16 @@ struct mmc_blk_data { static DEFINE_MUTEX(open_lock); +enum mmc_blk_status { + MMC_BLK_SUCCESS = 0, + MMC_BLK_PARTIAL, + MMC_BLK_RETRY, + MMC_BLK_RETRY_SINGLE, + MMC_BLK_DATA_ERR, + MMC_BLK_CMD_ERR, + MMC_BLK_ABORT, +}; + module_param(perdev_minors, int, 0444); MODULE_PARM_DESC(perdev_minors, "Minors numbers to allocate per device"); @@ -427,14 +437,6 @@ static const struct block_device_operations mmc_bdops = { #endif }; -struct mmc_blk_request { - struct mmc_request mrq; - struct mmc_command sbc; - struct mmc_command cmd; - struct mmc_command stop; - struct mmc_data data; -}; - static inline int mmc_blk_part_switch(struct mmc_card *card, struct mmc_blk_data *md) { @@ -525,7 +527,20 @@ static u32 mmc_sd_num_wr_blocks(struct mmc_card *card) return result; } -static u32 get_card_status(struct mmc_card *card, struct request *req) +static int send_stop(struct mmc_card *card, u32 *status) +{ + struct mmc_command cmd = {0}; + int err; + + cmd.opcode = MMC_STOP_TRANSMISSION; + cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; + err = mmc_wait_for_cmd(card->host, &cmd, 5); + if (err == 0) + *status = cmd.resp[0]; + return err; +} + +static int get_card_status(struct mmc_card *card, u32 *status, int retries) { struct mmc_command cmd = {0}; int err; @@ -534,11 +549,141 @@ static u32 get_card_status(struct mmc_card *card, struct request *req) if (!mmc_host_is_spi(card->host)) cmd.arg = card->rca << 16; cmd.flags = MMC_RSP_SPI_R2 | MMC_RSP_R1 | MMC_CMD_AC; - err = mmc_wait_for_cmd(card->host, &cmd, 0); + err = mmc_wait_for_cmd(card->host, &cmd, retries); + if (err == 0) + *status = cmd.resp[0]; + return err; +} + +#define ERR_RETRY 2 +#define ERR_ABORT 1 +#define ERR_CONTINUE 0 + +static int mmc_blk_cmd_error(struct request *req, const char *name, int error, + bool status_valid, u32 status) +{ + switch (error) { + case -EILSEQ: + /* response crc error, retry the r/w cmd */ + pr_err("%s: %s sending %s command, card status %#x\n", + req->rq_disk->disk_name, "response CRC error", + name, status); + return ERR_RETRY; + + case -ETIMEDOUT: + pr_err("%s: %s sending %s command, card status %#x\n", + req->rq_disk->disk_name, "timed out", name, status); + + /* If the status cmd initially failed, retry the r/w cmd */ + if (!status_valid) + return ERR_RETRY; + + /* + * If it was a r/w cmd crc error, or illegal command + * (eg, issued in wrong state) then retry - we should + * have corrected the state problem above. + */ + if (status & (R1_COM_CRC_ERROR | R1_ILLEGAL_COMMAND)) + return ERR_RETRY; + + /* Otherwise abort the command */ + return ERR_ABORT; + + default: + /* We don't understand the error code the driver gave us */ + pr_err("%s: unknown error %d sending read/write command, card status %#x\n", + req->rq_disk->disk_name, error, status); + return ERR_ABORT; + } +} + +/* + * Initial r/w and stop cmd error recovery. + * We don't know whether the card received the r/w cmd or not, so try to + * restore things back to a sane state. Essentially, we do this as follows: + * - Obtain card status. If the first attempt to obtain card status fails, + * the status word will reflect the failed status cmd, not the failed + * r/w cmd. If we fail to obtain card status, it suggests we can no + * longer communicate with the card. + * - Check the card state. If the card received the cmd but there was a + * transient problem with the response, it might still be in a data transfer + * mode. Try to send it a stop command. If this fails, we can't recover. + * - If the r/w cmd failed due to a response CRC error, it was probably + * transient, so retry the cmd. + * - If the r/w cmd timed out, but we didn't get the r/w cmd status, retry. + * - If the r/w cmd timed out, and the r/w cmd failed due to CRC error or + * illegal cmd, retry. + * Otherwise we don't understand what happened, so abort. + */ +static int mmc_blk_cmd_recovery(struct mmc_card *card, struct request *req, + struct mmc_blk_request *brq) +{ + bool prev_cmd_status_valid = true; + u32 status, stop_status = 0; + int err, retry; + + /* + * Try to get card status which indicates both the card state + * and why there was no response. If the first attempt fails, + * we can't be sure the returned status is for the r/w command. + */ + for (retry = 2; retry >= 0; retry--) { + err = get_card_status(card, &status, 0); + if (!err) + break; + + prev_cmd_status_valid = false; + pr_err("%s: error %d sending status command, %sing\n", + req->rq_disk->disk_name, err, retry ? "retry" : "abort"); + } + + /* We couldn't get a response from the card. Give up. */ if (err) - printk(KERN_ERR "%s: error %d sending status command", - req->rq_disk->disk_name, err); - return cmd.resp[0]; + return ERR_ABORT; + + /* + * Check the current card state. If it is in some data transfer + * mode, tell it to stop (and hopefully transition back to TRAN.) + */ + if (R1_CURRENT_STATE(status) == R1_STATE_DATA || + R1_CURRENT_STATE(status) == R1_STATE_RCV) { + err = send_stop(card, &stop_status); + if (err) + pr_err("%s: error %d sending stop command\n", + req->rq_disk->disk_name, err); + + /* + * If the stop cmd also timed out, the card is probably + * not present, so abort. Other errors are bad news too. + */ + if (err) + return ERR_ABORT; + } + + /* Check for set block count errors */ + if (brq->sbc.error) + return mmc_blk_cmd_error(req, "SET_BLOCK_COUNT", brq->sbc.error, + prev_cmd_status_valid, status); + + /* Check for r/w command errors */ + if (brq->cmd.error) + return mmc_blk_cmd_error(req, "r/w cmd", brq->cmd.error, + prev_cmd_status_valid, status); + + /* Now for stop errors. These aren't fatal to the transfer. */ + pr_err("%s: error %d sending stop command, original cmd response %#x, card status %#x\n", + req->rq_disk->disk_name, brq->stop.error, + brq->cmd.resp[0], status); + + /* + * Subsitute in our own stop status as this will give the error + * state which happened during the execution of the r/w command. + */ + if (stop_status) { + brq->stop.resp[0] = stop_status; + brq->stop.error = 0; + } + return ERR_CONTINUE; } static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) @@ -669,240 +814,324 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, } } -static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) +#define CMD_ERRORS \ + (R1_OUT_OF_RANGE | /* Command argument out of range */ \ + R1_ADDRESS_ERROR | /* Misaligned address */ \ + R1_BLOCK_LEN_ERROR | /* Transferred block length incorrect */\ + R1_WP_VIOLATION | /* Tried to write to protected block */ \ + R1_CC_ERROR | /* Card controller error */ \ + R1_ERROR) /* General/unknown error */ + +static int mmc_blk_err_check(struct mmc_card *card, + struct mmc_async_req *areq) { - struct mmc_blk_data *md = mq->data; - struct mmc_card *card = md->queue.card; - struct mmc_blk_request brq; - int ret = 1, disable_multi = 0; + enum mmc_blk_status ret = MMC_BLK_SUCCESS; + struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req, + mmc_active); + struct mmc_blk_request *brq = &mq_mrq->brq; + struct request *req = mq_mrq->req; /* - * Reliable writes are used to implement Forced Unit Access and - * REQ_META accesses, and are supported only on MMCs. + * sbc.error indicates a problem with the set block count + * command. No data will have been transferred. + * + * cmd.error indicates a problem with the r/w command. No + * data will have been transferred. + * + * stop.error indicates a problem with the stop command. Data + * may have been transferred, or may still be transferring. */ - bool do_rel_wr = ((req->cmd_flags & REQ_FUA) || - (req->cmd_flags & REQ_META)) && - (rq_data_dir(req) == WRITE) && - (md->flags & MMC_BLK_REL_WR); + if (brq->sbc.error || brq->cmd.error || brq->stop.error) { + switch (mmc_blk_cmd_recovery(card, req, brq)) { + case ERR_RETRY: + return MMC_BLK_RETRY; + case ERR_ABORT: + return MMC_BLK_ABORT; + case ERR_CONTINUE: + break; + } + } - do { - struct mmc_command cmd = {0}; - u32 readcmd, writecmd, status = 0; - - memset(&brq, 0, sizeof(struct mmc_blk_request)); - brq.mrq.cmd = &brq.cmd; - brq.mrq.data = &brq.data; - - brq.cmd.arg = blk_rq_pos(req); - if (!mmc_card_blockaddr(card)) - brq.cmd.arg <<= 9; - brq.cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC; - brq.data.blksz = 512; - brq.stop.opcode = MMC_STOP_TRANSMISSION; - brq.stop.arg = 0; - brq.stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; - brq.data.blocks = blk_rq_sectors(req); + /* + * Check for errors relating to the execution of the + * initial command - such as address errors. No data + * has been transferred. + */ + if (brq->cmd.resp[0] & CMD_ERRORS) { + pr_err("%s: r/w command failed, status = %#x\n", + req->rq_disk->disk_name, brq->cmd.resp[0]); + return MMC_BLK_ABORT; + } - /* - * The block layer doesn't support all sector count - * restrictions, so we need to be prepared for too big - * requests. - */ - if (brq.data.blocks > card->host->max_blk_count) - brq.data.blocks = card->host->max_blk_count; + /* + * Everything else is either success, or a data error of some + * kind. If it was a write, we may have transitioned to + * program mode, which we have to wait for it to complete. + */ + if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) { + u32 status; + do { + int err = get_card_status(card, &status, 5); + if (err) { + printk(KERN_ERR "%s: error %d requesting status\n", + req->rq_disk->disk_name, err); + return MMC_BLK_CMD_ERR; + } + /* + * Some cards mishandle the status bits, + * so make sure to check both the busy + * indication and the card state. + */ + } while (!(status & R1_READY_FOR_DATA) || + (R1_CURRENT_STATE(status) == R1_STATE_PRG)); + } - /* - * After a read error, we redo the request one sector at a time - * in order to accurately determine which sectors can be read - * successfully. - */ - if (disable_multi && brq.data.blocks > 1) - brq.data.blocks = 1; + if (brq->data.error) { + pr_err("%s: error %d transferring data, sector %u, nr %u, cmd response %#x, card status %#x\n", + req->rq_disk->disk_name, brq->data.error, + (unsigned)blk_rq_pos(req), + (unsigned)blk_rq_sectors(req), + brq->cmd.resp[0], brq->stop.resp[0]); - if (brq.data.blocks > 1 || do_rel_wr) { - /* SPI multiblock writes terminate using a special - * token, not a STOP_TRANSMISSION request. - */ - if (!mmc_host_is_spi(card->host) || - rq_data_dir(req) == READ) - brq.mrq.stop = &brq.stop; - readcmd = MMC_READ_MULTIPLE_BLOCK; - writecmd = MMC_WRITE_MULTIPLE_BLOCK; - } else { - brq.mrq.stop = NULL; - readcmd = MMC_READ_SINGLE_BLOCK; - writecmd = MMC_WRITE_BLOCK; - } if (rq_data_dir(req) == READ) { - brq.cmd.opcode = readcmd; - brq.data.flags |= MMC_DATA_READ; + if (brq->data.blocks > 1) { + /* Redo read one sector at a time */ + pr_warning("%s: retrying using single block read\n", + req->rq_disk->disk_name); + return MMC_BLK_RETRY_SINGLE; + } + return MMC_BLK_DATA_ERR; } else { - brq.cmd.opcode = writecmd; - brq.data.flags |= MMC_DATA_WRITE; + return MMC_BLK_CMD_ERR; } + } - if (do_rel_wr) - mmc_apply_rel_rw(&brq, card, req); + if (ret == MMC_BLK_SUCCESS && + blk_rq_bytes(req) != brq->data.bytes_xfered) + ret = MMC_BLK_PARTIAL; - /* - * Pre-defined multi-block transfers are preferable to - * open ended-ones (and necessary for reliable writes). - * However, it is not sufficient to just send CMD23, - * and avoid the final CMD12, as on an error condition - * CMD12 (stop) needs to be sent anyway. This, coupled - * with Auto-CMD23 enhancements provided by some - * hosts, means that the complexity of dealing - * with this is best left to the host. If CMD23 is - * supported by card and host, we'll fill sbc in and let - * the host deal with handling it correctly. This means - * that for hosts that don't expose MMC_CAP_CMD23, no - * change of behavior will be observed. - * - * N.B: Some MMC cards experience perf degradation. - * We'll avoid using CMD23-bounded multiblock writes for - * these, while retaining features like reliable writes. - */ + return ret; +} - if ((md->flags & MMC_BLK_CMD23) && - mmc_op_multi(brq.cmd.opcode) && - (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) { - brq.sbc.opcode = MMC_SET_BLOCK_COUNT; - brq.sbc.arg = brq.data.blocks | - (do_rel_wr ? (1 << 31) : 0); - brq.sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; - brq.mrq.sbc = &brq.sbc; - } +static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, + struct mmc_card *card, + int disable_multi, + struct mmc_queue *mq) +{ + u32 readcmd, writecmd; + struct mmc_blk_request *brq = &mqrq->brq; + struct request *req = mqrq->req; + struct mmc_blk_data *md = mq->data; - mmc_set_data_timeout(&brq.data, card); + /* + * Reliable writes are used to implement Forced Unit Access and + * REQ_META accesses, and are supported only on MMCs. + */ + bool do_rel_wr = ((req->cmd_flags & REQ_FUA) || + (req->cmd_flags & REQ_META)) && + (rq_data_dir(req) == WRITE) && + (md->flags & MMC_BLK_REL_WR); - brq.data.sg = mq->sg; - brq.data.sg_len = mmc_queue_map_sg(mq); + memset(brq, 0, sizeof(struct mmc_blk_request)); + brq->mrq.cmd = &brq->cmd; + brq->mrq.data = &brq->data; - /* - * Adjust the sg list so it is the same size as the - * request. + brq->cmd.arg = blk_rq_pos(req); + if (!mmc_card_blockaddr(card)) + brq->cmd.arg <<= 9; + brq->cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R1 | MMC_CMD_ADTC; + brq->data.blksz = 512; + brq->stop.opcode = MMC_STOP_TRANSMISSION; + brq->stop.arg = 0; + brq->stop.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC; + brq->data.blocks = blk_rq_sectors(req); + + /* + * The block layer doesn't support all sector count + * restrictions, so we need to be prepared for too big + * requests. + */ + if (brq->data.blocks > card->host->max_blk_count) + brq->data.blocks = card->host->max_blk_count; + + /* + * After a read error, we redo the request one sector at a time + * in order to accurately determine which sectors can be read + * successfully. + */ + if (disable_multi && brq->data.blocks > 1) + brq->data.blocks = 1; + + if (brq->data.blocks > 1 || do_rel_wr) { + /* SPI multiblock writes terminate using a special + * token, not a STOP_TRANSMISSION request. */ - if (brq.data.blocks != blk_rq_sectors(req)) { - int i, data_size = brq.data.blocks << 9; - struct scatterlist *sg; - - for_each_sg(brq.data.sg, sg, brq.data.sg_len, i) { - data_size -= sg->length; - if (data_size <= 0) { - sg->length += data_size; - i++; - break; - } - } - brq.data.sg_len = i; - } + if (!mmc_host_is_spi(card->host) || + rq_data_dir(req) == READ) + brq->mrq.stop = &brq->stop; + readcmd = MMC_READ_MULTIPLE_BLOCK; + writecmd = MMC_WRITE_MULTIPLE_BLOCK; + } else { + brq->mrq.stop = NULL; + readcmd = MMC_READ_SINGLE_BLOCK; + writecmd = MMC_WRITE_BLOCK; + } + if (rq_data_dir(req) == READ) { + brq->cmd.opcode = readcmd; + brq->data.flags |= MMC_DATA_READ; + } else { + brq->cmd.opcode = writecmd; + brq->data.flags |= MMC_DATA_WRITE; + } - mmc_queue_bounce_pre(mq); + if (do_rel_wr) + mmc_apply_rel_rw(brq, card, req); - mmc_wait_for_req(card->host, &brq.mrq); + /* + * Pre-defined multi-block transfers are preferable to + * open ended-ones (and necessary for reliable writes). + * However, it is not sufficient to just send CMD23, + * and avoid the final CMD12, as on an error condition + * CMD12 (stop) needs to be sent anyway. This, coupled + * with Auto-CMD23 enhancements provided by some + * hosts, means that the complexity of dealing + * with this is best left to the host. If CMD23 is + * supported by card and host, we'll fill sbc in and let + * the host deal with handling it correctly. This means + * that for hosts that don't expose MMC_CAP_CMD23, no + * change of behavior will be observed. + * + * N.B: Some MMC cards experience perf degradation. + * We'll avoid using CMD23-bounded multiblock writes for + * these, while retaining features like reliable writes. + */ - mmc_queue_bounce_post(mq); + if ((md->flags & MMC_BLK_CMD23) && + mmc_op_multi(brq->cmd.opcode) && + (do_rel_wr || !(card->quirks & MMC_QUIRK_BLK_NO_CMD23))) { + brq->sbc.opcode = MMC_SET_BLOCK_COUNT; + brq->sbc.arg = brq->data.blocks | + (do_rel_wr ? (1 << 31) : 0); + brq->sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; + brq->mrq.sbc = &brq->sbc; + } - /* - * Check for errors here, but don't jump to cmd_err - * until later as we need to wait for the card to leave - * programming mode even when things go wrong. - */ - if (brq.sbc.error || brq.cmd.error || - brq.data.error || brq.stop.error) { - if (brq.data.blocks > 1 && rq_data_dir(req) == READ) { - /* Redo read one sector at a time */ - printk(KERN_WARNING "%s: retrying using single " - "block read\n", req->rq_disk->disk_name); - disable_multi = 1; - continue; - } - status = get_card_status(card, req); - } + mmc_set_data_timeout(&brq->data, card); - if (brq.sbc.error) { - printk(KERN_ERR "%s: error %d sending SET_BLOCK_COUNT " - "command, response %#x, card status %#x\n", - req->rq_disk->disk_name, brq.sbc.error, - brq.sbc.resp[0], status); - } + brq->data.sg = mqrq->sg; + brq->data.sg_len = mmc_queue_map_sg(mq, mqrq); - if (brq.cmd.error) { - printk(KERN_ERR "%s: error %d sending read/write " - "command, response %#x, card status %#x\n", - req->rq_disk->disk_name, brq.cmd.error, - brq.cmd.resp[0], status); + /* + * Adjust the sg list so it is the same size as the + * request. + */ + if (brq->data.blocks != blk_rq_sectors(req)) { + int i, data_size = brq->data.blocks << 9; + struct scatterlist *sg; + + for_each_sg(brq->data.sg, sg, brq->data.sg_len, i) { + data_size -= sg->length; + if (data_size <= 0) { + sg->length += data_size; + i++; + break; + } } + brq->data.sg_len = i; + } - if (brq.data.error) { - if (brq.data.error == -ETIMEDOUT && brq.mrq.stop) - /* 'Stop' response contains card status */ - status = brq.mrq.stop->resp[0]; - printk(KERN_ERR "%s: error %d transferring data," - " sector %u, nr %u, card status %#x\n", - req->rq_disk->disk_name, brq.data.error, - (unsigned)blk_rq_pos(req), - (unsigned)blk_rq_sectors(req), status); - } + mqrq->mmc_active.mrq = &brq->mrq; + mqrq->mmc_active.err_check = mmc_blk_err_check; - if (brq.stop.error) { - printk(KERN_ERR "%s: error %d sending stop command, " - "response %#x, card status %#x\n", - req->rq_disk->disk_name, brq.stop.error, - brq.stop.resp[0], status); - } + mmc_queue_bounce_pre(mqrq); +} - if (!mmc_host_is_spi(card->host) && rq_data_dir(req) != READ) { - do { - int err; - - cmd.opcode = MMC_SEND_STATUS; - cmd.arg = card->rca << 16; - cmd.flags = MMC_RSP_R1 | MMC_CMD_AC; - err = mmc_wait_for_cmd(card->host, &cmd, 5); - if (err) { - printk(KERN_ERR "%s: error %d requesting status\n", - req->rq_disk->disk_name, err); - goto cmd_err; - } - /* - * Some cards mishandle the status bits, - * so make sure to check both the busy - * indication and the card state. - */ - } while (!(cmd.resp[0] & R1_READY_FOR_DATA) || - (R1_CURRENT_STATE(cmd.resp[0]) == 7)); - -#if 0 - if (cmd.resp[0] & ~0x00000900) - printk(KERN_ERR "%s: status = %08x\n", - req->rq_disk->disk_name, cmd.resp[0]); - if (mmc_decode_status(cmd.resp)) - goto cmd_err; -#endif - } +static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc) +{ + struct mmc_blk_data *md = mq->data; + struct mmc_card *card = md->queue.card; + struct mmc_blk_request *brq = &mq->mqrq_cur->brq; + int ret = 1, disable_multi = 0, retry = 0; + enum mmc_blk_status status; + struct mmc_queue_req *mq_rq; + struct request *req; + struct mmc_async_req *areq; + + if (!rqc && !mq->mqrq_prev->req) + return 0; - if (brq.cmd.error || brq.stop.error || brq.data.error) { - if (rq_data_dir(req) == READ) { + do { + if (rqc) { + mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); + areq = &mq->mqrq_cur->mmc_active; + } else + areq = NULL; + areq = mmc_start_req(card->host, areq, (int *) &status); + if (!areq) + return 0; + + mq_rq = container_of(areq, struct mmc_queue_req, mmc_active); + brq = &mq_rq->brq; + req = mq_rq->req; + mmc_queue_bounce_post(mq_rq); + + switch (status) { + case MMC_BLK_SUCCESS: + case MMC_BLK_PARTIAL: + /* + * A block was successfully transferred. + */ + spin_lock_irq(&md->lock); + ret = __blk_end_request(req, 0, + brq->data.bytes_xfered); + spin_unlock_irq(&md->lock); + if (status == MMC_BLK_SUCCESS && ret) { /* - * After an error, we redo I/O one sector at a - * time, so we only reach here after trying to - * read a single sector. + * The blk_end_request has returned non zero + * even though all data is transfered and no + * erros returned by host. + * If this happen it's a bug. */ - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, -EIO, brq.data.blksz); - spin_unlock_irq(&md->lock); - continue; + printk(KERN_ERR "%s BUG rq_tot %d d_xfer %d\n", + __func__, blk_rq_bytes(req), + brq->data.bytes_xfered); + rqc = NULL; + goto cmd_abort; } + break; + case MMC_BLK_CMD_ERR: goto cmd_err; + case MMC_BLK_RETRY_SINGLE: + disable_multi = 1; + break; + case MMC_BLK_RETRY: + if (retry++ < 5) + break; + case MMC_BLK_ABORT: + goto cmd_abort; + case MMC_BLK_DATA_ERR: + /* + * After an error, we redo I/O one sector at a + * time, so we only reach here after trying to + * read a single sector. + */ + spin_lock_irq(&md->lock); + ret = __blk_end_request(req, -EIO, + brq->data.blksz); + spin_unlock_irq(&md->lock); + if (!ret) + goto start_new_req; + break; } - /* - * A block was successfully transferred. - */ - spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, brq.data.bytes_xfered); - spin_unlock_irq(&md->lock); + if (ret) { + /* + * In case of a none complete request + * prepare it again and resend. + */ + mmc_blk_rw_rq_prep(mq_rq, card, disable_multi, mq); + mmc_start_req(card->host, &mq_rq->mmc_active, NULL); + } } while (ret); return 1; @@ -927,15 +1156,22 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *req) } } else { spin_lock_irq(&md->lock); - ret = __blk_end_request(req, 0, brq.data.bytes_xfered); + ret = __blk_end_request(req, 0, brq->data.bytes_xfered); spin_unlock_irq(&md->lock); } + cmd_abort: spin_lock_irq(&md->lock); while (ret) ret = __blk_end_request(req, -EIO, blk_rq_cur_bytes(req)); spin_unlock_irq(&md->lock); + start_new_req: + if (rqc) { + mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq); + mmc_start_req(card->host, &mq->mqrq_cur->mmc_active, NULL); + } + return 0; } @@ -945,26 +1181,37 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) struct mmc_blk_data *md = mq->data; struct mmc_card *card = md->queue.card; - mmc_claim_host(card->host); + if (req && !mq->mqrq_prev->req) + /* claim host only for the first request */ + mmc_claim_host(card->host); + ret = mmc_blk_part_switch(card, md); if (ret) { ret = 0; goto out; } - if (req->cmd_flags & REQ_DISCARD) { + if (req && req->cmd_flags & REQ_DISCARD) { + /* complete ongoing async transfer before issuing discard */ + if (card->host->areq) + mmc_blk_issue_rw_rq(mq, NULL); if (req->cmd_flags & REQ_SECURE) ret = mmc_blk_issue_secdiscard_rq(mq, req); else ret = mmc_blk_issue_discard_rq(mq, req); - } else if (req->cmd_flags & REQ_FLUSH) { + } else if (req && req->cmd_flags & REQ_FLUSH) { + /* complete ongoing async transfer before issuing flush */ + if (card->host->areq) + mmc_blk_issue_rw_rq(mq, NULL); ret = mmc_blk_issue_flush(mq, req); } else { ret = mmc_blk_issue_rw_rq(mq, req); } out: - mmc_release_host(card->host); + if (!req) + /* release host only when there are no more requests */ + mmc_release_host(card->host); return ret; } @@ -1024,7 +1271,7 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, INIT_LIST_HEAD(&md->part); md->usage = 1; - ret = mmc_init_queue(&md->queue, card, &md->lock); + ret = mmc_init_queue(&md->queue, card, &md->lock, subname); if (ret) goto err_putdisk; @@ -1297,6 +1544,9 @@ static void mmc_blk_remove(struct mmc_card *card) struct mmc_blk_data *md = mmc_get_drvdata(card); mmc_blk_remove_parts(card, md); + mmc_claim_host(card->host); + mmc_blk_part_switch(card, md); + mmc_release_host(card->host); mmc_blk_remove_req(md); mmc_set_drvdata(card, NULL); } diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c index 233cdfa..006a5e9 100644 --- a/drivers/mmc/card/mmc_test.c +++ b/drivers/mmc/card/mmc_test.c @@ -148,6 +148,27 @@ struct mmc_test_card { struct mmc_test_general_result *gr; }; +enum mmc_test_prep_media { + MMC_TEST_PREP_NONE = 0, + MMC_TEST_PREP_WRITE_FULL = 1 << 0, + MMC_TEST_PREP_ERASE = 1 << 1, +}; + +struct mmc_test_multiple_rw { + unsigned int *sg_len; + unsigned int *bs; + unsigned int len; + unsigned int size; + bool do_write; + bool do_nonblock_req; + enum mmc_test_prep_media prepare; +}; + +struct mmc_test_async_req { + struct mmc_async_req areq; + struct mmc_test_card *test; +}; + /*******************************************************************/ /* General helper functions */ /*******************************************************************/ @@ -367,21 +388,26 @@ out_free: * Map memory into a scatterlist. Optionally allow the same memory to be * mapped more than once. */ -static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long sz, +static int mmc_test_map_sg(struct mmc_test_mem *mem, unsigned long size, struct scatterlist *sglist, int repeat, unsigned int max_segs, unsigned int max_seg_sz, - unsigned int *sg_len) + unsigned int *sg_len, int min_sg_len) { struct scatterlist *sg = NULL; unsigned int i; + unsigned long sz = size; sg_init_table(sglist, max_segs); + if (min_sg_len > max_segs) + min_sg_len = max_segs; *sg_len = 0; do { for (i = 0; i < mem->cnt; i++) { unsigned long len = PAGE_SIZE << mem->arr[i].order; + if (min_sg_len && (size / min_sg_len < len)) + len = ALIGN(size / min_sg_len, 512); if (len > sz) len = sz; if (len > max_seg_sz) @@ -554,11 +580,12 @@ static void mmc_test_print_avg_rate(struct mmc_test_card *test, uint64_t bytes, printk(KERN_INFO "%s: Transfer of %u x %u sectors (%u x %u%s KiB) took " "%lu.%09lu seconds (%u kB/s, %u KiB/s, " - "%u.%02u IOPS)\n", + "%u.%02u IOPS, sg_len %d)\n", mmc_hostname(test->card->host), count, sectors, count, sectors >> 1, (sectors & 1 ? ".5" : ""), (unsigned long)ts.tv_sec, (unsigned long)ts.tv_nsec, - rate / 1000, rate / 1024, iops / 100, iops % 100); + rate / 1000, rate / 1024, iops / 100, iops % 100, + test->area.sg_len); mmc_test_save_transfer_result(test, count, sectors, ts, rate, iops); } @@ -661,7 +688,7 @@ static void mmc_test_prepare_broken_mrq(struct mmc_test_card *test, * Checks that a normal transfer didn't have any errors */ static int mmc_test_check_result(struct mmc_test_card *test, - struct mmc_request *mrq) + struct mmc_request *mrq) { int ret; @@ -685,6 +712,17 @@ static int mmc_test_check_result(struct mmc_test_card *test, return ret; } +static int mmc_test_check_result_async(struct mmc_card *card, + struct mmc_async_req *areq) +{ + struct mmc_test_async_req *test_async = + container_of(areq, struct mmc_test_async_req, areq); + + mmc_test_wait_busy(test_async->test); + + return mmc_test_check_result(test_async->test, areq->mrq); +} + /* * Checks that a "short transfer" behaved as expected */ @@ -720,6 +758,85 @@ static int mmc_test_check_broken_result(struct mmc_test_card *test, } /* + * Tests nonblock transfer with certain parameters + */ +static void mmc_test_nonblock_reset(struct mmc_request *mrq, + struct mmc_command *cmd, + struct mmc_command *stop, + struct mmc_data *data) +{ + memset(mrq, 0, sizeof(struct mmc_request)); + memset(cmd, 0, sizeof(struct mmc_command)); + memset(data, 0, sizeof(struct mmc_data)); + memset(stop, 0, sizeof(struct mmc_command)); + + mrq->cmd = cmd; + mrq->data = data; + mrq->stop = stop; +} +static int mmc_test_nonblock_transfer(struct mmc_test_card *test, + struct scatterlist *sg, unsigned sg_len, + unsigned dev_addr, unsigned blocks, + unsigned blksz, int write, int count) +{ + struct mmc_request mrq1; + struct mmc_command cmd1; + struct mmc_command stop1; + struct mmc_data data1; + + struct mmc_request mrq2; + struct mmc_command cmd2; + struct mmc_command stop2; + struct mmc_data data2; + + struct mmc_test_async_req test_areq[2]; + struct mmc_async_req *done_areq; + struct mmc_async_req *cur_areq = &test_areq[0].areq; + struct mmc_async_req *other_areq = &test_areq[1].areq; + int i; + int ret; + + test_areq[0].test = test; + test_areq[1].test = test; + + mmc_test_nonblock_reset(&mrq1, &cmd1, &stop1, &data1); + mmc_test_nonblock_reset(&mrq2, &cmd2, &stop2, &data2); + + cur_areq->mrq = &mrq1; + cur_areq->err_check = mmc_test_check_result_async; + other_areq->mrq = &mrq2; + other_areq->err_check = mmc_test_check_result_async; + + for (i = 0; i < count; i++) { + mmc_test_prepare_mrq(test, cur_areq->mrq, sg, sg_len, dev_addr, + blocks, blksz, write); + done_areq = mmc_start_req(test->card->host, cur_areq, &ret); + + if (ret || (!done_areq && i > 0)) + goto err; + + if (done_areq) { + if (done_areq->mrq == &mrq2) + mmc_test_nonblock_reset(&mrq2, &cmd2, + &stop2, &data2); + else + mmc_test_nonblock_reset(&mrq1, &cmd1, + &stop1, &data1); + } + done_areq = cur_areq; + cur_areq = other_areq; + other_areq = done_areq; + dev_addr += blocks; + } + + done_areq = mmc_start_req(test->card->host, NULL, &ret); + + return ret; +err: + return ret; +} + +/* * Tests a basic transfer with certain parameters */ static int mmc_test_simple_transfer(struct mmc_test_card *test, @@ -1302,7 +1419,7 @@ static int mmc_test_no_highmem(struct mmc_test_card *test) * Map sz bytes so that it can be transferred. */ static int mmc_test_area_map(struct mmc_test_card *test, unsigned long sz, - int max_scatter) + int max_scatter, int min_sg_len) { struct mmc_test_area *t = &test->area; int err; @@ -1315,7 +1432,7 @@ static int mmc_test_area_map(struct mmc_test_card *test, unsigned long sz, &t->sg_len); } else { err = mmc_test_map_sg(t->mem, sz, t->sg, 1, t->max_segs, - t->max_seg_sz, &t->sg_len); + t->max_seg_sz, &t->sg_len, min_sg_len); } if (err) printk(KERN_INFO "%s: Failed to map sg list\n", @@ -1336,14 +1453,17 @@ static int mmc_test_area_transfer(struct mmc_test_card *test, } /* - * Map and transfer bytes. + * Map and transfer bytes for multiple transfers. */ -static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, - unsigned int dev_addr, int write, int max_scatter, - int timed) +static int mmc_test_area_io_seq(struct mmc_test_card *test, unsigned long sz, + unsigned int dev_addr, int write, + int max_scatter, int timed, int count, + bool nonblock, int min_sg_len) { struct timespec ts1, ts2; - int ret; + int ret = 0; + int i; + struct mmc_test_area *t = &test->area; /* * In the case of a maximally scattered transfer, the maximum transfer @@ -1361,14 +1481,21 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, sz = max_tfr; } - ret = mmc_test_area_map(test, sz, max_scatter); + ret = mmc_test_area_map(test, sz, max_scatter, min_sg_len); if (ret) return ret; if (timed) getnstimeofday(&ts1); + if (nonblock) + ret = mmc_test_nonblock_transfer(test, t->sg, t->sg_len, + dev_addr, t->blocks, 512, write, count); + else + for (i = 0; i < count && ret == 0; i++) { + ret = mmc_test_area_transfer(test, dev_addr, write); + dev_addr += sz >> 9; + } - ret = mmc_test_area_transfer(test, dev_addr, write); if (ret) return ret; @@ -1376,11 +1503,19 @@ static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, getnstimeofday(&ts2); if (timed) - mmc_test_print_rate(test, sz, &ts1, &ts2); + mmc_test_print_avg_rate(test, sz, count, &ts1, &ts2); return 0; } +static int mmc_test_area_io(struct mmc_test_card *test, unsigned long sz, + unsigned int dev_addr, int write, int max_scatter, + int timed) +{ + return mmc_test_area_io_seq(test, sz, dev_addr, write, max_scatter, + timed, 1, false, 0); +} + /* * Write the test area entirely. */ @@ -1954,6 +2089,245 @@ static int mmc_test_large_seq_write_perf(struct mmc_test_card *test) return mmc_test_large_seq_perf(test, 1); } +static int mmc_test_rw_multiple(struct mmc_test_card *test, + struct mmc_test_multiple_rw *tdata, + unsigned int reqsize, unsigned int size, + int min_sg_len) +{ + unsigned int dev_addr; + struct mmc_test_area *t = &test->area; + int ret = 0; + + /* Set up test area */ + if (size > mmc_test_capacity(test->card) / 2 * 512) + size = mmc_test_capacity(test->card) / 2 * 512; + if (reqsize > t->max_tfr) + reqsize = t->max_tfr; + dev_addr = mmc_test_capacity(test->card) / 4; + if ((dev_addr & 0xffff0000)) + dev_addr &= 0xffff0000; /* Round to 64MiB boundary */ + else + dev_addr &= 0xfffff800; /* Round to 1MiB boundary */ + if (!dev_addr) + goto err; + + if (reqsize > size) + return 0; + + /* prepare test area */ + if (mmc_can_erase(test->card) && + tdata->prepare & MMC_TEST_PREP_ERASE) { + ret = mmc_erase(test->card, dev_addr, + size / 512, MMC_SECURE_ERASE_ARG); + if (ret) + ret = mmc_erase(test->card, dev_addr, + size / 512, MMC_ERASE_ARG); + if (ret) + goto err; + } + + /* Run test */ + ret = mmc_test_area_io_seq(test, reqsize, dev_addr, + tdata->do_write, 0, 1, size / reqsize, + tdata->do_nonblock_req, min_sg_len); + if (ret) + goto err; + + return ret; + err: + printk(KERN_INFO "[%s] error\n", __func__); + return ret; +} + +static int mmc_test_rw_multiple_size(struct mmc_test_card *test, + struct mmc_test_multiple_rw *rw) +{ + int ret = 0; + int i; + void *pre_req = test->card->host->ops->pre_req; + void *post_req = test->card->host->ops->post_req; + + if (rw->do_nonblock_req && + ((!pre_req && post_req) || (pre_req && !post_req))) { + printk(KERN_INFO "error: only one of pre/post is defined\n"); + return -EINVAL; + } + + for (i = 0 ; i < rw->len && ret == 0; i++) { + ret = mmc_test_rw_multiple(test, rw, rw->bs[i], rw->size, 0); + if (ret) + break; + } + return ret; +} + +static int mmc_test_rw_multiple_sg_len(struct mmc_test_card *test, + struct mmc_test_multiple_rw *rw) +{ + int ret = 0; + int i; + + for (i = 0 ; i < rw->len && ret == 0; i++) { + ret = mmc_test_rw_multiple(test, rw, 512*1024, rw->size, + rw->sg_len[i]); + if (ret) + break; + } + return ret; +} + +/* + * Multiple blocking write 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_write_blocking_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(bs), + .do_write = true, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +}; + +/* + * Multiple non-blocking write 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_write_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(bs), + .do_write = true, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +} + +/* + * Multiple blocking read 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_read_blocking_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(bs), + .do_write = false, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +} + +/* + * Multiple non-blocking read 4k to 4 MB chunks + */ +static int mmc_test_profile_mult_read_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int bs[] = {1 << 12, 1 << 13, 1 << 14, 1 << 15, 1 << 16, + 1 << 17, 1 << 18, 1 << 19, 1 << 20, 1 << 22}; + struct mmc_test_multiple_rw test_data = { + .bs = bs, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(bs), + .do_write = false, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_size(test, &test_data); +} + +/* + * Multiple blocking write 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_wr_blocking_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = true, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +}; + +/* + * Multiple non-blocking write 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_wr_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = true, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_ERASE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +} + +/* + * Multiple blocking read 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_r_blocking_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = false, + .do_nonblock_req = false, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +} + +/* + * Multiple non-blocking read 1 to 512 sg elements + */ +static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) +{ + unsigned int sg_len[] = {1, 1 << 3, 1 << 4, 1 << 5, 1 << 6, + 1 << 7, 1 << 8, 1 << 9}; + struct mmc_test_multiple_rw test_data = { + .sg_len = sg_len, + .size = TEST_AREA_MAX_SIZE, + .len = ARRAY_SIZE(sg_len), + .do_write = false, + .do_nonblock_req = true, + .prepare = MMC_TEST_PREP_NONE, + }; + + return mmc_test_rw_multiple_sg_len(test, &test_data); +} + static const struct mmc_test_case mmc_test_cases[] = { { .name = "Basic write (no data verification)", @@ -2221,6 +2595,61 @@ static const struct mmc_test_case mmc_test_cases[] = { .cleanup = mmc_test_area_cleanup, }, + { + .name = "Write performance with blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_write_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Write performance with non-blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_write_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance with blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_read_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance with non-blocking req 4k to 4MB", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_mult_read_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Write performance blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_wr_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Write performance non-blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_wr_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_r_blocking_perf, + .cleanup = mmc_test_area_cleanup, + }, + + { + .name = "Read performance non-blocking req 1 to 512 sg elems", + .prepare = mmc_test_area_prepare, + .run = mmc_test_profile_sglen_r_nonblock_perf, + .cleanup = mmc_test_area_cleanup, + }, }; static DEFINE_MUTEX(mmc_test_lock); @@ -2445,6 +2874,32 @@ static const struct file_operations mmc_test_fops_test = { .release = single_release, }; +static int mtf_testlist_show(struct seq_file *sf, void *data) +{ + int i; + + mutex_lock(&mmc_test_lock); + + for (i = 0; i < ARRAY_SIZE(mmc_test_cases); i++) + seq_printf(sf, "%d:\t%s\n", i+1, mmc_test_cases[i].name); + + mutex_unlock(&mmc_test_lock); + + return 0; +} + +static int mtf_testlist_open(struct inode *inode, struct file *file) +{ + return single_open(file, mtf_testlist_show, inode->i_private); +} + +static const struct file_operations mmc_test_fops_testlist = { + .open = mtf_testlist_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static void mmc_test_free_file_test(struct mmc_card *card) { struct mmc_test_dbgfs_file *df, *dfs; @@ -2476,7 +2931,18 @@ static int mmc_test_register_file_test(struct mmc_card *card) if (IS_ERR_OR_NULL(file)) { dev_err(&card->dev, - "Can't create file. Perhaps debugfs is disabled.\n"); + "Can't create test. Perhaps debugfs is disabled.\n"); + ret = -ENODEV; + goto err; + } + + if (card->debugfs_root) + file = debugfs_create_file("testlist", S_IRUGO, + card->debugfs_root, card, &mmc_test_fops_testlist); + + if (IS_ERR_OR_NULL(file)) { + dev_err(&card->dev, + "Can't create testlist. Perhaps debugfs is disabled.\n"); ret = -ENODEV; goto err; } diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index c07322c..45fb362 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -52,14 +52,18 @@ static int mmc_queue_thread(void *d) down(&mq->thread_sem); do { struct request *req = NULL; + struct mmc_queue_req *tmp; spin_lock_irq(q->queue_lock); set_current_state(TASK_INTERRUPTIBLE); req = blk_fetch_request(q); - mq->req = req; + mq->mqrq_cur->req = req; spin_unlock_irq(q->queue_lock); - if (!req) { + if (req || mq->mqrq_prev->req) { + set_current_state(TASK_RUNNING); + mq->issue_fn(mq, req); + } else { if (kthread_should_stop()) { set_current_state(TASK_RUNNING); break; @@ -67,11 +71,14 @@ static int mmc_queue_thread(void *d) up(&mq->thread_sem); schedule(); down(&mq->thread_sem); - continue; } - set_current_state(TASK_RUNNING); - mq->issue_fn(mq, req); + /* Current request becomes previous request and vice versa. */ + mq->mqrq_prev->brq.mrq.data = NULL; + mq->mqrq_prev->req = NULL; + tmp = mq->mqrq_prev; + mq->mqrq_prev = mq->mqrq_cur; + mq->mqrq_cur = tmp; } while (1); up(&mq->thread_sem); @@ -97,23 +104,63 @@ static void mmc_request(struct request_queue *q) return; } - if (!mq->req) + if (!mq->mqrq_cur->req && !mq->mqrq_prev->req) wake_up_process(mq->thread); } +struct scatterlist *mmc_alloc_sg(int sg_len, int *err) +{ + struct scatterlist *sg; + + sg = kmalloc(sizeof(struct scatterlist)*sg_len, GFP_KERNEL); + if (!sg) + *err = -ENOMEM; + else { + *err = 0; + sg_init_table(sg, sg_len); + } + + return sg; +} + +static void mmc_queue_setup_discard(struct request_queue *q, + struct mmc_card *card) +{ + unsigned max_discard; + + max_discard = mmc_calc_max_discard(card); + if (!max_discard) + return; + + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + q->limits.max_discard_sectors = max_discard; + if (card->erased_byte == 0) + q->limits.discard_zeroes_data = 1; + q->limits.discard_granularity = card->pref_erase << 9; + /* granularity must not be greater than max. discard */ + if (card->pref_erase > max_discard) + q->limits.discard_granularity = 0; + if (mmc_can_secure_erase_trim(card)) + queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, q); +} + /** * mmc_init_queue - initialise a queue structure. * @mq: mmc queue * @card: mmc card to attach this queue * @lock: queue lock + * @subname: partition subname * * Initialise a MMC card request queue. */ -int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock) +int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, + spinlock_t *lock, const char *subname) { struct mmc_host *host = card->host; u64 limit = BLK_BOUNCE_HIGH; int ret; + struct mmc_queue_req *mqrq_cur = &mq->mqrq[0]; + struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = *mmc_dev(host)->dma_mask; @@ -123,26 +170,16 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock if (!mq->queue) return -ENOMEM; + memset(&mq->mqrq_cur, 0, sizeof(mq->mqrq_cur)); + memset(&mq->mqrq_prev, 0, sizeof(mq->mqrq_prev)); + mq->mqrq_cur = mqrq_cur; + mq->mqrq_prev = mqrq_prev; mq->queue->queuedata = mq; - mq->req = NULL; blk_queue_prep_rq(mq->queue, mmc_prep_request); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue); - if (mmc_can_erase(card)) { - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mq->queue); - mq->queue->limits.max_discard_sectors = UINT_MAX; - if (card->erased_byte == 0) - mq->queue->limits.discard_zeroes_data = 1; - if (!mmc_can_trim(card) && is_power_of_2(card->erase_size)) { - mq->queue->limits.discard_granularity = - card->erase_size << 9; - mq->queue->limits.discard_alignment = - card->erase_size << 9; - } - if (mmc_can_secure_erase_trim(card)) - queue_flag_set_unlocked(QUEUE_FLAG_SECDISCARD, - mq->queue); - } + if (mmc_can_erase(card)) + mmc_queue_setup_discard(mq->queue, card); #ifdef CONFIG_MMC_BLOCK_BOUNCE if (host->max_segs == 1) { @@ -158,59 +195,70 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock bouncesz = host->max_blk_count * 512; if (bouncesz > 512) { - mq->bounce_buf = kmalloc(bouncesz, GFP_KERNEL); - if (!mq->bounce_buf) { + mqrq_cur->bounce_buf = kmalloc(bouncesz, GFP_KERNEL); + if (!mqrq_cur->bounce_buf) { + printk(KERN_WARNING "%s: unable to " + "allocate bounce cur buffer\n", + mmc_card_name(card)); + } + mqrq_prev->bounce_buf = kmalloc(bouncesz, GFP_KERNEL); + if (!mqrq_prev->bounce_buf) { printk(KERN_WARNING "%s: unable to " - "allocate bounce buffer\n", + "allocate bounce prev buffer\n", mmc_card_name(card)); + kfree(mqrq_cur->bounce_buf); + mqrq_cur->bounce_buf = NULL; } } - if (mq->bounce_buf) { + if (mqrq_cur->bounce_buf && mqrq_prev->bounce_buf) { blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_ANY); blk_queue_max_hw_sectors(mq->queue, bouncesz / 512); blk_queue_max_segments(mq->queue, bouncesz / 512); blk_queue_max_segment_size(mq->queue, bouncesz); - mq->sg = kmalloc(sizeof(struct scatterlist), - GFP_KERNEL); - if (!mq->sg) { - ret = -ENOMEM; + mqrq_cur->sg = mmc_alloc_sg(1, &ret); + if (ret) goto cleanup_queue; - } - sg_init_table(mq->sg, 1); - mq->bounce_sg = kmalloc(sizeof(struct scatterlist) * - bouncesz / 512, GFP_KERNEL); - if (!mq->bounce_sg) { - ret = -ENOMEM; + mqrq_cur->bounce_sg = + mmc_alloc_sg(bouncesz / 512, &ret); + if (ret) + goto cleanup_queue; + + mqrq_prev->sg = mmc_alloc_sg(1, &ret); + if (ret) + goto cleanup_queue; + + mqrq_prev->bounce_sg = + mmc_alloc_sg(bouncesz / 512, &ret); + if (ret) goto cleanup_queue; - } - sg_init_table(mq->bounce_sg, bouncesz / 512); } } #endif - if (!mq->bounce_buf) { + if (!mqrq_cur->bounce_buf && !mqrq_prev->bounce_buf) { blk_queue_bounce_limit(mq->queue, limit); blk_queue_max_hw_sectors(mq->queue, min(host->max_blk_count, host->max_req_size / 512)); blk_queue_max_segments(mq->queue, host->max_segs); blk_queue_max_segment_size(mq->queue, host->max_seg_size); - mq->sg = kmalloc(sizeof(struct scatterlist) * - host->max_segs, GFP_KERNEL); - if (!mq->sg) { - ret = -ENOMEM; + mqrq_cur->sg = mmc_alloc_sg(host->max_segs, &ret); + if (ret) + goto cleanup_queue; + + + mqrq_prev->sg = mmc_alloc_sg(host->max_segs, &ret); + if (ret) goto cleanup_queue; - } - sg_init_table(mq->sg, host->max_segs); } sema_init(&mq->thread_sem, 1); - mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d", - host->index); + mq->thread = kthread_run(mmc_queue_thread, mq, "mmcqd/%d%s", + host->index, subname ? subname : ""); if (IS_ERR(mq->thread)) { ret = PTR_ERR(mq->thread); @@ -219,16 +267,22 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock return 0; free_bounce_sg: - if (mq->bounce_sg) - kfree(mq->bounce_sg); - mq->bounce_sg = NULL; + kfree(mqrq_cur->bounce_sg); + mqrq_cur->bounce_sg = NULL; + kfree(mqrq_prev->bounce_sg); + mqrq_prev->bounce_sg = NULL; + cleanup_queue: - if (mq->sg) - kfree(mq->sg); - mq->sg = NULL; - if (mq->bounce_buf) - kfree(mq->bounce_buf); - mq->bounce_buf = NULL; + kfree(mqrq_cur->sg); + mqrq_cur->sg = NULL; + kfree(mqrq_cur->bounce_buf); + mqrq_cur->bounce_buf = NULL; + + kfree(mqrq_prev->sg); + mqrq_prev->sg = NULL; + kfree(mqrq_prev->bounce_buf); + mqrq_prev->bounce_buf = NULL; + blk_cleanup_queue(mq->queue); return ret; } @@ -237,6 +291,8 @@ void mmc_cleanup_queue(struct mmc_queue *mq) { struct request_queue *q = mq->queue; unsigned long flags; + struct mmc_queue_req *mqrq_cur = mq->mqrq_cur; + struct mmc_queue_req *mqrq_prev = mq->mqrq_prev; /* Make sure the queue isn't suspended, as that will deadlock */ mmc_queue_resume(mq); @@ -250,16 +306,23 @@ void mmc_cleanup_queue(struct mmc_queue *mq) blk_start_queue(q); spin_unlock_irqrestore(q->queue_lock, flags); - if (mq->bounce_sg) - kfree(mq->bounce_sg); - mq->bounce_sg = NULL; + kfree(mqrq_cur->bounce_sg); + mqrq_cur->bounce_sg = NULL; - kfree(mq->sg); - mq->sg = NULL; + kfree(mqrq_cur->sg); + mqrq_cur->sg = NULL; - if (mq->bounce_buf) - kfree(mq->bounce_buf); - mq->bounce_buf = NULL; + kfree(mqrq_cur->bounce_buf); + mqrq_cur->bounce_buf = NULL; + + kfree(mqrq_prev->bounce_sg); + mqrq_prev->bounce_sg = NULL; + + kfree(mqrq_prev->sg); + mqrq_prev->sg = NULL; + + kfree(mqrq_prev->bounce_buf); + mqrq_prev->bounce_buf = NULL; mq->card = NULL; } @@ -312,27 +375,27 @@ void mmc_queue_resume(struct mmc_queue *mq) /* * Prepare the sg list(s) to be handed of to the host driver */ -unsigned int mmc_queue_map_sg(struct mmc_queue *mq) +unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq) { unsigned int sg_len; size_t buflen; struct scatterlist *sg; int i; - if (!mq->bounce_buf) - return blk_rq_map_sg(mq->queue, mq->req, mq->sg); + if (!mqrq->bounce_buf) + return blk_rq_map_sg(mq->queue, mqrq->req, mqrq->sg); - BUG_ON(!mq->bounce_sg); + BUG_ON(!mqrq->bounce_sg); - sg_len = blk_rq_map_sg(mq->queue, mq->req, mq->bounce_sg); + sg_len = blk_rq_map_sg(mq->queue, mqrq->req, mqrq->bounce_sg); - mq->bounce_sg_len = sg_len; + mqrq->bounce_sg_len = sg_len; buflen = 0; - for_each_sg(mq->bounce_sg, sg, sg_len, i) + for_each_sg(mqrq->bounce_sg, sg, sg_len, i) buflen += sg->length; - sg_init_one(mq->sg, mq->bounce_buf, buflen); + sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen); return 1; } @@ -341,31 +404,30 @@ unsigned int mmc_queue_map_sg(struct mmc_queue *mq) * If writing, bounce the data to the buffer before the request * is sent to the host driver */ -void mmc_queue_bounce_pre(struct mmc_queue *mq) +void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq) { - if (!mq->bounce_buf) + if (!mqrq->bounce_buf) return; - if (rq_data_dir(mq->req) != WRITE) + if (rq_data_dir(mqrq->req) != WRITE) return; - sg_copy_to_buffer(mq->bounce_sg, mq->bounce_sg_len, - mq->bounce_buf, mq->sg[0].length); + sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, + mqrq->bounce_buf, mqrq->sg[0].length); } /* * If reading, bounce the data from the buffer after the request * has been handled by the host driver */ -void mmc_queue_bounce_post(struct mmc_queue *mq) +void mmc_queue_bounce_post(struct mmc_queue_req *mqrq) { - if (!mq->bounce_buf) + if (!mqrq->bounce_buf) return; - if (rq_data_dir(mq->req) != READ) + if (rq_data_dir(mqrq->req) != READ) return; - sg_copy_from_buffer(mq->bounce_sg, mq->bounce_sg_len, - mq->bounce_buf, mq->sg[0].length); + sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len, + mqrq->bounce_buf, mqrq->sg[0].length); } - diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index 64e66e0..d2a1eb4 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,28 +4,46 @@ struct request; struct task_struct; +struct mmc_blk_request { + struct mmc_request mrq; + struct mmc_command sbc; + struct mmc_command cmd; + struct mmc_command stop; + struct mmc_data data; +}; + +struct mmc_queue_req { + struct request *req; + struct mmc_blk_request brq; + struct scatterlist *sg; + char *bounce_buf; + struct scatterlist *bounce_sg; + unsigned int bounce_sg_len; + struct mmc_async_req mmc_active; +}; + struct mmc_queue { struct mmc_card *card; struct task_struct *thread; struct semaphore thread_sem; unsigned int flags; - struct request *req; int (*issue_fn)(struct mmc_queue *, struct request *); void *data; struct request_queue *queue; - struct scatterlist *sg; - char *bounce_buf; - struct scatterlist *bounce_sg; - unsigned int bounce_sg_len; + struct mmc_queue_req mqrq[2]; + struct mmc_queue_req *mqrq_cur; + struct mmc_queue_req *mqrq_prev; }; -extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *); +extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *, + const char *); extern void mmc_cleanup_queue(struct mmc_queue *); extern void mmc_queue_suspend(struct mmc_queue *); extern void mmc_queue_resume(struct mmc_queue *); -extern unsigned int mmc_queue_map_sg(struct mmc_queue *); -extern void mmc_queue_bounce_pre(struct mmc_queue *); -extern void mmc_queue_bounce_post(struct mmc_queue *); +extern unsigned int mmc_queue_map_sg(struct mmc_queue *, + struct mmc_queue_req *); +extern void mmc_queue_bounce_pre(struct mmc_queue_req *); +extern void mmc_queue_bounce_post(struct mmc_queue_req *); #endif diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 68091dd..f091b43 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -198,9 +198,109 @@ mmc_start_request(struct mmc_host *host, struct mmc_request *mrq) static void mmc_wait_done(struct mmc_request *mrq) { - complete(mrq->done_data); + complete(&mrq->completion); } +static void __mmc_start_req(struct mmc_host *host, struct mmc_request *mrq) +{ + init_completion(&mrq->completion); + mrq->done = mmc_wait_done; + mmc_start_request(host, mrq); +} + +static void mmc_wait_for_req_done(struct mmc_host *host, + struct mmc_request *mrq) +{ + wait_for_completion(&mrq->completion); +} + +/** + * mmc_pre_req - Prepare for a new request + * @host: MMC host to prepare command + * @mrq: MMC request to prepare for + * @is_first_req: true if there is no previous started request + * that may run in parellel to this call, otherwise false + * + * mmc_pre_req() is called in prior to mmc_start_req() to let + * host prepare for the new request. Preparation of a request may be + * performed while another request is running on the host. + */ +static void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq, + bool is_first_req) +{ + if (host->ops->pre_req) + host->ops->pre_req(host, mrq, is_first_req); +} + +/** + * mmc_post_req - Post process a completed request + * @host: MMC host to post process command + * @mrq: MMC request to post process for + * @err: Error, if non zero, clean up any resources made in pre_req + * + * Let the host post process a completed request. Post processing of + * a request may be performed while another reuqest is running. + */ +static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq, + int err) +{ + if (host->ops->post_req) + host->ops->post_req(host, mrq, err); +} + +/** + * mmc_start_req - start a non-blocking request + * @host: MMC host to start command + * @areq: async request to start + * @error: out parameter returns 0 for success, otherwise non zero + * + * Start a new MMC custom command request for a host. + * If there is on ongoing async request wait for completion + * of that request and start the new one and return. + * Does not wait for the new request to complete. + * + * Returns the completed request, NULL in case of none completed. + * Wait for the an ongoing request (previoulsy started) to complete and + * return the completed request. If there is no ongoing request, NULL + * is returned without waiting. NULL is not an error condition. + */ +struct mmc_async_req *mmc_start_req(struct mmc_host *host, + struct mmc_async_req *areq, int *error) +{ + int err = 0; + struct mmc_async_req *data = host->areq; + + /* Prepare a new request */ + if (areq) + mmc_pre_req(host, areq->mrq, !host->areq); + + if (host->areq) { + mmc_wait_for_req_done(host, host->areq->mrq); + err = host->areq->err_check(host->card, host->areq); + if (err) { + mmc_post_req(host, host->areq->mrq, 0); + if (areq) + mmc_post_req(host, areq->mrq, -EINVAL); + + host->areq = NULL; + goto out; + } + } + + if (areq) + __mmc_start_req(host, areq->mrq); + + if (host->areq) + mmc_post_req(host, host->areq->mrq, 0); + + host->areq = areq; + out: + if (error) + *error = err; + return data; +} +EXPORT_SYMBOL(mmc_start_req); + /** * mmc_wait_for_req - start a request and wait for completion * @host: MMC host to start command @@ -212,16 +312,9 @@ static void mmc_wait_done(struct mmc_request *mrq) */ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq) { - DECLARE_COMPLETION_ONSTACK(complete); - - mrq->done_data = &complete; - mrq->done = mmc_wait_done; - - mmc_start_request(host, mrq); - - wait_for_completion(&complete); + __mmc_start_req(host, mrq); + mmc_wait_for_req_done(host, mrq); } - EXPORT_SYMBOL(mmc_wait_for_req); /** @@ -1245,7 +1338,7 @@ static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card, */ timeout_clks <<= 1; timeout_us += (timeout_clks * 1000) / - (card->host->ios.clock / 1000); + (mmc_host_clk_rate(card->host) / 1000); erase_timeout = timeout_us / 1000; @@ -1516,6 +1609,82 @@ int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from, } EXPORT_SYMBOL(mmc_erase_group_aligned); +static unsigned int mmc_do_calc_max_discard(struct mmc_card *card, + unsigned int arg) +{ + struct mmc_host *host = card->host; + unsigned int max_discard, x, y, qty = 0, max_qty, timeout; + unsigned int last_timeout = 0; + + if (card->erase_shift) + max_qty = UINT_MAX >> card->erase_shift; + else if (mmc_card_sd(card)) + max_qty = UINT_MAX; + else + max_qty = UINT_MAX / card->erase_size; + + /* Find the largest qty with an OK timeout */ + do { + y = 0; + for (x = 1; x && x <= max_qty && max_qty - x >= qty; x <<= 1) { + timeout = mmc_erase_timeout(card, arg, qty + x); + if (timeout > host->max_discard_to) + break; + if (timeout < last_timeout) + break; + last_timeout = timeout; + y = x; + } + qty += y; + } while (y); + + if (!qty) + return 0; + + if (qty == 1) + return 1; + + /* Convert qty to sectors */ + if (card->erase_shift) + max_discard = --qty << card->erase_shift; + else if (mmc_card_sd(card)) + max_discard = qty; + else + max_discard = --qty * card->erase_size; + + return max_discard; +} + +unsigned int mmc_calc_max_discard(struct mmc_card *card) +{ + struct mmc_host *host = card->host; + unsigned int max_discard, max_trim; + + if (!host->max_discard_to) + return UINT_MAX; + + /* + * Without erase_group_def set, MMC erase timeout depends on clock + * frequence which can change. In that case, the best choice is + * just the preferred erase size. + */ + if (mmc_card_mmc(card) && !(card->ext_csd.erase_group_def & 1)) + return card->pref_erase; + + max_discard = mmc_do_calc_max_discard(card, MMC_ERASE_ARG); + if (mmc_can_trim(card)) { + max_trim = mmc_do_calc_max_discard(card, MMC_TRIM_ARG); + if (max_trim < max_discard) + max_discard = max_trim; + } else if (max_discard < card->erase_size) { + max_discard = 0; + } + pr_debug("%s: calculated max. discard sectors %u for timeout %u ms\n", + mmc_hostname(host), max_discard, host->max_discard_to); + return max_discard; +} +EXPORT_SYMBOL(mmc_calc_max_discard); + int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen) { struct mmc_command cmd = {0}; @@ -1663,6 +1832,10 @@ int mmc_power_save_host(struct mmc_host *host) { int ret = 0; +#ifdef CONFIG_MMC_DEBUG + pr_info("%s: %s: powering down\n", mmc_hostname(host), __func__); +#endif + mmc_bus_get(host); if (!host->bus_ops || host->bus_dead || !host->bus_ops->power_restore) { @@ -1685,6 +1858,10 @@ int mmc_power_restore_host(struct mmc_host *host) { int ret; +#ifdef CONFIG_MMC_DEBUG + pr_info("%s: %s: powering up\n", mmc_hostname(host), __func__); +#endif + mmc_bus_get(host); if (!host->bus_ops || host->bus_dead || !host->bus_ops->power_restore) { diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 2a7e43b..aa7d1d7 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -247,12 +247,12 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd) return 0; /* Version is coded in the CSD_STRUCTURE byte in the EXT_CSD register */ + card->ext_csd.raw_ext_csd_structure = ext_csd[EXT_CSD_STRUCTURE]; if (card->csd.structure == 3) { - int ext_csd_struct = ext_csd[EXT_CSD_STRUCTURE]; - if (ext_csd_struct > 2) { + if (card->ext_csd.raw_ext_csd_structure > 2) { printk(KERN_ERR "%s: unrecognised EXT_CSD structure " "version %d\n", mmc_hostname(card->host), - ext_csd_struct); + card->ext_csd.raw_ext_csd_structure); err = -EINVAL; goto out; } @@ -266,6 +266,10 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd) goto out; } + card->ext_csd.raw_sectors[0] = ext_csd[EXT_CSD_SEC_CNT + 0]; + card->ext_csd.raw_sectors[1] = ext_csd[EXT_CSD_SEC_CNT + 1]; + card->ext_csd.raw_sectors[2] = ext_csd[EXT_CSD_SEC_CNT + 2]; + card->ext_csd.raw_sectors[3] = ext_csd[EXT_CSD_SEC_CNT + 3]; if (card->ext_csd.rev >= 2) { card->ext_csd.sectors = ext_csd[EXT_CSD_SEC_CNT + 0] << 0 | @@ -277,7 +281,7 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd) if (card->ext_csd.sectors > (2u * 1024 * 1024 * 1024) / 512) mmc_card_set_blockaddr(card); } - + card->ext_csd.raw_card_type = ext_csd[EXT_CSD_CARD_TYPE]; switch (ext_csd[EXT_CSD_CARD_TYPE] & EXT_CSD_CARD_TYPE_MASK) { case EXT_CSD_CARD_TYPE_DDR_52 | EXT_CSD_CARD_TYPE_52 | EXT_CSD_CARD_TYPE_26: @@ -307,6 +311,11 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd) mmc_hostname(card->host)); } + card->ext_csd.raw_s_a_timeout = ext_csd[EXT_CSD_S_A_TIMEOUT]; + card->ext_csd.raw_erase_timeout_mult = + ext_csd[EXT_CSD_ERASE_TIMEOUT_MULT]; + card->ext_csd.raw_hc_erase_grp_size = + ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE]; if (card->ext_csd.rev >= 3) { u8 sa_shift = ext_csd[EXT_CSD_S_A_TIMEOUT]; card->ext_csd.part_config = ext_csd[EXT_CSD_PART_CONFIG]; @@ -334,6 +343,16 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd) card->ext_csd.boot_size = ext_csd[EXT_CSD_BOOT_MULT] << 17; } + card->ext_csd.raw_hc_erase_gap_size = + ext_csd[EXT_CSD_PARTITION_ATTRIBUTE]; + card->ext_csd.raw_sec_trim_mult = + ext_csd[EXT_CSD_SEC_TRIM_MULT]; + card->ext_csd.raw_sec_erase_mult = + ext_csd[EXT_CSD_SEC_ERASE_MULT]; + card->ext_csd.raw_sec_feature_support = + ext_csd[EXT_CSD_SEC_FEATURE_SUPPORT]; + card->ext_csd.raw_trim_mult = + ext_csd[EXT_CSD_TRIM_MULT]; if (card->ext_csd.rev >= 4) { /* * Enhanced area feature support -- check whether the eMMC @@ -341,7 +360,7 @@ static int mmc_read_ext_csd(struct mmc_card *card, u8 *ext_csd) * area offset and size to user by adding sysfs interface. */ if ((ext_csd[EXT_CSD_PARTITION_SUPPORT] & 0x2) && - (ext_csd[EXT_CSD_PARTITION_ATTRIBUTE] & 0x1)) { + (ext_csd[EXT_CSD_PARTITION_ATTRIBUTE] & 0x1)) { u8 hc_erase_grp_sz = ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE]; u8 hc_wp_grp_sz = @@ -401,17 +420,17 @@ static inline void mmc_free_ext_csd(u8 *ext_csd) } -static int mmc_compare_ext_csds(struct mmc_card *card, u8 *ext_csd, - unsigned bus_width) +static int mmc_compare_ext_csds(struct mmc_card *card, unsigned bus_width) { u8 *bw_ext_csd; int err; + if (bus_width == MMC_BUS_WIDTH_1) + return 0; + err = mmc_get_ext_csd(card, &bw_ext_csd); - if (err) - return err; - if ((ext_csd == NULL || bw_ext_csd == NULL)) { + if (err || bw_ext_csd == NULL) { if (bus_width != MMC_BUS_WIDTH_1) err = -EINVAL; goto out; @@ -421,35 +440,40 @@ static int mmc_compare_ext_csds(struct mmc_card *card, u8 *ext_csd, goto out; /* only compare read only fields */ - err = (!(ext_csd[EXT_CSD_PARTITION_SUPPORT] == + err = (!(card->ext_csd.raw_partition_support == bw_ext_csd[EXT_CSD_PARTITION_SUPPORT]) && - (ext_csd[EXT_CSD_ERASED_MEM_CONT] == + (card->ext_csd.raw_erased_mem_count == bw_ext_csd[EXT_CSD_ERASED_MEM_CONT]) && - (ext_csd[EXT_CSD_REV] == + (card->ext_csd.rev == bw_ext_csd[EXT_CSD_REV]) && - (ext_csd[EXT_CSD_STRUCTURE] == + (card->ext_csd.raw_ext_csd_structure == bw_ext_csd[EXT_CSD_STRUCTURE]) && - (ext_csd[EXT_CSD_CARD_TYPE] == + (card->ext_csd.raw_card_type == bw_ext_csd[EXT_CSD_CARD_TYPE]) && - (ext_csd[EXT_CSD_S_A_TIMEOUT] == + (card->ext_csd.raw_s_a_timeout == bw_ext_csd[EXT_CSD_S_A_TIMEOUT]) && - (ext_csd[EXT_CSD_HC_WP_GRP_SIZE] == + (card->ext_csd.raw_hc_erase_gap_size == bw_ext_csd[EXT_CSD_HC_WP_GRP_SIZE]) && - (ext_csd[EXT_CSD_ERASE_TIMEOUT_MULT] == + (card->ext_csd.raw_erase_timeout_mult == bw_ext_csd[EXT_CSD_ERASE_TIMEOUT_MULT]) && - (ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE] == + (card->ext_csd.raw_hc_erase_grp_size == bw_ext_csd[EXT_CSD_HC_ERASE_GRP_SIZE]) && - (ext_csd[EXT_CSD_SEC_TRIM_MULT] == + (card->ext_csd.raw_sec_trim_mult == bw_ext_csd[EXT_CSD_SEC_TRIM_MULT]) && - (ext_csd[EXT_CSD_SEC_ERASE_MULT] == + (card->ext_csd.raw_sec_erase_mult == bw_ext_csd[EXT_CSD_SEC_ERASE_MULT]) && - (ext_csd[EXT_CSD_SEC_FEATURE_SUPPORT] == + (card->ext_csd.raw_sec_feature_support == bw_ext_csd[EXT_CSD_SEC_FEATURE_SUPPORT]) && - (ext_csd[EXT_CSD_TRIM_MULT] == + (card->ext_csd.raw_trim_mult == bw_ext_csd[EXT_CSD_TRIM_MULT]) && - memcmp(&ext_csd[EXT_CSD_SEC_CNT], - &bw_ext_csd[EXT_CSD_SEC_CNT], - 4) != 0); + (card->ext_csd.raw_sectors[0] == + bw_ext_csd[EXT_CSD_SEC_CNT + 0]) && + (card->ext_csd.raw_sectors[1] == + bw_ext_csd[EXT_CSD_SEC_CNT + 1]) && + (card->ext_csd.raw_sectors[2] == + bw_ext_csd[EXT_CSD_SEC_CNT + 2]) && + (card->ext_csd.raw_sectors[3] == + bw_ext_csd[EXT_CSD_SEC_CNT + 3])); if (err) err = -EINVAL; @@ -770,7 +794,6 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr, */ if (!(host->caps & MMC_CAP_BUS_WIDTH_TEST)) err = mmc_compare_ext_csds(card, - ext_csd, bus_width); else err = mmc_bus_test(card, bus_width); diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index ff27741..633975f 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -409,52 +409,62 @@ out: static int sd_select_driver_type(struct mmc_card *card, u8 *status) { - int host_drv_type = 0, card_drv_type = 0; + int host_drv_type = SD_DRIVER_TYPE_B; + int card_drv_type = SD_DRIVER_TYPE_B; + int drive_strength; int err; /* * If the host doesn't support any of the Driver Types A,C or D, - * default Driver Type B is used. + * or there is no board specific handler then default Driver + * Type B is used. */ if (!(card->host->caps & (MMC_CAP_DRIVER_TYPE_A | MMC_CAP_DRIVER_TYPE_C | MMC_CAP_DRIVER_TYPE_D))) return 0; - if (card->host->caps & MMC_CAP_DRIVER_TYPE_A) { - host_drv_type = MMC_SET_DRIVER_TYPE_A; - if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A) - card_drv_type = MMC_SET_DRIVER_TYPE_A; - else if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_B) - card_drv_type = MMC_SET_DRIVER_TYPE_B; - else if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C) - card_drv_type = MMC_SET_DRIVER_TYPE_C; - } else if (card->host->caps & MMC_CAP_DRIVER_TYPE_C) { - host_drv_type = MMC_SET_DRIVER_TYPE_C; - if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C) - card_drv_type = MMC_SET_DRIVER_TYPE_C; - } else if (!(card->host->caps & MMC_CAP_DRIVER_TYPE_D)) { - /* - * If we are here, that means only the default driver type - * B is supported by the host. - */ - host_drv_type = MMC_SET_DRIVER_TYPE_B; - if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_B) - card_drv_type = MMC_SET_DRIVER_TYPE_B; - else if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C) - card_drv_type = MMC_SET_DRIVER_TYPE_C; - } + if (!card->host->ops->select_drive_strength) + return 0; + + if (card->host->caps & MMC_CAP_DRIVER_TYPE_A) + host_drv_type |= SD_DRIVER_TYPE_A; + + if (card->host->caps & MMC_CAP_DRIVER_TYPE_C) + host_drv_type |= SD_DRIVER_TYPE_C; + + if (card->host->caps & MMC_CAP_DRIVER_TYPE_D) + host_drv_type |= SD_DRIVER_TYPE_D; + + if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_A) + card_drv_type |= SD_DRIVER_TYPE_A; + + if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_C) + card_drv_type |= SD_DRIVER_TYPE_C; + + if (card->sw_caps.sd3_drv_type & SD_DRIVER_TYPE_D) + card_drv_type |= SD_DRIVER_TYPE_D; + + /* + * The drive strength that the hardware can support + * depends on the board design. Pass the appropriate + * information and let the hardware specific code + * return what is possible given the options + */ + drive_strength = card->host->ops->select_drive_strength( + card->sw_caps.uhs_max_dtr, + host_drv_type, card_drv_type); - err = mmc_sd_switch(card, 1, 2, card_drv_type, status); + err = mmc_sd_switch(card, 1, 2, drive_strength, status); if (err) return err; - if ((status[15] & 0xF) != card_drv_type) { - printk(KERN_WARNING "%s: Problem setting driver strength!\n", + if ((status[15] & 0xF) != drive_strength) { + printk(KERN_WARNING "%s: Problem setting drive strength!\n", mmc_hostname(card->host)); return 0; } - mmc_set_driver_type(card->host, host_drv_type); + mmc_set_driver_type(card->host, drive_strength); return 0; } diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 4d0c15b..262fff0 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -691,15 +691,54 @@ static int mmc_sdio_resume(struct mmc_host *host) static int mmc_sdio_power_restore(struct mmc_host *host) { int ret; + u32 ocr; BUG_ON(!host); BUG_ON(!host->card); mmc_claim_host(host); + + /* + * Reset the card by performing the same steps that are taken by + * mmc_rescan_try_freq() and mmc_attach_sdio() during a "normal" probe. + * + * sdio_reset() is technically not needed. Having just powered up the + * hardware, it should already be in reset state. However, some + * platforms (such as SD8686 on OLPC) do not instantly cut power, + * meaning that a reset is required when restoring power soon after + * powering off. It is harmless in other cases. + * + * The CMD5 reset (mmc_send_io_op_cond()), according to the SDIO spec, + * is not necessary for non-removable cards. However, it is required + * for OLPC SD8686 (which expects a [CMD5,5,3,7] init sequence), and + * harmless in other situations. + * + * With these steps taken, mmc_select_voltage() is also required to + * restore the correct voltage setting of the card. + */ + sdio_reset(host); + mmc_go_idle(host); + mmc_send_if_cond(host, host->ocr_avail); + + ret = mmc_send_io_op_cond(host, 0, &ocr); + if (ret) + goto out; + + if (host->ocr_avail_sdio) + host->ocr_avail = host->ocr_avail_sdio; + + host->ocr = mmc_select_voltage(host, ocr & ~0x7F); + if (!host->ocr) { + ret = -EINVAL; + goto out; + } + ret = mmc_sdio_init_card(host, host->ocr, host->card, mmc_card_keep_power(host)); if (!ret && host->sdio_irqs) mmc_signal_sdio_irq(host); + +out: mmc_release_host(host); return ret; diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index d29b9c3..e4e6822 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -167,11 +167,8 @@ static int sdio_bus_remove(struct device *dev) int ret = 0; /* Make sure card is powered before invoking ->remove() */ - if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD) { - ret = pm_runtime_get_sync(dev); - if (ret < 0) - goto out; - } + if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD) + pm_runtime_get_sync(dev); drv->remove(func); @@ -189,9 +186,8 @@ static int sdio_bus_remove(struct device *dev) /* Then undo the runtime PM settings in sdio_bus_probe() */ if (func->card->host->caps & MMC_CAP_POWER_OFF_CARD) - pm_runtime_put_noidle(dev); + pm_runtime_put_sync(dev); -out: return ret; } diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 56dbf3f..8c87096 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -81,28 +81,32 @@ config MMC_RICOH_MMC If unsure, say Y. -config MMC_SDHCI_OF - tristate "SDHCI support on OpenFirmware platforms" - depends on MMC_SDHCI && OF +config MMC_SDHCI_PLTFM + tristate "SDHCI platform and OF driver helper" + depends on MMC_SDHCI help - This selects the OF support for Secure Digital Host Controller - Interfaces. + This selects the common helper functions support for Secure Digital + Host Controller Interface based platform and OF drivers. + + If you have a controller with this interface, say Y or M here. If unsure, say N. config MMC_SDHCI_OF_ESDHC - bool "SDHCI OF support for the Freescale eSDHC controller" - depends on MMC_SDHCI_OF + tristate "SDHCI OF support for the Freescale eSDHC controller" + depends on MMC_SDHCI_PLTFM depends on PPC_OF select MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER help This selects the Freescale eSDHC controller support. + If you have a controller with this interface, say Y or M here. + If unsure, say N. config MMC_SDHCI_OF_HLWD - bool "SDHCI OF support for the Nintendo Wii SDHCI controllers" - depends on MMC_SDHCI_OF + tristate "SDHCI OF support for the Nintendo Wii SDHCI controllers" + depends on MMC_SDHCI_PLTFM depends on PPC_OF select MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER help @@ -110,40 +114,36 @@ config MMC_SDHCI_OF_HLWD found in the "Hollywood" chipset of the Nintendo Wii video game console. - If unsure, say N. - -config MMC_SDHCI_PLTFM - tristate "SDHCI support on the platform specific bus" - depends on MMC_SDHCI - help - This selects the platform specific bus support for Secure Digital Host - Controller Interface. - If you have a controller with this interface, say Y or M here. If unsure, say N. config MMC_SDHCI_CNS3XXX - bool "SDHCI support on the Cavium Networks CNS3xxx SoC" + tristate "SDHCI support on the Cavium Networks CNS3xxx SoC" depends on ARCH_CNS3XXX depends on MMC_SDHCI_PLTFM help This selects the SDHCI support for CNS3xxx System-on-Chip devices. + If you have a controller with this interface, say Y or M here. + If unsure, say N. config MMC_SDHCI_ESDHC_IMX - bool "SDHCI platform support for the Freescale eSDHC i.MX controller" - depends on MMC_SDHCI_PLTFM && (ARCH_MX25 || ARCH_MX35 || ARCH_MX5) + tristate "SDHCI platform support for the Freescale eSDHC i.MX controller" + depends on ARCH_MX25 || ARCH_MX35 || ARCH_MX5 + depends on MMC_SDHCI_PLTFM select MMC_SDHCI_IO_ACCESSORS help This selects the Freescale eSDHC controller support on the platform bus, found on platforms like mx35/51. + If you have a controller with this interface, say Y or M here. + If unsure, say N. config MMC_SDHCI_DOVE - bool "SDHCI support on Marvell's Dove SoC" + tristate "SDHCI support on Marvell's Dove SoC" depends on ARCH_DOVE depends on MMC_SDHCI_PLTFM select MMC_SDHCI_IO_ACCESSORS @@ -151,11 +151,14 @@ config MMC_SDHCI_DOVE This selects the Secure Digital Host Controller Interface in Marvell's Dove SoC. + If you have a controller with this interface, say Y or M here. + If unsure, say N. config MMC_SDHCI_TEGRA - bool "SDHCI platform support for the Tegra SD/MMC Controller" - depends on MMC_SDHCI_PLTFM && ARCH_TEGRA + tristate "SDHCI platform support for the Tegra SD/MMC Controller" + depends on ARCH_TEGRA + depends on MMC_SDHCI_PLTFM select MMC_SDHCI_IO_ACCESSORS help This selects the Tegra SD/MMC controller. If you have a Tegra @@ -178,14 +181,28 @@ config MMC_SDHCI_S3C If unsure, say N. -config MMC_SDHCI_PXA - tristate "Marvell PXA168/PXA910/MMP2 SD Host Controller support" - depends on ARCH_PXA || ARCH_MMP +config MMC_SDHCI_PXAV3 + tristate "Marvell MMP2 SD Host Controller support (PXAV3)" + depends on CLKDEV_LOOKUP select MMC_SDHCI - select MMC_SDHCI_IO_ACCESSORS + select MMC_SDHCI_PLTFM + default CPU_MMP2 + help + This selects the Marvell(R) PXAV3 SD Host Controller. + If you have a MMP2 platform with SD Host Controller + and a card slot, say Y or M here. + + If unsure, say N. + +config MMC_SDHCI_PXAV2 + tristate "Marvell PXA9XX SD Host Controller support (PXAV2)" + depends on CLKDEV_LOOKUP + select MMC_SDHCI + select MMC_SDHCI_PLTFM + default CPU_PXA910 help - This selects the Marvell(R) PXA168/PXA910/MMP2 SD Host Controller. - If you have a PXA168/PXA910/MMP2 platform with SD Host Controller + This selects the Marvell(R) PXAV2 SD Host Controller. + If you have a PXA9XX platform with SD Host Controller and a card slot, say Y or M here. If unsure, say N. @@ -281,13 +298,12 @@ config MMC_ATMELMCI endchoice config MMC_ATMELMCI_DMA - bool "Atmel MCI DMA support (EXPERIMENTAL)" - depends on MMC_ATMELMCI && (AVR32 || ARCH_AT91SAM9G45) && DMA_ENGINE && EXPERIMENTAL + bool "Atmel MCI DMA support" + depends on MMC_ATMELMCI && (AVR32 || ARCH_AT91SAM9G45) && DMA_ENGINE help Say Y here to have the Atmel MCI driver use a DMA engine to do data transfers and thus increase the throughput and - reduce the CPU utilization. Note that this is highly - experimental and may cause the driver to lock up. + reduce the CPU utilization. If unsure, say N. diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile index 58a5cf7..b4b83f3 100644 --- a/drivers/mmc/host/Makefile +++ b/drivers/mmc/host/Makefile @@ -9,7 +9,8 @@ obj-$(CONFIG_MMC_MXC) += mxcmmc.o obj-$(CONFIG_MMC_MXS) += mxs-mmc.o obj-$(CONFIG_MMC_SDHCI) += sdhci.o obj-$(CONFIG_MMC_SDHCI_PCI) += sdhci-pci.o -obj-$(CONFIG_MMC_SDHCI_PXA) += sdhci-pxa.o +obj-$(CONFIG_MMC_SDHCI_PXAV3) += sdhci-pxav3.o +obj-$(CONFIG_MMC_SDHCI_PXAV2) += sdhci-pxav2.o obj-$(CONFIG_MMC_SDHCI_S3C) += sdhci-s3c.o obj-$(CONFIG_MMC_SDHCI_SPEAR) += sdhci-spear.o obj-$(CONFIG_MMC_WBSD) += wbsd.o @@ -31,9 +32,7 @@ obj-$(CONFIG_MMC_SDRICOH_CS) += sdricoh_cs.o obj-$(CONFIG_MMC_TMIO) += tmio_mmc.o obj-$(CONFIG_MMC_TMIO_CORE) += tmio_mmc_core.o tmio_mmc_core-y := tmio_mmc_pio.o -ifneq ($(CONFIG_MMC_SDHI),n) -tmio_mmc_core-y += tmio_mmc_dma.o -endif +tmio_mmc_core-$(subst m,y,$(CONFIG_MMC_SDHI)) += tmio_mmc_dma.o obj-$(CONFIG_MMC_SDHI) += sh_mobile_sdhi.o obj-$(CONFIG_MMC_CB710) += cb710-mmc.o obj-$(CONFIG_MMC_VIA_SDMMC) += via-sdmmc.o @@ -44,17 +43,13 @@ obj-$(CONFIG_MMC_JZ4740) += jz4740_mmc.o obj-$(CONFIG_MMC_VUB300) += vub300.o obj-$(CONFIG_MMC_USHC) += ushc.o -obj-$(CONFIG_MMC_SDHCI_PLTFM) += sdhci-platform.o -sdhci-platform-y := sdhci-pltfm.o -sdhci-platform-$(CONFIG_MMC_SDHCI_CNS3XXX) += sdhci-cns3xxx.o -sdhci-platform-$(CONFIG_MMC_SDHCI_ESDHC_IMX) += sdhci-esdhc-imx.o -sdhci-platform-$(CONFIG_MMC_SDHCI_DOVE) += sdhci-dove.o -sdhci-platform-$(CONFIG_MMC_SDHCI_TEGRA) += sdhci-tegra.o - -obj-$(CONFIG_MMC_SDHCI_OF) += sdhci-of.o -sdhci-of-y := sdhci-of-core.o -sdhci-of-$(CONFIG_MMC_SDHCI_OF_ESDHC) += sdhci-of-esdhc.o -sdhci-of-$(CONFIG_MMC_SDHCI_OF_HLWD) += sdhci-of-hlwd.o +obj-$(CONFIG_MMC_SDHCI_PLTFM) += sdhci-pltfm.o +obj-$(CONFIG_MMC_SDHCI_CNS3XXX) += sdhci-cns3xxx.o +obj-$(CONFIG_MMC_SDHCI_ESDHC_IMX) += sdhci-esdhc-imx.o +obj-$(CONFIG_MMC_SDHCI_DOVE) += sdhci-dove.o +obj-$(CONFIG_MMC_SDHCI_TEGRA) += sdhci-tegra.o +obj-$(CONFIG_MMC_SDHCI_OF_ESDHC) += sdhci-of-esdhc.o +obj-$(CONFIG_MMC_SDHCI_OF_HLWD) += sdhci-of-hlwd.o ifeq ($(CONFIG_CB710_DEBUG),y) CFLAGS-cb710-mmc += -DDEBUG diff --git a/drivers/mmc/host/at91_mci.c b/drivers/mmc/host/at91_mci.c index d3e6a96..a4aa3af 100644 --- a/drivers/mmc/host/at91_mci.c +++ b/drivers/mmc/host/at91_mci.c @@ -77,7 +77,8 @@ #include <mach/board.h> #include <mach/cpu.h> -#include <mach/at91_mci.h> + +#include "at91_mci.h" #define DRIVER_NAME "at91_mci" diff --git a/arch/arm/mach-at91/include/mach/at91_mci.h b/drivers/mmc/host/at91_mci.h index 02182c1..eec3a6b 100644 --- a/arch/arm/mach-at91/include/mach/at91_mci.h +++ b/drivers/mmc/host/at91_mci.h @@ -1,5 +1,5 @@ /* - * arch/arm/mach-at91/include/mach/at91_mci.h + * drivers/mmc/host/at91_mci.h * * Copyright (C) 2005 Ivan Kokshaysky * Copyright (C) SAN People diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index aa8039f..fa8cae1 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -203,6 +203,7 @@ struct atmel_mci_slot { #define ATMCI_CARD_PRESENT 0 #define ATMCI_CARD_NEED_INIT 1 #define ATMCI_SHUTDOWN 2 +#define ATMCI_SUSPENDED 3 int detect_pin; int wp_pin; @@ -1878,10 +1879,72 @@ static int __exit atmci_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM +static int atmci_suspend(struct device *dev) +{ + struct atmel_mci *host = dev_get_drvdata(dev); + int i; + + for (i = 0; i < ATMEL_MCI_MAX_NR_SLOTS; i++) { + struct atmel_mci_slot *slot = host->slot[i]; + int ret; + + if (!slot) + continue; + ret = mmc_suspend_host(slot->mmc); + if (ret < 0) { + while (--i >= 0) { + slot = host->slot[i]; + if (slot + && test_bit(ATMCI_SUSPENDED, &slot->flags)) { + mmc_resume_host(host->slot[i]->mmc); + clear_bit(ATMCI_SUSPENDED, &slot->flags); + } + } + return ret; + } else { + set_bit(ATMCI_SUSPENDED, &slot->flags); + } + } + + return 0; +} + +static int atmci_resume(struct device *dev) +{ + struct atmel_mci *host = dev_get_drvdata(dev); + int i; + int ret = 0; + + for (i = 0; i < ATMEL_MCI_MAX_NR_SLOTS; i++) { + struct atmel_mci_slot *slot = host->slot[i]; + int err; + + slot = host->slot[i]; + if (!slot) + continue; + if (!test_bit(ATMCI_SUSPENDED, &slot->flags)) + continue; + err = mmc_resume_host(slot->mmc); + if (err < 0) + ret = err; + else + clear_bit(ATMCI_SUSPENDED, &slot->flags); + } + + return ret; +} +static SIMPLE_DEV_PM_OPS(atmci_pm, atmci_suspend, atmci_resume); +#define ATMCI_PM_OPS (&atmci_pm) +#else +#define ATMCI_PM_OPS NULL +#endif + static struct platform_driver atmci_driver = { .remove = __exit_p(atmci_remove), .driver = { .name = "atmel_mci", + .pm = ATMCI_PM_OPS, }, }; diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c index 66dcddb..0c839d3 100644 --- a/drivers/mmc/host/dw_mmc.c +++ b/drivers/mmc/host/dw_mmc.c @@ -33,6 +33,7 @@ #include <linux/mmc/dw_mmc.h> #include <linux/bitops.h> #include <linux/regulator/consumer.h> +#include <linux/workqueue.h> #include "dw_mmc.h" @@ -100,6 +101,8 @@ struct dw_mci_slot { int last_detect_state; }; +static struct workqueue_struct *dw_mci_card_workqueue; + #if defined(CONFIG_DEBUG_FS) static int dw_mci_req_show(struct seq_file *s, void *v) { @@ -284,7 +287,7 @@ static void send_stop_cmd(struct dw_mci *host, struct mmc_data *data) /* DMA interface functions */ static void dw_mci_stop_dma(struct dw_mci *host) { - if (host->use_dma) { + if (host->using_dma) { host->dma_ops->stop(host); host->dma_ops->cleanup(host); } else { @@ -432,6 +435,8 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data) unsigned int i, direction, sg_len; u32 temp; + host->using_dma = 0; + /* If we don't have a channel, we can't do DMA */ if (!host->use_dma) return -ENODEV; @@ -451,6 +456,8 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data) return -EINVAL; } + host->using_dma = 1; + if (data->flags & MMC_DATA_READ) direction = DMA_FROM_DEVICE; else @@ -489,14 +496,18 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data) host->sg = NULL; host->data = data; + if (data->flags & MMC_DATA_READ) + host->dir_status = DW_MCI_RECV_STATUS; + else + host->dir_status = DW_MCI_SEND_STATUS; + if (dw_mci_submit_data_dma(host, data)) { host->sg = data->sg; host->pio_offset = 0; - if (data->flags & MMC_DATA_READ) - host->dir_status = DW_MCI_RECV_STATUS; - else - host->dir_status = DW_MCI_SEND_STATUS; + host->part_buf_start = 0; + host->part_buf_count = 0; + mci_writel(host, RINTSTS, SDMMC_INT_TXDR | SDMMC_INT_RXDR); temp = mci_readl(host, INTMASK); temp |= SDMMC_INT_TXDR | SDMMC_INT_RXDR; mci_writel(host, INTMASK, temp); @@ -574,7 +585,7 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot) } /* Set the current slot bus width */ - mci_writel(host, CTYPE, slot->ctype); + mci_writel(host, CTYPE, (slot->ctype << slot->id)); } static void dw_mci_start_request(struct dw_mci *host, @@ -624,13 +635,13 @@ static void dw_mci_start_request(struct dw_mci *host, host->stop_cmdr = dw_mci_prepare_command(slot->mmc, mrq->stop); } +/* must be called with host->lock held */ static void dw_mci_queue_request(struct dw_mci *host, struct dw_mci_slot *slot, struct mmc_request *mrq) { dev_vdbg(&slot->mmc->class_dev, "queue request: state=%d\n", host->state); - spin_lock_bh(&host->lock); slot->mrq = mrq; if (host->state == STATE_IDLE) { @@ -639,8 +650,6 @@ static void dw_mci_queue_request(struct dw_mci *host, struct dw_mci_slot *slot, } else { list_add_tail(&slot->queue_node, &host->queue); } - - spin_unlock_bh(&host->lock); } static void dw_mci_request(struct mmc_host *mmc, struct mmc_request *mrq) @@ -650,14 +659,23 @@ static void dw_mci_request(struct mmc_host *mmc, struct mmc_request *mrq) WARN_ON(slot->mrq); + /* + * The check for card presence and queueing of the request must be + * atomic, otherwise the card could be removed in between and the + * request wouldn't fail until another card was inserted. + */ + spin_lock_bh(&host->lock); + if (!test_bit(DW_MMC_CARD_PRESENT, &slot->flags)) { + spin_unlock_bh(&host->lock); mrq->cmd->error = -ENOMEDIUM; mmc_request_done(mmc, mrq); return; } - /* We don't support multiple blocks of weird lengths. */ dw_mci_queue_request(host, slot, mrq); + + spin_unlock_bh(&host->lock); } static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) @@ -831,7 +849,7 @@ static void dw_mci_tasklet_func(unsigned long priv) struct mmc_command *cmd; enum dw_mci_state state; enum dw_mci_state prev_state; - u32 status; + u32 status, ctrl; spin_lock(&host->lock); @@ -891,13 +909,19 @@ static void dw_mci_tasklet_func(unsigned long priv) if (status & DW_MCI_DATA_ERROR_FLAGS) { if (status & SDMMC_INT_DTO) { - dev_err(&host->pdev->dev, - "data timeout error\n"); data->error = -ETIMEDOUT; } else if (status & SDMMC_INT_DCRC) { - dev_err(&host->pdev->dev, - "data CRC error\n"); data->error = -EILSEQ; + } else if (status & SDMMC_INT_EBE && + host->dir_status == + DW_MCI_SEND_STATUS) { + /* + * No data CRC status was returned. + * The number of bytes transferred will + * be exaggerated in PIO mode. + */ + data->bytes_xfered = 0; + data->error = -ETIMEDOUT; } else { dev_err(&host->pdev->dev, "data FIFO error " @@ -905,6 +929,16 @@ static void dw_mci_tasklet_func(unsigned long priv) status); data->error = -EIO; } + /* + * After an error, there may be data lingering + * in the FIFO, so reset it - doing so + * generates a block interrupt, hence setting + * the scatter-gather pointer to NULL. + */ + host->sg = NULL; + ctrl = mci_readl(host, CTRL); + ctrl |= SDMMC_CTRL_FIFO_RESET; + mci_writel(host, CTRL, ctrl); } else { data->bytes_xfered = data->blocks * data->blksz; data->error = 0; @@ -946,84 +980,278 @@ unlock: } -static void dw_mci_push_data16(struct dw_mci *host, void *buf, int cnt) +/* push final bytes to part_buf, only use during push */ +static void dw_mci_set_part_bytes(struct dw_mci *host, void *buf, int cnt) { - u16 *pdata = (u16 *)buf; + memcpy((void *)&host->part_buf, buf, cnt); + host->part_buf_count = cnt; +} - WARN_ON(cnt % 2 != 0); +/* append bytes to part_buf, only use during push */ +static int dw_mci_push_part_bytes(struct dw_mci *host, void *buf, int cnt) +{ + cnt = min(cnt, (1 << host->data_shift) - host->part_buf_count); + memcpy((void *)&host->part_buf + host->part_buf_count, buf, cnt); + host->part_buf_count += cnt; + return cnt; +} - cnt = cnt >> 1; - while (cnt > 0) { - mci_writew(host, DATA, *pdata++); - cnt--; +/* pull first bytes from part_buf, only use during pull */ +static int dw_mci_pull_part_bytes(struct dw_mci *host, void *buf, int cnt) +{ + cnt = min(cnt, (int)host->part_buf_count); + if (cnt) { + memcpy(buf, (void *)&host->part_buf + host->part_buf_start, + cnt); + host->part_buf_count -= cnt; + host->part_buf_start += cnt; } + return cnt; } -static void dw_mci_pull_data16(struct dw_mci *host, void *buf, int cnt) +/* pull final bytes from the part_buf, assuming it's just been filled */ +static void dw_mci_pull_final_bytes(struct dw_mci *host, void *buf, int cnt) { - u16 *pdata = (u16 *)buf; + memcpy(buf, &host->part_buf, cnt); + host->part_buf_start = cnt; + host->part_buf_count = (1 << host->data_shift) - cnt; +} - WARN_ON(cnt % 2 != 0); +static void dw_mci_push_data16(struct dw_mci *host, void *buf, int cnt) +{ + /* try and push anything in the part_buf */ + if (unlikely(host->part_buf_count)) { + int len = dw_mci_push_part_bytes(host, buf, cnt); + buf += len; + cnt -= len; + if (!sg_next(host->sg) || host->part_buf_count == 2) { + mci_writew(host, DATA, host->part_buf16); + host->part_buf_count = 0; + } + } +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (unlikely((unsigned long)buf & 0x1)) { + while (cnt >= 2) { + u16 aligned_buf[64]; + int len = min(cnt & -2, (int)sizeof(aligned_buf)); + int items = len >> 1; + int i; + /* memcpy from input buffer into aligned buffer */ + memcpy(aligned_buf, buf, len); + buf += len; + cnt -= len; + /* push data from aligned buffer into fifo */ + for (i = 0; i < items; ++i) + mci_writew(host, DATA, aligned_buf[i]); + } + } else +#endif + { + u16 *pdata = buf; + for (; cnt >= 2; cnt -= 2) + mci_writew(host, DATA, *pdata++); + buf = pdata; + } + /* put anything remaining in the part_buf */ + if (cnt) { + dw_mci_set_part_bytes(host, buf, cnt); + if (!sg_next(host->sg)) + mci_writew(host, DATA, host->part_buf16); + } +} - cnt = cnt >> 1; - while (cnt > 0) { - *pdata++ = mci_readw(host, DATA); - cnt--; +static void dw_mci_pull_data16(struct dw_mci *host, void *buf, int cnt) +{ +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (unlikely((unsigned long)buf & 0x1)) { + while (cnt >= 2) { + /* pull data from fifo into aligned buffer */ + u16 aligned_buf[64]; + int len = min(cnt & -2, (int)sizeof(aligned_buf)); + int items = len >> 1; + int i; + for (i = 0; i < items; ++i) + aligned_buf[i] = mci_readw(host, DATA); + /* memcpy from aligned buffer into output buffer */ + memcpy(buf, aligned_buf, len); + buf += len; + cnt -= len; + } + } else +#endif + { + u16 *pdata = buf; + for (; cnt >= 2; cnt -= 2) + *pdata++ = mci_readw(host, DATA); + buf = pdata; + } + if (cnt) { + host->part_buf16 = mci_readw(host, DATA); + dw_mci_pull_final_bytes(host, buf, cnt); } } static void dw_mci_push_data32(struct dw_mci *host, void *buf, int cnt) { - u32 *pdata = (u32 *)buf; - - WARN_ON(cnt % 4 != 0); - WARN_ON((unsigned long)pdata & 0x3); - - cnt = cnt >> 2; - while (cnt > 0) { - mci_writel(host, DATA, *pdata++); - cnt--; + /* try and push anything in the part_buf */ + if (unlikely(host->part_buf_count)) { + int len = dw_mci_push_part_bytes(host, buf, cnt); + buf += len; + cnt -= len; + if (!sg_next(host->sg) || host->part_buf_count == 4) { + mci_writel(host, DATA, host->part_buf32); + host->part_buf_count = 0; + } + } +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (unlikely((unsigned long)buf & 0x3)) { + while (cnt >= 4) { + u32 aligned_buf[32]; + int len = min(cnt & -4, (int)sizeof(aligned_buf)); + int items = len >> 2; + int i; + /* memcpy from input buffer into aligned buffer */ + memcpy(aligned_buf, buf, len); + buf += len; + cnt -= len; + /* push data from aligned buffer into fifo */ + for (i = 0; i < items; ++i) + mci_writel(host, DATA, aligned_buf[i]); + } + } else +#endif + { + u32 *pdata = buf; + for (; cnt >= 4; cnt -= 4) + mci_writel(host, DATA, *pdata++); + buf = pdata; + } + /* put anything remaining in the part_buf */ + if (cnt) { + dw_mci_set_part_bytes(host, buf, cnt); + if (!sg_next(host->sg)) + mci_writel(host, DATA, host->part_buf32); } } static void dw_mci_pull_data32(struct dw_mci *host, void *buf, int cnt) { - u32 *pdata = (u32 *)buf; - - WARN_ON(cnt % 4 != 0); - WARN_ON((unsigned long)pdata & 0x3); - - cnt = cnt >> 2; - while (cnt > 0) { - *pdata++ = mci_readl(host, DATA); - cnt--; +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (unlikely((unsigned long)buf & 0x3)) { + while (cnt >= 4) { + /* pull data from fifo into aligned buffer */ + u32 aligned_buf[32]; + int len = min(cnt & -4, (int)sizeof(aligned_buf)); + int items = len >> 2; + int i; + for (i = 0; i < items; ++i) + aligned_buf[i] = mci_readl(host, DATA); + /* memcpy from aligned buffer into output buffer */ + memcpy(buf, aligned_buf, len); + buf += len; + cnt -= len; + } + } else +#endif + { + u32 *pdata = buf; + for (; cnt >= 4; cnt -= 4) + *pdata++ = mci_readl(host, DATA); + buf = pdata; + } + if (cnt) { + host->part_buf32 = mci_readl(host, DATA); + dw_mci_pull_final_bytes(host, buf, cnt); } } static void dw_mci_push_data64(struct dw_mci *host, void *buf, int cnt) { - u64 *pdata = (u64 *)buf; - - WARN_ON(cnt % 8 != 0); - - cnt = cnt >> 3; - while (cnt > 0) { - mci_writeq(host, DATA, *pdata++); - cnt--; + /* try and push anything in the part_buf */ + if (unlikely(host->part_buf_count)) { + int len = dw_mci_push_part_bytes(host, buf, cnt); + buf += len; + cnt -= len; + if (!sg_next(host->sg) || host->part_buf_count == 8) { + mci_writew(host, DATA, host->part_buf); + host->part_buf_count = 0; + } + } +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (unlikely((unsigned long)buf & 0x7)) { + while (cnt >= 8) { + u64 aligned_buf[16]; + int len = min(cnt & -8, (int)sizeof(aligned_buf)); + int items = len >> 3; + int i; + /* memcpy from input buffer into aligned buffer */ + memcpy(aligned_buf, buf, len); + buf += len; + cnt -= len; + /* push data from aligned buffer into fifo */ + for (i = 0; i < items; ++i) + mci_writeq(host, DATA, aligned_buf[i]); + } + } else +#endif + { + u64 *pdata = buf; + for (; cnt >= 8; cnt -= 8) + mci_writeq(host, DATA, *pdata++); + buf = pdata; + } + /* put anything remaining in the part_buf */ + if (cnt) { + dw_mci_set_part_bytes(host, buf, cnt); + if (!sg_next(host->sg)) + mci_writeq(host, DATA, host->part_buf); } } static void dw_mci_pull_data64(struct dw_mci *host, void *buf, int cnt) { - u64 *pdata = (u64 *)buf; +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + if (unlikely((unsigned long)buf & 0x7)) { + while (cnt >= 8) { + /* pull data from fifo into aligned buffer */ + u64 aligned_buf[16]; + int len = min(cnt & -8, (int)sizeof(aligned_buf)); + int items = len >> 3; + int i; + for (i = 0; i < items; ++i) + aligned_buf[i] = mci_readq(host, DATA); + /* memcpy from aligned buffer into output buffer */ + memcpy(buf, aligned_buf, len); + buf += len; + cnt -= len; + } + } else +#endif + { + u64 *pdata = buf; + for (; cnt >= 8; cnt -= 8) + *pdata++ = mci_readq(host, DATA); + buf = pdata; + } + if (cnt) { + host->part_buf = mci_readq(host, DATA); + dw_mci_pull_final_bytes(host, buf, cnt); + } +} - WARN_ON(cnt % 8 != 0); +static void dw_mci_pull_data(struct dw_mci *host, void *buf, int cnt) +{ + int len; - cnt = cnt >> 3; - while (cnt > 0) { - *pdata++ = mci_readq(host, DATA); - cnt--; - } + /* get remaining partial bytes */ + len = dw_mci_pull_part_bytes(host, buf, cnt); + if (unlikely(len == cnt)) + return; + buf += len; + cnt -= len; + + /* get the rest of the data */ + host->pull_data(host, buf, cnt); } static void dw_mci_read_data_pio(struct dw_mci *host) @@ -1037,9 +1265,10 @@ static void dw_mci_read_data_pio(struct dw_mci *host) unsigned int nbytes = 0, len; do { - len = SDMMC_GET_FCNT(mci_readl(host, STATUS)) << shift; + len = host->part_buf_count + + (SDMMC_GET_FCNT(mci_readl(host, STATUS)) << shift); if (offset + len <= sg->length) { - host->pull_data(host, (void *)(buf + offset), len); + dw_mci_pull_data(host, (void *)(buf + offset), len); offset += len; nbytes += len; @@ -1055,8 +1284,8 @@ static void dw_mci_read_data_pio(struct dw_mci *host) } } else { unsigned int remaining = sg->length - offset; - host->pull_data(host, (void *)(buf + offset), - remaining); + dw_mci_pull_data(host, (void *)(buf + offset), + remaining); nbytes += remaining; flush_dcache_page(sg_page(sg)); @@ -1066,7 +1295,7 @@ static void dw_mci_read_data_pio(struct dw_mci *host) offset = len - remaining; buf = sg_virt(sg); - host->pull_data(host, buf, offset); + dw_mci_pull_data(host, buf, offset); nbytes += offset; } @@ -1083,7 +1312,6 @@ static void dw_mci_read_data_pio(struct dw_mci *host) return; } } while (status & SDMMC_INT_RXDR); /*if the RXDR is ready read again*/ - len = SDMMC_GET_FCNT(mci_readl(host, STATUS)); host->pio_offset = offset; data->bytes_xfered += nbytes; return; @@ -1105,8 +1333,9 @@ static void dw_mci_write_data_pio(struct dw_mci *host) unsigned int nbytes = 0, len; do { - len = SDMMC_FIFO_SZ - - (SDMMC_GET_FCNT(mci_readl(host, STATUS)) << shift); + len = ((host->fifo_depth - + SDMMC_GET_FCNT(mci_readl(host, STATUS))) << shift) + - host->part_buf_count; if (offset + len <= sg->length) { host->push_data(host, (void *)(buf + offset), len); @@ -1151,10 +1380,8 @@ static void dw_mci_write_data_pio(struct dw_mci *host) return; } } while (status & SDMMC_INT_TXDR); /* if TXDR write again */ - host->pio_offset = offset; data->bytes_xfered += nbytes; - return; done: @@ -1202,7 +1429,6 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) host->cmd_status = status; smp_wmb(); set_bit(EVENT_CMD_COMPLETE, &host->pending_events); - tasklet_schedule(&host->tasklet); } if (pending & DW_MCI_DATA_ERROR_FLAGS) { @@ -1211,7 +1437,9 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) host->data_status = status; smp_wmb(); set_bit(EVENT_DATA_ERROR, &host->pending_events); - tasklet_schedule(&host->tasklet); + if (!(pending & (SDMMC_INT_DTO | SDMMC_INT_DCRC | + SDMMC_INT_SBE | SDMMC_INT_EBE))) + tasklet_schedule(&host->tasklet); } if (pending & SDMMC_INT_DATA_OVER) { @@ -1229,13 +1457,13 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) if (pending & SDMMC_INT_RXDR) { mci_writel(host, RINTSTS, SDMMC_INT_RXDR); - if (host->sg) + if (host->dir_status == DW_MCI_RECV_STATUS && host->sg) dw_mci_read_data_pio(host); } if (pending & SDMMC_INT_TXDR) { mci_writel(host, RINTSTS, SDMMC_INT_TXDR); - if (host->sg) + if (host->dir_status == DW_MCI_SEND_STATUS && host->sg) dw_mci_write_data_pio(host); } @@ -1246,7 +1474,7 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) if (pending & SDMMC_INT_CD) { mci_writel(host, RINTSTS, SDMMC_INT_CD); - tasklet_schedule(&host->card_tasklet); + queue_work(dw_mci_card_workqueue, &host->card_work); } } while (pass_count++ < 5); @@ -1265,9 +1493,9 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static void dw_mci_tasklet_card(unsigned long data) +static void dw_mci_work_routine_card(struct work_struct *work) { - struct dw_mci *host = (struct dw_mci *)data; + struct dw_mci *host = container_of(work, struct dw_mci, card_work); int i; for (i = 0; i < host->num_slots; i++) { @@ -1279,22 +1507,21 @@ static void dw_mci_tasklet_card(unsigned long data) present = dw_mci_get_cd(mmc); while (present != slot->last_detect_state) { - spin_lock(&host->lock); - dev_dbg(&slot->mmc->class_dev, "card %s\n", present ? "inserted" : "removed"); + /* Power up slot (before spin_lock, may sleep) */ + if (present != 0 && host->pdata->setpower) + host->pdata->setpower(slot->id, mmc->ocr_avail); + + spin_lock_bh(&host->lock); + /* Card change detected */ slot->last_detect_state = present; - /* Power up slot */ - if (present != 0) { - if (host->pdata->setpower) - host->pdata->setpower(slot->id, - mmc->ocr_avail); - + /* Mark card as present if applicable */ + if (present != 0) set_bit(DW_MMC_CARD_PRESENT, &slot->flags); - } /* Clean up queue if present */ mrq = slot->mrq; @@ -1344,8 +1571,6 @@ static void dw_mci_tasklet_card(unsigned long data) /* Power down slot */ if (present == 0) { - if (host->pdata->setpower) - host->pdata->setpower(slot->id, 0); clear_bit(DW_MMC_CARD_PRESENT, &slot->flags); /* @@ -1367,7 +1592,12 @@ static void dw_mci_tasklet_card(unsigned long data) } - spin_unlock(&host->lock); + spin_unlock_bh(&host->lock); + + /* Power down slot (after spin_unlock, may sleep) */ + if (present == 0 && host->pdata->setpower) + host->pdata->setpower(slot->id, 0); + present = dw_mci_get_cd(mmc); } @@ -1467,7 +1697,7 @@ static int __init dw_mci_init_slot(struct dw_mci *host, unsigned int id) * Card may have been plugged in prior to boot so we * need to run the detect tasklet */ - tasklet_schedule(&host->card_tasklet); + queue_work(dw_mci_card_workqueue, &host->card_work); return 0; } @@ -1645,8 +1875,19 @@ static int dw_mci_probe(struct platform_device *pdev) * FIFO threshold settings RxMark = fifo_size / 2 - 1, * Tx Mark = fifo_size / 2 DMA Size = 8 */ - fifo_size = mci_readl(host, FIFOTH); - fifo_size = (fifo_size >> 16) & 0x7ff; + if (!host->pdata->fifo_depth) { + /* + * Power-on value of RX_WMark is FIFO_DEPTH-1, but this may + * have been overwritten by the bootloader, just like we're + * about to do, so if you know the value for your hardware, you + * should put it in the platform data. + */ + fifo_size = mci_readl(host, FIFOTH); + fifo_size = 1 + ((fifo_size >> 16) & 0x7ff); + } else { + fifo_size = host->pdata->fifo_depth; + } + host->fifo_depth = fifo_size; host->fifoth_val = ((0x2 << 28) | ((fifo_size/2 - 1) << 16) | ((fifo_size/2) << 0)); mci_writel(host, FIFOTH, host->fifoth_val); @@ -1656,12 +1897,15 @@ static int dw_mci_probe(struct platform_device *pdev) mci_writel(host, CLKSRC, 0); tasklet_init(&host->tasklet, dw_mci_tasklet_func, (unsigned long)host); - tasklet_init(&host->card_tasklet, - dw_mci_tasklet_card, (unsigned long)host); + dw_mci_card_workqueue = alloc_workqueue("dw-mci-card", + WQ_MEM_RECLAIM | WQ_NON_REENTRANT, 1); + if (!dw_mci_card_workqueue) + goto err_dmaunmap; + INIT_WORK(&host->card_work, dw_mci_work_routine_card); ret = request_irq(irq, dw_mci_interrupt, 0, "dw-mci", host); if (ret) - goto err_dmaunmap; + goto err_workqueue; platform_set_drvdata(pdev, host); @@ -1690,7 +1934,9 @@ static int dw_mci_probe(struct platform_device *pdev) mci_writel(host, CTRL, SDMMC_CTRL_INT_ENABLE); /* Enable mci interrupt */ dev_info(&pdev->dev, "DW MMC controller at irq %d, " - "%d bit host data width\n", irq, width); + "%d bit host data width, " + "%u deep fifo\n", + irq, width, fifo_size); if (host->quirks & DW_MCI_QUIRK_IDMAC_DTO) dev_info(&pdev->dev, "Internal DMAC interrupt fix enabled.\n"); @@ -1705,6 +1951,9 @@ err_init_slot: } free_irq(irq, host); +err_workqueue: + destroy_workqueue(dw_mci_card_workqueue); + err_dmaunmap: if (host->use_dma && host->dma_ops->exit) host->dma_ops->exit(host); @@ -1744,6 +1993,7 @@ static int __exit dw_mci_remove(struct platform_device *pdev) mci_writel(host, CLKSRC, 0); free_irq(platform_get_irq(pdev, 0), host); + destroy_workqueue(dw_mci_card_workqueue); dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma); if (host->use_dma && host->dma_ops->exit) diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h index 23c662a..027d377 100644 --- a/drivers/mmc/host/dw_mmc.h +++ b/drivers/mmc/host/dw_mmc.h @@ -118,7 +118,6 @@ #define SDMMC_CMD_INDX(n) ((n) & 0x1F) /* Status register defines */ #define SDMMC_GET_FCNT(x) (((x)>>17) & 0x1FF) -#define SDMMC_FIFO_SZ 32 /* Internal DMAC interrupt defines */ #define SDMMC_IDMAC_INT_AI BIT(9) #define SDMMC_IDMAC_INT_NI BIT(8) @@ -134,22 +133,22 @@ /* Register access macros */ #define mci_readl(dev, reg) \ - __raw_readl(dev->regs + SDMMC_##reg) + __raw_readl((dev)->regs + SDMMC_##reg) #define mci_writel(dev, reg, value) \ - __raw_writel((value), dev->regs + SDMMC_##reg) + __raw_writel((value), (dev)->regs + SDMMC_##reg) /* 16-bit FIFO access macros */ #define mci_readw(dev, reg) \ - __raw_readw(dev->regs + SDMMC_##reg) + __raw_readw((dev)->regs + SDMMC_##reg) #define mci_writew(dev, reg, value) \ - __raw_writew((value), dev->regs + SDMMC_##reg) + __raw_writew((value), (dev)->regs + SDMMC_##reg) /* 64-bit FIFO access macros */ #ifdef readq #define mci_readq(dev, reg) \ - __raw_readq(dev->regs + SDMMC_##reg) + __raw_readq((dev)->regs + SDMMC_##reg) #define mci_writeq(dev, reg, value) \ - __raw_writeq((value), dev->regs + SDMMC_##reg) + __raw_writeq((value), (dev)->regs + SDMMC_##reg) #else /* * Dummy readq implementation for architectures that don't define it. @@ -160,9 +159,9 @@ * rest of the code free from ifdefs. */ #define mci_readq(dev, reg) \ - (*(volatile u64 __force *)(dev->regs + SDMMC_##reg)) + (*(volatile u64 __force *)((dev)->regs + SDMMC_##reg)) #define mci_writeq(dev, reg, value) \ - (*(volatile u64 __force *)(dev->regs + SDMMC_##reg) = value) + (*(volatile u64 __force *)((dev)->regs + SDMMC_##reg) = (value)) #endif #endif /* _DW_MMC_H_ */ diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 7721de9..fef7140 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -226,6 +226,9 @@ static void __devinit mmci_dma_setup(struct mmci_host *host) return; } + /* initialize pre request cookie */ + host->next_data.cookie = 1; + /* Try to acquire a generic DMA engine slave channel */ dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); @@ -335,7 +338,8 @@ static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data) dir = DMA_FROM_DEVICE; } - dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir); + if (!data->host_cookie) + dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir); /* * Use of DMA with scatter-gather is impossible. @@ -353,7 +357,8 @@ static void mmci_dma_data_error(struct mmci_host *host) dmaengine_terminate_all(host->dma_current); } -static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) +static int mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data, + struct mmci_host_next *next) { struct variant_data *variant = host->variant; struct dma_slave_config conf = { @@ -364,13 +369,20 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) .src_maxburst = variant->fifohalfsize >> 2, /* # of words */ .dst_maxburst = variant->fifohalfsize >> 2, /* # of words */ }; - struct mmc_data *data = host->data; struct dma_chan *chan; struct dma_device *device; struct dma_async_tx_descriptor *desc; int nr_sg; - host->dma_current = NULL; + /* Check if next job is already prepared */ + if (data->host_cookie && !next && + host->dma_current && host->dma_desc_current) + return 0; + + if (!next) { + host->dma_current = NULL; + host->dma_desc_current = NULL; + } if (data->flags & MMC_DATA_READ) { conf.direction = DMA_FROM_DEVICE; @@ -385,7 +397,7 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) return -EINVAL; /* If less than or equal to the fifo size, don't bother with DMA */ - if (host->size <= variant->fifosize) + if (data->blksz * data->blocks <= variant->fifosize) return -EINVAL; device = chan->device; @@ -399,14 +411,38 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) if (!desc) goto unmap_exit; - /* Okay, go for it. */ - host->dma_current = chan; + if (next) { + next->dma_chan = chan; + next->dma_desc = desc; + } else { + host->dma_current = chan; + host->dma_desc_current = desc; + } + + return 0; + unmap_exit: + if (!next) + dmaengine_terminate_all(chan); + dma_unmap_sg(device->dev, data->sg, data->sg_len, conf.direction); + return -ENOMEM; +} + +static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) +{ + int ret; + struct mmc_data *data = host->data; + + ret = mmci_dma_prep_data(host, host->data, NULL); + if (ret) + return ret; + + /* Okay, go for it. */ dev_vdbg(mmc_dev(host->mmc), "Submit MMCI DMA job, sglen %d blksz %04x blks %04x flags %08x\n", data->sg_len, data->blksz, data->blocks, data->flags); - dmaengine_submit(desc); - dma_async_issue_pending(chan); + dmaengine_submit(host->dma_desc_current); + dma_async_issue_pending(host->dma_current); datactrl |= MCI_DPSM_DMAENABLE; @@ -421,14 +457,90 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl) writel(readl(host->base + MMCIMASK0) | MCI_DATAENDMASK, host->base + MMCIMASK0); return 0; +} -unmap_exit: - dmaengine_terminate_all(chan); - dma_unmap_sg(device->dev, data->sg, data->sg_len, conf.direction); - return -ENOMEM; +static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data) +{ + struct mmci_host_next *next = &host->next_data; + + if (data->host_cookie && data->host_cookie != next->cookie) { + printk(KERN_WARNING "[%s] invalid cookie: data->host_cookie %d" + " host->next_data.cookie %d\n", + __func__, data->host_cookie, host->next_data.cookie); + data->host_cookie = 0; + } + + if (!data->host_cookie) + return; + + host->dma_desc_current = next->dma_desc; + host->dma_current = next->dma_chan; + + next->dma_desc = NULL; + next->dma_chan = NULL; } + +static void mmci_pre_request(struct mmc_host *mmc, struct mmc_request *mrq, + bool is_first_req) +{ + struct mmci_host *host = mmc_priv(mmc); + struct mmc_data *data = mrq->data; + struct mmci_host_next *nd = &host->next_data; + + if (!data) + return; + + if (data->host_cookie) { + data->host_cookie = 0; + return; + } + + /* if config for dma */ + if (((data->flags & MMC_DATA_WRITE) && host->dma_tx_channel) || + ((data->flags & MMC_DATA_READ) && host->dma_rx_channel)) { + if (mmci_dma_prep_data(host, data, nd)) + data->host_cookie = 0; + else + data->host_cookie = ++nd->cookie < 0 ? 1 : nd->cookie; + } +} + +static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq, + int err) +{ + struct mmci_host *host = mmc_priv(mmc); + struct mmc_data *data = mrq->data; + struct dma_chan *chan; + enum dma_data_direction dir; + + if (!data) + return; + + if (data->flags & MMC_DATA_READ) { + dir = DMA_FROM_DEVICE; + chan = host->dma_rx_channel; + } else { + dir = DMA_TO_DEVICE; + chan = host->dma_tx_channel; + } + + + /* if config for dma */ + if (chan) { + if (err) + dmaengine_terminate_all(chan); + if (err || data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, dir); + mrq->data->host_cookie = 0; + } +} + #else /* Blank functions if the DMA engine is not available */ +static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data) +{ +} static inline void mmci_dma_setup(struct mmci_host *host) { } @@ -449,6 +561,10 @@ static inline int mmci_dma_start_data(struct mmci_host *host, unsigned int datac { return -ENOSYS; } + +#define mmci_pre_request NULL +#define mmci_post_request NULL + #endif static void mmci_start_data(struct mmci_host *host, struct mmc_data *data) @@ -582,6 +698,8 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data, data->error = -EILSEQ; } else if (status & MCI_DATATIMEOUT) { data->error = -ETIMEDOUT; + } else if (status & MCI_STARTBITERR) { + data->error = -ECOMM; } else if (status & MCI_TXUNDERRUN) { data->error = -EIO; } else if (status & MCI_RXOVERRUN) { @@ -870,6 +988,9 @@ static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq) host->mrq = mrq; + if (mrq->data) + mmci_get_next_data(host, mrq->data); + if (mrq->data && mrq->data->flags & MMC_DATA_READ) mmci_start_data(host, mrq->data); @@ -984,6 +1105,8 @@ static irqreturn_t mmci_cd_irq(int irq, void *dev_id) static const struct mmc_host_ops mmci_ops = { .request = mmci_request, + .pre_req = mmci_pre_request, + .post_req = mmci_post_request, .set_ios = mmci_set_ios, .get_ro = mmci_get_ro, .get_cd = mmci_get_cd, diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h index bb32e21..79e4143 100644 --- a/drivers/mmc/host/mmci.h +++ b/drivers/mmc/host/mmci.h @@ -86,6 +86,7 @@ #define MCI_CMDRESPEND (1 << 6) #define MCI_CMDSENT (1 << 7) #define MCI_DATAEND (1 << 8) +#define MCI_STARTBITERR (1 << 9) #define MCI_DATABLOCKEND (1 << 10) #define MCI_CMDACTIVE (1 << 11) #define MCI_TXACTIVE (1 << 12) @@ -112,6 +113,7 @@ #define MCI_CMDRESPENDCLR (1 << 6) #define MCI_CMDSENTCLR (1 << 7) #define MCI_DATAENDCLR (1 << 8) +#define MCI_STARTBITERRCLR (1 << 9) #define MCI_DATABLOCKENDCLR (1 << 10) /* Extended status bits for the ST Micro variants */ #define MCI_ST_SDIOITC (1 << 22) @@ -127,6 +129,7 @@ #define MCI_CMDRESPENDMASK (1 << 6) #define MCI_CMDSENTMASK (1 << 7) #define MCI_DATAENDMASK (1 << 8) +#define MCI_STARTBITERRMASK (1 << 9) #define MCI_DATABLOCKENDMASK (1 << 10) #define MCI_CMDACTIVEMASK (1 << 11) #define MCI_TXACTIVEMASK (1 << 12) @@ -150,7 +153,7 @@ #define MCI_IRQENABLE \ (MCI_CMDCRCFAILMASK|MCI_DATACRCFAILMASK|MCI_CMDTIMEOUTMASK| \ MCI_DATATIMEOUTMASK|MCI_TXUNDERRUNMASK|MCI_RXOVERRUNMASK| \ - MCI_CMDRESPENDMASK|MCI_CMDSENTMASK) + MCI_CMDRESPENDMASK|MCI_CMDSENTMASK|MCI_STARTBITERRMASK) /* These interrupts are directed to IRQ1 when two IRQ lines are available */ #define MCI_IRQ1MASK \ @@ -163,6 +166,12 @@ struct clk; struct variant_data; struct dma_chan; +struct mmci_host_next { + struct dma_async_tx_descriptor *dma_desc; + struct dma_chan *dma_chan; + s32 cookie; +}; + struct mmci_host { phys_addr_t phybase; void __iomem *base; @@ -200,6 +209,8 @@ struct mmci_host { struct dma_chan *dma_current; struct dma_chan *dma_rx_channel; struct dma_chan *dma_tx_channel; + struct dma_async_tx_descriptor *dma_desc_current; + struct mmci_host_next next_data; #define dma_inprogress(host) ((host)->dma_current) #else diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c index 99d39a6..d513d47 100644 --- a/drivers/mmc/host/mxs-mmc.c +++ b/drivers/mmc/host/mxs-mmc.c @@ -564,40 +564,38 @@ static void mxs_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) static void mxs_mmc_set_clk_rate(struct mxs_mmc_host *host, unsigned int rate) { - unsigned int ssp_rate, bit_rate; - u32 div1, div2; + unsigned int ssp_clk, ssp_sck; + u32 clock_divide, clock_rate; u32 val; - ssp_rate = clk_get_rate(host->clk); + ssp_clk = clk_get_rate(host->clk); - for (div1 = 2; div1 < 254; div1 += 2) { - div2 = ssp_rate / rate / div1; - if (div2 < 0x100) + for (clock_divide = 2; clock_divide <= 254; clock_divide += 2) { + clock_rate = DIV_ROUND_UP(ssp_clk, rate * clock_divide); + clock_rate = (clock_rate > 0) ? clock_rate - 1 : 0; + if (clock_rate <= 255) break; } - if (div1 >= 254) { + if (clock_divide > 254) { dev_err(mmc_dev(host->mmc), "%s: cannot set clock to %d\n", __func__, rate); return; } - if (div2 == 0) - bit_rate = ssp_rate / div1; - else - bit_rate = ssp_rate / div1 / div2; + ssp_sck = ssp_clk / clock_divide / (1 + clock_rate); val = readl(host->base + HW_SSP_TIMING); val &= ~(BM_SSP_TIMING_CLOCK_DIVIDE | BM_SSP_TIMING_CLOCK_RATE); - val |= BF_SSP(div1, TIMING_CLOCK_DIVIDE); - val |= BF_SSP(div2 - 1, TIMING_CLOCK_RATE); + val |= BF_SSP(clock_divide, TIMING_CLOCK_DIVIDE); + val |= BF_SSP(clock_rate, TIMING_CLOCK_RATE); writel(val, host->base + HW_SSP_TIMING); - host->clk_rate = bit_rate; + host->clk_rate = ssp_sck; dev_dbg(mmc_dev(host->mmc), - "%s: div1 %d, div2 %d, ssp %d, bit %d, rate %d\n", - __func__, div1, div2, ssp_rate, bit_rate, rate); + "%s: clock_divide %d, clock_rate %d, ssp_clk %d, rate_actual %d, rate_requested %d\n", + __func__, clock_divide, clock_rate, ssp_clk, ssp_sck, rate); } static void mxs_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) diff --git a/drivers/mmc/host/of_mmc_spi.c b/drivers/mmc/host/of_mmc_spi.c index e2aecb7..ab66f24 100644 --- a/drivers/mmc/host/of_mmc_spi.c +++ b/drivers/mmc/host/of_mmc_spi.c @@ -25,6 +25,11 @@ #include <linux/mmc/core.h> #include <linux/mmc/host.h> +/* For archs that don't support NO_IRQ (such as mips), provide a dummy value */ +#ifndef NO_IRQ +#define NO_IRQ 0 +#endif + MODULE_LICENSE("GPL"); enum { diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 5b2e215..21e4a79 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/interrupt.h> @@ -33,6 +34,7 @@ #include <linux/semaphore.h> #include <linux/gpio.h> #include <linux/regulator/consumer.h> +#include <linux/pm_runtime.h> #include <plat/dma.h> #include <mach/hardware.h> #include <plat/board.h> @@ -116,15 +118,13 @@ #define OMAP_MMC4_DEVID 3 #define OMAP_MMC5_DEVID 4 +#define MMC_AUTOSUSPEND_DELAY 100 #define MMC_TIMEOUT_MS 20 #define OMAP_MMC_MASTER_CLOCK 96000000 +#define OMAP_MMC_MIN_CLOCK 400000 +#define OMAP_MMC_MAX_CLOCK 52000000 #define DRIVER_NAME "omap_hsmmc" -/* Timeouts for entering power saving states on inactivity, msec */ -#define OMAP_MMC_DISABLED_TIMEOUT 100 -#define OMAP_MMC_SLEEP_TIMEOUT 1000 -#define OMAP_MMC_OFF_TIMEOUT 8000 - /* * One controller can have multiple slots, like on some omap boards using * omap.c controller driver. Luckily this is not currently done on any known @@ -141,6 +141,11 @@ #define OMAP_HSMMC_WRITE(base, reg, val) \ __raw_writel((val), (base) + OMAP_HSMMC_##reg) +struct omap_hsmmc_next { + unsigned int dma_len; + s32 cookie; +}; + struct omap_hsmmc_host { struct device *dev; struct mmc_host *mmc; @@ -148,7 +153,6 @@ struct omap_hsmmc_host { struct mmc_command *cmd; struct mmc_data *data; struct clk *fclk; - struct clk *iclk; struct clk *dbclk; /* * vcc == configured supply @@ -184,6 +188,7 @@ struct omap_hsmmc_host { int reqs_blocked; int use_reg; int req_in_progress; + struct omap_hsmmc_next next_data; struct omap_mmc_platform_data *pdata; }; @@ -429,7 +434,6 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host) return -EINVAL; } } - mmc_slot(host).ocr_mask = mmc_regulator_get_ocrmask(reg); /* Allow an aux regulator */ reg = regulator_get(host->dev, "vmmc_aux"); @@ -549,6 +553,15 @@ static void omap_hsmmc_gpio_free(struct omap_mmc_platform_data *pdata) } /* + * Start clock to the card + */ +static void omap_hsmmc_start_clock(struct omap_hsmmc_host *host) +{ + OMAP_HSMMC_WRITE(host->base, SYSCTL, + OMAP_HSMMC_READ(host->base, SYSCTL) | CEN); +} + +/* * Stop clock to the card */ static void omap_hsmmc_stop_clock(struct omap_hsmmc_host *host) @@ -585,6 +598,81 @@ static void omap_hsmmc_disable_irq(struct omap_hsmmc_host *host) OMAP_HSMMC_WRITE(host->base, STAT, STAT_CLEAR); } +/* Calculate divisor for the given clock frequency */ +static u16 calc_divisor(struct mmc_ios *ios) +{ + u16 dsor = 0; + + if (ios->clock) { + dsor = DIV_ROUND_UP(OMAP_MMC_MASTER_CLOCK, ios->clock); + if (dsor > 250) + dsor = 250; + } + + return dsor; +} + +static void omap_hsmmc_set_clock(struct omap_hsmmc_host *host) +{ + struct mmc_ios *ios = &host->mmc->ios; + unsigned long regval; + unsigned long timeout; + + dev_dbg(mmc_dev(host->mmc), "Set clock to %uHz\n", ios->clock); + + omap_hsmmc_stop_clock(host); + + regval = OMAP_HSMMC_READ(host->base, SYSCTL); + regval = regval & ~(CLKD_MASK | DTO_MASK); + regval = regval | (calc_divisor(ios) << 6) | (DTO << 16); + OMAP_HSMMC_WRITE(host->base, SYSCTL, regval); + OMAP_HSMMC_WRITE(host->base, SYSCTL, + OMAP_HSMMC_READ(host->base, SYSCTL) | ICE); + + /* Wait till the ICS bit is set */ + timeout = jiffies + msecs_to_jiffies(MMC_TIMEOUT_MS); + while ((OMAP_HSMMC_READ(host->base, SYSCTL) & ICS) != ICS + && time_before(jiffies, timeout)) + cpu_relax(); + + omap_hsmmc_start_clock(host); +} + +static void omap_hsmmc_set_bus_width(struct omap_hsmmc_host *host) +{ + struct mmc_ios *ios = &host->mmc->ios; + u32 con; + + con = OMAP_HSMMC_READ(host->base, CON); + switch (ios->bus_width) { + case MMC_BUS_WIDTH_8: + OMAP_HSMMC_WRITE(host->base, CON, con | DW8); + break; + case MMC_BUS_WIDTH_4: + OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); + OMAP_HSMMC_WRITE(host->base, HCTL, + OMAP_HSMMC_READ(host->base, HCTL) | FOUR_BIT); + break; + case MMC_BUS_WIDTH_1: + OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); + OMAP_HSMMC_WRITE(host->base, HCTL, + OMAP_HSMMC_READ(host->base, HCTL) & ~FOUR_BIT); + break; + } +} + +static void omap_hsmmc_set_bus_mode(struct omap_hsmmc_host *host) +{ + struct mmc_ios *ios = &host->mmc->ios; + u32 con; + + con = OMAP_HSMMC_READ(host->base, CON); + if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN) + OMAP_HSMMC_WRITE(host->base, CON, con | OD); + else + OMAP_HSMMC_WRITE(host->base, CON, con & ~OD); +} + #ifdef CONFIG_PM /* @@ -596,8 +684,7 @@ static int omap_hsmmc_context_restore(struct omap_hsmmc_host *host) struct mmc_ios *ios = &host->mmc->ios; struct omap_mmc_platform_data *pdata = host->pdata; int context_loss = 0; - u32 hctl, capa, con; - u16 dsor = 0; + u32 hctl, capa; unsigned long timeout; if (pdata->get_context_loss_count) { @@ -659,54 +746,12 @@ static int omap_hsmmc_context_restore(struct omap_hsmmc_host *host) if (host->power_mode == MMC_POWER_OFF) goto out; - con = OMAP_HSMMC_READ(host->base, CON); - switch (ios->bus_width) { - case MMC_BUS_WIDTH_8: - OMAP_HSMMC_WRITE(host->base, CON, con | DW8); - break; - case MMC_BUS_WIDTH_4: - OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) | FOUR_BIT); - break; - case MMC_BUS_WIDTH_1: - OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) & ~FOUR_BIT); - break; - } - - if (ios->clock) { - dsor = OMAP_MMC_MASTER_CLOCK / ios->clock; - if (dsor < 1) - dsor = 1; - - if (OMAP_MMC_MASTER_CLOCK / dsor > ios->clock) - dsor++; - - if (dsor > 250) - dsor = 250; - } - - OMAP_HSMMC_WRITE(host->base, SYSCTL, - OMAP_HSMMC_READ(host->base, SYSCTL) & ~CEN); - OMAP_HSMMC_WRITE(host->base, SYSCTL, (dsor << 6) | (DTO << 16)); - OMAP_HSMMC_WRITE(host->base, SYSCTL, - OMAP_HSMMC_READ(host->base, SYSCTL) | ICE); + omap_hsmmc_set_bus_width(host); - timeout = jiffies + msecs_to_jiffies(MMC_TIMEOUT_MS); - while ((OMAP_HSMMC_READ(host->base, SYSCTL) & ICS) != ICS - && time_before(jiffies, timeout)) - ; + omap_hsmmc_set_clock(host); - OMAP_HSMMC_WRITE(host->base, SYSCTL, - OMAP_HSMMC_READ(host->base, SYSCTL) | CEN); + omap_hsmmc_set_bus_mode(host); - con = OMAP_HSMMC_READ(host->base, CON); - if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN) - OMAP_HSMMC_WRITE(host->base, CON, con | OD); - else - OMAP_HSMMC_WRITE(host->base, CON, con & ~OD); out: host->context_loss = context_loss; @@ -962,7 +1007,8 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno) spin_unlock(&host->irq_lock); if (host->use_dma && dma_ch != -1) { - dma_unmap_sg(mmc_dev(host->mmc), host->data->sg, host->dma_len, + dma_unmap_sg(mmc_dev(host->mmc), host->data->sg, + host->data->sg_len, omap_hsmmc_get_dma_dir(host, host->data)); omap_free_dma(dma_ch); } @@ -973,14 +1019,14 @@ static void omap_hsmmc_dma_cleanup(struct omap_hsmmc_host *host, int errno) * Readable error output */ #ifdef CONFIG_MMC_DEBUG -static void omap_hsmmc_report_irq(struct omap_hsmmc_host *host, u32 status) +static void omap_hsmmc_dbg_report_irq(struct omap_hsmmc_host *host, u32 status) { /* --- means reserved bit without definition at documentation */ static const char *omap_hsmmc_status_bits[] = { - "CC", "TC", "BGE", "---", "BWR", "BRR", "---", "---", "CIRQ", - "OBI", "---", "---", "---", "---", "---", "ERRI", "CTO", "CCRC", - "CEB", "CIE", "DTO", "DCRC", "DEB", "---", "ACE", "---", - "---", "---", "---", "CERR", "CERR", "BADA", "---", "---", "---" + "CC" , "TC" , "BGE", "---", "BWR" , "BRR" , "---" , "---" , + "CIRQ", "OBI" , "---", "---", "---" , "---" , "---" , "ERRI", + "CTO" , "CCRC", "CEB", "CIE", "DTO" , "DCRC", "DEB" , "---" , + "ACE" , "---" , "---", "---", "CERR", "BADA", "---" , "---" }; char res[256]; char *buf = res; @@ -997,6 +1043,11 @@ static void omap_hsmmc_report_irq(struct omap_hsmmc_host *host, u32 status) dev_dbg(mmc_dev(host->mmc), "%s\n", res); } +#else +static inline void omap_hsmmc_dbg_report_irq(struct omap_hsmmc_host *host, + u32 status) +{ +} #endif /* CONFIG_MMC_DEBUG */ /* @@ -1055,9 +1106,7 @@ static void omap_hsmmc_do_irq(struct omap_hsmmc_host *host, int status) dev_dbg(mmc_dev(host->mmc), "IRQ Status is %x\n", status); if (status & ERR) { -#ifdef CONFIG_MMC_DEBUG - omap_hsmmc_report_irq(host, status); -#endif + omap_hsmmc_dbg_report_irq(host, status); if ((status & CMD_TIMEOUT) || (status & CMD_CRC)) { if (host->cmd) { @@ -1155,8 +1204,7 @@ static int omap_hsmmc_switch_opcond(struct omap_hsmmc_host *host, int vdd) int ret; /* Disable the clocks */ - clk_disable(host->fclk); - clk_disable(host->iclk); + pm_runtime_put_sync(host->dev); if (host->got_dbclk) clk_disable(host->dbclk); @@ -1167,8 +1215,7 @@ static int omap_hsmmc_switch_opcond(struct omap_hsmmc_host *host, int vdd) if (!ret) ret = mmc_slot(host).set_power(host->dev, host->slot_id, 1, vdd); - clk_enable(host->iclk); - clk_enable(host->fclk); + pm_runtime_get_sync(host->dev); if (host->got_dbclk) clk_enable(host->dbclk); @@ -1322,7 +1369,7 @@ static void omap_hsmmc_config_dma_params(struct omap_hsmmc_host *host, static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data) { struct omap_hsmmc_host *host = cb_data; - struct mmc_data *data = host->mrq->data; + struct mmc_data *data; int dma_ch, req_in_progress; if (!(ch_status & OMAP_DMA_BLOCK_IRQ)) { @@ -1337,6 +1384,7 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data) return; } + data = host->mrq->data; host->dma_sg_idx++; if (host->dma_sg_idx < host->dma_len) { /* Fire up the next transfer. */ @@ -1346,8 +1394,9 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data) return; } - dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->dma_len, - omap_hsmmc_get_dma_dir(host, data)); + if (!data->host_cookie) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + omap_hsmmc_get_dma_dir(host, data)); req_in_progress = host->req_in_progress; dma_ch = host->dma_ch; @@ -1365,6 +1414,45 @@ static void omap_hsmmc_dma_cb(int lch, u16 ch_status, void *cb_data) } } +static int omap_hsmmc_pre_dma_transfer(struct omap_hsmmc_host *host, + struct mmc_data *data, + struct omap_hsmmc_next *next) +{ + int dma_len; + + if (!next && data->host_cookie && + data->host_cookie != host->next_data.cookie) { + printk(KERN_WARNING "[%s] invalid cookie: data->host_cookie %d" + " host->next_data.cookie %d\n", + __func__, data->host_cookie, host->next_data.cookie); + data->host_cookie = 0; + } + + /* Check if next job is already prepared */ + if (next || + (!next && data->host_cookie != host->next_data.cookie)) { + dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg, + data->sg_len, + omap_hsmmc_get_dma_dir(host, data)); + + } else { + dma_len = host->next_data.dma_len; + host->next_data.dma_len = 0; + } + + + if (dma_len == 0) + return -EINVAL; + + if (next) { + next->dma_len = dma_len; + data->host_cookie = ++next->cookie < 0 ? 1 : next->cookie; + } else + host->dma_len = dma_len; + + return 0; +} + /* * Routine to configure and start DMA for the MMC card */ @@ -1398,9 +1486,10 @@ static int omap_hsmmc_start_dma_transfer(struct omap_hsmmc_host *host, mmc_hostname(host->mmc), ret); return ret; } + ret = omap_hsmmc_pre_dma_transfer(host, data, NULL); + if (ret) + return ret; - host->dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg, - data->sg_len, omap_hsmmc_get_dma_dir(host, data)); host->dma_ch = dma_ch; host->dma_sg_idx = 0; @@ -1480,6 +1569,35 @@ omap_hsmmc_prepare_data(struct omap_hsmmc_host *host, struct mmc_request *req) return 0; } +static void omap_hsmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq, + int err) +{ + struct omap_hsmmc_host *host = mmc_priv(mmc); + struct mmc_data *data = mrq->data; + + if (host->use_dma) { + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + omap_hsmmc_get_dma_dir(host, data)); + data->host_cookie = 0; + } +} + +static void omap_hsmmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq, + bool is_first_req) +{ + struct omap_hsmmc_host *host = mmc_priv(mmc); + + if (mrq->data->host_cookie) { + mrq->data->host_cookie = 0; + return ; + } + + if (host->use_dma) + if (omap_hsmmc_pre_dma_transfer(host, mrq->data, + &host->next_data)) + mrq->data->host_cookie = 0; +} + /* * Request function. for read/write operation */ @@ -1528,13 +1646,9 @@ static void omap_hsmmc_request(struct mmc_host *mmc, struct mmc_request *req) static void omap_hsmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) { struct omap_hsmmc_host *host = mmc_priv(mmc); - u16 dsor = 0; - unsigned long regval; - unsigned long timeout; - u32 con; int do_send_init_stream = 0; - mmc_host_enable(host->mmc); + pm_runtime_get_sync(host->dev); if (ios->power_mode != host->power_mode) { switch (ios->power_mode) { @@ -1557,22 +1671,7 @@ static void omap_hsmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) /* FIXME: set registers based only on changes to ios */ - con = OMAP_HSMMC_READ(host->base, CON); - switch (mmc->ios.bus_width) { - case MMC_BUS_WIDTH_8: - OMAP_HSMMC_WRITE(host->base, CON, con | DW8); - break; - case MMC_BUS_WIDTH_4: - OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) | FOUR_BIT); - break; - case MMC_BUS_WIDTH_1: - OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8); - OMAP_HSMMC_WRITE(host->base, HCTL, - OMAP_HSMMC_READ(host->base, HCTL) & ~FOUR_BIT); - break; - } + omap_hsmmc_set_bus_width(host); if (host->pdata->controller_flags & OMAP_HSMMC_SUPPORTS_DUAL_VOLT) { /* Only MMC1 can interface at 3V without some flavor @@ -1592,47 +1691,14 @@ static void omap_hsmmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) } } - if (ios->clock) { - dsor = OMAP_MMC_MASTER_CLOCK / ios->clock; - if (dsor < 1) - dsor = 1; - - if (OMAP_MMC_MASTER_CLOCK / dsor > ios->clock) - dsor++; - - if (dsor > 250) - dsor = 250; - } - omap_hsmmc_stop_clock(host); - regval = OMAP_HSMMC_READ(host->base, SYSCTL); - regval = regval & ~(CLKD_MASK); - regval = regval | (dsor << 6) | (DTO << 16); - OMAP_HSMMC_WRITE(host->base, SYSCTL, regval); - OMAP_HSMMC_WRITE(host->base, SYSCTL, - OMAP_HSMMC_READ(host->base, SYSCTL) | ICE); - - /* Wait till the ICS bit is set */ - timeout = jiffies + msecs_to_jiffies(MMC_TIMEOUT_MS); - while ((OMAP_HSMMC_READ(host->base, SYSCTL) & ICS) != ICS - && time_before(jiffies, timeout)) - msleep(1); - - OMAP_HSMMC_WRITE(host->base, SYSCTL, - OMAP_HSMMC_READ(host->base, SYSCTL) | CEN); + omap_hsmmc_set_clock(host); if (do_send_init_stream) send_init_stream(host); - con = OMAP_HSMMC_READ(host->base, CON); - if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN) - OMAP_HSMMC_WRITE(host->base, CON, con | OD); - else - OMAP_HSMMC_WRITE(host->base, CON, con & ~OD); + omap_hsmmc_set_bus_mode(host); - if (host->power_mode == MMC_POWER_OFF) - mmc_host_disable(host->mmc); - else - mmc_host_lazy_disable(host->mmc); + pm_runtime_put_autosuspend(host->dev); } static int omap_hsmmc_get_cd(struct mmc_host *mmc) @@ -1688,230 +1754,12 @@ static void omap_hsmmc_conf_bus_power(struct omap_hsmmc_host *host) set_sd_bus_power(host); } -/* - * Dynamic power saving handling, FSM: - * ENABLED -> DISABLED -> CARDSLEEP / REGSLEEP -> OFF - * ^___________| | | - * |______________________|______________________| - * - * ENABLED: mmc host is fully functional - * DISABLED: fclk is off - * CARDSLEEP: fclk is off, card is asleep, voltage regulator is asleep - * REGSLEEP: fclk is off, voltage regulator is asleep - * OFF: fclk is off, voltage regulator is off - * - * Transition handlers return the timeout for the next state transition - * or negative error. - */ - -enum {ENABLED = 0, DISABLED, CARDSLEEP, REGSLEEP, OFF}; - -/* Handler for [ENABLED -> DISABLED] transition */ -static int omap_hsmmc_enabled_to_disabled(struct omap_hsmmc_host *host) -{ - omap_hsmmc_context_save(host); - clk_disable(host->fclk); - host->dpm_state = DISABLED; - - dev_dbg(mmc_dev(host->mmc), "ENABLED -> DISABLED\n"); - - if (host->power_mode == MMC_POWER_OFF) - return 0; - - return OMAP_MMC_SLEEP_TIMEOUT; -} - -/* Handler for [DISABLED -> REGSLEEP / CARDSLEEP] transition */ -static int omap_hsmmc_disabled_to_sleep(struct omap_hsmmc_host *host) -{ - int err, new_state; - - if (!mmc_try_claim_host(host->mmc)) - return 0; - - clk_enable(host->fclk); - omap_hsmmc_context_restore(host); - if (mmc_card_can_sleep(host->mmc)) { - err = mmc_card_sleep(host->mmc); - if (err < 0) { - clk_disable(host->fclk); - mmc_release_host(host->mmc); - return err; - } - new_state = CARDSLEEP; - } else { - new_state = REGSLEEP; - } - if (mmc_slot(host).set_sleep) - mmc_slot(host).set_sleep(host->dev, host->slot_id, 1, 0, - new_state == CARDSLEEP); - /* FIXME: turn off bus power and perhaps interrupts too */ - clk_disable(host->fclk); - host->dpm_state = new_state; - - mmc_release_host(host->mmc); - - dev_dbg(mmc_dev(host->mmc), "DISABLED -> %s\n", - host->dpm_state == CARDSLEEP ? "CARDSLEEP" : "REGSLEEP"); - - if (mmc_slot(host).no_off) - return 0; - - if ((host->mmc->caps & MMC_CAP_NONREMOVABLE) || - mmc_slot(host).card_detect || - (mmc_slot(host).get_cover_state && - mmc_slot(host).get_cover_state(host->dev, host->slot_id))) - return OMAP_MMC_OFF_TIMEOUT; - - return 0; -} - -/* Handler for [REGSLEEP / CARDSLEEP -> OFF] transition */ -static int omap_hsmmc_sleep_to_off(struct omap_hsmmc_host *host) -{ - if (!mmc_try_claim_host(host->mmc)) - return 0; - - if (mmc_slot(host).no_off) - return 0; - - if (!((host->mmc->caps & MMC_CAP_NONREMOVABLE) || - mmc_slot(host).card_detect || - (mmc_slot(host).get_cover_state && - mmc_slot(host).get_cover_state(host->dev, host->slot_id)))) { - mmc_release_host(host->mmc); - return 0; - } - - mmc_slot(host).set_power(host->dev, host->slot_id, 0, 0); - host->vdd = 0; - host->power_mode = MMC_POWER_OFF; - - dev_dbg(mmc_dev(host->mmc), "%s -> OFF\n", - host->dpm_state == CARDSLEEP ? "CARDSLEEP" : "REGSLEEP"); - - host->dpm_state = OFF; - - mmc_release_host(host->mmc); - - return 0; -} - -/* Handler for [DISABLED -> ENABLED] transition */ -static int omap_hsmmc_disabled_to_enabled(struct omap_hsmmc_host *host) -{ - int err; - - err = clk_enable(host->fclk); - if (err < 0) - return err; - - omap_hsmmc_context_restore(host); - host->dpm_state = ENABLED; - - dev_dbg(mmc_dev(host->mmc), "DISABLED -> ENABLED\n"); - - return 0; -} - -/* Handler for [SLEEP -> ENABLED] transition */ -static int omap_hsmmc_sleep_to_enabled(struct omap_hsmmc_host *host) -{ - if (!mmc_try_claim_host(host->mmc)) - return 0; - - clk_enable(host->fclk); - omap_hsmmc_context_restore(host); - if (mmc_slot(host).set_sleep) - mmc_slot(host).set_sleep(host->dev, host->slot_id, 0, - host->vdd, host->dpm_state == CARDSLEEP); - if (mmc_card_can_sleep(host->mmc)) - mmc_card_awake(host->mmc); - - dev_dbg(mmc_dev(host->mmc), "%s -> ENABLED\n", - host->dpm_state == CARDSLEEP ? "CARDSLEEP" : "REGSLEEP"); - - host->dpm_state = ENABLED; - - mmc_release_host(host->mmc); - - return 0; -} - -/* Handler for [OFF -> ENABLED] transition */ -static int omap_hsmmc_off_to_enabled(struct omap_hsmmc_host *host) -{ - clk_enable(host->fclk); - - omap_hsmmc_context_restore(host); - omap_hsmmc_conf_bus_power(host); - mmc_power_restore_host(host->mmc); - - host->dpm_state = ENABLED; - - dev_dbg(mmc_dev(host->mmc), "OFF -> ENABLED\n"); - - return 0; -} - -/* - * Bring MMC host to ENABLED from any other PM state. - */ -static int omap_hsmmc_enable(struct mmc_host *mmc) -{ - struct omap_hsmmc_host *host = mmc_priv(mmc); - - switch (host->dpm_state) { - case DISABLED: - return omap_hsmmc_disabled_to_enabled(host); - case CARDSLEEP: - case REGSLEEP: - return omap_hsmmc_sleep_to_enabled(host); - case OFF: - return omap_hsmmc_off_to_enabled(host); - default: - dev_dbg(mmc_dev(host->mmc), "UNKNOWN state\n"); - return -EINVAL; - } -} - -/* - * Bring MMC host in PM state (one level deeper). - */ -static int omap_hsmmc_disable(struct mmc_host *mmc, int lazy) -{ - struct omap_hsmmc_host *host = mmc_priv(mmc); - - switch (host->dpm_state) { - case ENABLED: { - int delay; - - delay = omap_hsmmc_enabled_to_disabled(host); - if (lazy || delay < 0) - return delay; - return 0; - } - case DISABLED: - return omap_hsmmc_disabled_to_sleep(host); - case CARDSLEEP: - case REGSLEEP: - return omap_hsmmc_sleep_to_off(host); - default: - dev_dbg(mmc_dev(host->mmc), "UNKNOWN state\n"); - return -EINVAL; - } -} - static int omap_hsmmc_enable_fclk(struct mmc_host *mmc) { struct omap_hsmmc_host *host = mmc_priv(mmc); - int err; - err = clk_enable(host->fclk); - if (err) - return err; - dev_dbg(mmc_dev(host->mmc), "mmc_fclk: enabled\n"); - omap_hsmmc_context_restore(host); + pm_runtime_get_sync(host->dev); + return 0; } @@ -1919,26 +1767,17 @@ static int omap_hsmmc_disable_fclk(struct mmc_host *mmc, int lazy) { struct omap_hsmmc_host *host = mmc_priv(mmc); - omap_hsmmc_context_save(host); - clk_disable(host->fclk); - dev_dbg(mmc_dev(host->mmc), "mmc_fclk: disabled\n"); + pm_runtime_mark_last_busy(host->dev); + pm_runtime_put_autosuspend(host->dev); + return 0; } static const struct mmc_host_ops omap_hsmmc_ops = { .enable = omap_hsmmc_enable_fclk, .disable = omap_hsmmc_disable_fclk, - .request = omap_hsmmc_request, - .set_ios = omap_hsmmc_set_ios, - .get_cd = omap_hsmmc_get_cd, - .get_ro = omap_hsmmc_get_ro, - .init_card = omap_hsmmc_init_card, - /* NYET -- enable_sdio_irq */ -}; - -static const struct mmc_host_ops omap_hsmmc_ps_ops = { - .enable = omap_hsmmc_enable, - .disable = omap_hsmmc_disable, + .post_req = omap_hsmmc_post_req, + .pre_req = omap_hsmmc_pre_req, .request = omap_hsmmc_request, .set_ios = omap_hsmmc_set_ios, .get_cd = omap_hsmmc_get_cd, @@ -1968,15 +1807,12 @@ static int omap_hsmmc_regs_show(struct seq_file *s, void *data) host->dpm_state, mmc->nesting_cnt, host->context_loss, context_loss); - if (host->suspended || host->dpm_state == OFF) { + if (host->suspended) { seq_printf(s, "host suspended, can't read registers\n"); return 0; } - if (clk_enable(host->fclk) != 0) { - seq_printf(s, "can't read the regs\n"); - return 0; - } + pm_runtime_get_sync(host->dev); seq_printf(s, "SYSCONFIG:\t0x%08x\n", OMAP_HSMMC_READ(host->base, SYSCONFIG)); @@ -1993,7 +1829,8 @@ static int omap_hsmmc_regs_show(struct seq_file *s, void *data) seq_printf(s, "CAPA:\t\t0x%08x\n", OMAP_HSMMC_READ(host->base, CAPA)); - clk_disable(host->fclk); + pm_runtime_mark_last_busy(host->dev); + pm_runtime_put_autosuspend(host->dev); return 0; } @@ -2077,14 +1914,12 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev) host->mapbase = res->start; host->base = ioremap(host->mapbase, SZ_4K); host->power_mode = MMC_POWER_OFF; + host->next_data.cookie = 1; platform_set_drvdata(pdev, host); INIT_WORK(&host->mmc_carddetect_work, omap_hsmmc_detect); - if (mmc_slot(host).power_saving) - mmc->ops = &omap_hsmmc_ps_ops; - else - mmc->ops = &omap_hsmmc_ops; + mmc->ops = &omap_hsmmc_ops; /* * If regulator_disable can only put vcc_aux to sleep then there is @@ -2093,44 +1928,26 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev) if (mmc_slot(host).vcc_aux_disable_is_sleep) mmc_slot(host).no_off = 1; - mmc->f_min = 400000; - mmc->f_max = 52000000; + mmc->f_min = OMAP_MMC_MIN_CLOCK; + mmc->f_max = OMAP_MMC_MAX_CLOCK; spin_lock_init(&host->irq_lock); - host->iclk = clk_get(&pdev->dev, "ick"); - if (IS_ERR(host->iclk)) { - ret = PTR_ERR(host->iclk); - host->iclk = NULL; - goto err1; - } host->fclk = clk_get(&pdev->dev, "fck"); if (IS_ERR(host->fclk)) { ret = PTR_ERR(host->fclk); host->fclk = NULL; - clk_put(host->iclk); goto err1; } omap_hsmmc_context_save(host); mmc->caps |= MMC_CAP_DISABLE; - mmc_set_disable_delay(mmc, OMAP_MMC_DISABLED_TIMEOUT); - /* we start off in DISABLED state */ - host->dpm_state = DISABLED; - if (clk_enable(host->iclk) != 0) { - clk_put(host->iclk); - clk_put(host->fclk); - goto err1; - } - - if (mmc_host_enable(host->mmc) != 0) { - clk_disable(host->iclk); - clk_put(host->iclk); - clk_put(host->fclk); - goto err1; - } + pm_runtime_enable(host->dev); + pm_runtime_get_sync(host->dev); + pm_runtime_set_autosuspend_delay(host->dev, MMC_AUTOSUSPEND_DELAY); + pm_runtime_use_autosuspend(host->dev); if (cpu_is_omap2430()) { host->dbclk = clk_get(&pdev->dev, "mmchsdb_fck"); @@ -2240,8 +2057,6 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev) omap_hsmmc_disable_irq(host); - mmc_host_lazy_disable(host->mmc); - omap_hsmmc_protect_card(host); mmc_add_host(mmc); @@ -2259,6 +2074,8 @@ static int __init omap_hsmmc_probe(struct platform_device *pdev) } omap_hsmmc_debugfs(mmc); + pm_runtime_mark_last_busy(host->dev); + pm_runtime_put_autosuspend(host->dev); return 0; @@ -2274,10 +2091,9 @@ err_reg: err_irq_cd_init: free_irq(host->irq, host); err_irq: - mmc_host_disable(host->mmc); - clk_disable(host->iclk); + pm_runtime_mark_last_busy(host->dev); + pm_runtime_put_autosuspend(host->dev); clk_put(host->fclk); - clk_put(host->iclk); if (host->got_dbclk) { clk_disable(host->dbclk); clk_put(host->dbclk); @@ -2299,7 +2115,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) struct resource *res; if (host) { - mmc_host_enable(host->mmc); + pm_runtime_get_sync(host->dev); mmc_remove_host(host->mmc); if (host->use_reg) omap_hsmmc_reg_put(host); @@ -2310,10 +2126,9 @@ static int omap_hsmmc_remove(struct platform_device *pdev) free_irq(mmc_slot(host).card_detect_irq, host); flush_work_sync(&host->mmc_carddetect_work); - mmc_host_disable(host->mmc); - clk_disable(host->iclk); + pm_runtime_put_sync(host->dev); + pm_runtime_disable(host->dev); clk_put(host->fclk); - clk_put(host->iclk); if (host->got_dbclk) { clk_disable(host->dbclk); clk_put(host->dbclk); @@ -2343,6 +2158,7 @@ static int omap_hsmmc_suspend(struct device *dev) return 0; if (host) { + pm_runtime_get_sync(host->dev); host->suspended = 1; if (host->pdata->suspend) { ret = host->pdata->suspend(&pdev->dev, @@ -2357,13 +2173,11 @@ static int omap_hsmmc_suspend(struct device *dev) } cancel_work_sync(&host->mmc_carddetect_work); ret = mmc_suspend_host(host->mmc); - mmc_host_enable(host->mmc); + if (ret == 0) { omap_hsmmc_disable_irq(host); OMAP_HSMMC_WRITE(host->base, HCTL, OMAP_HSMMC_READ(host->base, HCTL) & ~SDBP); - mmc_host_disable(host->mmc); - clk_disable(host->iclk); if (host->got_dbclk) clk_disable(host->dbclk); } else { @@ -2375,9 +2189,8 @@ static int omap_hsmmc_suspend(struct device *dev) dev_dbg(mmc_dev(host->mmc), "Unmask interrupt failed\n"); } - mmc_host_disable(host->mmc); } - + pm_runtime_put_sync(host->dev); } return ret; } @@ -2393,14 +2206,7 @@ static int omap_hsmmc_resume(struct device *dev) return 0; if (host) { - ret = clk_enable(host->iclk); - if (ret) - goto clk_en_err; - - if (mmc_host_enable(host->mmc) != 0) { - clk_disable(host->iclk); - goto clk_en_err; - } + pm_runtime_get_sync(host->dev); if (host->got_dbclk) clk_enable(host->dbclk); @@ -2421,15 +2227,12 @@ static int omap_hsmmc_resume(struct device *dev) if (ret == 0) host->suspended = 0; - mmc_host_lazy_disable(host->mmc); + pm_runtime_mark_last_busy(host->dev); + pm_runtime_put_autosuspend(host->dev); } return ret; -clk_en_err: - dev_dbg(mmc_dev(host->mmc), - "Failed to enable MMC clocks during resume\n"); - return ret; } #else @@ -2437,9 +2240,33 @@ clk_en_err: #define omap_hsmmc_resume NULL #endif +static int omap_hsmmc_runtime_suspend(struct device *dev) +{ + struct omap_hsmmc_host *host; + + host = platform_get_drvdata(to_platform_device(dev)); + omap_hsmmc_context_save(host); + dev_dbg(mmc_dev(host->mmc), "disabled\n"); + + return 0; +} + +static int omap_hsmmc_runtime_resume(struct device *dev) +{ + struct omap_hsmmc_host *host; + + host = platform_get_drvdata(to_platform_device(dev)); + omap_hsmmc_context_restore(host); + dev_dbg(mmc_dev(host->mmc), "enabled\n"); + + return 0; +} + static struct dev_pm_ops omap_hsmmc_dev_pm_ops = { .suspend = omap_hsmmc_suspend, .resume = omap_hsmmc_resume, + .runtime_suspend = omap_hsmmc_runtime_suspend, + .runtime_resume = omap_hsmmc_runtime_resume, }; static struct platform_driver omap_hsmmc_driver = { diff --git a/drivers/mmc/host/sdhci-cns3xxx.c b/drivers/mmc/host/sdhci-cns3xxx.c index 9ebd1d7..4b920b7 100644 --- a/drivers/mmc/host/sdhci-cns3xxx.c +++ b/drivers/mmc/host/sdhci-cns3xxx.c @@ -15,9 +15,7 @@ #include <linux/delay.h> #include <linux/device.h> #include <linux/mmc/host.h> -#include <linux/mmc/sdhci-pltfm.h> #include <mach/cns3xxx.h> -#include "sdhci.h" #include "sdhci-pltfm.h" static unsigned int sdhci_cns3xxx_get_max_clk(struct sdhci_host *host) @@ -86,7 +84,7 @@ static struct sdhci_ops sdhci_cns3xxx_ops = { .set_clock = sdhci_cns3xxx_set_clock, }; -struct sdhci_pltfm_data sdhci_cns3xxx_pdata = { +static struct sdhci_pltfm_data sdhci_cns3xxx_pdata = { .ops = &sdhci_cns3xxx_ops, .quirks = SDHCI_QUIRK_BROKEN_DMA | SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK | @@ -95,3 +93,43 @@ struct sdhci_pltfm_data sdhci_cns3xxx_pdata = { SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_NONSTANDARD_CLOCK, }; + +static int __devinit sdhci_cns3xxx_probe(struct platform_device *pdev) +{ + return sdhci_pltfm_register(pdev, &sdhci_cns3xxx_pdata); +} + +static int __devexit sdhci_cns3xxx_remove(struct platform_device *pdev) +{ + return sdhci_pltfm_unregister(pdev); +} + +static struct platform_driver sdhci_cns3xxx_driver = { + .driver = { + .name = "sdhci-cns3xxx", + .owner = THIS_MODULE, + }, + .probe = sdhci_cns3xxx_probe, + .remove = __devexit_p(sdhci_cns3xxx_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif +}; + +static int __init sdhci_cns3xxx_init(void) +{ + return platform_driver_register(&sdhci_cns3xxx_driver); +} +module_init(sdhci_cns3xxx_init); + +static void __exit sdhci_cns3xxx_exit(void) +{ + platform_driver_unregister(&sdhci_cns3xxx_driver); +} +module_exit(sdhci_cns3xxx_exit); + +MODULE_DESCRIPTION("SDHCI driver for CNS3xxx"); +MODULE_AUTHOR("Scott Shu, " + "Anton Vorontsov <avorontsov@mvista.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-dove.c b/drivers/mmc/host/sdhci-dove.c index 2aeef4f..f2d29dc 100644 --- a/drivers/mmc/host/sdhci-dove.c +++ b/drivers/mmc/host/sdhci-dove.c @@ -22,7 +22,6 @@ #include <linux/io.h> #include <linux/mmc/host.h> -#include "sdhci.h" #include "sdhci-pltfm.h" static u16 sdhci_dove_readw(struct sdhci_host *host, int reg) @@ -61,10 +60,50 @@ static struct sdhci_ops sdhci_dove_ops = { .read_l = sdhci_dove_readl, }; -struct sdhci_pltfm_data sdhci_dove_pdata = { +static struct sdhci_pltfm_data sdhci_dove_pdata = { .ops = &sdhci_dove_ops, .quirks = SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER | SDHCI_QUIRK_NO_BUSY_IRQ | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_FORCE_DMA, }; + +static int __devinit sdhci_dove_probe(struct platform_device *pdev) +{ + return sdhci_pltfm_register(pdev, &sdhci_dove_pdata); +} + +static int __devexit sdhci_dove_remove(struct platform_device *pdev) +{ + return sdhci_pltfm_unregister(pdev); +} + +static struct platform_driver sdhci_dove_driver = { + .driver = { + .name = "sdhci-dove", + .owner = THIS_MODULE, + }, + .probe = sdhci_dove_probe, + .remove = __devexit_p(sdhci_dove_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif +}; + +static int __init sdhci_dove_init(void) +{ + return platform_driver_register(&sdhci_dove_driver); +} +module_init(sdhci_dove_init); + +static void __exit sdhci_dove_exit(void) +{ + platform_driver_unregister(&sdhci_dove_driver); +} +module_exit(sdhci_dove_exit); + +MODULE_DESCRIPTION("SDHCI driver for Dove"); +MODULE_AUTHOR("Saeed Bishara <saeed@marvell.com>, " + "Mike Rapoport <mike@compulab.co.il>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index a19967d..710b706 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -18,12 +18,10 @@ #include <linux/gpio.h> #include <linux/slab.h> #include <linux/mmc/host.h> -#include <linux/mmc/sdhci-pltfm.h> #include <linux/mmc/mmc.h> #include <linux/mmc/sdio.h> #include <mach/hardware.h> #include <mach/esdhc.h> -#include "sdhci.h" #include "sdhci-pltfm.h" #include "sdhci-esdhc.h" @@ -31,7 +29,7 @@ #define SDHCI_VENDOR_SPEC 0xC0 #define SDHCI_VENDOR_SPEC_SDIO_QUIRK 0x00000002 -#define ESDHC_FLAG_GPIO_FOR_CD_WP (1 << 0) +#define ESDHC_FLAG_GPIO_FOR_CD (1 << 0) /* * The CMDTYPE of the CMD register (offset 0xE) should be set to * "11" when the STOP CMD12 is issued on imx53 to abort one @@ -67,14 +65,14 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg) u32 val = readl(host->ioaddr + reg); if (unlikely((reg == SDHCI_PRESENT_STATE) - && (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD_WP))) { + && (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD))) { struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data; if (boarddata && gpio_is_valid(boarddata->cd_gpio) && gpio_get_value(boarddata->cd_gpio)) /* no card, if a valid gpio says so... */ - val &= SDHCI_CARD_PRESENT; + val &= ~SDHCI_CARD_PRESENT; else /* ... in all other cases assume card is present */ val |= SDHCI_CARD_PRESENT; @@ -89,7 +87,7 @@ static void esdhc_writel_le(struct sdhci_host *host, u32 val, int reg) struct pltfm_imx_data *imx_data = pltfm_host->priv; if (unlikely((reg == SDHCI_INT_ENABLE || reg == SDHCI_SIGNAL_ENABLE) - && (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD_WP))) + && (imx_data->flags & ESDHC_FLAG_GPIO_FOR_CD))) /* * these interrupts won't work with a custom card_detect gpio * (only applied to mx25/35) @@ -191,16 +189,6 @@ static unsigned int esdhc_pltfm_get_min_clock(struct sdhci_host *host) return clk_get_rate(pltfm_host->clk) / 256 / 16; } -static unsigned int esdhc_pltfm_get_ro(struct sdhci_host *host) -{ - struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data; - - if (boarddata && gpio_is_valid(boarddata->wp_gpio)) - return gpio_get_value(boarddata->wp_gpio); - else - return -ENOSYS; -} - static struct sdhci_ops sdhci_esdhc_ops = { .read_l = esdhc_readl_le, .read_w = esdhc_readw_le, @@ -212,6 +200,24 @@ static struct sdhci_ops sdhci_esdhc_ops = { .get_min_clock = esdhc_pltfm_get_min_clock, }; +static struct sdhci_pltfm_data sdhci_esdhc_imx_pdata = { + .quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_ADMA + | SDHCI_QUIRK_BROKEN_CARD_DETECTION, + /* ADMA has issues. Might be fixable */ + .ops = &sdhci_esdhc_ops, +}; + +static unsigned int esdhc_pltfm_get_ro(struct sdhci_host *host) +{ + struct esdhc_platform_data *boarddata = + host->mmc->parent->platform_data; + + if (boarddata && gpio_is_valid(boarddata->wp_gpio)) + return gpio_get_value(boarddata->wp_gpio); + else + return -ENOSYS; +} + static irqreturn_t cd_irq(int irq, void *data) { struct sdhci_host *sdhost = (struct sdhci_host *)data; @@ -220,30 +226,35 @@ static irqreturn_t cd_irq(int irq, void *data) return IRQ_HANDLED; }; -static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pdata) +static int __devinit sdhci_esdhc_imx_probe(struct platform_device *pdev) { - struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data; + struct sdhci_pltfm_host *pltfm_host; + struct sdhci_host *host; + struct esdhc_platform_data *boarddata; struct clk *clk; int err; struct pltfm_imx_data *imx_data; + host = sdhci_pltfm_init(pdev, &sdhci_esdhc_imx_pdata); + if (IS_ERR(host)) + return PTR_ERR(host); + + pltfm_host = sdhci_priv(host); + + imx_data = kzalloc(sizeof(struct pltfm_imx_data), GFP_KERNEL); + if (!imx_data) + return -ENOMEM; + pltfm_host->priv = imx_data; + clk = clk_get(mmc_dev(host->mmc), NULL); if (IS_ERR(clk)) { dev_err(mmc_dev(host->mmc), "clk err\n"); - return PTR_ERR(clk); + err = PTR_ERR(clk); + goto err_clk_get; } clk_enable(clk); pltfm_host->clk = clk; - imx_data = kzalloc(sizeof(struct pltfm_imx_data), GFP_KERNEL); - if (!imx_data) { - clk_disable(pltfm_host->clk); - clk_put(pltfm_host->clk); - return -ENOMEM; - } - pltfm_host->priv = imx_data; - if (!cpu_is_mx25()) host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL; @@ -257,6 +268,7 @@ static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pd if (!(cpu_is_mx25() || cpu_is_mx35() || cpu_is_mx51())) imx_data->flags |= ESDHC_FLAG_MULTIBLK_NO_INT; + boarddata = host->mmc->parent->platform_data; if (boarddata) { err = gpio_request_one(boarddata->wp_gpio, GPIOF_IN, "ESDHC_WP"); if (err) { @@ -284,11 +296,15 @@ static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pd goto no_card_detect_irq; } - imx_data->flags |= ESDHC_FLAG_GPIO_FOR_CD_WP; + imx_data->flags |= ESDHC_FLAG_GPIO_FOR_CD; /* Now we have a working card_detect again */ host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION; } + err = sdhci_add_host(host); + if (err) + goto err_add_host; + return 0; no_card_detect_irq: @@ -297,14 +313,23 @@ static int esdhc_pltfm_init(struct sdhci_host *host, struct sdhci_pltfm_data *pd boarddata->cd_gpio = err; not_supported: kfree(imx_data); - return 0; + err_add_host: + clk_disable(pltfm_host->clk); + clk_put(pltfm_host->clk); + err_clk_get: + sdhci_pltfm_free(pdev); + return err; } -static void esdhc_pltfm_exit(struct sdhci_host *host) +static int __devexit sdhci_esdhc_imx_remove(struct platform_device *pdev) { + struct sdhci_host *host = platform_get_drvdata(pdev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct esdhc_platform_data *boarddata = host->mmc->parent->platform_data; struct pltfm_imx_data *imx_data = pltfm_host->priv; + int dead = (readl(host->ioaddr + SDHCI_INT_STATUS) == 0xffffffff); + + sdhci_remove_host(host, dead); if (boarddata && gpio_is_valid(boarddata->wp_gpio)) gpio_free(boarddata->wp_gpio); @@ -319,13 +344,37 @@ static void esdhc_pltfm_exit(struct sdhci_host *host) clk_disable(pltfm_host->clk); clk_put(pltfm_host->clk); kfree(imx_data); + + sdhci_pltfm_free(pdev); + + return 0; } -struct sdhci_pltfm_data sdhci_esdhc_imx_pdata = { - .quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_ADMA - | SDHCI_QUIRK_BROKEN_CARD_DETECTION, - /* ADMA has issues. Might be fixable */ - .ops = &sdhci_esdhc_ops, - .init = esdhc_pltfm_init, - .exit = esdhc_pltfm_exit, +static struct platform_driver sdhci_esdhc_imx_driver = { + .driver = { + .name = "sdhci-esdhc-imx", + .owner = THIS_MODULE, + }, + .probe = sdhci_esdhc_imx_probe, + .remove = __devexit_p(sdhci_esdhc_imx_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif }; + +static int __init sdhci_esdhc_imx_init(void) +{ + return platform_driver_register(&sdhci_esdhc_imx_driver); +} +module_init(sdhci_esdhc_imx_init); + +static void __exit sdhci_esdhc_imx_exit(void) +{ + platform_driver_unregister(&sdhci_esdhc_imx_driver); +} +module_exit(sdhci_esdhc_imx_exit); + +MODULE_DESCRIPTION("SDHCI driver for Freescale i.MX eSDHC"); +MODULE_AUTHOR("Wolfram Sang <w.sang@pengutronix.de>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-of-core.c b/drivers/mmc/host/sdhci-of-core.c deleted file mode 100644 index 60e4186..0000000 --- a/drivers/mmc/host/sdhci-of-core.c +++ /dev/null @@ -1,253 +0,0 @@ -/* - * OpenFirmware bindings for Secure Digital Host Controller Interface. - * - * Copyright (c) 2007 Freescale Semiconductor, Inc. - * Copyright (c) 2009 MontaVista Software, Inc. - * - * Authors: Xiaobo Xie <X.Xie@freescale.com> - * Anton Vorontsov <avorontsov@ru.mvista.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - */ - -#include <linux/err.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/io.h> -#include <linux/interrupt.h> -#include <linux/delay.h> -#include <linux/of.h> -#include <linux/of_platform.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/mmc/host.h> -#ifdef CONFIG_PPC -#include <asm/machdep.h> -#endif -#include "sdhci-of.h" -#include "sdhci.h" - -#ifdef CONFIG_MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER - -/* - * These accessors are designed for big endian hosts doing I/O to - * little endian controllers incorporating a 32-bit hardware byte swapper. - */ - -u32 sdhci_be32bs_readl(struct sdhci_host *host, int reg) -{ - return in_be32(host->ioaddr + reg); -} - -u16 sdhci_be32bs_readw(struct sdhci_host *host, int reg) -{ - return in_be16(host->ioaddr + (reg ^ 0x2)); -} - -u8 sdhci_be32bs_readb(struct sdhci_host *host, int reg) -{ - return in_8(host->ioaddr + (reg ^ 0x3)); -} - -void sdhci_be32bs_writel(struct sdhci_host *host, u32 val, int reg) -{ - out_be32(host->ioaddr + reg, val); -} - -void sdhci_be32bs_writew(struct sdhci_host *host, u16 val, int reg) -{ - struct sdhci_of_host *of_host = sdhci_priv(host); - int base = reg & ~0x3; - int shift = (reg & 0x2) * 8; - - switch (reg) { - case SDHCI_TRANSFER_MODE: - /* - * Postpone this write, we must do it together with a - * command write that is down below. - */ - of_host->xfer_mode_shadow = val; - return; - case SDHCI_COMMAND: - sdhci_be32bs_writel(host, val << 16 | of_host->xfer_mode_shadow, - SDHCI_TRANSFER_MODE); - return; - } - clrsetbits_be32(host->ioaddr + base, 0xffff << shift, val << shift); -} - -void sdhci_be32bs_writeb(struct sdhci_host *host, u8 val, int reg) -{ - int base = reg & ~0x3; - int shift = (reg & 0x3) * 8; - - clrsetbits_be32(host->ioaddr + base , 0xff << shift, val << shift); -} -#endif /* CONFIG_MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER */ - -#ifdef CONFIG_PM - -static int sdhci_of_suspend(struct platform_device *ofdev, pm_message_t state) -{ - struct sdhci_host *host = dev_get_drvdata(&ofdev->dev); - - return mmc_suspend_host(host->mmc); -} - -static int sdhci_of_resume(struct platform_device *ofdev) -{ - struct sdhci_host *host = dev_get_drvdata(&ofdev->dev); - - return mmc_resume_host(host->mmc); -} - -#else - -#define sdhci_of_suspend NULL -#define sdhci_of_resume NULL - -#endif - -static bool __devinit sdhci_of_wp_inverted(struct device_node *np) -{ - if (of_get_property(np, "sdhci,wp-inverted", NULL)) - return true; - - /* Old device trees don't have the wp-inverted property. */ -#ifdef CONFIG_PPC - return machine_is(mpc837x_rdb) || machine_is(mpc837x_mds); -#else - return false; -#endif -} - -static const struct of_device_id sdhci_of_match[]; -static int __devinit sdhci_of_probe(struct platform_device *ofdev) -{ - const struct of_device_id *match; - struct device_node *np = ofdev->dev.of_node; - struct sdhci_of_data *sdhci_of_data; - struct sdhci_host *host; - struct sdhci_of_host *of_host; - const __be32 *clk; - int size; - int ret; - - match = of_match_device(sdhci_of_match, &ofdev->dev); - if (!match) - return -EINVAL; - sdhci_of_data = match->data; - - if (!of_device_is_available(np)) - return -ENODEV; - - host = sdhci_alloc_host(&ofdev->dev, sizeof(*of_host)); - if (IS_ERR(host)) - return -ENOMEM; - - of_host = sdhci_priv(host); - dev_set_drvdata(&ofdev->dev, host); - - host->ioaddr = of_iomap(np, 0); - if (!host->ioaddr) { - ret = -ENOMEM; - goto err_addr_map; - } - - host->irq = irq_of_parse_and_map(np, 0); - if (!host->irq) { - ret = -EINVAL; - goto err_no_irq; - } - - host->hw_name = dev_name(&ofdev->dev); - if (sdhci_of_data) { - host->quirks = sdhci_of_data->quirks; - host->ops = &sdhci_of_data->ops; - } - - if (of_get_property(np, "sdhci,auto-cmd12", NULL)) - host->quirks |= SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12; - - - if (of_get_property(np, "sdhci,1-bit-only", NULL)) - host->quirks |= SDHCI_QUIRK_FORCE_1_BIT_DATA; - - if (sdhci_of_wp_inverted(np)) - host->quirks |= SDHCI_QUIRK_INVERTED_WRITE_PROTECT; - - clk = of_get_property(np, "clock-frequency", &size); - if (clk && size == sizeof(*clk) && *clk) - of_host->clock = be32_to_cpup(clk); - - ret = sdhci_add_host(host); - if (ret) - goto err_add_host; - - return 0; - -err_add_host: - irq_dispose_mapping(host->irq); -err_no_irq: - iounmap(host->ioaddr); -err_addr_map: - sdhci_free_host(host); - return ret; -} - -static int __devexit sdhci_of_remove(struct platform_device *ofdev) -{ - struct sdhci_host *host = dev_get_drvdata(&ofdev->dev); - - sdhci_remove_host(host, 0); - sdhci_free_host(host); - irq_dispose_mapping(host->irq); - iounmap(host->ioaddr); - return 0; -} - -static const struct of_device_id sdhci_of_match[] = { -#ifdef CONFIG_MMC_SDHCI_OF_ESDHC - { .compatible = "fsl,mpc8379-esdhc", .data = &sdhci_esdhc, }, - { .compatible = "fsl,mpc8536-esdhc", .data = &sdhci_esdhc, }, - { .compatible = "fsl,esdhc", .data = &sdhci_esdhc, }, -#endif -#ifdef CONFIG_MMC_SDHCI_OF_HLWD - { .compatible = "nintendo,hollywood-sdhci", .data = &sdhci_hlwd, }, -#endif - { .compatible = "generic-sdhci", }, - {}, -}; -MODULE_DEVICE_TABLE(of, sdhci_of_match); - -static struct platform_driver sdhci_of_driver = { - .driver = { - .name = "sdhci-of", - .owner = THIS_MODULE, - .of_match_table = sdhci_of_match, - }, - .probe = sdhci_of_probe, - .remove = __devexit_p(sdhci_of_remove), - .suspend = sdhci_of_suspend, - .resume = sdhci_of_resume, -}; - -static int __init sdhci_of_init(void) -{ - return platform_driver_register(&sdhci_of_driver); -} -module_init(sdhci_of_init); - -static void __exit sdhci_of_exit(void) -{ - platform_driver_unregister(&sdhci_of_driver); -} -module_exit(sdhci_of_exit); - -MODULE_DESCRIPTION("Secure Digital Host Controller Interface OF driver"); -MODULE_AUTHOR("Xiaobo Xie <X.Xie@freescale.com>, " - "Anton Vorontsov <avorontsov@ru.mvista.com>"); -MODULE_LICENSE("GPL"); diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index ba40d6d..fe604df 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -16,8 +16,7 @@ #include <linux/io.h> #include <linux/delay.h> #include <linux/mmc/host.h> -#include "sdhci-of.h" -#include "sdhci.h" +#include "sdhci-pltfm.h" #include "sdhci-esdhc.h" static u16 esdhc_readw(struct sdhci_host *host, int reg) @@ -60,32 +59,83 @@ static int esdhc_of_enable_dma(struct sdhci_host *host) static unsigned int esdhc_of_get_max_clock(struct sdhci_host *host) { - struct sdhci_of_host *of_host = sdhci_priv(host); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - return of_host->clock; + return pltfm_host->clock; } static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host) { - struct sdhci_of_host *of_host = sdhci_priv(host); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - return of_host->clock / 256 / 16; + return pltfm_host->clock / 256 / 16; } -struct sdhci_of_data sdhci_esdhc = { +static struct sdhci_ops sdhci_esdhc_ops = { + .read_l = sdhci_be32bs_readl, + .read_w = esdhc_readw, + .read_b = sdhci_be32bs_readb, + .write_l = sdhci_be32bs_writel, + .write_w = esdhc_writew, + .write_b = esdhc_writeb, + .set_clock = esdhc_set_clock, + .enable_dma = esdhc_of_enable_dma, + .get_max_clock = esdhc_of_get_max_clock, + .get_min_clock = esdhc_of_get_min_clock, +}; + +static struct sdhci_pltfm_data sdhci_esdhc_pdata = { /* card detection could be handled via GPIO */ .quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_CARD_DETECTION | SDHCI_QUIRK_NO_CARD_NO_RESET, - .ops = { - .read_l = sdhci_be32bs_readl, - .read_w = esdhc_readw, - .read_b = sdhci_be32bs_readb, - .write_l = sdhci_be32bs_writel, - .write_w = esdhc_writew, - .write_b = esdhc_writeb, - .set_clock = esdhc_set_clock, - .enable_dma = esdhc_of_enable_dma, - .get_max_clock = esdhc_of_get_max_clock, - .get_min_clock = esdhc_of_get_min_clock, + .ops = &sdhci_esdhc_ops, +}; + +static int __devinit sdhci_esdhc_probe(struct platform_device *pdev) +{ + return sdhci_pltfm_register(pdev, &sdhci_esdhc_pdata); +} + +static int __devexit sdhci_esdhc_remove(struct platform_device *pdev) +{ + return sdhci_pltfm_unregister(pdev); +} + +static const struct of_device_id sdhci_esdhc_of_match[] = { + { .compatible = "fsl,mpc8379-esdhc" }, + { .compatible = "fsl,mpc8536-esdhc" }, + { .compatible = "fsl,esdhc" }, + { } +}; +MODULE_DEVICE_TABLE(of, sdhci_esdhc_of_match); + +static struct platform_driver sdhci_esdhc_driver = { + .driver = { + .name = "sdhci-esdhc", + .owner = THIS_MODULE, + .of_match_table = sdhci_esdhc_of_match, }, + .probe = sdhci_esdhc_probe, + .remove = __devexit_p(sdhci_esdhc_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif }; + +static int __init sdhci_esdhc_init(void) +{ + return platform_driver_register(&sdhci_esdhc_driver); +} +module_init(sdhci_esdhc_init); + +static void __exit sdhci_esdhc_exit(void) +{ + platform_driver_unregister(&sdhci_esdhc_driver); +} +module_exit(sdhci_esdhc_exit); + +MODULE_DESCRIPTION("SDHCI OF driver for Freescale MPC eSDHC"); +MODULE_AUTHOR("Xiaobo Xie <X.Xie@freescale.com>, " + "Anton Vorontsov <avorontsov@ru.mvista.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-of-hlwd.c b/drivers/mmc/host/sdhci-of-hlwd.c index 68ddb75..735be13 100644 --- a/drivers/mmc/host/sdhci-of-hlwd.c +++ b/drivers/mmc/host/sdhci-of-hlwd.c @@ -21,8 +21,7 @@ #include <linux/delay.h> #include <linux/mmc/host.h> -#include "sdhci-of.h" -#include "sdhci.h" +#include "sdhci-pltfm.h" /* * Ops and quirks for the Nintendo Wii SDHCI controllers. @@ -51,15 +50,63 @@ static void sdhci_hlwd_writeb(struct sdhci_host *host, u8 val, int reg) udelay(SDHCI_HLWD_WRITE_DELAY); } -struct sdhci_of_data sdhci_hlwd = { +static struct sdhci_ops sdhci_hlwd_ops = { + .read_l = sdhci_be32bs_readl, + .read_w = sdhci_be32bs_readw, + .read_b = sdhci_be32bs_readb, + .write_l = sdhci_hlwd_writel, + .write_w = sdhci_hlwd_writew, + .write_b = sdhci_hlwd_writeb, +}; + +static struct sdhci_pltfm_data sdhci_hlwd_pdata = { .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE, - .ops = { - .read_l = sdhci_be32bs_readl, - .read_w = sdhci_be32bs_readw, - .read_b = sdhci_be32bs_readb, - .write_l = sdhci_hlwd_writel, - .write_w = sdhci_hlwd_writew, - .write_b = sdhci_hlwd_writeb, + .ops = &sdhci_hlwd_ops, +}; + +static int __devinit sdhci_hlwd_probe(struct platform_device *pdev) +{ + return sdhci_pltfm_register(pdev, &sdhci_hlwd_pdata); +} + +static int __devexit sdhci_hlwd_remove(struct platform_device *pdev) +{ + return sdhci_pltfm_unregister(pdev); +} + +static const struct of_device_id sdhci_hlwd_of_match[] = { + { .compatible = "nintendo,hollywood-sdhci" }, + { } +}; +MODULE_DEVICE_TABLE(of, sdhci_hlwd_of_match); + +static struct platform_driver sdhci_hlwd_driver = { + .driver = { + .name = "sdhci-hlwd", + .owner = THIS_MODULE, + .of_match_table = sdhci_hlwd_of_match, }, + .probe = sdhci_hlwd_probe, + .remove = __devexit_p(sdhci_hlwd_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif }; + +static int __init sdhci_hlwd_init(void) +{ + return platform_driver_register(&sdhci_hlwd_driver); +} +module_init(sdhci_hlwd_init); + +static void __exit sdhci_hlwd_exit(void) +{ + platform_driver_unregister(&sdhci_hlwd_driver); +} +module_exit(sdhci_hlwd_exit); + +MODULE_DESCRIPTION("Nintendo Wii SDHCI OF driver"); +MODULE_AUTHOR("The GameCube Linux Team, Albert Herranz"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-of.h b/drivers/mmc/host/sdhci-of.h deleted file mode 100644 index ad09ad9..0000000 --- a/drivers/mmc/host/sdhci-of.h +++ /dev/null @@ -1,42 +0,0 @@ -/* - * OpenFirmware bindings for Secure Digital Host Controller Interface. - * - * Copyright (c) 2007 Freescale Semiconductor, Inc. - * Copyright (c) 2009 MontaVista Software, Inc. - * - * Authors: Xiaobo Xie <X.Xie@freescale.com> - * Anton Vorontsov <avorontsov@ru.mvista.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - */ - -#ifndef __SDHCI_OF_H -#define __SDHCI_OF_H - -#include <linux/types.h> -#include "sdhci.h" - -struct sdhci_of_data { - unsigned int quirks; - struct sdhci_ops ops; -}; - -struct sdhci_of_host { - unsigned int clock; - u16 xfer_mode_shadow; -}; - -extern u32 sdhci_be32bs_readl(struct sdhci_host *host, int reg); -extern u16 sdhci_be32bs_readw(struct sdhci_host *host, int reg); -extern u8 sdhci_be32bs_readb(struct sdhci_host *host, int reg); -extern void sdhci_be32bs_writel(struct sdhci_host *host, u32 val, int reg); -extern void sdhci_be32bs_writew(struct sdhci_host *host, u16 val, int reg); -extern void sdhci_be32bs_writeb(struct sdhci_host *host, u8 val, int reg); - -extern struct sdhci_of_data sdhci_esdhc; -extern struct sdhci_of_data sdhci_hlwd; - -#endif /* __SDHCI_OF_H */ diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index 936bbca..26c5286 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -143,6 +143,12 @@ static const struct sdhci_pci_fixes sdhci_cafe = { SDHCI_QUIRK_BROKEN_TIMEOUT_VAL, }; +static int mrst_hc_probe_slot(struct sdhci_pci_slot *slot) +{ + slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA; + return 0; +} + /* * ADMA operation is disabled for Moorestown platform due to * hardware bugs. @@ -157,8 +163,15 @@ static int mrst_hc_probe(struct sdhci_pci_chip *chip) return 0; } +static int mfd_emmc_probe_slot(struct sdhci_pci_slot *slot) +{ + slot->host->mmc->caps |= MMC_CAP_8_BIT_DATA; + return 0; +} + static const struct sdhci_pci_fixes sdhci_intel_mrst_hc0 = { .quirks = SDHCI_QUIRK_BROKEN_ADMA | SDHCI_QUIRK_NO_HISPD_BIT, + .probe_slot = mrst_hc_probe_slot, }; static const struct sdhci_pci_fixes sdhci_intel_mrst_hc1_hc2 = { @@ -170,8 +183,13 @@ static const struct sdhci_pci_fixes sdhci_intel_mfd_sd = { .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC, }; -static const struct sdhci_pci_fixes sdhci_intel_mfd_emmc_sdio = { +static const struct sdhci_pci_fixes sdhci_intel_mfd_sdio = { + .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC, +}; + +static const struct sdhci_pci_fixes sdhci_intel_mfd_emmc = { .quirks = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC, + .probe_slot = mfd_emmc_probe_slot, }; /* O2Micro extra registers */ @@ -682,7 +700,7 @@ static const struct pci_device_id pci_ids[] __devinitdata = { .device = PCI_DEVICE_ID_INTEL_MFD_SDIO1, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, - .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_emmc_sdio, + .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_sdio, }, { @@ -690,7 +708,7 @@ static const struct pci_device_id pci_ids[] __devinitdata = { .device = PCI_DEVICE_ID_INTEL_MFD_SDIO2, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, - .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_emmc_sdio, + .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_sdio, }, { @@ -698,7 +716,7 @@ static const struct pci_device_id pci_ids[] __devinitdata = { .device = PCI_DEVICE_ID_INTEL_MFD_EMMC0, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, - .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_emmc_sdio, + .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_emmc, }, { @@ -706,7 +724,7 @@ static const struct pci_device_id pci_ids[] __devinitdata = { .device = PCI_DEVICE_ID_INTEL_MFD_EMMC1, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, - .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_emmc_sdio, + .driver_data = (kernel_ulong_t)&sdhci_intel_mfd_emmc, }, { @@ -789,8 +807,34 @@ static int sdhci_pci_enable_dma(struct sdhci_host *host) return 0; } +static int sdhci_pci_8bit_width(struct sdhci_host *host, int width) +{ + u8 ctrl; + + ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL); + + switch (width) { + case MMC_BUS_WIDTH_8: + ctrl |= SDHCI_CTRL_8BITBUS; + ctrl &= ~SDHCI_CTRL_4BITBUS; + break; + case MMC_BUS_WIDTH_4: + ctrl |= SDHCI_CTRL_4BITBUS; + ctrl &= ~SDHCI_CTRL_8BITBUS; + break; + default: + ctrl &= ~(SDHCI_CTRL_8BITBUS | SDHCI_CTRL_4BITBUS); + break; + } + + sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL); + + return 0; +} + static struct sdhci_ops sdhci_pci_ops = { .enable_dma = sdhci_pci_enable_dma, + .platform_8bit_width = sdhci_pci_8bit_width, }; /*****************************************************************************\ diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c index dbab040..71c0ce1 100644 --- a/drivers/mmc/host/sdhci-pltfm.c +++ b/drivers/mmc/host/sdhci-pltfm.c @@ -2,6 +2,12 @@ * sdhci-pltfm.c Support for SDHCI platform devices * Copyright (c) 2009 Intel Corporation * + * Copyright (c) 2007 Freescale Semiconductor, Inc. + * Copyright (c) 2009 MontaVista Software, Inc. + * + * Authors: Xiaobo Xie <X.Xie@freescale.com> + * Anton Vorontsov <avorontsov@ru.mvista.com> + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -22,48 +28,66 @@ * Inspired by sdhci-pci.c, by Pierre Ossman */ -#include <linux/delay.h> -#include <linux/highmem.h> -#include <linux/mod_devicetable.h> -#include <linux/platform_device.h> +#include <linux/err.h> +#include <linux/of.h> +#ifdef CONFIG_PPC +#include <asm/machdep.h> +#endif +#include "sdhci-pltfm.h" -#include <linux/mmc/host.h> +static struct sdhci_ops sdhci_pltfm_ops = { +}; -#include <linux/io.h> -#include <linux/mmc/sdhci-pltfm.h> +#ifdef CONFIG_OF +static bool sdhci_of_wp_inverted(struct device_node *np) +{ + if (of_get_property(np, "sdhci,wp-inverted", NULL)) + return true; -#include "sdhci.h" -#include "sdhci-pltfm.h" + /* Old device trees don't have the wp-inverted property. */ +#ifdef CONFIG_PPC + return machine_is(mpc837x_rdb) || machine_is(mpc837x_mds); +#else + return false; +#endif /* CONFIG_PPC */ +} + +void sdhci_get_of_property(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct sdhci_host *host = platform_get_drvdata(pdev); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + const __be32 *clk; + int size; -/*****************************************************************************\ - * * - * SDHCI core callbacks * - * * -\*****************************************************************************/ + if (of_device_is_available(np)) { + if (of_get_property(np, "sdhci,auto-cmd12", NULL)) + host->quirks |= SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12; -static struct sdhci_ops sdhci_pltfm_ops = { -}; + if (of_get_property(np, "sdhci,1-bit-only", NULL)) + host->quirks |= SDHCI_QUIRK_FORCE_1_BIT_DATA; -/*****************************************************************************\ - * * - * Device probing/removal * - * * -\*****************************************************************************/ + if (sdhci_of_wp_inverted(np)) + host->quirks |= SDHCI_QUIRK_INVERTED_WRITE_PROTECT; -static int __devinit sdhci_pltfm_probe(struct platform_device *pdev) + clk = of_get_property(np, "clock-frequency", &size); + if (clk && size == sizeof(*clk) && *clk) + pltfm_host->clock = be32_to_cpup(clk); + } +} +#else +void sdhci_get_of_property(struct platform_device *pdev) {} +#endif /* CONFIG_OF */ +EXPORT_SYMBOL_GPL(sdhci_get_of_property); + +struct sdhci_host *sdhci_pltfm_init(struct platform_device *pdev, + struct sdhci_pltfm_data *pdata) { - const struct platform_device_id *platid = platform_get_device_id(pdev); - struct sdhci_pltfm_data *pdata; struct sdhci_host *host; struct sdhci_pltfm_host *pltfm_host; struct resource *iomem; int ret; - if (platid && platid->driver_data) - pdata = (void *)platid->driver_data; - else - pdata = pdev->dev.platform_data; - iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!iomem) { ret = -ENOMEM; @@ -71,8 +95,7 @@ static int __devinit sdhci_pltfm_probe(struct platform_device *pdev) } if (resource_size(iomem) < 0x100) - dev_err(&pdev->dev, "Invalid iomem size. You may " - "experience problems.\n"); + dev_err(&pdev->dev, "Invalid iomem size!\n"); /* Some PCI-based MFD need the parent here */ if (pdev->dev.parent != &platform_bus) @@ -87,7 +110,7 @@ static int __devinit sdhci_pltfm_probe(struct platform_device *pdev) pltfm_host = sdhci_priv(host); - host->hw_name = "platform"; + host->hw_name = dev_name(&pdev->dev); if (pdata && pdata->ops) host->ops = pdata->ops; else @@ -110,126 +133,95 @@ static int __devinit sdhci_pltfm_probe(struct platform_device *pdev) goto err_remap; } - if (pdata && pdata->init) { - ret = pdata->init(host, pdata); - if (ret) - goto err_plat_init; - } - - ret = sdhci_add_host(host); - if (ret) - goto err_add_host; - platform_set_drvdata(pdev, host); - return 0; + return host; -err_add_host: - if (pdata && pdata->exit) - pdata->exit(host); -err_plat_init: - iounmap(host->ioaddr); err_remap: release_mem_region(iomem->start, resource_size(iomem)); err_request: sdhci_free_host(host); err: - printk(KERN_ERR"Probing of sdhci-pltfm failed: %d\n", ret); - return ret; + dev_err(&pdev->dev, "%s failed %d\n", __func__, ret); + return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(sdhci_pltfm_init); -static int __devexit sdhci_pltfm_remove(struct platform_device *pdev) +void sdhci_pltfm_free(struct platform_device *pdev) { - struct sdhci_pltfm_data *pdata = pdev->dev.platform_data; struct sdhci_host *host = platform_get_drvdata(pdev); struct resource *iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - int dead; - u32 scratch; - - dead = 0; - scratch = readl(host->ioaddr + SDHCI_INT_STATUS); - if (scratch == (u32)-1) - dead = 1; - sdhci_remove_host(host, dead); - if (pdata && pdata->exit) - pdata->exit(host); iounmap(host->ioaddr); release_mem_region(iomem->start, resource_size(iomem)); sdhci_free_host(host); platform_set_drvdata(pdev, NULL); +} +EXPORT_SYMBOL_GPL(sdhci_pltfm_free); - return 0; +int sdhci_pltfm_register(struct platform_device *pdev, + struct sdhci_pltfm_data *pdata) +{ + struct sdhci_host *host; + int ret = 0; + + host = sdhci_pltfm_init(pdev, pdata); + if (IS_ERR(host)) + return PTR_ERR(host); + + sdhci_get_of_property(pdev); + + ret = sdhci_add_host(host); + if (ret) + sdhci_pltfm_free(pdev); + + return ret; } +EXPORT_SYMBOL_GPL(sdhci_pltfm_register); -static const struct platform_device_id sdhci_pltfm_ids[] = { - { "sdhci", }, -#ifdef CONFIG_MMC_SDHCI_CNS3XXX - { "sdhci-cns3xxx", (kernel_ulong_t)&sdhci_cns3xxx_pdata }, -#endif -#ifdef CONFIG_MMC_SDHCI_ESDHC_IMX - { "sdhci-esdhc-imx", (kernel_ulong_t)&sdhci_esdhc_imx_pdata }, -#endif -#ifdef CONFIG_MMC_SDHCI_DOVE - { "sdhci-dove", (kernel_ulong_t)&sdhci_dove_pdata }, -#endif -#ifdef CONFIG_MMC_SDHCI_TEGRA - { "sdhci-tegra", (kernel_ulong_t)&sdhci_tegra_pdata }, -#endif - { }, -}; -MODULE_DEVICE_TABLE(platform, sdhci_pltfm_ids); +int sdhci_pltfm_unregister(struct platform_device *pdev) +{ + struct sdhci_host *host = platform_get_drvdata(pdev); + int dead = (readl(host->ioaddr + SDHCI_INT_STATUS) == 0xffffffff); + + sdhci_remove_host(host, dead); + sdhci_pltfm_free(pdev); + + return 0; +} +EXPORT_SYMBOL_GPL(sdhci_pltfm_unregister); #ifdef CONFIG_PM -static int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state) +int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state) { struct sdhci_host *host = platform_get_drvdata(dev); return sdhci_suspend_host(host, state); } +EXPORT_SYMBOL_GPL(sdhci_pltfm_suspend); -static int sdhci_pltfm_resume(struct platform_device *dev) +int sdhci_pltfm_resume(struct platform_device *dev) { struct sdhci_host *host = platform_get_drvdata(dev); return sdhci_resume_host(host); } -#else -#define sdhci_pltfm_suspend NULL -#define sdhci_pltfm_resume NULL +EXPORT_SYMBOL_GPL(sdhci_pltfm_resume); #endif /* CONFIG_PM */ -static struct platform_driver sdhci_pltfm_driver = { - .driver = { - .name = "sdhci", - .owner = THIS_MODULE, - }, - .probe = sdhci_pltfm_probe, - .remove = __devexit_p(sdhci_pltfm_remove), - .id_table = sdhci_pltfm_ids, - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -}; - -/*****************************************************************************\ - * * - * Driver init/exit * - * * -\*****************************************************************************/ - -static int __init sdhci_drv_init(void) +static int __init sdhci_pltfm_drv_init(void) { - return platform_driver_register(&sdhci_pltfm_driver); + pr_info("sdhci-pltfm: SDHCI platform and OF driver helper\n"); + + return 0; } +module_init(sdhci_pltfm_drv_init); -static void __exit sdhci_drv_exit(void) +static void __exit sdhci_pltfm_drv_exit(void) { - platform_driver_unregister(&sdhci_pltfm_driver); } +module_exit(sdhci_pltfm_drv_exit); -module_init(sdhci_drv_init); -module_exit(sdhci_drv_exit); - -MODULE_DESCRIPTION("Secure Digital Host Controller Interface platform driver"); -MODULE_AUTHOR("Mocean Laboratories <info@mocean-labs.com>"); +MODULE_DESCRIPTION("SDHCI platform and OF driver helper"); +MODULE_AUTHOR("Intel Corporation"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-pltfm.h b/drivers/mmc/host/sdhci-pltfm.h index 2b37016..3a9fc3f 100644 --- a/drivers/mmc/host/sdhci-pltfm.h +++ b/drivers/mmc/host/sdhci-pltfm.h @@ -12,17 +12,95 @@ #define _DRIVERS_MMC_SDHCI_PLTFM_H #include <linux/clk.h> -#include <linux/types.h> -#include <linux/mmc/sdhci-pltfm.h> +#include <linux/platform_device.h> +#include "sdhci.h" + +struct sdhci_pltfm_data { + struct sdhci_ops *ops; + unsigned int quirks; +}; struct sdhci_pltfm_host { struct clk *clk; void *priv; /* to handle quirks across io-accessor calls */ + + /* migrate from sdhci_of_host */ + unsigned int clock; + u16 xfer_mode_shadow; }; -extern struct sdhci_pltfm_data sdhci_cns3xxx_pdata; -extern struct sdhci_pltfm_data sdhci_esdhc_imx_pdata; -extern struct sdhci_pltfm_data sdhci_dove_pdata; -extern struct sdhci_pltfm_data sdhci_tegra_pdata; +#ifdef CONFIG_MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER +/* + * These accessors are designed for big endian hosts doing I/O to + * little endian controllers incorporating a 32-bit hardware byte swapper. + */ +static inline u32 sdhci_be32bs_readl(struct sdhci_host *host, int reg) +{ + return in_be32(host->ioaddr + reg); +} + +static inline u16 sdhci_be32bs_readw(struct sdhci_host *host, int reg) +{ + return in_be16(host->ioaddr + (reg ^ 0x2)); +} + +static inline u8 sdhci_be32bs_readb(struct sdhci_host *host, int reg) +{ + return in_8(host->ioaddr + (reg ^ 0x3)); +} + +static inline void sdhci_be32bs_writel(struct sdhci_host *host, + u32 val, int reg) +{ + out_be32(host->ioaddr + reg, val); +} + +static inline void sdhci_be32bs_writew(struct sdhci_host *host, + u16 val, int reg) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + int base = reg & ~0x3; + int shift = (reg & 0x2) * 8; + + switch (reg) { + case SDHCI_TRANSFER_MODE: + /* + * Postpone this write, we must do it together with a + * command write that is down below. + */ + pltfm_host->xfer_mode_shadow = val; + return; + case SDHCI_COMMAND: + sdhci_be32bs_writel(host, + val << 16 | pltfm_host->xfer_mode_shadow, + SDHCI_TRANSFER_MODE); + return; + } + clrsetbits_be32(host->ioaddr + base, 0xffff << shift, val << shift); +} + +static inline void sdhci_be32bs_writeb(struct sdhci_host *host, u8 val, int reg) +{ + int base = reg & ~0x3; + int shift = (reg & 0x3) * 8; + + clrsetbits_be32(host->ioaddr + base , 0xff << shift, val << shift); +} +#endif /* CONFIG_MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER */ + +extern void sdhci_get_of_property(struct platform_device *pdev); + +extern struct sdhci_host *sdhci_pltfm_init(struct platform_device *pdev, + struct sdhci_pltfm_data *pdata); +extern void sdhci_pltfm_free(struct platform_device *pdev); + +extern int sdhci_pltfm_register(struct platform_device *pdev, + struct sdhci_pltfm_data *pdata); +extern int sdhci_pltfm_unregister(struct platform_device *pdev); + +#ifdef CONFIG_PM +extern int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state); +extern int sdhci_pltfm_resume(struct platform_device *dev); +#endif #endif /* _DRIVERS_MMC_SDHCI_PLTFM_H */ diff --git a/drivers/mmc/host/sdhci-pxa.c b/drivers/mmc/host/sdhci-pxa.c deleted file mode 100644 index 089c9a6..0000000 --- a/drivers/mmc/host/sdhci-pxa.c +++ /dev/null @@ -1,303 +0,0 @@ -/* linux/drivers/mmc/host/sdhci-pxa.c - * - * Copyright (C) 2010 Marvell International Ltd. - * Zhangfei Gao <zhangfei.gao@marvell.com> - * Kevin Wang <dwang4@marvell.com> - * Mingwei Wang <mwwang@marvell.com> - * Philip Rakity <prakity@marvell.com> - * Mark Brown <markb@marvell.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -/* Supports: - * SDHCI support for MMP2/PXA910/PXA168 - * - * Refer to sdhci-s3c.c. - */ - -#include <linux/delay.h> -#include <linux/platform_device.h> -#include <linux/mmc/host.h> -#include <linux/clk.h> -#include <linux/io.h> -#include <linux/err.h> -#include <plat/sdhci.h> -#include "sdhci.h" - -#define DRIVER_NAME "sdhci-pxa" - -#define SD_FIFO_PARAM 0x104 -#define DIS_PAD_SD_CLK_GATE 0x400 - -struct sdhci_pxa { - struct sdhci_host *host; - struct sdhci_pxa_platdata *pdata; - struct clk *clk; - struct resource *res; - - u8 clk_enable; -}; - -/*****************************************************************************\ - * * - * SDHCI core callbacks * - * * -\*****************************************************************************/ -static void set_clock(struct sdhci_host *host, unsigned int clock) -{ - struct sdhci_pxa *pxa = sdhci_priv(host); - u32 tmp = 0; - - if (clock == 0) { - if (pxa->clk_enable) { - clk_disable(pxa->clk); - pxa->clk_enable = 0; - } - } else { - if (0 == pxa->clk_enable) { - if (pxa->pdata->flags & PXA_FLAG_DISABLE_CLOCK_GATING) { - tmp = readl(host->ioaddr + SD_FIFO_PARAM); - tmp |= DIS_PAD_SD_CLK_GATE; - writel(tmp, host->ioaddr + SD_FIFO_PARAM); - } - clk_enable(pxa->clk); - pxa->clk_enable = 1; - } - } -} - -static int set_uhs_signaling(struct sdhci_host *host, unsigned int uhs) -{ - u16 ctrl_2; - - /* - * Set V18_EN -- UHS modes do not work without this. - * does not change signaling voltage - */ - ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2); - - /* Select Bus Speed Mode for host */ - ctrl_2 &= ~SDHCI_CTRL_UHS_MASK; - switch (uhs) { - case MMC_TIMING_UHS_SDR12: - ctrl_2 |= SDHCI_CTRL_UHS_SDR12; - break; - case MMC_TIMING_UHS_SDR25: - ctrl_2 |= SDHCI_CTRL_UHS_SDR25; - break; - case MMC_TIMING_UHS_SDR50: - ctrl_2 |= SDHCI_CTRL_UHS_SDR50 | SDHCI_CTRL_VDD_180; - break; - case MMC_TIMING_UHS_SDR104: - ctrl_2 |= SDHCI_CTRL_UHS_SDR104 | SDHCI_CTRL_VDD_180; - break; - case MMC_TIMING_UHS_DDR50: - ctrl_2 |= SDHCI_CTRL_UHS_DDR50 | SDHCI_CTRL_VDD_180; - break; - } - - sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2); - pr_debug("%s:%s uhs = %d, ctrl_2 = %04X\n", - __func__, mmc_hostname(host->mmc), uhs, ctrl_2); - - return 0; -} - -static struct sdhci_ops sdhci_pxa_ops = { - .set_uhs_signaling = set_uhs_signaling, - .set_clock = set_clock, -}; - -/*****************************************************************************\ - * * - * Device probing/removal * - * * -\*****************************************************************************/ - -static int __devinit sdhci_pxa_probe(struct platform_device *pdev) -{ - struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data; - struct device *dev = &pdev->dev; - struct sdhci_host *host = NULL; - struct resource *iomem = NULL; - struct sdhci_pxa *pxa = NULL; - int ret, irq; - - irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "no irq specified\n"); - return irq; - } - - iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!iomem) { - dev_err(dev, "no memory specified\n"); - return -ENOENT; - } - - host = sdhci_alloc_host(&pdev->dev, sizeof(struct sdhci_pxa)); - if (IS_ERR(host)) { - dev_err(dev, "failed to alloc host\n"); - return PTR_ERR(host); - } - - pxa = sdhci_priv(host); - pxa->host = host; - pxa->pdata = pdata; - pxa->clk_enable = 0; - - pxa->clk = clk_get(dev, "PXA-SDHCLK"); - if (IS_ERR(pxa->clk)) { - dev_err(dev, "failed to get io clock\n"); - ret = PTR_ERR(pxa->clk); - goto out; - } - - pxa->res = request_mem_region(iomem->start, resource_size(iomem), - mmc_hostname(host->mmc)); - if (!pxa->res) { - dev_err(&pdev->dev, "cannot request region\n"); - ret = -EBUSY; - goto out; - } - - host->ioaddr = ioremap(iomem->start, resource_size(iomem)); - if (!host->ioaddr) { - dev_err(&pdev->dev, "failed to remap registers\n"); - ret = -ENOMEM; - goto out; - } - - host->hw_name = "MMC"; - host->ops = &sdhci_pxa_ops; - host->irq = irq; - host->quirks = SDHCI_QUIRK_BROKEN_ADMA - | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL - | SDHCI_QUIRK_32BIT_DMA_ADDR - | SDHCI_QUIRK_32BIT_DMA_SIZE - | SDHCI_QUIRK_32BIT_ADMA_SIZE - | SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC; - - if (pdata->quirks) - host->quirks |= pdata->quirks; - - /* enable 1/8V DDR capable */ - host->mmc->caps |= MMC_CAP_1_8V_DDR; - - /* If slot design supports 8 bit data, indicate this to MMC. */ - if (pdata->flags & PXA_FLAG_SD_8_BIT_CAPABLE_SLOT) - host->mmc->caps |= MMC_CAP_8_BIT_DATA; - - ret = sdhci_add_host(host); - if (ret) { - dev_err(&pdev->dev, "failed to add host\n"); - goto out; - } - - if (pxa->pdata->max_speed) - host->mmc->f_max = pxa->pdata->max_speed; - - platform_set_drvdata(pdev, host); - - return 0; -out: - if (host) { - clk_put(pxa->clk); - if (host->ioaddr) - iounmap(host->ioaddr); - if (pxa->res) - release_mem_region(pxa->res->start, - resource_size(pxa->res)); - sdhci_free_host(host); - } - - return ret; -} - -static int __devexit sdhci_pxa_remove(struct platform_device *pdev) -{ - struct sdhci_host *host = platform_get_drvdata(pdev); - struct sdhci_pxa *pxa = sdhci_priv(host); - int dead = 0; - u32 scratch; - - if (host) { - scratch = readl(host->ioaddr + SDHCI_INT_STATUS); - if (scratch == (u32)-1) - dead = 1; - - sdhci_remove_host(host, dead); - - if (host->ioaddr) - iounmap(host->ioaddr); - if (pxa->res) - release_mem_region(pxa->res->start, - resource_size(pxa->res)); - if (pxa->clk_enable) { - clk_disable(pxa->clk); - pxa->clk_enable = 0; - } - clk_put(pxa->clk); - - sdhci_free_host(host); - platform_set_drvdata(pdev, NULL); - } - - return 0; -} - -#ifdef CONFIG_PM -static int sdhci_pxa_suspend(struct platform_device *dev, pm_message_t state) -{ - struct sdhci_host *host = platform_get_drvdata(dev); - - return sdhci_suspend_host(host, state); -} - -static int sdhci_pxa_resume(struct platform_device *dev) -{ - struct sdhci_host *host = platform_get_drvdata(dev); - - return sdhci_resume_host(host); -} -#else -#define sdhci_pxa_suspend NULL -#define sdhci_pxa_resume NULL -#endif - -static struct platform_driver sdhci_pxa_driver = { - .probe = sdhci_pxa_probe, - .remove = __devexit_p(sdhci_pxa_remove), - .suspend = sdhci_pxa_suspend, - .resume = sdhci_pxa_resume, - .driver = { - .name = DRIVER_NAME, - .owner = THIS_MODULE, - }, -}; - -/*****************************************************************************\ - * * - * Driver init/exit * - * * -\*****************************************************************************/ - -static int __init sdhci_pxa_init(void) -{ - return platform_driver_register(&sdhci_pxa_driver); -} - -static void __exit sdhci_pxa_exit(void) -{ - platform_driver_unregister(&sdhci_pxa_driver); -} - -module_init(sdhci_pxa_init); -module_exit(sdhci_pxa_exit); - -MODULE_DESCRIPTION("SDH controller driver for PXA168/PXA910/MMP2"); -MODULE_AUTHOR("Zhangfei Gao <zhangfei.gao@marvell.com>"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c new file mode 100644 index 0000000..38f5899 --- /dev/null +++ b/drivers/mmc/host/sdhci-pxav2.c @@ -0,0 +1,244 @@ +/* + * Copyright (C) 2010 Marvell International Ltd. + * Zhangfei Gao <zhangfei.gao@marvell.com> + * Kevin Wang <dwang4@marvell.com> + * Jun Nie <njun@marvell.com> + * Qiming Wu <wuqm@marvell.com> + * Philip Rakity <prakity@marvell.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/err.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/clk.h> +#include <linux/io.h> +#include <linux/gpio.h> +#include <linux/mmc/card.h> +#include <linux/mmc/host.h> +#include <linux/platform_data/pxa_sdhci.h> +#include <linux/slab.h> +#include "sdhci.h" +#include "sdhci-pltfm.h" + +#define SD_FIFO_PARAM 0xe0 +#define DIS_PAD_SD_CLK_GATE 0x0400 /* Turn on/off Dynamic SD Clock Gating */ +#define CLK_GATE_ON 0x0200 /* Disable/enable Clock Gate */ +#define CLK_GATE_CTL 0x0100 /* Clock Gate Control */ +#define CLK_GATE_SETTING_BITS (DIS_PAD_SD_CLK_GATE | \ + CLK_GATE_ON | CLK_GATE_CTL) + +#define SD_CLOCK_BURST_SIZE_SETUP 0xe6 +#define SDCLK_SEL_SHIFT 8 +#define SDCLK_SEL_MASK 0x3 +#define SDCLK_DELAY_SHIFT 10 +#define SDCLK_DELAY_MASK 0x3c + +#define SD_CE_ATA_2 0xea +#define MMC_CARD 0x1000 +#define MMC_WIDTH 0x0100 + +static void pxav2_set_private_registers(struct sdhci_host *host, u8 mask) +{ + struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc)); + struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data; + + if (mask == SDHCI_RESET_ALL) { + u16 tmp = 0; + + /* + * tune timing of read data/command when crc error happen + * no performance impact + */ + if (pdata->clk_delay_sel == 1) { + tmp = readw(host->ioaddr + SD_CLOCK_BURST_SIZE_SETUP); + + tmp &= ~(SDCLK_DELAY_MASK << SDCLK_DELAY_SHIFT); + tmp |= (pdata->clk_delay_cycles & SDCLK_DELAY_MASK) + << SDCLK_DELAY_SHIFT; + tmp &= ~(SDCLK_SEL_MASK << SDCLK_SEL_SHIFT); + tmp |= (1 & SDCLK_SEL_MASK) << SDCLK_SEL_SHIFT; + + writew(tmp, host->ioaddr + SD_CLOCK_BURST_SIZE_SETUP); + } + + if (pdata->flags & PXA_FLAG_ENABLE_CLOCK_GATING) { + tmp = readw(host->ioaddr + SD_FIFO_PARAM); + tmp &= ~CLK_GATE_SETTING_BITS; + writew(tmp, host->ioaddr + SD_FIFO_PARAM); + } else { + tmp = readw(host->ioaddr + SD_FIFO_PARAM); + tmp &= ~CLK_GATE_SETTING_BITS; + tmp |= CLK_GATE_SETTING_BITS; + writew(tmp, host->ioaddr + SD_FIFO_PARAM); + } + } +} + +static int pxav2_mmc_set_width(struct sdhci_host *host, int width) +{ + u8 ctrl; + u16 tmp; + + ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL); + tmp = readw(host->ioaddr + SD_CE_ATA_2); + if (width == MMC_BUS_WIDTH_8) { + ctrl &= ~SDHCI_CTRL_4BITBUS; + tmp |= MMC_CARD | MMC_WIDTH; + } else { + tmp &= ~(MMC_CARD | MMC_WIDTH); + if (width == MMC_BUS_WIDTH_4) + ctrl |= SDHCI_CTRL_4BITBUS; + else + ctrl &= ~SDHCI_CTRL_4BITBUS; + } + writew(tmp, host->ioaddr + SD_CE_ATA_2); + writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL); + + return 0; +} + +static u32 pxav2_get_max_clock(struct sdhci_host *host) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + + return clk_get_rate(pltfm_host->clk); +} + +static struct sdhci_ops pxav2_sdhci_ops = { + .get_max_clock = pxav2_get_max_clock, + .platform_reset_exit = pxav2_set_private_registers, + .platform_8bit_width = pxav2_mmc_set_width, +}; + +static int __devinit sdhci_pxav2_probe(struct platform_device *pdev) +{ + struct sdhci_pltfm_host *pltfm_host; + struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data; + struct device *dev = &pdev->dev; + struct sdhci_host *host = NULL; + struct sdhci_pxa *pxa = NULL; + int ret; + struct clk *clk; + + pxa = kzalloc(sizeof(struct sdhci_pxa), GFP_KERNEL); + if (!pxa) + return -ENOMEM; + + host = sdhci_pltfm_init(pdev, NULL); + if (IS_ERR(host)) { + kfree(pxa); + return PTR_ERR(host); + } + pltfm_host = sdhci_priv(host); + pltfm_host->priv = pxa; + + clk = clk_get(dev, "PXA-SDHCLK"); + if (IS_ERR(clk)) { + dev_err(dev, "failed to get io clock\n"); + ret = PTR_ERR(clk); + goto err_clk_get; + } + pltfm_host->clk = clk; + clk_enable(clk); + + host->quirks = SDHCI_QUIRK_BROKEN_ADMA + | SDHCI_QUIRK_BROKEN_TIMEOUT_VAL + | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN; + + if (pdata) { + if (pdata->flags & PXA_FLAG_CARD_PERMANENT) { + /* on-chip device */ + host->quirks |= SDHCI_QUIRK_BROKEN_CARD_DETECTION; + host->mmc->caps |= MMC_CAP_NONREMOVABLE; + } + + /* If slot design supports 8 bit data, indicate this to MMC. */ + if (pdata->flags & PXA_FLAG_SD_8_BIT_CAPABLE_SLOT) + host->mmc->caps |= MMC_CAP_8_BIT_DATA; + + if (pdata->quirks) + host->quirks |= pdata->quirks; + if (pdata->host_caps) + host->mmc->caps |= pdata->host_caps; + if (pdata->pm_caps) + host->mmc->pm_caps |= pdata->pm_caps; + } + + host->ops = &pxav2_sdhci_ops; + + ret = sdhci_add_host(host); + if (ret) { + dev_err(&pdev->dev, "failed to add host\n"); + goto err_add_host; + } + + platform_set_drvdata(pdev, host); + + return 0; + +err_add_host: + clk_disable(clk); + clk_put(clk); +err_clk_get: + sdhci_pltfm_free(pdev); + kfree(pxa); + return ret; +} + +static int __devexit sdhci_pxav2_remove(struct platform_device *pdev) +{ + struct sdhci_host *host = platform_get_drvdata(pdev); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_pxa *pxa = pltfm_host->priv; + + sdhci_remove_host(host, 1); + + clk_disable(pltfm_host->clk); + clk_put(pltfm_host->clk); + sdhci_pltfm_free(pdev); + kfree(pxa); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static struct platform_driver sdhci_pxav2_driver = { + .driver = { + .name = "sdhci-pxav2", + .owner = THIS_MODULE, + }, + .probe = sdhci_pxav2_probe, + .remove = __devexit_p(sdhci_pxav2_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif +}; +static int __init sdhci_pxav2_init(void) +{ + return platform_driver_register(&sdhci_pxav2_driver); +} + +static void __exit sdhci_pxav2_exit(void) +{ + platform_driver_unregister(&sdhci_pxav2_driver); +} + +module_init(sdhci_pxav2_init); +module_exit(sdhci_pxav2_exit); + +MODULE_DESCRIPTION("SDHCI driver for pxav2"); +MODULE_AUTHOR("Marvell International Ltd."); +MODULE_LICENSE("GPL v2"); + diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c new file mode 100644 index 0000000..4198dbb --- /dev/null +++ b/drivers/mmc/host/sdhci-pxav3.c @@ -0,0 +1,289 @@ +/* + * Copyright (C) 2010 Marvell International Ltd. + * Zhangfei Gao <zhangfei.gao@marvell.com> + * Kevin Wang <dwang4@marvell.com> + * Mingwei Wang <mwwang@marvell.com> + * Philip Rakity <prakity@marvell.com> + * Mark Brown <markb@marvell.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#include <linux/err.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/clk.h> +#include <linux/io.h> +#include <linux/gpio.h> +#include <linux/mmc/card.h> +#include <linux/mmc/host.h> +#include <linux/platform_data/pxa_sdhci.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include "sdhci.h" +#include "sdhci-pltfm.h" + +#define SD_CLOCK_BURST_SIZE_SETUP 0x10A +#define SDCLK_SEL 0x100 +#define SDCLK_DELAY_SHIFT 9 +#define SDCLK_DELAY_MASK 0x1f + +#define SD_CFG_FIFO_PARAM 0x100 +#define SDCFG_GEN_PAD_CLK_ON (1<<6) +#define SDCFG_GEN_PAD_CLK_CNT_MASK 0xFF +#define SDCFG_GEN_PAD_CLK_CNT_SHIFT 24 + +#define SD_SPI_MODE 0x108 +#define SD_CE_ATA_1 0x10C + +#define SD_CE_ATA_2 0x10E +#define SDCE_MISC_INT (1<<2) +#define SDCE_MISC_INT_EN (1<<1) + +static void pxav3_set_private_registers(struct sdhci_host *host, u8 mask) +{ + struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc)); + struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data; + + if (mask == SDHCI_RESET_ALL) { + /* + * tune timing of read data/command when crc error happen + * no performance impact + */ + if (pdata && 0 != pdata->clk_delay_cycles) { + u16 tmp; + + tmp = readw(host->ioaddr + SD_CLOCK_BURST_SIZE_SETUP); + tmp |= (pdata->clk_delay_cycles & SDCLK_DELAY_MASK) + << SDCLK_DELAY_SHIFT; + tmp |= SDCLK_SEL; + writew(tmp, host->ioaddr + SD_CLOCK_BURST_SIZE_SETUP); + } + } +} + +#define MAX_WAIT_COUNT 5 +static void pxav3_gen_init_74_clocks(struct sdhci_host *host, u8 power_mode) +{ + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_pxa *pxa = pltfm_host->priv; + u16 tmp; + int count; + + if (pxa->power_mode == MMC_POWER_UP + && power_mode == MMC_POWER_ON) { + + dev_dbg(mmc_dev(host->mmc), + "%s: slot->power_mode = %d," + "ios->power_mode = %d\n", + __func__, + pxa->power_mode, + power_mode); + + /* set we want notice of when 74 clocks are sent */ + tmp = readw(host->ioaddr + SD_CE_ATA_2); + tmp |= SDCE_MISC_INT_EN; + writew(tmp, host->ioaddr + SD_CE_ATA_2); + + /* start sending the 74 clocks */ + tmp = readw(host->ioaddr + SD_CFG_FIFO_PARAM); + tmp |= SDCFG_GEN_PAD_CLK_ON; + writew(tmp, host->ioaddr + SD_CFG_FIFO_PARAM); + + /* slowest speed is about 100KHz or 10usec per clock */ + udelay(740); + count = 0; + + while (count++ < MAX_WAIT_COUNT) { + if ((readw(host->ioaddr + SD_CE_ATA_2) + & SDCE_MISC_INT) == 0) + break; + udelay(10); + } + + if (count == MAX_WAIT_COUNT) + dev_warn(mmc_dev(host->mmc), "74 clock interrupt not cleared\n"); + + /* clear the interrupt bit if posted */ + tmp = readw(host->ioaddr + SD_CE_ATA_2); + tmp |= SDCE_MISC_INT; + writew(tmp, host->ioaddr + SD_CE_ATA_2); + } + pxa->power_mode = power_mode; +} + +static int pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs) +{ + u16 ctrl_2; + + /* + * Set V18_EN -- UHS modes do not work without this. + * does not change signaling voltage + */ + ctrl_2 = sdhci_readw(host, SDHCI_HOST_CONTROL2); + + /* Select Bus Speed Mode for host */ + ctrl_2 &= ~SDHCI_CTRL_UHS_MASK; + switch (uhs) { + case MMC_TIMING_UHS_SDR12: + ctrl_2 |= SDHCI_CTRL_UHS_SDR12; + break; + case MMC_TIMING_UHS_SDR25: + ctrl_2 |= SDHCI_CTRL_UHS_SDR25; + break; + case MMC_TIMING_UHS_SDR50: + ctrl_2 |= SDHCI_CTRL_UHS_SDR50 | SDHCI_CTRL_VDD_180; + break; + case MMC_TIMING_UHS_SDR104: + ctrl_2 |= SDHCI_CTRL_UHS_SDR104 | SDHCI_CTRL_VDD_180; + break; + case MMC_TIMING_UHS_DDR50: + ctrl_2 |= SDHCI_CTRL_UHS_DDR50 | SDHCI_CTRL_VDD_180; + break; + } + + sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2); + dev_dbg(mmc_dev(host->mmc), + "%s uhs = %d, ctrl_2 = %04X\n", + __func__, uhs, ctrl_2); + + return 0; +} + +static struct sdhci_ops pxav3_sdhci_ops = { + .platform_reset_exit = pxav3_set_private_registers, + .set_uhs_signaling = pxav3_set_uhs_signaling, + .platform_send_init_74_clocks = pxav3_gen_init_74_clocks, +}; + +static int __devinit sdhci_pxav3_probe(struct platform_device *pdev) +{ + struct sdhci_pltfm_host *pltfm_host; + struct sdhci_pxa_platdata *pdata = pdev->dev.platform_data; + struct device *dev = &pdev->dev; + struct sdhci_host *host = NULL; + struct sdhci_pxa *pxa = NULL; + int ret; + struct clk *clk; + + pxa = kzalloc(sizeof(struct sdhci_pxa), GFP_KERNEL); + if (!pxa) + return -ENOMEM; + + host = sdhci_pltfm_init(pdev, NULL); + if (IS_ERR(host)) { + kfree(pxa); + return PTR_ERR(host); + } + pltfm_host = sdhci_priv(host); + pltfm_host->priv = pxa; + + clk = clk_get(dev, "PXA-SDHCLK"); + if (IS_ERR(clk)) { + dev_err(dev, "failed to get io clock\n"); + ret = PTR_ERR(clk); + goto err_clk_get; + } + pltfm_host->clk = clk; + clk_enable(clk); + + host->quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL + | SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC; + + /* enable 1/8V DDR capable */ + host->mmc->caps |= MMC_CAP_1_8V_DDR; + + if (pdata) { + if (pdata->flags & PXA_FLAG_CARD_PERMANENT) { + /* on-chip device */ + host->quirks |= SDHCI_QUIRK_BROKEN_CARD_DETECTION; + host->mmc->caps |= MMC_CAP_NONREMOVABLE; + } + + /* If slot design supports 8 bit data, indicate this to MMC. */ + if (pdata->flags & PXA_FLAG_SD_8_BIT_CAPABLE_SLOT) + host->mmc->caps |= MMC_CAP_8_BIT_DATA; + + if (pdata->quirks) + host->quirks |= pdata->quirks; + if (pdata->host_caps) + host->mmc->caps |= pdata->host_caps; + if (pdata->pm_caps) + host->mmc->pm_caps |= pdata->pm_caps; + } + + host->ops = &pxav3_sdhci_ops; + + ret = sdhci_add_host(host); + if (ret) { + dev_err(&pdev->dev, "failed to add host\n"); + goto err_add_host; + } + + platform_set_drvdata(pdev, host); + + return 0; + +err_add_host: + clk_disable(clk); + clk_put(clk); +err_clk_get: + sdhci_pltfm_free(pdev); + kfree(pxa); + return ret; +} + +static int __devexit sdhci_pxav3_remove(struct platform_device *pdev) +{ + struct sdhci_host *host = platform_get_drvdata(pdev); + struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); + struct sdhci_pxa *pxa = pltfm_host->priv; + + sdhci_remove_host(host, 1); + + clk_disable(pltfm_host->clk); + clk_put(pltfm_host->clk); + sdhci_pltfm_free(pdev); + kfree(pxa); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static struct platform_driver sdhci_pxav3_driver = { + .driver = { + .name = "sdhci-pxav3", + .owner = THIS_MODULE, + }, + .probe = sdhci_pxav3_probe, + .remove = __devexit_p(sdhci_pxav3_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif +}; +static int __init sdhci_pxav3_init(void) +{ + return platform_driver_register(&sdhci_pxav3_driver); +} + +static void __exit sdhci_pxav3_exit(void) +{ + platform_driver_unregister(&sdhci_pxav3_driver); +} + +module_init(sdhci_pxav3_init); +module_exit(sdhci_pxav3_exit); + +MODULE_DESCRIPTION("SDHCI driver for pxav3"); +MODULE_AUTHOR("Marvell International Ltd."); +MODULE_LICENSE("GPL v2"); + diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c index 69e3ee3..460ffaf 100644 --- a/drivers/mmc/host/sdhci-s3c.c +++ b/drivers/mmc/host/sdhci-s3c.c @@ -612,16 +612,14 @@ static int sdhci_s3c_suspend(struct platform_device *dev, pm_message_t pm) { struct sdhci_host *host = platform_get_drvdata(dev); - sdhci_suspend_host(host, pm); - return 0; + return sdhci_suspend_host(host, pm); } static int sdhci_s3c_resume(struct platform_device *dev) { struct sdhci_host *host = platform_get_drvdata(dev); - sdhci_resume_host(host); - return 0; + return sdhci_resume_host(host); } #else diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 343c97e..18b0bd3 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -24,7 +24,6 @@ #include <mach/gpio.h> #include <mach/sdhci.h> -#include "sdhci.h" #include "sdhci-pltfm.h" static u32 tegra_sdhci_readl(struct sdhci_host *host, int reg) @@ -116,20 +115,42 @@ static int tegra_sdhci_8bit(struct sdhci_host *host, int bus_width) return 0; } +static struct sdhci_ops tegra_sdhci_ops = { + .get_ro = tegra_sdhci_get_ro, + .read_l = tegra_sdhci_readl, + .read_w = tegra_sdhci_readw, + .write_l = tegra_sdhci_writel, + .platform_8bit_width = tegra_sdhci_8bit, +}; + +static struct sdhci_pltfm_data sdhci_tegra_pdata = { + .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | + SDHCI_QUIRK_SINGLE_POWER_WRITE | + SDHCI_QUIRK_NO_HISPD_BIT | + SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC, + .ops = &tegra_sdhci_ops, +}; -static int tegra_sdhci_pltfm_init(struct sdhci_host *host, - struct sdhci_pltfm_data *pdata) +static int __devinit sdhci_tegra_probe(struct platform_device *pdev) { - struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc)); + struct sdhci_pltfm_host *pltfm_host; struct tegra_sdhci_platform_data *plat; + struct sdhci_host *host; struct clk *clk; int rc; + host = sdhci_pltfm_init(pdev, &sdhci_tegra_pdata); + if (IS_ERR(host)) + return PTR_ERR(host); + + pltfm_host = sdhci_priv(host); + plat = pdev->dev.platform_data; + if (plat == NULL) { dev_err(mmc_dev(host->mmc), "missing platform data\n"); - return -ENXIO; + rc = -ENXIO; + goto err_no_plat; } if (gpio_is_valid(plat->power_gpio)) { @@ -137,7 +158,7 @@ static int tegra_sdhci_pltfm_init(struct sdhci_host *host, if (rc) { dev_err(mmc_dev(host->mmc), "failed to allocate power gpio\n"); - goto out; + goto err_power_req; } tegra_gpio_enable(plat->power_gpio); gpio_direction_output(plat->power_gpio, 1); @@ -148,7 +169,7 @@ static int tegra_sdhci_pltfm_init(struct sdhci_host *host, if (rc) { dev_err(mmc_dev(host->mmc), "failed to allocate cd gpio\n"); - goto out_power; + goto err_cd_req; } tegra_gpio_enable(plat->cd_gpio); gpio_direction_input(plat->cd_gpio); @@ -159,7 +180,7 @@ static int tegra_sdhci_pltfm_init(struct sdhci_host *host, if (rc) { dev_err(mmc_dev(host->mmc), "request irq error\n"); - goto out_cd; + goto err_cd_irq_req; } } @@ -169,7 +190,7 @@ static int tegra_sdhci_pltfm_init(struct sdhci_host *host, if (rc) { dev_err(mmc_dev(host->mmc), "failed to allocate wp gpio\n"); - goto out_irq; + goto err_wp_req; } tegra_gpio_enable(plat->wp_gpio); gpio_direction_input(plat->wp_gpio); @@ -179,7 +200,7 @@ static int tegra_sdhci_pltfm_init(struct sdhci_host *host, if (IS_ERR(clk)) { dev_err(mmc_dev(host->mmc), "clk err\n"); rc = PTR_ERR(clk); - goto out_wp; + goto err_clk_get; } clk_enable(clk); pltfm_host->clk = clk; @@ -189,38 +210,47 @@ static int tegra_sdhci_pltfm_init(struct sdhci_host *host, if (plat->is_8bit) host->mmc->caps |= MMC_CAP_8_BIT_DATA; + rc = sdhci_add_host(host); + if (rc) + goto err_add_host; + return 0; -out_wp: +err_add_host: + clk_disable(pltfm_host->clk); + clk_put(pltfm_host->clk); +err_clk_get: if (gpio_is_valid(plat->wp_gpio)) { tegra_gpio_disable(plat->wp_gpio); gpio_free(plat->wp_gpio); } - -out_irq: +err_wp_req: if (gpio_is_valid(plat->cd_gpio)) free_irq(gpio_to_irq(plat->cd_gpio), host); -out_cd: +err_cd_irq_req: if (gpio_is_valid(plat->cd_gpio)) { tegra_gpio_disable(plat->cd_gpio); gpio_free(plat->cd_gpio); } - -out_power: +err_cd_req: if (gpio_is_valid(plat->power_gpio)) { tegra_gpio_disable(plat->power_gpio); gpio_free(plat->power_gpio); } - -out: +err_power_req: +err_no_plat: + sdhci_pltfm_free(pdev); return rc; } -static void tegra_sdhci_pltfm_exit(struct sdhci_host *host) +static int __devexit sdhci_tegra_remove(struct platform_device *pdev) { + struct sdhci_host *host = platform_get_drvdata(pdev); struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - struct platform_device *pdev = to_platform_device(mmc_dev(host->mmc)); struct tegra_sdhci_platform_data *plat; + int dead = (readl(host->ioaddr + SDHCI_INT_STATUS) == 0xffffffff); + + sdhci_remove_host(host, dead); plat = pdev->dev.platform_data; @@ -242,22 +272,37 @@ static void tegra_sdhci_pltfm_exit(struct sdhci_host *host) clk_disable(pltfm_host->clk); clk_put(pltfm_host->clk); + + sdhci_pltfm_free(pdev); + + return 0; } -static struct sdhci_ops tegra_sdhci_ops = { - .get_ro = tegra_sdhci_get_ro, - .read_l = tegra_sdhci_readl, - .read_w = tegra_sdhci_readw, - .write_l = tegra_sdhci_writel, - .platform_8bit_width = tegra_sdhci_8bit, +static struct platform_driver sdhci_tegra_driver = { + .driver = { + .name = "sdhci-tegra", + .owner = THIS_MODULE, + }, + .probe = sdhci_tegra_probe, + .remove = __devexit_p(sdhci_tegra_remove), +#ifdef CONFIG_PM + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +#endif }; -struct sdhci_pltfm_data sdhci_tegra_pdata = { - .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | - SDHCI_QUIRK_SINGLE_POWER_WRITE | - SDHCI_QUIRK_NO_HISPD_BIT | - SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC, - .ops = &tegra_sdhci_ops, - .init = tegra_sdhci_pltfm_init, - .exit = tegra_sdhci_pltfm_exit, -}; +static int __init sdhci_tegra_init(void) +{ + return platform_driver_register(&sdhci_tegra_driver); +} +module_init(sdhci_tegra_init); + +static void __exit sdhci_tegra_exit(void) +{ + platform_driver_unregister(&sdhci_tegra_driver); +} +module_exit(sdhci_tegra_exit); + +MODULE_DESCRIPTION("SDHCI driver for Tegra"); +MODULE_AUTHOR(" Google, Inc."); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 58d5436..c31a334 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -127,11 +127,15 @@ static void sdhci_mask_irqs(struct sdhci_host *host, u32 irqs) static void sdhci_set_card_detection(struct sdhci_host *host, bool enable) { - u32 irqs = SDHCI_INT_CARD_REMOVE | SDHCI_INT_CARD_INSERT; + u32 present, irqs; if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION) return; + present = sdhci_readl(host, SDHCI_PRESENT_STATE) & + SDHCI_CARD_PRESENT; + irqs = present ? SDHCI_INT_CARD_REMOVE : SDHCI_INT_CARD_INSERT; + if (enable) sdhci_unmask_irqs(host, irqs); else @@ -2154,13 +2158,30 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id) mmc_hostname(host->mmc), intmask); if (intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) { + u32 present = sdhci_readl(host, SDHCI_PRESENT_STATE) & + SDHCI_CARD_PRESENT; + + /* + * There is a observation on i.mx esdhc. INSERT bit will be + * immediately set again when it gets cleared, if a card is + * inserted. We have to mask the irq to prevent interrupt + * storm which will freeze the system. And the REMOVE gets + * the same situation. + * + * More testing are needed here to ensure it works for other + * platforms though. + */ + sdhci_mask_irqs(host, present ? SDHCI_INT_CARD_INSERT : + SDHCI_INT_CARD_REMOVE); + sdhci_unmask_irqs(host, present ? SDHCI_INT_CARD_REMOVE : + SDHCI_INT_CARD_INSERT); + sdhci_writel(host, intmask & (SDHCI_INT_CARD_INSERT | - SDHCI_INT_CARD_REMOVE), SDHCI_INT_STATUS); + SDHCI_INT_CARD_REMOVE), SDHCI_INT_STATUS); + intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE); tasklet_schedule(&host->card_tasklet); } - intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE); - if (intmask & SDHCI_INT_CMD_MASK) { sdhci_writel(host, intmask & SDHCI_INT_CMD_MASK, SDHCI_INT_STATUS); @@ -2488,6 +2509,11 @@ int sdhci_add_host(struct sdhci_host *host) } else mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200; + if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK) + mmc->max_discard_to = (1 << 27) / (mmc->f_max / 1000); + else + mmc->max_discard_to = (1 << 27) / host->timeout_clk; + mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23; if (host->quirks & SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12) diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index 14f8edb..557886b 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -175,6 +175,7 @@ struct sh_mmcif_host { enum mmcif_state state; spinlock_t lock; bool power; + bool card_present; /* DMA support */ struct dma_chan *chan_rx; @@ -877,23 +878,23 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) spin_unlock_irqrestore(&host->lock, flags); if (ios->power_mode == MMC_POWER_UP) { - if (p->set_pwr) - p->set_pwr(host->pd, ios->power_mode); - if (!host->power) { + if (!host->card_present) { /* See if we also get DMA */ sh_mmcif_request_dma(host, host->pd->dev.platform_data); - pm_runtime_get_sync(&host->pd->dev); - host->power = true; + host->card_present = true; } } else if (ios->power_mode == MMC_POWER_OFF || !ios->clock) { /* clock stop */ sh_mmcif_clock_control(host, 0); if (ios->power_mode == MMC_POWER_OFF) { - if (host->power) { - pm_runtime_put(&host->pd->dev); + if (host->card_present) { sh_mmcif_release_dma(host); - host->power = false; + host->card_present = false; } + } + if (host->power) { + pm_runtime_put(&host->pd->dev); + host->power = false; if (p->down_pwr) p->down_pwr(host->pd); } @@ -901,8 +902,16 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) return; } - if (ios->clock) + if (ios->clock) { + if (!host->power) { + if (p->set_pwr) + p->set_pwr(host->pd, ios->power_mode); + pm_runtime_get_sync(&host->pd->dev); + host->power = true; + sh_mmcif_sync_reset(host); + } sh_mmcif_clock_control(host, ios->clock); + } host->bus_width = ios->bus_width; host->state = STATE_IDLE; diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c index b365429..774f643 100644 --- a/drivers/mmc/host/sh_mobile_sdhi.c +++ b/drivers/mmc/host/sh_mobile_sdhi.c @@ -26,6 +26,7 @@ #include <linux/mmc/sh_mobile_sdhi.h> #include <linux/mfd/tmio.h> #include <linux/sh_dma.h> +#include <linux/delay.h> #include "tmio_mmc.h" @@ -55,6 +56,39 @@ static int sh_mobile_sdhi_get_cd(struct platform_device *pdev) return -ENOSYS; } +static int sh_mobile_sdhi_wait_idle(struct tmio_mmc_host *host) +{ + int timeout = 1000; + + while (--timeout && !(sd_ctrl_read16(host, CTL_STATUS2) & (1 << 13))) + udelay(1); + + if (!timeout) { + dev_warn(host->pdata->dev, "timeout waiting for SD bus idle\n"); + return -EBUSY; + } + + return 0; +} + +static int sh_mobile_sdhi_write16_hook(struct tmio_mmc_host *host, int addr) +{ + switch (addr) + { + case CTL_SD_CMD: + case CTL_STOP_INTERNAL_ACTION: + case CTL_XFER_BLK_COUNT: + case CTL_SD_CARD_CLK_CTL: + case CTL_SD_XFER_LEN: + case CTL_SD_MEM_CARD_OPT: + case CTL_TRANSACTION_CTL: + case CTL_DMA_ENABLE: + return sh_mobile_sdhi_wait_idle(host); + } + + return 0; +} + static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev) { struct sh_mobile_sdhi *priv; @@ -86,13 +120,15 @@ static int __devinit sh_mobile_sdhi_probe(struct platform_device *pdev) mmc_data->hclk = clk_get_rate(priv->clk); mmc_data->set_pwr = sh_mobile_sdhi_set_pwr; mmc_data->get_cd = sh_mobile_sdhi_get_cd; + if (mmc_data->flags & TMIO_MMC_HAS_IDLE_WAIT) + mmc_data->write16_hook = sh_mobile_sdhi_write16_hook; mmc_data->capabilities = MMC_CAP_MMC_HIGHSPEED; if (p) { mmc_data->flags = p->tmio_flags; mmc_data->ocr_mask = p->tmio_ocr_mask; mmc_data->capabilities |= p->tmio_caps; - if (p->dma_slave_tx >= 0 && p->dma_slave_rx >= 0) { + if (p->dma_slave_tx > 0 && p->dma_slave_rx > 0) { priv->param_tx.slave_id = p->dma_slave_tx; priv->param_rx.slave_id = p->dma_slave_rx; priv->dma_priv.chan_priv_tx = &priv->param_tx; @@ -165,13 +201,14 @@ static int sh_mobile_sdhi_remove(struct platform_device *pdev) p->pdata = NULL; + tmio_mmc_host_remove(host); + for (i = 0; i < 3; i++) { irq = platform_get_irq(pdev, i); if (irq >= 0) free_irq(irq, host); } - tmio_mmc_host_remove(host); clk_disable(priv->clk); clk_put(priv->clk); kfree(priv); diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index 8260bc2..087d880 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -18,6 +18,7 @@ #include <linux/highmem.h> #include <linux/mmc/tmio.h> +#include <linux/mutex.h> #include <linux/pagemap.h> #include <linux/spinlock.h> @@ -52,6 +53,8 @@ struct tmio_mmc_host { void (*set_clk_div)(struct platform_device *host, int state); int pm_error; + /* recognise system-wide suspend in runtime PM methods */ + bool pm_global; /* pio related stuff */ struct scatterlist *sg_ptr; @@ -73,8 +76,11 @@ struct tmio_mmc_host { /* Track lost interrupts */ struct delayed_work delayed_reset_work; - spinlock_t lock; + struct work_struct done; + + spinlock_t lock; /* protect host private data */ unsigned long last_req_ts; + struct mutex ios_lock; /* protect set_ios() context */ }; int tmio_mmc_host_probe(struct tmio_mmc_host **host, @@ -103,6 +109,7 @@ static inline void tmio_mmc_kunmap_atomic(struct scatterlist *sg, #if defined(CONFIG_MMC_SDHI) || defined(CONFIG_MMC_SDHI_MODULE) void tmio_mmc_start_dma(struct tmio_mmc_host *host, struct mmc_data *data); +void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable); void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata); void tmio_mmc_release_dma(struct tmio_mmc_host *host); #else @@ -111,6 +118,10 @@ static inline void tmio_mmc_start_dma(struct tmio_mmc_host *host, { } +static inline void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable) +{ +} + static inline void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata) { @@ -134,4 +145,44 @@ int tmio_mmc_host_resume(struct device *dev); int tmio_mmc_host_runtime_suspend(struct device *dev); int tmio_mmc_host_runtime_resume(struct device *dev); +static inline u16 sd_ctrl_read16(struct tmio_mmc_host *host, int addr) +{ + return readw(host->ctl + (addr << host->bus_shift)); +} + +static inline void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr, + u16 *buf, int count) +{ + readsw(host->ctl + (addr << host->bus_shift), buf, count); +} + +static inline u32 sd_ctrl_read32(struct tmio_mmc_host *host, int addr) +{ + return readw(host->ctl + (addr << host->bus_shift)) | + readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16; +} + +static inline void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val) +{ + /* If there is a hook and it returns non-zero then there + * is an error and the write should be skipped + */ + if (host->pdata->write16_hook && host->pdata->write16_hook(host, addr)) + return; + writew(val, host->ctl + (addr << host->bus_shift)); +} + +static inline void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr, + u16 *buf, int count) +{ + writesw(host->ctl + (addr << host->bus_shift), buf, count); +} + +static inline void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val) +{ + writew(val, host->ctl + (addr << host->bus_shift)); + writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift)); +} + + #endif diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c index 25f1ad6..2aa616d 100644 --- a/drivers/mmc/host/tmio_mmc_dma.c +++ b/drivers/mmc/host/tmio_mmc_dma.c @@ -22,11 +22,14 @@ #define TMIO_MMC_MIN_DMA_LEN 8 -static void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable) +void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable) { + if (!host->chan_tx || !host->chan_rx) + return; + #if defined(CONFIG_SUPERH) || defined(CONFIG_ARCH_SHMOBILE) /* Switch DMA mode on or off - SuperH specific? */ - writew(enable ? 2 : 0, host->ctl + (0xd8 << host->bus_shift)); + sd_ctrl_write16(host, CTL_DMA_ENABLE, enable ? 2 : 0); #endif } diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c index ad6347b..1f16357 100644 --- a/drivers/mmc/host/tmio_mmc_pio.c +++ b/drivers/mmc/host/tmio_mmc_pio.c @@ -46,40 +46,6 @@ #include "tmio_mmc.h" -static u16 sd_ctrl_read16(struct tmio_mmc_host *host, int addr) -{ - return readw(host->ctl + (addr << host->bus_shift)); -} - -static void sd_ctrl_read16_rep(struct tmio_mmc_host *host, int addr, - u16 *buf, int count) -{ - readsw(host->ctl + (addr << host->bus_shift), buf, count); -} - -static u32 sd_ctrl_read32(struct tmio_mmc_host *host, int addr) -{ - return readw(host->ctl + (addr << host->bus_shift)) | - readw(host->ctl + ((addr + 2) << host->bus_shift)) << 16; -} - -static void sd_ctrl_write16(struct tmio_mmc_host *host, int addr, u16 val) -{ - writew(val, host->ctl + (addr << host->bus_shift)); -} - -static void sd_ctrl_write16_rep(struct tmio_mmc_host *host, int addr, - u16 *buf, int count) -{ - writesw(host->ctl + (addr << host->bus_shift), buf, count); -} - -static void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val) -{ - writew(val, host->ctl + (addr << host->bus_shift)); - writew(val >> 16, host->ctl + ((addr + 2) << host->bus_shift)); -} - void tmio_mmc_enable_mmc_irqs(struct tmio_mmc_host *host, u32 i) { u32 mask = sd_ctrl_read32(host, CTL_IRQ_MASK) & ~(i & TMIO_MASK_IRQ); @@ -284,10 +250,16 @@ static void tmio_mmc_reset_work(struct work_struct *work) /* called with host->lock held, interrupts disabled */ static void tmio_mmc_finish_request(struct tmio_mmc_host *host) { - struct mmc_request *mrq = host->mrq; + struct mmc_request *mrq; + unsigned long flags; + + spin_lock_irqsave(&host->lock, flags); - if (!mrq) + mrq = host->mrq; + if (IS_ERR_OR_NULL(mrq)) { + spin_unlock_irqrestore(&host->lock, flags); return; + } host->cmd = NULL; host->data = NULL; @@ -296,11 +268,18 @@ static void tmio_mmc_finish_request(struct tmio_mmc_host *host) cancel_delayed_work(&host->delayed_reset_work); host->mrq = NULL; + spin_unlock_irqrestore(&host->lock, flags); - /* FIXME: mmc_request_done() can schedule! */ mmc_request_done(host->mmc, mrq); } +static void tmio_mmc_done_work(struct work_struct *work) +{ + struct tmio_mmc_host *host = container_of(work, struct tmio_mmc_host, + done); + tmio_mmc_finish_request(host); +} + /* These are the bitmasks the tmio chip requires to implement the MMC response * types. Note that R1 and R6 are the same in this scheme. */ #define APP_CMD 0x0040 @@ -467,7 +446,7 @@ void tmio_mmc_do_data_irq(struct tmio_mmc_host *host) BUG(); } - tmio_mmc_finish_request(host); + schedule_work(&host->done); } static void tmio_mmc_data_irq(struct tmio_mmc_host *host) @@ -557,7 +536,7 @@ static void tmio_mmc_cmd_irq(struct tmio_mmc_host *host, tasklet_schedule(&host->dma_issue); } } else { - tmio_mmc_finish_request(host); + schedule_work(&host->done); } out: @@ -567,6 +546,7 @@ out: irqreturn_t tmio_mmc_irq(int irq, void *devid) { struct tmio_mmc_host *host = devid; + struct mmc_host *mmc = host->mmc; struct tmio_mmc_data *pdata = host->pdata; unsigned int ireg, irq_mask, status; unsigned int sdio_ireg, sdio_irq_mask, sdio_status; @@ -588,13 +568,13 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) if (sdio_ireg && !host->sdio_irq_enabled) { pr_warning("tmio_mmc: Spurious SDIO IRQ, disabling! 0x%04x 0x%04x 0x%04x\n", sdio_status, sdio_irq_mask, sdio_ireg); - tmio_mmc_enable_sdio_irq(host->mmc, 0); + tmio_mmc_enable_sdio_irq(mmc, 0); goto out; } - if (host->mmc->caps & MMC_CAP_SDIO_IRQ && + if (mmc->caps & MMC_CAP_SDIO_IRQ && sdio_ireg & TMIO_SDIO_STAT_IOIRQ) - mmc_signal_sdio_irq(host->mmc); + mmc_signal_sdio_irq(mmc); if (sdio_ireg) goto out; @@ -603,58 +583,49 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) pr_debug_status(status); pr_debug_status(ireg); - if (!ireg) { - tmio_mmc_disable_mmc_irqs(host, status & ~irq_mask); - - pr_warning("tmio_mmc: Spurious irq, disabling! " - "0x%08x 0x%08x 0x%08x\n", status, irq_mask, ireg); - pr_debug_status(status); - + /* Card insert / remove attempts */ + if (ireg & (TMIO_STAT_CARD_INSERT | TMIO_STAT_CARD_REMOVE)) { + tmio_mmc_ack_mmc_irqs(host, TMIO_STAT_CARD_INSERT | + TMIO_STAT_CARD_REMOVE); + if ((((ireg & TMIO_STAT_CARD_REMOVE) && mmc->card) || + ((ireg & TMIO_STAT_CARD_INSERT) && !mmc->card)) && + !work_pending(&mmc->detect.work)) + mmc_detect_change(host->mmc, msecs_to_jiffies(100)); goto out; } - while (ireg) { - /* Card insert / remove attempts */ - if (ireg & (TMIO_STAT_CARD_INSERT | TMIO_STAT_CARD_REMOVE)) { - tmio_mmc_ack_mmc_irqs(host, TMIO_STAT_CARD_INSERT | - TMIO_STAT_CARD_REMOVE); - mmc_detect_change(host->mmc, msecs_to_jiffies(100)); - } - - /* CRC and other errors */ -/* if (ireg & TMIO_STAT_ERR_IRQ) - * handled |= tmio_error_irq(host, irq, stat); + /* CRC and other errors */ +/* if (ireg & TMIO_STAT_ERR_IRQ) + * handled |= tmio_error_irq(host, irq, stat); */ - /* Command completion */ - if (ireg & (TMIO_STAT_CMDRESPEND | TMIO_STAT_CMDTIMEOUT)) { - tmio_mmc_ack_mmc_irqs(host, - TMIO_STAT_CMDRESPEND | - TMIO_STAT_CMDTIMEOUT); - tmio_mmc_cmd_irq(host, status); - } - - /* Data transfer */ - if (ireg & (TMIO_STAT_RXRDY | TMIO_STAT_TXRQ)) { - tmio_mmc_ack_mmc_irqs(host, TMIO_STAT_RXRDY | TMIO_STAT_TXRQ); - tmio_mmc_pio_irq(host); - } - - /* Data transfer completion */ - if (ireg & TMIO_STAT_DATAEND) { - tmio_mmc_ack_mmc_irqs(host, TMIO_STAT_DATAEND); - tmio_mmc_data_irq(host); - } + /* Command completion */ + if (ireg & (TMIO_STAT_CMDRESPEND | TMIO_STAT_CMDTIMEOUT)) { + tmio_mmc_ack_mmc_irqs(host, + TMIO_STAT_CMDRESPEND | + TMIO_STAT_CMDTIMEOUT); + tmio_mmc_cmd_irq(host, status); + goto out; + } - /* Check status - keep going until we've handled it all */ - status = sd_ctrl_read32(host, CTL_STATUS); - irq_mask = sd_ctrl_read32(host, CTL_IRQ_MASK); - ireg = status & TMIO_MASK_IRQ & ~irq_mask; + /* Data transfer */ + if (ireg & (TMIO_STAT_RXRDY | TMIO_STAT_TXRQ)) { + tmio_mmc_ack_mmc_irqs(host, TMIO_STAT_RXRDY | TMIO_STAT_TXRQ); + tmio_mmc_pio_irq(host); + goto out; + } - pr_debug("Status at end of loop: %08x\n", status); - pr_debug_status(status); + /* Data transfer completion */ + if (ireg & TMIO_STAT_DATAEND) { + tmio_mmc_ack_mmc_irqs(host, TMIO_STAT_DATAEND); + tmio_mmc_data_irq(host); + goto out; } - pr_debug("MMC IRQ end\n"); + + pr_warning("tmio_mmc: Spurious irq, disabling! " + "0x%08x 0x%08x 0x%08x\n", status, irq_mask, ireg); + pr_debug_status(status); + tmio_mmc_disable_mmc_irqs(host, status & ~irq_mask); out: return IRQ_HANDLED; @@ -749,6 +720,8 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) struct tmio_mmc_data *pdata = host->pdata; unsigned long flags; + mutex_lock(&host->ios_lock); + spin_lock_irqsave(&host->lock, flags); if (host->mrq) { if (IS_ERR(host->mrq)) { @@ -764,6 +737,8 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) host->mrq->cmd->opcode, host->last_req_ts, jiffies); } spin_unlock_irqrestore(&host->lock, flags); + + mutex_unlock(&host->ios_lock); return; } @@ -771,33 +746,30 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) spin_unlock_irqrestore(&host->lock, flags); - if (ios->clock) - tmio_mmc_set_clock(host, ios->clock); - - /* Power sequence - OFF -> UP -> ON */ - if (ios->power_mode == MMC_POWER_UP) { - if ((pdata->flags & TMIO_MMC_HAS_COLD_CD) && !pdata->power) { + /* + * pdata->power == false only if COLD_CD is available, otherwise only + * in short time intervals during probing or resuming + */ + if (ios->power_mode == MMC_POWER_ON && ios->clock) { + if (!pdata->power) { pm_runtime_get_sync(&host->pdev->dev); pdata->power = true; } + tmio_mmc_set_clock(host, ios->clock); /* power up SD bus */ if (host->set_pwr) host->set_pwr(host->pdev, 1); - } else if (ios->power_mode == MMC_POWER_OFF || !ios->clock) { - /* power down SD bus */ - if (ios->power_mode == MMC_POWER_OFF) { - if (host->set_pwr) - host->set_pwr(host->pdev, 0); - if ((pdata->flags & TMIO_MMC_HAS_COLD_CD) && - pdata->power) { - pdata->power = false; - pm_runtime_put(&host->pdev->dev); - } - } - tmio_mmc_clk_stop(host); - } else { /* start bus clock */ tmio_mmc_clk_start(host); + } else if (ios->power_mode != MMC_POWER_UP) { + if (host->set_pwr) + host->set_pwr(host->pdev, 0); + if ((pdata->flags & TMIO_MMC_HAS_COLD_CD) && + pdata->power) { + pdata->power = false; + pm_runtime_put(&host->pdev->dev); + } + tmio_mmc_clk_stop(host); } switch (ios->bus_width) { @@ -817,6 +789,8 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) current->comm, task_pid_nr(current), ios->clock, ios->power_mode); host->mrq = NULL; + + mutex_unlock(&host->ios_lock); } static int tmio_mmc_get_ro(struct mmc_host *mmc) @@ -824,8 +798,8 @@ static int tmio_mmc_get_ro(struct mmc_host *mmc) struct tmio_mmc_host *host = mmc_priv(mmc); struct tmio_mmc_data *pdata = host->pdata; - return ((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) || - !(sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT)); + return !((pdata->flags & TMIO_MMC_WRPROTECT_DISABLE) || + (sd_ctrl_read32(host, CTL_STATUS) & TMIO_STAT_WRPROTECT)); } static int tmio_mmc_get_cd(struct mmc_host *mmc) @@ -913,16 +887,20 @@ int __devinit tmio_mmc_host_probe(struct tmio_mmc_host **host, tmio_mmc_enable_sdio_irq(mmc, 0); spin_lock_init(&_host->lock); + mutex_init(&_host->ios_lock); /* Init delayed work for request timeouts */ INIT_DELAYED_WORK(&_host->delayed_reset_work, tmio_mmc_reset_work); + INIT_WORK(&_host->done, tmio_mmc_done_work); /* See if we also get DMA */ tmio_mmc_request_dma(_host, pdata); /* We have to keep the device powered for its card detection to work */ - if (!(pdata->flags & TMIO_MMC_HAS_COLD_CD)) + if (!(pdata->flags & TMIO_MMC_HAS_COLD_CD)) { + pdata->power = true; pm_runtime_get_noresume(&pdev->dev); + } mmc_add_host(mmc); @@ -963,6 +941,7 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host) pm_runtime_get_sync(&pdev->dev); mmc_remove_host(host->mmc); + cancel_work_sync(&host->done); cancel_delayed_work_sync(&host->delayed_reset_work); tmio_mmc_release_dma(host); @@ -998,11 +977,16 @@ int tmio_mmc_host_resume(struct device *dev) /* The MMC core will perform the complete set up */ host->pdata->power = false; + host->pm_global = true; if (!host->pm_error) pm_runtime_get_sync(dev); - tmio_mmc_reset(mmc_priv(mmc)); - tmio_mmc_request_dma(host, host->pdata); + if (host->pm_global) { + /* Runtime PM resume callback didn't run */ + tmio_mmc_reset(host); + tmio_mmc_enable_dma(host, true); + host->pm_global = false; + } return mmc_resume_host(mmc); } @@ -1023,12 +1007,15 @@ int tmio_mmc_host_runtime_resume(struct device *dev) struct tmio_mmc_data *pdata = host->pdata; tmio_mmc_reset(host); + tmio_mmc_enable_dma(host, true); if (pdata->power) { /* Only entered after a card-insert interrupt */ - tmio_mmc_set_ios(mmc, &mmc->ios); + if (!mmc->card) + tmio_mmc_set_ios(mmc, &mmc->ios); mmc_detect_change(mmc, msecs_to_jiffies(100)); } + host->pm_global = false; return 0; } diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index cbb0330..d4455ff 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -2096,7 +2096,7 @@ static struct mmc_host_ops vub300_mmc_ops = { static int vub300_probe(struct usb_interface *interface, const struct usb_device_id *id) { /* NOT irq */ - struct vub300_mmc_host *vub300 = NULL; + struct vub300_mmc_host *vub300; struct usb_host_interface *iface_desc; struct usb_device *udev = usb_get_dev(interface_to_usbdev(interface)); int i; @@ -2118,23 +2118,20 @@ static int vub300_probe(struct usb_interface *interface, command_out_urb = usb_alloc_urb(0, GFP_KERNEL); if (!command_out_urb) { retval = -ENOMEM; - dev_err(&vub300->udev->dev, - "not enough memory for the command_out_urb\n"); + dev_err(&udev->dev, "not enough memory for command_out_urb\n"); goto error0; } command_res_urb = usb_alloc_urb(0, GFP_KERNEL); if (!command_res_urb) { retval = -ENOMEM; - dev_err(&vub300->udev->dev, - "not enough memory for the command_res_urb\n"); + dev_err(&udev->dev, "not enough memory for command_res_urb\n"); goto error1; } /* this also allocates memory for our VUB300 mmc host device */ mmc = mmc_alloc_host(sizeof(struct vub300_mmc_host), &udev->dev); if (!mmc) { retval = -ENOMEM; - dev_err(&vub300->udev->dev, - "not enough memory for the mmc_host\n"); + dev_err(&udev->dev, "not enough memory for the mmc_host\n"); goto error4; } /* MMC core transfer sizes tunable parameters */ diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c index 0bb254c..33d8aad 100644 --- a/drivers/mtd/nand/fsl_elbc_nand.c +++ b/drivers/mtd/nand/fsl_elbc_nand.c @@ -339,9 +339,9 @@ static void fsl_elbc_cmdfunc(struct mtd_info *mtd, unsigned int command, (FIR_OP_UA << FIR_OP1_SHIFT) | (FIR_OP_RBW << FIR_OP2_SHIFT)); out_be32(&lbc->fcr, NAND_CMD_READID << FCR_CMD0_SHIFT); - /* 5 bytes for manuf, device and exts */ - out_be32(&lbc->fbcr, 5); - elbc_fcm_ctrl->read_bytes = 5; + /* nand_get_flash_type() reads 8 bytes of entire ID string */ + out_be32(&lbc->fbcr, 8); + elbc_fcm_ctrl->read_bytes = 8; elbc_fcm_ctrl->use_mdr = 1; elbc_fcm_ctrl->mdr = 0; diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 65626c1..6c3fb5a 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -953,10 +953,14 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset) if (!ubi->peb_buf2) goto out_free; + err = ubi_debugging_init_dev(ubi); + if (err) + goto out_free; + err = attach_by_scanning(ubi); if (err) { dbg_err("failed to attach by scanning, error %d", err); - goto out_free; + goto out_debugging; } if (ubi->autoresize_vol_id != -1) { @@ -969,12 +973,16 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset) if (err) goto out_detach; + err = ubi_debugfs_init_dev(ubi); + if (err) + goto out_uif; + ubi->bgt_thread = kthread_create(ubi_thread, ubi, ubi->bgt_name); if (IS_ERR(ubi->bgt_thread)) { err = PTR_ERR(ubi->bgt_thread); ubi_err("cannot spawn \"%s\", error %d", ubi->bgt_name, err); - goto out_uif; + goto out_debugfs; } ubi_msg("attached mtd%d to ubi%d", mtd->index, ubi_num); @@ -1008,12 +1016,18 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, int vid_hdr_offset) ubi_notify_all(ubi, UBI_VOLUME_ADDED, NULL); return ubi_num; +out_debugfs: + ubi_debugfs_exit_dev(ubi); out_uif: + get_device(&ubi->dev); + ubi_assert(ref); uif_close(ubi); out_detach: ubi_wl_close(ubi); free_internal_volumes(ubi); vfree(ubi->vtbl); +out_debugging: + ubi_debugging_exit_dev(ubi); out_free: vfree(ubi->peb_buf1); vfree(ubi->peb_buf2); @@ -1080,11 +1094,13 @@ int ubi_detach_mtd_dev(int ubi_num, int anyway) */ get_device(&ubi->dev); + ubi_debugfs_exit_dev(ubi); uif_close(ubi); ubi_wl_close(ubi); free_internal_volumes(ubi); vfree(ubi->vtbl); put_mtd_device(ubi->mtd); + ubi_debugging_exit_dev(ubi); vfree(ubi->peb_buf1); vfree(ubi->peb_buf2); ubi_msg("mtd%d is detached from ubi%d", ubi->mtd->index, ubi->ubi_num); @@ -1199,6 +1215,11 @@ static int __init ubi_init(void) if (!ubi_wl_entry_slab) goto out_dev_unreg; + err = ubi_debugfs_init(); + if (err) + goto out_slab; + + /* Attach MTD devices */ for (i = 0; i < mtd_devs; i++) { struct mtd_dev_param *p = &mtd_dev_param[i]; @@ -1247,6 +1268,8 @@ out_detach: ubi_detach_mtd_dev(ubi_devices[k]->ubi_num, 1); mutex_unlock(&ubi_devices_mutex); } + ubi_debugfs_exit(); +out_slab: kmem_cache_destroy(ubi_wl_entry_slab); out_dev_unreg: misc_deregister(&ubi_ctrl_cdev); @@ -1270,6 +1293,7 @@ static void __exit ubi_exit(void) ubi_detach_mtd_dev(ubi_devices[i]->ubi_num, 1); mutex_unlock(&ubi_devices_mutex); } + ubi_debugfs_exit(); kmem_cache_destroy(ubi_wl_entry_slab); misc_deregister(&ubi_ctrl_cdev); class_remove_file(ubi_class, &ubi_version); diff --git a/drivers/mtd/ubi/debug.c b/drivers/mtd/ubi/debug.c index 2224cbe..ab80c0d 100644 --- a/drivers/mtd/ubi/debug.c +++ b/drivers/mtd/ubi/debug.c @@ -27,17 +27,9 @@ #ifdef CONFIG_MTD_UBI_DEBUG #include "ubi.h" +#include <linux/debugfs.h> +#include <linux/uaccess.h> #include <linux/module.h> -#include <linux/moduleparam.h> - -unsigned int ubi_chk_flags; -unsigned int ubi_tst_flags; - -module_param_named(debug_chks, ubi_chk_flags, uint, S_IRUGO | S_IWUSR); -module_param_named(debug_tsts, ubi_chk_flags, uint, S_IRUGO | S_IWUSR); - -MODULE_PARM_DESC(debug_chks, "Debug check flags"); -MODULE_PARM_DESC(debug_tsts, "Debug special test flags"); /** * ubi_dbg_dump_ec_hdr - dump an erase counter header. @@ -239,4 +231,261 @@ out: return; } +/** + * ubi_debugging_init_dev - initialize debugging for an UBI device. + * @ubi: UBI device description object + * + * This function initializes debugging-related data for UBI device @ubi. + * Returns zero in case of success and a negative error code in case of + * failure. + */ +int ubi_debugging_init_dev(struct ubi_device *ubi) +{ + ubi->dbg = kzalloc(sizeof(struct ubi_debug_info), GFP_KERNEL); + if (!ubi->dbg) + return -ENOMEM; + + return 0; +} + +/** + * ubi_debugging_exit_dev - free debugging data for an UBI device. + * @ubi: UBI device description object + */ +void ubi_debugging_exit_dev(struct ubi_device *ubi) +{ + kfree(ubi->dbg); +} + +/* + * Root directory for UBI stuff in debugfs. Contains sub-directories which + * contain the stuff specific to particular UBI devices. + */ +static struct dentry *dfs_rootdir; + +/** + * ubi_debugfs_init - create UBI debugfs directory. + * + * Create UBI debugfs directory. Returns zero in case of success and a negative + * error code in case of failure. + */ +int ubi_debugfs_init(void) +{ + dfs_rootdir = debugfs_create_dir("ubi", NULL); + if (IS_ERR_OR_NULL(dfs_rootdir)) { + int err = dfs_rootdir ? -ENODEV : PTR_ERR(dfs_rootdir); + + ubi_err("cannot create \"ubi\" debugfs directory, error %d\n", + err); + return err; + } + + return 0; +} + +/** + * ubi_debugfs_exit - remove UBI debugfs directory. + */ +void ubi_debugfs_exit(void) +{ + debugfs_remove(dfs_rootdir); +} + +/* Read an UBI debugfs file */ +static ssize_t dfs_file_read(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + unsigned long ubi_num = (unsigned long)file->private_data; + struct dentry *dent = file->f_path.dentry; + struct ubi_device *ubi; + struct ubi_debug_info *d; + char buf[3]; + int val; + + ubi = ubi_get_device(ubi_num); + if (!ubi) + return -ENODEV; + d = ubi->dbg; + + if (dent == d->dfs_chk_gen) + val = d->chk_gen; + else if (dent == d->dfs_chk_io) + val = d->chk_io; + else if (dent == d->dfs_disable_bgt) + val = d->disable_bgt; + else if (dent == d->dfs_emulate_bitflips) + val = d->emulate_bitflips; + else if (dent == d->dfs_emulate_io_failures) + val = d->emulate_io_failures; + else { + count = -EINVAL; + goto out; + } + + if (val) + buf[0] = '1'; + else + buf[0] = '0'; + buf[1] = '\n'; + buf[2] = 0x00; + + count = simple_read_from_buffer(user_buf, count, ppos, buf, 2); + +out: + ubi_put_device(ubi); + return count; +} + +/* Write an UBI debugfs file */ +static ssize_t dfs_file_write(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos) +{ + unsigned long ubi_num = (unsigned long)file->private_data; + struct dentry *dent = file->f_path.dentry; + struct ubi_device *ubi; + struct ubi_debug_info *d; + size_t buf_size; + char buf[8]; + int val; + + ubi = ubi_get_device(ubi_num); + if (!ubi) + return -ENODEV; + d = ubi->dbg; + + buf_size = min_t(size_t, count, (sizeof(buf) - 1)); + if (copy_from_user(buf, user_buf, buf_size)) { + count = -EFAULT; + goto out; + } + + if (buf[0] == '1') + val = 1; + else if (buf[0] == '0') + val = 0; + else { + count = -EINVAL; + goto out; + } + + if (dent == d->dfs_chk_gen) + d->chk_gen = val; + else if (dent == d->dfs_chk_io) + d->chk_io = val; + else if (dent == d->dfs_disable_bgt) + d->disable_bgt = val; + else if (dent == d->dfs_emulate_bitflips) + d->emulate_bitflips = val; + else if (dent == d->dfs_emulate_io_failures) + d->emulate_io_failures = val; + else + count = -EINVAL; + +out: + ubi_put_device(ubi); + return count; +} + +static int default_open(struct inode *inode, struct file *file) +{ + if (inode->i_private) + file->private_data = inode->i_private; + + return 0; +} + +/* File operations for all UBI debugfs files */ +static const struct file_operations dfs_fops = { + .read = dfs_file_read, + .write = dfs_file_write, + .open = default_open, + .llseek = no_llseek, + .owner = THIS_MODULE, +}; + +/** + * ubi_debugfs_init_dev - initialize debugfs for an UBI device. + * @ubi: UBI device description object + * + * This function creates all debugfs files for UBI device @ubi. Returns zero in + * case of success and a negative error code in case of failure. + */ +int ubi_debugfs_init_dev(struct ubi_device *ubi) +{ + int err, n; + unsigned long ubi_num = ubi->ubi_num; + const char *fname; + struct dentry *dent; + struct ubi_debug_info *d = ubi->dbg; + + n = snprintf(d->dfs_dir_name, UBI_DFS_DIR_LEN + 1, UBI_DFS_DIR_NAME, + ubi->ubi_num); + if (n == UBI_DFS_DIR_LEN) { + /* The array size is too small */ + fname = UBI_DFS_DIR_NAME; + dent = ERR_PTR(-EINVAL); + goto out; + } + + fname = d->dfs_dir_name; + dent = debugfs_create_dir(fname, dfs_rootdir); + if (IS_ERR_OR_NULL(dent)) + goto out; + d->dfs_dir = dent; + + fname = "chk_gen"; + dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_gen = dent; + + fname = "chk_io"; + dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_io = dent; + + fname = "tst_disable_bgt"; + dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_disable_bgt = dent; + + fname = "tst_emulate_bitflips"; + dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_emulate_bitflips = dent; + + fname = "tst_emulate_io_failures"; + dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, (void *)ubi_num, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_emulate_io_failures = dent; + + return 0; + +out_remove: + debugfs_remove_recursive(d->dfs_dir); +out: + err = dent ? PTR_ERR(dent) : -ENODEV; + ubi_err("cannot create \"%s\" debugfs file or directory, error %d\n", + fname, err); + return err; +} + +/** + * dbg_debug_exit_dev - free all debugfs files corresponding to device @ubi + * @ubi: UBI device description object + */ +void ubi_debugfs_exit_dev(struct ubi_device *ubi) +{ + debugfs_remove_recursive(ubi->dbg->dfs_dir); +} + #endif /* CONFIG_MTD_UBI_DEBUG */ diff --git a/drivers/mtd/ubi/debug.h b/drivers/mtd/ubi/debug.h index 3f1a09c..65b5b76 100644 --- a/drivers/mtd/ubi/debug.h +++ b/drivers/mtd/ubi/debug.h @@ -21,14 +21,6 @@ #ifndef __UBI_DEBUG_H__ #define __UBI_DEBUG_H__ -struct ubi_ec_hdr; -struct ubi_vid_hdr; -struct ubi_volume; -struct ubi_vtbl_record; -struct ubi_scan_volume; -struct ubi_scan_leb; -struct ubi_mkvol_req; - #ifdef CONFIG_MTD_UBI_DEBUG #include <linux/random.h> @@ -71,86 +63,103 @@ void ubi_dbg_dump_sv(const struct ubi_scan_volume *sv); void ubi_dbg_dump_seb(const struct ubi_scan_leb *seb, int type); void ubi_dbg_dump_mkvol_req(const struct ubi_mkvol_req *req); void ubi_dbg_dump_flash(struct ubi_device *ubi, int pnum, int offset, int len); - -extern unsigned int ubi_chk_flags; - -/* - * Debugging check flags. - * - * UBI_CHK_GEN: general checks - * UBI_CHK_IO: check writes and erases - */ -enum { - UBI_CHK_GEN = 0x1, - UBI_CHK_IO = 0x2, -}; - int ubi_dbg_check_all_ff(struct ubi_device *ubi, int pnum, int offset, int len); int ubi_dbg_check_write(struct ubi_device *ubi, const void *buf, int pnum, int offset, int len); - -extern unsigned int ubi_tst_flags; +int ubi_debugging_init_dev(struct ubi_device *ubi); +void ubi_debugging_exit_dev(struct ubi_device *ubi); +int ubi_debugfs_init(void); +void ubi_debugfs_exit(void); +int ubi_debugfs_init_dev(struct ubi_device *ubi); +void ubi_debugfs_exit_dev(struct ubi_device *ubi); /* - * Special testing flags. + * The UBI debugfs directory name pattern and maximum name length (3 for "ubi" + * + 2 for the number plus 1 for the trailing zero byte. + */ +#define UBI_DFS_DIR_NAME "ubi%d" +#define UBI_DFS_DIR_LEN (3 + 2 + 1) + +/** + * struct ubi_debug_info - debugging information for an UBI device. * - * UBIFS_TST_DISABLE_BGT: disable the background thread - * UBI_TST_EMULATE_BITFLIPS: emulate bit-flips - * UBI_TST_EMULATE_WRITE_FAILURES: emulate write failures - * UBI_TST_EMULATE_ERASE_FAILURES: emulate erase failures + * @chk_gen: if UBI general extra checks are enabled + * @chk_io: if UBI I/O extra checks are enabled + * @disable_bgt: disable the background task for testing purposes + * @emulate_bitflips: emulate bit-flips for testing purposes + * @emulate_io_failures: emulate write/erase failures for testing purposes + * @dfs_dir_name: name of debugfs directory containing files of this UBI device + * @dfs_dir: direntry object of the UBI device debugfs directory + * @dfs_chk_gen: debugfs knob to enable UBI general extra checks + * @dfs_chk_io: debugfs knob to enable UBI I/O extra checks + * @dfs_disable_bgt: debugfs knob to disable the background task + * @dfs_emulate_bitflips: debugfs knob to emulate bit-flips + * @dfs_emulate_io_failures: debugfs knob to emulate write/erase failures */ -enum { - UBI_TST_DISABLE_BGT = 0x1, - UBI_TST_EMULATE_BITFLIPS = 0x2, - UBI_TST_EMULATE_WRITE_FAILURES = 0x4, - UBI_TST_EMULATE_ERASE_FAILURES = 0x8, +struct ubi_debug_info { + unsigned int chk_gen:1; + unsigned int chk_io:1; + unsigned int disable_bgt:1; + unsigned int emulate_bitflips:1; + unsigned int emulate_io_failures:1; + char dfs_dir_name[UBI_DFS_DIR_LEN + 1]; + struct dentry *dfs_dir; + struct dentry *dfs_chk_gen; + struct dentry *dfs_chk_io; + struct dentry *dfs_disable_bgt; + struct dentry *dfs_emulate_bitflips; + struct dentry *dfs_emulate_io_failures; }; /** * ubi_dbg_is_bgt_disabled - if the background thread is disabled. + * @ubi: UBI device description object * * Returns non-zero if the UBI background thread is disabled for testing * purposes. */ -static inline int ubi_dbg_is_bgt_disabled(void) +static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi) { - return ubi_tst_flags & UBI_TST_DISABLE_BGT; + return ubi->dbg->disable_bgt; } /** * ubi_dbg_is_bitflip - if it is time to emulate a bit-flip. + * @ubi: UBI device description object * * Returns non-zero if a bit-flip should be emulated, otherwise returns zero. */ -static inline int ubi_dbg_is_bitflip(void) +static inline int ubi_dbg_is_bitflip(const struct ubi_device *ubi) { - if (ubi_tst_flags & UBI_TST_EMULATE_BITFLIPS) + if (ubi->dbg->emulate_bitflips) return !(random32() % 200); return 0; } /** * ubi_dbg_is_write_failure - if it is time to emulate a write failure. + * @ubi: UBI device description object * * Returns non-zero if a write failure should be emulated, otherwise returns * zero. */ -static inline int ubi_dbg_is_write_failure(void) +static inline int ubi_dbg_is_write_failure(const struct ubi_device *ubi) { - if (ubi_tst_flags & UBI_TST_EMULATE_WRITE_FAILURES) + if (ubi->dbg->emulate_io_failures) return !(random32() % 500); return 0; } /** * ubi_dbg_is_erase_failure - if its time to emulate an erase failure. + * @ubi: UBI device description object * * Returns non-zero if an erase failure should be emulated, otherwise returns * zero. */ -static inline int ubi_dbg_is_erase_failure(void) +static inline int ubi_dbg_is_erase_failure(const struct ubi_device *ubi) { - if (ubi_tst_flags & UBI_TST_EMULATE_ERASE_FAILURES) + if (ubi->dbg->emulate_io_failures) return !(random32() % 400); return 0; } @@ -201,11 +210,6 @@ static inline void ubi_dbg_dump_flash(struct ubi_device *ubi, static inline void ubi_dbg_print_hex_dump(const char *l, const char *ps, int pt, int r, int g, const void *b, size_t len, bool a) { return; } - -static inline int ubi_dbg_is_bgt_disabled(void) { return 0; } -static inline int ubi_dbg_is_bitflip(void) { return 0; } -static inline int ubi_dbg_is_write_failure(void) { return 0; } -static inline int ubi_dbg_is_erase_failure(void) { return 0; } static inline int ubi_dbg_check_all_ff(struct ubi_device *ubi, int pnum, int offset, int len) { return 0; } @@ -213,5 +217,20 @@ static inline int ubi_dbg_check_write(struct ubi_device *ubi, const void *buf, int pnum, int offset, int len) { return 0; } +static inline int ubi_debugging_init_dev(struct ubi_device *ubi) { return 0; } +static inline void ubi_debugging_exit_dev(struct ubi_device *ubi) { return; } +static inline int ubi_debugfs_init(void) { return 0; } +static inline void ubi_debugfs_exit(void) { return; } +static inline int ubi_debugfs_init_dev(struct ubi_device *ubi) { return 0; } +static inline void ubi_debugfs_exit_dev(struct ubi_device *ubi) { return; } + +static inline int +ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi) { return 0; } +static inline int ubi_dbg_is_bitflip(const struct ubi_device *ubi) { return 0; } +static inline int +ubi_dbg_is_write_failure(const struct ubi_device *ubi) { return 0; } +static inline int +ubi_dbg_is_erase_failure(const struct ubi_device *ubi) { return 0; } + #endif /* !CONFIG_MTD_UBI_DEBUG */ #endif /* !__UBI_DEBUG_H__ */ diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index 8c1b1c7..6ba55c2 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -212,7 +212,7 @@ retry: } else { ubi_assert(len == read); - if (ubi_dbg_is_bitflip()) { + if (ubi_dbg_is_bitflip(ubi)) { dbg_gen("bit-flip (emulated)"); err = UBI_IO_BITFLIPS; } @@ -281,7 +281,7 @@ int ubi_io_write(struct ubi_device *ubi, const void *buf, int pnum, int offset, return err; } - if (ubi_dbg_is_write_failure()) { + if (ubi_dbg_is_write_failure(ubi)) { dbg_err("cannot write %d bytes to PEB %d:%d " "(emulated)", len, pnum, offset); ubi_dbg_dump_stack(); @@ -396,7 +396,7 @@ retry: if (err) return err; - if (ubi_dbg_is_erase_failure()) { + if (ubi_dbg_is_erase_failure(ubi)) { dbg_err("cannot erase PEB %d (emulated)", pnum); return -EIO; } @@ -1146,7 +1146,7 @@ static int paranoid_check_not_bad(const struct ubi_device *ubi, int pnum) { int err; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; err = ubi_io_is_bad(ubi, pnum); @@ -1173,7 +1173,7 @@ static int paranoid_check_ec_hdr(const struct ubi_device *ubi, int pnum, int err; uint32_t magic; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; magic = be32_to_cpu(ec_hdr->magic); @@ -1211,7 +1211,7 @@ static int paranoid_check_peb_ec_hdr(const struct ubi_device *ubi, int pnum) uint32_t crc, hdr_crc; struct ubi_ec_hdr *ec_hdr; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS); @@ -1255,7 +1255,7 @@ static int paranoid_check_vid_hdr(const struct ubi_device *ubi, int pnum, int err; uint32_t magic; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; magic = be32_to_cpu(vid_hdr->magic); @@ -1296,7 +1296,7 @@ static int paranoid_check_peb_vid_hdr(const struct ubi_device *ubi, int pnum) struct ubi_vid_hdr *vid_hdr; void *p; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; vid_hdr = ubi_zalloc_vid_hdr(ubi, GFP_NOFS); @@ -1348,7 +1348,7 @@ int ubi_dbg_check_write(struct ubi_device *ubi, const void *buf, int pnum, void *buf1; loff_t addr = (loff_t)pnum * ubi->peb_size + offset; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; buf1 = __vmalloc(len, GFP_NOFS, PAGE_KERNEL); @@ -1412,7 +1412,7 @@ int ubi_dbg_check_all_ff(struct ubi_device *ubi, int pnum, int offset, int len) void *buf; loff_t addr = (loff_t)pnum * ubi->peb_size + offset; - if (!(ubi_chk_flags & UBI_CHK_IO)) + if (!ubi->dbg->chk_io) return 0; buf = __vmalloc(len, GFP_NOFS, PAGE_KERNEL); diff --git a/drivers/mtd/ubi/scan.c b/drivers/mtd/ubi/scan.c index 2135a53..a3a198f 100644 --- a/drivers/mtd/ubi/scan.c +++ b/drivers/mtd/ubi/scan.c @@ -1347,7 +1347,7 @@ static int paranoid_check_si(struct ubi_device *ubi, struct ubi_scan_info *si) struct ubi_scan_leb *seb, *last_seb; uint8_t *buf; - if (!(ubi_chk_flags & UBI_CHK_GEN)) + if (!ubi->dbg->chk_gen) return 0; /* diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index c6c2229..dc64c76 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -44,7 +44,6 @@ #include "ubi-media.h" #include "scan.h" -#include "debug.h" /* Maximum number of supported UBI devices */ #define UBI_MAX_DEVICES 32 @@ -390,6 +389,8 @@ struct ubi_wl_entry; * @peb_buf2: another buffer of PEB size used for different purposes * @buf_mutex: protects @peb_buf1 and @peb_buf2 * @ckvol_mutex: serializes static volume checking when opening + * + * @dbg: debugging information for this UBI device */ struct ubi_device { struct cdev cdev; @@ -472,8 +473,12 @@ struct ubi_device { void *peb_buf2; struct mutex buf_mutex; struct mutex ckvol_mutex; + + struct ubi_debug_info *dbg; }; +#include "debug.h" + extern struct kmem_cache *ubi_wl_entry_slab; extern const struct file_operations ubi_ctrl_cdev_operations; extern const struct file_operations ubi_cdev_operations; @@ -662,6 +667,7 @@ static inline void ubi_ro_mode(struct ubi_device *ubi) if (!ubi->ro_mode) { ubi->ro_mode = 1; ubi_warn("switch to read-only mode"); + ubi_dbg_dump_stack(); } } diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c index 366eb70..97e093d 100644 --- a/drivers/mtd/ubi/vmt.c +++ b/drivers/mtd/ubi/vmt.c @@ -871,7 +871,7 @@ static int paranoid_check_volumes(struct ubi_device *ubi) { int i, err = 0; - if (!(ubi_chk_flags & UBI_CHK_GEN)) + if (!ubi->dbg->chk_gen) return 0; for (i = 0; i < ubi->vtbl_slots; i++) { diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c index fd3bf77..4b50a30 100644 --- a/drivers/mtd/ubi/vtbl.c +++ b/drivers/mtd/ubi/vtbl.c @@ -307,8 +307,7 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_scan_info *si, { int err, tries = 0; static struct ubi_vid_hdr *vid_hdr; - struct ubi_scan_volume *sv; - struct ubi_scan_leb *new_seb, *old_seb = NULL; + struct ubi_scan_leb *new_seb; ubi_msg("create volume table (copy #%d)", copy + 1); @@ -316,15 +315,6 @@ static int create_vtbl(struct ubi_device *ubi, struct ubi_scan_info *si, if (!vid_hdr) return -ENOMEM; - /* - * Check if there is a logical eraseblock which would have to contain - * this volume table copy was found during scanning. It has to be wiped - * out. - */ - sv = ubi_scan_find_sv(si, UBI_LAYOUT_VOLUME_ID); - if (sv) - old_seb = ubi_scan_find_seb(sv, copy); - retry: new_seb = ubi_scan_get_free_peb(ubi, si); if (IS_ERR(new_seb)) { @@ -351,8 +341,8 @@ retry: goto write_error; /* - * And add it to the scanning information. Don't delete the old - * @old_seb as it will be deleted and freed in 'ubi_scan_add_used()'. + * And add it to the scanning information. Don't delete the old version + * of this LEB as it will be deleted and freed in 'ubi_scan_add_used()'. */ err = ubi_scan_add_used(ubi, si, new_seb->pnum, new_seb->ec, vid_hdr, 0); @@ -876,7 +866,7 @@ out_free: */ static void paranoid_vtbl_check(const struct ubi_device *ubi) { - if (!(ubi_chk_flags & UBI_CHK_GEN)) + if (!ubi->dbg->chk_gen) return; if (vtbl_check(ubi, ubi->vtbl)) { diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index ff2c495..42c684c 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -1,4 +1,5 @@ /* + * @ubi: UBI device description object * Copyright (c) International Business Machines Corp., 2006 * * This program is free software; you can redistribute it and/or modify @@ -163,12 +164,14 @@ struct ubi_work { #ifdef CONFIG_MTD_UBI_DEBUG static int paranoid_check_ec(struct ubi_device *ubi, int pnum, int ec); -static int paranoid_check_in_wl_tree(struct ubi_wl_entry *e, +static int paranoid_check_in_wl_tree(const struct ubi_device *ubi, + struct ubi_wl_entry *e, struct rb_root *root); -static int paranoid_check_in_pq(struct ubi_device *ubi, struct ubi_wl_entry *e); +static int paranoid_check_in_pq(const struct ubi_device *ubi, + struct ubi_wl_entry *e); #else #define paranoid_check_ec(ubi, pnum, ec) 0 -#define paranoid_check_in_wl_tree(e, root) +#define paranoid_check_in_wl_tree(ubi, e, root) #define paranoid_check_in_pq(ubi, e) 0 #endif @@ -449,7 +452,7 @@ retry: BUG(); } - paranoid_check_in_wl_tree(e, &ubi->free); + paranoid_check_in_wl_tree(ubi, e, &ubi->free); /* * Move the physical eraseblock to the protection queue where it will @@ -613,7 +616,7 @@ static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk) list_add_tail(&wrk->list, &ubi->works); ubi_assert(ubi->works_count >= 0); ubi->works_count += 1; - if (ubi->thread_enabled && !ubi_dbg_is_bgt_disabled()) + if (ubi->thread_enabled && !ubi_dbg_is_bgt_disabled(ubi)) wake_up_process(ubi->bgt_thread); spin_unlock(&ubi->wl_lock); } @@ -712,7 +715,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, e1->ec, e2->ec); goto out_cancel; } - paranoid_check_in_wl_tree(e1, &ubi->used); + paranoid_check_in_wl_tree(ubi, e1, &ubi->used); rb_erase(&e1->u.rb, &ubi->used); dbg_wl("move PEB %d EC %d to PEB %d EC %d", e1->pnum, e1->ec, e2->pnum, e2->ec); @@ -721,12 +724,12 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, scrubbing = 1; e1 = rb_entry(rb_first(&ubi->scrub), struct ubi_wl_entry, u.rb); e2 = find_wl_entry(&ubi->free, WL_FREE_MAX_DIFF); - paranoid_check_in_wl_tree(e1, &ubi->scrub); + paranoid_check_in_wl_tree(ubi, e1, &ubi->scrub); rb_erase(&e1->u.rb, &ubi->scrub); dbg_wl("scrub PEB %d to PEB %d", e1->pnum, e2->pnum); } - paranoid_check_in_wl_tree(e2, &ubi->free); + paranoid_check_in_wl_tree(ubi, e2, &ubi->free); rb_erase(&e2->u.rb, &ubi->free); ubi->move_from = e1; ubi->move_to = e2; @@ -1169,13 +1172,13 @@ retry: return 0; } else { if (in_wl_tree(e, &ubi->used)) { - paranoid_check_in_wl_tree(e, &ubi->used); + paranoid_check_in_wl_tree(ubi, e, &ubi->used); rb_erase(&e->u.rb, &ubi->used); } else if (in_wl_tree(e, &ubi->scrub)) { - paranoid_check_in_wl_tree(e, &ubi->scrub); + paranoid_check_in_wl_tree(ubi, e, &ubi->scrub); rb_erase(&e->u.rb, &ubi->scrub); } else if (in_wl_tree(e, &ubi->erroneous)) { - paranoid_check_in_wl_tree(e, &ubi->erroneous); + paranoid_check_in_wl_tree(ubi, e, &ubi->erroneous); rb_erase(&e->u.rb, &ubi->erroneous); ubi->erroneous_peb_count -= 1; ubi_assert(ubi->erroneous_peb_count >= 0); @@ -1242,7 +1245,7 @@ retry: } if (in_wl_tree(e, &ubi->used)) { - paranoid_check_in_wl_tree(e, &ubi->used); + paranoid_check_in_wl_tree(ubi, e, &ubi->used); rb_erase(&e->u.rb, &ubi->used); } else { int err; @@ -1364,7 +1367,7 @@ int ubi_thread(void *u) spin_lock(&ubi->wl_lock); if (list_empty(&ubi->works) || ubi->ro_mode || - !ubi->thread_enabled || ubi_dbg_is_bgt_disabled()) { + !ubi->thread_enabled || ubi_dbg_is_bgt_disabled(ubi)) { set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&ubi->wl_lock); schedule(); @@ -1579,7 +1582,7 @@ static int paranoid_check_ec(struct ubi_device *ubi, int pnum, int ec) long long read_ec; struct ubi_ec_hdr *ec_hdr; - if (!(ubi_chk_flags & UBI_CHK_GEN)) + if (!ubi->dbg->chk_gen) return 0; ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS); @@ -1609,16 +1612,18 @@ out_free: /** * paranoid_check_in_wl_tree - check that wear-leveling entry is in WL RB-tree. + * @ubi: UBI device description object * @e: the wear-leveling entry to check * @root: the root of the tree * * This function returns zero if @e is in the @root RB-tree and %-EINVAL if it * is not. */ -static int paranoid_check_in_wl_tree(struct ubi_wl_entry *e, +static int paranoid_check_in_wl_tree(const struct ubi_device *ubi, + struct ubi_wl_entry *e, struct rb_root *root) { - if (!(ubi_chk_flags & UBI_CHK_GEN)) + if (!ubi->dbg->chk_gen) return 0; if (in_wl_tree(e, root)) @@ -1638,12 +1643,13 @@ static int paranoid_check_in_wl_tree(struct ubi_wl_entry *e, * * This function returns zero if @e is in @ubi->pq and %-EINVAL if it is not. */ -static int paranoid_check_in_pq(struct ubi_device *ubi, struct ubi_wl_entry *e) +static int paranoid_check_in_pq(const struct ubi_device *ubi, + struct ubi_wl_entry *e) { struct ubi_wl_entry *p; int i; - if (!(ubi_chk_flags & UBI_CHK_GEN)) + if (!ubi->dbg->chk_gen) return 0; for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i) diff --git a/drivers/net/8139too.c b/drivers/net/8139too.c index 98517a3..e3bad82 100644 --- a/drivers/net/8139too.c +++ b/drivers/net/8139too.c @@ -992,6 +992,7 @@ static int __devinit rtl8139_init_one (struct pci_dev *pdev, * features */ dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA; + dev->vlan_features = dev->features; dev->irq = pdev->irq; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 19f04a3..93359fa 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -3416,7 +3416,8 @@ config NETCONSOLE config NETCONSOLE_DYNAMIC bool "Dynamic reconfiguration of logging targets" - depends on NETCONSOLE && SYSFS && CONFIGFS_FS + depends on NETCONSOLE && SYSFS && CONFIGFS_FS && \ + !(NETCONSOLE=y && CONFIGFS_FS=m) help This option enables the ability to dynamically reconfigure target parameters (interface, IP addresses, port numbers, MAC addresses) diff --git a/drivers/net/bna/bnad.c b/drivers/net/bna/bnad.c index 7d25a97..44e219c 100644 --- a/drivers/net/bna/bnad.c +++ b/drivers/net/bna/bnad.c @@ -1111,7 +1111,7 @@ bnad_mbox_irq_alloc(struct bnad *bnad, struct bna_intr_info *intr_info) { int err = 0; - unsigned long flags; + unsigned long irq_flags = 0, flags; u32 irq; irq_handler_t irq_handler; @@ -1125,18 +1125,17 @@ bnad_mbox_irq_alloc(struct bnad *bnad, if (bnad->cfg_flags & BNAD_CF_MSIX) { irq_handler = (irq_handler_t)bnad_msix_mbox_handler; irq = bnad->msix_table[bnad->msix_num - 1].vector; - flags = 0; intr_info->intr_type = BNA_INTR_T_MSIX; intr_info->idl[0].vector = bnad->msix_num - 1; } else { irq_handler = (irq_handler_t)bnad_isr; irq = bnad->pcidev->irq; - flags = IRQF_SHARED; + irq_flags = IRQF_SHARED; intr_info->intr_type = BNA_INTR_T_INTX; /* intr_info->idl.vector = 0 ? */ } spin_unlock_irqrestore(&bnad->bna_lock, flags); - + flags = irq_flags; sprintf(bnad->mbox_irq_name, "%s", BNAD_NAME); /* diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c index 4b70311..74be989 100644 --- a/drivers/net/bnx2x/bnx2x_main.c +++ b/drivers/net/bnx2x/bnx2x_main.c @@ -49,6 +49,7 @@ #include <linux/zlib.h> #include <linux/io.h> #include <linux/stringify.h> +#include <linux/vmalloc.h> #define BNX2X_MAIN #include "bnx2x.h" @@ -4537,8 +4538,7 @@ static int bnx2x_gunzip_init(struct bnx2x *bp) if (bp->strm == NULL) goto gunzip_nomem2; - bp->strm->workspace = kmalloc(zlib_inflate_workspacesize(), - GFP_KERNEL); + bp->strm->workspace = vmalloc(zlib_inflate_workspacesize()); if (bp->strm->workspace == NULL) goto gunzip_nomem3; @@ -4562,7 +4562,7 @@ gunzip_nomem1: static void bnx2x_gunzip_end(struct bnx2x *bp) { if (bp->strm) { - kfree(bp->strm->workspace); + vfree(bp->strm->workspace); kfree(bp->strm); bp->strm = NULL; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index eafe44a..63c22b0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1428,9 +1428,9 @@ out: return features; } -#define BOND_VLAN_FEATURES (NETIF_F_ALL_TX_OFFLOADS | \ - NETIF_F_SOFT_FEATURES | \ - NETIF_F_LRO) +#define BOND_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_HIGHDMA | NETIF_F_LRO) static void bond_compute_features(struct bonding *bond) { diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 1d699e3..754df5e 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -36,7 +36,7 @@ config CAN_SLCAN config CAN_DEV tristate "Platform CAN drivers with Netlink support" depends on CAN - default Y + default y ---help--- Enables the common framework for platform CAN drivers with Netlink support. This is the standard library for CAN drivers. @@ -45,7 +45,7 @@ config CAN_DEV config CAN_CALC_BITTIMING bool "CAN bit-timing calculation" depends on CAN_DEV - default Y + default y ---help--- If enabled, CAN bit-timing parameters will be calculated for the bit-rate specified via Netlink argument "bitrate" when the device diff --git a/drivers/net/cxgb3/sge.c b/drivers/net/cxgb3/sge.c index 3f562ba..76bf589 100644 --- a/drivers/net/cxgb3/sge.c +++ b/drivers/net/cxgb3/sge.c @@ -2026,7 +2026,7 @@ static void rx_eth(struct adapter *adap, struct sge_rspq *rq, skb->ip_summed = CHECKSUM_UNNECESSARY; } else skb_checksum_none_assert(skb); - skb_record_rx_queue(skb, qs - &adap->sge.qs[0]); + skb_record_rx_queue(skb, qs - &adap->sge.qs[pi->first_qset]); if (unlikely(p->vlan_valid)) { struct vlan_group *grp = pi->vlan_grp; @@ -2145,7 +2145,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, if (!complete) return; - skb_record_rx_queue(skb, qs - &adap->sge.qs[0]); + skb_record_rx_queue(skb, qs - &adap->sge.qs[pi->first_qset]); if (unlikely(cpl->vlan_valid)) { struct vlan_group *grp = pi->vlan_grp; diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index 2dfcc80..dfa55f9 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -2289,6 +2289,23 @@ static int gfar_set_mac_address(struct net_device *dev) return 0; } +/* Check if rx parser should be activated */ +void gfar_check_rx_parser_mode(struct gfar_private *priv) +{ + struct gfar __iomem *regs; + u32 tempval; + + regs = priv->gfargrp[0].regs; + + tempval = gfar_read(®s->rctrl); + /* If parse is no longer required, then disable parser */ + if (tempval & RCTRL_REQ_PARSER) + tempval |= RCTRL_PRSDEP_INIT; + else + tempval &= ~RCTRL_PRSDEP_INIT; + gfar_write(®s->rctrl, tempval); +} + /* Enables and disables VLAN insertion/extraction */ static void gfar_vlan_rx_register(struct net_device *dev, @@ -2325,12 +2342,9 @@ static void gfar_vlan_rx_register(struct net_device *dev, /* Disable VLAN tag extraction */ tempval = gfar_read(®s->rctrl); tempval &= ~RCTRL_VLEX; - /* If parse is no longer required, then disable parser */ - if (tempval & RCTRL_REQ_PARSER) - tempval |= RCTRL_PRSDEP_INIT; - else - tempval &= ~RCTRL_PRSDEP_INIT; gfar_write(®s->rctrl, tempval); + + gfar_check_rx_parser_mode(priv); } gfar_change_mtu(dev, dev->mtu); diff --git a/drivers/net/gianfar.h b/drivers/net/gianfar.h index ba36dc7..440e69d 100644 --- a/drivers/net/gianfar.h +++ b/drivers/net/gianfar.h @@ -274,7 +274,7 @@ extern const char gfar_driver_version[]; #define RCTRL_PROM 0x00000008 #define RCTRL_EMEN 0x00000002 #define RCTRL_REQ_PARSER (RCTRL_VLEX | RCTRL_IPCSEN | \ - RCTRL_TUCSEN) + RCTRL_TUCSEN | RCTRL_FILREN) #define RCTRL_CHECKSUMMING (RCTRL_IPCSEN | RCTRL_TUCSEN | \ RCTRL_PRSDEP_INIT) #define RCTRL_EXTHASH (RCTRL_GHTX) @@ -1156,6 +1156,7 @@ extern void gfar_configure_coalescing(struct gfar_private *priv, unsigned long tx_mask, unsigned long rx_mask); void gfar_init_sysfs(struct net_device *dev); int gfar_set_features(struct net_device *dev, u32 features); +extern void gfar_check_rx_parser_mode(struct gfar_private *priv); extern const struct ethtool_ops gfar_ethtool_ops; diff --git a/drivers/net/greth.c b/drivers/net/greth.c index f181304..672f096 100644 --- a/drivers/net/greth.c +++ b/drivers/net/greth.c @@ -1015,11 +1015,10 @@ static int greth_set_mac_add(struct net_device *dev, void *p) return -EINVAL; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + GRETH_REGSAVE(regs->esa_msb, dev->dev_addr[0] << 8 | dev->dev_addr[1]); + GRETH_REGSAVE(regs->esa_lsb, dev->dev_addr[2] << 24 | dev->dev_addr[3] << 16 | + dev->dev_addr[4] << 8 | dev->dev_addr[5]); - GRETH_REGSAVE(regs->esa_msb, addr->sa_data[0] << 8 | addr->sa_data[1]); - GRETH_REGSAVE(regs->esa_lsb, - addr->sa_data[2] << 24 | addr-> - sa_data[3] << 16 | addr->sa_data[4] << 8 | addr->sa_data[5]); return 0; } diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 3e5d0b6..0d28378 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -692,10 +692,10 @@ static void sixpack_close(struct tty_struct *tty) { struct sixpack *sp; - write_lock(&disc_data_lock); + write_lock_bh(&disc_data_lock); sp = tty->disc_data; tty->disc_data = NULL; - write_unlock(&disc_data_lock); + write_unlock_bh(&disc_data_lock); if (!sp) return; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 4c62839..bc02968 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -813,10 +813,10 @@ static void mkiss_close(struct tty_struct *tty) { struct mkiss *ax; - write_lock(&disc_data_lock); + write_lock_bh(&disc_data_lock); ax = tty->disc_data; tty->disc_data = NULL; - write_unlock(&disc_data_lock); + write_unlock_bh(&disc_data_lock); if (!ax) return; diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c index b78be08..60f46bc 100644 --- a/drivers/net/natsemi.c +++ b/drivers/net/natsemi.c @@ -140,7 +140,7 @@ MODULE_LICENSE("GPL"); module_param(mtu, int, 0); module_param(debug, int, 0); module_param(rx_copybreak, int, 0); -module_param(dspcfg_workaround, int, 1); +module_param(dspcfg_workaround, int, 0); module_param_array(options, int, NULL, 0); module_param_array(full_duplex, int, NULL, 0); MODULE_PARM_DESC(mtu, "DP8381x MTU (all boards)"); @@ -2028,8 +2028,8 @@ static void drain_rx(struct net_device *dev) np->rx_ring[i].cmd_status = 0; np->rx_ring[i].addr = cpu_to_le32(0xBADF00D0); /* An invalid address. */ if (np->rx_skbuff[i]) { - pci_unmap_single(np->pci_dev, - np->rx_dma[i], buflen, + pci_unmap_single(np->pci_dev, np->rx_dma[i], + buflen + NATSEMI_PADDING, PCI_DMA_FROMDEVICE); dev_kfree_skb(np->rx_skbuff[i]); } @@ -2360,7 +2360,8 @@ static void netdev_rx(struct net_device *dev, int *work_done, int work_to_do) PCI_DMA_FROMDEVICE); } else { pci_unmap_single(np->pci_dev, np->rx_dma[entry], - buflen, PCI_DMA_FROMDEVICE); + buflen + NATSEMI_PADDING, + PCI_DMA_FROMDEVICE); skb_put(skb = np->rx_skbuff[entry], pkt_len); np->rx_skbuff[entry] = NULL; } diff --git a/drivers/net/ppp_deflate.c b/drivers/net/ppp_deflate.c index 31e9407..1dbdf82 100644 --- a/drivers/net/ppp_deflate.c +++ b/drivers/net/ppp_deflate.c @@ -305,7 +305,7 @@ static void z_decomp_free(void *arg) if (state) { zlib_inflateEnd(&state->strm); - kfree(state->strm.workspace); + vfree(state->strm.workspace); kfree(state); } } @@ -345,8 +345,7 @@ static void *z_decomp_alloc(unsigned char *options, int opt_len) state->w_size = w_size; state->strm.next_out = NULL; - state->strm.workspace = kmalloc(zlib_inflate_workspacesize(), - GFP_KERNEL|__GFP_REPEAT); + state->strm.workspace = vmalloc(zlib_inflate_workspacesize()); if (state->strm.workspace == NULL) goto out_free; diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index 718879b..bc9a4bb 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -348,8 +348,9 @@ static int pppoe_device_event(struct notifier_block *this, /* Only look at sockets that are using this specific device. */ switch (event) { + case NETDEV_CHANGEADDR: case NETDEV_CHANGEMTU: - /* A change in mtu is a bad thing, requiring + /* A change in mtu or address is a bad thing, requiring * LCP re-negotiation. */ diff --git a/drivers/net/qlge/qlge.h b/drivers/net/qlge/qlge.h index d328507..ca306fd 100644 --- a/drivers/net/qlge/qlge.h +++ b/drivers/net/qlge/qlge.h @@ -16,7 +16,7 @@ */ #define DRV_NAME "qlge" #define DRV_STRING "QLogic 10 Gigabit PCI-E Ethernet Driver " -#define DRV_VERSION "v1.00.00.27.00.00-01" +#define DRV_VERSION "v1.00.00.29.00.00-01" #define WQ_ADDR_ALIGN 0x3 /* 4 byte alignment */ @@ -1996,6 +1996,7 @@ enum { QL_LB_LINK_UP = 10, QL_FRC_COREDUMP = 11, QL_EEH_FATAL = 12, + QL_ASIC_RECOVERY = 14, /* We are in ascic recovery. */ }; /* link_status bit definitions */ diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c index 930ae45..6b4ff97 100644 --- a/drivers/net/qlge/qlge_main.c +++ b/drivers/net/qlge/qlge_main.c @@ -2152,6 +2152,10 @@ void ql_queue_asic_error(struct ql_adapter *qdev) * thread */ clear_bit(QL_ADAPTER_UP, &qdev->flags); + /* Set asic recovery bit to indicate reset process that we are + * in fatal error recovery process rather than normal close + */ + set_bit(QL_ASIC_RECOVERY, &qdev->flags); queue_delayed_work(qdev->workqueue, &qdev->asic_reset_work, 0); } @@ -2166,23 +2170,20 @@ static void ql_process_chip_ae_intr(struct ql_adapter *qdev, return; case CAM_LOOKUP_ERR_EVENT: - netif_err(qdev, link, qdev->ndev, - "Multiple CAM hits lookup occurred.\n"); - netif_err(qdev, drv, qdev->ndev, - "This event shouldn't occur.\n"); + netdev_err(qdev->ndev, "Multiple CAM hits lookup occurred.\n"); + netdev_err(qdev->ndev, "This event shouldn't occur.\n"); ql_queue_asic_error(qdev); return; case SOFT_ECC_ERROR_EVENT: - netif_err(qdev, rx_err, qdev->ndev, - "Soft ECC error detected.\n"); + netdev_err(qdev->ndev, "Soft ECC error detected.\n"); ql_queue_asic_error(qdev); break; case PCI_ERR_ANON_BUF_RD: - netif_err(qdev, rx_err, qdev->ndev, - "PCI error occurred when reading anonymous buffers from rx_ring %d.\n", - ib_ae_rsp->q_id); + netdev_err(qdev->ndev, "PCI error occurred when reading " + "anonymous buffers from rx_ring %d.\n", + ib_ae_rsp->q_id); ql_queue_asic_error(qdev); break; @@ -2437,11 +2438,10 @@ static irqreturn_t qlge_isr(int irq, void *dev_id) */ if (var & STS_FE) { ql_queue_asic_error(qdev); - netif_err(qdev, intr, qdev->ndev, - "Got fatal error, STS = %x.\n", var); + netdev_err(qdev->ndev, "Got fatal error, STS = %x.\n", var); var = ql_read32(qdev, ERR_STS); - netif_err(qdev, intr, qdev->ndev, - "Resetting chip. Error Status Register = 0x%x\n", var); + netdev_err(qdev->ndev, "Resetting chip. " + "Error Status Register = 0x%x\n", var); return IRQ_HANDLED; } @@ -3818,11 +3818,17 @@ static int ql_adapter_reset(struct ql_adapter *qdev) end_jiffies = jiffies + max((unsigned long)1, usecs_to_jiffies(30)); - /* Stop management traffic. */ - ql_mb_set_mgmnt_traffic_ctl(qdev, MB_SET_MPI_TFK_STOP); + /* Check if bit is set then skip the mailbox command and + * clear the bit, else we are in normal reset process. + */ + if (!test_bit(QL_ASIC_RECOVERY, &qdev->flags)) { + /* Stop management traffic. */ + ql_mb_set_mgmnt_traffic_ctl(qdev, MB_SET_MPI_TFK_STOP); - /* Wait for the NIC and MGMNT FIFOs to empty. */ - ql_wait_fifo_empty(qdev); + /* Wait for the NIC and MGMNT FIFOs to empty. */ + ql_wait_fifo_empty(qdev); + } else + clear_bit(QL_ASIC_RECOVERY, &qdev->flags); ql_write32(qdev, RST_FO, (RST_FO_FR << 16) | RST_FO_FR); diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 200a363..0ffec46 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -677,9 +677,11 @@ static irqreturn_t r6040_interrupt(int irq, void *dev_id) if (status & RX_FIFO_FULL) dev->stats.rx_fifo_errors++; - /* Mask off RX interrupt */ - misr &= ~RX_INTS; - napi_schedule(&lp->napi); + if (likely(napi_schedule_prep(&lp->napi))) { + /* Mask off RX interrupt */ + misr &= ~RX_INTS; + __napi_schedule(&lp->napi); + } } /* TX interrupt request */ diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 05d8178..5990621 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -742,7 +742,7 @@ static void rtl8168_oob_notify(struct rtl8169_private *tp, u8 cmd) msleep(2); for (i = 0; i < 5; i++) { udelay(100); - if (!(RTL_R32(ERIDR) & ERIAR_FLAG)) + if (!(RTL_R32(ERIAR) & ERIAR_FLAG)) break; } diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index 77c5092..5d3436d 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -378,7 +378,7 @@ static int rionet_close(struct net_device *ndev) static void rionet_remove(struct rio_dev *rdev) { - struct net_device *ndev = NULL; + struct net_device *ndev = rio_get_drvdata(rdev); struct rionet_peer *peer, *tmp; free_pages((unsigned long)rionet_active, rdev->net->hport->sys_size ? @@ -433,22 +433,12 @@ static const struct net_device_ops rionet_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, }; -static int rionet_setup_netdev(struct rio_mport *mport) +static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev) { int rc = 0; - struct net_device *ndev = NULL; struct rionet_private *rnet; u16 device_id; - /* Allocate our net_device structure */ - ndev = alloc_etherdev(sizeof(struct rionet_private)); - if (ndev == NULL) { - printk(KERN_INFO "%s: could not allocate ethernet device.\n", - DRV_NAME); - rc = -ENOMEM; - goto out; - } - rionet_active = (struct rio_dev **)__get_free_pages(GFP_KERNEL, mport->sys_size ? __fls(sizeof(void *)) + 4 : 0); if (!rionet_active) { @@ -504,11 +494,21 @@ static int rionet_probe(struct rio_dev *rdev, const struct rio_device_id *id) int rc = -ENODEV; u32 lpef, lsrc_ops, ldst_ops; struct rionet_peer *peer; + struct net_device *ndev = NULL; /* If local device is not rionet capable, give up quickly */ if (!rionet_capable) goto out; + /* Allocate our net_device structure */ + ndev = alloc_etherdev(sizeof(struct rionet_private)); + if (ndev == NULL) { + printk(KERN_INFO "%s: could not allocate ethernet device.\n", + DRV_NAME); + rc = -ENOMEM; + goto out; + } + /* * First time through, make sure local device is rionet * capable, setup netdev, and set flags so this is skipped @@ -529,7 +529,7 @@ static int rionet_probe(struct rio_dev *rdev, const struct rio_device_id *id) goto out; } - rc = rionet_setup_netdev(rdev->net->hport); + rc = rionet_setup_netdev(rdev->net->hport, ndev); rionet_check = 1; } @@ -546,6 +546,8 @@ static int rionet_probe(struct rio_dev *rdev, const struct rio_device_id *id) list_add_tail(&peer->node, &rionet_peers); } + rio_set_drvdata(rdev, ndev); + out: return rc; } diff --git a/drivers/net/sh_eth.c b/drivers/net/sh_eth.c index 8a72a97..1f3f7b4 100644 --- a/drivers/net/sh_eth.c +++ b/drivers/net/sh_eth.c @@ -140,6 +140,8 @@ static struct sh_eth_cpu_data sh_eth_my_cpu_data = { .tpauser = 1, .hw_swap = 1, .no_ade = 1, + .rpadir = 1, + .rpadir_value = 2 << 16, }; #define SH_GIGA_ETH_BASE 0xfee00000 @@ -1184,8 +1186,8 @@ static void sh_eth_adjust_link(struct net_device *ndev) mdp->cd->set_rate(ndev); } if (mdp->link == PHY_DOWN) { - sh_eth_write(ndev, (sh_eth_read(ndev, ECMR) & ~ECMR_TXF) - | ECMR_DM, ECMR); + sh_eth_write(ndev, + (sh_eth_read(ndev, ECMR) & ~ECMR_TXF), ECMR); new_state = 1; mdp->link = phydev->link; } diff --git a/drivers/net/slip.c b/drivers/net/slip.c index 8ec1a9a..2f110fb 100644 --- a/drivers/net/slip.c +++ b/drivers/net/slip.c @@ -182,11 +182,11 @@ static int sl_alloc_bufs(struct slip *sl, int mtu) #ifdef SL_INCLUDE_CSLIP cbuff = xchg(&sl->cbuff, cbuff); slcomp = xchg(&sl->slcomp, slcomp); +#endif #ifdef CONFIG_SLIP_MODE_SLIP6 sl->xdata = 0; sl->xbits = 0; #endif -#endif spin_unlock_bh(&sl->lock); err = 0; diff --git a/drivers/net/tulip/dmfe.c b/drivers/net/tulip/dmfe.c index 4685127..9a21ca3 100644 --- a/drivers/net/tulip/dmfe.c +++ b/drivers/net/tulip/dmfe.c @@ -879,7 +879,6 @@ static void dmfe_free_tx_pkt(struct DEVICE *dev, struct dmfe_board_info * db) txptr = db->tx_remove_ptr; while(db->tx_packet_cnt) { tdes0 = le32_to_cpu(txptr->tdes0); - pr_debug("tdes0=%x\n", tdes0); if (tdes0 & 0x80000000) break; @@ -889,7 +888,6 @@ static void dmfe_free_tx_pkt(struct DEVICE *dev, struct dmfe_board_info * db) /* Transmit statistic counter */ if ( tdes0 != 0x7fffffff ) { - pr_debug("tdes0=%x\n", tdes0); dev->stats.collisions += (tdes0 >> 3) & 0xf; dev->stats.tx_bytes += le32_to_cpu(txptr->tdes1) & 0x7ff; if (tdes0 & TDES0_ERR_MASK) { @@ -986,7 +984,6 @@ static void dmfe_rx_packet(struct DEVICE *dev, struct dmfe_board_info * db) /* error summary bit check */ if (rdes0 & 0x8000) { /* This is a error packet */ - pr_debug("rdes0: %x\n", rdes0); dev->stats.rx_errors++; if (rdes0 & 1) dev->stats.rx_fifo_errors++; @@ -1638,7 +1635,6 @@ static u8 dmfe_sense_speed(struct dmfe_board_info * db) else /* DM9102/DM9102A */ phy_mode = phy_read(db->ioaddr, db->phy_addr, 17, db->chip_id) & 0xf000; - pr_debug("Phy_mode %x\n", phy_mode); switch (phy_mode) { case 0x1000: db->op_mode = DMFE_10MHF; break; case 0x2000: db->op_mode = DMFE_10MFD; break; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 387ca43..304fe78 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2421,10 +2421,8 @@ static void hso_free_net_device(struct hso_device *hso_dev) remove_net_device(hso_net->parent); - if (hso_net->net) { + if (hso_net->net) unregister_netdev(hso_net->net); - free_netdev(hso_net->net); - } /* start freeing */ for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) { @@ -2436,6 +2434,9 @@ static void hso_free_net_device(struct hso_device *hso_dev) kfree(hso_net->mux_bulk_tx_buf); hso_net->mux_bulk_tx_buf = NULL; + if (hso_net->net) + free_netdev(hso_net->net); + kfree(hso_dev); } diff --git a/drivers/net/usb/kalmia.c b/drivers/net/usb/kalmia.c index d965fb1..a9b6c63 100644 --- a/drivers/net/usb/kalmia.c +++ b/drivers/net/usb/kalmia.c @@ -100,34 +100,42 @@ kalmia_send_init_packet(struct usbnet *dev, u8 *init_msg, u8 init_msg_len, static int kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) { - char init_msg_1[] = + const static char init_msg_1[] = { 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00, 0x00, 0x00 }; - char init_msg_2[] = + const static char init_msg_2[] = { 0x57, 0x50, 0x04, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0xf4, 0x00, 0x00 }; - char receive_buf[28]; + const static int buflen = 28; + char *usb_buf; int status; - status = kalmia_send_init_packet(dev, init_msg_1, sizeof(init_msg_1) - / sizeof(init_msg_1[0]), receive_buf, 24); + usb_buf = kmalloc(buflen, GFP_DMA | GFP_KERNEL); + if (!usb_buf) + return -ENOMEM; + + memcpy(usb_buf, init_msg_1, 12); + status = kalmia_send_init_packet(dev, usb_buf, sizeof(init_msg_1) + / sizeof(init_msg_1[0]), usb_buf, 24); if (status != 0) return status; - status = kalmia_send_init_packet(dev, init_msg_2, sizeof(init_msg_2) - / sizeof(init_msg_2[0]), receive_buf, 28); + memcpy(usb_buf, init_msg_2, 12); + status = kalmia_send_init_packet(dev, usb_buf, sizeof(init_msg_2) + / sizeof(init_msg_2[0]), usb_buf, 28); if (status != 0) return status; - memcpy(ethernet_addr, receive_buf + 10, ETH_ALEN); + memcpy(ethernet_addr, usb_buf + 10, ETH_ALEN); + kfree(usb_buf); return status; } static int kalmia_bind(struct usbnet *dev, struct usb_interface *intf) { - u8 status; + int status; u8 ethernet_addr[ETH_ALEN]; /* Don't bind to AT command interface */ @@ -190,7 +198,8 @@ kalmia_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) dev_kfree_skb_any(skb); skb = skb2; - done: header_start = skb_push(skb, KALMIA_HEADER_LENGTH); +done: + header_start = skb_push(skb, KALMIA_HEADER_LENGTH); ether_type_1 = header_start[KALMIA_HEADER_LENGTH + 12]; ether_type_2 = header_start[KALMIA_HEADER_LENGTH + 13]; @@ -201,9 +210,8 @@ kalmia_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags) header_start[0] = 0x57; header_start[1] = 0x44; content_len = skb->len - KALMIA_HEADER_LENGTH; - header_start[2] = (content_len & 0xff); /* low byte */ - header_start[3] = (content_len >> 8); /* high byte */ + put_unaligned_le16(content_len, &header_start[2]); header_start[4] = ether_type_1; header_start[5] = ether_type_2; @@ -231,13 +239,13 @@ kalmia_rx_fixup(struct usbnet *dev, struct sk_buff *skb) * Our task here is to strip off framing, leaving skb with one * data frame for the usbnet framework code to process. */ - const u8 HEADER_END_OF_USB_PACKET[] = + const static u8 HEADER_END_OF_USB_PACKET[] = { 0x57, 0x5a, 0x00, 0x00, 0x08, 0x00 }; - const u8 EXPECTED_UNKNOWN_HEADER_1[] = + const static u8 EXPECTED_UNKNOWN_HEADER_1[] = { 0x57, 0x43, 0x1e, 0x00, 0x15, 0x02 }; - const u8 EXPECTED_UNKNOWN_HEADER_2[] = + const static u8 EXPECTED_UNKNOWN_HEADER_2[] = { 0x57, 0x50, 0x0e, 0x00, 0x00, 0x00 }; - u8 i = 0; + int i = 0; /* incomplete header? */ if (skb->len < KALMIA_HEADER_LENGTH) @@ -285,7 +293,7 @@ kalmia_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* subtract start header and end header */ usb_packet_length = skb->len - (2 * KALMIA_HEADER_LENGTH); - ether_packet_length = header_start[2] + (header_start[3] << 8); + ether_packet_length = get_unaligned_le16(&header_start[2]); skb_pull(skb, KALMIA_HEADER_LENGTH); /* Some small packets misses end marker */ diff --git a/drivers/net/usb/zaurus.c b/drivers/net/usb/zaurus.c index 241756e..1a2234c 100644 --- a/drivers/net/usb/zaurus.c +++ b/drivers/net/usb/zaurus.c @@ -331,17 +331,7 @@ static const struct usb_device_id products [] = { ZAURUS_MASTER_INTERFACE, .driver_info = ZAURUS_PXA_INFO, }, - - -/* At least some of the newest PXA units have very different lies about - * their standards support: they claim to be cell phones offering - * direct access to their radios! (No, they don't conform to CDC MDLM.) - */ { - USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_MDLM, - USB_CDC_PROTO_NONE), - .driver_info = (unsigned long) &bogus_mdlm_info, -}, { /* Motorola MOTOMAGX phones */ USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x6425, USB_CLASS_COMM, USB_CDC_SUBCLASS_MDLM, USB_CDC_PROTO_NONE), diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index fa6e2ac..6740235 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -575,7 +575,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, struct vmxnet3_cmd_ring *ring = &rq->rx_ring[ring_idx]; u32 val; - while (num_allocated < num_to_alloc) { + while (num_allocated <= num_to_alloc) { struct vmxnet3_rx_buf_info *rbi; union Vmxnet3_GenericDesc *gd; @@ -621,9 +621,15 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, BUG_ON(rbi->dma_addr == 0); gd->rxd.addr = cpu_to_le64(rbi->dma_addr); - gd->dword[2] = cpu_to_le32((ring->gen << VMXNET3_RXD_GEN_SHIFT) + gd->dword[2] = cpu_to_le32((!ring->gen << VMXNET3_RXD_GEN_SHIFT) | val | rbi->len); + /* Fill the last buffer but dont mark it ready, or else the + * device will think that the queue is full */ + if (num_allocated == num_to_alloc) + break; + + gd->dword[2] |= cpu_to_le32(ring->gen << VMXNET3_RXD_GEN_SHIFT); num_allocated++; vmxnet3_cmd_ring_adv_next2fill(ring); } @@ -1140,6 +1146,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2 }; u32 num_rxd = 0; + bool skip_page_frags = false; struct Vmxnet3_RxCompDesc *rcd; struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx; #ifdef __BIG_ENDIAN_BITFIELD @@ -1150,11 +1157,12 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, &rxComp); while (rcd->gen == rq->comp_ring.gen) { struct vmxnet3_rx_buf_info *rbi; - struct sk_buff *skb; + struct sk_buff *skb, *new_skb = NULL; + struct page *new_page = NULL; int num_to_alloc; struct Vmxnet3_RxDesc *rxd; u32 idx, ring_idx; - + struct vmxnet3_cmd_ring *ring = NULL; if (num_rxd >= quota) { /* we may stop even before we see the EOP desc of * the current pkt @@ -1165,6 +1173,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2); idx = rcd->rxdIdx; ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1; + ring = rq->rx_ring + ring_idx; vmxnet3_getRxDesc(rxd, &rq->rx_ring[ring_idx].base[idx].rxd, &rxCmdDesc); rbi = rq->buf_info[ring_idx] + idx; @@ -1193,37 +1202,80 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, goto rcd_done; } + skip_page_frags = false; ctx->skb = rbi->skb; - rbi->skb = NULL; + new_skb = dev_alloc_skb(rbi->len + NET_IP_ALIGN); + if (new_skb == NULL) { + /* Skb allocation failed, do not handover this + * skb to stack. Reuse it. Drop the existing pkt + */ + rq->stats.rx_buf_alloc_failure++; + ctx->skb = NULL; + rq->stats.drop_total++; + skip_page_frags = true; + goto rcd_done; + } pci_unmap_single(adapter->pdev, rbi->dma_addr, rbi->len, PCI_DMA_FROMDEVICE); skb_put(ctx->skb, rcd->len); + + /* Immediate refill */ + new_skb->dev = adapter->netdev; + skb_reserve(new_skb, NET_IP_ALIGN); + rbi->skb = new_skb; + rbi->dma_addr = pci_map_single(adapter->pdev, + rbi->skb->data, rbi->len, + PCI_DMA_FROMDEVICE); + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; + } else { - BUG_ON(ctx->skb == NULL); + BUG_ON(ctx->skb == NULL && !skip_page_frags); + /* non SOP buffer must be type 1 in most cases */ - if (rbi->buf_type == VMXNET3_RX_BUF_PAGE) { - BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_BODY); + BUG_ON(rbi->buf_type != VMXNET3_RX_BUF_PAGE); + BUG_ON(rxd->btype != VMXNET3_RXD_BTYPE_BODY); - if (rcd->len) { - pci_unmap_page(adapter->pdev, - rbi->dma_addr, rbi->len, - PCI_DMA_FROMDEVICE); + /* If an sop buffer was dropped, skip all + * following non-sop fragments. They will be reused. + */ + if (skip_page_frags) + goto rcd_done; - vmxnet3_append_frag(ctx->skb, rcd, rbi); - rbi->page = NULL; - } - } else { - /* - * The only time a non-SOP buffer is type 0 is - * when it's EOP and error flag is raised, which - * has already been handled. + new_page = alloc_page(GFP_ATOMIC); + if (unlikely(new_page == NULL)) { + /* Replacement page frag could not be allocated. + * Reuse this page. Drop the pkt and free the + * skb which contained this page as a frag. Skip + * processing all the following non-sop frags. */ - BUG_ON(true); + rq->stats.rx_buf_alloc_failure++; + dev_kfree_skb(ctx->skb); + ctx->skb = NULL; + skip_page_frags = true; + goto rcd_done; + } + + if (rcd->len) { + pci_unmap_page(adapter->pdev, + rbi->dma_addr, rbi->len, + PCI_DMA_FROMDEVICE); + + vmxnet3_append_frag(ctx->skb, rcd, rbi); } + + /* Immediate refill */ + rbi->page = new_page; + rbi->dma_addr = pci_map_page(adapter->pdev, rbi->page, + 0, PAGE_SIZE, + PCI_DMA_FROMDEVICE); + rxd->addr = cpu_to_le64(rbi->dma_addr); + rxd->len = rbi->len; } + skb = ctx->skb; if (rcd->eop) { skb->len += skb->data_len; @@ -1244,26 +1296,27 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, } rcd_done: - /* device may skip some rx descs */ - rq->rx_ring[ring_idx].next2comp = idx; - VMXNET3_INC_RING_IDX_ONLY(rq->rx_ring[ring_idx].next2comp, - rq->rx_ring[ring_idx].size); - - /* refill rx buffers frequently to avoid starving the h/w */ - num_to_alloc = vmxnet3_cmd_ring_desc_avail(rq->rx_ring + - ring_idx); - if (unlikely(num_to_alloc > VMXNET3_RX_ALLOC_THRESHOLD(rq, - ring_idx, adapter))) { - vmxnet3_rq_alloc_rx_buf(rq, ring_idx, num_to_alloc, - adapter); - - /* if needed, update the register */ - if (unlikely(rq->shared->updateRxProd)) { - VMXNET3_WRITE_BAR0_REG(adapter, - rxprod_reg[ring_idx] + rq->qid * 8, - rq->rx_ring[ring_idx].next2fill); - rq->uncommitted[ring_idx] = 0; - } + /* device may have skipped some rx descs */ + ring->next2comp = idx; + num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring); + ring = rq->rx_ring + ring_idx; + while (num_to_alloc) { + vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd, + &rxCmdDesc); + BUG_ON(!rxd->addr); + + /* Recv desc is ready to be used by the device */ + rxd->gen = ring->gen; + vmxnet3_cmd_ring_adv_next2fill(ring); + num_to_alloc--; + } + + /* if needed, update the register */ + if (unlikely(rq->shared->updateRxProd)) { + VMXNET3_WRITE_BAR0_REG(adapter, + rxprod_reg[ring_idx] + rq->qid * 8, + ring->next2fill); + rq->uncommitted[ring_idx] = 0; } vmxnet3_comp_ring_adv_next2proc(&rq->comp_ring); @@ -2894,6 +2947,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, else #endif num_rx_queues = 1; + num_rx_queues = rounddown_pow_of_two(num_rx_queues); if (enable_mq) num_tx_queues = min(VMXNET3_DEVICE_MAX_TX_QUEUES, @@ -2901,6 +2955,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, else num_tx_queues = 1; + num_tx_queues = rounddown_pow_of_two(num_tx_queues); netdev = alloc_etherdev_mq(sizeof(struct vmxnet3_adapter), max(num_tx_queues, num_rx_queues)); printk(KERN_INFO "# of Tx queues : %d, # of Rx queues : %d\n", @@ -3085,6 +3140,7 @@ vmxnet3_remove_device(struct pci_dev *pdev) else #endif num_rx_queues = 1; + num_rx_queues = rounddown_pow_of_two(num_rx_queues); cancel_work_sync(&adapter->work); diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index f50d36f..e08d75e 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -55,6 +55,7 @@ #include <linux/if_vlan.h> #include <linux/if_arp.h> #include <linux/inetdevice.h> +#include <linux/log2.h> #include "vmxnet3_defs.h" @@ -68,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.1.9.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.1.18.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01010900 +#define VMXNET3_DRIVER_VERSION_NUM 0x01011200 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/net/wireless/ath/ath5k/desc.c b/drivers/net/wireless/ath/ath5k/desc.c index 62172d5..f82383b 100644 --- a/drivers/net/wireless/ath/ath5k/desc.c +++ b/drivers/net/wireless/ath/ath5k/desc.c @@ -107,10 +107,13 @@ ath5k_hw_setup_2word_tx_desc(struct ath5k_hw *ah, struct ath5k_desc *desc, case AR5K_PKT_TYPE_BEACON: case AR5K_PKT_TYPE_PROBE_RESP: frame_type = AR5K_AR5210_TX_DESC_FRAME_TYPE_NO_DELAY; + break; case AR5K_PKT_TYPE_PIFS: frame_type = AR5K_AR5210_TX_DESC_FRAME_TYPE_PIFS; + break; default: frame_type = type; + break; } tx_ctl->tx_control_0 |= diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c index 1fef84f..392771f 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.c +++ b/drivers/net/wireless/ath/ath5k/eeprom.c @@ -691,14 +691,12 @@ ath5k_eeprom_free_pcal_info(struct ath5k_hw *ah, int mode) if (!chinfo[pier].pd_curves) continue; - for (pdg = 0; pdg < ee->ee_pd_gains[mode]; pdg++) { + for (pdg = 0; pdg < AR5K_EEPROM_N_PD_CURVES; pdg++) { struct ath5k_pdgain_info *pd = &chinfo[pier].pd_curves[pdg]; - if (pd != NULL) { - kfree(pd->pd_step); - kfree(pd->pd_pwr); - } + kfree(pd->pd_step); + kfree(pd->pd_pwr); } kfree(chinfo[pier].pd_curves); diff --git a/drivers/net/wireless/ath/ath5k/pci.c b/drivers/net/wireless/ath/ath5k/pci.c index 296c316..f2c0c23 100644 --- a/drivers/net/wireless/ath/ath5k/pci.c +++ b/drivers/net/wireless/ath/ath5k/pci.c @@ -297,7 +297,9 @@ ath5k_pci_remove(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int ath5k_pci_suspend(struct device *dev) { - struct ath5k_softc *sc = pci_get_drvdata(to_pci_dev(dev)); + struct pci_dev *pdev = to_pci_dev(dev); + struct ieee80211_hw *hw = pci_get_drvdata(pdev); + struct ath5k_softc *sc = hw->priv; ath5k_led_off(sc); return 0; @@ -306,7 +308,8 @@ static int ath5k_pci_suspend(struct device *dev) static int ath5k_pci_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); - struct ath5k_softc *sc = pci_get_drvdata(pdev); + struct ieee80211_hw *hw = pci_get_drvdata(pdev); + struct ath5k_softc *sc = hw->priv; /* * Suspend/Resume resets the PCI configuration space, so we have to diff --git a/drivers/net/wireless/ath/ath5k/sysfs.c b/drivers/net/wireless/ath/ath5k/sysfs.c index 929c68c..a073cdc 100644 --- a/drivers/net/wireless/ath/ath5k/sysfs.c +++ b/drivers/net/wireless/ath/ath5k/sysfs.c @@ -10,7 +10,8 @@ static ssize_t ath5k_attr_show_##name(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ - struct ath5k_softc *sc = dev_get_drvdata(dev); \ + struct ieee80211_hw *hw = dev_get_drvdata(dev); \ + struct ath5k_softc *sc = hw->priv; \ return snprintf(buf, PAGE_SIZE, "%d\n", get); \ } \ \ @@ -18,7 +19,8 @@ static ssize_t ath5k_attr_store_##name(struct device *dev, \ struct device_attribute *attr, \ const char *buf, size_t count) \ { \ - struct ath5k_softc *sc = dev_get_drvdata(dev); \ + struct ieee80211_hw *hw = dev_get_drvdata(dev); \ + struct ath5k_softc *sc = hw->priv; \ int val; \ \ val = (int)simple_strtoul(buf, NULL, 10); \ @@ -33,7 +35,8 @@ static ssize_t ath5k_attr_show_##name(struct device *dev, \ struct device_attribute *attr, \ char *buf) \ { \ - struct ath5k_softc *sc = dev_get_drvdata(dev); \ + struct ieee80211_hw *hw = dev_get_drvdata(dev); \ + struct ath5k_softc *sc = hw->priv; \ return snprintf(buf, PAGE_SIZE, "%d\n", get); \ } \ static DEVICE_ATTR(name, S_IRUGO, ath5k_attr_show_##name, NULL) diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c index b8cbfc7..3bad0b2 100644 --- a/drivers/net/wireless/ath/ath9k/pci.c +++ b/drivers/net/wireless/ath/ath9k/pci.c @@ -278,6 +278,12 @@ static int ath_pci_suspend(struct device *device) ath9k_hw_set_gpio(sc->sc_ah, sc->sc_ah->led_pin, 1); + /* The device has to be moved to FULLSLEEP forcibly. + * Otherwise the chip never moved to full sleep, + * when no interface is up. + */ + ath9k_hw_setpower(sc->sc_ah, ATH9K_PM_FULL_SLEEP); + return 0; } diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 3779b89..33443bc 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -671,7 +671,8 @@ static int ath_compute_num_delims(struct ath_softc *sc, struct ath_atx_tid *tid, * TODO - this could be improved to be dependent on the rate. * The hardware can keep up at lower rates, but not higher rates */ - if (fi->keyix != ATH9K_TXKEYIX_INVALID) + if ((fi->keyix != ATH9K_TXKEYIX_INVALID) && + !(sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA)) ndelim += ATH_AGGR_ENCRYPTDELIM; /* diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c index 2fb53d0..333b69e 100644 --- a/drivers/net/wireless/ath/carl9170/usb.c +++ b/drivers/net/wireless/ath/carl9170/usb.c @@ -112,6 +112,8 @@ static struct usb_device_id carl9170_usb_ids[] = { { USB_DEVICE(0x04bb, 0x093f) }, /* NEC WL300NU-G */ { USB_DEVICE(0x0409, 0x0249) }, + /* NEC WL300NU-AG */ + { USB_DEVICE(0x0409, 0x02b4) }, /* AVM FRITZ!WLAN USB Stick N */ { USB_DEVICE(0x057c, 0x8401) }, /* AVM FRITZ!WLAN USB Stick N 2.4 */ diff --git a/drivers/net/wireless/iwlwifi/iwl-1000.c b/drivers/net/wireless/iwlwifi/iwl-1000.c index 61d4a11..2a88e73 100644 --- a/drivers/net/wireless/iwlwifi/iwl-1000.c +++ b/drivers/net/wireless/iwlwifi/iwl-1000.c @@ -36,6 +36,7 @@ #include <net/mac80211.h> #include <linux/etherdevice.h> #include <asm/unaligned.h> +#include <linux/stringify.h> #include "iwl-eeprom.h" #include "iwl-dev.h" @@ -55,10 +56,10 @@ #define IWL100_UCODE_API_MIN 5 #define IWL1000_FW_PRE "iwlwifi-1000-" -#define IWL1000_MODULE_FIRMWARE(api) IWL1000_FW_PRE #api ".ucode" +#define IWL1000_MODULE_FIRMWARE(api) IWL1000_FW_PRE __stringify(api) ".ucode" #define IWL100_FW_PRE "iwlwifi-100-" -#define IWL100_MODULE_FIRMWARE(api) IWL100_FW_PRE #api ".ucode" +#define IWL100_MODULE_FIRMWARE(api) IWL100_FW_PRE __stringify(api) ".ucode" /* diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c index 2282279..3df76f5 100644 --- a/drivers/net/wireless/iwlwifi/iwl-2000.c +++ b/drivers/net/wireless/iwlwifi/iwl-2000.c @@ -36,6 +36,7 @@ #include <net/mac80211.h> #include <linux/etherdevice.h> #include <asm/unaligned.h> +#include <linux/stringify.h> #include "iwl-eeprom.h" #include "iwl-dev.h" @@ -58,13 +59,13 @@ #define IWL105_UCODE_API_MIN 5 #define IWL2030_FW_PRE "iwlwifi-2030-" -#define IWL2030_MODULE_FIRMWARE(api) IWL2030_FW_PRE #api ".ucode" +#define IWL2030_MODULE_FIRMWARE(api) IWL2030_FW_PRE __stringify(api) ".ucode" #define IWL2000_FW_PRE "iwlwifi-2000-" -#define IWL2000_MODULE_FIRMWARE(api) IWL2000_FW_PRE #api ".ucode" +#define IWL2000_MODULE_FIRMWARE(api) IWL2000_FW_PRE __stringify(api) ".ucode" #define IWL105_FW_PRE "iwlwifi-105-" -#define IWL105_MODULE_FIRMWARE(api) IWL105_FW_PRE #api ".ucode" +#define IWL105_MODULE_FIRMWARE(api) IWL105_FW_PRE __stringify(api) ".ucode" static void iwl2000_set_ct_threshold(struct iwl_priv *priv) { diff --git a/drivers/net/wireless/iwlwifi/iwl-5000.c b/drivers/net/wireless/iwlwifi/iwl-5000.c index f99f9c1..e816c27 100644 --- a/drivers/net/wireless/iwlwifi/iwl-5000.c +++ b/drivers/net/wireless/iwlwifi/iwl-5000.c @@ -37,6 +37,7 @@ #include <net/mac80211.h> #include <linux/etherdevice.h> #include <asm/unaligned.h> +#include <linux/stringify.h> #include "iwl-eeprom.h" #include "iwl-dev.h" @@ -57,10 +58,10 @@ #define IWL5150_UCODE_API_MIN 1 #define IWL5000_FW_PRE "iwlwifi-5000-" -#define IWL5000_MODULE_FIRMWARE(api) IWL5000_FW_PRE #api ".ucode" +#define IWL5000_MODULE_FIRMWARE(api) IWL5000_FW_PRE __stringify(api) ".ucode" #define IWL5150_FW_PRE "iwlwifi-5150-" -#define IWL5150_MODULE_FIRMWARE(api) IWL5150_FW_PRE #api ".ucode" +#define IWL5150_MODULE_FIRMWARE(api) IWL5150_FW_PRE __stringify(api) ".ucode" /* NIC configuration for 5000 series */ static void iwl5000_nic_config(struct iwl_priv *priv) diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index fbe565c..5b150bc 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -36,6 +36,7 @@ #include <net/mac80211.h> #include <linux/etherdevice.h> #include <asm/unaligned.h> +#include <linux/stringify.h> #include "iwl-eeprom.h" #include "iwl-dev.h" @@ -58,16 +59,16 @@ #define IWL6000G2_UCODE_API_MIN 4 #define IWL6000_FW_PRE "iwlwifi-6000-" -#define IWL6000_MODULE_FIRMWARE(api) IWL6000_FW_PRE #api ".ucode" +#define IWL6000_MODULE_FIRMWARE(api) IWL6000_FW_PRE __stringify(api) ".ucode" #define IWL6050_FW_PRE "iwlwifi-6050-" -#define IWL6050_MODULE_FIRMWARE(api) IWL6050_FW_PRE #api ".ucode" +#define IWL6050_MODULE_FIRMWARE(api) IWL6050_FW_PRE __stringify(api) ".ucode" #define IWL6005_FW_PRE "iwlwifi-6000g2a-" -#define IWL6005_MODULE_FIRMWARE(api) IWL6005_FW_PRE #api ".ucode" +#define IWL6005_MODULE_FIRMWARE(api) IWL6005_FW_PRE __stringify(api) ".ucode" #define IWL6030_FW_PRE "iwlwifi-6000g2b-" -#define IWL6030_MODULE_FIRMWARE(api) IWL6030_FW_PRE #api ".ucode" +#define IWL6030_MODULE_FIRMWARE(api) IWL6030_FW_PRE __stringify(api) ".ucode" static void iwl6000_set_ct_threshold(struct iwl_priv *priv) { diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index 213c80c..45cc51c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -1763,6 +1763,7 @@ int iwl_mac_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct iwl_rxon_context *ctx = iwl_rxon_ctx_from_vif(vif); struct iwl_rxon_context *bss_ctx = &priv->contexts[IWL_RXON_CTX_BSS]; struct iwl_rxon_context *tmp; + enum nl80211_iftype newviftype = newtype; u32 interface_modes; int err; @@ -1818,7 +1819,7 @@ int iwl_mac_change_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif, /* success */ iwl_teardown_interface(priv, vif, true); - vif->type = newtype; + vif->type = newviftype; vif->p2p = newp2p; err = iwl_setup_interface(priv, ctx); WARN_ON(err); diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c index 686e176..137dba9 100644 --- a/drivers/net/wireless/iwlwifi/iwl-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-tx.c @@ -126,7 +126,7 @@ static inline u8 iwl_tfd_get_num_tbs(struct iwl_tfd *tfd) } static void iwlagn_unmap_tfd(struct iwl_priv *priv, struct iwl_cmd_meta *meta, - struct iwl_tfd *tfd) + struct iwl_tfd *tfd, int dma_dir) { struct pci_dev *dev = priv->pci_dev; int i; @@ -151,7 +151,7 @@ static void iwlagn_unmap_tfd(struct iwl_priv *priv, struct iwl_cmd_meta *meta, /* Unmap chunks, if any. */ for (i = 1; i < num_tbs; i++) pci_unmap_single(dev, iwl_tfd_tb_get_addr(tfd, i), - iwl_tfd_tb_get_len(tfd, i), PCI_DMA_TODEVICE); + iwl_tfd_tb_get_len(tfd, i), dma_dir); } /** @@ -167,7 +167,8 @@ void iwlagn_txq_free_tfd(struct iwl_priv *priv, struct iwl_tx_queue *txq) struct iwl_tfd *tfd_tmp = txq->tfds; int index = txq->q.read_ptr; - iwlagn_unmap_tfd(priv, &txq->meta[index], &tfd_tmp[index]); + iwlagn_unmap_tfd(priv, &txq->meta[index], &tfd_tmp[index], + PCI_DMA_TODEVICE); /* free SKB */ if (txq->txb) { @@ -310,9 +311,7 @@ void iwl_cmd_queue_unmap(struct iwl_priv *priv) i = get_cmd_index(q, q->read_ptr); if (txq->meta[i].flags & CMD_MAPPED) { - pci_unmap_single(priv->pci_dev, - dma_unmap_addr(&txq->meta[i], mapping), - dma_unmap_len(&txq->meta[i], len), + iwlagn_unmap_tfd(priv, &txq->meta[i], &txq->tfds[i], PCI_DMA_BIDIRECTIONAL); txq->meta[i].flags = 0; } @@ -535,12 +534,7 @@ out_free_arrays: void iwl_tx_queue_reset(struct iwl_priv *priv, struct iwl_tx_queue *txq, int slots_num, u32 txq_id) { - int actual_slots = slots_num; - - if (txq_id == priv->cmd_queue) - actual_slots++; - - memset(txq->meta, 0, sizeof(struct iwl_cmd_meta) * actual_slots); + memset(txq->meta, 0, sizeof(struct iwl_cmd_meta) * slots_num); txq->need_update = 0; @@ -700,10 +694,11 @@ int iwl_enqueue_hcmd(struct iwl_priv *priv, struct iwl_host_cmd *cmd) if (!(cmd->dataflags[i] & IWL_HCMD_DFL_NOCOPY)) continue; phys_addr = pci_map_single(priv->pci_dev, (void *)cmd->data[i], - cmd->len[i], PCI_DMA_TODEVICE); + cmd->len[i], PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(priv->pci_dev, phys_addr)) { iwlagn_unmap_tfd(priv, out_meta, - &txq->tfds[q->write_ptr]); + &txq->tfds[q->write_ptr], + PCI_DMA_BIDIRECTIONAL); idx = -ENOMEM; goto out; } @@ -807,7 +802,7 @@ void iwl_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb) cmd = txq->cmd[cmd_index]; meta = &txq->meta[cmd_index]; - iwlagn_unmap_tfd(priv, meta, &txq->tfds[index]); + iwlagn_unmap_tfd(priv, meta, &txq->tfds[index], PCI_DMA_BIDIRECTIONAL); /* Input error checking is done when commands are added to queue. */ if (meta->flags & CMD_WANT_SKB) { diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c index 9f8ccae..254b64b 100644 --- a/drivers/net/wireless/rtlwifi/pci.c +++ b/drivers/net/wireless/rtlwifi/pci.c @@ -1624,6 +1624,16 @@ static bool _rtl_pci_find_adapter(struct pci_dev *pdev, pci_read_config_byte(pdev, 0x8, &revisionid); pci_read_config_word(pdev, 0x3C, &irqline); + /* PCI ID 0x10ec:0x8192 occurs for both RTL8192E, which uses + * r8192e_pci, and RTL8192SE, which uses this driver. If the + * revision ID is RTL_PCI_REVISION_ID_8192PCIE (0x01), then + * the correct driver is r8192e_pci, thus this routine should + * return false. + */ + if (deviceid == RTL_PCI_8192SE_DID && + revisionid == RTL_PCI_REVISION_ID_8192PCIE) + return false; + if (deviceid == RTL_PCI_8192_DID || deviceid == RTL_PCI_0044_DID || deviceid == RTL_PCI_0047_DID || @@ -1856,7 +1866,8 @@ int __devinit rtl_pci_probe(struct pci_dev *pdev, pci_write_config_byte(pdev, 0x04, 0x07); /* find adapter */ - _rtl_pci_find_adapter(pdev, hw); + if (!_rtl_pci_find_adapter(pdev, hw)) + goto fail3; /* Init IO handler */ _rtl_pci_io_handler_init(&pdev->dev, hw); diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c index bee7c14..942f7a3 100644 --- a/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c +++ b/drivers/net/wireless/rtlwifi/rtl8192cu/sw.c @@ -53,6 +53,8 @@ MODULE_FIRMWARE("rtlwifi/rtl8192cufw.bin"); static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw) { struct rtl_priv *rtlpriv = rtl_priv(hw); + const struct firmware *firmware; + int err; rtlpriv->dm.dm_initialgain_enable = 1; rtlpriv->dm.dm_flag = 0; @@ -64,6 +66,24 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw) ("Can't alloc buffer for fw.\n")); return 1; } + /* request fw */ + err = request_firmware(&firmware, rtlpriv->cfg->fw_name, + rtlpriv->io.dev); + if (err) { + RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, + ("Failed to request firmware!\n")); + return 1; + } + if (firmware->size > 0x4000) { + RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, + ("Firmware is too big!\n")); + release_firmware(firmware); + return 1; + } + memcpy(rtlpriv->rtlhal.pfirmware, firmware->data, firmware->size); + rtlpriv->rtlhal.fwsize = firmware->size; + release_firmware(firmware); + return 0; } @@ -278,6 +298,7 @@ static struct usb_device_id rtl8192c_usb_ids[] = { {RTL_USB_DEVICE(0x06f8, 0xe033, rtl92cu_hal_cfg)}, /*Hercules - Edimax*/ {RTL_USB_DEVICE(0x07b8, 0x8188, rtl92cu_hal_cfg)}, /*Abocom - Abocom*/ {RTL_USB_DEVICE(0x07b8, 0x8189, rtl92cu_hal_cfg)}, /*Funai - Abocom*/ + {RTL_USB_DEVICE(0x0846, 0x9041, rtl92cu_hal_cfg)}, /*NetGear WNA1000M*/ {RTL_USB_DEVICE(0x0Df6, 0x0052, rtl92cu_hal_cfg)}, /*Sitecom - Edimax*/ {RTL_USB_DEVICE(0x0eb0, 0x9071, rtl92cu_hal_cfg)}, /*NO Brand - Etop*/ /* HP - Lite-On ,8188CUS Slim Combo */ diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 135df16..46767c5 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -624,7 +624,7 @@ static int pci_pm_prepare(struct device *dev) * system from the sleep state, we'll have to prevent it from signaling * wake-up. */ - pm_runtime_resume(dev); + pm_runtime_get_sync(dev); if (drv && drv->pm && drv->pm->prepare) error = drv->pm->prepare(dev); @@ -638,6 +638,8 @@ static void pci_pm_complete(struct device *dev) if (drv && drv->pm && drv->pm->complete) drv->pm->complete(dev); + + pm_runtime_put_sync(dev); } #else /* !CONFIG_PM_SLEEP */ diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 5f10c23..692671b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3284,7 +3284,7 @@ static int pci_set_vga_state_arch(struct pci_dev *dev, bool decode, * @dev: the PCI device * @decode: true = enable decoding, false = disable decoding * @command_bits: PCI_COMMAND_IO and/or PCI_COMMAND_MEMORY - * @change_bridge_flags: traverse ancestors and change bridges + * @flags: traverse ancestors and change bridges * CHANGE_BRIDGE_ONLY / CHANGE_BRIDGE */ int pci_set_vga_state(struct pci_dev *dev, bool decode, @@ -3483,6 +3483,8 @@ static int __init pci_setup(char *str) pci_no_msi(); } else if (!strcmp(str, "noaer")) { pci_no_aer(); + } else if (!strncmp(str, "realloc", 7)) { + pci_realloc(); } else if (!strcmp(str, "nodomains")) { pci_no_domains(); } else if (!strncmp(str, "cbiosize=", 9)) { diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 731e202..3a39bf1 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -146,6 +146,8 @@ static inline void pci_no_msi(void) { } static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { } #endif +extern void pci_realloc(void); + static inline int pci_no_d1d2(struct pci_dev *dev) { unsigned int parent_dstates = 0; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 48849ff..bafb3c3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -168,7 +168,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, res->flags |= pci_calc_resource_flags(l) | IORESOURCE_SIZEALIGN; if (type == pci_bar_io) { l &= PCI_BASE_ADDRESS_IO_MASK; - mask = PCI_BASE_ADDRESS_IO_MASK & IO_SPACE_LIMIT; + mask = PCI_BASE_ADDRESS_IO_MASK & (u32) IO_SPACE_LIMIT; } else { l &= PCI_BASE_ADDRESS_MEM_MASK; mask = (u32)PCI_BASE_ADDRESS_MEM_MASK; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e8a1406..1196f61 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2758,9 +2758,34 @@ static void ricoh_mmc_fixup_r5c832(struct pci_dev *dev) dev_notice(&dev->dev, "proprietary Ricoh MMC controller disabled (via firewire function)\n"); dev_notice(&dev->dev, "MMC cards are now supported by standard SDHCI controller\n"); + + /* + * RICOH 0xe823 SD/MMC card reader fails to recognize + * certain types of SD/MMC cards. Lowering the SD base + * clock frequency from 200Mhz to 50Mhz fixes this issue. + * + * 0x150 - SD2.0 mode enable for changing base clock + * frequency to 50Mhz + * 0xe1 - Base clock frequency + * 0x32 - 50Mhz new clock frequency + * 0xf9 - Key register for 0x150 + * 0xfc - key register for 0xe1 + */ + if (dev->device == PCI_DEVICE_ID_RICOH_R5CE823) { + pci_write_config_byte(dev, 0xf9, 0xfc); + pci_write_config_byte(dev, 0x150, 0x10); + pci_write_config_byte(dev, 0xf9, 0x00); + pci_write_config_byte(dev, 0xfc, 0x01); + pci_write_config_byte(dev, 0xe1, 0x32); + pci_write_config_byte(dev, 0xfc, 0x00); + + dev_notice(&dev->dev, "MMC controller base frequency changed to 50Mhz.\n"); + } } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832); DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832); +DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5CE823, ricoh_mmc_fixup_r5c832); #endif /*CONFIG_MMC_RICOH_MMC*/ #if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 1e9e5a5..9995842 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -47,6 +47,13 @@ struct resource_list_x { (head)->next = NULL; \ } while (0) +int pci_realloc_enable = 0; +#define pci_realloc_enabled() pci_realloc_enable +void pci_realloc(void) +{ + pci_realloc_enable = 1; +} + /** * add_to_list() - add a new resource tracker to the list * @head: Head of the list @@ -1025,6 +1032,7 @@ static int __init pci_get_max_depth(void) return depth; } + /* * first try will not touch pci bridge res * second and later try will clear small leaf bridge res @@ -1068,6 +1076,13 @@ again: /* any device complain? */ if (!head.next) goto enable_and_dump; + + /* don't realloc if asked to do so */ + if (!pci_realloc_enabled()) { + free_list(resource_list_x, &head); + goto enable_and_dump; + } + failed_type = 0; for (list = head.next; list;) { failed_type |= list->flags; diff --git a/drivers/pcmcia/pxa2xx_vpac270.c b/drivers/pcmcia/pxa2xx_vpac270.c index 712baab..e956f65 100644 --- a/drivers/pcmcia/pxa2xx_vpac270.c +++ b/drivers/pcmcia/pxa2xx_vpac270.c @@ -76,10 +76,10 @@ static int vpac270_pcmcia_hw_init(struct soc_pcmcia_socket *skt) static void vpac270_pcmcia_hw_shutdown(struct soc_pcmcia_socket *skt) { if (skt->nr == 0) - gpio_request_array(vpac270_pcmcia_gpios, + gpio_free_array(vpac270_pcmcia_gpios, ARRAY_SIZE(vpac270_pcmcia_gpios)); else - gpio_request_array(vpac270_cf_gpios, + gpio_free_array(vpac270_cf_gpios, ARRAY_SIZE(vpac270_cf_gpios)); } diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 005417b..e1c4938 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -1156,9 +1156,9 @@ static acpi_status wmid3_set_device_status(u32 value, u16 device) struct wmid3_gds_input_param params = { .function_num = 0x1, .hotkey_number = 0x01, - .devices = ACER_WMID3_GDS_WIRELESS & - ACER_WMID3_GDS_THREEG & - ACER_WMID3_GDS_WIMAX & + .devices = ACER_WMID3_GDS_WIRELESS | + ACER_WMID3_GDS_THREEG | + ACER_WMID3_GDS_WIMAX | ACER_WMID3_GDS_BLUETOOTH, }; struct acpi_buffer input = { @@ -1445,6 +1445,8 @@ static void acer_wmi_notify(u32 value, void *context) union acpi_object *obj; struct event_return_value return_value; acpi_status status; + u16 device_state; + const struct key_entry *key; status = wmi_get_event_data(value, &response); if (status != AE_OK) { @@ -1472,23 +1474,32 @@ static void acer_wmi_notify(u32 value, void *context) switch (return_value.function) { case WMID_HOTKEY_EVENT: - if (return_value.device_state) { - u16 device_state = return_value.device_state; - pr_debug("device state: 0x%x\n", device_state); - if (has_cap(ACER_CAP_WIRELESS)) - rfkill_set_sw_state(wireless_rfkill, - !(device_state & ACER_WMID3_GDS_WIRELESS)); - if (has_cap(ACER_CAP_BLUETOOTH)) - rfkill_set_sw_state(bluetooth_rfkill, - !(device_state & ACER_WMID3_GDS_BLUETOOTH)); - if (has_cap(ACER_CAP_THREEG)) - rfkill_set_sw_state(threeg_rfkill, - !(device_state & ACER_WMID3_GDS_THREEG)); - } - if (!sparse_keymap_report_event(acer_wmi_input_dev, - return_value.key_num, 1, true)) + device_state = return_value.device_state; + pr_debug("device state: 0x%x\n", device_state); + + key = sparse_keymap_entry_from_scancode(acer_wmi_input_dev, + return_value.key_num); + if (!key) { pr_warn("Unknown key number - 0x%x\n", return_value.key_num); + } else { + switch (key->keycode) { + case KEY_WLAN: + case KEY_BLUETOOTH: + if (has_cap(ACER_CAP_WIRELESS)) + rfkill_set_sw_state(wireless_rfkill, + !(device_state & ACER_WMID3_GDS_WIRELESS)); + if (has_cap(ACER_CAP_THREEG)) + rfkill_set_sw_state(threeg_rfkill, + !(device_state & ACER_WMID3_GDS_THREEG)); + if (has_cap(ACER_CAP_BLUETOOTH)) + rfkill_set_sw_state(bluetooth_rfkill, + !(device_state & ACER_WMID3_GDS_BLUETOOTH)); + break; + } + sparse_keymap_report_entry(acer_wmi_input_dev, key, + 1, true); + } break; default: pr_warn("Unknown function number - %d - %d\n", diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 00460cb..3c7857c 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -1025,6 +1025,7 @@ static int asus_wmi_backlight_init(struct asus_wmi *asus) return power; memset(&props, 0, sizeof(struct backlight_properties)); + props.type = BACKLIGHT_PLATFORM; props.max_brightness = max; bd = backlight_device_register(asus->driver->name, &asus->platform_device->dev, asus, diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c index 3f204fd..8877b83 100644 --- a/drivers/platform/x86/compal-laptop.c +++ b/drivers/platform/x86/compal-laptop.c @@ -1030,8 +1030,10 @@ static int __devinit compal_probe(struct platform_device *pdev) initialize_fan_control_data(data); err = sysfs_create_group(&pdev->dev.kobj, &compal_attribute_group); - if (err) + if (err) { + kfree(data); return err; + } data->hwmon_dev = hwmon_device_register(&pdev->dev); if (IS_ERR(data->hwmon_dev)) { diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c index d3841de..e39ab1d 100644 --- a/drivers/platform/x86/dell-laptop.c +++ b/drivers/platform/x86/dell-laptop.c @@ -292,12 +292,9 @@ static int dell_rfkill_set(void *data, bool blocked) dell_send_request(buffer, 17, 11); /* If the hardware switch controls this radio, and the hardware - switch is disabled, don't allow changing the software state. - If the hardware switch is reported as not supported, always - fire the SMI to toggle the killswitch. */ + switch is disabled, don't allow changing the software state */ if ((hwswitch_state & BIT(hwswitch_bit)) && - !(buffer->output[1] & BIT(16)) && - (buffer->output[1] & BIT(0))) { + !(buffer->output[1] & BIT(16))) { ret = -EINVAL; goto out; } @@ -403,23 +400,6 @@ static const struct file_operations dell_debugfs_fops = { static void dell_update_rfkill(struct work_struct *ignored) { - int status; - - get_buffer(); - dell_send_request(buffer, 17, 11); - status = buffer->output[1]; - release_buffer(); - - /* if hardware rfkill is not supported, set it explicitly */ - if (!(status & BIT(0))) { - if (wifi_rfkill) - dell_rfkill_set((void *)1, !((status & BIT(17)) >> 17)); - if (bluetooth_rfkill) - dell_rfkill_set((void *)2, !((status & BIT(18)) >> 18)); - if (wwan_rfkill) - dell_rfkill_set((void *)3, !((status & BIT(19)) >> 19)); - } - if (wifi_rfkill) dell_rfkill_query(wifi_rfkill, (void *)1); if (bluetooth_rfkill) @@ -560,11 +540,11 @@ static int dell_get_intensity(struct backlight_device *bd) else dell_send_request(buffer, 0, 1); + ret = buffer->output[1]; + out: release_buffer(); - if (ret) - return ret; - return buffer->output[1]; + return ret; } static const struct backlight_ops dell_ops = { diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index f94017b..e2faa3c 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -207,6 +207,7 @@ static int hp_wmi_perform_query(int query, int write, void *buffer, }; struct acpi_buffer input = { sizeof(struct bios_args), &args }; struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + u32 rc; if (WARN_ON(insize > sizeof(args.data))) return -EINVAL; @@ -224,13 +225,13 @@ static int hp_wmi_perform_query(int query, int write, void *buffer, } bios_return = (struct bios_return *)obj->buffer.pointer; + rc = bios_return->return_code; - if (bios_return->return_code) { - if (bios_return->return_code != HPWMI_RET_UNKNOWN_CMDTYPE) - pr_warn("query 0x%x returned error 0x%x\n", - query, bios_return->return_code); + if (rc) { + if (rc != HPWMI_RET_UNKNOWN_CMDTYPE) + pr_warn("query 0x%x returned error 0x%x\n", query, rc); kfree(obj); - return bios_return->return_code; + return rc; } if (!outsize) { diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c index e936364..7f88c79 100644 --- a/drivers/platform/x86/intel_oaktrail.c +++ b/drivers/platform/x86/intel_oaktrail.c @@ -250,6 +250,7 @@ static int oaktrail_backlight_init(void) struct backlight_properties props; memset(&props, 0, sizeof(struct backlight_properties)); + props.type = BACKLIGHT_PLATFORM; props.max_brightness = OT_EC_BL_BRIGHTNESS_MAX; bd = backlight_device_register(DRIVER_NAME, &oaktrail_device->dev, NULL, diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 77f6e70..26c5b11 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -184,6 +184,10 @@ enum tpacpi_hkey_event_t { /* Misc bay events */ TP_HKEY_EV_OPTDRV_EJ = 0x3006, /* opt. drive tray ejected */ + TP_HKEY_EV_HOTPLUG_DOCK = 0x4010, /* docked into hotplug dock + or port replicator */ + TP_HKEY_EV_HOTPLUG_UNDOCK = 0x4011, /* undocked from hotplug + dock or port replicator */ /* User-interface events */ TP_HKEY_EV_LID_CLOSE = 0x5001, /* laptop lid closed */ @@ -194,6 +198,10 @@ enum tpacpi_hkey_event_t { TP_HKEY_EV_PEN_REMOVED = 0x500c, /* tablet pen removed */ TP_HKEY_EV_BRGHT_CHANGED = 0x5010, /* backlight control event */ + /* Key-related user-interface events */ + TP_HKEY_EV_KEY_NUMLOCK = 0x6000, /* NumLock key pressed */ + TP_HKEY_EV_KEY_FN = 0x6005, /* Fn key pressed? E420 */ + /* Thermal events */ TP_HKEY_EV_ALARM_BAT_HOT = 0x6011, /* battery too hot */ TP_HKEY_EV_ALARM_BAT_XHOT = 0x6012, /* battery critically hot */ @@ -201,6 +209,10 @@ enum tpacpi_hkey_event_t { TP_HKEY_EV_ALARM_SENSOR_XHOT = 0x6022, /* sensor critically hot */ TP_HKEY_EV_THM_TABLE_CHANGED = 0x6030, /* thermal table changed */ + TP_HKEY_EV_UNK_6040 = 0x6040, /* Related to AC change? + some sort of APM hint, + W520 */ + /* Misc */ TP_HKEY_EV_RFKILL_CHANGED = 0x7000, /* rfkill switch changed */ }; @@ -3513,6 +3525,34 @@ static bool hotkey_notify_wakeup(const u32 hkey, return true; } +static bool hotkey_notify_dockevent(const u32 hkey, + bool *send_acpi_ev, + bool *ignore_acpi_ev) +{ + /* 0x4000-0x4FFF: dock-related events */ + *send_acpi_ev = true; + *ignore_acpi_ev = false; + + switch (hkey) { + case TP_HKEY_EV_UNDOCK_ACK: + /* ACPI undock operation completed after wakeup */ + hotkey_autosleep_ack = 1; + pr_info("undocked\n"); + hotkey_wakeup_hotunplug_complete_notify_change(); + return true; + + case TP_HKEY_EV_HOTPLUG_DOCK: /* docked to port replicator */ + pr_info("docked into hotplug port replicator\n"); + return true; + case TP_HKEY_EV_HOTPLUG_UNDOCK: /* undocked from port replicator */ + pr_info("undocked from hotplug port replicator\n"); + return true; + + default: + return false; + } +} + static bool hotkey_notify_usrevent(const u32 hkey, bool *send_acpi_ev, bool *ignore_acpi_ev) @@ -3547,13 +3587,13 @@ static bool hotkey_notify_usrevent(const u32 hkey, static void thermal_dump_all_sensors(void); -static bool hotkey_notify_thermal(const u32 hkey, +static bool hotkey_notify_6xxx(const u32 hkey, bool *send_acpi_ev, bool *ignore_acpi_ev) { bool known = true; - /* 0x6000-0x6FFF: thermal alarms */ + /* 0x6000-0x6FFF: thermal alarms/notices and keyboard events */ *send_acpi_ev = true; *ignore_acpi_ev = false; @@ -3582,8 +3622,17 @@ static bool hotkey_notify_thermal(const u32 hkey, "a sensor reports something is extremely hot!\n"); /* recommended action: immediate sleep/hibernate */ break; + + case TP_HKEY_EV_KEY_NUMLOCK: + case TP_HKEY_EV_KEY_FN: + /* key press events, we just ignore them as long as the EC + * is still reporting them in the normal keyboard stream */ + *send_acpi_ev = false; + *ignore_acpi_ev = true; + return true; + default: - pr_alert("THERMAL ALERT: unknown thermal alarm received\n"); + pr_warn("unknown possible thermal alarm or keyboard event received\n"); known = false; } @@ -3652,15 +3701,9 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event) } break; case 4: - /* 0x4000-0x4FFF: dock-related wakeups */ - if (hkey == TP_HKEY_EV_UNDOCK_ACK) { - hotkey_autosleep_ack = 1; - pr_info("undocked\n"); - hotkey_wakeup_hotunplug_complete_notify_change(); - known_ev = true; - } else { - known_ev = false; - } + /* 0x4000-0x4FFF: dock-related events */ + known_ev = hotkey_notify_dockevent(hkey, &send_acpi_ev, + &ignore_acpi_ev); break; case 5: /* 0x5000-0x5FFF: human interface helpers */ @@ -3668,8 +3711,9 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event) &ignore_acpi_ev); break; case 6: - /* 0x6000-0x6FFF: thermal alarms */ - known_ev = hotkey_notify_thermal(hkey, &send_acpi_ev, + /* 0x6000-0x6FFF: thermal alarms/notices and + * keyboard events */ + known_ev = hotkey_notify_6xxx(hkey, &send_acpi_ev, &ignore_acpi_ev); break; case 7: diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c index e5f7b8f..2bb8f45 100644 --- a/drivers/regulator/db8500-prcmu.c +++ b/drivers/regulator/db8500-prcmu.c @@ -266,7 +266,7 @@ static struct regulator_ops db8500_regulator_switch_ops = { * Regulator information */ static struct db8500_regulator_info - db8500_regulator_info[DB8500_NUM_REGULATORS] = { +db8500_regulator_info[DB8500_NUM_REGULATORS] = { [DB8500_REGULATOR_VAPE] = { .desc = { .name = "db8500-vape", @@ -492,11 +492,9 @@ static int __devinit db8500_regulator_probe(struct platform_device *pdev) info->desc.name, err); /* if failing, unregister all earlier regulators */ - i--; - while (i >= 0) { + while (--i >= 0) { info = &db8500_regulator_info[i]; regulator_unregister(info->rdev); - i--; } return err; } @@ -536,13 +534,7 @@ static struct platform_driver db8500_regulator_driver = { static int __init db8500_regulator_init(void) { - int ret; - - ret = platform_driver_register(&db8500_regulator_driver); - if (ret < 0) - return -ENODEV; - - return 0; + return platform_driver_register(&db8500_regulator_driver); } static void __exit db8500_regulator_exit(void) diff --git a/drivers/regulator/max8952.c b/drivers/regulator/max8952.c index daff7fd..486ed81 100644 --- a/drivers/regulator/max8952.c +++ b/drivers/regulator/max8952.c @@ -139,7 +139,7 @@ static int max8952_set_voltage(struct regulator_dev *rdev, s8 vid = -1, i; if (!gpio_is_valid(max8952->pdata->gpio_vid0) || - !gpio_is_valid(max8952->pdata->gpio_vid0)) { + !gpio_is_valid(max8952->pdata->gpio_vid1)) { /* DVS not supported */ return -EPERM; } diff --git a/drivers/regulator/max8997.c b/drivers/regulator/max8997.c index 10d5a1d..ad6628c 100644 --- a/drivers/regulator/max8997.c +++ b/drivers/regulator/max8997.c @@ -39,25 +39,28 @@ struct max8997_data { struct regulator_dev **rdev; int ramp_delay; /* in mV/us */ + bool buck1_gpiodvs; + bool buck2_gpiodvs; + bool buck5_gpiodvs; u8 buck1_vol[8]; u8 buck2_vol[8]; u8 buck5_vol[8]; + int buck125_gpios[3]; int buck125_gpioindex; + bool ignore_gpiodvs_side_effect; u8 saved_states[MAX8997_REG_MAX]; }; static inline void max8997_set_gpio(struct max8997_data *max8997) { - struct max8997_platform_data *pdata = - dev_get_platdata(max8997->iodev->dev); int set3 = (max8997->buck125_gpioindex) & 0x1; int set2 = ((max8997->buck125_gpioindex) >> 1) & 0x1; int set1 = ((max8997->buck125_gpioindex) >> 2) & 0x1; - gpio_set_value(pdata->buck125_gpios[0], set1); - gpio_set_value(pdata->buck125_gpios[1], set2); - gpio_set_value(pdata->buck125_gpios[2], set3); + gpio_set_value(max8997->buck125_gpios[0], set1); + gpio_set_value(max8997->buck125_gpios[1], set2); + gpio_set_value(max8997->buck125_gpios[2], set3); } struct voltage_map_desc { @@ -380,8 +383,6 @@ static int max8997_get_voltage_register(struct regulator_dev *rdev, static int max8997_get_voltage(struct regulator_dev *rdev) { struct max8997_data *max8997 = rdev_get_drvdata(rdev); - struct max8997_platform_data *pdata = - dev_get_platdata(max8997->iodev->dev); struct i2c_client *i2c = max8997->iodev->i2c; int reg, shift, mask, ret; int rid = max8997_get_rid(rdev); @@ -391,9 +392,9 @@ static int max8997_get_voltage(struct regulator_dev *rdev) if (ret) return ret; - if ((rid == MAX8997_BUCK1 && pdata->buck1_gpiodvs) || - (rid == MAX8997_BUCK2 && pdata->buck2_gpiodvs) || - (rid == MAX8997_BUCK5 && pdata->buck5_gpiodvs)) + if ((rid == MAX8997_BUCK1 && max8997->buck1_gpiodvs) || + (rid == MAX8997_BUCK2 && max8997->buck2_gpiodvs) || + (rid == MAX8997_BUCK5 && max8997->buck5_gpiodvs)) reg += max8997->buck125_gpioindex; ret = max8997_read_reg(i2c, reg, &val); @@ -543,7 +544,8 @@ static int max8997_set_voltage_ldobuck(struct regulator_dev *rdev, rid == MAX8997_BUCK4 || rid == MAX8997_BUCK5) { /* If the voltage is increasing */ if (org < i) - udelay(desc->step * (i - org) / max8997->ramp_delay); + udelay(DIV_ROUND_UP(desc->step * (i - org), + max8997->ramp_delay)); } return ret; @@ -561,8 +563,6 @@ static int max8997_assess_side_effect(struct regulator_dev *rdev, u8 new_val, int *best) { struct max8997_data *max8997 = rdev_get_drvdata(rdev); - struct max8997_platform_data *pdata = - dev_get_platdata(max8997->iodev->dev); int rid = max8997_get_rid(rdev); u8 *buckx_val[3]; bool buckx_gpiodvs[3]; @@ -589,9 +589,9 @@ static int max8997_assess_side_effect(struct regulator_dev *rdev, buckx_val[0] = max8997->buck1_vol; buckx_val[1] = max8997->buck2_vol; buckx_val[2] = max8997->buck5_vol; - buckx_gpiodvs[0] = pdata->buck1_gpiodvs; - buckx_gpiodvs[1] = pdata->buck2_gpiodvs; - buckx_gpiodvs[2] = pdata->buck5_gpiodvs; + buckx_gpiodvs[0] = max8997->buck1_gpiodvs; + buckx_gpiodvs[1] = max8997->buck2_gpiodvs; + buckx_gpiodvs[2] = max8997->buck5_gpiodvs; for (i = 0; i < 8; i++) { int others; @@ -640,8 +640,6 @@ static int max8997_set_voltage_buck(struct regulator_dev *rdev, int min_uV, int max_uV, unsigned *selector) { struct max8997_data *max8997 = rdev_get_drvdata(rdev); - struct max8997_platform_data *pdata = - dev_get_platdata(max8997->iodev->dev); int rid = max8997_get_rid(rdev); const struct voltage_map_desc *desc; int new_val, new_idx, damage, tmp_val, tmp_idx, tmp_dmg; @@ -653,15 +651,15 @@ static int max8997_set_voltage_buck(struct regulator_dev *rdev, switch (rid) { case MAX8997_BUCK1: - if (pdata->buck1_gpiodvs) + if (max8997->buck1_gpiodvs) gpio_dvs_mode = true; break; case MAX8997_BUCK2: - if (pdata->buck2_gpiodvs) + if (max8997->buck2_gpiodvs) gpio_dvs_mode = true; break; case MAX8997_BUCK5: - if (pdata->buck5_gpiodvs) + if (max8997->buck5_gpiodvs) gpio_dvs_mode = true; break; } @@ -695,7 +693,7 @@ static int max8997_set_voltage_buck(struct regulator_dev *rdev, new_idx = tmp_idx; new_val = tmp_val; - if (pdata->ignore_gpiodvs_side_effect == false) + if (max8997->ignore_gpiodvs_side_effect == false) return -EINVAL; dev_warn(&rdev->dev, "MAX8997 GPIO-DVS Side Effect Warning: GPIO SET:" @@ -993,6 +991,11 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev) i2c = max8997->iodev->i2c; max8997->buck125_gpioindex = pdata->buck125_default_idx; + max8997->buck1_gpiodvs = pdata->buck1_gpiodvs; + max8997->buck2_gpiodvs = pdata->buck2_gpiodvs; + max8997->buck5_gpiodvs = pdata->buck5_gpiodvs; + memcpy(max8997->buck125_gpios, pdata->buck125_gpios, sizeof(int) * 3); + max8997->ignore_gpiodvs_side_effect = pdata->ignore_gpiodvs_side_effect; for (i = 0; i < 8; i++) { max8997->buck1_vol[i] = ret = @@ -1124,6 +1127,10 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev) 0x3f); } + /* Misc Settings */ + max8997->ramp_delay = 10; /* set 10mV/us, which is the default */ + max8997_write_reg(i2c, MAX8997_REG_BUCKRAMP, (0xf << 4) | 0x9); + for (i = 0; i < pdata->num_regulators; i++) { const struct voltage_map_desc *desc; int id = pdata->regulators[i].id; @@ -1148,10 +1155,6 @@ static __devinit int max8997_pmic_probe(struct platform_device *pdev) } } - /* Misc Settings */ - max8997->ramp_delay = 10; /* set 10mV/us, which is the default */ - max8997_write_reg(i2c, MAX8997_REG_BUCKRAMP, (0xf << 4) | 0x9); - return 0; err: for (i = 0; i < max8997->num_regulators; i++) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 4724ba3..b2005b4 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -149,6 +149,7 @@ static const struct i2c_device_id ds1307_id[] = { { "ds1340", ds_1340 }, { "ds3231", ds_3231 }, { "m41t00", m41t00 }, + { "pt7c4338", ds_1307 }, { "rx8025", rx_8025 }, { } }; diff --git a/drivers/rtc/rtc-vt8500.c b/drivers/rtc/rtc-vt8500.c index b8bc862..efd6066 100644 --- a/drivers/rtc/rtc-vt8500.c +++ b/drivers/rtc/rtc-vt8500.c @@ -78,7 +78,6 @@ struct vt8500_rtc { void __iomem *regbase; struct resource *res; int irq_alarm; - int irq_hz; struct rtc_device *rtc; spinlock_t lock; /* Protects this structure */ }; @@ -100,10 +99,6 @@ static irqreturn_t vt8500_rtc_irq(int irq, void *dev_id) if (isr & 1) events |= RTC_AF | RTC_IRQF; - /* Only second/minute interrupts are supported */ - if (isr & 2) - events |= RTC_UF | RTC_IRQF; - rtc_update_irq(vt8500_rtc->rtc, 1, events); return IRQ_HANDLED; @@ -199,27 +194,12 @@ static int vt8500_alarm_irq_enable(struct device *dev, unsigned int enabled) return 0; } -static int vt8500_update_irq_enable(struct device *dev, unsigned int enabled) -{ - struct vt8500_rtc *vt8500_rtc = dev_get_drvdata(dev); - unsigned long tmp = readl(vt8500_rtc->regbase + VT8500_RTC_CR); - - if (enabled) - tmp |= VT8500_RTC_CR_SM_SEC | VT8500_RTC_CR_SM_ENABLE; - else - tmp &= ~VT8500_RTC_CR_SM_ENABLE; - - writel(tmp, vt8500_rtc->regbase + VT8500_RTC_CR); - return 0; -} - static const struct rtc_class_ops vt8500_rtc_ops = { .read_time = vt8500_rtc_read_time, .set_time = vt8500_rtc_set_time, .read_alarm = vt8500_rtc_read_alarm, .set_alarm = vt8500_rtc_set_alarm, .alarm_irq_enable = vt8500_alarm_irq_enable, - .update_irq_enable = vt8500_update_irq_enable, }; static int __devinit vt8500_rtc_probe(struct platform_device *pdev) @@ -248,13 +228,6 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev) goto err_free; } - vt8500_rtc->irq_hz = platform_get_irq(pdev, 1); - if (vt8500_rtc->irq_hz < 0) { - dev_err(&pdev->dev, "No 1Hz IRQ resource defined\n"); - ret = -ENXIO; - goto err_free; - } - vt8500_rtc->res = request_mem_region(vt8500_rtc->res->start, resource_size(vt8500_rtc->res), "vt8500-rtc"); @@ -272,9 +245,8 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev) goto err_release; } - /* Enable the second/minute interrupt generation and enable RTC */ - writel(VT8500_RTC_CR_ENABLE | VT8500_RTC_CR_24H - | VT8500_RTC_CR_SM_ENABLE | VT8500_RTC_CR_SM_SEC, + /* Enable RTC and set it to 24-hour mode */ + writel(VT8500_RTC_CR_ENABLE | VT8500_RTC_CR_24H, vt8500_rtc->regbase + VT8500_RTC_CR); vt8500_rtc->rtc = rtc_device_register("vt8500-rtc", &pdev->dev, @@ -286,26 +258,16 @@ static int __devinit vt8500_rtc_probe(struct platform_device *pdev) goto err_unmap; } - ret = request_irq(vt8500_rtc->irq_hz, vt8500_rtc_irq, 0, - "rtc 1Hz", vt8500_rtc); - if (ret < 0) { - dev_err(&pdev->dev, "can't get irq %i, err %d\n", - vt8500_rtc->irq_hz, ret); - goto err_unreg; - } - ret = request_irq(vt8500_rtc->irq_alarm, vt8500_rtc_irq, 0, "rtc alarm", vt8500_rtc); if (ret < 0) { dev_err(&pdev->dev, "can't get irq %i, err %d\n", vt8500_rtc->irq_alarm, ret); - goto err_free_hz; + goto err_unreg; } return 0; -err_free_hz: - free_irq(vt8500_rtc->irq_hz, vt8500_rtc); err_unreg: rtc_device_unregister(vt8500_rtc->rtc); err_unmap: @@ -323,7 +285,6 @@ static int __devexit vt8500_rtc_remove(struct platform_device *pdev) struct vt8500_rtc *vt8500_rtc = platform_get_drvdata(pdev); free_irq(vt8500_rtc->irq_alarm, vt8500_rtc); - free_irq(vt8500_rtc->irq_hz, vt8500_rtc); rtc_device_unregister(vt8500_rtc->rtc); diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 4a1f029..8d9dae8 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -830,6 +830,19 @@ config SCSI_GDTH To compile this driver as a module, choose M here: the module will be called gdth. +config SCSI_ISCI + tristate "Intel(R) C600 Series Chipset SAS Controller" + depends on PCI && SCSI + depends on X86 + # (temporary): known alpha quality driver + depends on EXPERIMENTAL + select SCSI_SAS_LIBSAS + ---help--- + This driver supports the 6Gb/s SAS capabilities of the storage + control unit found in the Intel(R) C600 series chipset. + + The experimental tag will be removed after the driver exits alpha + config SCSI_GENERIC_NCR5380 tristate "Generic NCR5380/53c400 SCSI PIO support" depends on ISA && SCSI diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 7ad0b8a..3c08f53 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -73,6 +73,7 @@ obj-$(CONFIG_SCSI_AACRAID) += aacraid/ obj-$(CONFIG_SCSI_AIC7XXX_OLD) += aic7xxx_old.o obj-$(CONFIG_SCSI_AIC94XX) += aic94xx/ obj-$(CONFIG_SCSI_PM8001) += pm8001/ +obj-$(CONFIG_SCSI_ISCI) += isci/ obj-$(CONFIG_SCSI_IPS) += ips.o obj-$(CONFIG_SCSI_FD_MCS) += fd_mcs.o obj-$(CONFIG_SCSI_FUTURE_DOMAIN)+= fdomain.o diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index c6c0434..6bba23a 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -1037,6 +1037,7 @@ static void complete_scsi_command(struct CommandList *cp) unsigned char sense_key; unsigned char asc; /* additional sense code */ unsigned char ascq; /* additional sense code qualifier */ + unsigned long sense_data_size; ei = cp->err_info; cmd = (struct scsi_cmnd *) cp->scsi_cmd; @@ -1051,10 +1052,14 @@ static void complete_scsi_command(struct CommandList *cp) cmd->result |= ei->ScsiStatus; /* copy the sense data whether we need to or not. */ - memcpy(cmd->sense_buffer, ei->SenseInfo, - ei->SenseLen > SCSI_SENSE_BUFFERSIZE ? - SCSI_SENSE_BUFFERSIZE : - ei->SenseLen); + if (SCSI_SENSE_BUFFERSIZE < sizeof(ei->SenseInfo)) + sense_data_size = SCSI_SENSE_BUFFERSIZE; + else + sense_data_size = sizeof(ei->SenseInfo); + if (ei->SenseLen < sense_data_size) + sense_data_size = ei->SenseLen; + + memcpy(cmd->sense_buffer, ei->SenseInfo, sense_data_size); scsi_set_resid(cmd, ei->ResidualCnt); if (ei->CommandStatus == 0) { @@ -2580,7 +2585,8 @@ static int hpsa_passthru_ioctl(struct ctlr_info *h, void __user *argp) c->SG[0].Ext = 0; /* we are not chaining*/ } hpsa_scsi_do_simple_cmd_core(h, c); - hpsa_pci_unmap(h->pdev, c, 1, PCI_DMA_BIDIRECTIONAL); + if (iocommand.buf_size > 0) + hpsa_pci_unmap(h->pdev, c, 1, PCI_DMA_BIDIRECTIONAL); check_ioctl_unit_attention(h, c); /* Copy the error information out */ diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index b765061..bdfa223 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -4306,8 +4306,8 @@ static void ibmvfc_do_work(struct ibmvfc_host *vhost) spin_lock_irqsave(vhost->host->host_lock, flags); if (rc == H_CLOSED) vio_enable_interrupts(to_vio_dev(vhost->dev)); - else if (rc || (rc = ibmvfc_send_crq_init(vhost)) || - (rc = vio_enable_interrupts(to_vio_dev(vhost->dev)))) { + if (rc || (rc = ibmvfc_send_crq_init(vhost)) || + (rc = vio_enable_interrupts(to_vio_dev(vhost->dev)))) { ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD); dev_err(vhost->dev, "Error after reset (rc=%d)\n", rc); } diff --git a/drivers/scsi/isci/Makefile b/drivers/scsi/isci/Makefile new file mode 100644 index 0000000..3359e10 --- /dev/null +++ b/drivers/scsi/isci/Makefile @@ -0,0 +1,8 @@ +obj-$(CONFIG_SCSI_ISCI) += isci.o +isci-objs := init.o phy.o request.o \ + remote_device.o port.o \ + host.o task.o probe_roms.o \ + remote_node_context.o \ + remote_node_table.o \ + unsolicited_frame_control.o \ + port_config.o \ diff --git a/drivers/scsi/isci/firmware/Makefile b/drivers/scsi/isci/firmware/Makefile new file mode 100644 index 0000000..5f54461 --- /dev/null +++ b/drivers/scsi/isci/firmware/Makefile @@ -0,0 +1,19 @@ +# Makefile for create_fw +# +CC=gcc +CFLAGS=-c -Wall -O2 -g +LDFLAGS= +SOURCES=create_fw.c +OBJECTS=$(SOURCES:.cpp=.o) +EXECUTABLE=create_fw + +all: $(SOURCES) $(EXECUTABLE) + +$(EXECUTABLE): $(OBJECTS) + $(CC) $(LDFLAGS) $(OBJECTS) -o $@ + +.c.o: + $(CC) $(CFLAGS) $< -O $@ + +clean: + rm -f *.o $(EXECUTABLE) diff --git a/drivers/scsi/isci/firmware/README b/drivers/scsi/isci/firmware/README new file mode 100644 index 0000000..8056d2b --- /dev/null +++ b/drivers/scsi/isci/firmware/README @@ -0,0 +1,36 @@ +This defines the temporary binary blow we are to pass to the SCU +driver to emulate the binary firmware that we will eventually be +able to access via NVRAM on the SCU controller. + +The current size of the binary blob is expected to be 149 bytes or larger + +Header Types: +0x1: Phy Masks +0x2: Phy Gens +0x3: SAS Addrs +0xff: End of Data + +ID string - u8[12]: "#SCU MAGIC#\0" +Version - u8: 1 +SubVersion - u8: 0 + +Header Type - u8: 0x1 +Size - u8: 8 +Phy Mask - u32[8] + +Header Type - u8: 0x2 +Size - u8: 8 +Phy Gen - u32[8] + +Header Type - u8: 0x3 +Size - u8: 8 +Sas Addr - u64[8] + +Header Type - u8: 0xf + + +============================================================================== + +Place isci_firmware.bin in /lib/firmware +Be sure to recreate the initramfs image to include the firmware. + diff --git a/drivers/scsi/isci/firmware/create_fw.c b/drivers/scsi/isci/firmware/create_fw.c new file mode 100644 index 0000000..c7a2887 --- /dev/null +++ b/drivers/scsi/isci/firmware/create_fw.c @@ -0,0 +1,99 @@ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <string.h> +#include <errno.h> +#include <asm/types.h> +#include <strings.h> +#include <stdint.h> + +#include "create_fw.h" +#include "../probe_roms.h" + +int write_blob(struct isci_orom *isci_orom) +{ + FILE *fd; + int err; + size_t count; + + fd = fopen(blob_name, "w+"); + if (!fd) { + perror("Open file for write failed"); + fclose(fd); + return -EIO; + } + + count = fwrite(isci_orom, sizeof(struct isci_orom), 1, fd); + if (count != 1) { + perror("Write data failed"); + fclose(fd); + return -EIO; + } + + fclose(fd); + + return 0; +} + +void set_binary_values(struct isci_orom *isci_orom) +{ + int ctrl_idx, phy_idx, port_idx; + + /* setting OROM signature */ + strncpy(isci_orom->hdr.signature, sig, strlen(sig)); + isci_orom->hdr.version = version; + isci_orom->hdr.total_block_length = sizeof(struct isci_orom); + isci_orom->hdr.hdr_length = sizeof(struct sci_bios_oem_param_block_hdr); + isci_orom->hdr.num_elements = num_elements; + + for (ctrl_idx = 0; ctrl_idx < 2; ctrl_idx++) { + isci_orom->ctrl[ctrl_idx].controller.mode_type = mode_type; + isci_orom->ctrl[ctrl_idx].controller.max_concurrent_dev_spin_up = + max_num_concurrent_dev_spin_up; + isci_orom->ctrl[ctrl_idx].controller.do_enable_ssc = + enable_ssc; + + for (port_idx = 0; port_idx < 4; port_idx++) + isci_orom->ctrl[ctrl_idx].ports[port_idx].phy_mask = + phy_mask[ctrl_idx][port_idx]; + + for (phy_idx = 0; phy_idx < 4; phy_idx++) { + isci_orom->ctrl[ctrl_idx].phys[phy_idx].sas_address.high = + (__u32)(sas_addr[ctrl_idx][phy_idx] >> 32); + isci_orom->ctrl[ctrl_idx].phys[phy_idx].sas_address.low = + (__u32)(sas_addr[ctrl_idx][phy_idx]); + + isci_orom->ctrl[ctrl_idx].phys[phy_idx].afe_tx_amp_control0 = + afe_tx_amp_control0; + isci_orom->ctrl[ctrl_idx].phys[phy_idx].afe_tx_amp_control1 = + afe_tx_amp_control1; + isci_orom->ctrl[ctrl_idx].phys[phy_idx].afe_tx_amp_control2 = + afe_tx_amp_control2; + isci_orom->ctrl[ctrl_idx].phys[phy_idx].afe_tx_amp_control3 = + afe_tx_amp_control3; + } + } +} + +int main(void) +{ + int err; + struct isci_orom *isci_orom; + + isci_orom = malloc(sizeof(struct isci_orom)); + memset(isci_orom, 0, sizeof(struct isci_orom)); + + set_binary_values(isci_orom); + + err = write_blob(isci_orom); + if (err < 0) { + free(isci_orom); + return err; + } + + free(isci_orom); + return 0; +} diff --git a/drivers/scsi/isci/firmware/create_fw.h b/drivers/scsi/isci/firmware/create_fw.h new file mode 100644 index 0000000..5f29882 --- /dev/null +++ b/drivers/scsi/isci/firmware/create_fw.h @@ -0,0 +1,77 @@ +#ifndef _CREATE_FW_H_ +#define _CREATE_FW_H_ +#include "../probe_roms.h" + + +/* we are configuring for 2 SCUs */ +static const int num_elements = 2; + +/* + * For all defined arrays: + * elements 0-3 are for SCU0, ports 0-3 + * elements 4-7 are for SCU1, ports 0-3 + * + * valid configurations for one SCU are: + * P0 P1 P2 P3 + * ---------------- + * 0xF,0x0,0x0,0x0 # 1 x4 port + * 0x3,0x0,0x4,0x8 # Phys 0 and 1 are a x2 port, phy 2 and phy 3 are each x1 + * # ports + * 0x1,0x2,0xC,0x0 # Phys 0 and 1 are each x1 ports, phy 2 and phy 3 are a x2 + * # port + * 0x3,0x0,0xC,0x0 # Phys 0 and 1 are a x2 port, phy 2 and phy 3 are a x2 port + * 0x1,0x2,0x4,0x8 # Each phy is a x1 port (this is the default configuration) + * + * if there is a port/phy on which you do not wish to override the default + * values, use the value assigned to UNINIT_PARAM (255). + */ + +/* discovery mode type (port auto config mode by default ) */ + +/* + * if there is a port/phy on which you do not wish to override the default + * values, use the value "0000000000000000". SAS address of zero's is + * considered invalid and will not be used. + */ +#ifdef MPC +static const int mode_type = SCIC_PORT_MANUAL_CONFIGURATION_MODE; +static const __u8 phy_mask[2][4] = { {1, 2, 4, 8}, + {1, 2, 4, 8} }; +static const unsigned long long sas_addr[2][4] = { { 0x5FCFFFFFF0000001ULL, + 0x5FCFFFFFF0000002ULL, + 0x5FCFFFFFF0000003ULL, + 0x5FCFFFFFF0000004ULL }, + { 0x5FCFFFFFF0000005ULL, + 0x5FCFFFFFF0000006ULL, + 0x5FCFFFFFF0000007ULL, + 0x5FCFFFFFF0000008ULL } }; +#else /* APC (default) */ +static const int mode_type = SCIC_PORT_AUTOMATIC_CONFIGURATION_MODE; +static const __u8 phy_mask[2][4]; +static const unsigned long long sas_addr[2][4] = { { 0x5FCFFFFF00000001ULL, + 0x5FCFFFFF00000001ULL, + 0x5FCFFFFF00000001ULL, + 0x5FCFFFFF00000001ULL }, + { 0x5FCFFFFF00000002ULL, + 0x5FCFFFFF00000002ULL, + 0x5FCFFFFF00000002ULL, + 0x5FCFFFFF00000002ULL } }; +#endif + +/* Maximum number of concurrent device spin up */ +static const int max_num_concurrent_dev_spin_up = 1; + +/* enable of ssc operation */ +static const int enable_ssc; + +/* AFE_TX_AMP_CONTROL */ +static const unsigned int afe_tx_amp_control0 = 0x000bdd08; +static const unsigned int afe_tx_amp_control1 = 0x000ffc00; +static const unsigned int afe_tx_amp_control2 = 0x000b7c09; +static const unsigned int afe_tx_amp_control3 = 0x000afc6e; + +static const char blob_name[] = "isci_firmware.bin"; +static const char sig[] = "ISCUOEMB"; +static const unsigned char version = 0x10; + +#endif diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c new file mode 100644 index 0000000..26072f1 --- /dev/null +++ b/drivers/scsi/isci/host.c @@ -0,0 +1,2751 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#include <linux/circ_buf.h> +#include <linux/device.h> +#include <scsi/sas.h> +#include "host.h" +#include "isci.h" +#include "port.h" +#include "host.h" +#include "probe_roms.h" +#include "remote_device.h" +#include "request.h" +#include "scu_completion_codes.h" +#include "scu_event_codes.h" +#include "registers.h" +#include "scu_remote_node_context.h" +#include "scu_task_context.h" + +#define SCU_CONTEXT_RAM_INIT_STALL_TIME 200 + +#define smu_max_ports(dcc_value) \ + (\ + (((dcc_value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_SHIFT) + 1 \ + ) + +#define smu_max_task_contexts(dcc_value) \ + (\ + (((dcc_value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_TC_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_TC_SHIFT) + 1 \ + ) + +#define smu_max_rncs(dcc_value) \ + (\ + (((dcc_value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_RNC_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_RNC_SHIFT) + 1 \ + ) + +#define SCIC_SDS_CONTROLLER_PHY_START_TIMEOUT 100 + +/** + * + * + * The number of milliseconds to wait while a given phy is consuming power + * before allowing another set of phys to consume power. Ultimately, this will + * be specified by OEM parameter. + */ +#define SCIC_SDS_CONTROLLER_POWER_CONTROL_INTERVAL 500 + +/** + * NORMALIZE_PUT_POINTER() - + * + * This macro will normalize the completion queue put pointer so its value can + * be used as an array inde + */ +#define NORMALIZE_PUT_POINTER(x) \ + ((x) & SMU_COMPLETION_QUEUE_PUT_POINTER_MASK) + + +/** + * NORMALIZE_EVENT_POINTER() - + * + * This macro will normalize the completion queue event entry so its value can + * be used as an index. + */ +#define NORMALIZE_EVENT_POINTER(x) \ + (\ + ((x) & SMU_COMPLETION_QUEUE_GET_EVENT_POINTER_MASK) \ + >> SMU_COMPLETION_QUEUE_GET_EVENT_POINTER_SHIFT \ + ) + +/** + * NORMALIZE_GET_POINTER() - + * + * This macro will normalize the completion queue get pointer so its value can + * be used as an index into an array + */ +#define NORMALIZE_GET_POINTER(x) \ + ((x) & SMU_COMPLETION_QUEUE_GET_POINTER_MASK) + +/** + * NORMALIZE_GET_POINTER_CYCLE_BIT() - + * + * This macro will normalize the completion queue cycle pointer so it matches + * the completion queue cycle bit + */ +#define NORMALIZE_GET_POINTER_CYCLE_BIT(x) \ + ((SMU_CQGR_CYCLE_BIT & (x)) << (31 - SMU_COMPLETION_QUEUE_GET_CYCLE_BIT_SHIFT)) + +/** + * COMPLETION_QUEUE_CYCLE_BIT() - + * + * This macro will return the cycle bit of the completion queue entry + */ +#define COMPLETION_QUEUE_CYCLE_BIT(x) ((x) & 0x80000000) + +/* Init the state machine and call the state entry function (if any) */ +void sci_init_sm(struct sci_base_state_machine *sm, + const struct sci_base_state *state_table, u32 initial_state) +{ + sci_state_transition_t handler; + + sm->initial_state_id = initial_state; + sm->previous_state_id = initial_state; + sm->current_state_id = initial_state; + sm->state_table = state_table; + + handler = sm->state_table[initial_state].enter_state; + if (handler) + handler(sm); +} + +/* Call the state exit fn, update the current state, call the state entry fn */ +void sci_change_state(struct sci_base_state_machine *sm, u32 next_state) +{ + sci_state_transition_t handler; + + handler = sm->state_table[sm->current_state_id].exit_state; + if (handler) + handler(sm); + + sm->previous_state_id = sm->current_state_id; + sm->current_state_id = next_state; + + handler = sm->state_table[sm->current_state_id].enter_state; + if (handler) + handler(sm); +} + +static bool sci_controller_completion_queue_has_entries(struct isci_host *ihost) +{ + u32 get_value = ihost->completion_queue_get; + u32 get_index = get_value & SMU_COMPLETION_QUEUE_GET_POINTER_MASK; + + if (NORMALIZE_GET_POINTER_CYCLE_BIT(get_value) == + COMPLETION_QUEUE_CYCLE_BIT(ihost->completion_queue[get_index])) + return true; + + return false; +} + +static bool sci_controller_isr(struct isci_host *ihost) +{ + if (sci_controller_completion_queue_has_entries(ihost)) { + return true; + } else { + /* + * we have a spurious interrupt it could be that we have already + * emptied the completion queue from a previous interrupt */ + writel(SMU_ISR_COMPLETION, &ihost->smu_registers->interrupt_status); + + /* + * There is a race in the hardware that could cause us not to be notified + * of an interrupt completion if we do not take this step. We will mask + * then unmask the interrupts so if there is another interrupt pending + * the clearing of the interrupt source we get the next interrupt message. */ + writel(0xFF000000, &ihost->smu_registers->interrupt_mask); + writel(0, &ihost->smu_registers->interrupt_mask); + } + + return false; +} + +irqreturn_t isci_msix_isr(int vec, void *data) +{ + struct isci_host *ihost = data; + + if (sci_controller_isr(ihost)) + tasklet_schedule(&ihost->completion_tasklet); + + return IRQ_HANDLED; +} + +static bool sci_controller_error_isr(struct isci_host *ihost) +{ + u32 interrupt_status; + + interrupt_status = + readl(&ihost->smu_registers->interrupt_status); + interrupt_status &= (SMU_ISR_QUEUE_ERROR | SMU_ISR_QUEUE_SUSPEND); + + if (interrupt_status != 0) { + /* + * There is an error interrupt pending so let it through and handle + * in the callback */ + return true; + } + + /* + * There is a race in the hardware that could cause us not to be notified + * of an interrupt completion if we do not take this step. We will mask + * then unmask the error interrupts so if there was another interrupt + * pending we will be notified. + * Could we write the value of (SMU_ISR_QUEUE_ERROR | SMU_ISR_QUEUE_SUSPEND)? */ + writel(0xff, &ihost->smu_registers->interrupt_mask); + writel(0, &ihost->smu_registers->interrupt_mask); + + return false; +} + +static void sci_controller_task_completion(struct isci_host *ihost, u32 ent) +{ + u32 index = SCU_GET_COMPLETION_INDEX(ent); + struct isci_request *ireq = ihost->reqs[index]; + + /* Make sure that we really want to process this IO request */ + if (test_bit(IREQ_ACTIVE, &ireq->flags) && + ireq->io_tag != SCI_CONTROLLER_INVALID_IO_TAG && + ISCI_TAG_SEQ(ireq->io_tag) == ihost->io_request_sequence[index]) + /* Yep this is a valid io request pass it along to the + * io request handler + */ + sci_io_request_tc_completion(ireq, ent); +} + +static void sci_controller_sdma_completion(struct isci_host *ihost, u32 ent) +{ + u32 index; + struct isci_request *ireq; + struct isci_remote_device *idev; + + index = SCU_GET_COMPLETION_INDEX(ent); + + switch (scu_get_command_request_type(ent)) { + case SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC: + case SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_TC: + ireq = ihost->reqs[index]; + dev_warn(&ihost->pdev->dev, "%s: %x for io request %p\n", + __func__, ent, ireq); + /* @todo For a post TC operation we need to fail the IO + * request + */ + break; + case SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_RNC: + case SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC: + case SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_RNC: + idev = ihost->device_table[index]; + dev_warn(&ihost->pdev->dev, "%s: %x for device %p\n", + __func__, ent, idev); + /* @todo For a port RNC operation we need to fail the + * device + */ + break; + default: + dev_warn(&ihost->pdev->dev, "%s: unknown completion type %x\n", + __func__, ent); + break; + } +} + +static void sci_controller_unsolicited_frame(struct isci_host *ihost, u32 ent) +{ + u32 index; + u32 frame_index; + + struct scu_unsolicited_frame_header *frame_header; + struct isci_phy *iphy; + struct isci_remote_device *idev; + + enum sci_status result = SCI_FAILURE; + + frame_index = SCU_GET_FRAME_INDEX(ent); + + frame_header = ihost->uf_control.buffers.array[frame_index].header; + ihost->uf_control.buffers.array[frame_index].state = UNSOLICITED_FRAME_IN_USE; + + if (SCU_GET_FRAME_ERROR(ent)) { + /* + * / @todo If the IAF frame or SIGNATURE FIS frame has an error will + * / this cause a problem? We expect the phy initialization will + * / fail if there is an error in the frame. */ + sci_controller_release_frame(ihost, frame_index); + return; + } + + if (frame_header->is_address_frame) { + index = SCU_GET_PROTOCOL_ENGINE_INDEX(ent); + iphy = &ihost->phys[index]; + result = sci_phy_frame_handler(iphy, frame_index); + } else { + + index = SCU_GET_COMPLETION_INDEX(ent); + + if (index == SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX) { + /* + * This is a signature fis or a frame from a direct attached SATA + * device that has not yet been created. In either case forwared + * the frame to the PE and let it take care of the frame data. */ + index = SCU_GET_PROTOCOL_ENGINE_INDEX(ent); + iphy = &ihost->phys[index]; + result = sci_phy_frame_handler(iphy, frame_index); + } else { + if (index < ihost->remote_node_entries) + idev = ihost->device_table[index]; + else + idev = NULL; + + if (idev != NULL) + result = sci_remote_device_frame_handler(idev, frame_index); + else + sci_controller_release_frame(ihost, frame_index); + } + } + + if (result != SCI_SUCCESS) { + /* + * / @todo Is there any reason to report some additional error message + * / when we get this failure notifiction? */ + } +} + +static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) +{ + struct isci_remote_device *idev; + struct isci_request *ireq; + struct isci_phy *iphy; + u32 index; + + index = SCU_GET_COMPLETION_INDEX(ent); + + switch (scu_get_event_type(ent)) { + case SCU_EVENT_TYPE_SMU_COMMAND_ERROR: + /* / @todo The driver did something wrong and we need to fix the condtion. */ + dev_err(&ihost->pdev->dev, + "%s: SCIC Controller 0x%p received SMU command error " + "0x%x\n", + __func__, + ihost, + ent); + break; + + case SCU_EVENT_TYPE_SMU_PCQ_ERROR: + case SCU_EVENT_TYPE_SMU_ERROR: + case SCU_EVENT_TYPE_FATAL_MEMORY_ERROR: + /* + * / @todo This is a hardware failure and its likely that we want to + * / reset the controller. */ + dev_err(&ihost->pdev->dev, + "%s: SCIC Controller 0x%p received fatal controller " + "event 0x%x\n", + __func__, + ihost, + ent); + break; + + case SCU_EVENT_TYPE_TRANSPORT_ERROR: + ireq = ihost->reqs[index]; + sci_io_request_event_handler(ireq, ent); + break; + + case SCU_EVENT_TYPE_PTX_SCHEDULE_EVENT: + switch (scu_get_event_specifier(ent)) { + case SCU_EVENT_SPECIFIC_SMP_RESPONSE_NO_PE: + case SCU_EVENT_SPECIFIC_TASK_TIMEOUT: + ireq = ihost->reqs[index]; + if (ireq != NULL) + sci_io_request_event_handler(ireq, ent); + else + dev_warn(&ihost->pdev->dev, + "%s: SCIC Controller 0x%p received " + "event 0x%x for io request object " + "that doesnt exist.\n", + __func__, + ihost, + ent); + + break; + + case SCU_EVENT_SPECIFIC_IT_NEXUS_TIMEOUT: + idev = ihost->device_table[index]; + if (idev != NULL) + sci_remote_device_event_handler(idev, ent); + else + dev_warn(&ihost->pdev->dev, + "%s: SCIC Controller 0x%p received " + "event 0x%x for remote device object " + "that doesnt exist.\n", + __func__, + ihost, + ent); + + break; + } + break; + + case SCU_EVENT_TYPE_BROADCAST_CHANGE: + /* + * direct the broadcast change event to the phy first and then let + * the phy redirect the broadcast change to the port object */ + case SCU_EVENT_TYPE_ERR_CNT_EVENT: + /* + * direct error counter event to the phy object since that is where + * we get the event notification. This is a type 4 event. */ + case SCU_EVENT_TYPE_OSSP_EVENT: + index = SCU_GET_PROTOCOL_ENGINE_INDEX(ent); + iphy = &ihost->phys[index]; + sci_phy_event_handler(iphy, ent); + break; + + case SCU_EVENT_TYPE_RNC_SUSPEND_TX: + case SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX: + case SCU_EVENT_TYPE_RNC_OPS_MISC: + if (index < ihost->remote_node_entries) { + idev = ihost->device_table[index]; + + if (idev != NULL) + sci_remote_device_event_handler(idev, ent); + } else + dev_err(&ihost->pdev->dev, + "%s: SCIC Controller 0x%p received event 0x%x " + "for remote device object 0x%0x that doesnt " + "exist.\n", + __func__, + ihost, + ent, + index); + + break; + + default: + dev_warn(&ihost->pdev->dev, + "%s: SCIC Controller received unknown event code %x\n", + __func__, + ent); + break; + } +} + +static void sci_controller_process_completions(struct isci_host *ihost) +{ + u32 completion_count = 0; + u32 ent; + u32 get_index; + u32 get_cycle; + u32 event_get; + u32 event_cycle; + + dev_dbg(&ihost->pdev->dev, + "%s: completion queue begining get:0x%08x\n", + __func__, + ihost->completion_queue_get); + + /* Get the component parts of the completion queue */ + get_index = NORMALIZE_GET_POINTER(ihost->completion_queue_get); + get_cycle = SMU_CQGR_CYCLE_BIT & ihost->completion_queue_get; + + event_get = NORMALIZE_EVENT_POINTER(ihost->completion_queue_get); + event_cycle = SMU_CQGR_EVENT_CYCLE_BIT & ihost->completion_queue_get; + + while ( + NORMALIZE_GET_POINTER_CYCLE_BIT(get_cycle) + == COMPLETION_QUEUE_CYCLE_BIT(ihost->completion_queue[get_index]) + ) { + completion_count++; + + ent = ihost->completion_queue[get_index]; + + /* increment the get pointer and check for rollover to toggle the cycle bit */ + get_cycle ^= ((get_index+1) & SCU_MAX_COMPLETION_QUEUE_ENTRIES) << + (SMU_COMPLETION_QUEUE_GET_CYCLE_BIT_SHIFT - SCU_MAX_COMPLETION_QUEUE_SHIFT); + get_index = (get_index+1) & (SCU_MAX_COMPLETION_QUEUE_ENTRIES-1); + + dev_dbg(&ihost->pdev->dev, + "%s: completion queue entry:0x%08x\n", + __func__, + ent); + + switch (SCU_GET_COMPLETION_TYPE(ent)) { + case SCU_COMPLETION_TYPE_TASK: + sci_controller_task_completion(ihost, ent); + break; + + case SCU_COMPLETION_TYPE_SDMA: + sci_controller_sdma_completion(ihost, ent); + break; + + case SCU_COMPLETION_TYPE_UFI: + sci_controller_unsolicited_frame(ihost, ent); + break; + + case SCU_COMPLETION_TYPE_EVENT: + case SCU_COMPLETION_TYPE_NOTIFY: { + event_cycle ^= ((event_get+1) & SCU_MAX_EVENTS) << + (SMU_COMPLETION_QUEUE_GET_EVENT_CYCLE_BIT_SHIFT - SCU_MAX_EVENTS_SHIFT); + event_get = (event_get+1) & (SCU_MAX_EVENTS-1); + + sci_controller_event_completion(ihost, ent); + break; + } + default: + dev_warn(&ihost->pdev->dev, + "%s: SCIC Controller received unknown " + "completion type %x\n", + __func__, + ent); + break; + } + } + + /* Update the get register if we completed one or more entries */ + if (completion_count > 0) { + ihost->completion_queue_get = + SMU_CQGR_GEN_BIT(ENABLE) | + SMU_CQGR_GEN_BIT(EVENT_ENABLE) | + event_cycle | + SMU_CQGR_GEN_VAL(EVENT_POINTER, event_get) | + get_cycle | + SMU_CQGR_GEN_VAL(POINTER, get_index); + + writel(ihost->completion_queue_get, + &ihost->smu_registers->completion_queue_get); + + } + + dev_dbg(&ihost->pdev->dev, + "%s: completion queue ending get:0x%08x\n", + __func__, + ihost->completion_queue_get); + +} + +static void sci_controller_error_handler(struct isci_host *ihost) +{ + u32 interrupt_status; + + interrupt_status = + readl(&ihost->smu_registers->interrupt_status); + + if ((interrupt_status & SMU_ISR_QUEUE_SUSPEND) && + sci_controller_completion_queue_has_entries(ihost)) { + + sci_controller_process_completions(ihost); + writel(SMU_ISR_QUEUE_SUSPEND, &ihost->smu_registers->interrupt_status); + } else { + dev_err(&ihost->pdev->dev, "%s: status: %#x\n", __func__, + interrupt_status); + + sci_change_state(&ihost->sm, SCIC_FAILED); + + return; + } + + /* If we dont process any completions I am not sure that we want to do this. + * We are in the middle of a hardware fault and should probably be reset. + */ + writel(0, &ihost->smu_registers->interrupt_mask); +} + +irqreturn_t isci_intx_isr(int vec, void *data) +{ + irqreturn_t ret = IRQ_NONE; + struct isci_host *ihost = data; + + if (sci_controller_isr(ihost)) { + writel(SMU_ISR_COMPLETION, &ihost->smu_registers->interrupt_status); + tasklet_schedule(&ihost->completion_tasklet); + ret = IRQ_HANDLED; + } else if (sci_controller_error_isr(ihost)) { + spin_lock(&ihost->scic_lock); + sci_controller_error_handler(ihost); + spin_unlock(&ihost->scic_lock); + ret = IRQ_HANDLED; + } + + return ret; +} + +irqreturn_t isci_error_isr(int vec, void *data) +{ + struct isci_host *ihost = data; + + if (sci_controller_error_isr(ihost)) + sci_controller_error_handler(ihost); + + return IRQ_HANDLED; +} + +/** + * isci_host_start_complete() - This function is called by the core library, + * through the ISCI Module, to indicate controller start status. + * @isci_host: This parameter specifies the ISCI host object + * @completion_status: This parameter specifies the completion status from the + * core library. + * + */ +static void isci_host_start_complete(struct isci_host *ihost, enum sci_status completion_status) +{ + if (completion_status != SCI_SUCCESS) + dev_info(&ihost->pdev->dev, + "controller start timed out, continuing...\n"); + isci_host_change_state(ihost, isci_ready); + clear_bit(IHOST_START_PENDING, &ihost->flags); + wake_up(&ihost->eventq); +} + +int isci_host_scan_finished(struct Scsi_Host *shost, unsigned long time) +{ + struct isci_host *ihost = SHOST_TO_SAS_HA(shost)->lldd_ha; + + if (test_bit(IHOST_START_PENDING, &ihost->flags)) + return 0; + + /* todo: use sas_flush_discovery once it is upstream */ + scsi_flush_work(shost); + + scsi_flush_work(shost); + + dev_dbg(&ihost->pdev->dev, + "%s: ihost->status = %d, time = %ld\n", + __func__, isci_host_get_state(ihost), time); + + return 1; + +} + +/** + * sci_controller_get_suggested_start_timeout() - This method returns the + * suggested sci_controller_start() timeout amount. The user is free to + * use any timeout value, but this method provides the suggested minimum + * start timeout value. The returned value is based upon empirical + * information determined as a result of interoperability testing. + * @controller: the handle to the controller object for which to return the + * suggested start timeout. + * + * This method returns the number of milliseconds for the suggested start + * operation timeout. + */ +static u32 sci_controller_get_suggested_start_timeout(struct isci_host *ihost) +{ + /* Validate the user supplied parameters. */ + if (!ihost) + return 0; + + /* + * The suggested minimum timeout value for a controller start operation: + * + * Signature FIS Timeout + * + Phy Start Timeout + * + Number of Phy Spin Up Intervals + * --------------------------------- + * Number of milliseconds for the controller start operation. + * + * NOTE: The number of phy spin up intervals will be equivalent + * to the number of phys divided by the number phys allowed + * per interval - 1 (once OEM parameters are supported). + * Currently we assume only 1 phy per interval. */ + + return SCIC_SDS_SIGNATURE_FIS_TIMEOUT + + SCIC_SDS_CONTROLLER_PHY_START_TIMEOUT + + ((SCI_MAX_PHYS - 1) * SCIC_SDS_CONTROLLER_POWER_CONTROL_INTERVAL); +} + +static void sci_controller_enable_interrupts(struct isci_host *ihost) +{ + BUG_ON(ihost->smu_registers == NULL); + writel(0, &ihost->smu_registers->interrupt_mask); +} + +void sci_controller_disable_interrupts(struct isci_host *ihost) +{ + BUG_ON(ihost->smu_registers == NULL); + writel(0xffffffff, &ihost->smu_registers->interrupt_mask); +} + +static void sci_controller_enable_port_task_scheduler(struct isci_host *ihost) +{ + u32 port_task_scheduler_value; + + port_task_scheduler_value = + readl(&ihost->scu_registers->peg0.ptsg.control); + port_task_scheduler_value |= + (SCU_PTSGCR_GEN_BIT(ETM_ENABLE) | + SCU_PTSGCR_GEN_BIT(PTSG_ENABLE)); + writel(port_task_scheduler_value, + &ihost->scu_registers->peg0.ptsg.control); +} + +static void sci_controller_assign_task_entries(struct isci_host *ihost) +{ + u32 task_assignment; + + /* + * Assign all the TCs to function 0 + * TODO: Do we actually need to read this register to write it back? + */ + + task_assignment = + readl(&ihost->smu_registers->task_context_assignment[0]); + + task_assignment |= (SMU_TCA_GEN_VAL(STARTING, 0)) | + (SMU_TCA_GEN_VAL(ENDING, ihost->task_context_entries - 1)) | + (SMU_TCA_GEN_BIT(RANGE_CHECK_ENABLE)); + + writel(task_assignment, + &ihost->smu_registers->task_context_assignment[0]); + +} + +static void sci_controller_initialize_completion_queue(struct isci_host *ihost) +{ + u32 index; + u32 completion_queue_control_value; + u32 completion_queue_get_value; + u32 completion_queue_put_value; + + ihost->completion_queue_get = 0; + + completion_queue_control_value = + (SMU_CQC_QUEUE_LIMIT_SET(SCU_MAX_COMPLETION_QUEUE_ENTRIES - 1) | + SMU_CQC_EVENT_LIMIT_SET(SCU_MAX_EVENTS - 1)); + + writel(completion_queue_control_value, + &ihost->smu_registers->completion_queue_control); + + + /* Set the completion queue get pointer and enable the queue */ + completion_queue_get_value = ( + (SMU_CQGR_GEN_VAL(POINTER, 0)) + | (SMU_CQGR_GEN_VAL(EVENT_POINTER, 0)) + | (SMU_CQGR_GEN_BIT(ENABLE)) + | (SMU_CQGR_GEN_BIT(EVENT_ENABLE)) + ); + + writel(completion_queue_get_value, + &ihost->smu_registers->completion_queue_get); + + /* Set the completion queue put pointer */ + completion_queue_put_value = ( + (SMU_CQPR_GEN_VAL(POINTER, 0)) + | (SMU_CQPR_GEN_VAL(EVENT_POINTER, 0)) + ); + + writel(completion_queue_put_value, + &ihost->smu_registers->completion_queue_put); + + /* Initialize the cycle bit of the completion queue entries */ + for (index = 0; index < SCU_MAX_COMPLETION_QUEUE_ENTRIES; index++) { + /* + * If get.cycle_bit != completion_queue.cycle_bit + * its not a valid completion queue entry + * so at system start all entries are invalid */ + ihost->completion_queue[index] = 0x80000000; + } +} + +static void sci_controller_initialize_unsolicited_frame_queue(struct isci_host *ihost) +{ + u32 frame_queue_control_value; + u32 frame_queue_get_value; + u32 frame_queue_put_value; + + /* Write the queue size */ + frame_queue_control_value = + SCU_UFQC_GEN_VAL(QUEUE_SIZE, SCU_MAX_UNSOLICITED_FRAMES); + + writel(frame_queue_control_value, + &ihost->scu_registers->sdma.unsolicited_frame_queue_control); + + /* Setup the get pointer for the unsolicited frame queue */ + frame_queue_get_value = ( + SCU_UFQGP_GEN_VAL(POINTER, 0) + | SCU_UFQGP_GEN_BIT(ENABLE_BIT) + ); + + writel(frame_queue_get_value, + &ihost->scu_registers->sdma.unsolicited_frame_get_pointer); + /* Setup the put pointer for the unsolicited frame queue */ + frame_queue_put_value = SCU_UFQPP_GEN_VAL(POINTER, 0); + writel(frame_queue_put_value, + &ihost->scu_registers->sdma.unsolicited_frame_put_pointer); +} + +static void sci_controller_transition_to_ready(struct isci_host *ihost, enum sci_status status) +{ + if (ihost->sm.current_state_id == SCIC_STARTING) { + /* + * We move into the ready state, because some of the phys/ports + * may be up and operational. + */ + sci_change_state(&ihost->sm, SCIC_READY); + + isci_host_start_complete(ihost, status); + } +} + +static bool is_phy_starting(struct isci_phy *iphy) +{ + enum sci_phy_states state; + + state = iphy->sm.current_state_id; + switch (state) { + case SCI_PHY_STARTING: + case SCI_PHY_SUB_INITIAL: + case SCI_PHY_SUB_AWAIT_SAS_SPEED_EN: + case SCI_PHY_SUB_AWAIT_IAF_UF: + case SCI_PHY_SUB_AWAIT_SAS_POWER: + case SCI_PHY_SUB_AWAIT_SATA_POWER: + case SCI_PHY_SUB_AWAIT_SATA_PHY_EN: + case SCI_PHY_SUB_AWAIT_SATA_SPEED_EN: + case SCI_PHY_SUB_AWAIT_SIG_FIS_UF: + case SCI_PHY_SUB_FINAL: + return true; + default: + return false; + } +} + +/** + * sci_controller_start_next_phy - start phy + * @scic: controller + * + * If all the phys have been started, then attempt to transition the + * controller to the READY state and inform the user + * (sci_cb_controller_start_complete()). + */ +static enum sci_status sci_controller_start_next_phy(struct isci_host *ihost) +{ + struct sci_oem_params *oem = &ihost->oem_parameters; + struct isci_phy *iphy; + enum sci_status status; + + status = SCI_SUCCESS; + + if (ihost->phy_startup_timer_pending) + return status; + + if (ihost->next_phy_to_start >= SCI_MAX_PHYS) { + bool is_controller_start_complete = true; + u32 state; + u8 index; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + iphy = &ihost->phys[index]; + state = iphy->sm.current_state_id; + + if (!phy_get_non_dummy_port(iphy)) + continue; + + /* The controller start operation is complete iff: + * - all links have been given an opportunity to start + * - have no indication of a connected device + * - have an indication of a connected device and it has + * finished the link training process. + */ + if ((iphy->is_in_link_training == false && state == SCI_PHY_INITIAL) || + (iphy->is_in_link_training == false && state == SCI_PHY_STOPPED) || + (iphy->is_in_link_training == true && is_phy_starting(iphy))) { + is_controller_start_complete = false; + break; + } + } + + /* + * The controller has successfully finished the start process. + * Inform the SCI Core user and transition to the READY state. */ + if (is_controller_start_complete == true) { + sci_controller_transition_to_ready(ihost, SCI_SUCCESS); + sci_del_timer(&ihost->phy_timer); + ihost->phy_startup_timer_pending = false; + } + } else { + iphy = &ihost->phys[ihost->next_phy_to_start]; + + if (oem->controller.mode_type == SCIC_PORT_MANUAL_CONFIGURATION_MODE) { + if (phy_get_non_dummy_port(iphy) == NULL) { + ihost->next_phy_to_start++; + + /* Caution recursion ahead be forwarned + * + * The PHY was never added to a PORT in MPC mode + * so start the next phy in sequence This phy + * will never go link up and will not draw power + * the OEM parameters either configured the phy + * incorrectly for the PORT or it was never + * assigned to a PORT + */ + return sci_controller_start_next_phy(ihost); + } + } + + status = sci_phy_start(iphy); + + if (status == SCI_SUCCESS) { + sci_mod_timer(&ihost->phy_timer, + SCIC_SDS_CONTROLLER_PHY_START_TIMEOUT); + ihost->phy_startup_timer_pending = true; + } else { + dev_warn(&ihost->pdev->dev, + "%s: Controller stop operation failed " + "to stop phy %d because of status " + "%d.\n", + __func__, + ihost->phys[ihost->next_phy_to_start].phy_index, + status); + } + + ihost->next_phy_to_start++; + } + + return status; +} + +static void phy_startup_timeout(unsigned long data) +{ + struct sci_timer *tmr = (struct sci_timer *)data; + struct isci_host *ihost = container_of(tmr, typeof(*ihost), phy_timer); + unsigned long flags; + enum sci_status status; + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + ihost->phy_startup_timer_pending = false; + + do { + status = sci_controller_start_next_phy(ihost); + } while (status != SCI_SUCCESS); + +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +static u16 isci_tci_active(struct isci_host *ihost) +{ + return CIRC_CNT(ihost->tci_head, ihost->tci_tail, SCI_MAX_IO_REQUESTS); +} + +static enum sci_status sci_controller_start(struct isci_host *ihost, + u32 timeout) +{ + enum sci_status result; + u16 index; + + if (ihost->sm.current_state_id != SCIC_INITIALIZED) { + dev_warn(&ihost->pdev->dev, + "SCIC Controller start operation requested in " + "invalid state\n"); + return SCI_FAILURE_INVALID_STATE; + } + + /* Build the TCi free pool */ + BUILD_BUG_ON(SCI_MAX_IO_REQUESTS > 1 << sizeof(ihost->tci_pool[0]) * 8); + ihost->tci_head = 0; + ihost->tci_tail = 0; + for (index = 0; index < ihost->task_context_entries; index++) + isci_tci_free(ihost, index); + + /* Build the RNi free pool */ + sci_remote_node_table_initialize(&ihost->available_remote_nodes, + ihost->remote_node_entries); + + /* + * Before anything else lets make sure we will not be + * interrupted by the hardware. + */ + sci_controller_disable_interrupts(ihost); + + /* Enable the port task scheduler */ + sci_controller_enable_port_task_scheduler(ihost); + + /* Assign all the task entries to ihost physical function */ + sci_controller_assign_task_entries(ihost); + + /* Now initialize the completion queue */ + sci_controller_initialize_completion_queue(ihost); + + /* Initialize the unsolicited frame queue for use */ + sci_controller_initialize_unsolicited_frame_queue(ihost); + + /* Start all of the ports on this controller */ + for (index = 0; index < ihost->logical_port_entries; index++) { + struct isci_port *iport = &ihost->ports[index]; + + result = sci_port_start(iport); + if (result) + return result; + } + + sci_controller_start_next_phy(ihost); + + sci_mod_timer(&ihost->timer, timeout); + + sci_change_state(&ihost->sm, SCIC_STARTING); + + return SCI_SUCCESS; +} + +void isci_host_scan_start(struct Scsi_Host *shost) +{ + struct isci_host *ihost = SHOST_TO_SAS_HA(shost)->lldd_ha; + unsigned long tmo = sci_controller_get_suggested_start_timeout(ihost); + + set_bit(IHOST_START_PENDING, &ihost->flags); + + spin_lock_irq(&ihost->scic_lock); + sci_controller_start(ihost, tmo); + sci_controller_enable_interrupts(ihost); + spin_unlock_irq(&ihost->scic_lock); +} + +static void isci_host_stop_complete(struct isci_host *ihost, enum sci_status completion_status) +{ + isci_host_change_state(ihost, isci_stopped); + sci_controller_disable_interrupts(ihost); + clear_bit(IHOST_STOP_PENDING, &ihost->flags); + wake_up(&ihost->eventq); +} + +static void sci_controller_completion_handler(struct isci_host *ihost) +{ + /* Empty out the completion queue */ + if (sci_controller_completion_queue_has_entries(ihost)) + sci_controller_process_completions(ihost); + + /* Clear the interrupt and enable all interrupts again */ + writel(SMU_ISR_COMPLETION, &ihost->smu_registers->interrupt_status); + /* Could we write the value of SMU_ISR_COMPLETION? */ + writel(0xFF000000, &ihost->smu_registers->interrupt_mask); + writel(0, &ihost->smu_registers->interrupt_mask); +} + +/** + * isci_host_completion_routine() - This function is the delayed service + * routine that calls the sci core library's completion handler. It's + * scheduled as a tasklet from the interrupt service routine when interrupts + * in use, or set as the timeout function in polled mode. + * @data: This parameter specifies the ISCI host object + * + */ +static void isci_host_completion_routine(unsigned long data) +{ + struct isci_host *ihost = (struct isci_host *)data; + struct list_head completed_request_list; + struct list_head errored_request_list; + struct list_head *current_position; + struct list_head *next_position; + struct isci_request *request; + struct isci_request *next_request; + struct sas_task *task; + + INIT_LIST_HEAD(&completed_request_list); + INIT_LIST_HEAD(&errored_request_list); + + spin_lock_irq(&ihost->scic_lock); + + sci_controller_completion_handler(ihost); + + /* Take the lists of completed I/Os from the host. */ + + list_splice_init(&ihost->requests_to_complete, + &completed_request_list); + + /* Take the list of errored I/Os from the host. */ + list_splice_init(&ihost->requests_to_errorback, + &errored_request_list); + + spin_unlock_irq(&ihost->scic_lock); + + /* Process any completions in the lists. */ + list_for_each_safe(current_position, next_position, + &completed_request_list) { + + request = list_entry(current_position, struct isci_request, + completed_node); + task = isci_request_access_task(request); + + /* Normal notification (task_done) */ + dev_dbg(&ihost->pdev->dev, + "%s: Normal - request/task = %p/%p\n", + __func__, + request, + task); + + /* Return the task to libsas */ + if (task != NULL) { + + task->lldd_task = NULL; + if (!(task->task_state_flags & SAS_TASK_STATE_ABORTED)) { + + /* If the task is already in the abort path, + * the task_done callback cannot be called. + */ + task->task_done(task); + } + } + + spin_lock_irq(&ihost->scic_lock); + isci_free_tag(ihost, request->io_tag); + spin_unlock_irq(&ihost->scic_lock); + } + list_for_each_entry_safe(request, next_request, &errored_request_list, + completed_node) { + + task = isci_request_access_task(request); + + /* Use sas_task_abort */ + dev_warn(&ihost->pdev->dev, + "%s: Error - request/task = %p/%p\n", + __func__, + request, + task); + + if (task != NULL) { + + /* Put the task into the abort path if it's not there + * already. + */ + if (!(task->task_state_flags & SAS_TASK_STATE_ABORTED)) + sas_task_abort(task); + + } else { + /* This is a case where the request has completed with a + * status such that it needed further target servicing, + * but the sas_task reference has already been removed + * from the request. Since it was errored, it was not + * being aborted, so there is nothing to do except free + * it. + */ + + spin_lock_irq(&ihost->scic_lock); + /* Remove the request from the remote device's list + * of pending requests. + */ + list_del_init(&request->dev_node); + isci_free_tag(ihost, request->io_tag); + spin_unlock_irq(&ihost->scic_lock); + } + } + +} + +/** + * sci_controller_stop() - This method will stop an individual controller + * object.This method will invoke the associated user callback upon + * completion. The completion callback is called when the following + * conditions are met: -# the method return status is SCI_SUCCESS. -# the + * controller has been quiesced. This method will ensure that all IO + * requests are quiesced, phys are stopped, and all additional operation by + * the hardware is halted. + * @controller: the handle to the controller object to stop. + * @timeout: This parameter specifies the number of milliseconds in which the + * stop operation should complete. + * + * The controller must be in the STARTED or STOPPED state. Indicate if the + * controller stop method succeeded or failed in some way. SCI_SUCCESS if the + * stop operation successfully began. SCI_WARNING_ALREADY_IN_STATE if the + * controller is already in the STOPPED state. SCI_FAILURE_INVALID_STATE if the + * controller is not either in the STARTED or STOPPED states. + */ +static enum sci_status sci_controller_stop(struct isci_host *ihost, u32 timeout) +{ + if (ihost->sm.current_state_id != SCIC_READY) { + dev_warn(&ihost->pdev->dev, + "SCIC Controller stop operation requested in " + "invalid state\n"); + return SCI_FAILURE_INVALID_STATE; + } + + sci_mod_timer(&ihost->timer, timeout); + sci_change_state(&ihost->sm, SCIC_STOPPING); + return SCI_SUCCESS; +} + +/** + * sci_controller_reset() - This method will reset the supplied core + * controller regardless of the state of said controller. This operation is + * considered destructive. In other words, all current operations are wiped + * out. No IO completions for outstanding devices occur. Outstanding IO + * requests are not aborted or completed at the actual remote device. + * @controller: the handle to the controller object to reset. + * + * Indicate if the controller reset method succeeded or failed in some way. + * SCI_SUCCESS if the reset operation successfully started. SCI_FATAL_ERROR if + * the controller reset operation is unable to complete. + */ +static enum sci_status sci_controller_reset(struct isci_host *ihost) +{ + switch (ihost->sm.current_state_id) { + case SCIC_RESET: + case SCIC_READY: + case SCIC_STOPPED: + case SCIC_FAILED: + /* + * The reset operation is not a graceful cleanup, just + * perform the state transition. + */ + sci_change_state(&ihost->sm, SCIC_RESETTING); + return SCI_SUCCESS; + default: + dev_warn(&ihost->pdev->dev, + "SCIC Controller reset operation requested in " + "invalid state\n"); + return SCI_FAILURE_INVALID_STATE; + } +} + +void isci_host_deinit(struct isci_host *ihost) +{ + int i; + + isci_host_change_state(ihost, isci_stopping); + for (i = 0; i < SCI_MAX_PORTS; i++) { + struct isci_port *iport = &ihost->ports[i]; + struct isci_remote_device *idev, *d; + + list_for_each_entry_safe(idev, d, &iport->remote_dev_list, node) { + if (test_bit(IDEV_ALLOCATED, &idev->flags)) + isci_remote_device_stop(ihost, idev); + } + } + + set_bit(IHOST_STOP_PENDING, &ihost->flags); + + spin_lock_irq(&ihost->scic_lock); + sci_controller_stop(ihost, SCIC_CONTROLLER_STOP_TIMEOUT); + spin_unlock_irq(&ihost->scic_lock); + + wait_for_stop(ihost); + sci_controller_reset(ihost); + + /* Cancel any/all outstanding port timers */ + for (i = 0; i < ihost->logical_port_entries; i++) { + struct isci_port *iport = &ihost->ports[i]; + del_timer_sync(&iport->timer.timer); + } + + /* Cancel any/all outstanding phy timers */ + for (i = 0; i < SCI_MAX_PHYS; i++) { + struct isci_phy *iphy = &ihost->phys[i]; + del_timer_sync(&iphy->sata_timer.timer); + } + + del_timer_sync(&ihost->port_agent.timer.timer); + + del_timer_sync(&ihost->power_control.timer.timer); + + del_timer_sync(&ihost->timer.timer); + + del_timer_sync(&ihost->phy_timer.timer); +} + +static void __iomem *scu_base(struct isci_host *isci_host) +{ + struct pci_dev *pdev = isci_host->pdev; + int id = isci_host->id; + + return pcim_iomap_table(pdev)[SCI_SCU_BAR * 2] + SCI_SCU_BAR_SIZE * id; +} + +static void __iomem *smu_base(struct isci_host *isci_host) +{ + struct pci_dev *pdev = isci_host->pdev; + int id = isci_host->id; + + return pcim_iomap_table(pdev)[SCI_SMU_BAR * 2] + SCI_SMU_BAR_SIZE * id; +} + +static void isci_user_parameters_get(struct sci_user_parameters *u) +{ + int i; + + for (i = 0; i < SCI_MAX_PHYS; i++) { + struct sci_phy_user_params *u_phy = &u->phys[i]; + + u_phy->max_speed_generation = phy_gen; + + /* we are not exporting these for now */ + u_phy->align_insertion_frequency = 0x7f; + u_phy->in_connection_align_insertion_frequency = 0xff; + u_phy->notify_enable_spin_up_insertion_frequency = 0x33; + } + + u->stp_inactivity_timeout = stp_inactive_to; + u->ssp_inactivity_timeout = ssp_inactive_to; + u->stp_max_occupancy_timeout = stp_max_occ_to; + u->ssp_max_occupancy_timeout = ssp_max_occ_to; + u->no_outbound_task_timeout = no_outbound_task_to; + u->max_number_concurrent_device_spin_up = max_concurr_spinup; +} + +static void sci_controller_initial_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + sci_change_state(&ihost->sm, SCIC_RESET); +} + +static inline void sci_controller_starting_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + sci_del_timer(&ihost->timer); +} + +#define INTERRUPT_COALESCE_TIMEOUT_BASE_RANGE_LOWER_BOUND_NS 853 +#define INTERRUPT_COALESCE_TIMEOUT_BASE_RANGE_UPPER_BOUND_NS 1280 +#define INTERRUPT_COALESCE_TIMEOUT_MAX_US 2700000 +#define INTERRUPT_COALESCE_NUMBER_MAX 256 +#define INTERRUPT_COALESCE_TIMEOUT_ENCODE_MIN 7 +#define INTERRUPT_COALESCE_TIMEOUT_ENCODE_MAX 28 + +/** + * sci_controller_set_interrupt_coalescence() - This method allows the user to + * configure the interrupt coalescence. + * @controller: This parameter represents the handle to the controller object + * for which its interrupt coalesce register is overridden. + * @coalesce_number: Used to control the number of entries in the Completion + * Queue before an interrupt is generated. If the number of entries exceed + * this number, an interrupt will be generated. The valid range of the input + * is [0, 256]. A setting of 0 results in coalescing being disabled. + * @coalesce_timeout: Timeout value in microseconds. The valid range of the + * input is [0, 2700000] . A setting of 0 is allowed and results in no + * interrupt coalescing timeout. + * + * Indicate if the user successfully set the interrupt coalesce parameters. + * SCI_SUCCESS The user successfully updated the interrutp coalescence. + * SCI_FAILURE_INVALID_PARAMETER_VALUE The user input value is out of range. + */ +static enum sci_status +sci_controller_set_interrupt_coalescence(struct isci_host *ihost, + u32 coalesce_number, + u32 coalesce_timeout) +{ + u8 timeout_encode = 0; + u32 min = 0; + u32 max = 0; + + /* Check if the input parameters fall in the range. */ + if (coalesce_number > INTERRUPT_COALESCE_NUMBER_MAX) + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + + /* + * Defined encoding for interrupt coalescing timeout: + * Value Min Max Units + * ----- --- --- ----- + * 0 - - Disabled + * 1 13.3 20.0 ns + * 2 26.7 40.0 + * 3 53.3 80.0 + * 4 106.7 160.0 + * 5 213.3 320.0 + * 6 426.7 640.0 + * 7 853.3 1280.0 + * 8 1.7 2.6 us + * 9 3.4 5.1 + * 10 6.8 10.2 + * 11 13.7 20.5 + * 12 27.3 41.0 + * 13 54.6 81.9 + * 14 109.2 163.8 + * 15 218.5 327.7 + * 16 436.9 655.4 + * 17 873.8 1310.7 + * 18 1.7 2.6 ms + * 19 3.5 5.2 + * 20 7.0 10.5 + * 21 14.0 21.0 + * 22 28.0 41.9 + * 23 55.9 83.9 + * 24 111.8 167.8 + * 25 223.7 335.5 + * 26 447.4 671.1 + * 27 894.8 1342.2 + * 28 1.8 2.7 s + * Others Undefined */ + + /* + * Use the table above to decide the encode of interrupt coalescing timeout + * value for register writing. */ + if (coalesce_timeout == 0) + timeout_encode = 0; + else{ + /* make the timeout value in unit of (10 ns). */ + coalesce_timeout = coalesce_timeout * 100; + min = INTERRUPT_COALESCE_TIMEOUT_BASE_RANGE_LOWER_BOUND_NS / 10; + max = INTERRUPT_COALESCE_TIMEOUT_BASE_RANGE_UPPER_BOUND_NS / 10; + + /* get the encode of timeout for register writing. */ + for (timeout_encode = INTERRUPT_COALESCE_TIMEOUT_ENCODE_MIN; + timeout_encode <= INTERRUPT_COALESCE_TIMEOUT_ENCODE_MAX; + timeout_encode++) { + if (min <= coalesce_timeout && max > coalesce_timeout) + break; + else if (coalesce_timeout >= max && coalesce_timeout < min * 2 + && coalesce_timeout <= INTERRUPT_COALESCE_TIMEOUT_MAX_US * 100) { + if ((coalesce_timeout - max) < (2 * min - coalesce_timeout)) + break; + else{ + timeout_encode++; + break; + } + } else { + max = max * 2; + min = min * 2; + } + } + + if (timeout_encode == INTERRUPT_COALESCE_TIMEOUT_ENCODE_MAX + 1) + /* the value is out of range. */ + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + } + + writel(SMU_ICC_GEN_VAL(NUMBER, coalesce_number) | + SMU_ICC_GEN_VAL(TIMER, timeout_encode), + &ihost->smu_registers->interrupt_coalesce_control); + + + ihost->interrupt_coalesce_number = (u16)coalesce_number; + ihost->interrupt_coalesce_timeout = coalesce_timeout / 100; + + return SCI_SUCCESS; +} + + +static void sci_controller_ready_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + /* set the default interrupt coalescence number and timeout value. */ + sci_controller_set_interrupt_coalescence(ihost, 0x10, 250); +} + +static void sci_controller_ready_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + /* disable interrupt coalescence. */ + sci_controller_set_interrupt_coalescence(ihost, 0, 0); +} + +static enum sci_status sci_controller_stop_phys(struct isci_host *ihost) +{ + u32 index; + enum sci_status status; + enum sci_status phy_status; + + status = SCI_SUCCESS; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + phy_status = sci_phy_stop(&ihost->phys[index]); + + if (phy_status != SCI_SUCCESS && + phy_status != SCI_FAILURE_INVALID_STATE) { + status = SCI_FAILURE; + + dev_warn(&ihost->pdev->dev, + "%s: Controller stop operation failed to stop " + "phy %d because of status %d.\n", + __func__, + ihost->phys[index].phy_index, phy_status); + } + } + + return status; +} + +static enum sci_status sci_controller_stop_ports(struct isci_host *ihost) +{ + u32 index; + enum sci_status port_status; + enum sci_status status = SCI_SUCCESS; + + for (index = 0; index < ihost->logical_port_entries; index++) { + struct isci_port *iport = &ihost->ports[index]; + + port_status = sci_port_stop(iport); + + if ((port_status != SCI_SUCCESS) && + (port_status != SCI_FAILURE_INVALID_STATE)) { + status = SCI_FAILURE; + + dev_warn(&ihost->pdev->dev, + "%s: Controller stop operation failed to " + "stop port %d because of status %d.\n", + __func__, + iport->logical_port_index, + port_status); + } + } + + return status; +} + +static enum sci_status sci_controller_stop_devices(struct isci_host *ihost) +{ + u32 index; + enum sci_status status; + enum sci_status device_status; + + status = SCI_SUCCESS; + + for (index = 0; index < ihost->remote_node_entries; index++) { + if (ihost->device_table[index] != NULL) { + /* / @todo What timeout value do we want to provide to this request? */ + device_status = sci_remote_device_stop(ihost->device_table[index], 0); + + if ((device_status != SCI_SUCCESS) && + (device_status != SCI_FAILURE_INVALID_STATE)) { + dev_warn(&ihost->pdev->dev, + "%s: Controller stop operation failed " + "to stop device 0x%p because of " + "status %d.\n", + __func__, + ihost->device_table[index], device_status); + } + } + } + + return status; +} + +static void sci_controller_stopping_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + /* Stop all of the components for this controller */ + sci_controller_stop_phys(ihost); + sci_controller_stop_ports(ihost); + sci_controller_stop_devices(ihost); +} + +static void sci_controller_stopping_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + sci_del_timer(&ihost->timer); +} + +static void sci_controller_reset_hardware(struct isci_host *ihost) +{ + /* Disable interrupts so we dont take any spurious interrupts */ + sci_controller_disable_interrupts(ihost); + + /* Reset the SCU */ + writel(0xFFFFFFFF, &ihost->smu_registers->soft_reset_control); + + /* Delay for 1ms to before clearing the CQP and UFQPR. */ + udelay(1000); + + /* The write to the CQGR clears the CQP */ + writel(0x00000000, &ihost->smu_registers->completion_queue_get); + + /* The write to the UFQGP clears the UFQPR */ + writel(0, &ihost->scu_registers->sdma.unsolicited_frame_get_pointer); +} + +static void sci_controller_resetting_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_host *ihost = container_of(sm, typeof(*ihost), sm); + + sci_controller_reset_hardware(ihost); + sci_change_state(&ihost->sm, SCIC_RESET); +} + +static const struct sci_base_state sci_controller_state_table[] = { + [SCIC_INITIAL] = { + .enter_state = sci_controller_initial_state_enter, + }, + [SCIC_RESET] = {}, + [SCIC_INITIALIZING] = {}, + [SCIC_INITIALIZED] = {}, + [SCIC_STARTING] = { + .exit_state = sci_controller_starting_state_exit, + }, + [SCIC_READY] = { + .enter_state = sci_controller_ready_state_enter, + .exit_state = sci_controller_ready_state_exit, + }, + [SCIC_RESETTING] = { + .enter_state = sci_controller_resetting_state_enter, + }, + [SCIC_STOPPING] = { + .enter_state = sci_controller_stopping_state_enter, + .exit_state = sci_controller_stopping_state_exit, + }, + [SCIC_STOPPED] = {}, + [SCIC_FAILED] = {} +}; + +static void sci_controller_set_default_config_parameters(struct isci_host *ihost) +{ + /* these defaults are overridden by the platform / firmware */ + u16 index; + + /* Default to APC mode. */ + ihost->oem_parameters.controller.mode_type = SCIC_PORT_AUTOMATIC_CONFIGURATION_MODE; + + /* Default to APC mode. */ + ihost->oem_parameters.controller.max_concurrent_dev_spin_up = 1; + + /* Default to no SSC operation. */ + ihost->oem_parameters.controller.do_enable_ssc = false; + + /* Initialize all of the port parameter information to narrow ports. */ + for (index = 0; index < SCI_MAX_PORTS; index++) { + ihost->oem_parameters.ports[index].phy_mask = 0; + } + + /* Initialize all of the phy parameter information. */ + for (index = 0; index < SCI_MAX_PHYS; index++) { + /* Default to 6G (i.e. Gen 3) for now. */ + ihost->user_parameters.phys[index].max_speed_generation = 3; + + /* the frequencies cannot be 0 */ + ihost->user_parameters.phys[index].align_insertion_frequency = 0x7f; + ihost->user_parameters.phys[index].in_connection_align_insertion_frequency = 0xff; + ihost->user_parameters.phys[index].notify_enable_spin_up_insertion_frequency = 0x33; + + /* + * Previous Vitesse based expanders had a arbitration issue that + * is worked around by having the upper 32-bits of SAS address + * with a value greater then the Vitesse company identifier. + * Hence, usage of 0x5FCFFFFF. */ + ihost->oem_parameters.phys[index].sas_address.low = 0x1 + ihost->id; + ihost->oem_parameters.phys[index].sas_address.high = 0x5FCFFFFF; + } + + ihost->user_parameters.stp_inactivity_timeout = 5; + ihost->user_parameters.ssp_inactivity_timeout = 5; + ihost->user_parameters.stp_max_occupancy_timeout = 5; + ihost->user_parameters.ssp_max_occupancy_timeout = 20; + ihost->user_parameters.no_outbound_task_timeout = 20; +} + +static void controller_timeout(unsigned long data) +{ + struct sci_timer *tmr = (struct sci_timer *)data; + struct isci_host *ihost = container_of(tmr, typeof(*ihost), timer); + struct sci_base_state_machine *sm = &ihost->sm; + unsigned long flags; + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + if (sm->current_state_id == SCIC_STARTING) + sci_controller_transition_to_ready(ihost, SCI_FAILURE_TIMEOUT); + else if (sm->current_state_id == SCIC_STOPPING) { + sci_change_state(sm, SCIC_FAILED); + isci_host_stop_complete(ihost, SCI_FAILURE_TIMEOUT); + } else /* / @todo Now what do we want to do in this case? */ + dev_err(&ihost->pdev->dev, + "%s: Controller timer fired when controller was not " + "in a state being timed.\n", + __func__); + +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +static enum sci_status sci_controller_construct(struct isci_host *ihost, + void __iomem *scu_base, + void __iomem *smu_base) +{ + u8 i; + + sci_init_sm(&ihost->sm, sci_controller_state_table, SCIC_INITIAL); + + ihost->scu_registers = scu_base; + ihost->smu_registers = smu_base; + + sci_port_configuration_agent_construct(&ihost->port_agent); + + /* Construct the ports for this controller */ + for (i = 0; i < SCI_MAX_PORTS; i++) + sci_port_construct(&ihost->ports[i], i, ihost); + sci_port_construct(&ihost->ports[i], SCIC_SDS_DUMMY_PORT, ihost); + + /* Construct the phys for this controller */ + for (i = 0; i < SCI_MAX_PHYS; i++) { + /* Add all the PHYs to the dummy port */ + sci_phy_construct(&ihost->phys[i], + &ihost->ports[SCI_MAX_PORTS], i); + } + + ihost->invalid_phy_mask = 0; + + sci_init_timer(&ihost->timer, controller_timeout); + + /* Initialize the User and OEM parameters to default values. */ + sci_controller_set_default_config_parameters(ihost); + + return sci_controller_reset(ihost); +} + +int sci_oem_parameters_validate(struct sci_oem_params *oem) +{ + int i; + + for (i = 0; i < SCI_MAX_PORTS; i++) + if (oem->ports[i].phy_mask > SCIC_SDS_PARM_PHY_MASK_MAX) + return -EINVAL; + + for (i = 0; i < SCI_MAX_PHYS; i++) + if (oem->phys[i].sas_address.high == 0 && + oem->phys[i].sas_address.low == 0) + return -EINVAL; + + if (oem->controller.mode_type == SCIC_PORT_AUTOMATIC_CONFIGURATION_MODE) { + for (i = 0; i < SCI_MAX_PHYS; i++) + if (oem->ports[i].phy_mask != 0) + return -EINVAL; + } else if (oem->controller.mode_type == SCIC_PORT_MANUAL_CONFIGURATION_MODE) { + u8 phy_mask = 0; + + for (i = 0; i < SCI_MAX_PHYS; i++) + phy_mask |= oem->ports[i].phy_mask; + + if (phy_mask == 0) + return -EINVAL; + } else + return -EINVAL; + + if (oem->controller.max_concurrent_dev_spin_up > MAX_CONCURRENT_DEVICE_SPIN_UP_COUNT) + return -EINVAL; + + return 0; +} + +static enum sci_status sci_oem_parameters_set(struct isci_host *ihost) +{ + u32 state = ihost->sm.current_state_id; + + if (state == SCIC_RESET || + state == SCIC_INITIALIZING || + state == SCIC_INITIALIZED) { + + if (sci_oem_parameters_validate(&ihost->oem_parameters)) + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + + return SCI_SUCCESS; + } + + return SCI_FAILURE_INVALID_STATE; +} + +static void power_control_timeout(unsigned long data) +{ + struct sci_timer *tmr = (struct sci_timer *)data; + struct isci_host *ihost = container_of(tmr, typeof(*ihost), power_control.timer); + struct isci_phy *iphy; + unsigned long flags; + u8 i; + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + ihost->power_control.phys_granted_power = 0; + + if (ihost->power_control.phys_waiting == 0) { + ihost->power_control.timer_started = false; + goto done; + } + + for (i = 0; i < SCI_MAX_PHYS; i++) { + + if (ihost->power_control.phys_waiting == 0) + break; + + iphy = ihost->power_control.requesters[i]; + if (iphy == NULL) + continue; + + if (ihost->power_control.phys_granted_power >= + ihost->oem_parameters.controller.max_concurrent_dev_spin_up) + break; + + ihost->power_control.requesters[i] = NULL; + ihost->power_control.phys_waiting--; + ihost->power_control.phys_granted_power++; + sci_phy_consume_power_handler(iphy); + } + + /* + * It doesn't matter if the power list is empty, we need to start the + * timer in case another phy becomes ready. + */ + sci_mod_timer(tmr, SCIC_SDS_CONTROLLER_POWER_CONTROL_INTERVAL); + ihost->power_control.timer_started = true; + +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +void sci_controller_power_control_queue_insert(struct isci_host *ihost, + struct isci_phy *iphy) +{ + BUG_ON(iphy == NULL); + + if (ihost->power_control.phys_granted_power < + ihost->oem_parameters.controller.max_concurrent_dev_spin_up) { + ihost->power_control.phys_granted_power++; + sci_phy_consume_power_handler(iphy); + + /* + * stop and start the power_control timer. When the timer fires, the + * no_of_phys_granted_power will be set to 0 + */ + if (ihost->power_control.timer_started) + sci_del_timer(&ihost->power_control.timer); + + sci_mod_timer(&ihost->power_control.timer, + SCIC_SDS_CONTROLLER_POWER_CONTROL_INTERVAL); + ihost->power_control.timer_started = true; + + } else { + /* Add the phy in the waiting list */ + ihost->power_control.requesters[iphy->phy_index] = iphy; + ihost->power_control.phys_waiting++; + } +} + +void sci_controller_power_control_queue_remove(struct isci_host *ihost, + struct isci_phy *iphy) +{ + BUG_ON(iphy == NULL); + + if (ihost->power_control.requesters[iphy->phy_index]) + ihost->power_control.phys_waiting--; + + ihost->power_control.requesters[iphy->phy_index] = NULL; +} + +#define AFE_REGISTER_WRITE_DELAY 10 + +/* Initialize the AFE for this phy index. We need to read the AFE setup from + * the OEM parameters + */ +static void sci_controller_afe_initialization(struct isci_host *ihost) +{ + const struct sci_oem_params *oem = &ihost->oem_parameters; + struct pci_dev *pdev = ihost->pdev; + u32 afe_status; + u32 phy_id; + + /* Clear DFX Status registers */ + writel(0x0081000f, &ihost->scu_registers->afe.afe_dfx_master_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + + if (is_b0(pdev)) { + /* PM Rx Equalization Save, PM SPhy Rx Acknowledgement + * Timer, PM Stagger Timer */ + writel(0x0007BFFF, &ihost->scu_registers->afe.afe_pmsn_master_control2); + udelay(AFE_REGISTER_WRITE_DELAY); + } + + /* Configure bias currents to normal */ + if (is_a2(pdev)) + writel(0x00005A00, &ihost->scu_registers->afe.afe_bias_control); + else if (is_b0(pdev) || is_c0(pdev)) + writel(0x00005F00, &ihost->scu_registers->afe.afe_bias_control); + + udelay(AFE_REGISTER_WRITE_DELAY); + + /* Enable PLL */ + if (is_b0(pdev) || is_c0(pdev)) + writel(0x80040A08, &ihost->scu_registers->afe.afe_pll_control0); + else + writel(0x80040908, &ihost->scu_registers->afe.afe_pll_control0); + + udelay(AFE_REGISTER_WRITE_DELAY); + + /* Wait for the PLL to lock */ + do { + afe_status = readl(&ihost->scu_registers->afe.afe_common_block_status); + udelay(AFE_REGISTER_WRITE_DELAY); + } while ((afe_status & 0x00001000) == 0); + + if (is_a2(pdev)) { + /* Shorten SAS SNW lock time (RxLock timer value from 76 us to 50 us) */ + writel(0x7bcc96ad, &ihost->scu_registers->afe.afe_pmsn_master_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + } + + for (phy_id = 0; phy_id < SCI_MAX_PHYS; phy_id++) { + const struct sci_phy_oem_params *oem_phy = &oem->phys[phy_id]; + + if (is_b0(pdev)) { + /* Configure transmitter SSC parameters */ + writel(0x00030000, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_ssc_control); + udelay(AFE_REGISTER_WRITE_DELAY); + } else if (is_c0(pdev)) { + /* Configure transmitter SSC parameters */ + writel(0x0003000, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_ssc_control); + udelay(AFE_REGISTER_WRITE_DELAY); + + /* + * All defaults, except the Receive Word Alignament/Comma Detect + * Enable....(0xe800) */ + writel(0x00004500, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_xcvr_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + } else { + /* + * All defaults, except the Receive Word Alignament/Comma Detect + * Enable....(0xe800) */ + writel(0x00004512, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_xcvr_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + + writel(0x0050100F, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_xcvr_control1); + udelay(AFE_REGISTER_WRITE_DELAY); + } + + /* + * Power up TX and RX out from power down (PWRDNTX and PWRDNRX) + * & increase TX int & ext bias 20%....(0xe85c) */ + if (is_a2(pdev)) + writel(0x000003F0, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_channel_control); + else if (is_b0(pdev)) { + /* Power down TX and RX (PWRDNTX and PWRDNRX) */ + writel(0x000003D7, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_channel_control); + udelay(AFE_REGISTER_WRITE_DELAY); + + /* + * Power up TX and RX out from power down (PWRDNTX and PWRDNRX) + * & increase TX int & ext bias 20%....(0xe85c) */ + writel(0x000003D4, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_channel_control); + } else { + writel(0x000001E7, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_channel_control); + udelay(AFE_REGISTER_WRITE_DELAY); + + /* + * Power up TX and RX out from power down (PWRDNTX and PWRDNRX) + * & increase TX int & ext bias 20%....(0xe85c) */ + writel(0x000001E4, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_channel_control); + } + udelay(AFE_REGISTER_WRITE_DELAY); + + if (is_a2(pdev)) { + /* Enable TX equalization (0xe824) */ + writel(0x00040000, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_control); + udelay(AFE_REGISTER_WRITE_DELAY); + } + + /* + * RDPI=0x0(RX Power On), RXOOBDETPDNC=0x0, TPD=0x0(TX Power On), + * RDD=0x0(RX Detect Enabled) ....(0xe800) */ + writel(0x00004100, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_xcvr_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + + /* Leave DFE/FFE on */ + if (is_a2(pdev)) + writel(0x3F11103F, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_rx_ssc_control0); + else if (is_b0(pdev)) { + writel(0x3F11103F, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_rx_ssc_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + /* Enable TX equalization (0xe824) */ + writel(0x00040000, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_control); + } else { + writel(0x0140DF0F, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_rx_ssc_control1); + udelay(AFE_REGISTER_WRITE_DELAY); + + writel(0x3F6F103F, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_rx_ssc_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + + /* Enable TX equalization (0xe824) */ + writel(0x00040000, &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_control); + } + + udelay(AFE_REGISTER_WRITE_DELAY); + + writel(oem_phy->afe_tx_amp_control0, + &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_amp_control0); + udelay(AFE_REGISTER_WRITE_DELAY); + + writel(oem_phy->afe_tx_amp_control1, + &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_amp_control1); + udelay(AFE_REGISTER_WRITE_DELAY); + + writel(oem_phy->afe_tx_amp_control2, + &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_amp_control2); + udelay(AFE_REGISTER_WRITE_DELAY); + + writel(oem_phy->afe_tx_amp_control3, + &ihost->scu_registers->afe.scu_afe_xcvr[phy_id].afe_tx_amp_control3); + udelay(AFE_REGISTER_WRITE_DELAY); + } + + /* Transfer control to the PEs */ + writel(0x00010f00, &ihost->scu_registers->afe.afe_dfx_master_control0); + udelay(AFE_REGISTER_WRITE_DELAY); +} + +static void sci_controller_initialize_power_control(struct isci_host *ihost) +{ + sci_init_timer(&ihost->power_control.timer, power_control_timeout); + + memset(ihost->power_control.requesters, 0, + sizeof(ihost->power_control.requesters)); + + ihost->power_control.phys_waiting = 0; + ihost->power_control.phys_granted_power = 0; +} + +static enum sci_status sci_controller_initialize(struct isci_host *ihost) +{ + struct sci_base_state_machine *sm = &ihost->sm; + enum sci_status result = SCI_FAILURE; + unsigned long i, state, val; + + if (ihost->sm.current_state_id != SCIC_RESET) { + dev_warn(&ihost->pdev->dev, + "SCIC Controller initialize operation requested " + "in invalid state\n"); + return SCI_FAILURE_INVALID_STATE; + } + + sci_change_state(sm, SCIC_INITIALIZING); + + sci_init_timer(&ihost->phy_timer, phy_startup_timeout); + + ihost->next_phy_to_start = 0; + ihost->phy_startup_timer_pending = false; + + sci_controller_initialize_power_control(ihost); + + /* + * There is nothing to do here for B0 since we do not have to + * program the AFE registers. + * / @todo The AFE settings are supposed to be correct for the B0 but + * / presently they seem to be wrong. */ + sci_controller_afe_initialization(ihost); + + + /* Take the hardware out of reset */ + writel(0, &ihost->smu_registers->soft_reset_control); + + /* + * / @todo Provide meaningfull error code for hardware failure + * result = SCI_FAILURE_CONTROLLER_HARDWARE; */ + for (i = 100; i >= 1; i--) { + u32 status; + + /* Loop until the hardware reports success */ + udelay(SCU_CONTEXT_RAM_INIT_STALL_TIME); + status = readl(&ihost->smu_registers->control_status); + + if ((status & SCU_RAM_INIT_COMPLETED) == SCU_RAM_INIT_COMPLETED) + break; + } + if (i == 0) + goto out; + + /* + * Determine what are the actaul device capacities that the + * hardware will support */ + val = readl(&ihost->smu_registers->device_context_capacity); + + /* Record the smaller of the two capacity values */ + ihost->logical_port_entries = min(smu_max_ports(val), SCI_MAX_PORTS); + ihost->task_context_entries = min(smu_max_task_contexts(val), SCI_MAX_IO_REQUESTS); + ihost->remote_node_entries = min(smu_max_rncs(val), SCI_MAX_REMOTE_DEVICES); + + /* + * Make all PEs that are unassigned match up with the + * logical ports + */ + for (i = 0; i < ihost->logical_port_entries; i++) { + struct scu_port_task_scheduler_group_registers __iomem + *ptsg = &ihost->scu_registers->peg0.ptsg; + + writel(i, &ptsg->protocol_engine[i]); + } + + /* Initialize hardware PCI Relaxed ordering in DMA engines */ + val = readl(&ihost->scu_registers->sdma.pdma_configuration); + val |= SCU_PDMACR_GEN_BIT(PCI_RELAXED_ORDERING_ENABLE); + writel(val, &ihost->scu_registers->sdma.pdma_configuration); + + val = readl(&ihost->scu_registers->sdma.cdma_configuration); + val |= SCU_CDMACR_GEN_BIT(PCI_RELAXED_ORDERING_ENABLE); + writel(val, &ihost->scu_registers->sdma.cdma_configuration); + + /* + * Initialize the PHYs before the PORTs because the PHY registers + * are accessed during the port initialization. + */ + for (i = 0; i < SCI_MAX_PHYS; i++) { + result = sci_phy_initialize(&ihost->phys[i], + &ihost->scu_registers->peg0.pe[i].tl, + &ihost->scu_registers->peg0.pe[i].ll); + if (result != SCI_SUCCESS) + goto out; + } + + for (i = 0; i < ihost->logical_port_entries; i++) { + struct isci_port *iport = &ihost->ports[i]; + + iport->port_task_scheduler_registers = &ihost->scu_registers->peg0.ptsg.port[i]; + iport->port_pe_configuration_register = &ihost->scu_registers->peg0.ptsg.protocol_engine[0]; + iport->viit_registers = &ihost->scu_registers->peg0.viit[i]; + } + + result = sci_port_configuration_agent_initialize(ihost, &ihost->port_agent); + + out: + /* Advance the controller state machine */ + if (result == SCI_SUCCESS) + state = SCIC_INITIALIZED; + else + state = SCIC_FAILED; + sci_change_state(sm, state); + + return result; +} + +static enum sci_status sci_user_parameters_set(struct isci_host *ihost, + struct sci_user_parameters *sci_parms) +{ + u32 state = ihost->sm.current_state_id; + + if (state == SCIC_RESET || + state == SCIC_INITIALIZING || + state == SCIC_INITIALIZED) { + u16 index; + + /* + * Validate the user parameters. If they are not legal, then + * return a failure. + */ + for (index = 0; index < SCI_MAX_PHYS; index++) { + struct sci_phy_user_params *user_phy; + + user_phy = &sci_parms->phys[index]; + + if (!((user_phy->max_speed_generation <= + SCIC_SDS_PARM_MAX_SPEED) && + (user_phy->max_speed_generation > + SCIC_SDS_PARM_NO_SPEED))) + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + + if (user_phy->in_connection_align_insertion_frequency < + 3) + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + + if ((user_phy->in_connection_align_insertion_frequency < + 3) || + (user_phy->align_insertion_frequency == 0) || + (user_phy-> + notify_enable_spin_up_insertion_frequency == + 0)) + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + } + + if ((sci_parms->stp_inactivity_timeout == 0) || + (sci_parms->ssp_inactivity_timeout == 0) || + (sci_parms->stp_max_occupancy_timeout == 0) || + (sci_parms->ssp_max_occupancy_timeout == 0) || + (sci_parms->no_outbound_task_timeout == 0)) + return SCI_FAILURE_INVALID_PARAMETER_VALUE; + + memcpy(&ihost->user_parameters, sci_parms, sizeof(*sci_parms)); + + return SCI_SUCCESS; + } + + return SCI_FAILURE_INVALID_STATE; +} + +static int sci_controller_mem_init(struct isci_host *ihost) +{ + struct device *dev = &ihost->pdev->dev; + dma_addr_t dma; + size_t size; + int err; + + size = SCU_MAX_COMPLETION_QUEUE_ENTRIES * sizeof(u32); + ihost->completion_queue = dmam_alloc_coherent(dev, size, &dma, GFP_KERNEL); + if (!ihost->completion_queue) + return -ENOMEM; + + writel(lower_32_bits(dma), &ihost->smu_registers->completion_queue_lower); + writel(upper_32_bits(dma), &ihost->smu_registers->completion_queue_upper); + + size = ihost->remote_node_entries * sizeof(union scu_remote_node_context); + ihost->remote_node_context_table = dmam_alloc_coherent(dev, size, &dma, + GFP_KERNEL); + if (!ihost->remote_node_context_table) + return -ENOMEM; + + writel(lower_32_bits(dma), &ihost->smu_registers->remote_node_context_lower); + writel(upper_32_bits(dma), &ihost->smu_registers->remote_node_context_upper); + + size = ihost->task_context_entries * sizeof(struct scu_task_context), + ihost->task_context_table = dmam_alloc_coherent(dev, size, &dma, GFP_KERNEL); + if (!ihost->task_context_table) + return -ENOMEM; + + ihost->task_context_dma = dma; + writel(lower_32_bits(dma), &ihost->smu_registers->host_task_table_lower); + writel(upper_32_bits(dma), &ihost->smu_registers->host_task_table_upper); + + err = sci_unsolicited_frame_control_construct(ihost); + if (err) + return err; + + /* + * Inform the silicon as to the location of the UF headers and + * address table. + */ + writel(lower_32_bits(ihost->uf_control.headers.physical_address), + &ihost->scu_registers->sdma.uf_header_base_address_lower); + writel(upper_32_bits(ihost->uf_control.headers.physical_address), + &ihost->scu_registers->sdma.uf_header_base_address_upper); + + writel(lower_32_bits(ihost->uf_control.address_table.physical_address), + &ihost->scu_registers->sdma.uf_address_table_lower); + writel(upper_32_bits(ihost->uf_control.address_table.physical_address), + &ihost->scu_registers->sdma.uf_address_table_upper); + + return 0; +} + +int isci_host_init(struct isci_host *ihost) +{ + int err = 0, i; + enum sci_status status; + struct sci_user_parameters sci_user_params; + struct isci_pci_info *pci_info = to_pci_info(ihost->pdev); + + spin_lock_init(&ihost->state_lock); + spin_lock_init(&ihost->scic_lock); + init_waitqueue_head(&ihost->eventq); + + isci_host_change_state(ihost, isci_starting); + + status = sci_controller_construct(ihost, scu_base(ihost), + smu_base(ihost)); + + if (status != SCI_SUCCESS) { + dev_err(&ihost->pdev->dev, + "%s: sci_controller_construct failed - status = %x\n", + __func__, + status); + return -ENODEV; + } + + ihost->sas_ha.dev = &ihost->pdev->dev; + ihost->sas_ha.lldd_ha = ihost; + + /* + * grab initial values stored in the controller object for OEM and USER + * parameters + */ + isci_user_parameters_get(&sci_user_params); + status = sci_user_parameters_set(ihost, &sci_user_params); + if (status != SCI_SUCCESS) { + dev_warn(&ihost->pdev->dev, + "%s: sci_user_parameters_set failed\n", + __func__); + return -ENODEV; + } + + /* grab any OEM parameters specified in orom */ + if (pci_info->orom) { + status = isci_parse_oem_parameters(&ihost->oem_parameters, + pci_info->orom, + ihost->id); + if (status != SCI_SUCCESS) { + dev_warn(&ihost->pdev->dev, + "parsing firmware oem parameters failed\n"); + return -EINVAL; + } + } + + status = sci_oem_parameters_set(ihost); + if (status != SCI_SUCCESS) { + dev_warn(&ihost->pdev->dev, + "%s: sci_oem_parameters_set failed\n", + __func__); + return -ENODEV; + } + + tasklet_init(&ihost->completion_tasklet, + isci_host_completion_routine, (unsigned long)ihost); + + INIT_LIST_HEAD(&ihost->requests_to_complete); + INIT_LIST_HEAD(&ihost->requests_to_errorback); + + spin_lock_irq(&ihost->scic_lock); + status = sci_controller_initialize(ihost); + spin_unlock_irq(&ihost->scic_lock); + if (status != SCI_SUCCESS) { + dev_warn(&ihost->pdev->dev, + "%s: sci_controller_initialize failed -" + " status = 0x%x\n", + __func__, status); + return -ENODEV; + } + + err = sci_controller_mem_init(ihost); + if (err) + return err; + + for (i = 0; i < SCI_MAX_PORTS; i++) + isci_port_init(&ihost->ports[i], ihost, i); + + for (i = 0; i < SCI_MAX_PHYS; i++) + isci_phy_init(&ihost->phys[i], ihost, i); + + for (i = 0; i < SCI_MAX_REMOTE_DEVICES; i++) { + struct isci_remote_device *idev = &ihost->devices[i]; + + INIT_LIST_HEAD(&idev->reqs_in_process); + INIT_LIST_HEAD(&idev->node); + } + + for (i = 0; i < SCI_MAX_IO_REQUESTS; i++) { + struct isci_request *ireq; + dma_addr_t dma; + + ireq = dmam_alloc_coherent(&ihost->pdev->dev, + sizeof(struct isci_request), &dma, + GFP_KERNEL); + if (!ireq) + return -ENOMEM; + + ireq->tc = &ihost->task_context_table[i]; + ireq->owning_controller = ihost; + spin_lock_init(&ireq->state_lock); + ireq->request_daddr = dma; + ireq->isci_host = ihost; + ihost->reqs[i] = ireq; + } + + return 0; +} + +void sci_controller_link_up(struct isci_host *ihost, struct isci_port *iport, + struct isci_phy *iphy) +{ + switch (ihost->sm.current_state_id) { + case SCIC_STARTING: + sci_del_timer(&ihost->phy_timer); + ihost->phy_startup_timer_pending = false; + ihost->port_agent.link_up_handler(ihost, &ihost->port_agent, + iport, iphy); + sci_controller_start_next_phy(ihost); + break; + case SCIC_READY: + ihost->port_agent.link_up_handler(ihost, &ihost->port_agent, + iport, iphy); + break; + default: + dev_dbg(&ihost->pdev->dev, + "%s: SCIC Controller linkup event from phy %d in " + "unexpected state %d\n", __func__, iphy->phy_index, + ihost->sm.current_state_id); + } +} + +void sci_controller_link_down(struct isci_host *ihost, struct isci_port *iport, + struct isci_phy *iphy) +{ + switch (ihost->sm.current_state_id) { + case SCIC_STARTING: + case SCIC_READY: + ihost->port_agent.link_down_handler(ihost, &ihost->port_agent, + iport, iphy); + break; + default: + dev_dbg(&ihost->pdev->dev, + "%s: SCIC Controller linkdown event from phy %d in " + "unexpected state %d\n", + __func__, + iphy->phy_index, + ihost->sm.current_state_id); + } +} + +static bool sci_controller_has_remote_devices_stopping(struct isci_host *ihost) +{ + u32 index; + + for (index = 0; index < ihost->remote_node_entries; index++) { + if ((ihost->device_table[index] != NULL) && + (ihost->device_table[index]->sm.current_state_id == SCI_DEV_STOPPING)) + return true; + } + + return false; +} + +void sci_controller_remote_device_stopped(struct isci_host *ihost, + struct isci_remote_device *idev) +{ + if (ihost->sm.current_state_id != SCIC_STOPPING) { + dev_dbg(&ihost->pdev->dev, + "SCIC Controller 0x%p remote device stopped event " + "from device 0x%p in unexpected state %d\n", + ihost, idev, + ihost->sm.current_state_id); + return; + } + + if (!sci_controller_has_remote_devices_stopping(ihost)) + sci_change_state(&ihost->sm, SCIC_STOPPED); +} + +void sci_controller_post_request(struct isci_host *ihost, u32 request) +{ + dev_dbg(&ihost->pdev->dev, "%s[%d]: %#x\n", + __func__, ihost->id, request); + + writel(request, &ihost->smu_registers->post_context_port); +} + +struct isci_request *sci_request_by_tag(struct isci_host *ihost, u16 io_tag) +{ + u16 task_index; + u16 task_sequence; + + task_index = ISCI_TAG_TCI(io_tag); + + if (task_index < ihost->task_context_entries) { + struct isci_request *ireq = ihost->reqs[task_index]; + + if (test_bit(IREQ_ACTIVE, &ireq->flags)) { + task_sequence = ISCI_TAG_SEQ(io_tag); + + if (task_sequence == ihost->io_request_sequence[task_index]) + return ireq; + } + } + + return NULL; +} + +/** + * This method allocates remote node index and the reserves the remote node + * context space for use. This method can fail if there are no more remote + * node index available. + * @scic: This is the controller object which contains the set of + * free remote node ids + * @sci_dev: This is the device object which is requesting the a remote node + * id + * @node_id: This is the remote node id that is assinged to the device if one + * is available + * + * enum sci_status SCI_FAILURE_OUT_OF_RESOURCES if there are no available remote + * node index available. + */ +enum sci_status sci_controller_allocate_remote_node_context(struct isci_host *ihost, + struct isci_remote_device *idev, + u16 *node_id) +{ + u16 node_index; + u32 remote_node_count = sci_remote_device_node_count(idev); + + node_index = sci_remote_node_table_allocate_remote_node( + &ihost->available_remote_nodes, remote_node_count + ); + + if (node_index != SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX) { + ihost->device_table[node_index] = idev; + + *node_id = node_index; + + return SCI_SUCCESS; + } + + return SCI_FAILURE_INSUFFICIENT_RESOURCES; +} + +void sci_controller_free_remote_node_context(struct isci_host *ihost, + struct isci_remote_device *idev, + u16 node_id) +{ + u32 remote_node_count = sci_remote_device_node_count(idev); + + if (ihost->device_table[node_id] == idev) { + ihost->device_table[node_id] = NULL; + + sci_remote_node_table_release_remote_node_index( + &ihost->available_remote_nodes, remote_node_count, node_id + ); + } +} + +void sci_controller_copy_sata_response(void *response_buffer, + void *frame_header, + void *frame_buffer) +{ + /* XXX type safety? */ + memcpy(response_buffer, frame_header, sizeof(u32)); + + memcpy(response_buffer + sizeof(u32), + frame_buffer, + sizeof(struct dev_to_host_fis) - sizeof(u32)); +} + +void sci_controller_release_frame(struct isci_host *ihost, u32 frame_index) +{ + if (sci_unsolicited_frame_control_release_frame(&ihost->uf_control, frame_index)) + writel(ihost->uf_control.get, + &ihost->scu_registers->sdma.unsolicited_frame_get_pointer); +} + +void isci_tci_free(struct isci_host *ihost, u16 tci) +{ + u16 tail = ihost->tci_tail & (SCI_MAX_IO_REQUESTS-1); + + ihost->tci_pool[tail] = tci; + ihost->tci_tail = tail + 1; +} + +static u16 isci_tci_alloc(struct isci_host *ihost) +{ + u16 head = ihost->tci_head & (SCI_MAX_IO_REQUESTS-1); + u16 tci = ihost->tci_pool[head]; + + ihost->tci_head = head + 1; + return tci; +} + +static u16 isci_tci_space(struct isci_host *ihost) +{ + return CIRC_SPACE(ihost->tci_head, ihost->tci_tail, SCI_MAX_IO_REQUESTS); +} + +u16 isci_alloc_tag(struct isci_host *ihost) +{ + if (isci_tci_space(ihost)) { + u16 tci = isci_tci_alloc(ihost); + u8 seq = ihost->io_request_sequence[tci]; + + return ISCI_TAG(seq, tci); + } + + return SCI_CONTROLLER_INVALID_IO_TAG; +} + +enum sci_status isci_free_tag(struct isci_host *ihost, u16 io_tag) +{ + u16 tci = ISCI_TAG_TCI(io_tag); + u16 seq = ISCI_TAG_SEQ(io_tag); + + /* prevent tail from passing head */ + if (isci_tci_active(ihost) == 0) + return SCI_FAILURE_INVALID_IO_TAG; + + if (seq == ihost->io_request_sequence[tci]) { + ihost->io_request_sequence[tci] = (seq+1) & (SCI_MAX_SEQ-1); + + isci_tci_free(ihost, tci); + + return SCI_SUCCESS; + } + return SCI_FAILURE_INVALID_IO_TAG; +} + +enum sci_status sci_controller_start_io(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + enum sci_status status; + + if (ihost->sm.current_state_id != SCIC_READY) { + dev_warn(&ihost->pdev->dev, "invalid state to start I/O"); + return SCI_FAILURE_INVALID_STATE; + } + + status = sci_remote_device_start_io(ihost, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + set_bit(IREQ_ACTIVE, &ireq->flags); + sci_controller_post_request(ihost, ireq->post_context); + return SCI_SUCCESS; +} + +enum sci_status sci_controller_terminate_request(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + /* terminate an ongoing (i.e. started) core IO request. This does not + * abort the IO request at the target, but rather removes the IO + * request from the host controller. + */ + enum sci_status status; + + if (ihost->sm.current_state_id != SCIC_READY) { + dev_warn(&ihost->pdev->dev, + "invalid state to terminate request\n"); + return SCI_FAILURE_INVALID_STATE; + } + + status = sci_io_request_terminate(ireq); + if (status != SCI_SUCCESS) + return status; + + /* + * Utilize the original post context command and or in the POST_TC_ABORT + * request sub-type. + */ + sci_controller_post_request(ihost, + ireq->post_context | SCU_CONTEXT_COMMAND_REQUEST_POST_TC_ABORT); + return SCI_SUCCESS; +} + +/** + * sci_controller_complete_io() - This method will perform core specific + * completion operations for an IO request. After this method is invoked, + * the user should consider the IO request as invalid until it is properly + * reused (i.e. re-constructed). + * @ihost: The handle to the controller object for which to complete the + * IO request. + * @idev: The handle to the remote device object for which to complete + * the IO request. + * @ireq: the handle to the io request object to complete. + */ +enum sci_status sci_controller_complete_io(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + enum sci_status status; + u16 index; + + switch (ihost->sm.current_state_id) { + case SCIC_STOPPING: + /* XXX: Implement this function */ + return SCI_FAILURE; + case SCIC_READY: + status = sci_remote_device_complete_io(ihost, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + index = ISCI_TAG_TCI(ireq->io_tag); + clear_bit(IREQ_ACTIVE, &ireq->flags); + return SCI_SUCCESS; + default: + dev_warn(&ihost->pdev->dev, "invalid state to complete I/O"); + return SCI_FAILURE_INVALID_STATE; + } + +} + +enum sci_status sci_controller_continue_io(struct isci_request *ireq) +{ + struct isci_host *ihost = ireq->owning_controller; + + if (ihost->sm.current_state_id != SCIC_READY) { + dev_warn(&ihost->pdev->dev, "invalid state to continue I/O"); + return SCI_FAILURE_INVALID_STATE; + } + + set_bit(IREQ_ACTIVE, &ireq->flags); + sci_controller_post_request(ihost, ireq->post_context); + return SCI_SUCCESS; +} + +/** + * sci_controller_start_task() - This method is called by the SCIC user to + * send/start a framework task management request. + * @controller: the handle to the controller object for which to start the task + * management request. + * @remote_device: the handle to the remote device object for which to start + * the task management request. + * @task_request: the handle to the task request object to start. + */ +enum sci_task_status sci_controller_start_task(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + enum sci_status status; + + if (ihost->sm.current_state_id != SCIC_READY) { + dev_warn(&ihost->pdev->dev, + "%s: SCIC Controller starting task from invalid " + "state\n", + __func__); + return SCI_TASK_FAILURE_INVALID_STATE; + } + + status = sci_remote_device_start_task(ihost, idev, ireq); + switch (status) { + case SCI_FAILURE_RESET_DEVICE_PARTIAL_SUCCESS: + set_bit(IREQ_ACTIVE, &ireq->flags); + + /* + * We will let framework know this task request started successfully, + * although core is still woring on starting the request (to post tc when + * RNC is resumed.) + */ + return SCI_SUCCESS; + case SCI_SUCCESS: + set_bit(IREQ_ACTIVE, &ireq->flags); + sci_controller_post_request(ihost, ireq->post_context); + break; + default: + break; + } + + return status; +} diff --git a/drivers/scsi/isci/host.h b/drivers/scsi/isci/host.h new file mode 100644 index 0000000..062101a --- /dev/null +++ b/drivers/scsi/isci/host.h @@ -0,0 +1,542 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _SCI_HOST_H_ +#define _SCI_HOST_H_ + +#include "remote_device.h" +#include "phy.h" +#include "isci.h" +#include "remote_node_table.h" +#include "registers.h" +#include "unsolicited_frame_control.h" +#include "probe_roms.h" + +struct isci_request; +struct scu_task_context; + + +/** + * struct sci_power_control - + * + * This structure defines the fields for managing power control for direct + * attached disk devices. + */ +struct sci_power_control { + /** + * This field is set when the power control timer is running and cleared when + * it is not. + */ + bool timer_started; + + /** + * Timer to control when the directed attached disks can consume power. + */ + struct sci_timer timer; + + /** + * This field is used to keep track of how many phys are put into the + * requesters field. + */ + u8 phys_waiting; + + /** + * This field is used to keep track of how many phys have been granted to consume power + */ + u8 phys_granted_power; + + /** + * This field is an array of phys that we are waiting on. The phys are direct + * mapped into requesters via struct sci_phy.phy_index + */ + struct isci_phy *requesters[SCI_MAX_PHYS]; + +}; + +struct sci_port_configuration_agent; +typedef void (*port_config_fn)(struct isci_host *, + struct sci_port_configuration_agent *, + struct isci_port *, struct isci_phy *); + +struct sci_port_configuration_agent { + u16 phy_configured_mask; + u16 phy_ready_mask; + struct { + u8 min_index; + u8 max_index; + } phy_valid_port_range[SCI_MAX_PHYS]; + bool timer_pending; + port_config_fn link_up_handler; + port_config_fn link_down_handler; + struct sci_timer timer; +}; + +/** + * isci_host - primary host/controller object + * @timer: timeout start/stop operations + * @device_table: rni (hw remote node index) to remote device lookup table + * @available_remote_nodes: rni allocator + * @power_control: manage device spin up + * @io_request_sequence: generation number for tci's (task contexts) + * @task_context_table: hw task context table + * @remote_node_context_table: hw remote node context table + * @completion_queue: hw-producer driver-consumer communication ring + * @completion_queue_get: tracks the driver 'head' of the ring to notify hw + * @logical_port_entries: min({driver|silicon}-supported-port-count) + * @remote_node_entries: min({driver|silicon}-supported-node-count) + * @task_context_entries: min({driver|silicon}-supported-task-count) + * @phy_timer: phy startup timer + * @invalid_phy_mask: if an invalid_link_up notification is reported a bit for + * the phy index is set so further notifications are not + * made. Once the phy reports link up and is made part of a + * port then this bit is cleared. + + */ +struct isci_host { + struct sci_base_state_machine sm; + /* XXX can we time this externally */ + struct sci_timer timer; + /* XXX drop reference module params directly */ + struct sci_user_parameters user_parameters; + /* XXX no need to be a union */ + struct sci_oem_params oem_parameters; + struct sci_port_configuration_agent port_agent; + struct isci_remote_device *device_table[SCI_MAX_REMOTE_DEVICES]; + struct sci_remote_node_table available_remote_nodes; + struct sci_power_control power_control; + u8 io_request_sequence[SCI_MAX_IO_REQUESTS]; + struct scu_task_context *task_context_table; + dma_addr_t task_context_dma; + union scu_remote_node_context *remote_node_context_table; + u32 *completion_queue; + u32 completion_queue_get; + u32 logical_port_entries; + u32 remote_node_entries; + u32 task_context_entries; + struct sci_unsolicited_frame_control uf_control; + + /* phy startup */ + struct sci_timer phy_timer; + /* XXX kill */ + bool phy_startup_timer_pending; + u32 next_phy_to_start; + /* XXX convert to unsigned long and use bitops */ + u8 invalid_phy_mask; + + /* TODO attempt dynamic interrupt coalescing scheme */ + u16 interrupt_coalesce_number; + u32 interrupt_coalesce_timeout; + struct smu_registers __iomem *smu_registers; + struct scu_registers __iomem *scu_registers; + + u16 tci_head; + u16 tci_tail; + u16 tci_pool[SCI_MAX_IO_REQUESTS]; + + int id; /* unique within a given pci device */ + struct isci_phy phys[SCI_MAX_PHYS]; + struct isci_port ports[SCI_MAX_PORTS + 1]; /* includes dummy port */ + struct sas_ha_struct sas_ha; + + spinlock_t state_lock; + struct pci_dev *pdev; + enum isci_status status; + #define IHOST_START_PENDING 0 + #define IHOST_STOP_PENDING 1 + unsigned long flags; + wait_queue_head_t eventq; + struct Scsi_Host *shost; + struct tasklet_struct completion_tasklet; + struct list_head requests_to_complete; + struct list_head requests_to_errorback; + spinlock_t scic_lock; + struct isci_request *reqs[SCI_MAX_IO_REQUESTS]; + struct isci_remote_device devices[SCI_MAX_REMOTE_DEVICES]; +}; + +/** + * enum sci_controller_states - This enumeration depicts all the states + * for the common controller state machine. + */ +enum sci_controller_states { + /** + * Simply the initial state for the base controller state machine. + */ + SCIC_INITIAL = 0, + + /** + * This state indicates that the controller is reset. The memory for + * the controller is in it's initial state, but the controller requires + * initialization. + * This state is entered from the INITIAL state. + * This state is entered from the RESETTING state. + */ + SCIC_RESET, + + /** + * This state is typically an action state that indicates the controller + * is in the process of initialization. In this state no new IO operations + * are permitted. + * This state is entered from the RESET state. + */ + SCIC_INITIALIZING, + + /** + * This state indicates that the controller has been successfully + * initialized. In this state no new IO operations are permitted. + * This state is entered from the INITIALIZING state. + */ + SCIC_INITIALIZED, + + /** + * This state indicates the the controller is in the process of becoming + * ready (i.e. starting). In this state no new IO operations are permitted. + * This state is entered from the INITIALIZED state. + */ + SCIC_STARTING, + + /** + * This state indicates the controller is now ready. Thus, the user + * is able to perform IO operations on the controller. + * This state is entered from the STARTING state. + */ + SCIC_READY, + + /** + * This state is typically an action state that indicates the controller + * is in the process of resetting. Thus, the user is unable to perform + * IO operations on the controller. A reset is considered destructive in + * most cases. + * This state is entered from the READY state. + * This state is entered from the FAILED state. + * This state is entered from the STOPPED state. + */ + SCIC_RESETTING, + + /** + * This state indicates that the controller is in the process of stopping. + * In this state no new IO operations are permitted, but existing IO + * operations are allowed to complete. + * This state is entered from the READY state. + */ + SCIC_STOPPING, + + /** + * This state indicates that the controller has successfully been stopped. + * In this state no new IO operations are permitted. + * This state is entered from the STOPPING state. + */ + SCIC_STOPPED, + + /** + * This state indicates that the controller could not successfully be + * initialized. In this state no new IO operations are permitted. + * This state is entered from the INITIALIZING state. + * This state is entered from the STARTING state. + * This state is entered from the STOPPING state. + * This state is entered from the RESETTING state. + */ + SCIC_FAILED, +}; + +/** + * struct isci_pci_info - This class represents the pci function containing the + * controllers. Depending on PCI SKU, there could be up to 2 controllers in + * the PCI function. + */ +#define SCI_MAX_MSIX_INT (SCI_NUM_MSI_X_INT*SCI_MAX_CONTROLLERS) + +struct isci_pci_info { + struct msix_entry msix_entries[SCI_MAX_MSIX_INT]; + struct isci_host *hosts[SCI_MAX_CONTROLLERS]; + struct isci_orom *orom; +}; + +static inline struct isci_pci_info *to_pci_info(struct pci_dev *pdev) +{ + return pci_get_drvdata(pdev); +} + +#define for_each_isci_host(id, ihost, pdev) \ + for (id = 0, ihost = to_pci_info(pdev)->hosts[id]; \ + id < ARRAY_SIZE(to_pci_info(pdev)->hosts) && ihost; \ + ihost = to_pci_info(pdev)->hosts[++id]) + +static inline enum isci_status isci_host_get_state(struct isci_host *isci_host) +{ + return isci_host->status; +} + +static inline void isci_host_change_state(struct isci_host *isci_host, + enum isci_status status) +{ + unsigned long flags; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_host = %p, state = 0x%x", + __func__, + isci_host, + status); + spin_lock_irqsave(&isci_host->state_lock, flags); + isci_host->status = status; + spin_unlock_irqrestore(&isci_host->state_lock, flags); + +} + +static inline void wait_for_start(struct isci_host *ihost) +{ + wait_event(ihost->eventq, !test_bit(IHOST_START_PENDING, &ihost->flags)); +} + +static inline void wait_for_stop(struct isci_host *ihost) +{ + wait_event(ihost->eventq, !test_bit(IHOST_STOP_PENDING, &ihost->flags)); +} + +static inline void wait_for_device_start(struct isci_host *ihost, struct isci_remote_device *idev) +{ + wait_event(ihost->eventq, !test_bit(IDEV_START_PENDING, &idev->flags)); +} + +static inline void wait_for_device_stop(struct isci_host *ihost, struct isci_remote_device *idev) +{ + wait_event(ihost->eventq, !test_bit(IDEV_STOP_PENDING, &idev->flags)); +} + +static inline struct isci_host *dev_to_ihost(struct domain_device *dev) +{ + return dev->port->ha->lldd_ha; +} + +/* we always use protocol engine group zero */ +#define ISCI_PEG 0 + +/* see sci_controller_io_tag_allocate|free for how seq and tci are built */ +#define ISCI_TAG(seq, tci) (((u16) (seq)) << 12 | tci) + +/* these are returned by the hardware, so sanitize them */ +#define ISCI_TAG_SEQ(tag) (((tag) >> 12) & (SCI_MAX_SEQ-1)) +#define ISCI_TAG_TCI(tag) ((tag) & (SCI_MAX_IO_REQUESTS-1)) + +/* expander attached sata devices require 3 rnc slots */ +static inline int sci_remote_device_node_count(struct isci_remote_device *idev) +{ + struct domain_device *dev = idev->domain_dev; + + if ((dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) && + !idev->is_direct_attached) + return SCU_STP_REMOTE_NODE_COUNT; + return SCU_SSP_REMOTE_NODE_COUNT; +} + +/** + * sci_controller_clear_invalid_phy() - + * + * This macro will clear the bit in the invalid phy mask for this controller + * object. This is used to control messages reported for invalid link up + * notifications. + */ +#define sci_controller_clear_invalid_phy(controller, phy) \ + ((controller)->invalid_phy_mask &= ~(1 << (phy)->phy_index)) + +static inline struct device *sciphy_to_dev(struct isci_phy *iphy) +{ + + if (!iphy || !iphy->isci_port || !iphy->isci_port->isci_host) + return NULL; + + return &iphy->isci_port->isci_host->pdev->dev; +} + +static inline struct device *sciport_to_dev(struct isci_port *iport) +{ + + if (!iport || !iport->isci_host) + return NULL; + + return &iport->isci_host->pdev->dev; +} + +static inline struct device *scirdev_to_dev(struct isci_remote_device *idev) +{ + if (!idev || !idev->isci_port || !idev->isci_port->isci_host) + return NULL; + + return &idev->isci_port->isci_host->pdev->dev; +} + +static inline bool is_a2(struct pci_dev *pdev) +{ + if (pdev->revision < 4) + return true; + return false; +} + +static inline bool is_b0(struct pci_dev *pdev) +{ + if (pdev->revision == 4) + return true; + return false; +} + +static inline bool is_c0(struct pci_dev *pdev) +{ + if (pdev->revision >= 5) + return true; + return false; +} + +void sci_controller_post_request(struct isci_host *ihost, + u32 request); +void sci_controller_release_frame(struct isci_host *ihost, + u32 frame_index); +void sci_controller_copy_sata_response(void *response_buffer, + void *frame_header, + void *frame_buffer); +enum sci_status sci_controller_allocate_remote_node_context(struct isci_host *ihost, + struct isci_remote_device *idev, + u16 *node_id); +void sci_controller_free_remote_node_context( + struct isci_host *ihost, + struct isci_remote_device *idev, + u16 node_id); + +struct isci_request *sci_request_by_tag(struct isci_host *ihost, + u16 io_tag); + +void sci_controller_power_control_queue_insert( + struct isci_host *ihost, + struct isci_phy *iphy); + +void sci_controller_power_control_queue_remove( + struct isci_host *ihost, + struct isci_phy *iphy); + +void sci_controller_link_up( + struct isci_host *ihost, + struct isci_port *iport, + struct isci_phy *iphy); + +void sci_controller_link_down( + struct isci_host *ihost, + struct isci_port *iport, + struct isci_phy *iphy); + +void sci_controller_remote_device_stopped( + struct isci_host *ihost, + struct isci_remote_device *idev); + +void sci_controller_copy_task_context( + struct isci_host *ihost, + struct isci_request *ireq); + +void sci_controller_register_setup(struct isci_host *ihost); + +enum sci_status sci_controller_continue_io(struct isci_request *ireq); +int isci_host_scan_finished(struct Scsi_Host *, unsigned long); +void isci_host_scan_start(struct Scsi_Host *); +u16 isci_alloc_tag(struct isci_host *ihost); +enum sci_status isci_free_tag(struct isci_host *ihost, u16 io_tag); +void isci_tci_free(struct isci_host *ihost, u16 tci); + +int isci_host_init(struct isci_host *); + +void isci_host_init_controller_names( + struct isci_host *isci_host, + unsigned int controller_idx); + +void isci_host_deinit( + struct isci_host *); + +void isci_host_port_link_up( + struct isci_host *, + struct isci_port *, + struct isci_phy *); +int isci_host_dev_found(struct domain_device *); + +void isci_host_remote_device_start_complete( + struct isci_host *, + struct isci_remote_device *, + enum sci_status); + +void sci_controller_disable_interrupts( + struct isci_host *ihost); + +enum sci_status sci_controller_start_io( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_task_status sci_controller_start_task( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_status sci_controller_terminate_request( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_status sci_controller_complete_io( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +void sci_port_configuration_agent_construct( + struct sci_port_configuration_agent *port_agent); + +enum sci_status sci_port_configuration_agent_initialize( + struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent); +#endif diff --git a/drivers/scsi/isci/init.c b/drivers/scsi/isci/init.c new file mode 100644 index 0000000..61e0d09 --- /dev/null +++ b/drivers/scsi/isci/init.c @@ -0,0 +1,565 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/firmware.h> +#include <linux/efi.h> +#include <asm/string.h> +#include "isci.h" +#include "task.h" +#include "probe_roms.h" + +static struct scsi_transport_template *isci_transport_template; + +static DEFINE_PCI_DEVICE_TABLE(isci_id_table) = { + { PCI_VDEVICE(INTEL, 0x1D61),}, + { PCI_VDEVICE(INTEL, 0x1D63),}, + { PCI_VDEVICE(INTEL, 0x1D65),}, + { PCI_VDEVICE(INTEL, 0x1D67),}, + { PCI_VDEVICE(INTEL, 0x1D69),}, + { PCI_VDEVICE(INTEL, 0x1D6B),}, + { PCI_VDEVICE(INTEL, 0x1D60),}, + { PCI_VDEVICE(INTEL, 0x1D62),}, + { PCI_VDEVICE(INTEL, 0x1D64),}, + { PCI_VDEVICE(INTEL, 0x1D66),}, + { PCI_VDEVICE(INTEL, 0x1D68),}, + { PCI_VDEVICE(INTEL, 0x1D6A),}, + {} +}; + +MODULE_DEVICE_TABLE(pci, isci_id_table); + +/* linux isci specific settings */ + +unsigned char no_outbound_task_to = 20; +module_param(no_outbound_task_to, byte, 0); +MODULE_PARM_DESC(no_outbound_task_to, "No Outbound Task Timeout (1us incr)"); + +u16 ssp_max_occ_to = 20; +module_param(ssp_max_occ_to, ushort, 0); +MODULE_PARM_DESC(ssp_max_occ_to, "SSP Max occupancy timeout (100us incr)"); + +u16 stp_max_occ_to = 5; +module_param(stp_max_occ_to, ushort, 0); +MODULE_PARM_DESC(stp_max_occ_to, "STP Max occupancy timeout (100us incr)"); + +u16 ssp_inactive_to = 5; +module_param(ssp_inactive_to, ushort, 0); +MODULE_PARM_DESC(ssp_inactive_to, "SSP inactivity timeout (100us incr)"); + +u16 stp_inactive_to = 5; +module_param(stp_inactive_to, ushort, 0); +MODULE_PARM_DESC(stp_inactive_to, "STP inactivity timeout (100us incr)"); + +unsigned char phy_gen = 3; +module_param(phy_gen, byte, 0); +MODULE_PARM_DESC(phy_gen, "PHY generation (1: 1.5Gbps 2: 3.0Gbps 3: 6.0Gbps)"); + +unsigned char max_concurr_spinup = 1; +module_param(max_concurr_spinup, byte, 0); +MODULE_PARM_DESC(max_concurr_spinup, "Max concurrent device spinup"); + +static struct scsi_host_template isci_sht = { + + .module = THIS_MODULE, + .name = DRV_NAME, + .proc_name = DRV_NAME, + .queuecommand = sas_queuecommand, + .target_alloc = sas_target_alloc, + .slave_configure = sas_slave_configure, + .slave_destroy = sas_slave_destroy, + .scan_finished = isci_host_scan_finished, + .scan_start = isci_host_scan_start, + .change_queue_depth = sas_change_queue_depth, + .change_queue_type = sas_change_queue_type, + .bios_param = sas_bios_param, + .can_queue = ISCI_CAN_QUEUE_VAL, + .cmd_per_lun = 1, + .this_id = -1, + .sg_tablesize = SG_ALL, + .max_sectors = SCSI_DEFAULT_MAX_SECTORS, + .use_clustering = ENABLE_CLUSTERING, + .eh_device_reset_handler = sas_eh_device_reset_handler, + .eh_bus_reset_handler = isci_bus_reset_handler, + .slave_alloc = sas_slave_alloc, + .target_destroy = sas_target_destroy, + .ioctl = sas_ioctl, +}; + +static struct sas_domain_function_template isci_transport_ops = { + + /* The class calls these to notify the LLDD of an event. */ + .lldd_port_formed = isci_port_formed, + .lldd_port_deformed = isci_port_deformed, + + /* The class calls these when a device is found or gone. */ + .lldd_dev_found = isci_remote_device_found, + .lldd_dev_gone = isci_remote_device_gone, + + .lldd_execute_task = isci_task_execute_task, + /* Task Management Functions. Must be called from process context. */ + .lldd_abort_task = isci_task_abort_task, + .lldd_abort_task_set = isci_task_abort_task_set, + .lldd_clear_aca = isci_task_clear_aca, + .lldd_clear_task_set = isci_task_clear_task_set, + .lldd_I_T_nexus_reset = isci_task_I_T_nexus_reset, + .lldd_lu_reset = isci_task_lu_reset, + .lldd_query_task = isci_task_query_task, + + /* Port and Adapter management */ + .lldd_clear_nexus_port = isci_task_clear_nexus_port, + .lldd_clear_nexus_ha = isci_task_clear_nexus_ha, + + /* Phy management */ + .lldd_control_phy = isci_phy_control, +}; + + +/****************************************************************************** +* P R O T E C T E D M E T H O D S +******************************************************************************/ + + + +/** + * isci_register_sas_ha() - This method initializes various lldd + * specific members of the sas_ha struct and calls the libsas + * sas_register_ha() function. + * @isci_host: This parameter specifies the lldd specific wrapper for the + * libsas sas_ha struct. + * + * This method returns an error code indicating sucess or failure. The user + * should check for possible memory allocation error return otherwise, a zero + * indicates success. + */ +static int isci_register_sas_ha(struct isci_host *isci_host) +{ + int i; + struct sas_ha_struct *sas_ha = &(isci_host->sas_ha); + struct asd_sas_phy **sas_phys; + struct asd_sas_port **sas_ports; + + sas_phys = devm_kzalloc(&isci_host->pdev->dev, + SCI_MAX_PHYS * sizeof(void *), + GFP_KERNEL); + if (!sas_phys) + return -ENOMEM; + + sas_ports = devm_kzalloc(&isci_host->pdev->dev, + SCI_MAX_PORTS * sizeof(void *), + GFP_KERNEL); + if (!sas_ports) + return -ENOMEM; + + /*----------------- Libsas Initialization Stuff---------------------- + * Set various fields in the sas_ha struct: + */ + + sas_ha->sas_ha_name = DRV_NAME; + sas_ha->lldd_module = THIS_MODULE; + sas_ha->sas_addr = &isci_host->phys[0].sas_addr[0]; + + /* set the array of phy and port structs. */ + for (i = 0; i < SCI_MAX_PHYS; i++) { + sas_phys[i] = &isci_host->phys[i].sas_phy; + sas_ports[i] = &isci_host->ports[i].sas_port; + } + + sas_ha->sas_phy = sas_phys; + sas_ha->sas_port = sas_ports; + sas_ha->num_phys = SCI_MAX_PHYS; + + sas_ha->lldd_queue_size = ISCI_CAN_QUEUE_VAL; + sas_ha->lldd_max_execute_num = 1; + sas_ha->strict_wide_ports = 1; + + sas_register_ha(sas_ha); + + return 0; +} + +static ssize_t isci_show_id(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct Scsi_Host *shost = container_of(dev, typeof(*shost), shost_dev); + struct sas_ha_struct *sas_ha = SHOST_TO_SAS_HA(shost); + struct isci_host *ihost = container_of(sas_ha, typeof(*ihost), sas_ha); + + return snprintf(buf, PAGE_SIZE, "%d\n", ihost->id); +} + +static DEVICE_ATTR(isci_id, S_IRUGO, isci_show_id, NULL); + +static void isci_unregister(struct isci_host *isci_host) +{ + struct Scsi_Host *shost; + + if (!isci_host) + return; + + shost = isci_host->shost; + device_remove_file(&shost->shost_dev, &dev_attr_isci_id); + + sas_unregister_ha(&isci_host->sas_ha); + + sas_remove_host(isci_host->shost); + scsi_remove_host(isci_host->shost); + scsi_host_put(isci_host->shost); +} + +static int __devinit isci_pci_init(struct pci_dev *pdev) +{ + int err, bar_num, bar_mask = 0; + void __iomem * const *iomap; + + err = pcim_enable_device(pdev); + if (err) { + dev_err(&pdev->dev, + "failed enable PCI device %s!\n", + pci_name(pdev)); + return err; + } + + for (bar_num = 0; bar_num < SCI_PCI_BAR_COUNT; bar_num++) + bar_mask |= 1 << (bar_num * 2); + + err = pcim_iomap_regions(pdev, bar_mask, DRV_NAME); + if (err) + return err; + + iomap = pcim_iomap_table(pdev); + if (!iomap) + return -ENOMEM; + + pci_set_master(pdev); + + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (err) { + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (err) + return err; + } + + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (err) { + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (err) + return err; + } + + return 0; +} + +static int num_controllers(struct pci_dev *pdev) +{ + /* bar size alone can tell us if we are running with a dual controller + * part, no need to trust revision ids that might be under broken firmware + * control + */ + resource_size_t scu_bar_size = pci_resource_len(pdev, SCI_SCU_BAR*2); + resource_size_t smu_bar_size = pci_resource_len(pdev, SCI_SMU_BAR*2); + + if (scu_bar_size >= SCI_SCU_BAR_SIZE*SCI_MAX_CONTROLLERS && + smu_bar_size >= SCI_SMU_BAR_SIZE*SCI_MAX_CONTROLLERS) + return SCI_MAX_CONTROLLERS; + else + return 1; +} + +static int isci_setup_interrupts(struct pci_dev *pdev) +{ + int err, i, num_msix; + struct isci_host *ihost; + struct isci_pci_info *pci_info = to_pci_info(pdev); + + /* + * Determine the number of vectors associated with this + * PCI function. + */ + num_msix = num_controllers(pdev) * SCI_NUM_MSI_X_INT; + + for (i = 0; i < num_msix; i++) + pci_info->msix_entries[i].entry = i; + + err = pci_enable_msix(pdev, pci_info->msix_entries, num_msix); + if (err) + goto intx; + + for (i = 0; i < num_msix; i++) { + int id = i / SCI_NUM_MSI_X_INT; + struct msix_entry *msix = &pci_info->msix_entries[i]; + irq_handler_t isr; + + ihost = pci_info->hosts[id]; + /* odd numbered vectors are error interrupts */ + if (i & 1) + isr = isci_error_isr; + else + isr = isci_msix_isr; + + err = devm_request_irq(&pdev->dev, msix->vector, isr, 0, + DRV_NAME"-msix", ihost); + if (!err) + continue; + + dev_info(&pdev->dev, "msix setup failed falling back to intx\n"); + while (i--) { + id = i / SCI_NUM_MSI_X_INT; + ihost = pci_info->hosts[id]; + msix = &pci_info->msix_entries[i]; + devm_free_irq(&pdev->dev, msix->vector, ihost); + } + pci_disable_msix(pdev); + goto intx; + } + return 0; + + intx: + for_each_isci_host(i, ihost, pdev) { + err = devm_request_irq(&pdev->dev, pdev->irq, isci_intx_isr, + IRQF_SHARED, DRV_NAME"-intx", ihost); + if (err) + break; + } + return err; +} + +static struct isci_host *isci_host_alloc(struct pci_dev *pdev, int id) +{ + struct isci_host *isci_host; + struct Scsi_Host *shost; + int err; + + isci_host = devm_kzalloc(&pdev->dev, sizeof(*isci_host), GFP_KERNEL); + if (!isci_host) + return NULL; + + isci_host->pdev = pdev; + isci_host->id = id; + + shost = scsi_host_alloc(&isci_sht, sizeof(void *)); + if (!shost) + return NULL; + isci_host->shost = shost; + + err = isci_host_init(isci_host); + if (err) + goto err_shost; + + SHOST_TO_SAS_HA(shost) = &isci_host->sas_ha; + isci_host->sas_ha.core.shost = shost; + shost->transportt = isci_transport_template; + + shost->max_id = ~0; + shost->max_lun = ~0; + shost->max_cmd_len = MAX_COMMAND_SIZE; + + err = scsi_add_host(shost, &pdev->dev); + if (err) + goto err_shost; + + err = isci_register_sas_ha(isci_host); + if (err) + goto err_shost_remove; + + err = device_create_file(&shost->shost_dev, &dev_attr_isci_id); + if (err) + goto err_unregister_ha; + + return isci_host; + + err_unregister_ha: + sas_unregister_ha(&(isci_host->sas_ha)); + err_shost_remove: + scsi_remove_host(shost); + err_shost: + scsi_host_put(shost); + + return NULL; +} + +static int __devinit isci_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct isci_pci_info *pci_info; + int err, i; + struct isci_host *isci_host; + const struct firmware *fw = NULL; + struct isci_orom *orom = NULL; + char *source = "(platform)"; + + dev_info(&pdev->dev, "driver configured for rev: %d silicon\n", + pdev->revision); + + pci_info = devm_kzalloc(&pdev->dev, sizeof(*pci_info), GFP_KERNEL); + if (!pci_info) + return -ENOMEM; + pci_set_drvdata(pdev, pci_info); + + if (efi_enabled) + orom = isci_get_efi_var(pdev); + + if (!orom) + orom = isci_request_oprom(pdev); + + for (i = 0; orom && i < ARRAY_SIZE(orom->ctrl); i++) { + if (sci_oem_parameters_validate(&orom->ctrl[i])) { + dev_warn(&pdev->dev, + "[%d]: invalid oem parameters detected, falling back to firmware\n", i); + devm_kfree(&pdev->dev, orom); + orom = NULL; + break; + } + } + + if (!orom) { + source = "(firmware)"; + orom = isci_request_firmware(pdev, fw); + if (!orom) { + /* TODO convert this to WARN_TAINT_ONCE once the + * orom/efi parameter support is widely available + */ + dev_warn(&pdev->dev, + "Loading user firmware failed, using default " + "values\n"); + dev_warn(&pdev->dev, + "Default OEM configuration being used: 4 " + "narrow ports, and default SAS Addresses\n"); + } + } + + if (orom) + dev_info(&pdev->dev, + "OEM SAS parameters (version: %u.%u) loaded %s\n", + (orom->hdr.version & 0xf0) >> 4, + (orom->hdr.version & 0xf), source); + + pci_info->orom = orom; + + err = isci_pci_init(pdev); + if (err) + return err; + + for (i = 0; i < num_controllers(pdev); i++) { + struct isci_host *h = isci_host_alloc(pdev, i); + + if (!h) { + err = -ENOMEM; + goto err_host_alloc; + } + pci_info->hosts[i] = h; + } + + err = isci_setup_interrupts(pdev); + if (err) + goto err_host_alloc; + + for_each_isci_host(i, isci_host, pdev) + scsi_scan_host(isci_host->shost); + + return 0; + + err_host_alloc: + for_each_isci_host(i, isci_host, pdev) + isci_unregister(isci_host); + return err; +} + +static void __devexit isci_pci_remove(struct pci_dev *pdev) +{ + struct isci_host *ihost; + int i; + + for_each_isci_host(i, ihost, pdev) { + isci_unregister(ihost); + isci_host_deinit(ihost); + sci_controller_disable_interrupts(ihost); + } +} + +static struct pci_driver isci_pci_driver = { + .name = DRV_NAME, + .id_table = isci_id_table, + .probe = isci_pci_probe, + .remove = __devexit_p(isci_pci_remove), +}; + +static __init int isci_init(void) +{ + int err; + + pr_info("%s: Intel(R) C600 SAS Controller Driver\n", DRV_NAME); + + isci_transport_template = sas_domain_attach_transport(&isci_transport_ops); + if (!isci_transport_template) + return -ENOMEM; + + err = pci_register_driver(&isci_pci_driver); + if (err) + sas_release_transport(isci_transport_template); + + return err; +} + +static __exit void isci_exit(void) +{ + pci_unregister_driver(&isci_pci_driver); + sas_release_transport(isci_transport_template); +} + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_FIRMWARE(ISCI_FW_NAME); +module_init(isci_init); +module_exit(isci_exit); diff --git a/drivers/scsi/isci/isci.h b/drivers/scsi/isci/isci.h new file mode 100644 index 0000000..d1de633 --- /dev/null +++ b/drivers/scsi/isci/isci.h @@ -0,0 +1,538 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __ISCI_H__ +#define __ISCI_H__ + +#include <linux/interrupt.h> +#include <linux/types.h> + +#define DRV_NAME "isci" +#define SCI_PCI_BAR_COUNT 2 +#define SCI_NUM_MSI_X_INT 2 +#define SCI_SMU_BAR 0 +#define SCI_SMU_BAR_SIZE (16*1024) +#define SCI_SCU_BAR 1 +#define SCI_SCU_BAR_SIZE (4*1024*1024) +#define SCI_IO_SPACE_BAR0 2 +#define SCI_IO_SPACE_BAR1 3 +#define ISCI_CAN_QUEUE_VAL 250 /* < SCI_MAX_IO_REQUESTS ? */ +#define SCIC_CONTROLLER_STOP_TIMEOUT 5000 + +#define SCI_CONTROLLER_INVALID_IO_TAG 0xFFFF + +#define SCI_MAX_PHYS (4UL) +#define SCI_MAX_PORTS SCI_MAX_PHYS +#define SCI_MAX_SMP_PHYS (384) /* not silicon constrained */ +#define SCI_MAX_REMOTE_DEVICES (256UL) +#define SCI_MAX_IO_REQUESTS (256UL) +#define SCI_MAX_SEQ (16) +#define SCI_MAX_MSIX_MESSAGES (2) +#define SCI_MAX_SCATTER_GATHER_ELEMENTS 130 /* not silicon constrained */ +#define SCI_MAX_CONTROLLERS 2 +#define SCI_MAX_DOMAINS SCI_MAX_PORTS + +#define SCU_MAX_CRITICAL_NOTIFICATIONS (384) +#define SCU_MAX_EVENTS_SHIFT (7) +#define SCU_MAX_EVENTS (1 << SCU_MAX_EVENTS_SHIFT) +#define SCU_MAX_UNSOLICITED_FRAMES (128) +#define SCU_MAX_COMPLETION_QUEUE_SCRATCH (128) +#define SCU_MAX_COMPLETION_QUEUE_ENTRIES (SCU_MAX_CRITICAL_NOTIFICATIONS \ + + SCU_MAX_EVENTS \ + + SCU_MAX_UNSOLICITED_FRAMES \ + + SCI_MAX_IO_REQUESTS \ + + SCU_MAX_COMPLETION_QUEUE_SCRATCH) +#define SCU_MAX_COMPLETION_QUEUE_SHIFT (ilog2(SCU_MAX_COMPLETION_QUEUE_ENTRIES)) + +#define SCU_ABSOLUTE_MAX_UNSOLICITED_FRAMES (4096) +#define SCU_UNSOLICITED_FRAME_BUFFER_SIZE (1024) +#define SCU_INVALID_FRAME_INDEX (0xFFFF) + +#define SCU_IO_REQUEST_MAX_SGE_SIZE (0x00FFFFFF) +#define SCU_IO_REQUEST_MAX_TRANSFER_LENGTH (0x00FFFFFF) + +static inline void check_sizes(void) +{ + BUILD_BUG_ON_NOT_POWER_OF_2(SCU_MAX_EVENTS); + BUILD_BUG_ON(SCU_MAX_UNSOLICITED_FRAMES <= 8); + BUILD_BUG_ON_NOT_POWER_OF_2(SCU_MAX_UNSOLICITED_FRAMES); + BUILD_BUG_ON_NOT_POWER_OF_2(SCU_MAX_COMPLETION_QUEUE_ENTRIES); + BUILD_BUG_ON(SCU_MAX_UNSOLICITED_FRAMES > SCU_ABSOLUTE_MAX_UNSOLICITED_FRAMES); + BUILD_BUG_ON_NOT_POWER_OF_2(SCI_MAX_IO_REQUESTS); + BUILD_BUG_ON_NOT_POWER_OF_2(SCI_MAX_SEQ); +} + +/** + * enum sci_status - This is the general return status enumeration for non-IO, + * non-task management related SCI interface methods. + * + * + */ +enum sci_status { + /** + * This member indicates successful completion. + */ + SCI_SUCCESS = 0, + + /** + * This value indicates that the calling method completed successfully, + * but that the IO may have completed before having it's start method + * invoked. This occurs during SAT translation for requests that do + * not require an IO to the target or for any other requests that may + * be completed without having to submit IO. + */ + SCI_SUCCESS_IO_COMPLETE_BEFORE_START, + + /** + * This Value indicates that the SCU hardware returned an early response + * because the io request specified more data than is returned by the + * target device (mode pages, inquiry data, etc.). The completion routine + * will handle this case to get the actual number of bytes transferred. + */ + SCI_SUCCESS_IO_DONE_EARLY, + + /** + * This member indicates that the object for which a state change is + * being requested is already in said state. + */ + SCI_WARNING_ALREADY_IN_STATE, + + /** + * This member indicates interrupt coalescence timer may cause SAS + * specification compliance issues (i.e. SMP target mode response + * frames must be returned within 1.9 milliseconds). + */ + SCI_WARNING_TIMER_CONFLICT, + + /** + * This field indicates a sequence of action is not completed yet. Mostly, + * this status is used when multiple ATA commands are needed in a SATI translation. + */ + SCI_WARNING_SEQUENCE_INCOMPLETE, + + /** + * This member indicates that there was a general failure. + */ + SCI_FAILURE, + + /** + * This member indicates that the SCI implementation is unable to complete + * an operation due to a critical flaw the prevents any further operation + * (i.e. an invalid pointer). + */ + SCI_FATAL_ERROR, + + /** + * This member indicates the calling function failed, because the state + * of the controller is in a state that prevents successful completion. + */ + SCI_FAILURE_INVALID_STATE, + + /** + * This member indicates the calling function failed, because there is + * insufficient resources/memory to complete the request. + */ + SCI_FAILURE_INSUFFICIENT_RESOURCES, + + /** + * This member indicates the calling function failed, because the + * controller object required for the operation can't be located. + */ + SCI_FAILURE_CONTROLLER_NOT_FOUND, + + /** + * This member indicates the calling function failed, because the + * discovered controller type is not supported by the library. + */ + SCI_FAILURE_UNSUPPORTED_CONTROLLER_TYPE, + + /** + * This member indicates the calling function failed, because the + * requested initialization data version isn't supported. + */ + SCI_FAILURE_UNSUPPORTED_INIT_DATA_VERSION, + + /** + * This member indicates the calling function failed, because the + * requested configuration of SAS Phys into SAS Ports is not supported. + */ + SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION, + + /** + * This member indicates the calling function failed, because the + * requested protocol is not supported by the remote device, port, + * or controller. + */ + SCI_FAILURE_UNSUPPORTED_PROTOCOL, + + /** + * This member indicates the calling function failed, because the + * requested information type is not supported by the SCI implementation. + */ + SCI_FAILURE_UNSUPPORTED_INFORMATION_TYPE, + + /** + * This member indicates the calling function failed, because the + * device already exists. + */ + SCI_FAILURE_DEVICE_EXISTS, + + /** + * This member indicates the calling function failed, because adding + * a phy to the object is not possible. + */ + SCI_FAILURE_ADDING_PHY_UNSUPPORTED, + + /** + * This member indicates the calling function failed, because the + * requested information type is not supported by the SCI implementation. + */ + SCI_FAILURE_UNSUPPORTED_INFORMATION_FIELD, + + /** + * This member indicates the calling function failed, because the SCI + * implementation does not support the supplied time limit. + */ + SCI_FAILURE_UNSUPPORTED_TIME_LIMIT, + + /** + * This member indicates the calling method failed, because the SCI + * implementation does not contain the specified Phy. + */ + SCI_FAILURE_INVALID_PHY, + + /** + * This member indicates the calling method failed, because the SCI + * implementation does not contain the specified Port. + */ + SCI_FAILURE_INVALID_PORT, + + /** + * This member indicates the calling method was partly successful + * The port was reset but not all phys in port are operational + */ + SCI_FAILURE_RESET_PORT_PARTIAL_SUCCESS, + + /** + * This member indicates that calling method failed + * The port reset did not complete because none of the phys are operational + */ + SCI_FAILURE_RESET_PORT_FAILURE, + + /** + * This member indicates the calling method failed, because the SCI + * implementation does not contain the specified remote device. + */ + SCI_FAILURE_INVALID_REMOTE_DEVICE, + + /** + * This member indicates the calling method failed, because the remote + * device is in a bad state and requires a reset. + */ + SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED, + + /** + * This member indicates the calling method failed, because the SCI + * implementation does not contain or support the specified IO tag. + */ + SCI_FAILURE_INVALID_IO_TAG, + + /** + * This member indicates that the operation failed and the user should + * check the response data associated with the IO. + */ + SCI_FAILURE_IO_RESPONSE_VALID, + + /** + * This member indicates that the operation failed, the failure is + * controller implementation specific, and the response data associated + * with the request is not valid. You can query for the controller + * specific error information via sci_controller_get_request_status() + */ + SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR, + + /** + * This member indicated that the operation failed because the + * user requested this IO to be terminated. + */ + SCI_FAILURE_IO_TERMINATED, + + /** + * This member indicates that the operation failed and the associated + * request requires a SCSI abort task to be sent to the target. + */ + SCI_FAILURE_IO_REQUIRES_SCSI_ABORT, + + /** + * This member indicates that the operation failed because the supplied + * device could not be located. + */ + SCI_FAILURE_DEVICE_NOT_FOUND, + + /** + * This member indicates that the operation failed because the + * objects association is required and is not correctly set. + */ + SCI_FAILURE_INVALID_ASSOCIATION, + + /** + * This member indicates that the operation failed, because a timeout + * occurred. + */ + SCI_FAILURE_TIMEOUT, + + /** + * This member indicates that the operation failed, because the user + * specified a value that is either invalid or not supported. + */ + SCI_FAILURE_INVALID_PARAMETER_VALUE, + + /** + * This value indicates that the operation failed, because the number + * of messages (MSI-X) is not supported. + */ + SCI_FAILURE_UNSUPPORTED_MESSAGE_COUNT, + + /** + * This value indicates that the method failed due to a lack of + * available NCQ tags. + */ + SCI_FAILURE_NO_NCQ_TAG_AVAILABLE, + + /** + * This value indicates that a protocol violation has occurred on the + * link. + */ + SCI_FAILURE_PROTOCOL_VIOLATION, + + /** + * This value indicates a failure condition that retry may help to clear. + */ + SCI_FAILURE_RETRY_REQUIRED, + + /** + * This field indicates the retry limit was reached when a retry is attempted + */ + SCI_FAILURE_RETRY_LIMIT_REACHED, + + /** + * This member indicates the calling method was partly successful. + * Mostly, this status is used when a LUN_RESET issued to an expander attached + * STP device in READY NCQ substate needs to have RNC suspended/resumed + * before posting TC. + */ + SCI_FAILURE_RESET_DEVICE_PARTIAL_SUCCESS, + + /** + * This field indicates an illegal phy connection based on the routing attribute + * of both expander phy attached to each other. + */ + SCI_FAILURE_ILLEGAL_ROUTING_ATTRIBUTE_CONFIGURATION, + + /** + * This field indicates a CONFIG ROUTE INFO command has a response with function result + * INDEX DOES NOT EXIST, usually means exceeding max route index. + */ + SCI_FAILURE_EXCEED_MAX_ROUTE_INDEX, + + /** + * This value indicates that an unsupported PCI device ID has been + * specified. This indicates that attempts to invoke + * sci_library_allocate_controller() will fail. + */ + SCI_FAILURE_UNSUPPORTED_PCI_DEVICE_ID + +}; + +/** + * enum sci_io_status - This enumeration depicts all of the possible IO + * completion status values. Each value in this enumeration maps directly + * to a value in the enum sci_status enumeration. Please refer to that + * enumeration for detailed comments concerning what the status represents. + * + * Add the API to retrieve the SCU status from the core. Check to see that the + * following status are properly handled: - SCI_IO_FAILURE_UNSUPPORTED_PROTOCOL + * - SCI_IO_FAILURE_INVALID_IO_TAG + */ +enum sci_io_status { + SCI_IO_SUCCESS = SCI_SUCCESS, + SCI_IO_FAILURE = SCI_FAILURE, + SCI_IO_SUCCESS_COMPLETE_BEFORE_START = SCI_SUCCESS_IO_COMPLETE_BEFORE_START, + SCI_IO_SUCCESS_IO_DONE_EARLY = SCI_SUCCESS_IO_DONE_EARLY, + SCI_IO_FAILURE_INVALID_STATE = SCI_FAILURE_INVALID_STATE, + SCI_IO_FAILURE_INSUFFICIENT_RESOURCES = SCI_FAILURE_INSUFFICIENT_RESOURCES, + SCI_IO_FAILURE_UNSUPPORTED_PROTOCOL = SCI_FAILURE_UNSUPPORTED_PROTOCOL, + SCI_IO_FAILURE_RESPONSE_VALID = SCI_FAILURE_IO_RESPONSE_VALID, + SCI_IO_FAILURE_CONTROLLER_SPECIFIC_ERR = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR, + SCI_IO_FAILURE_TERMINATED = SCI_FAILURE_IO_TERMINATED, + SCI_IO_FAILURE_REQUIRES_SCSI_ABORT = SCI_FAILURE_IO_REQUIRES_SCSI_ABORT, + SCI_IO_FAILURE_INVALID_PARAMETER_VALUE = SCI_FAILURE_INVALID_PARAMETER_VALUE, + SCI_IO_FAILURE_NO_NCQ_TAG_AVAILABLE = SCI_FAILURE_NO_NCQ_TAG_AVAILABLE, + SCI_IO_FAILURE_PROTOCOL_VIOLATION = SCI_FAILURE_PROTOCOL_VIOLATION, + + SCI_IO_FAILURE_REMOTE_DEVICE_RESET_REQUIRED = SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED, + + SCI_IO_FAILURE_RETRY_REQUIRED = SCI_FAILURE_RETRY_REQUIRED, + SCI_IO_FAILURE_RETRY_LIMIT_REACHED = SCI_FAILURE_RETRY_LIMIT_REACHED, + SCI_IO_FAILURE_INVALID_REMOTE_DEVICE = SCI_FAILURE_INVALID_REMOTE_DEVICE +}; + +/** + * enum sci_task_status - This enumeration depicts all of the possible task + * completion status values. Each value in this enumeration maps directly + * to a value in the enum sci_status enumeration. Please refer to that + * enumeration for detailed comments concerning what the status represents. + * + * Check to see that the following status are properly handled: + */ +enum sci_task_status { + SCI_TASK_SUCCESS = SCI_SUCCESS, + SCI_TASK_FAILURE = SCI_FAILURE, + SCI_TASK_FAILURE_INVALID_STATE = SCI_FAILURE_INVALID_STATE, + SCI_TASK_FAILURE_INSUFFICIENT_RESOURCES = SCI_FAILURE_INSUFFICIENT_RESOURCES, + SCI_TASK_FAILURE_UNSUPPORTED_PROTOCOL = SCI_FAILURE_UNSUPPORTED_PROTOCOL, + SCI_TASK_FAILURE_INVALID_TAG = SCI_FAILURE_INVALID_IO_TAG, + SCI_TASK_FAILURE_RESPONSE_VALID = SCI_FAILURE_IO_RESPONSE_VALID, + SCI_TASK_FAILURE_CONTROLLER_SPECIFIC_ERR = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR, + SCI_TASK_FAILURE_TERMINATED = SCI_FAILURE_IO_TERMINATED, + SCI_TASK_FAILURE_INVALID_PARAMETER_VALUE = SCI_FAILURE_INVALID_PARAMETER_VALUE, + + SCI_TASK_FAILURE_REMOTE_DEVICE_RESET_REQUIRED = SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED, + SCI_TASK_FAILURE_RESET_DEVICE_PARTIAL_SUCCESS = SCI_FAILURE_RESET_DEVICE_PARTIAL_SUCCESS + +}; + +/** + * sci_swab32_cpy - convert between scsi and scu-hardware byte format + * @dest: receive the 4-byte endian swapped version of src + * @src: word aligned source buffer + * + * scu hardware handles SSP/SMP control, response, and unidentified + * frames in "big endian dword" order. Regardless of host endian this + * is always a swab32()-per-dword conversion of the standard definition, + * i.e. single byte fields swapped and multi-byte fields in little- + * endian + */ +static inline void sci_swab32_cpy(void *_dest, void *_src, ssize_t word_cnt) +{ + u32 *dest = _dest, *src = _src; + + while (--word_cnt >= 0) + dest[word_cnt] = swab32(src[word_cnt]); +} + +extern unsigned char no_outbound_task_to; +extern u16 ssp_max_occ_to; +extern u16 stp_max_occ_to; +extern u16 ssp_inactive_to; +extern u16 stp_inactive_to; +extern unsigned char phy_gen; +extern unsigned char max_concurr_spinup; + +irqreturn_t isci_msix_isr(int vec, void *data); +irqreturn_t isci_intx_isr(int vec, void *data); +irqreturn_t isci_error_isr(int vec, void *data); + +/* + * Each timer is associated with a cancellation flag that is set when + * del_timer() is called and checked in the timer callback function. This + * is needed since del_timer_sync() cannot be called with sci_lock held. + * For deinit however, del_timer_sync() is used without holding the lock. + */ +struct sci_timer { + struct timer_list timer; + bool cancel; +}; + +static inline +void sci_init_timer(struct sci_timer *tmr, void (*fn)(unsigned long)) +{ + tmr->timer.function = fn; + tmr->timer.data = (unsigned long) tmr; + tmr->cancel = 0; + init_timer(&tmr->timer); +} + +static inline void sci_mod_timer(struct sci_timer *tmr, unsigned long msec) +{ + tmr->cancel = 0; + mod_timer(&tmr->timer, jiffies + msecs_to_jiffies(msec)); +} + +static inline void sci_del_timer(struct sci_timer *tmr) +{ + tmr->cancel = 1; + del_timer(&tmr->timer); +} + +struct sci_base_state_machine { + const struct sci_base_state *state_table; + u32 initial_state_id; + u32 current_state_id; + u32 previous_state_id; +}; + +typedef void (*sci_state_transition_t)(struct sci_base_state_machine *sm); + +struct sci_base_state { + sci_state_transition_t enter_state; /* Called on state entry */ + sci_state_transition_t exit_state; /* Called on state exit */ +}; + +extern void sci_init_sm(struct sci_base_state_machine *sm, + const struct sci_base_state *state_table, + u32 initial_state); +extern void sci_change_state(struct sci_base_state_machine *sm, u32 next_state); +#endif /* __ISCI_H__ */ diff --git a/drivers/scsi/isci/phy.c b/drivers/scsi/isci/phy.c new file mode 100644 index 0000000..79313a7 --- /dev/null +++ b/drivers/scsi/isci/phy.c @@ -0,0 +1,1312 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "isci.h" +#include "host.h" +#include "phy.h" +#include "scu_event_codes.h" +#include "probe_roms.h" + +/* Maximum arbitration wait time in micro-seconds */ +#define SCIC_SDS_PHY_MAX_ARBITRATION_WAIT_TIME (700) + +enum sas_linkrate sci_phy_linkrate(struct isci_phy *iphy) +{ + return iphy->max_negotiated_speed; +} + +static enum sci_status +sci_phy_transport_layer_initialization(struct isci_phy *iphy, + struct scu_transport_layer_registers __iomem *reg) +{ + u32 tl_control; + + iphy->transport_layer_registers = reg; + + writel(SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX, + &iphy->transport_layer_registers->stp_rni); + + /* + * Hardware team recommends that we enable the STP prefetch for all + * transports + */ + tl_control = readl(&iphy->transport_layer_registers->control); + tl_control |= SCU_TLCR_GEN_BIT(STP_WRITE_DATA_PREFETCH); + writel(tl_control, &iphy->transport_layer_registers->control); + + return SCI_SUCCESS; +} + +static enum sci_status +sci_phy_link_layer_initialization(struct isci_phy *iphy, + struct scu_link_layer_registers __iomem *reg) +{ + struct isci_host *ihost = iphy->owning_port->owning_controller; + int phy_idx = iphy->phy_index; + struct sci_phy_user_params *phy_user = &ihost->user_parameters.phys[phy_idx]; + struct sci_phy_oem_params *phy_oem = + &ihost->oem_parameters.phys[phy_idx]; + u32 phy_configuration; + struct sci_phy_cap phy_cap; + u32 parity_check = 0; + u32 parity_count = 0; + u32 llctl, link_rate; + u32 clksm_value = 0; + + iphy->link_layer_registers = reg; + + /* Set our IDENTIFY frame data */ + #define SCI_END_DEVICE 0x01 + + writel(SCU_SAS_TIID_GEN_BIT(SMP_INITIATOR) | + SCU_SAS_TIID_GEN_BIT(SSP_INITIATOR) | + SCU_SAS_TIID_GEN_BIT(STP_INITIATOR) | + SCU_SAS_TIID_GEN_BIT(DA_SATA_HOST) | + SCU_SAS_TIID_GEN_VAL(DEVICE_TYPE, SCI_END_DEVICE), + &iphy->link_layer_registers->transmit_identification); + + /* Write the device SAS Address */ + writel(0xFEDCBA98, + &iphy->link_layer_registers->sas_device_name_high); + writel(phy_idx, &iphy->link_layer_registers->sas_device_name_low); + + /* Write the source SAS Address */ + writel(phy_oem->sas_address.high, + &iphy->link_layer_registers->source_sas_address_high); + writel(phy_oem->sas_address.low, + &iphy->link_layer_registers->source_sas_address_low); + + /* Clear and Set the PHY Identifier */ + writel(0, &iphy->link_layer_registers->identify_frame_phy_id); + writel(SCU_SAS_TIPID_GEN_VALUE(ID, phy_idx), + &iphy->link_layer_registers->identify_frame_phy_id); + + /* Change the initial state of the phy configuration register */ + phy_configuration = + readl(&iphy->link_layer_registers->phy_configuration); + + /* Hold OOB state machine in reset */ + phy_configuration |= SCU_SAS_PCFG_GEN_BIT(OOB_RESET); + writel(phy_configuration, + &iphy->link_layer_registers->phy_configuration); + + /* Configure the SNW capabilities */ + phy_cap.all = 0; + phy_cap.start = 1; + phy_cap.gen3_no_ssc = 1; + phy_cap.gen2_no_ssc = 1; + phy_cap.gen1_no_ssc = 1; + if (ihost->oem_parameters.controller.do_enable_ssc == true) { + phy_cap.gen3_ssc = 1; + phy_cap.gen2_ssc = 1; + phy_cap.gen1_ssc = 1; + } + + /* + * The SAS specification indicates that the phy_capabilities that + * are transmitted shall have an even parity. Calculate the parity. */ + parity_check = phy_cap.all; + while (parity_check != 0) { + if (parity_check & 0x1) + parity_count++; + parity_check >>= 1; + } + + /* + * If parity indicates there are an odd number of bits set, then + * set the parity bit to 1 in the phy capabilities. */ + if ((parity_count % 2) != 0) + phy_cap.parity = 1; + + writel(phy_cap.all, &iphy->link_layer_registers->phy_capabilities); + + /* Set the enable spinup period but disable the ability to send + * notify enable spinup + */ + writel(SCU_ENSPINUP_GEN_VAL(COUNT, + phy_user->notify_enable_spin_up_insertion_frequency), + &iphy->link_layer_registers->notify_enable_spinup_control); + + /* Write the ALIGN Insertion Ferequency for connected phy and + * inpendent of connected state + */ + clksm_value = SCU_ALIGN_INSERTION_FREQUENCY_GEN_VAL(CONNECTED, + phy_user->in_connection_align_insertion_frequency); + + clksm_value |= SCU_ALIGN_INSERTION_FREQUENCY_GEN_VAL(GENERAL, + phy_user->align_insertion_frequency); + + writel(clksm_value, &iphy->link_layer_registers->clock_skew_management); + + /* @todo Provide a way to write this register correctly */ + writel(0x02108421, + &iphy->link_layer_registers->afe_lookup_table_control); + + llctl = SCU_SAS_LLCTL_GEN_VAL(NO_OUTBOUND_TASK_TIMEOUT, + (u8)ihost->user_parameters.no_outbound_task_timeout); + + switch (phy_user->max_speed_generation) { + case SCIC_SDS_PARM_GEN3_SPEED: + link_rate = SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_GEN3; + break; + case SCIC_SDS_PARM_GEN2_SPEED: + link_rate = SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_GEN2; + break; + default: + link_rate = SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_GEN1; + break; + } + llctl |= SCU_SAS_LLCTL_GEN_VAL(MAX_LINK_RATE, link_rate); + writel(llctl, &iphy->link_layer_registers->link_layer_control); + + if (is_a2(ihost->pdev)) { + /* Program the max ARB time for the PHY to 700us so we inter-operate with + * the PMC expander which shuts down PHYs if the expander PHY generates too + * many breaks. This time value will guarantee that the initiator PHY will + * generate the break. + */ + writel(SCIC_SDS_PHY_MAX_ARBITRATION_WAIT_TIME, + &iphy->link_layer_registers->maximum_arbitration_wait_timer_timeout); + } + + /* Disable link layer hang detection, rely on the OS timeout for I/O timeouts. */ + writel(0, &iphy->link_layer_registers->link_layer_hang_detection_timeout); + + /* We can exit the initial state to the stopped state */ + sci_change_state(&iphy->sm, SCI_PHY_STOPPED); + + return SCI_SUCCESS; +} + +static void phy_sata_timeout(unsigned long data) +{ + struct sci_timer *tmr = (struct sci_timer *)data; + struct isci_phy *iphy = container_of(tmr, typeof(*iphy), sata_timer); + struct isci_host *ihost = iphy->owning_port->owning_controller; + unsigned long flags; + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + dev_dbg(sciphy_to_dev(iphy), + "%s: SCIC SDS Phy 0x%p did not receive signature fis before " + "timeout.\n", + __func__, + iphy); + + sci_change_state(&iphy->sm, SCI_PHY_STARTING); +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +/** + * This method returns the port currently containing this phy. If the phy is + * currently contained by the dummy port, then the phy is considered to not + * be part of a port. + * @sci_phy: This parameter specifies the phy for which to retrieve the + * containing port. + * + * This method returns a handle to a port that contains the supplied phy. + * NULL This value is returned if the phy is not part of a real + * port (i.e. it's contained in the dummy port). !NULL All other + * values indicate a handle/pointer to the port containing the phy. + */ +struct isci_port *phy_get_non_dummy_port(struct isci_phy *iphy) +{ + struct isci_port *iport = iphy->owning_port; + + if (iport->physical_port_index == SCIC_SDS_DUMMY_PORT) + return NULL; + + return iphy->owning_port; +} + +/** + * This method will assign a port to the phy object. + * @out]: iphy This parameter specifies the phy for which to assign a port + * object. + * + * + */ +void sci_phy_set_port( + struct isci_phy *iphy, + struct isci_port *iport) +{ + iphy->owning_port = iport; + + if (iphy->bcn_received_while_port_unassigned) { + iphy->bcn_received_while_port_unassigned = false; + sci_port_broadcast_change_received(iphy->owning_port, iphy); + } +} + +enum sci_status sci_phy_initialize(struct isci_phy *iphy, + struct scu_transport_layer_registers __iomem *tl, + struct scu_link_layer_registers __iomem *ll) +{ + /* Perfrom the initialization of the TL hardware */ + sci_phy_transport_layer_initialization(iphy, tl); + + /* Perofrm the initialization of the PE hardware */ + sci_phy_link_layer_initialization(iphy, ll); + + /* There is nothing that needs to be done in this state just + * transition to the stopped state + */ + sci_change_state(&iphy->sm, SCI_PHY_STOPPED); + + return SCI_SUCCESS; +} + +/** + * This method assigns the direct attached device ID for this phy. + * + * @iphy The phy for which the direct attached device id is to + * be assigned. + * @device_id The direct attached device ID to assign to the phy. + * This will either be the RNi for the device or an invalid RNi if there + * is no current device assigned to the phy. + */ +void sci_phy_setup_transport(struct isci_phy *iphy, u32 device_id) +{ + u32 tl_control; + + writel(device_id, &iphy->transport_layer_registers->stp_rni); + + /* + * The read should guarantee that the first write gets posted + * before the next write + */ + tl_control = readl(&iphy->transport_layer_registers->control); + tl_control |= SCU_TLCR_GEN_BIT(CLEAR_TCI_NCQ_MAPPING_TABLE); + writel(tl_control, &iphy->transport_layer_registers->control); +} + +static void sci_phy_suspend(struct isci_phy *iphy) +{ + u32 scu_sas_pcfg_value; + + scu_sas_pcfg_value = + readl(&iphy->link_layer_registers->phy_configuration); + scu_sas_pcfg_value |= SCU_SAS_PCFG_GEN_BIT(SUSPEND_PROTOCOL_ENGINE); + writel(scu_sas_pcfg_value, + &iphy->link_layer_registers->phy_configuration); + + sci_phy_setup_transport(iphy, SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX); +} + +void sci_phy_resume(struct isci_phy *iphy) +{ + u32 scu_sas_pcfg_value; + + scu_sas_pcfg_value = + readl(&iphy->link_layer_registers->phy_configuration); + scu_sas_pcfg_value &= ~SCU_SAS_PCFG_GEN_BIT(SUSPEND_PROTOCOL_ENGINE); + writel(scu_sas_pcfg_value, + &iphy->link_layer_registers->phy_configuration); +} + +void sci_phy_get_sas_address(struct isci_phy *iphy, struct sci_sas_address *sas) +{ + sas->high = readl(&iphy->link_layer_registers->source_sas_address_high); + sas->low = readl(&iphy->link_layer_registers->source_sas_address_low); +} + +void sci_phy_get_attached_sas_address(struct isci_phy *iphy, struct sci_sas_address *sas) +{ + struct sas_identify_frame *iaf; + + iaf = &iphy->frame_rcvd.iaf; + memcpy(sas, iaf->sas_addr, SAS_ADDR_SIZE); +} + +void sci_phy_get_protocols(struct isci_phy *iphy, struct sci_phy_proto *proto) +{ + proto->all = readl(&iphy->link_layer_registers->transmit_identification); +} + +enum sci_status sci_phy_start(struct isci_phy *iphy) +{ + enum sci_phy_states state = iphy->sm.current_state_id; + + if (state != SCI_PHY_STOPPED) { + dev_dbg(sciphy_to_dev(iphy), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + return SCI_SUCCESS; +} + +enum sci_status sci_phy_stop(struct isci_phy *iphy) +{ + enum sci_phy_states state = iphy->sm.current_state_id; + + switch (state) { + case SCI_PHY_SUB_INITIAL: + case SCI_PHY_SUB_AWAIT_OSSP_EN: + case SCI_PHY_SUB_AWAIT_SAS_SPEED_EN: + case SCI_PHY_SUB_AWAIT_SAS_POWER: + case SCI_PHY_SUB_AWAIT_SATA_POWER: + case SCI_PHY_SUB_AWAIT_SATA_PHY_EN: + case SCI_PHY_SUB_AWAIT_SATA_SPEED_EN: + case SCI_PHY_SUB_AWAIT_SIG_FIS_UF: + case SCI_PHY_SUB_FINAL: + case SCI_PHY_READY: + break; + default: + dev_dbg(sciphy_to_dev(iphy), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + sci_change_state(&iphy->sm, SCI_PHY_STOPPED); + return SCI_SUCCESS; +} + +enum sci_status sci_phy_reset(struct isci_phy *iphy) +{ + enum sci_phy_states state = iphy->sm.current_state_id; + + if (state != SCI_PHY_READY) { + dev_dbg(sciphy_to_dev(iphy), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + sci_change_state(&iphy->sm, SCI_PHY_RESETTING); + return SCI_SUCCESS; +} + +enum sci_status sci_phy_consume_power_handler(struct isci_phy *iphy) +{ + enum sci_phy_states state = iphy->sm.current_state_id; + + switch (state) { + case SCI_PHY_SUB_AWAIT_SAS_POWER: { + u32 enable_spinup; + + enable_spinup = readl(&iphy->link_layer_registers->notify_enable_spinup_control); + enable_spinup |= SCU_ENSPINUP_GEN_BIT(ENABLE); + writel(enable_spinup, &iphy->link_layer_registers->notify_enable_spinup_control); + + /* Change state to the final state this substate machine has run to completion */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_FINAL); + + return SCI_SUCCESS; + } + case SCI_PHY_SUB_AWAIT_SATA_POWER: { + u32 scu_sas_pcfg_value; + + /* Release the spinup hold state and reset the OOB state machine */ + scu_sas_pcfg_value = + readl(&iphy->link_layer_registers->phy_configuration); + scu_sas_pcfg_value &= + ~(SCU_SAS_PCFG_GEN_BIT(SATA_SPINUP_HOLD) | SCU_SAS_PCFG_GEN_BIT(OOB_ENABLE)); + scu_sas_pcfg_value |= SCU_SAS_PCFG_GEN_BIT(OOB_RESET); + writel(scu_sas_pcfg_value, + &iphy->link_layer_registers->phy_configuration); + + /* Now restart the OOB operation */ + scu_sas_pcfg_value &= ~SCU_SAS_PCFG_GEN_BIT(OOB_RESET); + scu_sas_pcfg_value |= SCU_SAS_PCFG_GEN_BIT(OOB_ENABLE); + writel(scu_sas_pcfg_value, + &iphy->link_layer_registers->phy_configuration); + + /* Change state to the final state this substate machine has run to completion */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_AWAIT_SATA_PHY_EN); + + return SCI_SUCCESS; + } + default: + dev_dbg(sciphy_to_dev(iphy), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +static void sci_phy_start_sas_link_training(struct isci_phy *iphy) +{ + /* continue the link training for the phy as if it were a SAS PHY + * instead of a SATA PHY. This is done because the completion queue had a SAS + * PHY DETECTED event when the state machine was expecting a SATA PHY event. + */ + u32 phy_control; + + phy_control = readl(&iphy->link_layer_registers->phy_configuration); + phy_control |= SCU_SAS_PCFG_GEN_BIT(SATA_SPINUP_HOLD); + writel(phy_control, + &iphy->link_layer_registers->phy_configuration); + + sci_change_state(&iphy->sm, SCI_PHY_SUB_AWAIT_SAS_SPEED_EN); + + iphy->protocol = SCIC_SDS_PHY_PROTOCOL_SAS; +} + +static void sci_phy_start_sata_link_training(struct isci_phy *iphy) +{ + /* This method continues the link training for the phy as if it were a SATA PHY + * instead of a SAS PHY. This is done because the completion queue had a SATA + * SPINUP HOLD event when the state machine was expecting a SAS PHY event. none + */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_AWAIT_SATA_POWER); + + iphy->protocol = SCIC_SDS_PHY_PROTOCOL_SATA; +} + +/** + * sci_phy_complete_link_training - perform processing common to + * all protocols upon completion of link training. + * @sci_phy: This parameter specifies the phy object for which link training + * has completed. + * @max_link_rate: This parameter specifies the maximum link rate to be + * associated with this phy. + * @next_state: This parameter specifies the next state for the phy's starting + * sub-state machine. + * + */ +static void sci_phy_complete_link_training(struct isci_phy *iphy, + enum sas_linkrate max_link_rate, + u32 next_state) +{ + iphy->max_negotiated_speed = max_link_rate; + + sci_change_state(&iphy->sm, next_state); +} + +enum sci_status sci_phy_event_handler(struct isci_phy *iphy, u32 event_code) +{ + enum sci_phy_states state = iphy->sm.current_state_id; + + switch (state) { + case SCI_PHY_SUB_AWAIT_OSSP_EN: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_SAS_PHY_DETECTED: + sci_phy_start_sas_link_training(iphy); + iphy->is_in_link_training = true; + break; + case SCU_EVENT_SATA_SPINUP_HOLD: + sci_phy_start_sata_link_training(iphy); + iphy->is_in_link_training = true; + break; + default: + dev_dbg(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, + event_code); + return SCI_FAILURE; + } + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_SAS_SPEED_EN: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_SAS_PHY_DETECTED: + /* + * Why is this being reported again by the controller? + * We would re-enter this state so just stay here */ + break; + case SCU_EVENT_SAS_15: + case SCU_EVENT_SAS_15_SSC: + sci_phy_complete_link_training(iphy, SAS_LINK_RATE_1_5_GBPS, + SCI_PHY_SUB_AWAIT_IAF_UF); + break; + case SCU_EVENT_SAS_30: + case SCU_EVENT_SAS_30_SSC: + sci_phy_complete_link_training(iphy, SAS_LINK_RATE_3_0_GBPS, + SCI_PHY_SUB_AWAIT_IAF_UF); + break; + case SCU_EVENT_SAS_60: + case SCU_EVENT_SAS_60_SSC: + sci_phy_complete_link_training(iphy, SAS_LINK_RATE_6_0_GBPS, + SCI_PHY_SUB_AWAIT_IAF_UF); + break; + case SCU_EVENT_SATA_SPINUP_HOLD: + /* + * We were doing SAS PHY link training and received a SATA PHY event + * continue OOB/SN as if this were a SATA PHY */ + sci_phy_start_sata_link_training(iphy); + break; + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, event_code); + + return SCI_FAILURE; + break; + } + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_IAF_UF: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_SAS_PHY_DETECTED: + /* Backup the state machine */ + sci_phy_start_sas_link_training(iphy); + break; + case SCU_EVENT_SATA_SPINUP_HOLD: + /* We were doing SAS PHY link training and received a + * SATA PHY event continue OOB/SN as if this were a + * SATA PHY + */ + sci_phy_start_sata_link_training(iphy); + break; + case SCU_EVENT_RECEIVED_IDENTIFY_TIMEOUT: + case SCU_EVENT_LINK_FAILURE: + case SCU_EVENT_HARD_RESET_RECEIVED: + /* Start the oob/sn state machine over again */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, event_code); + return SCI_FAILURE; + } + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_SAS_POWER: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received unexpected " + "event_code %x\n", + __func__, + event_code); + return SCI_FAILURE; + } + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_SATA_POWER: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + case SCU_EVENT_SATA_SPINUP_HOLD: + /* These events are received every 10ms and are + * expected while in this state + */ + break; + + case SCU_EVENT_SAS_PHY_DETECTED: + /* There has been a change in the phy type before OOB/SN for the + * SATA finished start down the SAS link traning path. + */ + sci_phy_start_sas_link_training(iphy); + break; + + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, event_code); + + return SCI_FAILURE; + } + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_SATA_PHY_EN: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + case SCU_EVENT_SATA_SPINUP_HOLD: + /* These events might be received since we dont know how many may be in + * the completion queue while waiting for power + */ + break; + case SCU_EVENT_SATA_PHY_DETECTED: + iphy->protocol = SCIC_SDS_PHY_PROTOCOL_SATA; + + /* We have received the SATA PHY notification change state */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_AWAIT_SATA_SPEED_EN); + break; + case SCU_EVENT_SAS_PHY_DETECTED: + /* There has been a change in the phy type before OOB/SN for the + * SATA finished start down the SAS link traning path. + */ + sci_phy_start_sas_link_training(iphy); + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, + event_code); + + return SCI_FAILURE;; + } + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_SATA_SPEED_EN: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_SATA_PHY_DETECTED: + /* + * The hardware reports multiple SATA PHY detected events + * ignore the extras */ + break; + case SCU_EVENT_SATA_15: + case SCU_EVENT_SATA_15_SSC: + sci_phy_complete_link_training(iphy, SAS_LINK_RATE_1_5_GBPS, + SCI_PHY_SUB_AWAIT_SIG_FIS_UF); + break; + case SCU_EVENT_SATA_30: + case SCU_EVENT_SATA_30_SSC: + sci_phy_complete_link_training(iphy, SAS_LINK_RATE_3_0_GBPS, + SCI_PHY_SUB_AWAIT_SIG_FIS_UF); + break; + case SCU_EVENT_SATA_60: + case SCU_EVENT_SATA_60_SSC: + sci_phy_complete_link_training(iphy, SAS_LINK_RATE_6_0_GBPS, + SCI_PHY_SUB_AWAIT_SIG_FIS_UF); + break; + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + case SCU_EVENT_SAS_PHY_DETECTED: + /* + * There has been a change in the phy type before OOB/SN for the + * SATA finished start down the SAS link traning path. */ + sci_phy_start_sas_link_training(iphy); + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, event_code); + + return SCI_FAILURE; + } + + return SCI_SUCCESS; + case SCI_PHY_SUB_AWAIT_SIG_FIS_UF: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_SATA_PHY_DETECTED: + /* Backup the state machine */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_AWAIT_SATA_SPEED_EN); + break; + + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + + default: + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected event_code %x\n", + __func__, + event_code); + + return SCI_FAILURE; + } + return SCI_SUCCESS; + case SCI_PHY_READY: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_LINK_FAILURE: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + case SCU_EVENT_BROADCAST_CHANGE: + /* Broadcast change received. Notify the port. */ + if (phy_get_non_dummy_port(iphy) != NULL) + sci_port_broadcast_change_received(iphy->owning_port, iphy); + else + iphy->bcn_received_while_port_unassigned = true; + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%sP SCIC PHY 0x%p ready state machine received " + "unexpected event_code %x\n", + __func__, iphy, event_code); + return SCI_FAILURE_INVALID_STATE; + } + return SCI_SUCCESS; + case SCI_PHY_RESETTING: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_HARD_RESET_TRANSMITTED: + /* Link failure change state back to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + break; + default: + dev_warn(sciphy_to_dev(iphy), + "%s: SCIC PHY 0x%p resetting state machine received " + "unexpected event_code %x\n", + __func__, iphy, event_code); + + return SCI_FAILURE_INVALID_STATE; + break; + } + return SCI_SUCCESS; + default: + dev_dbg(sciphy_to_dev(iphy), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_phy_frame_handler(struct isci_phy *iphy, u32 frame_index) +{ + enum sci_phy_states state = iphy->sm.current_state_id; + struct isci_host *ihost = iphy->owning_port->owning_controller; + enum sci_status result; + unsigned long flags; + + switch (state) { + case SCI_PHY_SUB_AWAIT_IAF_UF: { + u32 *frame_words; + struct sas_identify_frame iaf; + + result = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_words); + + if (result != SCI_SUCCESS) + return result; + + sci_swab32_cpy(&iaf, frame_words, sizeof(iaf) / sizeof(u32)); + if (iaf.frame_type == 0) { + u32 state; + + spin_lock_irqsave(&iphy->sas_phy.frame_rcvd_lock, flags); + memcpy(&iphy->frame_rcvd.iaf, &iaf, sizeof(iaf)); + spin_unlock_irqrestore(&iphy->sas_phy.frame_rcvd_lock, flags); + if (iaf.smp_tport) { + /* We got the IAF for an expander PHY go to the final + * state since there are no power requirements for + * expander phys. + */ + state = SCI_PHY_SUB_FINAL; + } else { + /* We got the IAF we can now go to the await spinup + * semaphore state + */ + state = SCI_PHY_SUB_AWAIT_SAS_POWER; + } + sci_change_state(&iphy->sm, state); + result = SCI_SUCCESS; + } else + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected frame id %x\n", + __func__, frame_index); + + sci_controller_release_frame(ihost, frame_index); + return result; + } + case SCI_PHY_SUB_AWAIT_SIG_FIS_UF: { + struct dev_to_host_fis *frame_header; + u32 *fis_frame_data; + + result = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_header); + + if (result != SCI_SUCCESS) + return result; + + if ((frame_header->fis_type == FIS_REGD2H) && + !(frame_header->status & ATA_BUSY)) { + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&fis_frame_data); + + spin_lock_irqsave(&iphy->sas_phy.frame_rcvd_lock, flags); + sci_controller_copy_sata_response(&iphy->frame_rcvd.fis, + frame_header, + fis_frame_data); + spin_unlock_irqrestore(&iphy->sas_phy.frame_rcvd_lock, flags); + + /* got IAF we can now go to the await spinup semaphore state */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_FINAL); + + result = SCI_SUCCESS; + } else + dev_warn(sciphy_to_dev(iphy), + "%s: PHY starting substate machine received " + "unexpected frame id %x\n", + __func__, frame_index); + + /* Regardless of the result we are done with this frame with it */ + sci_controller_release_frame(ihost, frame_index); + + return result; + } + default: + dev_dbg(sciphy_to_dev(iphy), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + +} + +static void sci_phy_starting_initial_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + /* This is just an temporary state go off to the starting state */ + sci_change_state(&iphy->sm, SCI_PHY_SUB_AWAIT_OSSP_EN); +} + +static void sci_phy_starting_await_sas_power_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_host *ihost = iphy->owning_port->owning_controller; + + sci_controller_power_control_queue_insert(ihost, iphy); +} + +static void sci_phy_starting_await_sas_power_substate_exit(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_host *ihost = iphy->owning_port->owning_controller; + + sci_controller_power_control_queue_remove(ihost, iphy); +} + +static void sci_phy_starting_await_sata_power_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_host *ihost = iphy->owning_port->owning_controller; + + sci_controller_power_control_queue_insert(ihost, iphy); +} + +static void sci_phy_starting_await_sata_power_substate_exit(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_host *ihost = iphy->owning_port->owning_controller; + + sci_controller_power_control_queue_remove(ihost, iphy); +} + +static void sci_phy_starting_await_sata_phy_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + sci_mod_timer(&iphy->sata_timer, SCIC_SDS_SATA_LINK_TRAINING_TIMEOUT); +} + +static void sci_phy_starting_await_sata_phy_substate_exit(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + sci_del_timer(&iphy->sata_timer); +} + +static void sci_phy_starting_await_sata_speed_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + sci_mod_timer(&iphy->sata_timer, SCIC_SDS_SATA_LINK_TRAINING_TIMEOUT); +} + +static void sci_phy_starting_await_sata_speed_substate_exit(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + sci_del_timer(&iphy->sata_timer); +} + +static void sci_phy_starting_await_sig_fis_uf_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + if (sci_port_link_detected(iphy->owning_port, iphy)) { + + /* + * Clear the PE suspend condition so we can actually + * receive SIG FIS + * The hardware will not respond to the XRDY until the PE + * suspend condition is cleared. + */ + sci_phy_resume(iphy); + + sci_mod_timer(&iphy->sata_timer, + SCIC_SDS_SIGNATURE_FIS_TIMEOUT); + } else + iphy->is_in_link_training = false; +} + +static void sci_phy_starting_await_sig_fis_uf_substate_exit(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + sci_del_timer(&iphy->sata_timer); +} + +static void sci_phy_starting_final_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + /* State machine has run to completion so exit out and change + * the base state machine to the ready state + */ + sci_change_state(&iphy->sm, SCI_PHY_READY); +} + +/** + * + * @sci_phy: This is the struct isci_phy object to stop. + * + * This method will stop the struct isci_phy object. This does not reset the + * protocol engine it just suspends it and places it in a state where it will + * not cause the end device to power up. none + */ +static void scu_link_layer_stop_protocol_engine( + struct isci_phy *iphy) +{ + u32 scu_sas_pcfg_value; + u32 enable_spinup_value; + + /* Suspend the protocol engine and place it in a sata spinup hold state */ + scu_sas_pcfg_value = + readl(&iphy->link_layer_registers->phy_configuration); + scu_sas_pcfg_value |= + (SCU_SAS_PCFG_GEN_BIT(OOB_RESET) | + SCU_SAS_PCFG_GEN_BIT(SUSPEND_PROTOCOL_ENGINE) | + SCU_SAS_PCFG_GEN_BIT(SATA_SPINUP_HOLD)); + writel(scu_sas_pcfg_value, + &iphy->link_layer_registers->phy_configuration); + + /* Disable the notify enable spinup primitives */ + enable_spinup_value = readl(&iphy->link_layer_registers->notify_enable_spinup_control); + enable_spinup_value &= ~SCU_ENSPINUP_GEN_BIT(ENABLE); + writel(enable_spinup_value, &iphy->link_layer_registers->notify_enable_spinup_control); +} + +/** + * + * + * This method will start the OOB/SN state machine for this struct isci_phy object. + */ +static void scu_link_layer_start_oob( + struct isci_phy *iphy) +{ + u32 scu_sas_pcfg_value; + + scu_sas_pcfg_value = + readl(&iphy->link_layer_registers->phy_configuration); + scu_sas_pcfg_value |= SCU_SAS_PCFG_GEN_BIT(OOB_ENABLE); + scu_sas_pcfg_value &= + ~(SCU_SAS_PCFG_GEN_BIT(OOB_RESET) | + SCU_SAS_PCFG_GEN_BIT(HARD_RESET)); + writel(scu_sas_pcfg_value, + &iphy->link_layer_registers->phy_configuration); +} + +/** + * + * + * This method will transmit a hard reset request on the specified phy. The SCU + * hardware requires that we reset the OOB state machine and set the hard reset + * bit in the phy configuration register. We then must start OOB over with the + * hard reset bit set. + */ +static void scu_link_layer_tx_hard_reset( + struct isci_phy *iphy) +{ + u32 phy_configuration_value; + + /* + * SAS Phys must wait for the HARD_RESET_TX event notification to transition + * to the starting state. */ + phy_configuration_value = + readl(&iphy->link_layer_registers->phy_configuration); + phy_configuration_value |= + (SCU_SAS_PCFG_GEN_BIT(HARD_RESET) | + SCU_SAS_PCFG_GEN_BIT(OOB_RESET)); + writel(phy_configuration_value, + &iphy->link_layer_registers->phy_configuration); + + /* Now take the OOB state machine out of reset */ + phy_configuration_value |= SCU_SAS_PCFG_GEN_BIT(OOB_ENABLE); + phy_configuration_value &= ~SCU_SAS_PCFG_GEN_BIT(OOB_RESET); + writel(phy_configuration_value, + &iphy->link_layer_registers->phy_configuration); +} + +static void sci_phy_stopped_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_port *iport = iphy->owning_port; + struct isci_host *ihost = iport->owning_controller; + + /* + * @todo We need to get to the controller to place this PE in a + * reset state + */ + sci_del_timer(&iphy->sata_timer); + + scu_link_layer_stop_protocol_engine(iphy); + + if (iphy->sm.previous_state_id != SCI_PHY_INITIAL) + sci_controller_link_down(ihost, phy_get_non_dummy_port(iphy), iphy); +} + +static void sci_phy_starting_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_port *iport = iphy->owning_port; + struct isci_host *ihost = iport->owning_controller; + + scu_link_layer_stop_protocol_engine(iphy); + scu_link_layer_start_oob(iphy); + + /* We don't know what kind of phy we are going to be just yet */ + iphy->protocol = SCIC_SDS_PHY_PROTOCOL_UNKNOWN; + iphy->bcn_received_while_port_unassigned = false; + + if (iphy->sm.previous_state_id == SCI_PHY_READY) + sci_controller_link_down(ihost, phy_get_non_dummy_port(iphy), iphy); + + sci_change_state(&iphy->sm, SCI_PHY_SUB_INITIAL); +} + +static void sci_phy_ready_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + struct isci_port *iport = iphy->owning_port; + struct isci_host *ihost = iport->owning_controller; + + sci_controller_link_up(ihost, phy_get_non_dummy_port(iphy), iphy); +} + +static void sci_phy_ready_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + sci_phy_suspend(iphy); +} + +static void sci_phy_resetting_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_phy *iphy = container_of(sm, typeof(*iphy), sm); + + /* The phy is being reset, therefore deactivate it from the port. In + * the resetting state we don't notify the user regarding link up and + * link down notifications + */ + sci_port_deactivate_phy(iphy->owning_port, iphy, false); + + if (iphy->protocol == SCIC_SDS_PHY_PROTOCOL_SAS) { + scu_link_layer_tx_hard_reset(iphy); + } else { + /* The SCU does not need to have a discrete reset state so + * just go back to the starting state. + */ + sci_change_state(&iphy->sm, SCI_PHY_STARTING); + } +} + +static const struct sci_base_state sci_phy_state_table[] = { + [SCI_PHY_INITIAL] = { }, + [SCI_PHY_STOPPED] = { + .enter_state = sci_phy_stopped_state_enter, + }, + [SCI_PHY_STARTING] = { + .enter_state = sci_phy_starting_state_enter, + }, + [SCI_PHY_SUB_INITIAL] = { + .enter_state = sci_phy_starting_initial_substate_enter, + }, + [SCI_PHY_SUB_AWAIT_OSSP_EN] = { }, + [SCI_PHY_SUB_AWAIT_SAS_SPEED_EN] = { }, + [SCI_PHY_SUB_AWAIT_IAF_UF] = { }, + [SCI_PHY_SUB_AWAIT_SAS_POWER] = { + .enter_state = sci_phy_starting_await_sas_power_substate_enter, + .exit_state = sci_phy_starting_await_sas_power_substate_exit, + }, + [SCI_PHY_SUB_AWAIT_SATA_POWER] = { + .enter_state = sci_phy_starting_await_sata_power_substate_enter, + .exit_state = sci_phy_starting_await_sata_power_substate_exit + }, + [SCI_PHY_SUB_AWAIT_SATA_PHY_EN] = { + .enter_state = sci_phy_starting_await_sata_phy_substate_enter, + .exit_state = sci_phy_starting_await_sata_phy_substate_exit + }, + [SCI_PHY_SUB_AWAIT_SATA_SPEED_EN] = { + .enter_state = sci_phy_starting_await_sata_speed_substate_enter, + .exit_state = sci_phy_starting_await_sata_speed_substate_exit + }, + [SCI_PHY_SUB_AWAIT_SIG_FIS_UF] = { + .enter_state = sci_phy_starting_await_sig_fis_uf_substate_enter, + .exit_state = sci_phy_starting_await_sig_fis_uf_substate_exit + }, + [SCI_PHY_SUB_FINAL] = { + .enter_state = sci_phy_starting_final_substate_enter, + }, + [SCI_PHY_READY] = { + .enter_state = sci_phy_ready_state_enter, + .exit_state = sci_phy_ready_state_exit, + }, + [SCI_PHY_RESETTING] = { + .enter_state = sci_phy_resetting_state_enter, + }, + [SCI_PHY_FINAL] = { }, +}; + +void sci_phy_construct(struct isci_phy *iphy, + struct isci_port *iport, u8 phy_index) +{ + sci_init_sm(&iphy->sm, sci_phy_state_table, SCI_PHY_INITIAL); + + /* Copy the rest of the input data to our locals */ + iphy->owning_port = iport; + iphy->phy_index = phy_index; + iphy->bcn_received_while_port_unassigned = false; + iphy->protocol = SCIC_SDS_PHY_PROTOCOL_UNKNOWN; + iphy->link_layer_registers = NULL; + iphy->max_negotiated_speed = SAS_LINK_RATE_UNKNOWN; + + /* Create the SIGNATURE FIS Timeout timer for this phy */ + sci_init_timer(&iphy->sata_timer, phy_sata_timeout); +} + +void isci_phy_init(struct isci_phy *iphy, struct isci_host *ihost, int index) +{ + struct sci_oem_params *oem = &ihost->oem_parameters; + u64 sci_sas_addr; + __be64 sas_addr; + + sci_sas_addr = oem->phys[index].sas_address.high; + sci_sas_addr <<= 32; + sci_sas_addr |= oem->phys[index].sas_address.low; + sas_addr = cpu_to_be64(sci_sas_addr); + memcpy(iphy->sas_addr, &sas_addr, sizeof(sas_addr)); + + iphy->isci_port = NULL; + iphy->sas_phy.enabled = 0; + iphy->sas_phy.id = index; + iphy->sas_phy.sas_addr = &iphy->sas_addr[0]; + iphy->sas_phy.frame_rcvd = (u8 *)&iphy->frame_rcvd; + iphy->sas_phy.ha = &ihost->sas_ha; + iphy->sas_phy.lldd_phy = iphy; + iphy->sas_phy.enabled = 1; + iphy->sas_phy.class = SAS; + iphy->sas_phy.iproto = SAS_PROTOCOL_ALL; + iphy->sas_phy.tproto = 0; + iphy->sas_phy.type = PHY_TYPE_PHYSICAL; + iphy->sas_phy.role = PHY_ROLE_INITIATOR; + iphy->sas_phy.oob_mode = OOB_NOT_CONNECTED; + iphy->sas_phy.linkrate = SAS_LINK_RATE_UNKNOWN; + memset(&iphy->frame_rcvd, 0, sizeof(iphy->frame_rcvd)); +} + + +/** + * isci_phy_control() - This function is one of the SAS Domain Template + * functions. This is a phy management function. + * @phy: This parameter specifies the sphy being controlled. + * @func: This parameter specifies the phy control function being invoked. + * @buf: This parameter is specific to the phy function being invoked. + * + * status, zero indicates success. + */ +int isci_phy_control(struct asd_sas_phy *sas_phy, + enum phy_func func, + void *buf) +{ + int ret = 0; + struct isci_phy *iphy = sas_phy->lldd_phy; + struct isci_port *iport = iphy->isci_port; + struct isci_host *ihost = sas_phy->ha->lldd_ha; + unsigned long flags; + + dev_dbg(&ihost->pdev->dev, + "%s: phy %p; func %d; buf %p; isci phy %p, port %p\n", + __func__, sas_phy, func, buf, iphy, iport); + + switch (func) { + case PHY_FUNC_DISABLE: + spin_lock_irqsave(&ihost->scic_lock, flags); + sci_phy_stop(iphy); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + break; + + case PHY_FUNC_LINK_RESET: + spin_lock_irqsave(&ihost->scic_lock, flags); + sci_phy_stop(iphy); + sci_phy_start(iphy); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + break; + + case PHY_FUNC_HARD_RESET: + if (!iport) + return -ENODEV; + + /* Perform the port reset. */ + ret = isci_port_perform_hard_reset(ihost, iport, iphy); + + break; + + default: + dev_dbg(&ihost->pdev->dev, + "%s: phy %p; func %d NOT IMPLEMENTED!\n", + __func__, sas_phy, func); + ret = -ENOSYS; + break; + } + return ret; +} diff --git a/drivers/scsi/isci/phy.h b/drivers/scsi/isci/phy.h new file mode 100644 index 0000000..67699c8 --- /dev/null +++ b/drivers/scsi/isci/phy.h @@ -0,0 +1,504 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _ISCI_PHY_H_ +#define _ISCI_PHY_H_ + +#include <scsi/sas.h> +#include <scsi/libsas.h> +#include "isci.h" +#include "sas.h" + +/* This is the timeout value for the SATA phy to wait for a SIGNATURE FIS + * before restarting the starting state machine. Technically, the old parallel + * ATA specification required up to 30 seconds for a device to issue its + * signature FIS as a result of a soft reset. Now we see that devices respond + * generally within 15 seconds, but we'll use 25 for now. + */ +#define SCIC_SDS_SIGNATURE_FIS_TIMEOUT 25000 + +/* This is the timeout for the SATA OOB/SN because the hardware does not + * recognize a hot plug after OOB signal but before the SN signals. We need to + * make sure after a hotplug timeout if we have not received the speed event + * notification from the hardware that we restart the hardware OOB state + * machine. + */ +#define SCIC_SDS_SATA_LINK_TRAINING_TIMEOUT 250 + +enum sci_phy_protocol { + SCIC_SDS_PHY_PROTOCOL_UNKNOWN, + SCIC_SDS_PHY_PROTOCOL_SAS, + SCIC_SDS_PHY_PROTOCOL_SATA, + SCIC_SDS_MAX_PHY_PROTOCOLS +}; + +/** + * isci_phy - hba local phy infrastructure + * @sm: + * @protocol: attached device protocol + * @phy_index: physical index relative to the controller (0-3) + * @bcn_received_while_port_unassigned: bcn to report after port association + * @sata_timer: timeout SATA signature FIS arrival + */ +struct isci_phy { + struct sci_base_state_machine sm; + struct isci_port *owning_port; + enum sas_linkrate max_negotiated_speed; + enum sci_phy_protocol protocol; + u8 phy_index; + bool bcn_received_while_port_unassigned; + bool is_in_link_training; + struct sci_timer sata_timer; + struct scu_transport_layer_registers __iomem *transport_layer_registers; + struct scu_link_layer_registers __iomem *link_layer_registers; + struct asd_sas_phy sas_phy; + struct isci_port *isci_port; + u8 sas_addr[SAS_ADDR_SIZE]; + union { + struct sas_identify_frame iaf; + struct dev_to_host_fis fis; + } frame_rcvd; +}; + +static inline struct isci_phy *to_iphy(struct asd_sas_phy *sas_phy) +{ + struct isci_phy *iphy = container_of(sas_phy, typeof(*iphy), sas_phy); + + return iphy; +} + +struct sci_phy_cap { + union { + struct { + /* + * The SAS specification indicates the start bit shall + * always be set to + * 1. This implementation will have the start bit set + * to 0 if the PHY CAPABILITIES were either not + * received or speed negotiation failed. + */ + u8 start:1; + u8 tx_ssc_type:1; + u8 res1:2; + u8 req_logical_linkrate:4; + + u32 gen1_no_ssc:1; + u32 gen1_ssc:1; + u32 gen2_no_ssc:1; + u32 gen2_ssc:1; + u32 gen3_no_ssc:1; + u32 gen3_ssc:1; + u32 res2:17; + u32 parity:1; + }; + u32 all; + }; +} __packed; + +/* this data structure reflects the link layer transmit identification reg */ +struct sci_phy_proto { + union { + struct { + u16 _r_a:1; + u16 smp_iport:1; + u16 stp_iport:1; + u16 ssp_iport:1; + u16 _r_b:4; + u16 _r_c:1; + u16 smp_tport:1; + u16 stp_tport:1; + u16 ssp_tport:1; + u16 _r_d:4; + }; + u16 all; + }; +} __packed; + + +/** + * struct sci_phy_properties - This structure defines the properties common to + * all phys that can be retrieved. + * + * + */ +struct sci_phy_properties { + /** + * This field specifies the port that currently contains the + * supplied phy. This field may be set to NULL + * if the phy is not currently contained in a port. + */ + struct isci_port *iport; + + /** + * This field specifies the link rate at which the phy is + * currently operating. + */ + enum sas_linkrate negotiated_link_rate; + + /** + * This field specifies the index of the phy in relation to other + * phys within the controller. This index is zero relative. + */ + u8 index; +}; + +/** + * struct sci_sas_phy_properties - This structure defines the properties, + * specific to a SAS phy, that can be retrieved. + * + * + */ +struct sci_sas_phy_properties { + /** + * This field delineates the Identify Address Frame received + * from the remote end point. + */ + struct sas_identify_frame rcvd_iaf; + + /** + * This field delineates the Phy capabilities structure received + * from the remote end point. + */ + struct sci_phy_cap rcvd_cap; + +}; + +/** + * struct sci_sata_phy_properties - This structure defines the properties, + * specific to a SATA phy, that can be retrieved. + * + * + */ +struct sci_sata_phy_properties { + /** + * This field delineates the signature FIS received from the + * attached target. + */ + struct dev_to_host_fis signature_fis; + + /** + * This field specifies to the user if a port selector is connected + * on the specified phy. + */ + bool is_port_selector_present; + +}; + +/** + * enum sci_phy_counter_id - This enumeration depicts the various pieces of + * optional information that can be retrieved for a specific phy. + * + * + */ +enum sci_phy_counter_id { + /** + * This PHY information field tracks the number of frames received. + */ + SCIC_PHY_COUNTER_RECEIVED_FRAME, + + /** + * This PHY information field tracks the number of frames transmitted. + */ + SCIC_PHY_COUNTER_TRANSMITTED_FRAME, + + /** + * This PHY information field tracks the number of DWORDs received. + */ + SCIC_PHY_COUNTER_RECEIVED_FRAME_WORD, + + /** + * This PHY information field tracks the number of DWORDs transmitted. + */ + SCIC_PHY_COUNTER_TRANSMITTED_FRAME_DWORD, + + /** + * This PHY information field tracks the number of times DWORD + * synchronization was lost. + */ + SCIC_PHY_COUNTER_LOSS_OF_SYNC_ERROR, + + /** + * This PHY information field tracks the number of received DWORDs with + * running disparity errors. + */ + SCIC_PHY_COUNTER_RECEIVED_DISPARITY_ERROR, + + /** + * This PHY information field tracks the number of received frames with a + * CRC error (not including short or truncated frames). + */ + SCIC_PHY_COUNTER_RECEIVED_FRAME_CRC_ERROR, + + /** + * This PHY information field tracks the number of DONE (ACK/NAK TIMEOUT) + * primitives received. + */ + SCIC_PHY_COUNTER_RECEIVED_DONE_ACK_NAK_TIMEOUT, + + /** + * This PHY information field tracks the number of DONE (ACK/NAK TIMEOUT) + * primitives transmitted. + */ + SCIC_PHY_COUNTER_TRANSMITTED_DONE_ACK_NAK_TIMEOUT, + + /** + * This PHY information field tracks the number of times the inactivity + * timer for connections on the phy has been utilized. + */ + SCIC_PHY_COUNTER_INACTIVITY_TIMER_EXPIRED, + + /** + * This PHY information field tracks the number of DONE (CREDIT TIMEOUT) + * primitives received. + */ + SCIC_PHY_COUNTER_RECEIVED_DONE_CREDIT_TIMEOUT, + + /** + * This PHY information field tracks the number of DONE (CREDIT TIMEOUT) + * primitives transmitted. + */ + SCIC_PHY_COUNTER_TRANSMITTED_DONE_CREDIT_TIMEOUT, + + /** + * This PHY information field tracks the number of CREDIT BLOCKED + * primitives received. + * @note Depending on remote device implementation, credit blocks + * may occur regularly. + */ + SCIC_PHY_COUNTER_RECEIVED_CREDIT_BLOCKED, + + /** + * This PHY information field contains the number of short frames + * received. A short frame is simply a frame smaller then what is + * allowed by either the SAS or SATA specification. + */ + SCIC_PHY_COUNTER_RECEIVED_SHORT_FRAME, + + /** + * This PHY information field contains the number of frames received after + * credit has been exhausted. + */ + SCIC_PHY_COUNTER_RECEIVED_FRAME_WITHOUT_CREDIT, + + /** + * This PHY information field contains the number of frames received after + * a DONE has been received. + */ + SCIC_PHY_COUNTER_RECEIVED_FRAME_AFTER_DONE, + + /** + * This PHY information field contains the number of times the phy + * failed to achieve DWORD synchronization during speed negotiation. + */ + SCIC_PHY_COUNTER_SN_DWORD_SYNC_ERROR +}; + +enum sci_phy_states { + /** + * Simply the initial state for the base domain state machine. + */ + SCI_PHY_INITIAL, + + /** + * This state indicates that the phy has successfully been stopped. + * In this state no new IO operations are permitted on this phy. + * This state is entered from the INITIAL state. + * This state is entered from the STARTING state. + * This state is entered from the READY state. + * This state is entered from the RESETTING state. + */ + SCI_PHY_STOPPED, + + /** + * This state indicates that the phy is in the process of becomming + * ready. In this state no new IO operations are permitted on this phy. + * This state is entered from the STOPPED state. + * This state is entered from the READY state. + * This state is entered from the RESETTING state. + */ + SCI_PHY_STARTING, + + /** + * Initial state + */ + SCI_PHY_SUB_INITIAL, + + /** + * Wait state for the hardware OSSP event type notification + */ + SCI_PHY_SUB_AWAIT_OSSP_EN, + + /** + * Wait state for the PHY speed notification + */ + SCI_PHY_SUB_AWAIT_SAS_SPEED_EN, + + /** + * Wait state for the IAF Unsolicited frame notification + */ + SCI_PHY_SUB_AWAIT_IAF_UF, + + /** + * Wait state for the request to consume power + */ + SCI_PHY_SUB_AWAIT_SAS_POWER, + + /** + * Wait state for request to consume power + */ + SCI_PHY_SUB_AWAIT_SATA_POWER, + + /** + * Wait state for the SATA PHY notification + */ + SCI_PHY_SUB_AWAIT_SATA_PHY_EN, + + /** + * Wait for the SATA PHY speed notification + */ + SCI_PHY_SUB_AWAIT_SATA_SPEED_EN, + + /** + * Wait state for the SIGNATURE FIS unsolicited frame notification + */ + SCI_PHY_SUB_AWAIT_SIG_FIS_UF, + + /** + * Exit state for this state machine + */ + SCI_PHY_SUB_FINAL, + + /** + * This state indicates the the phy is now ready. Thus, the user + * is able to perform IO operations utilizing this phy as long as it + * is currently part of a valid port. + * This state is entered from the STARTING state. + */ + SCI_PHY_READY, + + /** + * This state indicates that the phy is in the process of being reset. + * In this state no new IO operations are permitted on this phy. + * This state is entered from the READY state. + */ + SCI_PHY_RESETTING, + + /** + * Simply the final state for the base phy state machine. + */ + SCI_PHY_FINAL, +}; + +void sci_phy_construct( + struct isci_phy *iphy, + struct isci_port *iport, + u8 phy_index); + +struct isci_port *phy_get_non_dummy_port(struct isci_phy *iphy); + +void sci_phy_set_port( + struct isci_phy *iphy, + struct isci_port *iport); + +enum sci_status sci_phy_initialize( + struct isci_phy *iphy, + struct scu_transport_layer_registers __iomem *transport_layer_registers, + struct scu_link_layer_registers __iomem *link_layer_registers); + +enum sci_status sci_phy_start( + struct isci_phy *iphy); + +enum sci_status sci_phy_stop( + struct isci_phy *iphy); + +enum sci_status sci_phy_reset( + struct isci_phy *iphy); + +void sci_phy_resume( + struct isci_phy *iphy); + +void sci_phy_setup_transport( + struct isci_phy *iphy, + u32 device_id); + +enum sci_status sci_phy_event_handler( + struct isci_phy *iphy, + u32 event_code); + +enum sci_status sci_phy_frame_handler( + struct isci_phy *iphy, + u32 frame_index); + +enum sci_status sci_phy_consume_power_handler( + struct isci_phy *iphy); + +void sci_phy_get_sas_address( + struct isci_phy *iphy, + struct sci_sas_address *sas_address); + +void sci_phy_get_attached_sas_address( + struct isci_phy *iphy, + struct sci_sas_address *sas_address); + +struct sci_phy_proto; +void sci_phy_get_protocols( + struct isci_phy *iphy, + struct sci_phy_proto *protocols); +enum sas_linkrate sci_phy_linkrate(struct isci_phy *iphy); + +struct isci_host; +void isci_phy_init(struct isci_phy *iphy, struct isci_host *ihost, int index); +int isci_phy_control(struct asd_sas_phy *phy, enum phy_func func, void *buf); + +#endif /* !defined(_ISCI_PHY_H_) */ diff --git a/drivers/scsi/isci/port.c b/drivers/scsi/isci/port.c new file mode 100644 index 0000000..8f6f9b7 --- /dev/null +++ b/drivers/scsi/isci/port.c @@ -0,0 +1,1757 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "isci.h" +#include "port.h" +#include "request.h" + +#define SCIC_SDS_PORT_HARD_RESET_TIMEOUT (1000) +#define SCU_DUMMY_INDEX (0xFFFF) + +static void isci_port_change_state(struct isci_port *iport, enum isci_status status) +{ + unsigned long flags; + + dev_dbg(&iport->isci_host->pdev->dev, + "%s: iport = %p, state = 0x%x\n", + __func__, iport, status); + + /* XXX pointless lock */ + spin_lock_irqsave(&iport->state_lock, flags); + iport->status = status; + spin_unlock_irqrestore(&iport->state_lock, flags); +} + +static void sci_port_get_protocols(struct isci_port *iport, struct sci_phy_proto *proto) +{ + u8 index; + + proto->all = 0; + for (index = 0; index < SCI_MAX_PHYS; index++) { + struct isci_phy *iphy = iport->phy_table[index]; + + if (!iphy) + continue; + sci_phy_get_protocols(iphy, proto); + } +} + +static u32 sci_port_get_phys(struct isci_port *iport) +{ + u32 index; + u32 mask; + + mask = 0; + for (index = 0; index < SCI_MAX_PHYS; index++) + if (iport->phy_table[index]) + mask |= (1 << index); + + return mask; +} + +/** + * sci_port_get_properties() - This method simply returns the properties + * regarding the port, such as: physical index, protocols, sas address, etc. + * @port: this parameter specifies the port for which to retrieve the physical + * index. + * @properties: This parameter specifies the properties structure into which to + * copy the requested information. + * + * Indicate if the user specified a valid port. SCI_SUCCESS This value is + * returned if the specified port was valid. SCI_FAILURE_INVALID_PORT This + * value is returned if the specified port is not valid. When this value is + * returned, no data is copied to the properties output parameter. + */ +static enum sci_status sci_port_get_properties(struct isci_port *iport, + struct sci_port_properties *prop) +{ + if (!iport || iport->logical_port_index == SCIC_SDS_DUMMY_PORT) + return SCI_FAILURE_INVALID_PORT; + + prop->index = iport->logical_port_index; + prop->phy_mask = sci_port_get_phys(iport); + sci_port_get_sas_address(iport, &prop->local.sas_address); + sci_port_get_protocols(iport, &prop->local.protocols); + sci_port_get_attached_sas_address(iport, &prop->remote.sas_address); + + return SCI_SUCCESS; +} + +static void sci_port_bcn_enable(struct isci_port *iport) +{ + struct isci_phy *iphy; + u32 val; + int i; + + for (i = 0; i < ARRAY_SIZE(iport->phy_table); i++) { + iphy = iport->phy_table[i]; + if (!iphy) + continue; + val = readl(&iphy->link_layer_registers->link_layer_control); + /* clear the bit by writing 1. */ + writel(val, &iphy->link_layer_registers->link_layer_control); + } +} + +/* called under sci_lock to stabilize phy:port associations */ +void isci_port_bcn_enable(struct isci_host *ihost, struct isci_port *iport) +{ + int i; + + clear_bit(IPORT_BCN_BLOCKED, &iport->flags); + wake_up(&ihost->eventq); + + if (!test_and_clear_bit(IPORT_BCN_PENDING, &iport->flags)) + return; + + for (i = 0; i < ARRAY_SIZE(iport->phy_table); i++) { + struct isci_phy *iphy = iport->phy_table[i]; + + if (!iphy) + continue; + + ihost->sas_ha.notify_port_event(&iphy->sas_phy, + PORTE_BROADCAST_RCVD); + break; + } +} + +static void isci_port_bc_change_received(struct isci_host *ihost, + struct isci_port *iport, + struct isci_phy *iphy) +{ + if (iport && test_bit(IPORT_BCN_BLOCKED, &iport->flags)) { + dev_dbg(&ihost->pdev->dev, + "%s: disabled BCN; isci_phy = %p, sas_phy = %p\n", + __func__, iphy, &iphy->sas_phy); + set_bit(IPORT_BCN_PENDING, &iport->flags); + atomic_inc(&iport->event); + wake_up(&ihost->eventq); + } else { + dev_dbg(&ihost->pdev->dev, + "%s: isci_phy = %p, sas_phy = %p\n", + __func__, iphy, &iphy->sas_phy); + + ihost->sas_ha.notify_port_event(&iphy->sas_phy, + PORTE_BROADCAST_RCVD); + } + sci_port_bcn_enable(iport); +} + +static void isci_port_link_up(struct isci_host *isci_host, + struct isci_port *iport, + struct isci_phy *iphy) +{ + unsigned long flags; + struct sci_port_properties properties; + unsigned long success = true; + + BUG_ON(iphy->isci_port != NULL); + + iphy->isci_port = iport; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_port = %p\n", + __func__, iport); + + spin_lock_irqsave(&iphy->sas_phy.frame_rcvd_lock, flags); + + isci_port_change_state(iphy->isci_port, isci_starting); + + sci_port_get_properties(iport, &properties); + + if (iphy->protocol == SCIC_SDS_PHY_PROTOCOL_SATA) { + u64 attached_sas_address; + + iphy->sas_phy.oob_mode = SATA_OOB_MODE; + iphy->sas_phy.frame_rcvd_size = sizeof(struct dev_to_host_fis); + + /* + * For direct-attached SATA devices, the SCI core will + * automagically assign a SAS address to the end device + * for the purpose of creating a port. This SAS address + * will not be the same as assigned to the PHY and needs + * to be obtained from struct sci_port_properties properties. + */ + attached_sas_address = properties.remote.sas_address.high; + attached_sas_address <<= 32; + attached_sas_address |= properties.remote.sas_address.low; + swab64s(&attached_sas_address); + + memcpy(&iphy->sas_phy.attached_sas_addr, + &attached_sas_address, sizeof(attached_sas_address)); + } else if (iphy->protocol == SCIC_SDS_PHY_PROTOCOL_SAS) { + iphy->sas_phy.oob_mode = SAS_OOB_MODE; + iphy->sas_phy.frame_rcvd_size = sizeof(struct sas_identify_frame); + + /* Copy the attached SAS address from the IAF */ + memcpy(iphy->sas_phy.attached_sas_addr, + iphy->frame_rcvd.iaf.sas_addr, SAS_ADDR_SIZE); + } else { + dev_err(&isci_host->pdev->dev, "%s: unkown target\n", __func__); + success = false; + } + + iphy->sas_phy.phy->negotiated_linkrate = sci_phy_linkrate(iphy); + + spin_unlock_irqrestore(&iphy->sas_phy.frame_rcvd_lock, flags); + + /* Notify libsas that we have an address frame, if indeed + * we've found an SSP, SMP, or STP target */ + if (success) + isci_host->sas_ha.notify_port_event(&iphy->sas_phy, + PORTE_BYTES_DMAED); +} + + +/** + * isci_port_link_down() - This function is called by the sci core when a link + * becomes inactive. + * @isci_host: This parameter specifies the isci host object. + * @phy: This parameter specifies the isci phy with the active link. + * @port: This parameter specifies the isci port with the active link. + * + */ +static void isci_port_link_down(struct isci_host *isci_host, + struct isci_phy *isci_phy, + struct isci_port *isci_port) +{ + struct isci_remote_device *isci_device; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_port = %p\n", __func__, isci_port); + + if (isci_port) { + + /* check to see if this is the last phy on this port. */ + if (isci_phy->sas_phy.port && + isci_phy->sas_phy.port->num_phys == 1) { + atomic_inc(&isci_port->event); + isci_port_bcn_enable(isci_host, isci_port); + + /* change the state for all devices on this port. The + * next task sent to this device will be returned as + * SAS_TASK_UNDELIVERED, and the scsi mid layer will + * remove the target + */ + list_for_each_entry(isci_device, + &isci_port->remote_dev_list, + node) { + dev_dbg(&isci_host->pdev->dev, + "%s: isci_device = %p\n", + __func__, isci_device); + set_bit(IDEV_GONE, &isci_device->flags); + } + } + isci_port_change_state(isci_port, isci_stopping); + } + + /* Notify libsas of the borken link, this will trigger calls to our + * isci_port_deformed and isci_dev_gone functions. + */ + sas_phy_disconnected(&isci_phy->sas_phy); + isci_host->sas_ha.notify_phy_event(&isci_phy->sas_phy, + PHYE_LOSS_OF_SIGNAL); + + isci_phy->isci_port = NULL; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_port = %p - Done\n", __func__, isci_port); +} + + +/** + * isci_port_ready() - This function is called by the sci core when a link + * becomes ready. + * @isci_host: This parameter specifies the isci host object. + * @port: This parameter specifies the sci port with the active link. + * + */ +static void isci_port_ready(struct isci_host *isci_host, struct isci_port *isci_port) +{ + dev_dbg(&isci_host->pdev->dev, + "%s: isci_port = %p\n", __func__, isci_port); + + complete_all(&isci_port->start_complete); + isci_port_change_state(isci_port, isci_ready); + return; +} + +/** + * isci_port_not_ready() - This function is called by the sci core when a link + * is not ready. All remote devices on this link will be removed if they are + * in the stopping state. + * @isci_host: This parameter specifies the isci host object. + * @port: This parameter specifies the sci port with the active link. + * + */ +static void isci_port_not_ready(struct isci_host *isci_host, struct isci_port *isci_port) +{ + dev_dbg(&isci_host->pdev->dev, + "%s: isci_port = %p\n", __func__, isci_port); +} + +static void isci_port_stop_complete(struct isci_host *ihost, + struct isci_port *iport, + enum sci_status completion_status) +{ + dev_dbg(&ihost->pdev->dev, "Port stop complete\n"); +} + +/** + * isci_port_hard_reset_complete() - This function is called by the sci core + * when the hard reset complete notification has been received. + * @port: This parameter specifies the sci port with the active link. + * @completion_status: This parameter specifies the core status for the reset + * process. + * + */ +static void isci_port_hard_reset_complete(struct isci_port *isci_port, + enum sci_status completion_status) +{ + dev_dbg(&isci_port->isci_host->pdev->dev, + "%s: isci_port = %p, completion_status=%x\n", + __func__, isci_port, completion_status); + + /* Save the status of the hard reset from the port. */ + isci_port->hard_reset_status = completion_status; + + complete_all(&isci_port->hard_reset_complete); +} + +/* This method will return a true value if the specified phy can be assigned to + * this port The following is a list of phys for each port that are allowed: - + * Port 0 - 3 2 1 0 - Port 1 - 1 - Port 2 - 3 2 - Port 3 - 3 This method + * doesn't preclude all configurations. It merely ensures that a phy is part + * of the allowable set of phy identifiers for that port. For example, one + * could assign phy 3 to port 0 and no other phys. Please refer to + * sci_port_is_phy_mask_valid() for information regarding whether the + * phy_mask for a port can be supported. bool true if this is a valid phy + * assignment for the port false if this is not a valid phy assignment for the + * port + */ +bool sci_port_is_valid_phy_assignment(struct isci_port *iport, u32 phy_index) +{ + struct isci_host *ihost = iport->owning_controller; + struct sci_user_parameters *user = &ihost->user_parameters; + + /* Initialize to invalid value. */ + u32 existing_phy_index = SCI_MAX_PHYS; + u32 index; + + if ((iport->physical_port_index == 1) && (phy_index != 1)) + return false; + + if (iport->physical_port_index == 3 && phy_index != 3) + return false; + + if (iport->physical_port_index == 2 && + (phy_index == 0 || phy_index == 1)) + return false; + + for (index = 0; index < SCI_MAX_PHYS; index++) + if (iport->phy_table[index] && index != phy_index) + existing_phy_index = index; + + /* Ensure that all of the phys in the port are capable of + * operating at the same maximum link rate. + */ + if (existing_phy_index < SCI_MAX_PHYS && + user->phys[phy_index].max_speed_generation != + user->phys[existing_phy_index].max_speed_generation) + return false; + + return true; +} + +/** + * + * @sci_port: This is the port object for which to determine if the phy mask + * can be supported. + * + * This method will return a true value if the port's phy mask can be supported + * by the SCU. The following is a list of valid PHY mask configurations for + * each port: - Port 0 - [[3 2] 1] 0 - Port 1 - [1] - Port 2 - [[3] 2] + * - Port 3 - [3] This method returns a boolean indication specifying if the + * phy mask can be supported. true if this is a valid phy assignment for the + * port false if this is not a valid phy assignment for the port + */ +static bool sci_port_is_phy_mask_valid( + struct isci_port *iport, + u32 phy_mask) +{ + if (iport->physical_port_index == 0) { + if (((phy_mask & 0x0F) == 0x0F) + || ((phy_mask & 0x03) == 0x03) + || ((phy_mask & 0x01) == 0x01) + || (phy_mask == 0)) + return true; + } else if (iport->physical_port_index == 1) { + if (((phy_mask & 0x02) == 0x02) + || (phy_mask == 0)) + return true; + } else if (iport->physical_port_index == 2) { + if (((phy_mask & 0x0C) == 0x0C) + || ((phy_mask & 0x04) == 0x04) + || (phy_mask == 0)) + return true; + } else if (iport->physical_port_index == 3) { + if (((phy_mask & 0x08) == 0x08) + || (phy_mask == 0)) + return true; + } + + return false; +} + +/* + * This method retrieves a currently active (i.e. connected) phy contained in + * the port. Currently, the lowest order phy that is connected is returned. + * This method returns a pointer to a SCIS_SDS_PHY object. NULL This value is + * returned if there are no currently active (i.e. connected to a remote end + * point) phys contained in the port. All other values specify a struct sci_phy + * object that is active in the port. + */ +static struct isci_phy *sci_port_get_a_connected_phy(struct isci_port *iport) +{ + u32 index; + struct isci_phy *iphy; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + /* Ensure that the phy is both part of the port and currently + * connected to the remote end-point. + */ + iphy = iport->phy_table[index]; + if (iphy && sci_port_active_phy(iport, iphy)) + return iphy; + } + + return NULL; +} + +static enum sci_status sci_port_set_phy(struct isci_port *iport, struct isci_phy *iphy) +{ + /* Check to see if we can add this phy to a port + * that means that the phy is not part of a port and that the port does + * not already have a phy assinged to the phy index. + */ + if (!iport->phy_table[iphy->phy_index] && + !phy_get_non_dummy_port(iphy) && + sci_port_is_valid_phy_assignment(iport, iphy->phy_index)) { + /* Phy is being added in the stopped state so we are in MPC mode + * make logical port index = physical port index + */ + iport->logical_port_index = iport->physical_port_index; + iport->phy_table[iphy->phy_index] = iphy; + sci_phy_set_port(iphy, iport); + + return SCI_SUCCESS; + } + + return SCI_FAILURE; +} + +static enum sci_status sci_port_clear_phy(struct isci_port *iport, struct isci_phy *iphy) +{ + /* Make sure that this phy is part of this port */ + if (iport->phy_table[iphy->phy_index] == iphy && + phy_get_non_dummy_port(iphy) == iport) { + struct isci_host *ihost = iport->owning_controller; + + /* Yep it is assigned to this port so remove it */ + sci_phy_set_port(iphy, &ihost->ports[SCI_MAX_PORTS]); + iport->phy_table[iphy->phy_index] = NULL; + return SCI_SUCCESS; + } + + return SCI_FAILURE; +} + +void sci_port_get_sas_address(struct isci_port *iport, struct sci_sas_address *sas) +{ + u32 index; + + sas->high = 0; + sas->low = 0; + for (index = 0; index < SCI_MAX_PHYS; index++) + if (iport->phy_table[index]) + sci_phy_get_sas_address(iport->phy_table[index], sas); +} + +void sci_port_get_attached_sas_address(struct isci_port *iport, struct sci_sas_address *sas) +{ + struct isci_phy *iphy; + + /* + * Ensure that the phy is both part of the port and currently + * connected to the remote end-point. + */ + iphy = sci_port_get_a_connected_phy(iport); + if (iphy) { + if (iphy->protocol != SCIC_SDS_PHY_PROTOCOL_SATA) { + sci_phy_get_attached_sas_address(iphy, sas); + } else { + sci_phy_get_sas_address(iphy, sas); + sas->low += iphy->phy_index; + } + } else { + sas->high = 0; + sas->low = 0; + } +} + +/** + * sci_port_construct_dummy_rnc() - create dummy rnc for si workaround + * + * @sci_port: logical port on which we need to create the remote node context + * @rni: remote node index for this remote node context. + * + * This routine will construct a dummy remote node context data structure + * This structure will be posted to the hardware to work around a scheduler + * error in the hardware. + */ +static void sci_port_construct_dummy_rnc(struct isci_port *iport, u16 rni) +{ + union scu_remote_node_context *rnc; + + rnc = &iport->owning_controller->remote_node_context_table[rni]; + + memset(rnc, 0, sizeof(union scu_remote_node_context)); + + rnc->ssp.remote_sas_address_hi = 0; + rnc->ssp.remote_sas_address_lo = 0; + + rnc->ssp.remote_node_index = rni; + rnc->ssp.remote_node_port_width = 1; + rnc->ssp.logical_port_index = iport->physical_port_index; + + rnc->ssp.nexus_loss_timer_enable = false; + rnc->ssp.check_bit = false; + rnc->ssp.is_valid = true; + rnc->ssp.is_remote_node_context = true; + rnc->ssp.function_number = 0; + rnc->ssp.arbitration_wait_time = 0; +} + +/* + * construct a dummy task context data structure. This + * structure will be posted to the hardwre to work around a scheduler error + * in the hardware. + */ +static void sci_port_construct_dummy_task(struct isci_port *iport, u16 tag) +{ + struct isci_host *ihost = iport->owning_controller; + struct scu_task_context *task_context; + + task_context = &ihost->task_context_table[ISCI_TAG_TCI(tag)]; + memset(task_context, 0, sizeof(struct scu_task_context)); + + task_context->initiator_request = 1; + task_context->connection_rate = 1; + task_context->logical_port_index = iport->physical_port_index; + task_context->protocol_type = SCU_TASK_CONTEXT_PROTOCOL_SSP; + task_context->task_index = ISCI_TAG_TCI(tag); + task_context->valid = SCU_TASK_CONTEXT_VALID; + task_context->context_type = SCU_TASK_CONTEXT_TYPE; + task_context->remote_node_index = iport->reserved_rni; + task_context->do_not_dma_ssp_good_response = 1; + task_context->task_phase = 0x01; +} + +static void sci_port_destroy_dummy_resources(struct isci_port *iport) +{ + struct isci_host *ihost = iport->owning_controller; + + if (iport->reserved_tag != SCI_CONTROLLER_INVALID_IO_TAG) + isci_free_tag(ihost, iport->reserved_tag); + + if (iport->reserved_rni != SCU_DUMMY_INDEX) + sci_remote_node_table_release_remote_node_index(&ihost->available_remote_nodes, + 1, iport->reserved_rni); + + iport->reserved_rni = SCU_DUMMY_INDEX; + iport->reserved_tag = SCI_CONTROLLER_INVALID_IO_TAG; +} + +void sci_port_setup_transports(struct isci_port *iport, u32 device_id) +{ + u8 index; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + if (iport->active_phy_mask & (1 << index)) + sci_phy_setup_transport(iport->phy_table[index], device_id); + } +} + +static void sci_port_activate_phy(struct isci_port *iport, struct isci_phy *iphy, + bool do_notify_user) +{ + struct isci_host *ihost = iport->owning_controller; + + if (iphy->protocol != SCIC_SDS_PHY_PROTOCOL_SATA) + sci_phy_resume(iphy); + + iport->active_phy_mask |= 1 << iphy->phy_index; + + sci_controller_clear_invalid_phy(ihost, iphy); + + if (do_notify_user == true) + isci_port_link_up(ihost, iport, iphy); +} + +void sci_port_deactivate_phy(struct isci_port *iport, struct isci_phy *iphy, + bool do_notify_user) +{ + struct isci_host *ihost = iport->owning_controller; + + iport->active_phy_mask &= ~(1 << iphy->phy_index); + + iphy->max_negotiated_speed = SAS_LINK_RATE_UNKNOWN; + + /* Re-assign the phy back to the LP as if it were a narrow port */ + writel(iphy->phy_index, + &iport->port_pe_configuration_register[iphy->phy_index]); + + if (do_notify_user == true) + isci_port_link_down(ihost, iphy, iport); +} + +static void sci_port_invalid_link_up(struct isci_port *iport, struct isci_phy *iphy) +{ + struct isci_host *ihost = iport->owning_controller; + + /* + * Check to see if we have alreay reported this link as bad and if + * not go ahead and tell the SCI_USER that we have discovered an + * invalid link. + */ + if ((ihost->invalid_phy_mask & (1 << iphy->phy_index)) == 0) { + ihost->invalid_phy_mask |= 1 << iphy->phy_index; + dev_warn(&ihost->pdev->dev, "Invalid link up!\n"); + } +} + +static bool is_port_ready_state(enum sci_port_states state) +{ + switch (state) { + case SCI_PORT_READY: + case SCI_PORT_SUB_WAITING: + case SCI_PORT_SUB_OPERATIONAL: + case SCI_PORT_SUB_CONFIGURING: + return true; + default: + return false; + } +} + +/* flag dummy rnc hanling when exiting a ready state */ +static void port_state_machine_change(struct isci_port *iport, + enum sci_port_states state) +{ + struct sci_base_state_machine *sm = &iport->sm; + enum sci_port_states old_state = sm->current_state_id; + + if (is_port_ready_state(old_state) && !is_port_ready_state(state)) + iport->ready_exit = true; + + sci_change_state(sm, state); + iport->ready_exit = false; +} + +/** + * sci_port_general_link_up_handler - phy can be assigned to port? + * @sci_port: sci_port object for which has a phy that has gone link up. + * @sci_phy: This is the struct isci_phy object that has gone link up. + * @do_notify_user: This parameter specifies whether to inform the user (via + * sci_port_link_up()) as to the fact that a new phy as become ready. + * + * Determine if this phy can be assigned to this + * port . If the phy is not a valid PHY for + * this port then the function will notify the user. A PHY can only be + * part of a port if it's attached SAS ADDRESS is the same as all other PHYs in + * the same port. none + */ +static void sci_port_general_link_up_handler(struct isci_port *iport, + struct isci_phy *iphy, + bool do_notify_user) +{ + struct sci_sas_address port_sas_address; + struct sci_sas_address phy_sas_address; + + sci_port_get_attached_sas_address(iport, &port_sas_address); + sci_phy_get_attached_sas_address(iphy, &phy_sas_address); + + /* If the SAS address of the new phy matches the SAS address of + * other phys in the port OR this is the first phy in the port, + * then activate the phy and allow it to be used for operations + * in this port. + */ + if ((phy_sas_address.high == port_sas_address.high && + phy_sas_address.low == port_sas_address.low) || + iport->active_phy_mask == 0) { + struct sci_base_state_machine *sm = &iport->sm; + + sci_port_activate_phy(iport, iphy, do_notify_user); + if (sm->current_state_id == SCI_PORT_RESETTING) + port_state_machine_change(iport, SCI_PORT_READY); + } else + sci_port_invalid_link_up(iport, iphy); +} + + + +/** + * This method returns false if the port only has a single phy object assigned. + * If there are no phys or more than one phy then the method will return + * true. + * @sci_port: The port for which the wide port condition is to be checked. + * + * bool true Is returned if this is a wide ported port. false Is returned if + * this is a narrow port. + */ +static bool sci_port_is_wide(struct isci_port *iport) +{ + u32 index; + u32 phy_count = 0; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + if (iport->phy_table[index] != NULL) { + phy_count++; + } + } + + return phy_count != 1; +} + +/** + * This method is called by the PHY object when the link is detected. if the + * port wants the PHY to continue on to the link up state then the port + * layer must return true. If the port object returns false the phy object + * must halt its attempt to go link up. + * @sci_port: The port associated with the phy object. + * @sci_phy: The phy object that is trying to go link up. + * + * true if the phy object can continue to the link up condition. true Is + * returned if this phy can continue to the ready state. false Is returned if + * can not continue on to the ready state. This notification is in place for + * wide ports and direct attached phys. Since there are no wide ported SATA + * devices this could become an invalid port configuration. + */ +bool sci_port_link_detected( + struct isci_port *iport, + struct isci_phy *iphy) +{ + if ((iport->logical_port_index != SCIC_SDS_DUMMY_PORT) && + (iphy->protocol == SCIC_SDS_PHY_PROTOCOL_SATA) && + sci_port_is_wide(iport)) { + sci_port_invalid_link_up(iport, iphy); + + return false; + } + + return true; +} + +static void port_timeout(unsigned long data) +{ + struct sci_timer *tmr = (struct sci_timer *)data; + struct isci_port *iport = container_of(tmr, typeof(*iport), timer); + struct isci_host *ihost = iport->owning_controller; + unsigned long flags; + u32 current_state; + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + current_state = iport->sm.current_state_id; + + if (current_state == SCI_PORT_RESETTING) { + /* if the port is still in the resetting state then the timeout + * fired before the reset completed. + */ + port_state_machine_change(iport, SCI_PORT_FAILED); + } else if (current_state == SCI_PORT_STOPPED) { + /* if the port is stopped then the start request failed In this + * case stay in the stopped state. + */ + dev_err(sciport_to_dev(iport), + "%s: SCIC Port 0x%p failed to stop before tiemout.\n", + __func__, + iport); + } else if (current_state == SCI_PORT_STOPPING) { + /* if the port is still stopping then the stop has not completed */ + isci_port_stop_complete(iport->owning_controller, + iport, + SCI_FAILURE_TIMEOUT); + } else { + /* The port is in the ready state and we have a timer + * reporting a timeout this should not happen. + */ + dev_err(sciport_to_dev(iport), + "%s: SCIC Port 0x%p is processing a timeout operation " + "in state %d.\n", __func__, iport, current_state); + } + +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +/* --------------------------------------------------------------------------- */ + +/** + * This function updates the hardwares VIIT entry for this port. + * + * + */ +static void sci_port_update_viit_entry(struct isci_port *iport) +{ + struct sci_sas_address sas_address; + + sci_port_get_sas_address(iport, &sas_address); + + writel(sas_address.high, + &iport->viit_registers->initiator_sas_address_hi); + writel(sas_address.low, + &iport->viit_registers->initiator_sas_address_lo); + + /* This value get cleared just in case its not already cleared */ + writel(0, &iport->viit_registers->reserved); + + /* We are required to update the status register last */ + writel(SCU_VIIT_ENTRY_ID_VIIT | + SCU_VIIT_IPPT_INITIATOR | + ((1 << iport->physical_port_index) << SCU_VIIT_ENTRY_LPVIE_SHIFT) | + SCU_VIIT_STATUS_ALL_VALID, + &iport->viit_registers->status); +} + +enum sas_linkrate sci_port_get_max_allowed_speed(struct isci_port *iport) +{ + u16 index; + struct isci_phy *iphy; + enum sas_linkrate max_allowed_speed = SAS_LINK_RATE_6_0_GBPS; + + /* + * Loop through all of the phys in this port and find the phy with the + * lowest maximum link rate. */ + for (index = 0; index < SCI_MAX_PHYS; index++) { + iphy = iport->phy_table[index]; + if (iphy && sci_port_active_phy(iport, iphy) && + iphy->max_negotiated_speed < max_allowed_speed) + max_allowed_speed = iphy->max_negotiated_speed; + } + + return max_allowed_speed; +} + +static void sci_port_suspend_port_task_scheduler(struct isci_port *iport) +{ + u32 pts_control_value; + + pts_control_value = readl(&iport->port_task_scheduler_registers->control); + pts_control_value |= SCU_PTSxCR_GEN_BIT(SUSPEND); + writel(pts_control_value, &iport->port_task_scheduler_registers->control); +} + +/** + * sci_port_post_dummy_request() - post dummy/workaround request + * @sci_port: port to post task + * + * Prevent the hardware scheduler from posting new requests to the front + * of the scheduler queue causing a starvation problem for currently + * ongoing requests. + * + */ +static void sci_port_post_dummy_request(struct isci_port *iport) +{ + struct isci_host *ihost = iport->owning_controller; + u16 tag = iport->reserved_tag; + struct scu_task_context *tc; + u32 command; + + tc = &ihost->task_context_table[ISCI_TAG_TCI(tag)]; + tc->abort = 0; + + command = SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC | + iport->physical_port_index << SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT | + ISCI_TAG_TCI(tag); + + sci_controller_post_request(ihost, command); +} + +/** + * This routine will abort the dummy request. This will alow the hardware to + * power down parts of the silicon to save power. + * + * @sci_port: The port on which the task must be aborted. + * + */ +static void sci_port_abort_dummy_request(struct isci_port *iport) +{ + struct isci_host *ihost = iport->owning_controller; + u16 tag = iport->reserved_tag; + struct scu_task_context *tc; + u32 command; + + tc = &ihost->task_context_table[ISCI_TAG_TCI(tag)]; + tc->abort = 1; + + command = SCU_CONTEXT_COMMAND_REQUEST_POST_TC_ABORT | + iport->physical_port_index << SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT | + ISCI_TAG_TCI(tag); + + sci_controller_post_request(ihost, command); +} + +/** + * + * @sci_port: This is the struct isci_port object to resume. + * + * This method will resume the port task scheduler for this port object. none + */ +static void +sci_port_resume_port_task_scheduler(struct isci_port *iport) +{ + u32 pts_control_value; + + pts_control_value = readl(&iport->port_task_scheduler_registers->control); + pts_control_value &= ~SCU_PTSxCR_GEN_BIT(SUSPEND); + writel(pts_control_value, &iport->port_task_scheduler_registers->control); +} + +static void sci_port_ready_substate_waiting_enter(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + sci_port_suspend_port_task_scheduler(iport); + + iport->not_ready_reason = SCIC_PORT_NOT_READY_NO_ACTIVE_PHYS; + + if (iport->active_phy_mask != 0) { + /* At least one of the phys on the port is ready */ + port_state_machine_change(iport, + SCI_PORT_SUB_OPERATIONAL); + } +} + +static void sci_port_ready_substate_operational_enter(struct sci_base_state_machine *sm) +{ + u32 index; + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + struct isci_host *ihost = iport->owning_controller; + + isci_port_ready(ihost, iport); + + for (index = 0; index < SCI_MAX_PHYS; index++) { + if (iport->phy_table[index]) { + writel(iport->physical_port_index, + &iport->port_pe_configuration_register[ + iport->phy_table[index]->phy_index]); + } + } + + sci_port_update_viit_entry(iport); + + sci_port_resume_port_task_scheduler(iport); + + /* + * Post the dummy task for the port so the hardware can schedule + * io correctly + */ + sci_port_post_dummy_request(iport); +} + +static void sci_port_invalidate_dummy_remote_node(struct isci_port *iport) +{ + struct isci_host *ihost = iport->owning_controller; + u8 phys_index = iport->physical_port_index; + union scu_remote_node_context *rnc; + u16 rni = iport->reserved_rni; + u32 command; + + rnc = &ihost->remote_node_context_table[rni]; + + rnc->ssp.is_valid = false; + + /* ensure the preceding tc abort request has reached the + * controller and give it ample time to act before posting the rnc + * invalidate + */ + readl(&ihost->smu_registers->interrupt_status); /* flush */ + udelay(10); + + command = SCU_CONTEXT_COMMAND_POST_RNC_INVALIDATE | + phys_index << SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT | rni; + + sci_controller_post_request(ihost, command); +} + +/** + * + * @object: This is the object which is cast to a struct isci_port object. + * + * This method will perform the actions required by the struct isci_port on + * exiting the SCI_PORT_SUB_OPERATIONAL. This function reports + * the port not ready and suspends the port task scheduler. none + */ +static void sci_port_ready_substate_operational_exit(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + struct isci_host *ihost = iport->owning_controller; + + /* + * Kill the dummy task for this port if it has not yet posted + * the hardware will treat this as a NOP and just return abort + * complete. + */ + sci_port_abort_dummy_request(iport); + + isci_port_not_ready(ihost, iport); + + if (iport->ready_exit) + sci_port_invalidate_dummy_remote_node(iport); +} + +static void sci_port_ready_substate_configuring_enter(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + struct isci_host *ihost = iport->owning_controller; + + if (iport->active_phy_mask == 0) { + isci_port_not_ready(ihost, iport); + + port_state_machine_change(iport, + SCI_PORT_SUB_WAITING); + } else if (iport->started_request_count == 0) + port_state_machine_change(iport, + SCI_PORT_SUB_OPERATIONAL); +} + +static void sci_port_ready_substate_configuring_exit(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + sci_port_suspend_port_task_scheduler(iport); + if (iport->ready_exit) + sci_port_invalidate_dummy_remote_node(iport); +} + +enum sci_status sci_port_start(struct isci_port *iport) +{ + struct isci_host *ihost = iport->owning_controller; + enum sci_status status = SCI_SUCCESS; + enum sci_port_states state; + u32 phy_mask; + + state = iport->sm.current_state_id; + if (state != SCI_PORT_STOPPED) { + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + if (iport->assigned_device_count > 0) { + /* TODO This is a start failure operation because + * there are still devices assigned to this port. + * There must be no devices assigned to a port on a + * start operation. + */ + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + + if (iport->reserved_rni == SCU_DUMMY_INDEX) { + u16 rni = sci_remote_node_table_allocate_remote_node( + &ihost->available_remote_nodes, 1); + + if (rni != SCU_DUMMY_INDEX) + sci_port_construct_dummy_rnc(iport, rni); + else + status = SCI_FAILURE_INSUFFICIENT_RESOURCES; + iport->reserved_rni = rni; + } + + if (iport->reserved_tag == SCI_CONTROLLER_INVALID_IO_TAG) { + u16 tag; + + tag = isci_alloc_tag(ihost); + if (tag == SCI_CONTROLLER_INVALID_IO_TAG) + status = SCI_FAILURE_INSUFFICIENT_RESOURCES; + else + sci_port_construct_dummy_task(iport, tag); + iport->reserved_tag = tag; + } + + if (status == SCI_SUCCESS) { + phy_mask = sci_port_get_phys(iport); + + /* + * There are one or more phys assigned to this port. Make sure + * the port's phy mask is in fact legal and supported by the + * silicon. + */ + if (sci_port_is_phy_mask_valid(iport, phy_mask) == true) { + port_state_machine_change(iport, + SCI_PORT_READY); + + return SCI_SUCCESS; + } + status = SCI_FAILURE; + } + + if (status != SCI_SUCCESS) + sci_port_destroy_dummy_resources(iport); + + return status; +} + +enum sci_status sci_port_stop(struct isci_port *iport) +{ + enum sci_port_states state; + + state = iport->sm.current_state_id; + switch (state) { + case SCI_PORT_STOPPED: + return SCI_SUCCESS; + case SCI_PORT_SUB_WAITING: + case SCI_PORT_SUB_OPERATIONAL: + case SCI_PORT_SUB_CONFIGURING: + case SCI_PORT_RESETTING: + port_state_machine_change(iport, + SCI_PORT_STOPPING); + return SCI_SUCCESS; + default: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +static enum sci_status sci_port_hard_reset(struct isci_port *iport, u32 timeout) +{ + enum sci_status status = SCI_FAILURE_INVALID_PHY; + struct isci_phy *iphy = NULL; + enum sci_port_states state; + u32 phy_index; + + state = iport->sm.current_state_id; + if (state != SCI_PORT_SUB_OPERATIONAL) { + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + /* Select a phy on which we can send the hard reset request. */ + for (phy_index = 0; phy_index < SCI_MAX_PHYS && !iphy; phy_index++) { + iphy = iport->phy_table[phy_index]; + if (iphy && !sci_port_active_phy(iport, iphy)) { + /* + * We found a phy but it is not ready select + * different phy + */ + iphy = NULL; + } + } + + /* If we have a phy then go ahead and start the reset procedure */ + if (!iphy) + return status; + status = sci_phy_reset(iphy); + + if (status != SCI_SUCCESS) + return status; + + sci_mod_timer(&iport->timer, timeout); + iport->not_ready_reason = SCIC_PORT_NOT_READY_HARD_RESET_REQUESTED; + + port_state_machine_change(iport, SCI_PORT_RESETTING); + return SCI_SUCCESS; +} + +/** + * sci_port_add_phy() - + * @sci_port: This parameter specifies the port in which the phy will be added. + * @sci_phy: This parameter is the phy which is to be added to the port. + * + * This method will add a PHY to the selected port. This method returns an + * enum sci_status. SCI_SUCCESS the phy has been added to the port. Any other + * status is a failure to add the phy to the port. + */ +enum sci_status sci_port_add_phy(struct isci_port *iport, + struct isci_phy *iphy) +{ + enum sci_status status; + enum sci_port_states state; + + state = iport->sm.current_state_id; + switch (state) { + case SCI_PORT_STOPPED: { + struct sci_sas_address port_sas_address; + + /* Read the port assigned SAS Address if there is one */ + sci_port_get_sas_address(iport, &port_sas_address); + + if (port_sas_address.high != 0 && port_sas_address.low != 0) { + struct sci_sas_address phy_sas_address; + + /* Make sure that the PHY SAS Address matches the SAS Address + * for this port + */ + sci_phy_get_sas_address(iphy, &phy_sas_address); + + if (port_sas_address.high != phy_sas_address.high || + port_sas_address.low != phy_sas_address.low) + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + return sci_port_set_phy(iport, iphy); + } + case SCI_PORT_SUB_WAITING: + case SCI_PORT_SUB_OPERATIONAL: + status = sci_port_set_phy(iport, iphy); + + if (status != SCI_SUCCESS) + return status; + + sci_port_general_link_up_handler(iport, iphy, true); + iport->not_ready_reason = SCIC_PORT_NOT_READY_RECONFIGURING; + port_state_machine_change(iport, SCI_PORT_SUB_CONFIGURING); + + return status; + case SCI_PORT_SUB_CONFIGURING: + status = sci_port_set_phy(iport, iphy); + + if (status != SCI_SUCCESS) + return status; + sci_port_general_link_up_handler(iport, iphy, true); + + /* Re-enter the configuring state since this may be the last phy in + * the port. + */ + port_state_machine_change(iport, + SCI_PORT_SUB_CONFIGURING); + return SCI_SUCCESS; + default: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +/** + * sci_port_remove_phy() - + * @sci_port: This parameter specifies the port in which the phy will be added. + * @sci_phy: This parameter is the phy which is to be added to the port. + * + * This method will remove the PHY from the selected PORT. This method returns + * an enum sci_status. SCI_SUCCESS the phy has been removed from the port. Any + * other status is a failure to add the phy to the port. + */ +enum sci_status sci_port_remove_phy(struct isci_port *iport, + struct isci_phy *iphy) +{ + enum sci_status status; + enum sci_port_states state; + + state = iport->sm.current_state_id; + + switch (state) { + case SCI_PORT_STOPPED: + return sci_port_clear_phy(iport, iphy); + case SCI_PORT_SUB_OPERATIONAL: + status = sci_port_clear_phy(iport, iphy); + if (status != SCI_SUCCESS) + return status; + + sci_port_deactivate_phy(iport, iphy, true); + iport->not_ready_reason = SCIC_PORT_NOT_READY_RECONFIGURING; + port_state_machine_change(iport, + SCI_PORT_SUB_CONFIGURING); + return SCI_SUCCESS; + case SCI_PORT_SUB_CONFIGURING: + status = sci_port_clear_phy(iport, iphy); + + if (status != SCI_SUCCESS) + return status; + sci_port_deactivate_phy(iport, iphy, true); + + /* Re-enter the configuring state since this may be the last phy in + * the port + */ + port_state_machine_change(iport, + SCI_PORT_SUB_CONFIGURING); + return SCI_SUCCESS; + default: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_port_link_up(struct isci_port *iport, + struct isci_phy *iphy) +{ + enum sci_port_states state; + + state = iport->sm.current_state_id; + switch (state) { + case SCI_PORT_SUB_WAITING: + /* Since this is the first phy going link up for the port we + * can just enable it and continue + */ + sci_port_activate_phy(iport, iphy, true); + + port_state_machine_change(iport, + SCI_PORT_SUB_OPERATIONAL); + return SCI_SUCCESS; + case SCI_PORT_SUB_OPERATIONAL: + sci_port_general_link_up_handler(iport, iphy, true); + return SCI_SUCCESS; + case SCI_PORT_RESETTING: + /* TODO We should make sure that the phy that has gone + * link up is the same one on which we sent the reset. It is + * possible that the phy on which we sent the reset is not the + * one that has gone link up and we want to make sure that + * phy being reset comes back. Consider the case where a + * reset is sent but before the hardware processes the reset it + * get a link up on the port because of a hot plug event. + * because of the reset request this phy will go link down + * almost immediately. + */ + + /* In the resetting state we don't notify the user regarding + * link up and link down notifications. + */ + sci_port_general_link_up_handler(iport, iphy, false); + return SCI_SUCCESS; + default: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_port_link_down(struct isci_port *iport, + struct isci_phy *iphy) +{ + enum sci_port_states state; + + state = iport->sm.current_state_id; + switch (state) { + case SCI_PORT_SUB_OPERATIONAL: + sci_port_deactivate_phy(iport, iphy, true); + + /* If there are no active phys left in the port, then + * transition the port to the WAITING state until such time + * as a phy goes link up + */ + if (iport->active_phy_mask == 0) + port_state_machine_change(iport, + SCI_PORT_SUB_WAITING); + return SCI_SUCCESS; + case SCI_PORT_RESETTING: + /* In the resetting state we don't notify the user regarding + * link up and link down notifications. */ + sci_port_deactivate_phy(iport, iphy, false); + return SCI_SUCCESS; + default: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_port_start_io(struct isci_port *iport, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + enum sci_port_states state; + + state = iport->sm.current_state_id; + switch (state) { + case SCI_PORT_SUB_WAITING: + return SCI_FAILURE_INVALID_STATE; + case SCI_PORT_SUB_OPERATIONAL: + iport->started_request_count++; + return SCI_SUCCESS; + default: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_port_complete_io(struct isci_port *iport, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + enum sci_port_states state; + + state = iport->sm.current_state_id; + switch (state) { + case SCI_PORT_STOPPED: + dev_warn(sciport_to_dev(iport), + "%s: in wrong state: %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + case SCI_PORT_STOPPING: + sci_port_decrement_request_count(iport); + + if (iport->started_request_count == 0) + port_state_machine_change(iport, + SCI_PORT_STOPPED); + break; + case SCI_PORT_READY: + case SCI_PORT_RESETTING: + case SCI_PORT_FAILED: + case SCI_PORT_SUB_WAITING: + case SCI_PORT_SUB_OPERATIONAL: + sci_port_decrement_request_count(iport); + break; + case SCI_PORT_SUB_CONFIGURING: + sci_port_decrement_request_count(iport); + if (iport->started_request_count == 0) { + port_state_machine_change(iport, + SCI_PORT_SUB_OPERATIONAL); + } + break; + } + return SCI_SUCCESS; +} + +static void sci_port_enable_port_task_scheduler(struct isci_port *iport) +{ + u32 pts_control_value; + + /* enable the port task scheduler in a suspended state */ + pts_control_value = readl(&iport->port_task_scheduler_registers->control); + pts_control_value |= SCU_PTSxCR_GEN_BIT(ENABLE) | SCU_PTSxCR_GEN_BIT(SUSPEND); + writel(pts_control_value, &iport->port_task_scheduler_registers->control); +} + +static void sci_port_disable_port_task_scheduler(struct isci_port *iport) +{ + u32 pts_control_value; + + pts_control_value = readl(&iport->port_task_scheduler_registers->control); + pts_control_value &= + ~(SCU_PTSxCR_GEN_BIT(ENABLE) | SCU_PTSxCR_GEN_BIT(SUSPEND)); + writel(pts_control_value, &iport->port_task_scheduler_registers->control); +} + +static void sci_port_post_dummy_remote_node(struct isci_port *iport) +{ + struct isci_host *ihost = iport->owning_controller; + u8 phys_index = iport->physical_port_index; + union scu_remote_node_context *rnc; + u16 rni = iport->reserved_rni; + u32 command; + + rnc = &ihost->remote_node_context_table[rni]; + rnc->ssp.is_valid = true; + + command = SCU_CONTEXT_COMMAND_POST_RNC_32 | + phys_index << SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT | rni; + + sci_controller_post_request(ihost, command); + + /* ensure hardware has seen the post rnc command and give it + * ample time to act before sending the suspend + */ + readl(&ihost->smu_registers->interrupt_status); /* flush */ + udelay(10); + + command = SCU_CONTEXT_COMMAND_POST_RNC_SUSPEND_TX_RX | + phys_index << SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT | rni; + + sci_controller_post_request(ihost, command); +} + +static void sci_port_stopped_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + if (iport->sm.previous_state_id == SCI_PORT_STOPPING) { + /* + * If we enter this state becasuse of a request to stop + * the port then we want to disable the hardwares port + * task scheduler. */ + sci_port_disable_port_task_scheduler(iport); + } +} + +static void sci_port_stopped_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + /* Enable and suspend the port task scheduler */ + sci_port_enable_port_task_scheduler(iport); +} + +static void sci_port_ready_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + struct isci_host *ihost = iport->owning_controller; + u32 prev_state; + + prev_state = iport->sm.previous_state_id; + if (prev_state == SCI_PORT_RESETTING) + isci_port_hard_reset_complete(iport, SCI_SUCCESS); + else + isci_port_not_ready(ihost, iport); + + /* Post and suspend the dummy remote node context for this port. */ + sci_port_post_dummy_remote_node(iport); + + /* Start the ready substate machine */ + port_state_machine_change(iport, + SCI_PORT_SUB_WAITING); +} + +static void sci_port_resetting_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + sci_del_timer(&iport->timer); +} + +static void sci_port_stopping_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + sci_del_timer(&iport->timer); + + sci_port_destroy_dummy_resources(iport); +} + +static void sci_port_failed_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_port *iport = container_of(sm, typeof(*iport), sm); + + isci_port_hard_reset_complete(iport, SCI_FAILURE_TIMEOUT); +} + +/* --------------------------------------------------------------------------- */ + +static const struct sci_base_state sci_port_state_table[] = { + [SCI_PORT_STOPPED] = { + .enter_state = sci_port_stopped_state_enter, + .exit_state = sci_port_stopped_state_exit + }, + [SCI_PORT_STOPPING] = { + .exit_state = sci_port_stopping_state_exit + }, + [SCI_PORT_READY] = { + .enter_state = sci_port_ready_state_enter, + }, + [SCI_PORT_SUB_WAITING] = { + .enter_state = sci_port_ready_substate_waiting_enter, + }, + [SCI_PORT_SUB_OPERATIONAL] = { + .enter_state = sci_port_ready_substate_operational_enter, + .exit_state = sci_port_ready_substate_operational_exit + }, + [SCI_PORT_SUB_CONFIGURING] = { + .enter_state = sci_port_ready_substate_configuring_enter, + .exit_state = sci_port_ready_substate_configuring_exit + }, + [SCI_PORT_RESETTING] = { + .exit_state = sci_port_resetting_state_exit + }, + [SCI_PORT_FAILED] = { + .enter_state = sci_port_failed_state_enter, + } +}; + +void sci_port_construct(struct isci_port *iport, u8 index, + struct isci_host *ihost) +{ + sci_init_sm(&iport->sm, sci_port_state_table, SCI_PORT_STOPPED); + + iport->logical_port_index = SCIC_SDS_DUMMY_PORT; + iport->physical_port_index = index; + iport->active_phy_mask = 0; + iport->ready_exit = false; + + iport->owning_controller = ihost; + + iport->started_request_count = 0; + iport->assigned_device_count = 0; + + iport->reserved_rni = SCU_DUMMY_INDEX; + iport->reserved_tag = SCI_CONTROLLER_INVALID_IO_TAG; + + sci_init_timer(&iport->timer, port_timeout); + + iport->port_task_scheduler_registers = NULL; + + for (index = 0; index < SCI_MAX_PHYS; index++) + iport->phy_table[index] = NULL; +} + +void isci_port_init(struct isci_port *iport, struct isci_host *ihost, int index) +{ + INIT_LIST_HEAD(&iport->remote_dev_list); + INIT_LIST_HEAD(&iport->domain_dev_list); + spin_lock_init(&iport->state_lock); + init_completion(&iport->start_complete); + iport->isci_host = ihost; + isci_port_change_state(iport, isci_freed); + atomic_set(&iport->event, 0); +} + +/** + * isci_port_get_state() - This function gets the status of the port object. + * @isci_port: This parameter points to the isci_port object + * + * status of the object as a isci_status enum. + */ +enum isci_status isci_port_get_state( + struct isci_port *isci_port) +{ + return isci_port->status; +} + +void sci_port_broadcast_change_received(struct isci_port *iport, struct isci_phy *iphy) +{ + struct isci_host *ihost = iport->owning_controller; + + /* notify the user. */ + isci_port_bc_change_received(ihost, iport, iphy); +} + +int isci_port_perform_hard_reset(struct isci_host *ihost, struct isci_port *iport, + struct isci_phy *iphy) +{ + unsigned long flags; + enum sci_status status; + int idx, ret = TMF_RESP_FUNC_COMPLETE; + + dev_dbg(&ihost->pdev->dev, "%s: iport = %p\n", + __func__, iport); + + init_completion(&iport->hard_reset_complete); + + spin_lock_irqsave(&ihost->scic_lock, flags); + + #define ISCI_PORT_RESET_TIMEOUT SCIC_SDS_SIGNATURE_FIS_TIMEOUT + status = sci_port_hard_reset(iport, ISCI_PORT_RESET_TIMEOUT); + + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + if (status == SCI_SUCCESS) { + wait_for_completion(&iport->hard_reset_complete); + + dev_dbg(&ihost->pdev->dev, + "%s: iport = %p; hard reset completion\n", + __func__, iport); + + if (iport->hard_reset_status != SCI_SUCCESS) + ret = TMF_RESP_FUNC_FAILED; + } else { + ret = TMF_RESP_FUNC_FAILED; + + dev_err(&ihost->pdev->dev, + "%s: iport = %p; sci_port_hard_reset call" + " failed 0x%x\n", + __func__, iport, status); + + } + + /* If the hard reset for the port has failed, consider this + * the same as link failures on all phys in the port. + */ + if (ret != TMF_RESP_FUNC_COMPLETE) { + + dev_err(&ihost->pdev->dev, + "%s: iport = %p; hard reset failed " + "(0x%x) - driving explicit link fail for all phys\n", + __func__, iport, iport->hard_reset_status); + + /* Down all phys in the port. */ + spin_lock_irqsave(&ihost->scic_lock, flags); + for (idx = 0; idx < SCI_MAX_PHYS; ++idx) { + struct isci_phy *iphy = iport->phy_table[idx]; + + if (!iphy) + continue; + sci_phy_stop(iphy); + sci_phy_start(iphy); + } + spin_unlock_irqrestore(&ihost->scic_lock, flags); + } + return ret; +} + +/** + * isci_port_deformed() - This function is called by libsas when a port becomes + * inactive. + * @phy: This parameter specifies the libsas phy with the inactive port. + * + */ +void isci_port_deformed(struct asd_sas_phy *phy) +{ + pr_debug("%s: sas_phy = %p\n", __func__, phy); +} + +/** + * isci_port_formed() - This function is called by libsas when a port becomes + * active. + * @phy: This parameter specifies the libsas phy with the active port. + * + */ +void isci_port_formed(struct asd_sas_phy *phy) +{ + pr_debug("%s: sas_phy = %p, sas_port = %p\n", __func__, phy, phy->port); +} diff --git a/drivers/scsi/isci/port.h b/drivers/scsi/isci/port.h new file mode 100644 index 0000000..b50ecd4 --- /dev/null +++ b/drivers/scsi/isci/port.h @@ -0,0 +1,306 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _ISCI_PORT_H_ +#define _ISCI_PORT_H_ + +#include <scsi/libsas.h> +#include "isci.h" +#include "sas.h" +#include "phy.h" + +#define SCIC_SDS_DUMMY_PORT 0xFF + +struct isci_phy; +struct isci_host; + +enum isci_status { + isci_freed = 0x00, + isci_starting = 0x01, + isci_ready = 0x02, + isci_ready_for_io = 0x03, + isci_stopping = 0x04, + isci_stopped = 0x05, +}; + +/** + * struct isci_port - isci direct attached sas port object + * @event: counts bcns and port stop events (for bcn filtering) + * @ready_exit: several states constitute 'ready'. When exiting ready we + * need to take extra port-teardown actions that are + * skipped when exiting to another 'ready' state. + * @logical_port_index: software port index + * @physical_port_index: hardware port index + * @active_phy_mask: identifies phy members + * @reserved_tag: + * @reserved_rni: reserver for port task scheduler workaround + * @started_request_count: reference count for outstanding commands + * @not_ready_reason: set during state transitions and notified + * @timer: timeout start/stop operations + */ +struct isci_port { + enum isci_status status; + #define IPORT_BCN_BLOCKED 0 + #define IPORT_BCN_PENDING 1 + unsigned long flags; + atomic_t event; + struct isci_host *isci_host; + struct asd_sas_port sas_port; + struct list_head remote_dev_list; + spinlock_t state_lock; + struct list_head domain_dev_list; + struct completion start_complete; + struct completion hard_reset_complete; + enum sci_status hard_reset_status; + struct sci_base_state_machine sm; + bool ready_exit; + u8 logical_port_index; + u8 physical_port_index; + u8 active_phy_mask; + u16 reserved_rni; + u16 reserved_tag; + u32 started_request_count; + u32 assigned_device_count; + u32 not_ready_reason; + struct isci_phy *phy_table[SCI_MAX_PHYS]; + struct isci_host *owning_controller; + struct sci_timer timer; + struct scu_port_task_scheduler_registers __iomem *port_task_scheduler_registers; + /* XXX rework: only one register, no need to replicate per-port */ + u32 __iomem *port_pe_configuration_register; + struct scu_viit_entry __iomem *viit_registers; +}; + +enum sci_port_not_ready_reason_code { + SCIC_PORT_NOT_READY_NO_ACTIVE_PHYS, + SCIC_PORT_NOT_READY_HARD_RESET_REQUESTED, + SCIC_PORT_NOT_READY_INVALID_PORT_CONFIGURATION, + SCIC_PORT_NOT_READY_RECONFIGURING, + + SCIC_PORT_NOT_READY_REASON_CODE_MAX +}; + +struct sci_port_end_point_properties { + struct sci_sas_address sas_address; + struct sci_phy_proto protocols; +}; + +struct sci_port_properties { + u32 index; + struct sci_port_end_point_properties local; + struct sci_port_end_point_properties remote; + u32 phy_mask; +}; + +/** + * enum sci_port_states - This enumeration depicts all the states for the + * common port state machine. + * + * + */ +enum sci_port_states { + /** + * This state indicates that the port has successfully been stopped. + * In this state no new IO operations are permitted. + * This state is entered from the STOPPING state. + */ + SCI_PORT_STOPPED, + + /** + * This state indicates that the port is in the process of stopping. + * In this state no new IO operations are permitted, but existing IO + * operations are allowed to complete. + * This state is entered from the READY state. + */ + SCI_PORT_STOPPING, + + /** + * This state indicates the port is now ready. Thus, the user is + * able to perform IO operations on this port. + * This state is entered from the STARTING state. + */ + SCI_PORT_READY, + + /** + * The substate where the port is started and ready but has no + * active phys. + */ + SCI_PORT_SUB_WAITING, + + /** + * The substate where the port is started and ready and there is + * at least one phy operational. + */ + SCI_PORT_SUB_OPERATIONAL, + + /** + * The substate where the port is started and there was an + * add/remove phy event. This state is only used in Automatic + * Port Configuration Mode (APC) + */ + SCI_PORT_SUB_CONFIGURING, + + /** + * This state indicates the port is in the process of performing a hard + * reset. Thus, the user is unable to perform IO operations on this + * port. + * This state is entered from the READY state. + */ + SCI_PORT_RESETTING, + + /** + * This state indicates the port has failed a reset request. This state + * is entered when a port reset request times out. + * This state is entered from the RESETTING state. + */ + SCI_PORT_FAILED, + + +}; + +static inline void sci_port_decrement_request_count(struct isci_port *iport) +{ + if (WARN_ONCE(iport->started_request_count == 0, + "%s: tried to decrement started_request_count past 0!?", + __func__)) + /* pass */; + else + iport->started_request_count--; +} + +#define sci_port_active_phy(port, phy) \ + (((port)->active_phy_mask & (1 << (phy)->phy_index)) != 0) + +void sci_port_construct( + struct isci_port *iport, + u8 port_index, + struct isci_host *ihost); + +enum sci_status sci_port_start(struct isci_port *iport); +enum sci_status sci_port_stop(struct isci_port *iport); + +enum sci_status sci_port_add_phy( + struct isci_port *iport, + struct isci_phy *iphy); + +enum sci_status sci_port_remove_phy( + struct isci_port *iport, + struct isci_phy *iphy); + +void sci_port_setup_transports( + struct isci_port *iport, + u32 device_id); + +void isci_port_bcn_enable(struct isci_host *, struct isci_port *); + +void sci_port_deactivate_phy( + struct isci_port *iport, + struct isci_phy *iphy, + bool do_notify_user); + +bool sci_port_link_detected( + struct isci_port *iport, + struct isci_phy *iphy); + +enum sci_status sci_port_link_up(struct isci_port *iport, + struct isci_phy *iphy); +enum sci_status sci_port_link_down(struct isci_port *iport, + struct isci_phy *iphy); + +struct isci_request; +struct isci_remote_device; +enum sci_status sci_port_start_io( + struct isci_port *iport, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_status sci_port_complete_io( + struct isci_port *iport, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sas_linkrate sci_port_get_max_allowed_speed( + struct isci_port *iport); + +void sci_port_broadcast_change_received( + struct isci_port *iport, + struct isci_phy *iphy); + +bool sci_port_is_valid_phy_assignment( + struct isci_port *iport, + u32 phy_index); + +void sci_port_get_sas_address( + struct isci_port *iport, + struct sci_sas_address *sas_address); + +void sci_port_get_attached_sas_address( + struct isci_port *iport, + struct sci_sas_address *sas_address); + +enum isci_status isci_port_get_state( + struct isci_port *isci_port); + +void isci_port_formed(struct asd_sas_phy *); +void isci_port_deformed(struct asd_sas_phy *); + +void isci_port_init( + struct isci_port *port, + struct isci_host *host, + int index); + +int isci_port_perform_hard_reset(struct isci_host *ihost, struct isci_port *iport, + struct isci_phy *iphy); +#endif /* !defined(_ISCI_PORT_H_) */ diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c new file mode 100644 index 0000000..486b113 --- /dev/null +++ b/drivers/scsi/isci/port_config.c @@ -0,0 +1,754 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "host.h" + +#define SCIC_SDS_MPC_RECONFIGURATION_TIMEOUT (10) +#define SCIC_SDS_APC_RECONFIGURATION_TIMEOUT (10) +#define SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION (100) + +enum SCIC_SDS_APC_ACTIVITY { + SCIC_SDS_APC_SKIP_PHY, + SCIC_SDS_APC_ADD_PHY, + SCIC_SDS_APC_START_TIMER, + + SCIC_SDS_APC_ACTIVITY_MAX +}; + +/* + * ****************************************************************************** + * General port configuration agent routines + * ****************************************************************************** */ + +/** + * + * @address_one: A SAS Address to be compared. + * @address_two: A SAS Address to be compared. + * + * Compare the two SAS Address and if SAS Address One is greater than SAS + * Address Two then return > 0 else if SAS Address One is less than SAS Address + * Two return < 0 Otherwise they are the same return 0 A signed value of x > 0 + * > y where x is returned for Address One > Address Two y is returned for + * Address One < Address Two 0 is returned ofr Address One = Address Two + */ +static s32 sci_sas_address_compare( + struct sci_sas_address address_one, + struct sci_sas_address address_two) +{ + if (address_one.high > address_two.high) { + return 1; + } else if (address_one.high < address_two.high) { + return -1; + } else if (address_one.low > address_two.low) { + return 1; + } else if (address_one.low < address_two.low) { + return -1; + } + + /* The two SAS Address must be identical */ + return 0; +} + +/** + * + * @controller: The controller object used for the port search. + * @phy: The phy object to match. + * + * This routine will find a matching port for the phy. This means that the + * port and phy both have the same broadcast sas address and same received sas + * address. The port address or the NULL if there is no matching + * port. port address if the port can be found to match the phy. + * NULL if there is no matching port for the phy. + */ +static struct isci_port *sci_port_configuration_agent_find_port( + struct isci_host *ihost, + struct isci_phy *iphy) +{ + u8 i; + struct sci_sas_address port_sas_address; + struct sci_sas_address port_attached_device_address; + struct sci_sas_address phy_sas_address; + struct sci_sas_address phy_attached_device_address; + + /* + * Since this phy can be a member of a wide port check to see if one or + * more phys match the sent and received SAS address as this phy in which + * case it should participate in the same port. + */ + sci_phy_get_sas_address(iphy, &phy_sas_address); + sci_phy_get_attached_sas_address(iphy, &phy_attached_device_address); + + for (i = 0; i < ihost->logical_port_entries; i++) { + struct isci_port *iport = &ihost->ports[i]; + + sci_port_get_sas_address(iport, &port_sas_address); + sci_port_get_attached_sas_address(iport, &port_attached_device_address); + + if (sci_sas_address_compare(port_sas_address, phy_sas_address) == 0 && + sci_sas_address_compare(port_attached_device_address, phy_attached_device_address) == 0) + return iport; + } + + return NULL; +} + +/** + * + * @controller: This is the controller object that contains the port agent + * @port_agent: This is the port configruation agent for the controller. + * + * This routine will validate the port configuration is correct for the SCU + * hardware. The SCU hardware allows for port configurations as follows. LP0 + * -> (PE0), (PE0, PE1), (PE0, PE1, PE2, PE3) LP1 -> (PE1) LP2 -> (PE2), (PE2, + * PE3) LP3 -> (PE3) enum sci_status SCI_SUCCESS the port configuration is valid for + * this port configuration agent. SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION + * the port configuration is not valid for this port configuration agent. + */ +static enum sci_status sci_port_configuration_agent_validate_ports( + struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent) +{ + struct sci_sas_address first_address; + struct sci_sas_address second_address; + + /* + * Sanity check the max ranges for all the phys the max index + * is always equal to the port range index */ + if (port_agent->phy_valid_port_range[0].max_index != 0 || + port_agent->phy_valid_port_range[1].max_index != 1 || + port_agent->phy_valid_port_range[2].max_index != 2 || + port_agent->phy_valid_port_range[3].max_index != 3) + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + + /* + * This is a request to configure a single x4 port or at least attempt + * to make all the phys into a single port */ + if (port_agent->phy_valid_port_range[0].min_index == 0 && + port_agent->phy_valid_port_range[1].min_index == 0 && + port_agent->phy_valid_port_range[2].min_index == 0 && + port_agent->phy_valid_port_range[3].min_index == 0) + return SCI_SUCCESS; + + /* + * This is a degenerate case where phy 1 and phy 2 are assigned + * to the same port this is explicitly disallowed by the hardware + * unless they are part of the same x4 port and this condition was + * already checked above. */ + if (port_agent->phy_valid_port_range[2].min_index == 1) { + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + + /* + * PE0 and PE3 can never have the same SAS Address unless they + * are part of the same x4 wide port and we have already checked + * for this condition. */ + sci_phy_get_sas_address(&ihost->phys[0], &first_address); + sci_phy_get_sas_address(&ihost->phys[3], &second_address); + + if (sci_sas_address_compare(first_address, second_address) == 0) { + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + + /* + * PE0 and PE1 are configured into a 2x1 ports make sure that the + * SAS Address for PE0 and PE2 are different since they can not be + * part of the same port. */ + if (port_agent->phy_valid_port_range[0].min_index == 0 && + port_agent->phy_valid_port_range[1].min_index == 1) { + sci_phy_get_sas_address(&ihost->phys[0], &first_address); + sci_phy_get_sas_address(&ihost->phys[2], &second_address); + + if (sci_sas_address_compare(first_address, second_address) == 0) { + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + } + + /* + * PE2 and PE3 are configured into a 2x1 ports make sure that the + * SAS Address for PE1 and PE3 are different since they can not be + * part of the same port. */ + if (port_agent->phy_valid_port_range[2].min_index == 2 && + port_agent->phy_valid_port_range[3].min_index == 3) { + sci_phy_get_sas_address(&ihost->phys[1], &first_address); + sci_phy_get_sas_address(&ihost->phys[3], &second_address); + + if (sci_sas_address_compare(first_address, second_address) == 0) { + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + } + + return SCI_SUCCESS; +} + +/* + * ****************************************************************************** + * Manual port configuration agent routines + * ****************************************************************************** */ + +/* verify all of the phys in the same port are using the same SAS address */ +static enum sci_status +sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent) +{ + u32 phy_mask; + u32 assigned_phy_mask; + struct sci_sas_address sas_address; + struct sci_sas_address phy_assigned_address; + u8 port_index; + u8 phy_index; + + assigned_phy_mask = 0; + sas_address.high = 0; + sas_address.low = 0; + + for (port_index = 0; port_index < SCI_MAX_PORTS; port_index++) { + phy_mask = ihost->oem_parameters.ports[port_index].phy_mask; + + if (!phy_mask) + continue; + /* + * Make sure that one or more of the phys were not already assinged to + * a different port. */ + if ((phy_mask & ~assigned_phy_mask) == 0) { + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + + /* Find the starting phy index for this round through the loop */ + for (phy_index = 0; phy_index < SCI_MAX_PHYS; phy_index++) { + if ((phy_mask & (1 << phy_index)) == 0) + continue; + sci_phy_get_sas_address(&ihost->phys[phy_index], + &sas_address); + + /* + * The phy_index can be used as the starting point for the + * port range since the hardware starts all logical ports + * the same as the PE index. */ + port_agent->phy_valid_port_range[phy_index].min_index = port_index; + port_agent->phy_valid_port_range[phy_index].max_index = phy_index; + + if (phy_index != port_index) { + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + + break; + } + + /* + * See how many additional phys are being added to this logical port. + * Note: We have not moved the current phy_index so we will actually + * compare the startting phy with itself. + * This is expected and required to add the phy to the port. */ + while (phy_index < SCI_MAX_PHYS) { + if ((phy_mask & (1 << phy_index)) == 0) + continue; + sci_phy_get_sas_address(&ihost->phys[phy_index], + &phy_assigned_address); + + if (sci_sas_address_compare(sas_address, phy_assigned_address) != 0) { + /* + * The phy mask specified that this phy is part of the same port + * as the starting phy and it is not so fail this configuration */ + return SCI_FAILURE_UNSUPPORTED_PORT_CONFIGURATION; + } + + port_agent->phy_valid_port_range[phy_index].min_index = port_index; + port_agent->phy_valid_port_range[phy_index].max_index = phy_index; + + sci_port_add_phy(&ihost->ports[port_index], + &ihost->phys[phy_index]); + + assigned_phy_mask |= (1 << phy_index); + } + + phy_index++; + } + + return sci_port_configuration_agent_validate_ports(ihost, port_agent); +} + +static void mpc_agent_timeout(unsigned long data) +{ + u8 index; + struct sci_timer *tmr = (struct sci_timer *)data; + struct sci_port_configuration_agent *port_agent; + struct isci_host *ihost; + unsigned long flags; + u16 configure_phy_mask; + + port_agent = container_of(tmr, typeof(*port_agent), timer); + ihost = container_of(port_agent, typeof(*ihost), port_agent); + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + port_agent->timer_pending = false; + + /* Find the mask of phys that are reported read but as yet unconfigured into a port */ + configure_phy_mask = ~port_agent->phy_configured_mask & port_agent->phy_ready_mask; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + struct isci_phy *iphy = &ihost->phys[index]; + + if (configure_phy_mask & (1 << index)) { + port_agent->link_up_handler(ihost, port_agent, + phy_get_non_dummy_port(iphy), + iphy); + } + } + +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +static void sci_mpc_agent_link_up(struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent, + struct isci_port *iport, + struct isci_phy *iphy) +{ + /* If the port is NULL then the phy was not assigned to a port. + * This is because the phy was not given the same SAS Address as + * the other PHYs in the port. + */ + if (!iport) + return; + + port_agent->phy_ready_mask |= (1 << iphy->phy_index); + sci_port_link_up(iport, iphy); + if ((iport->active_phy_mask & (1 << iphy->phy_index))) + port_agent->phy_configured_mask |= (1 << iphy->phy_index); +} + +/** + * + * @controller: This is the controller object that receives the link down + * notification. + * @port: This is the port object associated with the phy. If the is no + * associated port this is an NULL. The port is an invalid + * handle only if the phy was never port of this port. This happens when + * the phy is not broadcasting the same SAS address as the other phys in the + * assigned port. + * @phy: This is the phy object which has gone link down. + * + * This function handles the manual port configuration link down notifications. + * Since all ports and phys are associated at initialization time we just turn + * around and notifiy the port object of the link down event. If this PHY is + * not associated with a port there is no action taken. Is it possible to get a + * link down notification from a phy that has no assocoated port? + */ +static void sci_mpc_agent_link_down( + struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent, + struct isci_port *iport, + struct isci_phy *iphy) +{ + if (iport != NULL) { + /* + * If we can form a new port from the remainder of the phys + * then we want to start the timer to allow the SCI User to + * cleanup old devices and rediscover the port before + * rebuilding the port with the phys that remain in the ready + * state. + */ + port_agent->phy_ready_mask &= ~(1 << iphy->phy_index); + port_agent->phy_configured_mask &= ~(1 << iphy->phy_index); + + /* + * Check to see if there are more phys waiting to be + * configured into a port. If there are allow the SCI User + * to tear down this port, if necessary, and then reconstruct + * the port after the timeout. + */ + if ((port_agent->phy_configured_mask == 0x0000) && + (port_agent->phy_ready_mask != 0x0000) && + !port_agent->timer_pending) { + port_agent->timer_pending = true; + + sci_mod_timer(&port_agent->timer, + SCIC_SDS_MPC_RECONFIGURATION_TIMEOUT); + } + + sci_port_link_down(iport, iphy); + } +} + +/* verify phys are assigned a valid SAS address for automatic port + * configuration mode. + */ +static enum sci_status +sci_apc_agent_validate_phy_configuration(struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent) +{ + u8 phy_index; + u8 port_index; + struct sci_sas_address sas_address; + struct sci_sas_address phy_assigned_address; + + phy_index = 0; + + while (phy_index < SCI_MAX_PHYS) { + port_index = phy_index; + + /* Get the assigned SAS Address for the first PHY on the controller. */ + sci_phy_get_sas_address(&ihost->phys[phy_index], + &sas_address); + + while (++phy_index < SCI_MAX_PHYS) { + sci_phy_get_sas_address(&ihost->phys[phy_index], + &phy_assigned_address); + + /* Verify each of the SAS address are all the same for every PHY */ + if (sci_sas_address_compare(sas_address, phy_assigned_address) == 0) { + port_agent->phy_valid_port_range[phy_index].min_index = port_index; + port_agent->phy_valid_port_range[phy_index].max_index = phy_index; + } else { + port_agent->phy_valid_port_range[phy_index].min_index = phy_index; + port_agent->phy_valid_port_range[phy_index].max_index = phy_index; + break; + } + } + } + + return sci_port_configuration_agent_validate_ports(ihost, port_agent); +} + +static void sci_apc_agent_configure_ports(struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent, + struct isci_phy *iphy, + bool start_timer) +{ + u8 port_index; + enum sci_status status; + struct isci_port *iport; + enum SCIC_SDS_APC_ACTIVITY apc_activity = SCIC_SDS_APC_SKIP_PHY; + + iport = sci_port_configuration_agent_find_port(ihost, iphy); + + if (iport) { + if (sci_port_is_valid_phy_assignment(iport, iphy->phy_index)) + apc_activity = SCIC_SDS_APC_ADD_PHY; + else + apc_activity = SCIC_SDS_APC_SKIP_PHY; + } else { + /* + * There is no matching Port for this PHY so lets search through the + * Ports and see if we can add the PHY to its own port or maybe start + * the timer and wait to see if a wider port can be made. + * + * Note the break when we reach the condition of the port id == phy id */ + for (port_index = port_agent->phy_valid_port_range[iphy->phy_index].min_index; + port_index <= port_agent->phy_valid_port_range[iphy->phy_index].max_index; + port_index++) { + + iport = &ihost->ports[port_index]; + + /* First we must make sure that this PHY can be added to this Port. */ + if (sci_port_is_valid_phy_assignment(iport, iphy->phy_index)) { + /* + * Port contains a PHY with a greater PHY ID than the current + * PHY that has gone link up. This phy can not be part of any + * port so skip it and move on. */ + if (iport->active_phy_mask > (1 << iphy->phy_index)) { + apc_activity = SCIC_SDS_APC_SKIP_PHY; + break; + } + + /* + * We have reached the end of our Port list and have not found + * any reason why we should not either add the PHY to the port + * or wait for more phys to become active. */ + if (iport->physical_port_index == iphy->phy_index) { + /* + * The Port either has no active PHYs. + * Consider that if the port had any active PHYs we would have + * or active PHYs with + * a lower PHY Id than this PHY. */ + if (apc_activity != SCIC_SDS_APC_START_TIMER) { + apc_activity = SCIC_SDS_APC_ADD_PHY; + } + + break; + } + + /* + * The current Port has no active PHYs and this PHY could be part + * of this Port. Since we dont know as yet setup to start the + * timer and see if there is a better configuration. */ + if (iport->active_phy_mask == 0) { + apc_activity = SCIC_SDS_APC_START_TIMER; + } + } else if (iport->active_phy_mask != 0) { + /* + * The Port has an active phy and the current Phy can not + * participate in this port so skip the PHY and see if + * there is a better configuration. */ + apc_activity = SCIC_SDS_APC_SKIP_PHY; + } + } + } + + /* + * Check to see if the start timer operations should instead map to an + * add phy operation. This is caused because we have been waiting to + * add a phy to a port but could not becuase the automatic port + * configuration engine had a choice of possible ports for the phy. + * Since we have gone through a timeout we are going to restrict the + * choice to the smallest possible port. */ + if ( + (start_timer == false) + && (apc_activity == SCIC_SDS_APC_START_TIMER) + ) { + apc_activity = SCIC_SDS_APC_ADD_PHY; + } + + switch (apc_activity) { + case SCIC_SDS_APC_ADD_PHY: + status = sci_port_add_phy(iport, iphy); + + if (status == SCI_SUCCESS) { + port_agent->phy_configured_mask |= (1 << iphy->phy_index); + } + break; + + case SCIC_SDS_APC_START_TIMER: + /* + * This can occur for either a link down event, or a link + * up event where we cannot yet tell the port to which a + * phy belongs. + */ + if (port_agent->timer_pending) + sci_del_timer(&port_agent->timer); + + port_agent->timer_pending = true; + sci_mod_timer(&port_agent->timer, + SCIC_SDS_APC_WAIT_LINK_UP_NOTIFICATION); + break; + + case SCIC_SDS_APC_SKIP_PHY: + default: + /* do nothing the PHY can not be made part of a port at this time. */ + break; + } +} + +/** + * sci_apc_agent_link_up - handle apc link up events + * @scic: This is the controller object that receives the link up + * notification. + * @sci_port: This is the port object associated with the phy. If the is no + * associated port this is an NULL. + * @sci_phy: This is the phy object which has gone link up. + * + * This method handles the automatic port configuration for link up + * notifications. Is it possible to get a link down notification from a phy + * that has no assocoated port? + */ +static void sci_apc_agent_link_up(struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent, + struct isci_port *iport, + struct isci_phy *iphy) +{ + u8 phy_index = iphy->phy_index; + + if (!iport) { + /* the phy is not the part of this port */ + port_agent->phy_ready_mask |= 1 << phy_index; + sci_apc_agent_configure_ports(ihost, port_agent, iphy, true); + } else { + /* the phy is already the part of the port */ + u32 port_state = iport->sm.current_state_id; + + /* if the PORT'S state is resetting then the link up is from + * port hard reset in this case, we need to tell the port + * that link up is recieved + */ + BUG_ON(port_state != SCI_PORT_RESETTING); + port_agent->phy_ready_mask |= 1 << phy_index; + sci_port_link_up(iport, iphy); + } +} + +/** + * + * @controller: This is the controller object that receives the link down + * notification. + * @iport: This is the port object associated with the phy. If the is no + * associated port this is an NULL. + * @iphy: This is the phy object which has gone link down. + * + * This method handles the automatic port configuration link down + * notifications. not associated with a port there is no action taken. Is it + * possible to get a link down notification from a phy that has no assocoated + * port? + */ +static void sci_apc_agent_link_down( + struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent, + struct isci_port *iport, + struct isci_phy *iphy) +{ + port_agent->phy_ready_mask &= ~(1 << iphy->phy_index); + + if (!iport) + return; + if (port_agent->phy_configured_mask & (1 << iphy->phy_index)) { + enum sci_status status; + + status = sci_port_remove_phy(iport, iphy); + + if (status == SCI_SUCCESS) + port_agent->phy_configured_mask &= ~(1 << iphy->phy_index); + } +} + +/* configure the phys into ports when the timer fires */ +static void apc_agent_timeout(unsigned long data) +{ + u32 index; + struct sci_timer *tmr = (struct sci_timer *)data; + struct sci_port_configuration_agent *port_agent; + struct isci_host *ihost; + unsigned long flags; + u16 configure_phy_mask; + + port_agent = container_of(tmr, typeof(*port_agent), timer); + ihost = container_of(port_agent, typeof(*ihost), port_agent); + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmr->cancel) + goto done; + + port_agent->timer_pending = false; + + configure_phy_mask = ~port_agent->phy_configured_mask & port_agent->phy_ready_mask; + + if (!configure_phy_mask) + return; + + for (index = 0; index < SCI_MAX_PHYS; index++) { + if ((configure_phy_mask & (1 << index)) == 0) + continue; + + sci_apc_agent_configure_ports(ihost, port_agent, + &ihost->phys[index], false); + } + +done: + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +/* + * ****************************************************************************** + * Public port configuration agent routines + * ****************************************************************************** */ + +/** + * + * + * This method will construct the port configuration agent for operation. This + * call is universal for both manual port configuration and automatic port + * configuration modes. + */ +void sci_port_configuration_agent_construct( + struct sci_port_configuration_agent *port_agent) +{ + u32 index; + + port_agent->phy_configured_mask = 0x00; + port_agent->phy_ready_mask = 0x00; + + port_agent->link_up_handler = NULL; + port_agent->link_down_handler = NULL; + + port_agent->timer_pending = false; + + for (index = 0; index < SCI_MAX_PORTS; index++) { + port_agent->phy_valid_port_range[index].min_index = 0; + port_agent->phy_valid_port_range[index].max_index = 0; + } +} + +enum sci_status sci_port_configuration_agent_initialize( + struct isci_host *ihost, + struct sci_port_configuration_agent *port_agent) +{ + enum sci_status status; + enum sci_port_configuration_mode mode; + + mode = ihost->oem_parameters.controller.mode_type; + + if (mode == SCIC_PORT_MANUAL_CONFIGURATION_MODE) { + status = sci_mpc_agent_validate_phy_configuration( + ihost, port_agent); + + port_agent->link_up_handler = sci_mpc_agent_link_up; + port_agent->link_down_handler = sci_mpc_agent_link_down; + + sci_init_timer(&port_agent->timer, mpc_agent_timeout); + } else { + status = sci_apc_agent_validate_phy_configuration( + ihost, port_agent); + + port_agent->link_up_handler = sci_apc_agent_link_up; + port_agent->link_down_handler = sci_apc_agent_link_down; + + sci_init_timer(&port_agent->timer, apc_agent_timeout); + } + + return status; +} diff --git a/drivers/scsi/isci/probe_roms.c b/drivers/scsi/isci/probe_roms.c new file mode 100644 index 0000000..b5f4341 --- /dev/null +++ b/drivers/scsi/isci/probe_roms.c @@ -0,0 +1,243 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + */ + +/* probe_roms - scan for oem parameters */ + +#include <linux/kernel.h> +#include <linux/firmware.h> +#include <linux/uaccess.h> +#include <linux/efi.h> +#include <asm/probe_roms.h> + +#include "isci.h" +#include "task.h" +#include "probe_roms.h" + +static efi_char16_t isci_efivar_name[] = { + 'R', 's', 't', 'S', 'c', 'u', 'O' +}; + +struct isci_orom *isci_request_oprom(struct pci_dev *pdev) +{ + void __iomem *oprom = pci_map_biosrom(pdev); + struct isci_orom *rom = NULL; + size_t len, i; + int j; + char oem_sig[4]; + struct isci_oem_hdr oem_hdr; + u8 *tmp, sum; + + if (!oprom) + return NULL; + + len = pci_biosrom_size(pdev); + rom = devm_kzalloc(&pdev->dev, sizeof(*rom), GFP_KERNEL); + if (!rom) { + dev_warn(&pdev->dev, + "Unable to allocate memory for orom\n"); + return NULL; + } + + for (i = 0; i < len && rom; i += ISCI_OEM_SIG_SIZE) { + memcpy_fromio(oem_sig, oprom + i, ISCI_OEM_SIG_SIZE); + + /* we think we found the OEM table */ + if (memcmp(oem_sig, ISCI_OEM_SIG, ISCI_OEM_SIG_SIZE) == 0) { + size_t copy_len; + + memcpy_fromio(&oem_hdr, oprom + i, sizeof(oem_hdr)); + + copy_len = min(oem_hdr.len - sizeof(oem_hdr), + sizeof(*rom)); + + memcpy_fromio(rom, + oprom + i + sizeof(oem_hdr), + copy_len); + + /* calculate checksum */ + tmp = (u8 *)&oem_hdr; + for (j = 0, sum = 0; j < sizeof(oem_hdr); j++, tmp++) + sum += *tmp; + + tmp = (u8 *)rom; + for (j = 0; j < sizeof(*rom); j++, tmp++) + sum += *tmp; + + if (sum != 0) { + dev_warn(&pdev->dev, + "OEM table checksum failed\n"); + continue; + } + + /* keep going if that's not the oem param table */ + if (memcmp(rom->hdr.signature, + ISCI_ROM_SIG, + ISCI_ROM_SIG_SIZE) != 0) + continue; + + dev_info(&pdev->dev, + "OEM parameter table found in OROM\n"); + break; + } + } + + if (i >= len) { + dev_err(&pdev->dev, "oprom parse error\n"); + devm_kfree(&pdev->dev, rom); + rom = NULL; + } + pci_unmap_biosrom(oprom); + + return rom; +} + +enum sci_status isci_parse_oem_parameters(struct sci_oem_params *oem, + struct isci_orom *orom, int scu_index) +{ + /* check for valid inputs */ + if (scu_index < 0 || scu_index >= SCI_MAX_CONTROLLERS || + scu_index > orom->hdr.num_elements || !oem) + return -EINVAL; + + *oem = orom->ctrl[scu_index]; + return 0; +} + +struct isci_orom *isci_request_firmware(struct pci_dev *pdev, const struct firmware *fw) +{ + struct isci_orom *orom = NULL, *data; + int i, j; + + if (request_firmware(&fw, ISCI_FW_NAME, &pdev->dev) != 0) + return NULL; + + if (fw->size < sizeof(*orom)) + goto out; + + data = (struct isci_orom *)fw->data; + + if (strncmp(ISCI_ROM_SIG, data->hdr.signature, + strlen(ISCI_ROM_SIG)) != 0) + goto out; + + orom = devm_kzalloc(&pdev->dev, fw->size, GFP_KERNEL); + if (!orom) + goto out; + + memcpy(orom, fw->data, fw->size); + + if (is_c0(pdev)) + goto out; + + /* + * deprecated: override default amp_control for pre-preproduction + * silicon revisions + */ + for (i = 0; i < ARRAY_SIZE(orom->ctrl); i++) + for (j = 0; j < ARRAY_SIZE(orom->ctrl[i].phys); j++) { + orom->ctrl[i].phys[j].afe_tx_amp_control0 = 0xe7c03; + orom->ctrl[i].phys[j].afe_tx_amp_control1 = 0xe7c03; + orom->ctrl[i].phys[j].afe_tx_amp_control2 = 0xe7c03; + orom->ctrl[i].phys[j].afe_tx_amp_control3 = 0xe7c03; + } + out: + release_firmware(fw); + + return orom; +} + +static struct efi *get_efi(void) +{ +#ifdef CONFIG_EFI + return &efi; +#else + return NULL; +#endif +} + +struct isci_orom *isci_get_efi_var(struct pci_dev *pdev) +{ + efi_status_t status; + struct isci_orom *rom; + struct isci_oem_hdr *oem_hdr; + u8 *tmp, sum; + int j; + unsigned long data_len; + u8 *efi_data; + u32 efi_attrib = 0; + + data_len = 1024; + efi_data = devm_kzalloc(&pdev->dev, data_len, GFP_KERNEL); + if (!efi_data) { + dev_warn(&pdev->dev, + "Unable to allocate memory for EFI data\n"); + return NULL; + } + + rom = (struct isci_orom *)(efi_data + sizeof(struct isci_oem_hdr)); + + if (get_efi()) + status = get_efi()->get_variable(isci_efivar_name, + &ISCI_EFI_VENDOR_GUID, + &efi_attrib, + &data_len, + efi_data); + else + status = EFI_NOT_FOUND; + + if (status != EFI_SUCCESS) { + dev_warn(&pdev->dev, + "Unable to obtain EFI var data for OEM parms\n"); + return NULL; + } + + oem_hdr = (struct isci_oem_hdr *)efi_data; + + if (memcmp(oem_hdr->sig, ISCI_OEM_SIG, ISCI_OEM_SIG_SIZE) != 0) { + dev_warn(&pdev->dev, + "Invalid OEM header signature\n"); + return NULL; + } + + /* calculate checksum */ + tmp = (u8 *)efi_data; + for (j = 0, sum = 0; j < (sizeof(*oem_hdr) + sizeof(*rom)); j++, tmp++) + sum += *tmp; + + if (sum != 0) { + dev_warn(&pdev->dev, + "OEM table checksum failed\n"); + return NULL; + } + + if (memcmp(rom->hdr.signature, + ISCI_ROM_SIG, + ISCI_ROM_SIG_SIZE) != 0) { + dev_warn(&pdev->dev, + "Invalid OEM table signature\n"); + return NULL; + } + + return rom; +} diff --git a/drivers/scsi/isci/probe_roms.h b/drivers/scsi/isci/probe_roms.h new file mode 100644 index 0000000..dc007e6 --- /dev/null +++ b/drivers/scsi/isci/probe_roms.h @@ -0,0 +1,249 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _ISCI_PROBE_ROMS_H_ +#define _ISCI_PROBE_ROMS_H_ + +#ifdef __KERNEL__ +#include <linux/firmware.h> +#include <linux/pci.h> +#include <linux/efi.h> +#include "isci.h" + +#define SCIC_SDS_PARM_NO_SPEED 0 + +/* generation 1 (i.e. 1.5 Gb/s) */ +#define SCIC_SDS_PARM_GEN1_SPEED 1 + +/* generation 2 (i.e. 3.0 Gb/s) */ +#define SCIC_SDS_PARM_GEN2_SPEED 2 + +/* generation 3 (i.e. 6.0 Gb/s) */ +#define SCIC_SDS_PARM_GEN3_SPEED 3 +#define SCIC_SDS_PARM_MAX_SPEED SCIC_SDS_PARM_GEN3_SPEED + +/* parameters that can be set by module parameters */ +struct sci_user_parameters { + struct sci_phy_user_params { + /** + * This field specifies the NOTIFY (ENABLE SPIN UP) primitive + * insertion frequency for this phy index. + */ + u32 notify_enable_spin_up_insertion_frequency; + + /** + * This method specifies the number of transmitted DWORDs within which + * to transmit a single ALIGN primitive. This value applies regardless + * of what type of device is attached or connection state. A value of + * 0 indicates that no ALIGN primitives will be inserted. + */ + u16 align_insertion_frequency; + + /** + * This method specifies the number of transmitted DWORDs within which + * to transmit 2 ALIGN primitives. This applies for SAS connections + * only. A minimum value of 3 is required for this field. + */ + u16 in_connection_align_insertion_frequency; + + /** + * This field indicates the maximum speed generation to be utilized + * by phys in the supplied port. + * - A value of 1 indicates generation 1 (i.e. 1.5 Gb/s). + * - A value of 2 indicates generation 2 (i.e. 3.0 Gb/s). + * - A value of 3 indicates generation 3 (i.e. 6.0 Gb/s). + */ + u8 max_speed_generation; + + } phys[SCI_MAX_PHYS]; + + /** + * This field specifies the maximum number of direct attached devices + * that can have power supplied to them simultaneously. + */ + u8 max_number_concurrent_device_spin_up; + + /** + * This field specifies the number of seconds to allow a phy to consume + * power before yielding to another phy. + * + */ + u8 phy_spin_up_delay_interval; + + /** + * These timer values specifies how long a link will remain open with no + * activity in increments of a microsecond, it can be in increments of + * 100 microseconds if the upper most bit is set. + * + */ + u16 stp_inactivity_timeout; + u16 ssp_inactivity_timeout; + + /** + * These timer values specifies how long a link will remain open in increments + * of 100 microseconds. + * + */ + u16 stp_max_occupancy_timeout; + u16 ssp_max_occupancy_timeout; + + /** + * This timer value specifies how long a link will remain open with no + * outbound traffic in increments of a microsecond. + * + */ + u8 no_outbound_task_timeout; + +}; + +#define SCIC_SDS_PARM_PHY_MASK_MIN 0x0 +#define SCIC_SDS_PARM_PHY_MASK_MAX 0xF +#define MAX_CONCURRENT_DEVICE_SPIN_UP_COUNT 4 + +struct sci_oem_params; +int sci_oem_parameters_validate(struct sci_oem_params *oem); + +struct isci_orom; +struct isci_orom *isci_request_oprom(struct pci_dev *pdev); +enum sci_status isci_parse_oem_parameters(struct sci_oem_params *oem, + struct isci_orom *orom, int scu_index); +struct isci_orom *isci_request_firmware(struct pci_dev *pdev, const struct firmware *fw); +struct isci_orom *isci_get_efi_var(struct pci_dev *pdev); + +struct isci_oem_hdr { + u8 sig[4]; + u8 rev_major; + u8 rev_minor; + u16 len; + u8 checksum; + u8 reserved1; + u16 reserved2; +} __attribute__ ((packed)); + +#else +#define SCI_MAX_PORTS 4 +#define SCI_MAX_PHYS 4 +#define SCI_MAX_CONTROLLERS 2 +#endif + +#define ISCI_FW_NAME "isci/isci_firmware.bin" + +#define ROMSIGNATURE 0xaa55 + +#define ISCI_OEM_SIG "$OEM" +#define ISCI_OEM_SIG_SIZE 4 +#define ISCI_ROM_SIG "ISCUOEMB" +#define ISCI_ROM_SIG_SIZE 8 + +#define ISCI_EFI_VENDOR_GUID \ + EFI_GUID(0x193dfefa, 0xa445, 0x4302, 0x99, 0xd8, 0xef, 0x3a, 0xad, \ + 0x1a, 0x04, 0xc6) +#define ISCI_EFI_VAR_NAME "RstScuO" + +/* Allowed PORT configuration modes APC Automatic PORT configuration mode is + * defined by the OEM configuration parameters providing no PHY_MASK parameters + * for any PORT. i.e. There are no phys assigned to any of the ports at start. + * MPC Manual PORT configuration mode is defined by the OEM configuration + * parameters providing a PHY_MASK value for any PORT. It is assumed that any + * PORT with no PHY_MASK is an invalid port and not all PHYs must be assigned. + * A PORT_PHY mask that assigns just a single PHY to a port and no other PHYs + * being assigned is sufficient to declare manual PORT configuration. + */ +enum sci_port_configuration_mode { + SCIC_PORT_MANUAL_CONFIGURATION_MODE = 0, + SCIC_PORT_AUTOMATIC_CONFIGURATION_MODE = 1 +}; + +struct sci_bios_oem_param_block_hdr { + uint8_t signature[ISCI_ROM_SIG_SIZE]; + uint16_t total_block_length; + uint8_t hdr_length; + uint8_t version; + uint8_t preboot_source; + uint8_t num_elements; + uint16_t element_length; + uint8_t reserved[8]; +} __attribute__ ((packed)); + +struct sci_oem_params { + struct { + uint8_t mode_type; + uint8_t max_concurrent_dev_spin_up; + uint8_t do_enable_ssc; + uint8_t reserved; + } controller; + + struct { + uint8_t phy_mask; + } ports[SCI_MAX_PORTS]; + + struct sci_phy_oem_params { + struct { + uint32_t high; + uint32_t low; + } sas_address; + + uint32_t afe_tx_amp_control0; + uint32_t afe_tx_amp_control1; + uint32_t afe_tx_amp_control2; + uint32_t afe_tx_amp_control3; + } phys[SCI_MAX_PHYS]; +} __attribute__ ((packed)); + +struct isci_orom { + struct sci_bios_oem_param_block_hdr hdr; + struct sci_oem_params ctrl[SCI_MAX_CONTROLLERS]; +} __attribute__ ((packed)); + +#endif diff --git a/drivers/scsi/isci/registers.h b/drivers/scsi/isci/registers.h new file mode 100644 index 0000000..9b266c7 --- /dev/null +++ b/drivers/scsi/isci/registers.h @@ -0,0 +1,1934 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCU_REGISTERS_H_ +#define _SCU_REGISTERS_H_ + +/** + * This file contains the constants and structures for the SCU memory mapped + * registers. + * + * + */ + +#define SCU_VIIT_ENTRY_ID_MASK (0xC0000000) +#define SCU_VIIT_ENTRY_ID_SHIFT (30) + +#define SCU_VIIT_ENTRY_FUNCTION_MASK (0x0FF00000) +#define SCU_VIIT_ENTRY_FUNCTION_SHIFT (20) + +#define SCU_VIIT_ENTRY_IPPTMODE_MASK (0x0001F800) +#define SCU_VIIT_ENTRY_IPPTMODE_SHIFT (12) + +#define SCU_VIIT_ENTRY_LPVIE_MASK (0x00000F00) +#define SCU_VIIT_ENTRY_LPVIE_SHIFT (8) + +#define SCU_VIIT_ENTRY_STATUS_MASK (0x000000FF) +#define SCU_VIIT_ENTRY_STATUS_SHIFT (0) + +#define SCU_VIIT_ENTRY_ID_INVALID (0 << SCU_VIIT_ENTRY_ID_SHIFT) +#define SCU_VIIT_ENTRY_ID_VIIT (1 << SCU_VIIT_ENTRY_ID_SHIFT) +#define SCU_VIIT_ENTRY_ID_IIT (2 << SCU_VIIT_ENTRY_ID_SHIFT) +#define SCU_VIIT_ENTRY_ID_VIRT_EXP (3 << SCU_VIIT_ENTRY_ID_SHIFT) + +#define SCU_VIIT_IPPT_SSP_INITIATOR (0x01 << SCU_VIIT_ENTRY_IPPTMODE_SHIFT) +#define SCU_VIIT_IPPT_SMP_INITIATOR (0x02 << SCU_VIIT_ENTRY_IPPTMODE_SHIFT) +#define SCU_VIIT_IPPT_STP_INITIATOR (0x04 << SCU_VIIT_ENTRY_IPPTMODE_SHIFT) +#define SCU_VIIT_IPPT_INITIATOR \ + (\ + SCU_VIIT_IPPT_SSP_INITIATOR \ + | SCU_VIIT_IPPT_SMP_INITIATOR \ + | SCU_VIIT_IPPT_STP_INITIATOR \ + ) + +#define SCU_VIIT_STATUS_RNC_VALID (0x01 << SCU_VIIT_ENTRY_STATUS_SHIFT) +#define SCU_VIIT_STATUS_ADDRESS_VALID (0x02 << SCU_VIIT_ENTRY_STATUS_SHIFT) +#define SCU_VIIT_STATUS_RNI_VALID (0x04 << SCU_VIIT_ENTRY_STATUS_SHIFT) +#define SCU_VIIT_STATUS_ALL_VALID \ + (\ + SCU_VIIT_STATUS_RNC_VALID \ + | SCU_VIIT_STATUS_ADDRESS_VALID \ + | SCU_VIIT_STATUS_RNI_VALID \ + ) + +#define SCU_VIIT_IPPT_SMP_TARGET (0x10 << SCU_VIIT_ENTRY_IPPTMODE_SHIFT) + +/** + * struct scu_viit_entry - This is the SCU Virtual Initiator Table Entry + * + * + */ +struct scu_viit_entry { + /** + * This must be encoded as to the type of initiator that is being constructed + * for this port. + */ + u32 status; + + /** + * Virtual initiator high SAS Address + */ + u32 initiator_sas_address_hi; + + /** + * Virtual initiator low SAS Address + */ + u32 initiator_sas_address_lo; + + /** + * This must be 0 + */ + u32 reserved; + +}; + + +/* IIT Status Defines */ +#define SCU_IIT_ENTRY_ID_MASK (0xC0000000) +#define SCU_IIT_ENTRY_ID_SHIFT (30) + +#define SCU_IIT_ENTRY_STATUS_UPDATE_MASK (0x20000000) +#define SCU_IIT_ENTRY_STATUS_UPDATE_SHIFT (29) + +#define SCU_IIT_ENTRY_LPI_MASK (0x00000F00) +#define SCU_IIT_ENTRY_LPI_SHIFT (8) + +#define SCU_IIT_ENTRY_STATUS_MASK (0x000000FF) +#define SCU_IIT_ENTRY_STATUS_SHIFT (0) + +/* IIT Remote Initiator Defines */ +#define SCU_IIT_ENTRY_REMOTE_TAG_MASK (0x0000FFFF) +#define SCU_IIT_ENTRY_REMOTE_TAG_SHIFT (0) + +#define SCU_IIT_ENTRY_REMOTE_RNC_MASK (0x0FFF0000) +#define SCU_IIT_ENTRY_REMOTE_RNC_SHIFT (16) + +#define SCU_IIT_ENTRY_ID_INVALID (0 << SCU_IIT_ENTRY_ID_SHIFT) +#define SCU_IIT_ENTRY_ID_VIIT (1 << SCU_IIT_ENTRY_ID_SHIFT) +#define SCU_IIT_ENTRY_ID_IIT (2 << SCU_IIT_ENTRY_ID_SHIFT) +#define SCU_IIT_ENTRY_ID_VIRT_EXP (3 << SCU_IIT_ENTRY_ID_SHIFT) + +/** + * struct scu_iit_entry - This will be implemented later when we support + * virtual functions + * + * + */ +struct scu_iit_entry { + u32 status; + u32 remote_initiator_sas_address_hi; + u32 remote_initiator_sas_address_lo; + u32 remote_initiator; + +}; + +/* Generate a value for an SCU register */ +#define SCU_GEN_VALUE(name, value) \ + (((value) << name ## _SHIFT) & (name ## _MASK)) + +/* + * Generate a bit value for an SCU register + * Make sure that the register MASK is just a single bit */ +#define SCU_GEN_BIT(name) \ + SCU_GEN_VALUE(name, ((u32)1)) + +#define SCU_SET_BIT(name, reg_value) \ + ((reg_value) | SCU_GEN_BIT(name)) + +#define SCU_CLEAR_BIT(name, reg_value) \ + ((reg_value)$ ~(SCU_GEN_BIT(name))) + +/* + * ***************************************************************************** + * Unions for bitfield definitions of SCU Registers + * SMU Post Context Port + * ***************************************************************************** */ +#define SMU_POST_CONTEXT_PORT_CONTEXT_INDEX_SHIFT (0) +#define SMU_POST_CONTEXT_PORT_CONTEXT_INDEX_MASK (0x00000FFF) +#define SMU_POST_CONTEXT_PORT_LOGICAL_PORT_INDEX_SHIFT (12) +#define SMU_POST_CONTEXT_PORT_LOGICAL_PORT_INDEX_MASK (0x0000F000) +#define SMU_POST_CONTEXT_PORT_PROTOCOL_ENGINE_SHIFT (16) +#define SMU_POST_CONTEXT_PORT_PROTOCOL_ENGINE_MASK (0x00030000) +#define SMU_POST_CONTEXT_PORT_COMMAND_CONTEXT_SHIFT (18) +#define SMU_POST_CONTEXT_PORT_COMMAND_CONTEXT_MASK (0x00FC0000) +#define SMU_POST_CONTEXT_PORT_RESERVED_MASK (0xFF000000) + +#define SMU_PCP_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_POST_CONTEXT_PORT_ ## name, value) + +/* ***************************************************************************** */ +#define SMU_INTERRUPT_STATUS_COMPLETION_SHIFT (31) +#define SMU_INTERRUPT_STATUS_COMPLETION_MASK (0x80000000) +#define SMU_INTERRUPT_STATUS_QUEUE_SUSPEND_SHIFT (1) +#define SMU_INTERRUPT_STATUS_QUEUE_SUSPEND_MASK (0x00000002) +#define SMU_INTERRUPT_STATUS_QUEUE_ERROR_SHIFT (0) +#define SMU_INTERRUPT_STATUS_QUEUE_ERROR_MASK (0x00000001) +#define SMU_INTERRUPT_STATUS_RESERVED_MASK (0x7FFFFFFC) + +#define SMU_ISR_GEN_BIT(name) \ + SCU_GEN_BIT(SMU_INTERRUPT_STATUS_ ## name) + +#define SMU_ISR_QUEUE_ERROR SMU_ISR_GEN_BIT(QUEUE_ERROR) +#define SMU_ISR_QUEUE_SUSPEND SMU_ISR_GEN_BIT(QUEUE_SUSPEND) +#define SMU_ISR_COMPLETION SMU_ISR_GEN_BIT(COMPLETION) + +/* ***************************************************************************** */ +#define SMU_INTERRUPT_MASK_COMPLETION_SHIFT (31) +#define SMU_INTERRUPT_MASK_COMPLETION_MASK (0x80000000) +#define SMU_INTERRUPT_MASK_QUEUE_SUSPEND_SHIFT (1) +#define SMU_INTERRUPT_MASK_QUEUE_SUSPEND_MASK (0x00000002) +#define SMU_INTERRUPT_MASK_QUEUE_ERROR_SHIFT (0) +#define SMU_INTERRUPT_MASK_QUEUE_ERROR_MASK (0x00000001) +#define SMU_INTERRUPT_MASK_RESERVED_MASK (0x7FFFFFFC) + +#define SMU_IMR_GEN_BIT(name) \ + SCU_GEN_BIT(SMU_INTERRUPT_MASK_ ## name) + +#define SMU_IMR_QUEUE_ERROR SMU_IMR_GEN_BIT(QUEUE_ERROR) +#define SMU_IMR_QUEUE_SUSPEND SMU_IMR_GEN_BIT(QUEUE_SUSPEND) +#define SMU_IMR_COMPLETION SMU_IMR_GEN_BIT(COMPLETION) + +/* ***************************************************************************** */ +#define SMU_INTERRUPT_COALESCING_CONTROL_TIMER_SHIFT (0) +#define SMU_INTERRUPT_COALESCING_CONTROL_TIMER_MASK (0x0000001F) +#define SMU_INTERRUPT_COALESCING_CONTROL_NUMBER_SHIFT (8) +#define SMU_INTERRUPT_COALESCING_CONTROL_NUMBER_MASK (0x0000FF00) +#define SMU_INTERRUPT_COALESCING_CONTROL_RESERVED_MASK (0xFFFF00E0) + +#define SMU_ICC_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_INTERRUPT_COALESCING_CONTROL_ ## name, value) + +/* ***************************************************************************** */ +#define SMU_TASK_CONTEXT_RANGE_START_SHIFT (0) +#define SMU_TASK_CONTEXT_RANGE_START_MASK (0x00000FFF) +#define SMU_TASK_CONTEXT_RANGE_ENDING_SHIFT (16) +#define SMU_TASK_CONTEXT_RANGE_ENDING_MASK (0x0FFF0000) +#define SMU_TASK_CONTEXT_RANGE_ENABLE_SHIFT (31) +#define SMU_TASK_CONTEXT_RANGE_ENABLE_MASK (0x80000000) +#define SMU_TASK_CONTEXT_RANGE_RESERVED_MASK (0x7000F000) + +#define SMU_TCR_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_TASK_CONTEXT_RANGE_ ## name, value) + +#define SMU_TCR_GEN_BIT(name, value) \ + SCU_GEN_BIT(SMU_TASK_CONTEXT_RANGE_ ## name) + +/* ***************************************************************************** */ + +#define SMU_COMPLETION_QUEUE_PUT_POINTER_SHIFT (0) +#define SMU_COMPLETION_QUEUE_PUT_POINTER_MASK (0x00003FFF) +#define SMU_COMPLETION_QUEUE_PUT_CYCLE_BIT_SHIFT (15) +#define SMU_COMPLETION_QUEUE_PUT_CYCLE_BIT_MASK (0x00008000) +#define SMU_COMPLETION_QUEUE_PUT_EVENT_POINTER_SHIFT (16) +#define SMU_COMPLETION_QUEUE_PUT_EVENT_POINTER_MASK (0x03FF0000) +#define SMU_COMPLETION_QUEUE_PUT_EVENT_CYCLE_BIT_SHIFT (26) +#define SMU_COMPLETION_QUEUE_PUT_EVENT_CYCLE_BIT_MASK (0x04000000) +#define SMU_COMPLETION_QUEUE_PUT_RESERVED_MASK (0xF8004000) + +#define SMU_CQPR_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_COMPLETION_QUEUE_PUT_ ## name, value) + +#define SMU_CQPR_GEN_BIT(name) \ + SCU_GEN_BIT(SMU_COMPLETION_QUEUE_PUT_ ## name) + +/* ***************************************************************************** */ + +#define SMU_COMPLETION_QUEUE_GET_POINTER_SHIFT (0) +#define SMU_COMPLETION_QUEUE_GET_POINTER_MASK (0x00003FFF) +#define SMU_COMPLETION_QUEUE_GET_CYCLE_BIT_SHIFT (15) +#define SMU_COMPLETION_QUEUE_GET_CYCLE_BIT_MASK (0x00008000) +#define SMU_COMPLETION_QUEUE_GET_EVENT_POINTER_SHIFT (16) +#define SMU_COMPLETION_QUEUE_GET_EVENT_POINTER_MASK (0x03FF0000) +#define SMU_COMPLETION_QUEUE_GET_EVENT_CYCLE_BIT_SHIFT (26) +#define SMU_COMPLETION_QUEUE_GET_EVENT_CYCLE_BIT_MASK (0x04000000) +#define SMU_COMPLETION_QUEUE_GET_ENABLE_SHIFT (30) +#define SMU_COMPLETION_QUEUE_GET_ENABLE_MASK (0x40000000) +#define SMU_COMPLETION_QUEUE_GET_EVENT_ENABLE_SHIFT (31) +#define SMU_COMPLETION_QUEUE_GET_EVENT_ENABLE_MASK (0x80000000) +#define SMU_COMPLETION_QUEUE_GET_RESERVED_MASK (0x38004000) + +#define SMU_CQGR_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_COMPLETION_QUEUE_GET_ ## name, value) + +#define SMU_CQGR_GEN_BIT(name) \ + SCU_GEN_BIT(SMU_COMPLETION_QUEUE_GET_ ## name) + +#define SMU_CQGR_CYCLE_BIT \ + SMU_CQGR_GEN_BIT(CYCLE_BIT) + +#define SMU_CQGR_EVENT_CYCLE_BIT \ + SMU_CQGR_GEN_BIT(EVENT_CYCLE_BIT) + +#define SMU_CQGR_GET_POINTER_SET(value) \ + SMU_CQGR_GEN_VAL(POINTER, value) + + +/* ***************************************************************************** */ +#define SMU_COMPLETION_QUEUE_CONTROL_QUEUE_LIMIT_SHIFT (0) +#define SMU_COMPLETION_QUEUE_CONTROL_QUEUE_LIMIT_MASK (0x00003FFF) +#define SMU_COMPLETION_QUEUE_CONTROL_EVENT_LIMIT_SHIFT (16) +#define SMU_COMPLETION_QUEUE_CONTROL_EVENT_LIMIT_MASK (0x03FF0000) +#define SMU_COMPLETION_QUEUE_CONTROL_RESERVED_MASK (0xFC00C000) + +#define SMU_CQC_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_COMPLETION_QUEUE_CONTROL_ ## name, value) + +#define SMU_CQC_QUEUE_LIMIT_SET(value) \ + SMU_CQC_GEN_VAL(QUEUE_LIMIT, value) + +#define SMU_CQC_EVENT_LIMIT_SET(value) \ + SMU_CQC_GEN_VAL(EVENT_LIMIT, value) + + +/* ***************************************************************************** */ +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_TC_SHIFT (0) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_TC_MASK (0x00000FFF) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_SHIFT (12) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_MASK (0x00007000) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_RNC_SHIFT (15) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_RNC_MASK (0x07FF8000) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_PEG_SHIFT (27) +#define SMU_DEVICE_CONTEXT_CAPACITY_MAX_PEG_MASK (0x08000000) +#define SMU_DEVICE_CONTEXT_CAPACITY_RESERVED_MASK (0xF0000000) + +#define SMU_DCC_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_DEVICE_CONTEXT_CAPACITY_ ## name, value) + +#define SMU_DCC_GET_MAX_PEG(value) \ + (\ + ((value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_PEG_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_SHIFT \ + ) + +#define SMU_DCC_GET_MAX_LP(value) \ + (\ + ((value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_LP_SHIFT \ + ) + +#define SMU_DCC_GET_MAX_TC(value) \ + (\ + ((value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_TC_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_TC_SHIFT \ + ) + +#define SMU_DCC_GET_MAX_RNC(value) \ + (\ + ((value) & SMU_DEVICE_CONTEXT_CAPACITY_MAX_RNC_MASK) \ + >> SMU_DEVICE_CONTEXT_CAPACITY_MAX_RNC_SHIFT \ + ) + +/* -------------------------------------------------------------------------- */ + +#define SMU_CONTROL_STATUS_TASK_CONTEXT_RANGE_ENABLE_SHIFT (0) +#define SMU_CONTROL_STATUS_TASK_CONTEXT_RANGE_ENABLE_MASK (0x00000001) +#define SMU_CONTROL_STATUS_COMPLETION_BYTE_SWAP_ENABLE_SHIFT (1) +#define SMU_CONTROL_STATUS_COMPLETION_BYTE_SWAP_ENABLE_MASK (0x00000002) +#define SMU_CONTROL_STATUS_CONTEXT_RAM_INIT_COMPLETED_SHIFT (16) +#define SMU_CONTROL_STATUS_CONTEXT_RAM_INIT_COMPLETED_MASK (0x00010000) +#define SMU_CONTROL_STATUS_SCHEDULER_RAM_INIT_COMPLETED_SHIFT (17) +#define SMU_CONTROL_STATUS_SCHEDULER_RAM_INIT_COMPLETED_MASK (0x00020000) +#define SMU_CONTROL_STATUS_RESERVED_MASK (0xFFFCFFFC) + +#define SMU_SMUCSR_GEN_BIT(name) \ + SCU_GEN_BIT(SMU_CONTROL_STATUS_ ## name) + +#define SMU_SMUCSR_SCHEDULER_RAM_INIT_COMPLETED \ + (SMU_SMUCSR_GEN_BIT(SCHEDULER_RAM_INIT_COMPLETED)) + +#define SMU_SMUCSR_CONTEXT_RAM_INIT_COMPLETED \ + (SMU_SMUCSR_GEN_BIT(CONTEXT_RAM_INIT_COMPLETED)) + +#define SCU_RAM_INIT_COMPLETED \ + (\ + SMU_SMUCSR_CONTEXT_RAM_INIT_COMPLETED \ + | SMU_SMUCSR_SCHEDULER_RAM_INIT_COMPLETED \ + ) + +/* -------------------------------------------------------------------------- */ + +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE0_SHIFT (0) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE0_MASK (0x00000001) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE1_SHIFT (1) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE1_MASK (0x00000002) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE2_SHIFT (2) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE2_MASK (0x00000004) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE3_SHIFT (3) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_PE3_MASK (0x00000008) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE0_SHIFT (8) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE0_MASK (0x00000100) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE1_SHIFT (9) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE1_MASK (0x00000200) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE2_SHIFT (10) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE2_MASK (0x00000400) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE3_SHIFT (11) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_PE3_MASK (0x00000800) + +#define SMU_RESET_PROTOCOL_ENGINE(peg, pe) \ + ((1 << (pe)) << ((peg) * 8)) + +#define SMU_RESET_PEG_PROTOCOL_ENGINES(peg) \ + (\ + SMU_RESET_PROTOCOL_ENGINE(peg, 0) \ + | SMU_RESET_PROTOCOL_ENGINE(peg, 1) \ + | SMU_RESET_PROTOCOL_ENGINE(peg, 2) \ + | SMU_RESET_PROTOCOL_ENGINE(peg, 3) \ + ) + +#define SMU_RESET_ALL_PROTOCOL_ENGINES() \ + (\ + SMU_RESET_PEG_PROTOCOL_ENGINES(0) \ + | SMU_RESET_PEG_PROTOCOL_ENGINES(1) \ + ) + +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG0_LP0_SHIFT (16) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG0_LP0_MASK (0x00010000) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG0_LP2_SHIFT (17) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG0_LP2_MASK (0x00020000) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG1_LP0_SHIFT (18) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG1_LP0_MASK (0x00040000) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG1_LP2_SHIFT (19) +#define SMU_SOFTRESET_CONTROL_RESET_WIDE_PORT_PEG1_LP2_MASK (0x00080000) + +#define SMU_RESET_WIDE_PORT_QUEUE(peg, wide_port) \ + ((1 << ((wide_port) / 2)) << ((peg) * 2) << 16) + +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_SHIFT (20) +#define SMU_SOFTRESET_CONTROL_RESET_PEG0_MASK (0x00100000) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_SHIFT (21) +#define SMU_SOFTRESET_CONTROL_RESET_PEG1_MASK (0x00200000) +#define SMU_SOFTRESET_CONTROL_RESET_SCU_SHIFT (22) +#define SMU_SOFTRESET_CONTROL_RESET_SCU_MASK (0x00400000) + +/* + * It seems to make sense that if you are going to reset the protocol + * engine group that you would also reset all of the protocol engines */ +#define SMU_RESET_PROTOCOL_ENGINE_GROUP(peg) \ + (\ + (1 << ((peg) + 20)) \ + | SMU_RESET_WIDE_PORT_QUEUE(peg, 0) \ + | SMU_RESET_WIDE_PORT_QUEUE(peg, 1) \ + | SMU_RESET_PEG_PROTOCOL_ENGINES(peg) \ + ) + +#define SMU_RESET_ALL_PROTOCOL_ENGINE_GROUPS() \ + (\ + SMU_RESET_PROTOCOL_ENGINE_GROUP(0) \ + | SMU_RESET_PROTOCOL_ENGINE_GROUP(1) \ + ) + +#define SMU_RESET_SCU() (0xFFFFFFFF) + + + +/* ***************************************************************************** */ +#define SMU_TASK_CONTEXT_ASSIGNMENT_STARTING_SHIFT (0) +#define SMU_TASK_CONTEXT_ASSIGNMENT_STARTING_MASK (0x00000FFF) +#define SMU_TASK_CONTEXT_ASSIGNMENT_ENDING_SHIFT (16) +#define SMU_TASK_CONTEXT_ASSIGNMENT_ENDING_MASK (0x0FFF0000) +#define SMU_TASK_CONTEXT_ASSIGNMENT_RANGE_CHECK_ENABLE_SHIFT (31) +#define SMU_TASK_CONTEXT_ASSIGNMENT_RANGE_CHECK_ENABLE_MASK (0x80000000) +#define SMU_TASK_CONTEXT_ASSIGNMENT_RESERVED_MASK (0x7000F000) + +#define SMU_TCA_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SMU_TASK_CONTEXT_ASSIGNMENT_ ## name, value) + +#define SMU_TCA_GEN_BIT(name) \ + SCU_GEN_BIT(SMU_TASK_CONTEXT_ASSIGNMENT_ ## name) + +/* ***************************************************************************** */ +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_CONTROL_QUEUE_SIZE_SHIFT (0) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_CONTROL_QUEUE_SIZE_MASK (0x00000FFF) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_CONTROL_RESERVED_MASK (0xFFFFF000) + +#define SCU_UFQC_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SDMA_UNSOLICITED_FRAME_QUEUE_CONTROL_ ## name, value) + +#define SCU_UFQC_QUEUE_SIZE_SET(value) \ + SCU_UFQC_GEN_VAL(QUEUE_SIZE, value) + +/* ***************************************************************************** */ +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_POINTER_SHIFT (0) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_POINTER_MASK (0x00000FFF) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_CYCLE_BIT_SHIFT (12) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_CYCLE_BIT_MASK (0x00001000) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_RESERVED_MASK (0xFFFFE000) + +#define SCU_UFQPP_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_ ## name, value) + +#define SCU_UFQPP_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SDMA_UNSOLICITED_FRAME_QUEUE_PUT_ ## name) + +/* + * ***************************************************************************** + * * SDMA Registers + * ***************************************************************************** */ +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_POINTER_SHIFT (0) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_POINTER_MASK (0x00000FFF) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_CYCLE_BIT_SHIFT (12) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_CYCLE_BIT_MASK (12) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_ENABLE_BIT_SHIFT (31) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_ENABLE_BIT_MASK (0x80000000) +#define SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_RESERVED_MASK (0x7FFFE000) + +#define SCU_UFQGP_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_ ## name, value) + +#define SCU_UFQGP_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SDMA_UNSOLICITED_FRAME_QUEUE_GET_ ## name) + +#define SCU_UFQGP_CYCLE_BIT(value) \ + SCU_UFQGP_GEN_BIT(CYCLE_BIT, value) + +#define SCU_UFQGP_GET_POINTER(value) \ + SCU_UFQGP_GEN_VALUE(POINTER, value) + +#define SCU_UFQGP_ENABLE(value) \ + (SCU_UFQGP_GEN_BIT(ENABLE) | value) + +#define SCU_UFQGP_DISABLE(value) \ + (~SCU_UFQGP_GEN_BIT(ENABLE) & value) + +#define SCU_UFQGP_VALUE(bit, value) \ + (SCU_UFQGP_CYCLE_BIT(bit) | SCU_UFQGP_GET_POINTER(value)) + +/* ***************************************************************************** */ +#define SCU_PDMA_CONFIGURATION_ADDRESS_MODIFIER_SHIFT (0) +#define SCU_PDMA_CONFIGURATION_ADDRESS_MODIFIER_MASK (0x0000FFFF) +#define SCU_PDMA_CONFIGURATION_PCI_RELAXED_ORDERING_ENABLE_SHIFT (16) +#define SCU_PDMA_CONFIGURATION_PCI_RELAXED_ORDERING_ENABLE_MASK (0x00010000) +#define SCU_PDMA_CONFIGURATION_PCI_NO_SNOOP_ENABLE_SHIFT (17) +#define SCU_PDMA_CONFIGURATION_PCI_NO_SNOOP_ENABLE_MASK (0x00020000) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_BYTE_SWAP_SHIFT (18) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_BYTE_SWAP_MASK (0x00040000) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_XPI_SGL_FETCH_SHIFT (19) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_XPI_SGL_FETCH_MASK (0x00080000) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_XPI_RX_HEADER_RAM_WRITE_SHIFT (20) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_XPI_RX_HEADER_RAM_WRITE_MASK (0x00100000) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_XPI_UF_ADDRESS_FETCH_SHIFT (21) +#define SCU_PDMA_CONFIGURATION_BIG_ENDIAN_CONTROL_XPI_UF_ADDRESS_FETCH_MASK (0x00200000) +#define SCU_PDMA_CONFIGURATION_ADDRESS_MODIFIER_SELECT_SHIFT (22) +#define SCU_PDMA_CONFIGURATION_ADDRESS_MODIFIER_SELECT_MASK (0x00400000) +#define SCU_PDMA_CONFIGURATION_RESERVED_MASK (0xFF800000) + +#define SCU_PDMACR_GEN_VALUE(name, value) \ + SCU_GEN_VALUE(SCU_PDMA_CONFIGURATION_ ## name, value) + +#define SCU_PDMACR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_PDMA_CONFIGURATION_ ## name) + +#define SCU_PDMACR_BE_GEN_BIT(name) \ + SCU_PCMACR_GEN_BIT(BIG_ENDIAN_CONTROL_ ## name) + +/* ***************************************************************************** */ +#define SCU_CDMA_CONFIGURATION_PCI_RELAXED_ORDERING_ENABLE_SHIFT (8) +#define SCU_CDMA_CONFIGURATION_PCI_RELAXED_ORDERING_ENABLE_MASK (0x00000100) + +#define SCU_CDMACR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_CDMA_CONFIGURATION_ ## name) + +/* + * ***************************************************************************** + * * SCU Link Layer Registers + * ***************************************************************************** */ +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_TIMEOUT_SHIFT (0) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_TIMEOUT_MASK (0x000000FF) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_LOCK_TIME_SHIFT (8) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_LOCK_TIME_MASK (0x0000FF00) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_RATE_CHANGE_DELAY_SHIFT (16) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_RATE_CHANGE_DELAY_MASK (0x00FF0000) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_DWORD_SYNC_TIMEOUT_SHIFT (24) +#define SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_DWORD_SYNC_TIMEOUT_MASK (0xFF000000) +#define SCU_LINK_LAYER_SPEED_NECGOIATION_TIMER_VALUES_REQUIRED_MASK (0x00000000) +#define SCU_LINK_LAYER_SPEED_NECGOIATION_TIMER_VALUES_DEFAULT_MASK (0x7D00676F) +#define SCU_LINK_LAYER_SPEED_NECGOIATION_TIMER_VALUES_RESERVED_MASK (0x00FF0000) + +#define SCU_SAS_SPDTOV_GEN_VALUE(name, value) \ + SCU_GEN_VALUE(SCU_LINK_LAYER_SPEED_NEGOTIATION_TIMER_VALUES_ ## name, value) + + +#define SCU_LINK_STATUS_DWORD_SYNC_AQUIRED_SHIFT (2) +#define SCU_LINK_STATUS_DWORD_SYNC_AQUIRED_MASK (0x00000004) +#define SCU_LINK_STATUS_TRANSMIT_PORT_SELECTION_DONE_SHIFT (4) +#define SCU_LINK_STATUS_TRANSMIT_PORT_SELECTION_DONE_MASK (0x00000010) +#define SCU_LINK_STATUS_RECEIVER_CREDIT_EXHAUSTED_SHIFT (5) +#define SCU_LINK_STATUS_RECEIVER_CREDIT_EXHAUSTED_MASK (0x00000020) +#define SCU_LINK_STATUS_RESERVED_MASK (0xFFFFFFCD) + +#define SCU_SAS_LLSTA_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_LINK_STATUS_ ## name) + + +/* TODO: Where is the SATA_PSELTOV register? */ + +/* + * ***************************************************************************** + * * SCU SAS Maximum Arbitration Wait Time Timeout Register + * ***************************************************************************** */ +#define SCU_SAS_MAX_ARBITRATION_WAIT_TIME_TIMEOUT_VALUE_SHIFT (0) +#define SCU_SAS_MAX_ARBITRATION_WAIT_TIME_TIMEOUT_VALUE_MASK (0x00007FFF) +#define SCU_SAS_MAX_ARBITRATION_WAIT_TIME_TIMEOUT_SCALE_SHIFT (15) +#define SCU_SAS_MAX_ARBITRATION_WAIT_TIME_TIMEOUT_SCALE_MASK (0x00008000) + +#define SCU_SAS_MAWTTOV_GEN_VALUE(name, value) \ + SCU_GEN_VALUE(SCU_SAS_MAX_ARBITRATION_WAIT_TIME_TIMEOUT_ ## name, value) + +#define SCU_SAS_MAWTTOV_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SAS_MAX_ARBITRATION_WAIT_TIME_TIMEOUT_ ## name) + + +/* + * TODO: Where is the SAS_LNKTOV regsiter? + * TODO: Where is the SAS_PHYTOV register? */ + +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SMP_TARGET_SHIFT (1) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SMP_TARGET_MASK (0x00000002) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_STP_TARGET_SHIFT (2) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_STP_TARGET_MASK (0x00000004) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SSP_TARGET_SHIFT (3) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SSP_TARGET_MASK (0x00000008) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_DA_SATA_HOST_SHIFT (8) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_DA_SATA_HOST_MASK (0x00000100) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SMP_INITIATOR_SHIFT (9) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SMP_INITIATOR_MASK (0x00000200) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_STP_INITIATOR_SHIFT (10) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_STP_INITIATOR_MASK (0x00000400) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SSP_INITIATOR_SHIFT (11) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_SSP_INITIATOR_MASK (0x00000800) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_REASON_CODE_SHIFT (16) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_REASON_CODE_MASK (0x000F0000) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_ADDRESS_FRAME_TYPE_SHIFT (24) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_ADDRESS_FRAME_TYPE_MASK (0x0F000000) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_DEVICE_TYPE_SHIFT (28) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_DEVICE_TYPE_MASK (0x70000000) +#define SCU_SAS_TRANSMIT_IDENTIFICATION_RESERVED_MASK (0x80F0F1F1) + +#define SCU_SAS_TIID_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SAS_TRANSMIT_IDENTIFICATION_ ## name, value) + +#define SCU_SAS_TIID_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SAS_TRANSMIT_IDENTIFICATION_ ## name) + +/* SAS Identify Frame PHY Identifier Register */ +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_BREAK_REPLY_CAPABLE_SHIFT (16) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_BREAK_REPLY_CAPABLE_MASK (0x00010000) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_REQUESTED_INSIDE_ZPSDS_SHIFT (17) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_REQUESTED_INSIDE_ZPSDS_MASK (0x00020000) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_INSIDE_ZPSDS_PERSISTENT_SHIFT (18) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_INSIDE_ZPSDS_PERSISTENT_MASK (0x00040000) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_ID_SHIFT (24) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_ID_MASK (0xFF000000) +#define SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_RESERVED_MASK (0x00F800FF) + +#define SCU_SAS_TIPID_GEN_VALUE(name, value) \ + SCU_GEN_VALUE(SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_ ## name, value) + +#define SCU_SAS_TIPID_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_LINK_LAYER_IDENTIFY_FRAME_PHY_IDENTIFIER_ ## name) + + +#define SCU_SAS_PHY_CONFIGURATION_TX_PARITY_CHECK_SHIFT (4) +#define SCU_SAS_PHY_CONFIGURATION_TX_PARITY_CHECK_MASK (0x00000010) +#define SCU_SAS_PHY_CONFIGURATION_TX_BAD_CRC_SHIFT (6) +#define SCU_SAS_PHY_CONFIGURATION_TX_BAD_CRC_MASK (0x00000040) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_SCRAMBLER_SHIFT (7) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_SCRAMBLER_MASK (0x00000080) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_DESCRAMBLER_SHIFT (8) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_DESCRAMBLER_MASK (0x00000100) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_CREDIT_INSERTION_SHIFT (9) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_CREDIT_INSERTION_MASK (0x00000200) +#define SCU_SAS_PHY_CONFIGURATION_SUSPEND_PROTOCOL_ENGINE_SHIFT (11) +#define SCU_SAS_PHY_CONFIGURATION_SUSPEND_PROTOCOL_ENGINE_MASK (0x00000800) +#define SCU_SAS_PHY_CONFIGURATION_SATA_SPINUP_HOLD_SHIFT (12) +#define SCU_SAS_PHY_CONFIGURATION_SATA_SPINUP_HOLD_MASK (0x00001000) +#define SCU_SAS_PHY_CONFIGURATION_TRANSMIT_PORT_SELECTION_SIGNAL_SHIFT (13) +#define SCU_SAS_PHY_CONFIGURATION_TRANSMIT_PORT_SELECTION_SIGNAL_MASK (0x00002000) +#define SCU_SAS_PHY_CONFIGURATION_HARD_RESET_SHIFT (14) +#define SCU_SAS_PHY_CONFIGURATION_HARD_RESET_MASK (0x00004000) +#define SCU_SAS_PHY_CONFIGURATION_OOB_ENABLE_SHIFT (15) +#define SCU_SAS_PHY_CONFIGURATION_OOB_ENABLE_MASK (0x00008000) +#define SCU_SAS_PHY_CONFIGURATION_ENABLE_FRAME_TX_INSERT_ALIGN_SHIFT (23) +#define SCU_SAS_PHY_CONFIGURATION_ENABLE_FRAME_TX_INSERT_ALIGN_MASK (0x00800000) +#define SCU_SAS_PHY_CONFIGURATION_FORWARD_IDENTIFY_FRAME_SHIFT (27) +#define SCU_SAS_PHY_CONFIGURATION_FORWARD_IDENTIFY_FRAME_MASK (0x08000000) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_BYTE_TRANSPOSE_STP_FRAME_SHIFT (28) +#define SCU_SAS_PHY_CONFIGURATION_DISABLE_BYTE_TRANSPOSE_STP_FRAME_MASK (0x10000000) +#define SCU_SAS_PHY_CONFIGURATION_OOB_RESET_SHIFT (29) +#define SCU_SAS_PHY_CONFIGURATION_OOB_RESET_MASK (0x20000000) +#define SCU_SAS_PHY_CONFIGURATION_THREE_IAF_ENABLE_SHIFT (30) +#define SCU_SAS_PHY_CONFIGURATION_THREE_IAF_ENABLE_MASK (0x40000000) +#define SCU_SAS_PHY_CONFIGURATION_OOB_ALIGN0_ENABLE_SHIFT (31) +#define SCU_SAS_PHY_CONFIGURATION_OOB_ALIGN0_ENABLE_MASK (0x80000000) +#define SCU_SAS_PHY_CONFIGURATION_REQUIRED_MASK (0x0100000F) +#define SCU_SAS_PHY_CONFIGURATION_DEFAULT_MASK (0x4180100F) +#define SCU_SAS_PHY_CONFIGURATION_RESERVED_MASK (0x00000000) + +#define SCU_SAS_PCFG_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SAS_PHY_CONFIGURATION_ ## name) + +#define SCU_LINK_LAYER_ALIGN_INSERTION_FREQUENCY_GENERAL_SHIFT (0) +#define SCU_LINK_LAYER_ALIGN_INSERTION_FREQUENCY_GENERAL_MASK (0x000007FF) +#define SCU_LINK_LAYER_ALIGN_INSERTION_FREQUENCY_CONNECTED_SHIFT (16) +#define SCU_LINK_LAYER_ALIGN_INSERTION_FREQUENCY_CONNECTED_MASK (0x00ff0000) + +#define SCU_ALIGN_INSERTION_FREQUENCY_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_LINK_LAYER_ALIGN_INSERTION_FREQUENCY_##name, value) + +#define SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_COUNT_SHIFT (0) +#define SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_COUNT_MASK (0x0003FFFF) +#define SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_ENABLE_SHIFT (31) +#define SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_ENABLE_MASK (0x80000000) +#define SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_RESERVED_MASK (0x7FFC0000) + +#define SCU_ENSPINUP_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_ ## name, value) + +#define SCU_ENSPINUP_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_LINK_LAYER_ENABLE_SPINUP_CONTROL_ ## name) + + +#define SCU_LINK_LAYER_PHY_CAPABILITIES_TXSSCTYPE_SHIFT (1) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_TXSSCTYPE_MASK (0x00000002) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_RLLRATE_SHIFT (4) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_RLLRATE_MASK (0x000000F0) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SWO15GBPS_SHIFT (8) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SWO15GBPS_MASK (0x00000100) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SW15GBPS_SHIFT (9) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SW15GBPS_MASK (0x00000201) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SWO30GBPS_SHIFT (10) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SWO30GBPS_MASK (0x00000401) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SW30GBPS_SHIFT (11) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SW30GBPS_MASK (0x00000801) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SWO60GBPS_SHIFT (12) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SWO60GBPS_MASK (0x00001001) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SW60GBPS_SHIFT (13) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_SW60GBPS_MASK (0x00002001) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_EVEN_PARITY_SHIFT (31) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_EVEN_PARITY_MASK (0x80000000) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_DEFAULT_MASK (0x00003F01) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_REQUIRED_MASK (0x00000001) +#define SCU_LINK_LAYER_PHY_CAPABILITIES_RESERVED_MASK (0x7FFFC00D) + +#define SCU_SAS_PHYCAP_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_LINK_LAYER_PHY_CAPABILITIES_ ## name, value) + +#define SCU_SAS_PHYCAP_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_LINK_LAYER_PHY_CAPABILITIES_ ## name) + + +#define SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_VIRTUAL_EXPANDER_PHY_ZONE_GROUP_SHIFT (0) +#define SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_VIRTUAL_EXPANDER_PHY_ZONE_GROUP_MASK (0x000000FF) +#define SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_INSIDE_SOURCE_ZONE_GROUP_SHIFT (31) +#define SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_INSIDE_SOURCE_ZONE_GROUP_MASK (0x80000000) +#define SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_RESERVED_MASK (0x7FFFFF00) + +#define SCU_PSZGCR_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_ ## name, value) + +#define SCU_PSZGCR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_LINK_LAYER_PHY_SOURCE_ZONE_GROUP_CONTROL_ ## name) + +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE0_LOCKED_SHIFT (1) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE0_LOCKED_MASK (0x00000002) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE0_UPDATING_SHIFT (2) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE0_UPDATING_MASK (0x00000004) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE1_LOCKED_SHIFT (4) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE1_LOCKED_MASK (0x00000010) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE1_UPDATING_SHIFT (5) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZONE1_UPDATING_MASK (0x00000020) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE0_SHIFT (16) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE0_MASK (0x00030000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE0_SHIFT (19) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE0_MASK (0x00080000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE1_SHIFT (20) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE1_MASK (0x00300000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE1_SHIFT (23) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE1_MASK (0x00800000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE2_SHIFT (24) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE2_MASK (0x03000000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE2_SHIFT (27) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE2_MASK (0x08000000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE3_SHIFT (28) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ZPT_ASSOCIATION_PE3_MASK (0x30000000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE3_SHIFT (31) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_AIP_ENABLE_PE3_MASK (0x80000000) +#define SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_RESERVED_MASK (0x4444FFC9) + +#define SCU_PEG_SCUVZECR_GEN_VAL(name, val) \ + SCU_GEN_VALUE(SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ ## name, val) + +#define SCU_PEG_SCUVZECR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_PROTOCOL_ENGINE_GROUP_VIRTUAL_ZONING_EXPANDER_CONTROL_ ## name) + + +/* + * ***************************************************************************** + * * Port Task Scheduler registers shift and mask values + * ***************************************************************************** */ +#define SCU_PTSG_CONTROL_IT_NEXUS_TIMEOUT_SHIFT (0) +#define SCU_PTSG_CONTROL_IT_NEXUS_TIMEOUT_MASK (0x0000FFFF) +#define SCU_PTSG_CONTROL_TASK_TIMEOUT_SHIFT (16) +#define SCU_PTSG_CONTROL_TASK_TIMEOUT_MASK (0x00FF0000) +#define SCU_PTSG_CONTROL_PTSG_ENABLE_SHIFT (24) +#define SCU_PTSG_CONTROL_PTSG_ENABLE_MASK (0x01000000) +#define SCU_PTSG_CONTROL_ETM_ENABLE_SHIFT (25) +#define SCU_PTSG_CONTROL_ETM_ENABLE_MASK (0x02000000) +#define SCU_PTSG_CONTROL_DEFAULT_MASK (0x00020002) +#define SCU_PTSG_CONTROL_REQUIRED_MASK (0x00000000) +#define SCU_PTSG_CONTROL_RESERVED_MASK (0xFC000000) + +#define SCU_PTSGCR_GEN_VAL(name, val) \ + SCU_GEN_VALUE(SCU_PTSG_CONTROL_ ## name, val) + +#define SCU_PTSGCR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_PTSG_CONTROL_ ## name) + + +/* ***************************************************************************** */ +#define SCU_PTSG_REAL_TIME_CLOCK_SHIFT (0) +#define SCU_PTSG_REAL_TIME_CLOCK_MASK (0x0000FFFF) +#define SCU_PTSG_REAL_TIME_CLOCK_RESERVED_MASK (0xFFFF0000) + +#define SCU_RTCR_GEN_VAL(name, val) \ + SCU_GEN_VALUE(SCU_PTSG_ ## name, val) + + +#define SCU_PTSG_REAL_TIME_CLOCK_CONTROL_PRESCALER_VALUE_SHIFT (0) +#define SCU_PTSG_REAL_TIME_CLOCK_CONTROL_PRESCALER_VALUE_MASK (0x00FFFFFF) +#define SCU_PTSG_REAL_TIME_CLOCK_CONTROL_RESERVED_MASK (0xFF000000) + +#define SCU_RTCCR_GEN_VAL(name, val) \ + SCU_GEN_VALUE(SCU_PTSG_REAL_TIME_CLOCK_CONTROL_ ## name, val) + + +#define SCU_PTSG_PORT_TASK_SCHEDULER_CONTROL_SUSPEND_SHIFT (0) +#define SCU_PTSG_PORT_TASK_SCHEDULER_CONTROL_SUSPEND_MASK (0x00000001) +#define SCU_PTSG_PORT_TASK_SCHEDULER_CONTROL_ENABLE_SHIFT (1) +#define SCU_PTSG_PORT_TASK_SCHEDULER_CONTROL_ENABLE_MASK (0x00000002) +#define SCU_PTSG_PORT_TASK_SCHEDULER_CONTROL_RESERVED_MASK (0xFFFFFFFC) + +#define SCU_PTSxCR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_PTSG_PORT_TASK_SCHEDULER_CONTROL_ ## name) + + +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_NEXT_RN_VALID_SHIFT (0) +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_NEXT_RN_VALID_MASK (0x00000001) +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_ACTIVE_RNSC_LIST_VALID_SHIFT (1) +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_ACTIVE_RNSC_LIST_VALID_MASK (0x00000002) +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_PTS_SUSPENDED_SHIFT (2) +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_PTS_SUSPENDED_MASK (0x00000004) +#define SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_RESERVED_MASK (0xFFFFFFF8) + +#define SCU_PTSxSR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_PTSG_PORT_TASK_SCHEDULER_STATUS_ ## name) + + +/* + * ***************************************************************************** + * * SGPIO Register shift and mask values + * ***************************************************************************** */ +#define SCU_SGPIO_CONTROL_SGPIO_ENABLE_SHIFT (0) +#define SCU_SGPIO_CONTROL_SGPIO_ENABLE_MASK (0x00000001) +#define SCU_SGPIO_CONTROL_SGPIO_SERIAL_CLOCK_SELECT_SHIFT (1) +#define SCU_SGPIO_CONTROL_SGPIO_SERIAL_CLOCK_SELECT_MASK (0x00000002) +#define SCU_SGPIO_CONTROL_SGPIO_SERIAL_SHIFT_WIDTH_SELECT_SHIFT (2) +#define SCU_SGPIO_CONTROL_SGPIO_SERIAL_SHIFT_WIDTH_SELECT_MASK (0x00000004) +#define SCU_SGPIO_CONTROL_SGPIO_TEST_BIT_SHIFT (15) +#define SCU_SGPIO_CONTROL_SGPIO_TEST_BIT_MASK (0x00008000) +#define SCU_SGPIO_CONTROL_SGPIO_RESERVED_MASK (0xFFFF7FF8) + +#define SCU_SGICRx_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SGPIO_CONTROL_SGPIO_ ## name) + +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R0_SHIFT (0) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R0_MASK (0x0000000F) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R1_SHIFT (4) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R1_MASK (0x000000F0) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R2_SHIFT (8) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R2_MASK (0x00000F00) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R3_SHIFT (12) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_R3_MASK (0x0000F000) +#define SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_RESERVED_MASK (0xFFFF0000) + +#define SCU_SGPBRx_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SGPIO_PROGRAMMABLE_BLINK_REGISTER_ ## name, value) + +#define SCU_SGPIO_START_DRIVE_LOWER_R0_SHIFT (0) +#define SCU_SGPIO_START_DRIVE_LOWER_R0_MASK (0x00000003) +#define SCU_SGPIO_START_DRIVE_LOWER_R1_SHIFT (4) +#define SCU_SGPIO_START_DRIVE_LOWER_R1_MASK (0x00000030) +#define SCU_SGPIO_START_DRIVE_LOWER_R2_SHIFT (8) +#define SCU_SGPIO_START_DRIVE_LOWER_R2_MASK (0x00000300) +#define SCU_SGPIO_START_DRIVE_LOWER_R3_SHIFT (12) +#define SCU_SGPIO_START_DRIVE_LOWER_R3_MASK (0x00003000) +#define SCU_SGPIO_START_DRIVE_LOWER_RESERVED_MASK (0xFFFF8888) + +#define SCU_SGSDLRx_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SGPIO_START_DRIVE_LOWER_ ## name, value) + +#define SCU_SGPIO_START_DRIVE_UPPER_R0_SHIFT (0) +#define SCU_SGPIO_START_DRIVE_UPPER_R0_MASK (0x00000003) +#define SCU_SGPIO_START_DRIVE_UPPER_R1_SHIFT (4) +#define SCU_SGPIO_START_DRIVE_UPPER_R1_MASK (0x00000030) +#define SCU_SGPIO_START_DRIVE_UPPER_R2_SHIFT (8) +#define SCU_SGPIO_START_DRIVE_UPPER_R2_MASK (0x00000300) +#define SCU_SGPIO_START_DRIVE_UPPER_R3_SHIFT (12) +#define SCU_SGPIO_START_DRIVE_UPPER_R3_MASK (0x00003000) +#define SCU_SGPIO_START_DRIVE_UPPER_RESERVED_MASK (0xFFFF8888) + +#define SCU_SGSDURx_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SGPIO_START_DRIVE_LOWER_ ## name, value) + +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D0_SHIFT (0) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D0_MASK (0x00000003) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D1_SHIFT (4) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D1_MASK (0x00000030) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D2_SHIFT (8) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D2_MASK (0x00000300) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D3_SHIFT (12) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_D3_MASK (0x00003000) +#define SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_RESERVED_MASK (0xFFFF8888) + +#define SCU_SGSIDLRx_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_ ## name, value) + +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D0_SHIFT (0) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D0_MASK (0x00000003) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D1_SHIFT (4) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D1_MASK (0x00000030) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D2_SHIFT (8) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D2_MASK (0x00000300) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D3_SHIFT (12) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_D3_MASK (0x00003000) +#define SCU_SGPIO_SERIAL_INPUT_DATA_UPPER_RESERVED_MASK (0xFFFF8888) + +#define SCU_SGSIDURx_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SGPIO_SERIAL_INPUT_DATA_LOWER_ ## name, value) + +#define SCU_SGPIO_VENDOR_SPECIFIC_CODE_SHIFT (0) +#define SCU_SGPIO_VENDOR_SPECIFIC_CODE_MASK (0x0000000F) +#define SCU_SGPIO_VENDOR_SPECIFIC_CODE_RESERVED_MASK (0xFFFFFFF0) + +#define SCU_SGVSCR_GEN_VAL(value) \ + SCU_GEN_VALUE(SCU_SGPIO_VENDOR_SPECIFIC_CODE ## name, value) + +#define SCU_SGPIO_OUPUT_DATA_SELECT_INPUT_DATA0_SHIFT (0) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INPUT_DATA0_MASK (0x00000003) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INVERT_INPUT_DATA0_SHIFT (2) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INVERT_INPUT_DATA0_MASK (0x00000004) +#define SCU_SGPIO_OUPUT_DATA_SELECT_JOG_ENABLE_DATA0_SHIFT (3) +#define SCU_SGPIO_OUPUT_DATA_SELECT_JOG_ENABLE_DATA0_MASK (0x00000008) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INPUT_DATA1_SHIFT (4) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INPUT_DATA1_MASK (0x00000030) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INVERT_INPUT_DATA1_SHIFT (6) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INVERT_INPUT_DATA1_MASK (0x00000040) +#define SCU_SGPIO_OUPUT_DATA_SELECT_JOG_ENABLE_DATA1_SHIFT (7) +#define SCU_SGPIO_OUPUT_DATA_SELECT_JOG_ENABLE_DATA1_MASK (0x00000080) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INPUT_DATA2_SHIFT (8) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INPUT_DATA2_MASK (0x00000300) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INVERT_INPUT_DATA2_SHIFT (10) +#define SCU_SGPIO_OUPUT_DATA_SELECT_INVERT_INPUT_DATA2_MASK (0x00000400) +#define SCU_SGPIO_OUPUT_DATA_SELECT_JOG_ENABLE_DATA2_SHIFT (11) +#define SCU_SGPIO_OUPUT_DATA_SELECT_JOG_ENABLE_DATA2_MASK (0x00000800) +#define SCU_SGPIO_OUPUT_DATA_SELECT_RESERVED_MASK (0xFFFFF000) + +#define SCU_SGODSR_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SGPIO_OUPUT_DATA_SELECT_ ## name, value) + +#define SCU_SGODSR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SGPIO_OUPUT_DATA_SELECT_ ## name) + +/* + * ***************************************************************************** + * * SMU Registers + * ***************************************************************************** */ + +/* + * ---------------------------------------------------------------------------- + * SMU Registers + * These registers are based off of BAR0 + * + * To calculate the offset for other functions use + * BAR0 + FN# * SystemPageSize * 2 + * + * The TCA is only accessable from FN#0 (Physical Function) and each + * is programmed by (BAR0 + SCU_SMU_TCA_OFFSET + (FN# * 0x04)) or + * TCA0 for FN#0 is at BAR0 + 0x0400 + * TCA1 for FN#1 is at BAR0 + 0x0404 + * etc. + * ---------------------------------------------------------------------------- + * Accessable to all FN#s */ +#define SCU_SMU_PCP_OFFSET 0x0000 +#define SCU_SMU_AMR_OFFSET 0x0004 +#define SCU_SMU_ISR_OFFSET 0x0010 +#define SCU_SMU_IMR_OFFSET 0x0014 +#define SCU_SMU_ICC_OFFSET 0x0018 +#define SCU_SMU_HTTLBAR_OFFSET 0x0020 +#define SCU_SMU_HTTUBAR_OFFSET 0x0024 +#define SCU_SMU_TCR_OFFSET 0x0028 +#define SCU_SMU_CQLBAR_OFFSET 0x0030 +#define SCU_SMU_CQUBAR_OFFSET 0x0034 +#define SCU_SMU_CQPR_OFFSET 0x0040 +#define SCU_SMU_CQGR_OFFSET 0x0044 +#define SCU_SMU_CQC_OFFSET 0x0048 +/* Accessable to FN#0 only */ +#define SCU_SMU_RNCLBAR_OFFSET 0x0080 +#define SCU_SMU_RNCUBAR_OFFSET 0x0084 +#define SCU_SMU_DCC_OFFSET 0x0090 +#define SCU_SMU_DFC_OFFSET 0x0094 +#define SCU_SMU_SMUCSR_OFFSET 0x0098 +#define SCU_SMU_SCUSRCR_OFFSET 0x009C +#define SCU_SMU_SMAW_OFFSET 0x00A0 +#define SCU_SMU_SMDW_OFFSET 0x00A4 +/* Accessable to FN#0 only */ +#define SCU_SMU_TCA_OFFSET 0x0400 +/* Accessable to all FN#s */ +#define SCU_SMU_MT_MLAR0_OFFSET 0x2000 +#define SCU_SMU_MT_MUAR0_OFFSET 0x2004 +#define SCU_SMU_MT_MDR0_OFFSET 0x2008 +#define SCU_SMU_MT_VCR0_OFFSET 0x200C +#define SCU_SMU_MT_MLAR1_OFFSET 0x2010 +#define SCU_SMU_MT_MUAR1_OFFSET 0x2014 +#define SCU_SMU_MT_MDR1_OFFSET 0x2018 +#define SCU_SMU_MT_VCR1_OFFSET 0x201C +#define SCU_SMU_MPBA_OFFSET 0x3000 + +/** + * struct smu_registers - These are the SMU registers + * + * + */ +struct smu_registers { +/* 0x0000 PCP */ + u32 post_context_port; +/* 0x0004 AMR */ + u32 address_modifier; + u32 reserved_08; + u32 reserved_0C; +/* 0x0010 ISR */ + u32 interrupt_status; +/* 0x0014 IMR */ + u32 interrupt_mask; +/* 0x0018 ICC */ + u32 interrupt_coalesce_control; + u32 reserved_1C; +/* 0x0020 HTTLBAR */ + u32 host_task_table_lower; +/* 0x0024 HTTUBAR */ + u32 host_task_table_upper; +/* 0x0028 TCR */ + u32 task_context_range; + u32 reserved_2C; +/* 0x0030 CQLBAR */ + u32 completion_queue_lower; +/* 0x0034 CQUBAR */ + u32 completion_queue_upper; + u32 reserved_38; + u32 reserved_3C; +/* 0x0040 CQPR */ + u32 completion_queue_put; +/* 0x0044 CQGR */ + u32 completion_queue_get; +/* 0x0048 CQC */ + u32 completion_queue_control; + u32 reserved_4C; + u32 reserved_5x[4]; + u32 reserved_6x[4]; + u32 reserved_7x[4]; +/* + * Accessable to FN#0 only + * 0x0080 RNCLBAR */ + u32 remote_node_context_lower; +/* 0x0084 RNCUBAR */ + u32 remote_node_context_upper; + u32 reserved_88; + u32 reserved_8C; +/* 0x0090 DCC */ + u32 device_context_capacity; +/* 0x0094 DFC */ + u32 device_function_capacity; +/* 0x0098 SMUCSR */ + u32 control_status; +/* 0x009C SCUSRCR */ + u32 soft_reset_control; +/* 0x00A0 SMAW */ + u32 mmr_address_window; +/* 0x00A4 SMDW */ + u32 mmr_data_window; + u32 reserved_A8; + u32 reserved_AC; +/* A whole bunch of reserved space */ + u32 reserved_Bx[4]; + u32 reserved_Cx[4]; + u32 reserved_Dx[4]; + u32 reserved_Ex[4]; + u32 reserved_Fx[4]; + u32 reserved_1xx[64]; + u32 reserved_2xx[64]; + u32 reserved_3xx[64]; +/* + * Accessable to FN#0 only + * 0x0400 TCA */ + u32 task_context_assignment[256]; +/* MSI-X registers not included */ +}; + +/* + * ***************************************************************************** + * SDMA Registers + * ***************************************************************************** */ +#define SCU_SDMA_BASE 0x6000 +#define SCU_SDMA_PUFATLHAR_OFFSET 0x0000 +#define SCU_SDMA_PUFATUHAR_OFFSET 0x0004 +#define SCU_SDMA_UFLHBAR_OFFSET 0x0008 +#define SCU_SDMA_UFUHBAR_OFFSET 0x000C +#define SCU_SDMA_UFQC_OFFSET 0x0010 +#define SCU_SDMA_UFQPP_OFFSET 0x0014 +#define SCU_SDMA_UFQGP_OFFSET 0x0018 +#define SCU_SDMA_PDMACR_OFFSET 0x001C +#define SCU_SDMA_CDMACR_OFFSET 0x0080 + +/** + * struct scu_sdma_registers - These are the SCU SDMA Registers + * + * + */ +struct scu_sdma_registers { +/* 0x0000 PUFATLHAR */ + u32 uf_address_table_lower; +/* 0x0004 PUFATUHAR */ + u32 uf_address_table_upper; +/* 0x0008 UFLHBAR */ + u32 uf_header_base_address_lower; +/* 0x000C UFUHBAR */ + u32 uf_header_base_address_upper; +/* 0x0010 UFQC */ + u32 unsolicited_frame_queue_control; +/* 0x0014 UFQPP */ + u32 unsolicited_frame_put_pointer; +/* 0x0018 UFQGP */ + u32 unsolicited_frame_get_pointer; +/* 0x001C PDMACR */ + u32 pdma_configuration; +/* Reserved until offset 0x80 */ + u32 reserved_0020_007C[0x18]; +/* 0x0080 CDMACR */ + u32 cdma_configuration; +/* Remainder SDMA register space */ + u32 reserved_0084_0400[0xDF]; + +}; + +/* + * ***************************************************************************** + * * SCU Link Registers + * ***************************************************************************** */ +#define SCU_PEG0_OFFSET 0x0000 +#define SCU_PEG1_OFFSET 0x8000 + +#define SCU_TL0_OFFSET 0x0000 +#define SCU_TL1_OFFSET 0x0400 +#define SCU_TL2_OFFSET 0x0800 +#define SCU_TL3_OFFSET 0x0C00 + +#define SCU_LL_OFFSET 0x0080 +#define SCU_LL0_OFFSET (SCU_TL0_OFFSET + SCU_LL_OFFSET) +#define SCU_LL1_OFFSET (SCU_TL1_OFFSET + SCU_LL_OFFSET) +#define SCU_LL2_OFFSET (SCU_TL2_OFFSET + SCU_LL_OFFSET) +#define SCU_LL3_OFFSET (SCU_TL3_OFFSET + SCU_LL_OFFSET) + +/* Transport Layer Offsets (PEG + TL) */ +#define SCU_TLCR_OFFSET 0x0000 +#define SCU_TLADTR_OFFSET 0x0004 +#define SCU_TLTTMR_OFFSET 0x0008 +#define SCU_TLEECR0_OFFSET 0x000C +#define SCU_STPTLDARNI_OFFSET 0x0010 + + +#define SCU_TLCR_HASH_SAS_CHECKING_ENABLE_SHIFT (0) +#define SCU_TLCR_HASH_SAS_CHECKING_ENABLE_MASK (0x00000001) +#define SCU_TLCR_CLEAR_TCI_NCQ_MAPPING_TABLE_SHIFT (1) +#define SCU_TLCR_CLEAR_TCI_NCQ_MAPPING_TABLE_MASK (0x00000002) +#define SCU_TLCR_STP_WRITE_DATA_PREFETCH_SHIFT (3) +#define SCU_TLCR_STP_WRITE_DATA_PREFETCH_MASK (0x00000008) +#define SCU_TLCR_CMD_NAK_STATUS_CODE_SHIFT (4) +#define SCU_TLCR_CMD_NAK_STATUS_CODE_MASK (0x00000010) +#define SCU_TLCR_RESERVED_MASK (0xFFFFFFEB) + +#define SCU_TLCR_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_TLCR_ ## name) + +/** + * struct scu_transport_layer_registers - These are the SCU Transport Layer + * registers + * + * + */ +struct scu_transport_layer_registers { + /* 0x0000 TLCR */ + u32 control; + /* 0x0004 TLADTR */ + u32 arbitration_delay_timer; + /* 0x0008 TLTTMR */ + u32 timer_test_mode; + /* 0x000C reserved */ + u32 reserved_0C; + /* 0x0010 STPTLDARNI */ + u32 stp_rni; + /* 0x0014 TLFEWPORCTRL */ + u32 tlfe_wpo_read_control; + /* 0x0018 TLFEWPORDATA */ + u32 tlfe_wpo_read_data; + /* 0x001C RXTLSSCSR1 */ + u32 rxtl_single_step_control_status_1; + /* 0x0020 RXTLSSCSR2 */ + u32 rxtl_single_step_control_status_2; + /* 0x0024 AWTRDDCR */ + u32 tlfe_awt_retry_delay_debug_control; + /* Remainder of TL memory space */ + u32 reserved_0028_007F[0x16]; + +}; + +/* Protocol Engine Group Registers */ +#define SCU_SCUVZECRx_OFFSET 0x1080 + +/* Link Layer Offsets (PEG + TL + LL) */ +#define SCU_SAS_SPDTOV_OFFSET 0x0000 +#define SCU_SAS_LLSTA_OFFSET 0x0004 +#define SCU_SATA_PSELTOV_OFFSET 0x0008 +#define SCU_SAS_TIMETOV_OFFSET 0x0010 +#define SCU_SAS_LOSTOT_OFFSET 0x0014 +#define SCU_SAS_LNKTOV_OFFSET 0x0018 +#define SCU_SAS_PHYTOV_OFFSET 0x001C +#define SCU_SAS_AFERCNT_OFFSET 0x0020 +#define SCU_SAS_WERCNT_OFFSET 0x0024 +#define SCU_SAS_TIID_OFFSET 0x0028 +#define SCU_SAS_TIDNH_OFFSET 0x002C +#define SCU_SAS_TIDNL_OFFSET 0x0030 +#define SCU_SAS_TISSAH_OFFSET 0x0034 +#define SCU_SAS_TISSAL_OFFSET 0x0038 +#define SCU_SAS_TIPID_OFFSET 0x003C +#define SCU_SAS_TIRES2_OFFSET 0x0040 +#define SCU_SAS_ADRSTA_OFFSET 0x0044 +#define SCU_SAS_MAWTTOV_OFFSET 0x0048 +#define SCU_SAS_FRPLDFIL_OFFSET 0x0054 +#define SCU_SAS_RFCNT_OFFSET 0x0060 +#define SCU_SAS_TFCNT_OFFSET 0x0064 +#define SCU_SAS_RFDCNT_OFFSET 0x0068 +#define SCU_SAS_TFDCNT_OFFSET 0x006C +#define SCU_SAS_LERCNT_OFFSET 0x0070 +#define SCU_SAS_RDISERRCNT_OFFSET 0x0074 +#define SCU_SAS_CRERCNT_OFFSET 0x0078 +#define SCU_STPCTL_OFFSET 0x007C +#define SCU_SAS_PCFG_OFFSET 0x0080 +#define SCU_SAS_CLKSM_OFFSET 0x0084 +#define SCU_SAS_TXCOMWAKE_OFFSET 0x0088 +#define SCU_SAS_TXCOMINIT_OFFSET 0x008C +#define SCU_SAS_TXCOMSAS_OFFSET 0x0090 +#define SCU_SAS_COMINIT_OFFSET 0x0094 +#define SCU_SAS_COMWAKE_OFFSET 0x0098 +#define SCU_SAS_COMSAS_OFFSET 0x009C +#define SCU_SAS_SFERCNT_OFFSET 0x00A0 +#define SCU_SAS_CDFERCNT_OFFSET 0x00A4 +#define SCU_SAS_DNFERCNT_OFFSET 0x00A8 +#define SCU_SAS_PRSTERCNT_OFFSET 0x00AC +#define SCU_SAS_CNTCTL_OFFSET 0x00B0 +#define SCU_SAS_SSPTOV_OFFSET 0x00B4 +#define SCU_FTCTL_OFFSET 0x00B8 +#define SCU_FRCTL_OFFSET 0x00BC +#define SCU_FTWMRK_OFFSET 0x00C0 +#define SCU_ENSPINUP_OFFSET 0x00C4 +#define SCU_SAS_TRNTOV_OFFSET 0x00C8 +#define SCU_SAS_PHYCAP_OFFSET 0x00CC +#define SCU_SAS_PHYCTL_OFFSET 0x00D0 +#define SCU_SAS_LLCTL_OFFSET 0x00D8 +#define SCU_AFE_XCVRCR_OFFSET 0x00DC +#define SCU_AFE_LUTCR_OFFSET 0x00E0 + +#define SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_SHIFT (0) +#define SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_MASK (0x00000003) +#define SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_GEN1 (0) +#define SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_GEN2 (1) +#define SCU_SAS_LINK_LAYER_CONTROL_MAX_LINK_RATE_GEN3 (2) +#define SCU_SAS_LINK_LAYER_CONTROL_BROADCAST_PRIMITIVE_SHIFT (2) +#define SCU_SAS_LINK_LAYER_CONTROL_BROADCAST_PRIMITIVE_MASK (0x000003FC) +#define SCU_SAS_LINK_LAYER_CONTROL_CLOSE_NO_ACTIVE_TASK_DISABLE_SHIFT (16) +#define SCU_SAS_LINK_LAYER_CONTROL_CLOSE_NO_ACTIVE_TASK_DISABLE_MASK (0x00010000) +#define SCU_SAS_LINK_LAYER_CONTROL_CLOSE_NO_OUTBOUND_TASK_DISABLE_SHIFT (17) +#define SCU_SAS_LINK_LAYER_CONTROL_CLOSE_NO_OUTBOUND_TASK_DISABLE_MASK (0x00020000) +#define SCU_SAS_LINK_LAYER_CONTROL_NO_OUTBOUND_TASK_TIMEOUT_SHIFT (24) +#define SCU_SAS_LINK_LAYER_CONTROL_NO_OUTBOUND_TASK_TIMEOUT_MASK (0xFF000000) +#define SCU_SAS_LINK_LAYER_CONTROL_RESERVED (0x00FCFC00) + +#define SCU_SAS_LLCTL_GEN_VAL(name, value) \ + SCU_GEN_VALUE(SCU_SAS_LINK_LAYER_CONTROL_ ## name, value) + +#define SCU_SAS_LLCTL_GEN_BIT(name) \ + SCU_GEN_BIT(SCU_SAS_LINK_LAYER_CONTROL_ ## name) + + +/* #define SCU_FRXHECR_DCNT_OFFSET 0x00B0 */ +#define SCU_PSZGCR_OFFSET 0x00E4 +#define SCU_SAS_RECPHYCAP_OFFSET 0x00E8 +/* #define SCU_TX_LUTSEL_OFFSET 0x00B8 */ + +#define SCU_SAS_PTxC_OFFSET 0x00D4 /* Same offset as SAS_TCTSTM */ + +/** + * struct scu_link_layer_registers - SCU Link Layer Registers + * + * + */ +struct scu_link_layer_registers { +/* 0x0000 SAS_SPDTOV */ + u32 speed_negotiation_timers; +/* 0x0004 SAS_LLSTA */ + u32 link_layer_status; +/* 0x0008 SATA_PSELTOV */ + u32 port_selector_timeout; + u32 reserved0C; +/* 0x0010 SAS_TIMETOV */ + u32 timeout_unit_value; +/* 0x0014 SAS_RCDTOV */ + u32 rcd_timeout; +/* 0x0018 SAS_LNKTOV */ + u32 link_timer_timeouts; +/* 0x001C SAS_PHYTOV */ + u32 sas_phy_timeouts; +/* 0x0020 SAS_AFERCNT */ + u32 received_address_frame_error_counter; +/* 0x0024 SAS_WERCNT */ + u32 invalid_dword_counter; +/* 0x0028 SAS_TIID */ + u32 transmit_identification; +/* 0x002C SAS_TIDNH */ + u32 sas_device_name_high; +/* 0x0030 SAS_TIDNL */ + u32 sas_device_name_low; +/* 0x0034 SAS_TISSAH */ + u32 source_sas_address_high; +/* 0x0038 SAS_TISSAL */ + u32 source_sas_address_low; +/* 0x003C SAS_TIPID */ + u32 identify_frame_phy_id; +/* 0x0040 SAS_TIRES2 */ + u32 identify_frame_reserved; +/* 0x0044 SAS_ADRSTA */ + u32 received_address_frame; +/* 0x0048 SAS_MAWTTOV */ + u32 maximum_arbitration_wait_timer_timeout; +/* 0x004C SAS_PTxC */ + u32 transmit_primitive; +/* 0x0050 SAS_RORES */ + u32 error_counter_event_notification_control; +/* 0x0054 SAS_FRPLDFIL */ + u32 frxq_payload_fill_threshold; +/* 0x0058 SAS_LLHANG_TOT */ + u32 link_layer_hang_detection_timeout; + u32 reserved_5C; +/* 0x0060 SAS_RFCNT */ + u32 received_frame_count; +/* 0x0064 SAS_TFCNT */ + u32 transmit_frame_count; +/* 0x0068 SAS_RFDCNT */ + u32 received_dword_count; +/* 0x006C SAS_TFDCNT */ + u32 transmit_dword_count; +/* 0x0070 SAS_LERCNT */ + u32 loss_of_sync_error_count; +/* 0x0074 SAS_RDISERRCNT */ + u32 running_disparity_error_count; +/* 0x0078 SAS_CRERCNT */ + u32 received_frame_crc_error_count; +/* 0x007C STPCTL */ + u32 stp_control; +/* 0x0080 SAS_PCFG */ + u32 phy_configuration; +/* 0x0084 SAS_CLKSM */ + u32 clock_skew_management; +/* 0x0088 SAS_TXCOMWAKE */ + u32 transmit_comwake_signal; +/* 0x008C SAS_TXCOMINIT */ + u32 transmit_cominit_signal; +/* 0x0090 SAS_TXCOMSAS */ + u32 transmit_comsas_signal; +/* 0x0094 SAS_COMINIT */ + u32 cominit_control; +/* 0x0098 SAS_COMWAKE */ + u32 comwake_control; +/* 0x009C SAS_COMSAS */ + u32 comsas_control; +/* 0x00A0 SAS_SFERCNT */ + u32 received_short_frame_count; +/* 0x00A4 SAS_CDFERCNT */ + u32 received_frame_without_credit_count; +/* 0x00A8 SAS_DNFERCNT */ + u32 received_frame_after_done_count; +/* 0x00AC SAS_PRSTERCNT */ + u32 phy_reset_problem_count; +/* 0x00B0 SAS_CNTCTL */ + u32 counter_control; +/* 0x00B4 SAS_SSPTOV */ + u32 ssp_timer_timeout_values; +/* 0x00B8 FTCTL */ + u32 ftx_control; +/* 0x00BC FRCTL */ + u32 frx_control; +/* 0x00C0 FTWMRK */ + u32 ftx_watermark; +/* 0x00C4 ENSPINUP */ + u32 notify_enable_spinup_control; +/* 0x00C8 SAS_TRNTOV */ + u32 sas_training_sequence_timer_values; +/* 0x00CC SAS_PHYCAP */ + u32 phy_capabilities; +/* 0x00D0 SAS_PHYCTL */ + u32 phy_control; + u32 reserved_d4; +/* 0x00D8 LLCTL */ + u32 link_layer_control; +/* 0x00DC AFE_XCVRCR */ + u32 afe_xcvr_control; +/* 0x00E0 AFE_LUTCR */ + u32 afe_lookup_table_control; +/* 0x00E4 PSZGCR */ + u32 phy_source_zone_group_control; +/* 0x00E8 SAS_RECPHYCAP */ + u32 receive_phycap; + u32 reserved_ec; +/* 0x00F0 SNAFERXRSTCTL */ + u32 speed_negotiation_afe_rx_reset_control; +/* 0x00F4 SAS_SSIPMCTL */ + u32 power_management_control; +/* 0x00F8 SAS_PSPREQ_PRIM */ + u32 sas_pm_partial_request_primitive; +/* 0x00FC SAS_PSSREQ_PRIM */ + u32 sas_pm_slumber_request_primitive; +/* 0x0100 SAS_PPSACK_PRIM */ + u32 sas_pm_ack_primitive_register; +/* 0x0104 SAS_PSNAK_PRIM */ + u32 sas_pm_nak_primitive_register; +/* 0x0108 SAS_SSIPMTOV */ + u32 sas_primitive_timeout; + u32 reserved_10c; +/* 0x0110 - 0x011C PLAPRDCTRLxREG */ + u32 pla_product_control[4]; +/* 0x0120 PLAPRDSUMREG */ + u32 pla_product_sum; +/* 0x0124 PLACONTROLREG */ + u32 pla_control; +/* Remainder of memory space 896 bytes */ + u32 reserved_0128_037f[0x96]; + +}; + +/* + * 0x00D4 // Same offset as SAS_TCTSTM SAS_PTxC + * u32 primitive_transmit_control; */ + +/* + * ---------------------------------------------------------------------------- + * SGPIO + * ---------------------------------------------------------------------------- */ +#define SCU_SGPIO_OFFSET 0x1400 + +/* #define SCU_SGPIO_OFFSET 0x6000 // later moves to 0x1400 see HSD 652625 */ +#define SCU_SGPIO_SGICR_OFFSET 0x0000 +#define SCU_SGPIO_SGPBR_OFFSET 0x0004 +#define SCU_SGPIO_SGSDLR_OFFSET 0x0008 +#define SCU_SGPIO_SGSDUR_OFFSET 0x000C +#define SCU_SGPIO_SGSIDLR_OFFSET 0x0010 +#define SCU_SGPIO_SGSIDUR_OFFSET 0x0014 +#define SCU_SGPIO_SGVSCR_OFFSET 0x0018 +/* Address from 0x0820 to 0x083C */ +#define SCU_SGPIO_SGODSR_OFFSET 0x0020 + +/** + * struct scu_sgpio_registers - SCU SGPIO Registers + * + * + */ +struct scu_sgpio_registers { +/* 0x0000 SGPIO_SGICR */ + u32 interface_control; +/* 0x0004 SGPIO_SGPBR */ + u32 blink_rate; +/* 0x0008 SGPIO_SGSDLR */ + u32 start_drive_lower; +/* 0x000C SGPIO_SGSDUR */ + u32 start_drive_upper; +/* 0x0010 SGPIO_SGSIDLR */ + u32 serial_input_lower; +/* 0x0014 SGPIO_SGSIDUR */ + u32 serial_input_upper; +/* 0x0018 SGPIO_SGVSCR */ + u32 vendor_specific_code; +/* 0x0020 SGPIO_SGODSR */ + u32 ouput_data_select[8]; +/* Remainder of memory space 256 bytes */ + u32 reserved_1444_14ff[0x31]; + +}; + +/* + * ***************************************************************************** + * * Defines for VIIT entry offsets + * * Access additional entries by SCU_VIIT_BASE + index * 0x10 + * ***************************************************************************** */ +#define SCU_VIIT_BASE 0x1c00 + +struct scu_viit_registers { + u32 registers[256]; +}; + +/* + * ***************************************************************************** + * * SCU PORT TASK SCHEDULER REGISTERS + * ***************************************************************************** */ + +#define SCU_PTSG_BASE 0x1000 + +#define SCU_PTSG_PTSGCR_OFFSET 0x0000 +#define SCU_PTSG_RTCR_OFFSET 0x0004 +#define SCU_PTSG_RTCCR_OFFSET 0x0008 +#define SCU_PTSG_PTS0CR_OFFSET 0x0010 +#define SCU_PTSG_PTS0SR_OFFSET 0x0014 +#define SCU_PTSG_PTS1CR_OFFSET 0x0018 +#define SCU_PTSG_PTS1SR_OFFSET 0x001C +#define SCU_PTSG_PTS2CR_OFFSET 0x0020 +#define SCU_PTSG_PTS2SR_OFFSET 0x0024 +#define SCU_PTSG_PTS3CR_OFFSET 0x0028 +#define SCU_PTSG_PTS3SR_OFFSET 0x002C +#define SCU_PTSG_PCSPE0CR_OFFSET 0x0030 +#define SCU_PTSG_PCSPE1CR_OFFSET 0x0034 +#define SCU_PTSG_PCSPE2CR_OFFSET 0x0038 +#define SCU_PTSG_PCSPE3CR_OFFSET 0x003C +#define SCU_PTSG_ETMTSCCR_OFFSET 0x0040 +#define SCU_PTSG_ETMRNSCCR_OFFSET 0x0044 + +/** + * struct scu_port_task_scheduler_registers - These are the control/stats pairs + * for each Port Task Scheduler. + * + * + */ +struct scu_port_task_scheduler_registers { + u32 control; + u32 status; +}; + +/** + * struct scu_port_task_scheduler_group_registers - These are the PORT Task + * Scheduler registers + * + * + */ +struct scu_port_task_scheduler_group_registers { +/* 0x0000 PTSGCR */ + u32 control; +/* 0x0004 RTCR */ + u32 real_time_clock; +/* 0x0008 RTCCR */ + u32 real_time_clock_control; +/* 0x000C */ + u32 reserved_0C; +/* + * 0x0010 PTS0CR + * 0x0014 PTS0SR + * 0x0018 PTS1CR + * 0x001C PTS1SR + * 0x0020 PTS2CR + * 0x0024 PTS2SR + * 0x0028 PTS3CR + * 0x002C PTS3SR */ + struct scu_port_task_scheduler_registers port[4]; +/* + * 0x0030 PCSPE0CR + * 0x0034 PCSPE1CR + * 0x0038 PCSPE2CR + * 0x003C PCSPE3CR */ + u32 protocol_engine[4]; +/* 0x0040 ETMTSCCR */ + u32 tc_scanning_interval_control; +/* 0x0044 ETMRNSCCR */ + u32 rnc_scanning_interval_control; +/* Remainder of memory space 128 bytes */ + u32 reserved_1048_107f[0x0E]; + +}; + +#define SCU_PTSG_SCUVZECR_OFFSET 0x003C + +/* + * ***************************************************************************** + * * AFE REGISTERS + * ***************************************************************************** */ +#define SCU_AFE_MMR_BASE 0xE000 + +/* + * AFE 0 is at offset 0x0800 + * AFE 1 is at offset 0x0900 + * AFE 2 is at offset 0x0a00 + * AFE 3 is at offset 0x0b00 */ +struct scu_afe_transceiver { + /* 0x0000 AFE_XCVR_CTRL0 */ + u32 afe_xcvr_control0; + /* 0x0004 AFE_XCVR_CTRL1 */ + u32 afe_xcvr_control1; + /* 0x0008 */ + u32 reserved_0008; + /* 0x000c afe_dfx_rx_control0 */ + u32 afe_dfx_rx_control0; + /* 0x0010 AFE_DFX_RX_CTRL1 */ + u32 afe_dfx_rx_control1; + /* 0x0014 */ + u32 reserved_0014; + /* 0x0018 AFE_DFX_RX_STS0 */ + u32 afe_dfx_rx_status0; + /* 0x001c AFE_DFX_RX_STS1 */ + u32 afe_dfx_rx_status1; + /* 0x0020 */ + u32 reserved_0020; + /* 0x0024 AFE_TX_CTRL */ + u32 afe_tx_control; + /* 0x0028 AFE_TX_AMP_CTRL0 */ + u32 afe_tx_amp_control0; + /* 0x002c AFE_TX_AMP_CTRL1 */ + u32 afe_tx_amp_control1; + /* 0x0030 AFE_TX_AMP_CTRL2 */ + u32 afe_tx_amp_control2; + /* 0x0034 AFE_TX_AMP_CTRL3 */ + u32 afe_tx_amp_control3; + /* 0x0038 afe_tx_ssc_control */ + u32 afe_tx_ssc_control; + /* 0x003c */ + u32 reserved_003c; + /* 0x0040 AFE_RX_SSC_CTRL0 */ + u32 afe_rx_ssc_control0; + /* 0x0044 AFE_RX_SSC_CTRL1 */ + u32 afe_rx_ssc_control1; + /* 0x0048 AFE_RX_SSC_CTRL2 */ + u32 afe_rx_ssc_control2; + /* 0x004c AFE_RX_EQ_STS0 */ + u32 afe_rx_eq_status0; + /* 0x0050 AFE_RX_EQ_STS1 */ + u32 afe_rx_eq_status1; + /* 0x0054 AFE_RX_CDR_STS */ + u32 afe_rx_cdr_status; + /* 0x0058 */ + u32 reserved_0058; + /* 0x005c AFE_CHAN_CTRL */ + u32 afe_channel_control; + /* 0x0060-0x006c */ + u32 reserved_0060_006c[0x04]; + /* 0x0070 AFE_XCVR_EC_STS0 */ + u32 afe_xcvr_error_capture_status0; + /* 0x0074 AFE_XCVR_EC_STS1 */ + u32 afe_xcvr_error_capture_status1; + /* 0x0078 AFE_XCVR_EC_STS2 */ + u32 afe_xcvr_error_capture_status2; + /* 0x007c afe_xcvr_ec_status3 */ + u32 afe_xcvr_error_capture_status3; + /* 0x0080 AFE_XCVR_EC_STS4 */ + u32 afe_xcvr_error_capture_status4; + /* 0x0084 AFE_XCVR_EC_STS5 */ + u32 afe_xcvr_error_capture_status5; + /* 0x0088-0x00fc */ + u32 reserved_008c_00fc[0x1e]; +}; + +/** + * struct scu_afe_registers - AFE Regsiters + * + * + */ +/* Uaoa AFE registers */ +struct scu_afe_registers { + /* 0Xe000 AFE_BIAS_CTRL */ + u32 afe_bias_control; + u32 reserved_0004; + /* 0x0008 AFE_PLL_CTRL0 */ + u32 afe_pll_control0; + /* 0x000c AFE_PLL_CTRL1 */ + u32 afe_pll_control1; + /* 0x0010 AFE_PLL_CTRL2 */ + u32 afe_pll_control2; + /* 0x0014 AFE_CB_STS */ + u32 afe_common_block_status; + /* 0x0018-0x007c */ + u32 reserved_18_7c[0x1a]; + /* 0x0080 AFE_PMSN_MCTRL0 */ + u32 afe_pmsn_master_control0; + /* 0x0084 AFE_PMSN_MCTRL1 */ + u32 afe_pmsn_master_control1; + /* 0x0088 AFE_PMSN_MCTRL2 */ + u32 afe_pmsn_master_control2; + /* 0x008C-0x00fc */ + u32 reserved_008c_00fc[0x1D]; + /* 0x0100 AFE_DFX_MST_CTRL0 */ + u32 afe_dfx_master_control0; + /* 0x0104 AFE_DFX_MST_CTRL1 */ + u32 afe_dfx_master_control1; + /* 0x0108 AFE_DFX_DCL_CTRL */ + u32 afe_dfx_dcl_control; + /* 0x010c AFE_DFX_DMON_CTRL */ + u32 afe_dfx_digital_monitor_control; + /* 0x0110 AFE_DFX_AMONP_CTRL */ + u32 afe_dfx_analog_p_monitor_control; + /* 0x0114 AFE_DFX_AMONN_CTRL */ + u32 afe_dfx_analog_n_monitor_control; + /* 0x0118 AFE_DFX_NTL_STS */ + u32 afe_dfx_ntl_status; + /* 0x011c AFE_DFX_FIFO_STS0 */ + u32 afe_dfx_fifo_status0; + /* 0x0120 AFE_DFX_FIFO_STS1 */ + u32 afe_dfx_fifo_status1; + /* 0x0124 AFE_DFX_MPAT_CTRL */ + u32 afe_dfx_master_pattern_control; + /* 0x0128 AFE_DFX_P0_CTRL */ + u32 afe_dfx_p0_control; + /* 0x012c-0x01a8 AFE_DFX_P0_DRx */ + u32 afe_dfx_p0_data[32]; + /* 0x01ac */ + u32 reserved_01ac; + /* 0x01b0-0x020c AFE_DFX_P0_IRx */ + u32 afe_dfx_p0_instruction[24]; + /* 0x0210 */ + u32 reserved_0210; + /* 0x0214 AFE_DFX_P1_CTRL */ + u32 afe_dfx_p1_control; + /* 0x0218-0x245 AFE_DFX_P1_DRx */ + u32 afe_dfx_p1_data[16]; + /* 0x0258-0x029c */ + u32 reserved_0258_029c[0x12]; + /* 0x02a0-0x02bc AFE_DFX_P1_IRx */ + u32 afe_dfx_p1_instruction[8]; + /* 0x02c0-0x2fc */ + u32 reserved_02c0_02fc[0x10]; + /* 0x0300 AFE_DFX_TX_PMSN_CTRL */ + u32 afe_dfx_tx_pmsn_control; + /* 0x0304 AFE_DFX_RX_PMSN_CTRL */ + u32 afe_dfx_rx_pmsn_control; + u32 reserved_0308; + /* 0x030c AFE_DFX_NOA_CTRL0 */ + u32 afe_dfx_noa_control0; + /* 0x0310 AFE_DFX_NOA_CTRL1 */ + u32 afe_dfx_noa_control1; + /* 0x0314 AFE_DFX_NOA_CTRL2 */ + u32 afe_dfx_noa_control2; + /* 0x0318 AFE_DFX_NOA_CTRL3 */ + u32 afe_dfx_noa_control3; + /* 0x031c AFE_DFX_NOA_CTRL4 */ + u32 afe_dfx_noa_control4; + /* 0x0320 AFE_DFX_NOA_CTRL5 */ + u32 afe_dfx_noa_control5; + /* 0x0324 AFE_DFX_NOA_CTRL6 */ + u32 afe_dfx_noa_control6; + /* 0x0328 AFE_DFX_NOA_CTRL7 */ + u32 afe_dfx_noa_control7; + /* 0x032c-0x07fc */ + u32 reserved_032c_07fc[0x135]; + + /* 0x0800-0x0bfc */ + struct scu_afe_transceiver scu_afe_xcvr[4]; + + /* 0x0c00-0x0ffc */ + u32 reserved_0c00_0ffc[0x0100]; +}; + +struct scu_protocol_engine_group_registers { + u32 table[0xE0]; +}; + + +struct scu_viit_iit { + u32 table[256]; +}; + +/** + * Placeholder for the ZONE Partition Table information ZONING will not be + * included in the 1.1 release. + * + * + */ +struct scu_zone_partition_table { + u32 table[2048]; +}; + +/** + * Placeholder for the CRAM register since I am not sure if we need to + * read/write to these registers as yet. + * + * + */ +struct scu_completion_ram { + u32 ram[128]; +}; + +/** + * Placeholder for the FBRAM registers since I am not sure if we need to + * read/write to these registers as yet. + * + * + */ +struct scu_frame_buffer_ram { + u32 ram[128]; +}; + +#define scu_scratch_ram_SIZE_IN_DWORDS 256 + +/** + * Placeholder for the scratch RAM registers. + * + * + */ +struct scu_scratch_ram { + u32 ram[scu_scratch_ram_SIZE_IN_DWORDS]; +}; + +/** + * Placeholder since I am not yet sure what these registers are here for. + * + * + */ +struct noa_protocol_engine_partition { + u32 reserved[64]; +}; + +/** + * Placeholder since I am not yet sure what these registers are here for. + * + * + */ +struct noa_hub_partition { + u32 reserved[64]; +}; + +/** + * Placeholder since I am not yet sure what these registers are here for. + * + * + */ +struct noa_host_interface_partition { + u32 reserved[64]; +}; + +/** + * struct transport_link_layer_pair - The SCU Hardware pairs up the TL + * registers with the LL registers so we must place them adjcent to make the + * array of registers in the PEG. + * + * + */ +struct transport_link_layer_pair { + struct scu_transport_layer_registers tl; + struct scu_link_layer_registers ll; +}; + +/** + * struct scu_peg_registers - SCU Protocol Engine Memory mapped register space. + * These registers are unique to each protocol engine group. There can be + * at most two PEG for a single SCU part. + * + * + */ +struct scu_peg_registers { + struct transport_link_layer_pair pe[4]; + struct scu_port_task_scheduler_group_registers ptsg; + struct scu_protocol_engine_group_registers peg; + struct scu_sgpio_registers sgpio; + u32 reserved_01500_1BFF[0x1C0]; + struct scu_viit_entry viit[64]; + struct scu_zone_partition_table zpt0; + struct scu_zone_partition_table zpt1; +}; + +/** + * struct scu_registers - SCU regsiters including both PEG registers if we turn + * on that compile option. All of these registers are in the memory mapped + * space returned from BAR1. + * + * + */ +struct scu_registers { + /* 0x0000 - PEG 0 */ + struct scu_peg_registers peg0; + + /* 0x6000 - SDMA and Miscellaneous */ + struct scu_sdma_registers sdma; + struct scu_completion_ram cram; + struct scu_frame_buffer_ram fbram; + u32 reserved_6800_69FF[0x80]; + struct noa_protocol_engine_partition noa_pe; + struct noa_hub_partition noa_hub; + struct noa_host_interface_partition noa_if; + u32 reserved_6d00_7fff[0x4c0]; + + /* 0x8000 - PEG 1 */ + struct scu_peg_registers peg1; + + /* 0xE000 - AFE Registers */ + struct scu_afe_registers afe; + + /* 0xF000 - reserved */ + u32 reserved_f000_211fff[0x80c00]; + + /* 0x212000 - scratch RAM */ + struct scu_scratch_ram scratch_ram; +}; + +#endif /* _SCU_REGISTERS_HEADER_ */ diff --git a/drivers/scsi/isci/remote_device.c b/drivers/scsi/isci/remote_device.c new file mode 100644 index 0000000..b6e6368 --- /dev/null +++ b/drivers/scsi/isci/remote_device.c @@ -0,0 +1,1501 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#include <scsi/sas.h> +#include "isci.h" +#include "port.h" +#include "remote_device.h" +#include "request.h" +#include "remote_node_context.h" +#include "scu_event_codes.h" +#include "task.h" + +/** + * isci_remote_device_not_ready() - This function is called by the ihost when + * the remote device is not ready. We mark the isci device as ready (not + * "ready_for_io") and signal the waiting proccess. + * @isci_host: This parameter specifies the isci host object. + * @isci_device: This parameter specifies the remote device + * + * sci_lock is held on entrance to this function. + */ +static void isci_remote_device_not_ready(struct isci_host *ihost, + struct isci_remote_device *idev, u32 reason) +{ + struct isci_request *ireq; + + dev_dbg(&ihost->pdev->dev, + "%s: isci_device = %p\n", __func__, idev); + + switch (reason) { + case SCIC_REMOTE_DEVICE_NOT_READY_STOP_REQUESTED: + set_bit(IDEV_GONE, &idev->flags); + break; + case SCIC_REMOTE_DEVICE_NOT_READY_SATA_SDB_ERROR_FIS_RECEIVED: + set_bit(IDEV_IO_NCQERROR, &idev->flags); + + /* Kill all outstanding requests for the device. */ + list_for_each_entry(ireq, &idev->reqs_in_process, dev_node) { + + dev_dbg(&ihost->pdev->dev, + "%s: isci_device = %p request = %p\n", + __func__, idev, ireq); + + sci_controller_terminate_request(ihost, + idev, + ireq); + } + /* Fall through into the default case... */ + default: + clear_bit(IDEV_IO_READY, &idev->flags); + break; + } +} + +/** + * isci_remote_device_ready() - This function is called by the ihost when the + * remote device is ready. We mark the isci device as ready and signal the + * waiting proccess. + * @ihost: our valid isci_host + * @idev: remote device + * + */ +static void isci_remote_device_ready(struct isci_host *ihost, struct isci_remote_device *idev) +{ + dev_dbg(&ihost->pdev->dev, + "%s: idev = %p\n", __func__, idev); + + clear_bit(IDEV_IO_NCQERROR, &idev->flags); + set_bit(IDEV_IO_READY, &idev->flags); + if (test_and_clear_bit(IDEV_START_PENDING, &idev->flags)) + wake_up(&ihost->eventq); +} + +/* called once the remote node context is ready to be freed. + * The remote device can now report that its stop operation is complete. none + */ +static void rnc_destruct_done(void *_dev) +{ + struct isci_remote_device *idev = _dev; + + BUG_ON(idev->started_request_count != 0); + sci_change_state(&idev->sm, SCI_DEV_STOPPED); +} + +static enum sci_status sci_remote_device_terminate_requests(struct isci_remote_device *idev) +{ + struct isci_host *ihost = idev->owning_port->owning_controller; + enum sci_status status = SCI_SUCCESS; + u32 i; + + for (i = 0; i < SCI_MAX_IO_REQUESTS; i++) { + struct isci_request *ireq = ihost->reqs[i]; + enum sci_status s; + + if (!test_bit(IREQ_ACTIVE, &ireq->flags) || + ireq->target_device != idev) + continue; + + s = sci_controller_terminate_request(ihost, idev, ireq); + if (s != SCI_SUCCESS) + status = s; + } + + return status; +} + +enum sci_status sci_remote_device_stop(struct isci_remote_device *idev, + u32 timeout) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + + switch (state) { + case SCI_DEV_INITIAL: + case SCI_DEV_FAILED: + case SCI_DEV_FINAL: + default: + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + case SCI_DEV_STOPPED: + return SCI_SUCCESS; + case SCI_DEV_STARTING: + /* device not started so there had better be no requests */ + BUG_ON(idev->started_request_count != 0); + sci_remote_node_context_destruct(&idev->rnc, + rnc_destruct_done, idev); + /* Transition to the stopping state and wait for the + * remote node to complete being posted and invalidated. + */ + sci_change_state(sm, SCI_DEV_STOPPING); + return SCI_SUCCESS; + case SCI_DEV_READY: + case SCI_STP_DEV_IDLE: + case SCI_STP_DEV_CMD: + case SCI_STP_DEV_NCQ: + case SCI_STP_DEV_NCQ_ERROR: + case SCI_STP_DEV_AWAIT_RESET: + case SCI_SMP_DEV_IDLE: + case SCI_SMP_DEV_CMD: + sci_change_state(sm, SCI_DEV_STOPPING); + if (idev->started_request_count == 0) { + sci_remote_node_context_destruct(&idev->rnc, + rnc_destruct_done, idev); + return SCI_SUCCESS; + } else + return sci_remote_device_terminate_requests(idev); + break; + case SCI_DEV_STOPPING: + /* All requests should have been terminated, but if there is an + * attempt to stop a device already in the stopping state, then + * try again to terminate. + */ + return sci_remote_device_terminate_requests(idev); + case SCI_DEV_RESETTING: + sci_change_state(sm, SCI_DEV_STOPPING); + return SCI_SUCCESS; + } +} + +enum sci_status sci_remote_device_reset(struct isci_remote_device *idev) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + + switch (state) { + case SCI_DEV_INITIAL: + case SCI_DEV_STOPPED: + case SCI_DEV_STARTING: + case SCI_SMP_DEV_IDLE: + case SCI_SMP_DEV_CMD: + case SCI_DEV_STOPPING: + case SCI_DEV_FAILED: + case SCI_DEV_RESETTING: + case SCI_DEV_FINAL: + default: + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + case SCI_DEV_READY: + case SCI_STP_DEV_IDLE: + case SCI_STP_DEV_CMD: + case SCI_STP_DEV_NCQ: + case SCI_STP_DEV_NCQ_ERROR: + case SCI_STP_DEV_AWAIT_RESET: + sci_change_state(sm, SCI_DEV_RESETTING); + return SCI_SUCCESS; + } +} + +enum sci_status sci_remote_device_reset_complete(struct isci_remote_device *idev) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + + if (state != SCI_DEV_RESETTING) { + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + sci_change_state(sm, SCI_DEV_READY); + return SCI_SUCCESS; +} + +enum sci_status sci_remote_device_suspend(struct isci_remote_device *idev, + u32 suspend_type) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + + if (state != SCI_STP_DEV_CMD) { + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + return sci_remote_node_context_suspend(&idev->rnc, + suspend_type, NULL, NULL); +} + +enum sci_status sci_remote_device_frame_handler(struct isci_remote_device *idev, + u32 frame_index) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + struct isci_host *ihost = idev->owning_port->owning_controller; + enum sci_status status; + + switch (state) { + case SCI_DEV_INITIAL: + case SCI_DEV_STOPPED: + case SCI_DEV_STARTING: + case SCI_STP_DEV_IDLE: + case SCI_SMP_DEV_IDLE: + case SCI_DEV_FINAL: + default: + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + /* Return the frame back to the controller */ + sci_controller_release_frame(ihost, frame_index); + return SCI_FAILURE_INVALID_STATE; + case SCI_DEV_READY: + case SCI_STP_DEV_NCQ_ERROR: + case SCI_STP_DEV_AWAIT_RESET: + case SCI_DEV_STOPPING: + case SCI_DEV_FAILED: + case SCI_DEV_RESETTING: { + struct isci_request *ireq; + struct ssp_frame_hdr hdr; + void *frame_header; + ssize_t word_cnt; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + &frame_header); + if (status != SCI_SUCCESS) + return status; + + word_cnt = sizeof(hdr) / sizeof(u32); + sci_swab32_cpy(&hdr, frame_header, word_cnt); + + ireq = sci_request_by_tag(ihost, be16_to_cpu(hdr.tag)); + if (ireq && ireq->target_device == idev) { + /* The IO request is now in charge of releasing the frame */ + status = sci_io_request_frame_handler(ireq, frame_index); + } else { + /* We could not map this tag to a valid IO + * request Just toss the frame and continue + */ + sci_controller_release_frame(ihost, frame_index); + } + break; + } + case SCI_STP_DEV_NCQ: { + struct dev_to_host_fis *hdr; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&hdr); + if (status != SCI_SUCCESS) + return status; + + if (hdr->fis_type == FIS_SETDEVBITS && + (hdr->status & ATA_ERR)) { + idev->not_ready_reason = SCIC_REMOTE_DEVICE_NOT_READY_SATA_SDB_ERROR_FIS_RECEIVED; + + /* TODO Check sactive and complete associated IO if any. */ + sci_change_state(sm, SCI_STP_DEV_NCQ_ERROR); + } else if (hdr->fis_type == FIS_REGD2H && + (hdr->status & ATA_ERR)) { + /* + * Some devices return D2H FIS when an NCQ error is detected. + * Treat this like an SDB error FIS ready reason. + */ + idev->not_ready_reason = SCIC_REMOTE_DEVICE_NOT_READY_SATA_SDB_ERROR_FIS_RECEIVED; + sci_change_state(&idev->sm, SCI_STP_DEV_NCQ_ERROR); + } else + status = SCI_FAILURE; + + sci_controller_release_frame(ihost, frame_index); + break; + } + case SCI_STP_DEV_CMD: + case SCI_SMP_DEV_CMD: + /* The device does not process any UF received from the hardware while + * in this state. All unsolicited frames are forwarded to the io request + * object. + */ + status = sci_io_request_frame_handler(idev->working_request, frame_index); + break; + } + + return status; +} + +static bool is_remote_device_ready(struct isci_remote_device *idev) +{ + + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + + switch (state) { + case SCI_DEV_READY: + case SCI_STP_DEV_IDLE: + case SCI_STP_DEV_CMD: + case SCI_STP_DEV_NCQ: + case SCI_STP_DEV_NCQ_ERROR: + case SCI_STP_DEV_AWAIT_RESET: + case SCI_SMP_DEV_IDLE: + case SCI_SMP_DEV_CMD: + return true; + default: + return false; + } +} + +enum sci_status sci_remote_device_event_handler(struct isci_remote_device *idev, + u32 event_code) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + enum sci_status status; + + switch (scu_get_event_type(event_code)) { + case SCU_EVENT_TYPE_RNC_OPS_MISC: + case SCU_EVENT_TYPE_RNC_SUSPEND_TX: + case SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX: + status = sci_remote_node_context_event_handler(&idev->rnc, event_code); + break; + case SCU_EVENT_TYPE_PTX_SCHEDULE_EVENT: + if (scu_get_event_code(event_code) == SCU_EVENT_IT_NEXUS_TIMEOUT) { + status = SCI_SUCCESS; + + /* Suspend the associated RNC */ + sci_remote_node_context_suspend(&idev->rnc, + SCI_SOFTWARE_SUSPENSION, + NULL, NULL); + + dev_dbg(scirdev_to_dev(idev), + "%s: device: %p event code: %x: %s\n", + __func__, idev, event_code, + is_remote_device_ready(idev) + ? "I_T_Nexus_Timeout event" + : "I_T_Nexus_Timeout event in wrong state"); + + break; + } + /* Else, fall through and treat as unhandled... */ + default: + dev_dbg(scirdev_to_dev(idev), + "%s: device: %p event code: %x: %s\n", + __func__, idev, event_code, + is_remote_device_ready(idev) + ? "unexpected event" + : "unexpected event in wrong state"); + status = SCI_FAILURE_INVALID_STATE; + break; + } + + if (status != SCI_SUCCESS) + return status; + + if (state == SCI_STP_DEV_IDLE) { + + /* We pick up suspension events to handle specifically to this + * state. We resume the RNC right away. + */ + if (scu_get_event_type(event_code) == SCU_EVENT_TYPE_RNC_SUSPEND_TX || + scu_get_event_type(event_code) == SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX) + status = sci_remote_node_context_resume(&idev->rnc, NULL, NULL); + } + + return status; +} + +static void sci_remote_device_start_request(struct isci_remote_device *idev, + struct isci_request *ireq, + enum sci_status status) +{ + struct isci_port *iport = idev->owning_port; + + /* cleanup requests that failed after starting on the port */ + if (status != SCI_SUCCESS) + sci_port_complete_io(iport, idev, ireq); + else { + kref_get(&idev->kref); + idev->started_request_count++; + } +} + +enum sci_status sci_remote_device_start_io(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + struct isci_port *iport = idev->owning_port; + enum sci_status status; + + switch (state) { + case SCI_DEV_INITIAL: + case SCI_DEV_STOPPED: + case SCI_DEV_STARTING: + case SCI_STP_DEV_NCQ_ERROR: + case SCI_DEV_STOPPING: + case SCI_DEV_FAILED: + case SCI_DEV_RESETTING: + case SCI_DEV_FINAL: + default: + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + case SCI_DEV_READY: + /* attempt to start an io request for this device object. The remote + * device object will issue the start request for the io and if + * successful it will start the request for the port object then + * increment its own request count. + */ + status = sci_port_start_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_remote_node_context_start_io(&idev->rnc, ireq); + if (status != SCI_SUCCESS) + break; + + status = sci_request_start(ireq); + break; + case SCI_STP_DEV_IDLE: { + /* handle the start io operation for a sata device that is in + * the command idle state. - Evalute the type of IO request to + * be started - If its an NCQ request change to NCQ substate - + * If its any other command change to the CMD substate + * + * If this is a softreset we may want to have a different + * substate. + */ + enum sci_remote_device_states new_state; + struct sas_task *task = isci_request_access_task(ireq); + + status = sci_port_start_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_remote_node_context_start_io(&idev->rnc, ireq); + if (status != SCI_SUCCESS) + break; + + status = sci_request_start(ireq); + if (status != SCI_SUCCESS) + break; + + if (task->ata_task.use_ncq) + new_state = SCI_STP_DEV_NCQ; + else { + idev->working_request = ireq; + new_state = SCI_STP_DEV_CMD; + } + sci_change_state(sm, new_state); + break; + } + case SCI_STP_DEV_NCQ: { + struct sas_task *task = isci_request_access_task(ireq); + + if (task->ata_task.use_ncq) { + status = sci_port_start_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_remote_node_context_start_io(&idev->rnc, ireq); + if (status != SCI_SUCCESS) + break; + + status = sci_request_start(ireq); + } else + return SCI_FAILURE_INVALID_STATE; + break; + } + case SCI_STP_DEV_AWAIT_RESET: + return SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED; + case SCI_SMP_DEV_IDLE: + status = sci_port_start_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_remote_node_context_start_io(&idev->rnc, ireq); + if (status != SCI_SUCCESS) + break; + + status = sci_request_start(ireq); + if (status != SCI_SUCCESS) + break; + + idev->working_request = ireq; + sci_change_state(&idev->sm, SCI_SMP_DEV_CMD); + break; + case SCI_STP_DEV_CMD: + case SCI_SMP_DEV_CMD: + /* device is already handling a command it can not accept new commands + * until this one is complete. + */ + return SCI_FAILURE_INVALID_STATE; + } + + sci_remote_device_start_request(idev, ireq, status); + return status; +} + +static enum sci_status common_complete_io(struct isci_port *iport, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + enum sci_status status; + + status = sci_request_complete(ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_port_complete_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + sci_remote_device_decrement_request_count(idev); + return status; +} + +enum sci_status sci_remote_device_complete_io(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + struct isci_port *iport = idev->owning_port; + enum sci_status status; + + switch (state) { + case SCI_DEV_INITIAL: + case SCI_DEV_STOPPED: + case SCI_DEV_STARTING: + case SCI_STP_DEV_IDLE: + case SCI_SMP_DEV_IDLE: + case SCI_DEV_FAILED: + case SCI_DEV_FINAL: + default: + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + case SCI_DEV_READY: + case SCI_STP_DEV_AWAIT_RESET: + case SCI_DEV_RESETTING: + status = common_complete_io(iport, idev, ireq); + break; + case SCI_STP_DEV_CMD: + case SCI_STP_DEV_NCQ: + case SCI_STP_DEV_NCQ_ERROR: + status = common_complete_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + break; + + if (ireq->sci_status == SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED) { + /* This request causes hardware error, device needs to be Lun Reset. + * So here we force the state machine to IDLE state so the rest IOs + * can reach RNC state handler, these IOs will be completed by RNC with + * status of "DEVICE_RESET_REQUIRED", instead of "INVALID STATE". + */ + sci_change_state(sm, SCI_STP_DEV_AWAIT_RESET); + } else if (idev->started_request_count == 0) + sci_change_state(sm, SCI_STP_DEV_IDLE); + break; + case SCI_SMP_DEV_CMD: + status = common_complete_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + break; + sci_change_state(sm, SCI_SMP_DEV_IDLE); + break; + case SCI_DEV_STOPPING: + status = common_complete_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + break; + + if (idev->started_request_count == 0) + sci_remote_node_context_destruct(&idev->rnc, + rnc_destruct_done, + idev); + break; + } + + if (status != SCI_SUCCESS) + dev_err(scirdev_to_dev(idev), + "%s: Port:0x%p Device:0x%p Request:0x%p Status:0x%x " + "could not complete\n", __func__, iport, + idev, ireq, status); + else + isci_put_device(idev); + + return status; +} + +static void sci_remote_device_continue_request(void *dev) +{ + struct isci_remote_device *idev = dev; + + /* we need to check if this request is still valid to continue. */ + if (idev->working_request) + sci_controller_continue_io(idev->working_request); +} + +enum sci_status sci_remote_device_start_task(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + struct isci_port *iport = idev->owning_port; + enum sci_status status; + + switch (state) { + case SCI_DEV_INITIAL: + case SCI_DEV_STOPPED: + case SCI_DEV_STARTING: + case SCI_SMP_DEV_IDLE: + case SCI_SMP_DEV_CMD: + case SCI_DEV_STOPPING: + case SCI_DEV_FAILED: + case SCI_DEV_RESETTING: + case SCI_DEV_FINAL: + default: + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + case SCI_STP_DEV_IDLE: + case SCI_STP_DEV_CMD: + case SCI_STP_DEV_NCQ: + case SCI_STP_DEV_NCQ_ERROR: + case SCI_STP_DEV_AWAIT_RESET: + status = sci_port_start_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_remote_node_context_start_task(&idev->rnc, ireq); + if (status != SCI_SUCCESS) + goto out; + + status = sci_request_start(ireq); + if (status != SCI_SUCCESS) + goto out; + + /* Note: If the remote device state is not IDLE this will + * replace the request that probably resulted in the task + * management request. + */ + idev->working_request = ireq; + sci_change_state(sm, SCI_STP_DEV_CMD); + + /* The remote node context must cleanup the TCi to NCQ mapping + * table. The only way to do this correctly is to either write + * to the TLCR register or to invalidate and repost the RNC. In + * either case the remote node context state machine will take + * the correct action when the remote node context is suspended + * and later resumed. + */ + sci_remote_node_context_suspend(&idev->rnc, + SCI_SOFTWARE_SUSPENSION, NULL, NULL); + sci_remote_node_context_resume(&idev->rnc, + sci_remote_device_continue_request, + idev); + + out: + sci_remote_device_start_request(idev, ireq, status); + /* We need to let the controller start request handler know that + * it can't post TC yet. We will provide a callback function to + * post TC when RNC gets resumed. + */ + return SCI_FAILURE_RESET_DEVICE_PARTIAL_SUCCESS; + case SCI_DEV_READY: + status = sci_port_start_io(iport, idev, ireq); + if (status != SCI_SUCCESS) + return status; + + status = sci_remote_node_context_start_task(&idev->rnc, ireq); + if (status != SCI_SUCCESS) + break; + + status = sci_request_start(ireq); + break; + } + sci_remote_device_start_request(idev, ireq, status); + + return status; +} + +void sci_remote_device_post_request(struct isci_remote_device *idev, u32 request) +{ + struct isci_port *iport = idev->owning_port; + u32 context; + + context = request | + (ISCI_PEG << SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_SHIFT) | + (iport->physical_port_index << SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT) | + idev->rnc.remote_node_index; + + sci_controller_post_request(iport->owning_controller, context); +} + +/* called once the remote node context has transisitioned to a + * ready state. This is the indication that the remote device object can also + * transition to ready. + */ +static void remote_device_resume_done(void *_dev) +{ + struct isci_remote_device *idev = _dev; + + if (is_remote_device_ready(idev)) + return; + + /* go 'ready' if we are not already in a ready state */ + sci_change_state(&idev->sm, SCI_DEV_READY); +} + +static void sci_stp_remote_device_ready_idle_substate_resume_complete_handler(void *_dev) +{ + struct isci_remote_device *idev = _dev; + struct isci_host *ihost = idev->owning_port->owning_controller; + + /* For NCQ operation we do not issue a isci_remote_device_not_ready(). + * As a result, avoid sending the ready notification. + */ + if (idev->sm.previous_state_id != SCI_STP_DEV_NCQ) + isci_remote_device_ready(ihost, idev); +} + +static void sci_remote_device_initial_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + + /* Initial state is a transitional state to the stopped state */ + sci_change_state(&idev->sm, SCI_DEV_STOPPED); +} + +/** + * sci_remote_device_destruct() - free remote node context and destruct + * @remote_device: This parameter specifies the remote device to be destructed. + * + * Remote device objects are a limited resource. As such, they must be + * protected. Thus calls to construct and destruct are mutually exclusive and + * non-reentrant. The return value shall indicate if the device was + * successfully destructed or if some failure occurred. enum sci_status This value + * is returned if the device is successfully destructed. + * SCI_FAILURE_INVALID_REMOTE_DEVICE This value is returned if the supplied + * device isn't valid (e.g. it's already been destoryed, the handle isn't + * valid, etc.). + */ +static enum sci_status sci_remote_device_destruct(struct isci_remote_device *idev) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + struct isci_host *ihost; + + if (state != SCI_DEV_STOPPED) { + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + ihost = idev->owning_port->owning_controller; + sci_controller_free_remote_node_context(ihost, idev, + idev->rnc.remote_node_index); + idev->rnc.remote_node_index = SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX; + sci_change_state(sm, SCI_DEV_FINAL); + + return SCI_SUCCESS; +} + +/** + * isci_remote_device_deconstruct() - This function frees an isci_remote_device. + * @ihost: This parameter specifies the isci host object. + * @idev: This parameter specifies the remote device to be freed. + * + */ +static void isci_remote_device_deconstruct(struct isci_host *ihost, struct isci_remote_device *idev) +{ + dev_dbg(&ihost->pdev->dev, + "%s: isci_device = %p\n", __func__, idev); + + /* There should not be any outstanding io's. All paths to + * here should go through isci_remote_device_nuke_requests. + * If we hit this condition, we will need a way to complete + * io requests in process */ + BUG_ON(!list_empty(&idev->reqs_in_process)); + + sci_remote_device_destruct(idev); + list_del_init(&idev->node); + isci_put_device(idev); +} + +static void sci_remote_device_stopped_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + u32 prev_state; + + /* If we are entering from the stopping state let the SCI User know that + * the stop operation has completed. + */ + prev_state = idev->sm.previous_state_id; + if (prev_state == SCI_DEV_STOPPING) + isci_remote_device_deconstruct(ihost, idev); + + sci_controller_remote_device_stopped(ihost, idev); +} + +static void sci_remote_device_starting_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + + isci_remote_device_not_ready(ihost, idev, + SCIC_REMOTE_DEVICE_NOT_READY_START_REQUESTED); +} + +static void sci_remote_device_ready_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + struct domain_device *dev = idev->domain_dev; + + if (dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_SATA)) { + sci_change_state(&idev->sm, SCI_STP_DEV_IDLE); + } else if (dev_is_expander(dev)) { + sci_change_state(&idev->sm, SCI_SMP_DEV_IDLE); + } else + isci_remote_device_ready(ihost, idev); +} + +static void sci_remote_device_ready_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct domain_device *dev = idev->domain_dev; + + if (dev->dev_type == SAS_END_DEV) { + struct isci_host *ihost = idev->owning_port->owning_controller; + + isci_remote_device_not_ready(ihost, idev, + SCIC_REMOTE_DEVICE_NOT_READY_STOP_REQUESTED); + } +} + +static void sci_remote_device_resetting_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + + sci_remote_node_context_suspend( + &idev->rnc, SCI_SOFTWARE_SUSPENSION, NULL, NULL); +} + +static void sci_remote_device_resetting_state_exit(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + + sci_remote_node_context_resume(&idev->rnc, NULL, NULL); +} + +static void sci_stp_remote_device_ready_idle_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + + idev->working_request = NULL; + if (sci_remote_node_context_is_ready(&idev->rnc)) { + /* + * Since the RNC is ready, it's alright to finish completion + * processing (e.g. signal the remote device is ready). */ + sci_stp_remote_device_ready_idle_substate_resume_complete_handler(idev); + } else { + sci_remote_node_context_resume(&idev->rnc, + sci_stp_remote_device_ready_idle_substate_resume_complete_handler, + idev); + } +} + +static void sci_stp_remote_device_ready_cmd_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + + BUG_ON(idev->working_request == NULL); + + isci_remote_device_not_ready(ihost, idev, + SCIC_REMOTE_DEVICE_NOT_READY_SATA_REQUEST_STARTED); +} + +static void sci_stp_remote_device_ready_ncq_error_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + + if (idev->not_ready_reason == SCIC_REMOTE_DEVICE_NOT_READY_SATA_SDB_ERROR_FIS_RECEIVED) + isci_remote_device_not_ready(ihost, idev, + idev->not_ready_reason); +} + +static void sci_smp_remote_device_ready_idle_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + + isci_remote_device_ready(ihost, idev); +} + +static void sci_smp_remote_device_ready_cmd_substate_enter(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + struct isci_host *ihost = idev->owning_port->owning_controller; + + BUG_ON(idev->working_request == NULL); + + isci_remote_device_not_ready(ihost, idev, + SCIC_REMOTE_DEVICE_NOT_READY_SMP_REQUEST_STARTED); +} + +static void sci_smp_remote_device_ready_cmd_substate_exit(struct sci_base_state_machine *sm) +{ + struct isci_remote_device *idev = container_of(sm, typeof(*idev), sm); + + idev->working_request = NULL; +} + +static const struct sci_base_state sci_remote_device_state_table[] = { + [SCI_DEV_INITIAL] = { + .enter_state = sci_remote_device_initial_state_enter, + }, + [SCI_DEV_STOPPED] = { + .enter_state = sci_remote_device_stopped_state_enter, + }, + [SCI_DEV_STARTING] = { + .enter_state = sci_remote_device_starting_state_enter, + }, + [SCI_DEV_READY] = { + .enter_state = sci_remote_device_ready_state_enter, + .exit_state = sci_remote_device_ready_state_exit + }, + [SCI_STP_DEV_IDLE] = { + .enter_state = sci_stp_remote_device_ready_idle_substate_enter, + }, + [SCI_STP_DEV_CMD] = { + .enter_state = sci_stp_remote_device_ready_cmd_substate_enter, + }, + [SCI_STP_DEV_NCQ] = { }, + [SCI_STP_DEV_NCQ_ERROR] = { + .enter_state = sci_stp_remote_device_ready_ncq_error_substate_enter, + }, + [SCI_STP_DEV_AWAIT_RESET] = { }, + [SCI_SMP_DEV_IDLE] = { + .enter_state = sci_smp_remote_device_ready_idle_substate_enter, + }, + [SCI_SMP_DEV_CMD] = { + .enter_state = sci_smp_remote_device_ready_cmd_substate_enter, + .exit_state = sci_smp_remote_device_ready_cmd_substate_exit, + }, + [SCI_DEV_STOPPING] = { }, + [SCI_DEV_FAILED] = { }, + [SCI_DEV_RESETTING] = { + .enter_state = sci_remote_device_resetting_state_enter, + .exit_state = sci_remote_device_resetting_state_exit + }, + [SCI_DEV_FINAL] = { }, +}; + +/** + * sci_remote_device_construct() - common construction + * @sci_port: SAS/SATA port through which this device is accessed. + * @sci_dev: remote device to construct + * + * This routine just performs benign initialization and does not + * allocate the remote_node_context which is left to + * sci_remote_device_[de]a_construct(). sci_remote_device_destruct() + * frees the remote_node_context(s) for the device. + */ +static void sci_remote_device_construct(struct isci_port *iport, + struct isci_remote_device *idev) +{ + idev->owning_port = iport; + idev->started_request_count = 0; + + sci_init_sm(&idev->sm, sci_remote_device_state_table, SCI_DEV_INITIAL); + + sci_remote_node_context_construct(&idev->rnc, + SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX); +} + +/** + * sci_remote_device_da_construct() - construct direct attached device. + * + * The information (e.g. IAF, Signature FIS, etc.) necessary to build + * the device is known to the SCI Core since it is contained in the + * sci_phy object. Remote node context(s) is/are a global resource + * allocated by this routine, freed by sci_remote_device_destruct(). + * + * Returns: + * SCI_FAILURE_DEVICE_EXISTS - device has already been constructed. + * SCI_FAILURE_UNSUPPORTED_PROTOCOL - e.g. sas device attached to + * sata-only controller instance. + * SCI_FAILURE_INSUFFICIENT_RESOURCES - remote node contexts exhausted. + */ +static enum sci_status sci_remote_device_da_construct(struct isci_port *iport, + struct isci_remote_device *idev) +{ + enum sci_status status; + struct domain_device *dev = idev->domain_dev; + + sci_remote_device_construct(iport, idev); + + /* + * This information is request to determine how many remote node context + * entries will be needed to store the remote node. + */ + idev->is_direct_attached = true; + status = sci_controller_allocate_remote_node_context(iport->owning_controller, + idev, + &idev->rnc.remote_node_index); + + if (status != SCI_SUCCESS) + return status; + + if (dev->dev_type == SAS_END_DEV || dev->dev_type == SATA_DEV || + (dev->tproto & SAS_PROTOCOL_STP) || dev_is_expander(dev)) + /* pass */; + else + return SCI_FAILURE_UNSUPPORTED_PROTOCOL; + + idev->connection_rate = sci_port_get_max_allowed_speed(iport); + + /* / @todo Should I assign the port width by reading all of the phys on the port? */ + idev->device_port_width = 1; + + return SCI_SUCCESS; +} + +/** + * sci_remote_device_ea_construct() - construct expander attached device + * + * Remote node context(s) is/are a global resource allocated by this + * routine, freed by sci_remote_device_destruct(). + * + * Returns: + * SCI_FAILURE_DEVICE_EXISTS - device has already been constructed. + * SCI_FAILURE_UNSUPPORTED_PROTOCOL - e.g. sas device attached to + * sata-only controller instance. + * SCI_FAILURE_INSUFFICIENT_RESOURCES - remote node contexts exhausted. + */ +static enum sci_status sci_remote_device_ea_construct(struct isci_port *iport, + struct isci_remote_device *idev) +{ + struct domain_device *dev = idev->domain_dev; + enum sci_status status; + + sci_remote_device_construct(iport, idev); + + status = sci_controller_allocate_remote_node_context(iport->owning_controller, + idev, + &idev->rnc.remote_node_index); + if (status != SCI_SUCCESS) + return status; + + if (dev->dev_type == SAS_END_DEV || dev->dev_type == SATA_DEV || + (dev->tproto & SAS_PROTOCOL_STP) || dev_is_expander(dev)) + /* pass */; + else + return SCI_FAILURE_UNSUPPORTED_PROTOCOL; + + /* + * For SAS-2 the physical link rate is actually a logical link + * rate that incorporates multiplexing. The SCU doesn't + * incorporate multiplexing and for the purposes of the + * connection the logical link rate is that same as the + * physical. Furthermore, the SAS-2 and SAS-1.1 fields overlay + * one another, so this code works for both situations. */ + idev->connection_rate = min_t(u16, sci_port_get_max_allowed_speed(iport), + dev->linkrate); + + /* / @todo Should I assign the port width by reading all of the phys on the port? */ + idev->device_port_width = 1; + + return SCI_SUCCESS; +} + +/** + * sci_remote_device_start() - This method will start the supplied remote + * device. This method enables normal IO requests to flow through to the + * remote device. + * @remote_device: This parameter specifies the device to be started. + * @timeout: This parameter specifies the number of milliseconds in which the + * start operation should complete. + * + * An indication of whether the device was successfully started. SCI_SUCCESS + * This value is returned if the device was successfully started. + * SCI_FAILURE_INVALID_PHY This value is returned if the user attempts to start + * the device when there have been no phys added to it. + */ +static enum sci_status sci_remote_device_start(struct isci_remote_device *idev, + u32 timeout) +{ + struct sci_base_state_machine *sm = &idev->sm; + enum sci_remote_device_states state = sm->current_state_id; + enum sci_status status; + + if (state != SCI_DEV_STOPPED) { + dev_warn(scirdev_to_dev(idev), "%s: in wrong state: %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + status = sci_remote_node_context_resume(&idev->rnc, + remote_device_resume_done, + idev); + if (status != SCI_SUCCESS) + return status; + + sci_change_state(sm, SCI_DEV_STARTING); + + return SCI_SUCCESS; +} + +static enum sci_status isci_remote_device_construct(struct isci_port *iport, + struct isci_remote_device *idev) +{ + struct isci_host *ihost = iport->isci_host; + struct domain_device *dev = idev->domain_dev; + enum sci_status status; + + if (dev->parent && dev_is_expander(dev->parent)) + status = sci_remote_device_ea_construct(iport, idev); + else + status = sci_remote_device_da_construct(iport, idev); + + if (status != SCI_SUCCESS) { + dev_dbg(&ihost->pdev->dev, "%s: construct failed: %d\n", + __func__, status); + + return status; + } + + /* start the device. */ + status = sci_remote_device_start(idev, ISCI_REMOTE_DEVICE_START_TIMEOUT); + + if (status != SCI_SUCCESS) + dev_warn(&ihost->pdev->dev, "remote device start failed: %d\n", + status); + + return status; +} + +void isci_remote_device_nuke_requests(struct isci_host *ihost, struct isci_remote_device *idev) +{ + DECLARE_COMPLETION_ONSTACK(aborted_task_completion); + + dev_dbg(&ihost->pdev->dev, + "%s: idev = %p\n", __func__, idev); + + /* Cleanup all requests pending for this device. */ + isci_terminate_pending_requests(ihost, idev); + + dev_dbg(&ihost->pdev->dev, + "%s: idev = %p, done\n", __func__, idev); +} + +/** + * This function builds the isci_remote_device when a libsas dev_found message + * is received. + * @isci_host: This parameter specifies the isci host object. + * @port: This parameter specifies the isci_port conected to this device. + * + * pointer to new isci_remote_device. + */ +static struct isci_remote_device * +isci_remote_device_alloc(struct isci_host *ihost, struct isci_port *iport) +{ + struct isci_remote_device *idev; + int i; + + for (i = 0; i < SCI_MAX_REMOTE_DEVICES; i++) { + idev = &ihost->devices[i]; + if (!test_and_set_bit(IDEV_ALLOCATED, &idev->flags)) + break; + } + + if (i >= SCI_MAX_REMOTE_DEVICES) { + dev_warn(&ihost->pdev->dev, "%s: failed\n", __func__); + return NULL; + } + + if (WARN_ONCE(!list_empty(&idev->reqs_in_process), "found requests in process\n")) + return NULL; + + if (WARN_ONCE(!list_empty(&idev->node), "found non-idle remote device\n")) + return NULL; + + return idev; +} + +void isci_remote_device_release(struct kref *kref) +{ + struct isci_remote_device *idev = container_of(kref, typeof(*idev), kref); + struct isci_host *ihost = idev->isci_port->isci_host; + + idev->domain_dev = NULL; + idev->isci_port = NULL; + clear_bit(IDEV_START_PENDING, &idev->flags); + clear_bit(IDEV_STOP_PENDING, &idev->flags); + clear_bit(IDEV_IO_READY, &idev->flags); + clear_bit(IDEV_GONE, &idev->flags); + clear_bit(IDEV_EH, &idev->flags); + smp_mb__before_clear_bit(); + clear_bit(IDEV_ALLOCATED, &idev->flags); + wake_up(&ihost->eventq); +} + +/** + * isci_remote_device_stop() - This function is called internally to stop the + * remote device. + * @isci_host: This parameter specifies the isci host object. + * @isci_device: This parameter specifies the remote device. + * + * The status of the ihost request to stop. + */ +enum sci_status isci_remote_device_stop(struct isci_host *ihost, struct isci_remote_device *idev) +{ + enum sci_status status; + unsigned long flags; + + dev_dbg(&ihost->pdev->dev, + "%s: isci_device = %p\n", __func__, idev); + + spin_lock_irqsave(&ihost->scic_lock, flags); + idev->domain_dev->lldd_dev = NULL; /* disable new lookups */ + set_bit(IDEV_GONE, &idev->flags); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + /* Kill all outstanding requests. */ + isci_remote_device_nuke_requests(ihost, idev); + + set_bit(IDEV_STOP_PENDING, &idev->flags); + + spin_lock_irqsave(&ihost->scic_lock, flags); + status = sci_remote_device_stop(idev, 50); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + /* Wait for the stop complete callback. */ + if (WARN_ONCE(status != SCI_SUCCESS, "failed to stop device\n")) + /* nothing to wait for */; + else + wait_for_device_stop(ihost, idev); + + return status; +} + +/** + * isci_remote_device_gone() - This function is called by libsas when a domain + * device is removed. + * @domain_device: This parameter specifies the libsas domain device. + * + */ +void isci_remote_device_gone(struct domain_device *dev) +{ + struct isci_host *ihost = dev_to_ihost(dev); + struct isci_remote_device *idev = dev->lldd_dev; + + dev_dbg(&ihost->pdev->dev, + "%s: domain_device = %p, isci_device = %p, isci_port = %p\n", + __func__, dev, idev, idev->isci_port); + + isci_remote_device_stop(ihost, idev); +} + + +/** + * isci_remote_device_found() - This function is called by libsas when a remote + * device is discovered. A remote device object is created and started. the + * function then sleeps until the sci core device started message is + * received. + * @domain_device: This parameter specifies the libsas domain device. + * + * status, zero indicates success. + */ +int isci_remote_device_found(struct domain_device *domain_dev) +{ + struct isci_host *isci_host = dev_to_ihost(domain_dev); + struct isci_port *isci_port; + struct isci_phy *isci_phy; + struct asd_sas_port *sas_port; + struct asd_sas_phy *sas_phy; + struct isci_remote_device *isci_device; + enum sci_status status; + + dev_dbg(&isci_host->pdev->dev, + "%s: domain_device = %p\n", __func__, domain_dev); + + wait_for_start(isci_host); + + sas_port = domain_dev->port; + sas_phy = list_first_entry(&sas_port->phy_list, struct asd_sas_phy, + port_phy_el); + isci_phy = to_iphy(sas_phy); + isci_port = isci_phy->isci_port; + + /* we are being called for a device on this port, + * so it has to come up eventually + */ + wait_for_completion(&isci_port->start_complete); + + if ((isci_stopping == isci_port_get_state(isci_port)) || + (isci_stopped == isci_port_get_state(isci_port))) + return -ENODEV; + + isci_device = isci_remote_device_alloc(isci_host, isci_port); + if (!isci_device) + return -ENODEV; + + kref_init(&isci_device->kref); + INIT_LIST_HEAD(&isci_device->node); + + spin_lock_irq(&isci_host->scic_lock); + isci_device->domain_dev = domain_dev; + isci_device->isci_port = isci_port; + list_add_tail(&isci_device->node, &isci_port->remote_dev_list); + + set_bit(IDEV_START_PENDING, &isci_device->flags); + status = isci_remote_device_construct(isci_port, isci_device); + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_device = %p\n", + __func__, isci_device); + + if (status == SCI_SUCCESS) { + /* device came up, advertise it to the world */ + domain_dev->lldd_dev = isci_device; + } else + isci_put_device(isci_device); + spin_unlock_irq(&isci_host->scic_lock); + + /* wait for the device ready callback. */ + wait_for_device_start(isci_host, isci_device); + + return status == SCI_SUCCESS ? 0 : -ENODEV; +} +/** + * isci_device_is_reset_pending() - This function will check if there is any + * pending reset condition on the device. + * @request: This parameter is the isci_device object. + * + * true if there is a reset pending for the device. + */ +bool isci_device_is_reset_pending( + struct isci_host *isci_host, + struct isci_remote_device *isci_device) +{ + struct isci_request *isci_request; + struct isci_request *tmp_req; + bool reset_is_pending = false; + unsigned long flags; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_device = %p\n", __func__, isci_device); + + spin_lock_irqsave(&isci_host->scic_lock, flags); + + /* Check for reset on all pending requests. */ + list_for_each_entry_safe(isci_request, tmp_req, + &isci_device->reqs_in_process, dev_node) { + dev_dbg(&isci_host->pdev->dev, + "%s: isci_device = %p request = %p\n", + __func__, isci_device, isci_request); + + if (isci_request->ttype == io_task) { + struct sas_task *task = isci_request_access_task( + isci_request); + + spin_lock(&task->task_state_lock); + if (task->task_state_flags & SAS_TASK_NEED_DEV_RESET) + reset_is_pending = true; + spin_unlock(&task->task_state_lock); + } + } + + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_device = %p reset_is_pending = %d\n", + __func__, isci_device, reset_is_pending); + + return reset_is_pending; +} + +/** + * isci_device_clear_reset_pending() - This function will clear if any pending + * reset condition flags on the device. + * @request: This parameter is the isci_device object. + * + * true if there is a reset pending for the device. + */ +void isci_device_clear_reset_pending(struct isci_host *ihost, struct isci_remote_device *idev) +{ + struct isci_request *isci_request; + struct isci_request *tmp_req; + unsigned long flags = 0; + + dev_dbg(&ihost->pdev->dev, "%s: idev=%p, ihost=%p\n", + __func__, idev, ihost); + + spin_lock_irqsave(&ihost->scic_lock, flags); + + /* Clear reset pending on all pending requests. */ + list_for_each_entry_safe(isci_request, tmp_req, + &idev->reqs_in_process, dev_node) { + dev_dbg(&ihost->pdev->dev, "%s: idev = %p request = %p\n", + __func__, idev, isci_request); + + if (isci_request->ttype == io_task) { + + unsigned long flags2; + struct sas_task *task = isci_request_access_task( + isci_request); + + spin_lock_irqsave(&task->task_state_lock, flags2); + task->task_state_flags &= ~SAS_TASK_NEED_DEV_RESET; + spin_unlock_irqrestore(&task->task_state_lock, flags2); + } + } + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} diff --git a/drivers/scsi/isci/remote_device.h b/drivers/scsi/isci/remote_device.h new file mode 100644 index 0000000..57ccfc3 --- /dev/null +++ b/drivers/scsi/isci/remote_device.h @@ -0,0 +1,352 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _ISCI_REMOTE_DEVICE_H_ +#define _ISCI_REMOTE_DEVICE_H_ +#include <scsi/libsas.h> +#include <linux/kref.h> +#include "scu_remote_node_context.h" +#include "remote_node_context.h" +#include "port.h" + +enum sci_remote_device_not_ready_reason_code { + SCIC_REMOTE_DEVICE_NOT_READY_START_REQUESTED, + SCIC_REMOTE_DEVICE_NOT_READY_STOP_REQUESTED, + SCIC_REMOTE_DEVICE_NOT_READY_SATA_REQUEST_STARTED, + SCIC_REMOTE_DEVICE_NOT_READY_SATA_SDB_ERROR_FIS_RECEIVED, + SCIC_REMOTE_DEVICE_NOT_READY_SMP_REQUEST_STARTED, + SCIC_REMOTE_DEVICE_NOT_READY_REASON_CODE_MAX +}; + +/** + * isci_remote_device - isci representation of a sas expander / end point + * @device_port_width: hw setting for number of simultaneous connections + * @connection_rate: per-taskcontext connection rate for this device + * @working_request: SATA requests have no tag we for unaccelerated + * protocols we need a method to associate unsolicited + * frames with a pending request + */ +struct isci_remote_device { + #define IDEV_START_PENDING 0 + #define IDEV_STOP_PENDING 1 + #define IDEV_ALLOCATED 2 + #define IDEV_EH 3 + #define IDEV_GONE 4 + #define IDEV_IO_READY 5 + #define IDEV_IO_NCQERROR 6 + unsigned long flags; + struct kref kref; + struct isci_port *isci_port; + struct domain_device *domain_dev; + struct list_head node; + struct list_head reqs_in_process; + struct sci_base_state_machine sm; + u32 device_port_width; + enum sas_linkrate connection_rate; + bool is_direct_attached; + struct isci_port *owning_port; + struct sci_remote_node_context rnc; + /* XXX unify with device reference counting and delete */ + u32 started_request_count; + struct isci_request *working_request; + u32 not_ready_reason; +}; + +#define ISCI_REMOTE_DEVICE_START_TIMEOUT 5000 + +/* device reference routines must be called under sci_lock */ +static inline struct isci_remote_device *isci_lookup_device(struct domain_device *dev) +{ + struct isci_remote_device *idev = dev->lldd_dev; + + if (idev && !test_bit(IDEV_GONE, &idev->flags)) { + kref_get(&idev->kref); + return idev; + } + + return NULL; +} + +void isci_remote_device_release(struct kref *kref); +static inline void isci_put_device(struct isci_remote_device *idev) +{ + if (idev) + kref_put(&idev->kref, isci_remote_device_release); +} + +enum sci_status isci_remote_device_stop(struct isci_host *ihost, + struct isci_remote_device *idev); +void isci_remote_device_nuke_requests(struct isci_host *ihost, + struct isci_remote_device *idev); +void isci_remote_device_gone(struct domain_device *domain_dev); +int isci_remote_device_found(struct domain_device *domain_dev); +bool isci_device_is_reset_pending(struct isci_host *ihost, + struct isci_remote_device *idev); +void isci_device_clear_reset_pending(struct isci_host *ihost, + struct isci_remote_device *idev); +/** + * sci_remote_device_stop() - This method will stop both transmission and + * reception of link activity for the supplied remote device. This method + * disables normal IO requests from flowing through to the remote device. + * @remote_device: This parameter specifies the device to be stopped. + * @timeout: This parameter specifies the number of milliseconds in which the + * stop operation should complete. + * + * An indication of whether the device was successfully stopped. SCI_SUCCESS + * This value is returned if the transmission and reception for the device was + * successfully stopped. + */ +enum sci_status sci_remote_device_stop( + struct isci_remote_device *idev, + u32 timeout); + +/** + * sci_remote_device_reset() - This method will reset the device making it + * ready for operation. This method must be called anytime the device is + * reset either through a SMP phy control or a port hard reset request. + * @remote_device: This parameter specifies the device to be reset. + * + * This method does not actually cause the device hardware to be reset. This + * method resets the software object so that it will be operational after a + * device hardware reset completes. An indication of whether the device reset + * was accepted. SCI_SUCCESS This value is returned if the device reset is + * started. + */ +enum sci_status sci_remote_device_reset( + struct isci_remote_device *idev); + +/** + * sci_remote_device_reset_complete() - This method informs the device object + * that the reset operation is complete and the device can resume operation + * again. + * @remote_device: This parameter specifies the device which is to be informed + * of the reset complete operation. + * + * An indication that the device is resuming operation. SCI_SUCCESS the device + * is resuming operation. + */ +enum sci_status sci_remote_device_reset_complete( + struct isci_remote_device *idev); + +/** + * enum sci_remote_device_states - This enumeration depicts all the states + * for the common remote device state machine. + * + * + */ +enum sci_remote_device_states { + /** + * Simply the initial state for the base remote device state machine. + */ + SCI_DEV_INITIAL, + + /** + * This state indicates that the remote device has successfully been + * stopped. In this state no new IO operations are permitted. + * This state is entered from the INITIAL state. + * This state is entered from the STOPPING state. + */ + SCI_DEV_STOPPED, + + /** + * This state indicates the the remote device is in the process of + * becoming ready (i.e. starting). In this state no new IO operations + * are permitted. + * This state is entered from the STOPPED state. + */ + SCI_DEV_STARTING, + + /** + * This state indicates the remote device is now ready. Thus, the user + * is able to perform IO operations on the remote device. + * This state is entered from the STARTING state. + */ + SCI_DEV_READY, + + /** + * This is the idle substate for the stp remote device. When there are no + * active IO for the device it is is in this state. + */ + SCI_STP_DEV_IDLE, + + /** + * This is the command state for for the STP remote device. This state is + * entered when the device is processing a non-NCQ command. The device object + * will fail any new start IO requests until this command is complete. + */ + SCI_STP_DEV_CMD, + + /** + * This is the NCQ state for the STP remote device. This state is entered + * when the device is processing an NCQ reuqest. It will remain in this state + * so long as there is one or more NCQ requests being processed. + */ + SCI_STP_DEV_NCQ, + + /** + * This is the NCQ error state for the STP remote device. This state is + * entered when an SDB error FIS is received by the device object while in the + * NCQ state. The device object will only accept a READ LOG command while in + * this state. + */ + SCI_STP_DEV_NCQ_ERROR, + + /** + * This is the READY substate indicates the device is waiting for the RESET task + * coming to be recovered from certain hardware specific error. + */ + SCI_STP_DEV_AWAIT_RESET, + + /** + * This is the ready operational substate for the remote device. This is the + * normal operational state for a remote device. + */ + SCI_SMP_DEV_IDLE, + + /** + * This is the suspended state for the remote device. This is the state that + * the device is placed in when a RNC suspend is received by the SCU hardware. + */ + SCI_SMP_DEV_CMD, + + /** + * This state indicates that the remote device is in the process of + * stopping. In this state no new IO operations are permitted, but + * existing IO operations are allowed to complete. + * This state is entered from the READY state. + * This state is entered from the FAILED state. + */ + SCI_DEV_STOPPING, + + /** + * This state indicates that the remote device has failed. + * In this state no new IO operations are permitted. + * This state is entered from the INITIALIZING state. + * This state is entered from the READY state. + */ + SCI_DEV_FAILED, + + /** + * This state indicates the device is being reset. + * In this state no new IO operations are permitted. + * This state is entered from the READY state. + */ + SCI_DEV_RESETTING, + + /** + * Simply the final state for the base remote device state machine. + */ + SCI_DEV_FINAL, +}; + +static inline struct isci_remote_device *rnc_to_dev(struct sci_remote_node_context *rnc) +{ + struct isci_remote_device *idev; + + idev = container_of(rnc, typeof(*idev), rnc); + + return idev; +} + +static inline bool dev_is_expander(struct domain_device *dev) +{ + return dev->dev_type == EDGE_DEV || dev->dev_type == FANOUT_DEV; +} + +static inline void sci_remote_device_decrement_request_count(struct isci_remote_device *idev) +{ + /* XXX delete this voodoo when converting to the top-level device + * reference count + */ + if (WARN_ONCE(idev->started_request_count == 0, + "%s: tried to decrement started_request_count past 0!?", + __func__)) + /* pass */; + else + idev->started_request_count--; +} + +enum sci_status sci_remote_device_frame_handler( + struct isci_remote_device *idev, + u32 frame_index); + +enum sci_status sci_remote_device_event_handler( + struct isci_remote_device *idev, + u32 event_code); + +enum sci_status sci_remote_device_start_io( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_status sci_remote_device_start_task( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_status sci_remote_device_complete_io( + struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq); + +enum sci_status sci_remote_device_suspend( + struct isci_remote_device *idev, + u32 suspend_type); + +void sci_remote_device_post_request( + struct isci_remote_device *idev, + u32 request); + +#endif /* !defined(_ISCI_REMOTE_DEVICE_H_) */ diff --git a/drivers/scsi/isci/remote_node_context.c b/drivers/scsi/isci/remote_node_context.c new file mode 100644 index 0000000..748e833 --- /dev/null +++ b/drivers/scsi/isci/remote_node_context.c @@ -0,0 +1,627 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "host.h" +#include "isci.h" +#include "remote_device.h" +#include "remote_node_context.h" +#include "scu_event_codes.h" +#include "scu_task_context.h" + + +/** + * + * @sci_rnc: The RNC for which the is posted request is being made. + * + * This method will return true if the RNC is not in the initial state. In all + * other states the RNC is considered active and this will return true. The + * destroy request of the state machine drives the RNC back to the initial + * state. If the state machine changes then this routine will also have to be + * changed. bool true if the state machine is not in the initial state false if + * the state machine is in the initial state + */ + +/** + * + * @sci_rnc: The state of the remote node context object to check. + * + * This method will return true if the remote node context is in a READY state + * otherwise it will return false bool true if the remote node context is in + * the ready state. false if the remote node context is not in the ready state. + */ +bool sci_remote_node_context_is_ready( + struct sci_remote_node_context *sci_rnc) +{ + u32 current_state = sci_rnc->sm.current_state_id; + + if (current_state == SCI_RNC_READY) { + return true; + } + + return false; +} + +static union scu_remote_node_context *sci_rnc_by_id(struct isci_host *ihost, u16 id) +{ + if (id < ihost->remote_node_entries && + ihost->device_table[id]) + return &ihost->remote_node_context_table[id]; + + return NULL; +} + +static void sci_remote_node_context_construct_buffer(struct sci_remote_node_context *sci_rnc) +{ + struct isci_remote_device *idev = rnc_to_dev(sci_rnc); + struct domain_device *dev = idev->domain_dev; + int rni = sci_rnc->remote_node_index; + union scu_remote_node_context *rnc; + struct isci_host *ihost; + __le64 sas_addr; + + ihost = idev->owning_port->owning_controller; + rnc = sci_rnc_by_id(ihost, rni); + + memset(rnc, 0, sizeof(union scu_remote_node_context) + * sci_remote_device_node_count(idev)); + + rnc->ssp.remote_node_index = rni; + rnc->ssp.remote_node_port_width = idev->device_port_width; + rnc->ssp.logical_port_index = idev->owning_port->physical_port_index; + + /* sas address is __be64, context ram format is __le64 */ + sas_addr = cpu_to_le64(SAS_ADDR(dev->sas_addr)); + rnc->ssp.remote_sas_address_hi = upper_32_bits(sas_addr); + rnc->ssp.remote_sas_address_lo = lower_32_bits(sas_addr); + + rnc->ssp.nexus_loss_timer_enable = true; + rnc->ssp.check_bit = false; + rnc->ssp.is_valid = false; + rnc->ssp.is_remote_node_context = true; + rnc->ssp.function_number = 0; + + rnc->ssp.arbitration_wait_time = 0; + + if (dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) { + rnc->ssp.connection_occupancy_timeout = + ihost->user_parameters.stp_max_occupancy_timeout; + rnc->ssp.connection_inactivity_timeout = + ihost->user_parameters.stp_inactivity_timeout; + } else { + rnc->ssp.connection_occupancy_timeout = + ihost->user_parameters.ssp_max_occupancy_timeout; + rnc->ssp.connection_inactivity_timeout = + ihost->user_parameters.ssp_inactivity_timeout; + } + + rnc->ssp.initial_arbitration_wait_time = 0; + + /* Open Address Frame Parameters */ + rnc->ssp.oaf_connection_rate = idev->connection_rate; + rnc->ssp.oaf_features = 0; + rnc->ssp.oaf_source_zone_group = 0; + rnc->ssp.oaf_more_compatibility_features = 0; +} + +/** + * + * @sci_rnc: + * @callback: + * @callback_parameter: + * + * This method will setup the remote node context object so it will transition + * to its ready state. If the remote node context is already setup to + * transition to its final state then this function does nothing. none + */ +static void sci_remote_node_context_setup_to_resume( + struct sci_remote_node_context *sci_rnc, + scics_sds_remote_node_context_callback callback, + void *callback_parameter) +{ + if (sci_rnc->destination_state != SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_FINAL) { + sci_rnc->destination_state = SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_READY; + sci_rnc->user_callback = callback; + sci_rnc->user_cookie = callback_parameter; + } +} + +static void sci_remote_node_context_setup_to_destory( + struct sci_remote_node_context *sci_rnc, + scics_sds_remote_node_context_callback callback, + void *callback_parameter) +{ + sci_rnc->destination_state = SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_FINAL; + sci_rnc->user_callback = callback; + sci_rnc->user_cookie = callback_parameter; +} + +/** + * + * + * This method just calls the user callback function and then resets the + * callback. + */ +static void sci_remote_node_context_notify_user( + struct sci_remote_node_context *rnc) +{ + if (rnc->user_callback != NULL) { + (*rnc->user_callback)(rnc->user_cookie); + + rnc->user_callback = NULL; + rnc->user_cookie = NULL; + } +} + +static void sci_remote_node_context_continue_state_transitions(struct sci_remote_node_context *rnc) +{ + if (rnc->destination_state == SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_READY) + sci_remote_node_context_resume(rnc, rnc->user_callback, + rnc->user_cookie); +} + +static void sci_remote_node_context_validate_context_buffer(struct sci_remote_node_context *sci_rnc) +{ + union scu_remote_node_context *rnc_buffer; + struct isci_remote_device *idev = rnc_to_dev(sci_rnc); + struct domain_device *dev = idev->domain_dev; + struct isci_host *ihost = idev->owning_port->owning_controller; + + rnc_buffer = sci_rnc_by_id(ihost, sci_rnc->remote_node_index); + + rnc_buffer->ssp.is_valid = true; + + if (!idev->is_direct_attached && + (dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP))) { + sci_remote_device_post_request(idev, SCU_CONTEXT_COMMAND_POST_RNC_96); + } else { + sci_remote_device_post_request(idev, SCU_CONTEXT_COMMAND_POST_RNC_32); + + if (idev->is_direct_attached) + sci_port_setup_transports(idev->owning_port, + sci_rnc->remote_node_index); + } +} + +static void sci_remote_node_context_invalidate_context_buffer(struct sci_remote_node_context *sci_rnc) +{ + union scu_remote_node_context *rnc_buffer; + struct isci_remote_device *idev = rnc_to_dev(sci_rnc); + struct isci_host *ihost = idev->owning_port->owning_controller; + + rnc_buffer = sci_rnc_by_id(ihost, sci_rnc->remote_node_index); + + rnc_buffer->ssp.is_valid = false; + + sci_remote_device_post_request(rnc_to_dev(sci_rnc), + SCU_CONTEXT_COMMAND_POST_RNC_INVALIDATE); +} + +static void sci_remote_node_context_initial_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *rnc = container_of(sm, typeof(*rnc), sm); + + /* Check to see if we have gotten back to the initial state because + * someone requested to destroy the remote node context object. + */ + if (sm->previous_state_id == SCI_RNC_INVALIDATING) { + rnc->destination_state = SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_UNSPECIFIED; + sci_remote_node_context_notify_user(rnc); + } +} + +static void sci_remote_node_context_posting_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *sci_rnc = container_of(sm, typeof(*sci_rnc), sm); + + sci_remote_node_context_validate_context_buffer(sci_rnc); +} + +static void sci_remote_node_context_invalidating_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *rnc = container_of(sm, typeof(*rnc), sm); + + sci_remote_node_context_invalidate_context_buffer(rnc); +} + +static void sci_remote_node_context_resuming_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *rnc = container_of(sm, typeof(*rnc), sm); + struct isci_remote_device *idev; + struct domain_device *dev; + + idev = rnc_to_dev(rnc); + dev = idev->domain_dev; + + /* + * For direct attached SATA devices we need to clear the TLCR + * NCQ to TCi tag mapping on the phy and in cases where we + * resume because of a target reset we also need to update + * the STPTLDARNI register with the RNi of the device + */ + if ((dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) && + idev->is_direct_attached) + sci_port_setup_transports(idev->owning_port, + rnc->remote_node_index); + + sci_remote_device_post_request(idev, SCU_CONTEXT_COMMAND_POST_RNC_RESUME); +} + +static void sci_remote_node_context_ready_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *rnc = container_of(sm, typeof(*rnc), sm); + + rnc->destination_state = SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_UNSPECIFIED; + + if (rnc->user_callback) + sci_remote_node_context_notify_user(rnc); +} + +static void sci_remote_node_context_tx_suspended_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *rnc = container_of(sm, typeof(*rnc), sm); + + sci_remote_node_context_continue_state_transitions(rnc); +} + +static void sci_remote_node_context_tx_rx_suspended_state_enter(struct sci_base_state_machine *sm) +{ + struct sci_remote_node_context *rnc = container_of(sm, typeof(*rnc), sm); + + sci_remote_node_context_continue_state_transitions(rnc); +} + +static const struct sci_base_state sci_remote_node_context_state_table[] = { + [SCI_RNC_INITIAL] = { + .enter_state = sci_remote_node_context_initial_state_enter, + }, + [SCI_RNC_POSTING] = { + .enter_state = sci_remote_node_context_posting_state_enter, + }, + [SCI_RNC_INVALIDATING] = { + .enter_state = sci_remote_node_context_invalidating_state_enter, + }, + [SCI_RNC_RESUMING] = { + .enter_state = sci_remote_node_context_resuming_state_enter, + }, + [SCI_RNC_READY] = { + .enter_state = sci_remote_node_context_ready_state_enter, + }, + [SCI_RNC_TX_SUSPENDED] = { + .enter_state = sci_remote_node_context_tx_suspended_state_enter, + }, + [SCI_RNC_TX_RX_SUSPENDED] = { + .enter_state = sci_remote_node_context_tx_rx_suspended_state_enter, + }, + [SCI_RNC_AWAIT_SUSPENSION] = { }, +}; + +void sci_remote_node_context_construct(struct sci_remote_node_context *rnc, + u16 remote_node_index) +{ + memset(rnc, 0, sizeof(struct sci_remote_node_context)); + + rnc->remote_node_index = remote_node_index; + rnc->destination_state = SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_UNSPECIFIED; + + sci_init_sm(&rnc->sm, sci_remote_node_context_state_table, SCI_RNC_INITIAL); +} + +enum sci_status sci_remote_node_context_event_handler(struct sci_remote_node_context *sci_rnc, + u32 event_code) +{ + enum scis_sds_remote_node_context_states state; + + state = sci_rnc->sm.current_state_id; + switch (state) { + case SCI_RNC_POSTING: + switch (scu_get_event_code(event_code)) { + case SCU_EVENT_POST_RNC_COMPLETE: + sci_change_state(&sci_rnc->sm, SCI_RNC_READY); + break; + default: + goto out; + } + break; + case SCI_RNC_INVALIDATING: + if (scu_get_event_code(event_code) == SCU_EVENT_POST_RNC_INVALIDATE_COMPLETE) { + if (sci_rnc->destination_state == SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_FINAL) + state = SCI_RNC_INITIAL; + else + state = SCI_RNC_POSTING; + sci_change_state(&sci_rnc->sm, state); + } else { + switch (scu_get_event_type(event_code)) { + case SCU_EVENT_TYPE_RNC_SUSPEND_TX: + case SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX: + /* We really dont care if the hardware is going to suspend + * the device since it's being invalidated anyway */ + dev_dbg(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: SCIC Remote Node Context 0x%p was " + "suspeneded by hardware while being " + "invalidated.\n", __func__, sci_rnc); + break; + default: + goto out; + } + } + break; + case SCI_RNC_RESUMING: + if (scu_get_event_code(event_code) == SCU_EVENT_POST_RCN_RELEASE) { + sci_change_state(&sci_rnc->sm, SCI_RNC_READY); + } else { + switch (scu_get_event_type(event_code)) { + case SCU_EVENT_TYPE_RNC_SUSPEND_TX: + case SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX: + /* We really dont care if the hardware is going to suspend + * the device since it's being resumed anyway */ + dev_dbg(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: SCIC Remote Node Context 0x%p was " + "suspeneded by hardware while being resumed.\n", + __func__, sci_rnc); + break; + default: + goto out; + } + } + break; + case SCI_RNC_READY: + switch (scu_get_event_type(event_code)) { + case SCU_EVENT_TL_RNC_SUSPEND_TX: + sci_change_state(&sci_rnc->sm, SCI_RNC_TX_SUSPENDED); + sci_rnc->suspension_code = scu_get_event_specifier(event_code); + break; + case SCU_EVENT_TL_RNC_SUSPEND_TX_RX: + sci_change_state(&sci_rnc->sm, SCI_RNC_TX_RX_SUSPENDED); + sci_rnc->suspension_code = scu_get_event_specifier(event_code); + break; + default: + goto out; + } + break; + case SCI_RNC_AWAIT_SUSPENSION: + switch (scu_get_event_type(event_code)) { + case SCU_EVENT_TL_RNC_SUSPEND_TX: + sci_change_state(&sci_rnc->sm, SCI_RNC_TX_SUSPENDED); + sci_rnc->suspension_code = scu_get_event_specifier(event_code); + break; + case SCU_EVENT_TL_RNC_SUSPEND_TX_RX: + sci_change_state(&sci_rnc->sm, SCI_RNC_TX_RX_SUSPENDED); + sci_rnc->suspension_code = scu_get_event_specifier(event_code); + break; + default: + goto out; + } + break; + default: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + return SCI_SUCCESS; + + out: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: code: %#x state: %d\n", __func__, event_code, state); + return SCI_FAILURE; + +} + +enum sci_status sci_remote_node_context_destruct(struct sci_remote_node_context *sci_rnc, + scics_sds_remote_node_context_callback cb_fn, + void *cb_p) +{ + enum scis_sds_remote_node_context_states state; + + state = sci_rnc->sm.current_state_id; + switch (state) { + case SCI_RNC_INVALIDATING: + sci_remote_node_context_setup_to_destory(sci_rnc, cb_fn, cb_p); + return SCI_SUCCESS; + case SCI_RNC_POSTING: + case SCI_RNC_RESUMING: + case SCI_RNC_READY: + case SCI_RNC_TX_SUSPENDED: + case SCI_RNC_TX_RX_SUSPENDED: + case SCI_RNC_AWAIT_SUSPENSION: + sci_remote_node_context_setup_to_destory(sci_rnc, cb_fn, cb_p); + sci_change_state(&sci_rnc->sm, SCI_RNC_INVALIDATING); + return SCI_SUCCESS; + case SCI_RNC_INITIAL: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + /* We have decided that the destruct request on the remote node context + * can not fail since it is either in the initial/destroyed state or is + * can be destroyed. + */ + return SCI_SUCCESS; + default: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_remote_node_context_suspend(struct sci_remote_node_context *sci_rnc, + u32 suspend_type, + scics_sds_remote_node_context_callback cb_fn, + void *cb_p) +{ + enum scis_sds_remote_node_context_states state; + + state = sci_rnc->sm.current_state_id; + if (state != SCI_RNC_READY) { + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + sci_rnc->user_callback = cb_fn; + sci_rnc->user_cookie = cb_p; + sci_rnc->suspension_code = suspend_type; + + if (suspend_type == SCI_SOFTWARE_SUSPENSION) { + sci_remote_device_post_request(rnc_to_dev(sci_rnc), + SCU_CONTEXT_COMMAND_POST_RNC_SUSPEND_TX); + } + + sci_change_state(&sci_rnc->sm, SCI_RNC_AWAIT_SUSPENSION); + return SCI_SUCCESS; +} + +enum sci_status sci_remote_node_context_resume(struct sci_remote_node_context *sci_rnc, + scics_sds_remote_node_context_callback cb_fn, + void *cb_p) +{ + enum scis_sds_remote_node_context_states state; + + state = sci_rnc->sm.current_state_id; + switch (state) { + case SCI_RNC_INITIAL: + if (sci_rnc->remote_node_index == SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX) + return SCI_FAILURE_INVALID_STATE; + + sci_remote_node_context_setup_to_resume(sci_rnc, cb_fn, cb_p); + sci_remote_node_context_construct_buffer(sci_rnc); + sci_change_state(&sci_rnc->sm, SCI_RNC_POSTING); + return SCI_SUCCESS; + case SCI_RNC_POSTING: + case SCI_RNC_INVALIDATING: + case SCI_RNC_RESUMING: + if (sci_rnc->destination_state != SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_READY) + return SCI_FAILURE_INVALID_STATE; + + sci_rnc->user_callback = cb_fn; + sci_rnc->user_cookie = cb_p; + return SCI_SUCCESS; + case SCI_RNC_TX_SUSPENDED: { + struct isci_remote_device *idev = rnc_to_dev(sci_rnc); + struct domain_device *dev = idev->domain_dev; + + sci_remote_node_context_setup_to_resume(sci_rnc, cb_fn, cb_p); + + /* TODO: consider adding a resume action of NONE, INVALIDATE, WRITE_TLCR */ + if (dev->dev_type == SAS_END_DEV || dev_is_expander(dev)) + sci_change_state(&sci_rnc->sm, SCI_RNC_RESUMING); + else if (dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) { + if (idev->is_direct_attached) { + /* @todo Fix this since I am being silly in writing to the STPTLDARNI register. */ + sci_change_state(&sci_rnc->sm, SCI_RNC_RESUMING); + } else { + sci_change_state(&sci_rnc->sm, SCI_RNC_INVALIDATING); + } + } else + return SCI_FAILURE; + return SCI_SUCCESS; + } + case SCI_RNC_TX_RX_SUSPENDED: + sci_remote_node_context_setup_to_resume(sci_rnc, cb_fn, cb_p); + sci_change_state(&sci_rnc->sm, SCI_RNC_RESUMING); + return SCI_FAILURE_INVALID_STATE; + case SCI_RNC_AWAIT_SUSPENSION: + sci_remote_node_context_setup_to_resume(sci_rnc, cb_fn, cb_p); + return SCI_SUCCESS; + default: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} + +enum sci_status sci_remote_node_context_start_io(struct sci_remote_node_context *sci_rnc, + struct isci_request *ireq) +{ + enum scis_sds_remote_node_context_states state; + + state = sci_rnc->sm.current_state_id; + + switch (state) { + case SCI_RNC_READY: + return SCI_SUCCESS; + case SCI_RNC_TX_SUSPENDED: + case SCI_RNC_TX_RX_SUSPENDED: + case SCI_RNC_AWAIT_SUSPENSION: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + return SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED; + default: + break; + } + dev_dbg(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: requested to start IO while still resuming, %d\n", + __func__, state); + return SCI_FAILURE_INVALID_STATE; +} + +enum sci_status sci_remote_node_context_start_task(struct sci_remote_node_context *sci_rnc, + struct isci_request *ireq) +{ + enum scis_sds_remote_node_context_states state; + + state = sci_rnc->sm.current_state_id; + switch (state) { + case SCI_RNC_RESUMING: + case SCI_RNC_READY: + case SCI_RNC_AWAIT_SUSPENSION: + return SCI_SUCCESS; + case SCI_RNC_TX_SUSPENDED: + case SCI_RNC_TX_RX_SUSPENDED: + sci_remote_node_context_resume(sci_rnc, NULL, NULL); + return SCI_SUCCESS; + default: + dev_warn(scirdev_to_dev(rnc_to_dev(sci_rnc)), + "%s: invalid state %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } +} diff --git a/drivers/scsi/isci/remote_node_context.h b/drivers/scsi/isci/remote_node_context.h new file mode 100644 index 0000000..41580ad --- /dev/null +++ b/drivers/scsi/isci/remote_node_context.h @@ -0,0 +1,224 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCIC_SDS_REMOTE_NODE_CONTEXT_H_ +#define _SCIC_SDS_REMOTE_NODE_CONTEXT_H_ + +/** + * This file contains the structures, constants, and prototypes associated with + * the remote node context in the silicon. It exists to model and manage + * the remote node context in the silicon. + * + * + */ + +#include "isci.h" + +/** + * + * + * This constant represents an invalid remote device id, it is used to program + * the STPDARNI register so the driver knows when it has received a SIGNATURE + * FIS from the SCU. + */ +#define SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX 0x0FFF + +#define SCU_HARDWARE_SUSPENSION (0) +#define SCI_SOFTWARE_SUSPENSION (1) + +struct isci_request; +struct isci_remote_device; +struct sci_remote_node_context; + +typedef void (*scics_sds_remote_node_context_callback)(void *); + +/** + * This is the enumeration of the remote node context states. + */ +enum scis_sds_remote_node_context_states { + /** + * This state is the initial state for a remote node context. On a resume + * request the remote node context will transition to the posting state. + */ + SCI_RNC_INITIAL, + + /** + * This is a transition state that posts the RNi to the hardware. Once the RNC + * is posted the remote node context will be made ready. + */ + SCI_RNC_POSTING, + + /** + * This is a transition state that will post an RNC invalidate to the + * hardware. Once the invalidate is complete the remote node context will + * transition to the posting state. + */ + SCI_RNC_INVALIDATING, + + /** + * This is a transition state that will post an RNC resume to the hardare. + * Once the event notification of resume complete is received the remote node + * context will transition to the ready state. + */ + SCI_RNC_RESUMING, + + /** + * This is the state that the remote node context must be in to accept io + * request operations. + */ + SCI_RNC_READY, + + /** + * This is the state that the remote node context transitions to when it gets + * a TX suspend notification from the hardware. + */ + SCI_RNC_TX_SUSPENDED, + + /** + * This is the state that the remote node context transitions to when it gets + * a TX RX suspend notification from the hardware. + */ + SCI_RNC_TX_RX_SUSPENDED, + + /** + * This state is a wait state for the remote node context that waits for a + * suspend notification from the hardware. This state is entered when either + * there is a request to supend the remote node context or when there is a TC + * completion where the remote node will be suspended by the hardware. + */ + SCI_RNC_AWAIT_SUSPENSION +}; + +/** + * + * + * This enumeration is used to define the end destination state for the remote + * node context. + */ +enum sci_remote_node_context_destination_state { + SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_UNSPECIFIED, + SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_READY, + SCIC_SDS_REMOTE_NODE_DESTINATION_STATE_FINAL +}; + +/** + * struct sci_remote_node_context - This structure contains the data + * associated with the remote node context object. The remote node context + * (RNC) object models the the remote device information necessary to manage + * the silicon RNC. + */ +struct sci_remote_node_context { + /** + * This field indicates the remote node index (RNI) associated with + * this RNC. + */ + u16 remote_node_index; + + /** + * This field is the recored suspension code or the reason for the remote node + * context suspension. + */ + u32 suspension_code; + + /** + * This field is true if the remote node context is resuming from its current + * state. This can cause an automatic resume on receiving a suspension + * notification. + */ + enum sci_remote_node_context_destination_state destination_state; + + /** + * This field contains the callback function that the user requested to be + * called when the requested state transition is complete. + */ + scics_sds_remote_node_context_callback user_callback; + + /** + * This field contains the parameter that is called when the user requested + * state transition is completed. + */ + void *user_cookie; + + /** + * This field contains the data for the object's state machine. + */ + struct sci_base_state_machine sm; +}; + +void sci_remote_node_context_construct(struct sci_remote_node_context *rnc, + u16 remote_node_index); + + +bool sci_remote_node_context_is_ready( + struct sci_remote_node_context *sci_rnc); + +enum sci_status sci_remote_node_context_event_handler(struct sci_remote_node_context *sci_rnc, + u32 event_code); +enum sci_status sci_remote_node_context_destruct(struct sci_remote_node_context *sci_rnc, + scics_sds_remote_node_context_callback callback, + void *callback_parameter); +enum sci_status sci_remote_node_context_suspend(struct sci_remote_node_context *sci_rnc, + u32 suspend_type, + scics_sds_remote_node_context_callback cb_fn, + void *cb_p); +enum sci_status sci_remote_node_context_resume(struct sci_remote_node_context *sci_rnc, + scics_sds_remote_node_context_callback cb_fn, + void *cb_p); +enum sci_status sci_remote_node_context_start_task(struct sci_remote_node_context *sci_rnc, + struct isci_request *ireq); +enum sci_status sci_remote_node_context_start_io(struct sci_remote_node_context *sci_rnc, + struct isci_request *ireq); + +#endif /* _SCIC_SDS_REMOTE_NODE_CONTEXT_H_ */ diff --git a/drivers/scsi/isci/remote_node_table.c b/drivers/scsi/isci/remote_node_table.c new file mode 100644 index 0000000..301b314 --- /dev/null +++ b/drivers/scsi/isci/remote_node_table.c @@ -0,0 +1,598 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/** + * This file contains the implementation of the SCIC_SDS_REMOTE_NODE_TABLE + * public, protected, and private methods. + * + * + */ +#include "remote_node_table.h" +#include "remote_node_context.h" + +/** + * + * @remote_node_table: This is the remote node index table from which the + * selection will be made. + * @group_table_index: This is the index to the group table from which to + * search for an available selection. + * + * This routine will find the bit position in absolute bit terms of the next 32 + * + bit position. If there are available bits in the first u32 then it is + * just bit position. u32 This is the absolute bit position for an available + * group. + */ +static u32 sci_remote_node_table_get_group_index( + struct sci_remote_node_table *remote_node_table, + u32 group_table_index) +{ + u32 dword_index; + u32 *group_table; + u32 bit_index; + + group_table = remote_node_table->remote_node_groups[group_table_index]; + + for (dword_index = 0; dword_index < remote_node_table->group_array_size; dword_index++) { + if (group_table[dword_index] != 0) { + for (bit_index = 0; bit_index < 32; bit_index++) { + if ((group_table[dword_index] & (1 << bit_index)) != 0) { + return (dword_index * 32) + bit_index; + } + } + } + } + + return SCIC_SDS_REMOTE_NODE_TABLE_INVALID_INDEX; +} + +/** + * + * @out]: remote_node_table This the remote node table in which to clear the + * selector. + * @set_index: This is the remote node selector in which the change will be + * made. + * @group_index: This is the bit index in the table to be modified. + * + * This method will clear the group index entry in the specified group index + * table. none + */ +static void sci_remote_node_table_clear_group_index( + struct sci_remote_node_table *remote_node_table, + u32 group_table_index, + u32 group_index) +{ + u32 dword_index; + u32 bit_index; + u32 *group_table; + + BUG_ON(group_table_index >= SCU_STP_REMOTE_NODE_COUNT); + BUG_ON(group_index >= (u32)(remote_node_table->group_array_size * 32)); + + dword_index = group_index / 32; + bit_index = group_index % 32; + group_table = remote_node_table->remote_node_groups[group_table_index]; + + group_table[dword_index] = group_table[dword_index] & ~(1 << bit_index); +} + +/** + * + * @out]: remote_node_table This the remote node table in which to set the + * selector. + * @group_table_index: This is the remote node selector in which the change + * will be made. + * @group_index: This is the bit position in the table to be modified. + * + * This method will set the group index bit entry in the specified gropu index + * table. none + */ +static void sci_remote_node_table_set_group_index( + struct sci_remote_node_table *remote_node_table, + u32 group_table_index, + u32 group_index) +{ + u32 dword_index; + u32 bit_index; + u32 *group_table; + + BUG_ON(group_table_index >= SCU_STP_REMOTE_NODE_COUNT); + BUG_ON(group_index >= (u32)(remote_node_table->group_array_size * 32)); + + dword_index = group_index / 32; + bit_index = group_index % 32; + group_table = remote_node_table->remote_node_groups[group_table_index]; + + group_table[dword_index] = group_table[dword_index] | (1 << bit_index); +} + +/** + * + * @out]: remote_node_table This is the remote node table in which to modify + * the remote node availability. + * @remote_node_index: This is the remote node index that is being returned to + * the table. + * + * This method will set the remote to available in the remote node allocation + * table. none + */ +static void sci_remote_node_table_set_node_index( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_index) +{ + u32 dword_location; + u32 dword_remainder; + u32 slot_normalized; + u32 slot_position; + + BUG_ON( + (remote_node_table->available_nodes_array_size * SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD) + <= (remote_node_index / SCU_STP_REMOTE_NODE_COUNT) + ); + + dword_location = remote_node_index / SCIC_SDS_REMOTE_NODES_PER_DWORD; + dword_remainder = remote_node_index % SCIC_SDS_REMOTE_NODES_PER_DWORD; + slot_normalized = (dword_remainder / SCU_STP_REMOTE_NODE_COUNT) * sizeof(u32); + slot_position = remote_node_index % SCU_STP_REMOTE_NODE_COUNT; + + remote_node_table->available_remote_nodes[dword_location] |= + 1 << (slot_normalized + slot_position); +} + +/** + * + * @out]: remote_node_table This is the remote node table from which to clear + * the available remote node bit. + * @remote_node_index: This is the remote node index which is to be cleared + * from the table. + * + * This method clears the remote node index from the table of available remote + * nodes. none + */ +static void sci_remote_node_table_clear_node_index( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_index) +{ + u32 dword_location; + u32 dword_remainder; + u32 slot_position; + u32 slot_normalized; + + BUG_ON( + (remote_node_table->available_nodes_array_size * SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD) + <= (remote_node_index / SCU_STP_REMOTE_NODE_COUNT) + ); + + dword_location = remote_node_index / SCIC_SDS_REMOTE_NODES_PER_DWORD; + dword_remainder = remote_node_index % SCIC_SDS_REMOTE_NODES_PER_DWORD; + slot_normalized = (dword_remainder / SCU_STP_REMOTE_NODE_COUNT) * sizeof(u32); + slot_position = remote_node_index % SCU_STP_REMOTE_NODE_COUNT; + + remote_node_table->available_remote_nodes[dword_location] &= + ~(1 << (slot_normalized + slot_position)); +} + +/** + * + * @out]: remote_node_table The remote node table from which the slot will be + * cleared. + * @group_index: The index for the slot that is to be cleared. + * + * This method clears the entire table slot at the specified slot index. none + */ +static void sci_remote_node_table_clear_group( + struct sci_remote_node_table *remote_node_table, + u32 group_index) +{ + u32 dword_location; + u32 dword_remainder; + u32 dword_value; + + BUG_ON( + (remote_node_table->available_nodes_array_size * SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD) + <= (group_index / SCU_STP_REMOTE_NODE_COUNT) + ); + + dword_location = group_index / SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD; + dword_remainder = group_index % SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD; + + dword_value = remote_node_table->available_remote_nodes[dword_location]; + dword_value &= ~(SCIC_SDS_REMOTE_NODE_TABLE_FULL_SLOT_VALUE << (dword_remainder * 4)); + remote_node_table->available_remote_nodes[dword_location] = dword_value; +} + +/** + * + * @remote_node_table: + * + * THis method sets an entire remote node group in the remote node table. + */ +static void sci_remote_node_table_set_group( + struct sci_remote_node_table *remote_node_table, + u32 group_index) +{ + u32 dword_location; + u32 dword_remainder; + u32 dword_value; + + BUG_ON( + (remote_node_table->available_nodes_array_size * SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD) + <= (group_index / SCU_STP_REMOTE_NODE_COUNT) + ); + + dword_location = group_index / SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD; + dword_remainder = group_index % SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD; + + dword_value = remote_node_table->available_remote_nodes[dword_location]; + dword_value |= (SCIC_SDS_REMOTE_NODE_TABLE_FULL_SLOT_VALUE << (dword_remainder * 4)); + remote_node_table->available_remote_nodes[dword_location] = dword_value; +} + +/** + * + * @remote_node_table: This is the remote node table that for which the group + * value is to be returned. + * @group_index: This is the group index to use to find the group value. + * + * This method will return the group value for the specified group index. The + * bit values at the specified remote node group index. + */ +static u8 sci_remote_node_table_get_group_value( + struct sci_remote_node_table *remote_node_table, + u32 group_index) +{ + u32 dword_location; + u32 dword_remainder; + u32 dword_value; + + dword_location = group_index / SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD; + dword_remainder = group_index % SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD; + + dword_value = remote_node_table->available_remote_nodes[dword_location]; + dword_value &= (SCIC_SDS_REMOTE_NODE_TABLE_FULL_SLOT_VALUE << (dword_remainder * 4)); + dword_value = dword_value >> (dword_remainder * 4); + + return (u8)dword_value; +} + +/** + * + * @out]: remote_node_table The remote that which is to be initialized. + * @remote_node_entries: The number of entries to put in the table. + * + * This method will initialize the remote node table for use. none + */ +void sci_remote_node_table_initialize( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_entries) +{ + u32 index; + + /* + * Initialize the raw data we could improve the speed by only initializing + * those entries that we are actually going to be used */ + memset( + remote_node_table->available_remote_nodes, + 0x00, + sizeof(remote_node_table->available_remote_nodes) + ); + + memset( + remote_node_table->remote_node_groups, + 0x00, + sizeof(remote_node_table->remote_node_groups) + ); + + /* Initialize the available remote node sets */ + remote_node_table->available_nodes_array_size = (u16) + (remote_node_entries / SCIC_SDS_REMOTE_NODES_PER_DWORD) + + ((remote_node_entries % SCIC_SDS_REMOTE_NODES_PER_DWORD) != 0); + + + /* Initialize each full DWORD to a FULL SET of remote nodes */ + for (index = 0; index < remote_node_entries; index++) { + sci_remote_node_table_set_node_index(remote_node_table, index); + } + + remote_node_table->group_array_size = (u16) + (remote_node_entries / (SCU_STP_REMOTE_NODE_COUNT * 32)) + + ((remote_node_entries % (SCU_STP_REMOTE_NODE_COUNT * 32)) != 0); + + for (index = 0; index < (remote_node_entries / SCU_STP_REMOTE_NODE_COUNT); index++) { + /* + * These are all guaranteed to be full slot values so fill them in the + * available sets of 3 remote nodes */ + sci_remote_node_table_set_group_index(remote_node_table, 2, index); + } + + /* Now fill in any remainders that we may find */ + if ((remote_node_entries % SCU_STP_REMOTE_NODE_COUNT) == 2) { + sci_remote_node_table_set_group_index(remote_node_table, 1, index); + } else if ((remote_node_entries % SCU_STP_REMOTE_NODE_COUNT) == 1) { + sci_remote_node_table_set_group_index(remote_node_table, 0, index); + } +} + +/** + * + * @out]: remote_node_table The remote node table from which to allocate a + * remote node. + * @table_index: The group index that is to be used for the search. + * + * This method will allocate a single RNi from the remote node table. The + * table index will determine from which remote node group table to search. + * This search may fail and another group node table can be specified. The + * function is designed to allow a serach of the available single remote node + * group up to the triple remote node group. If an entry is found in the + * specified table the remote node is removed and the remote node groups are + * updated. The RNi value or an invalid remote node context if an RNi can not + * be found. + */ +static u16 sci_remote_node_table_allocate_single_remote_node( + struct sci_remote_node_table *remote_node_table, + u32 group_table_index) +{ + u8 index; + u8 group_value; + u32 group_index; + u16 remote_node_index = SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX; + + group_index = sci_remote_node_table_get_group_index( + remote_node_table, group_table_index); + + /* We could not find an available slot in the table selector 0 */ + if (group_index != SCIC_SDS_REMOTE_NODE_TABLE_INVALID_INDEX) { + group_value = sci_remote_node_table_get_group_value( + remote_node_table, group_index); + + for (index = 0; index < SCU_STP_REMOTE_NODE_COUNT; index++) { + if (((1 << index) & group_value) != 0) { + /* We have selected a bit now clear it */ + remote_node_index = (u16)(group_index * SCU_STP_REMOTE_NODE_COUNT + + index); + + sci_remote_node_table_clear_group_index( + remote_node_table, group_table_index, group_index + ); + + sci_remote_node_table_clear_node_index( + remote_node_table, remote_node_index + ); + + if (group_table_index > 0) { + sci_remote_node_table_set_group_index( + remote_node_table, group_table_index - 1, group_index + ); + } + + break; + } + } + } + + return remote_node_index; +} + +/** + * + * @remote_node_table: This is the remote node table from which to allocate the + * remote node entries. + * @group_table_index: THis is the group table index which must equal two (2) + * for this operation. + * + * This method will allocate three consecutive remote node context entries. If + * there are no remaining triple entries the function will return a failure. + * The remote node index that represents three consecutive remote node entries + * or an invalid remote node context if none can be found. + */ +static u16 sci_remote_node_table_allocate_triple_remote_node( + struct sci_remote_node_table *remote_node_table, + u32 group_table_index) +{ + u32 group_index; + u16 remote_node_index = SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX; + + group_index = sci_remote_node_table_get_group_index( + remote_node_table, group_table_index); + + if (group_index != SCIC_SDS_REMOTE_NODE_TABLE_INVALID_INDEX) { + remote_node_index = (u16)group_index * SCU_STP_REMOTE_NODE_COUNT; + + sci_remote_node_table_clear_group_index( + remote_node_table, group_table_index, group_index + ); + + sci_remote_node_table_clear_group( + remote_node_table, group_index + ); + } + + return remote_node_index; +} + +/** + * + * @remote_node_table: This is the remote node table from which the remote node + * allocation is to take place. + * @remote_node_count: This is ther remote node count which is one of + * SCU_SSP_REMOTE_NODE_COUNT(1) or SCU_STP_REMOTE_NODE_COUNT(3). + * + * This method will allocate a remote node that mataches the remote node count + * specified by the caller. Valid values for remote node count is + * SCU_SSP_REMOTE_NODE_COUNT(1) or SCU_STP_REMOTE_NODE_COUNT(3). u16 This is + * the remote node index that is returned or an invalid remote node context. + */ +u16 sci_remote_node_table_allocate_remote_node( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_count) +{ + u16 remote_node_index = SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX; + + if (remote_node_count == SCU_SSP_REMOTE_NODE_COUNT) { + remote_node_index = + sci_remote_node_table_allocate_single_remote_node( + remote_node_table, 0); + + if (remote_node_index == SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX) { + remote_node_index = + sci_remote_node_table_allocate_single_remote_node( + remote_node_table, 1); + } + + if (remote_node_index == SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX) { + remote_node_index = + sci_remote_node_table_allocate_single_remote_node( + remote_node_table, 2); + } + } else if (remote_node_count == SCU_STP_REMOTE_NODE_COUNT) { + remote_node_index = + sci_remote_node_table_allocate_triple_remote_node( + remote_node_table, 2); + } + + return remote_node_index; +} + +/** + * + * @remote_node_table: + * + * This method will free a single remote node index back to the remote node + * table. This routine will update the remote node groups + */ +static void sci_remote_node_table_release_single_remote_node( + struct sci_remote_node_table *remote_node_table, + u16 remote_node_index) +{ + u32 group_index; + u8 group_value; + + group_index = remote_node_index / SCU_STP_REMOTE_NODE_COUNT; + + group_value = sci_remote_node_table_get_group_value(remote_node_table, group_index); + + /* + * Assert that we are not trying to add an entry to a slot that is already + * full. */ + BUG_ON(group_value == SCIC_SDS_REMOTE_NODE_TABLE_FULL_SLOT_VALUE); + + if (group_value == 0x00) { + /* + * There are no entries in this slot so it must be added to the single + * slot table. */ + sci_remote_node_table_set_group_index(remote_node_table, 0, group_index); + } else if ((group_value & (group_value - 1)) == 0) { + /* + * There is only one entry in this slot so it must be moved from the + * single slot table to the dual slot table */ + sci_remote_node_table_clear_group_index(remote_node_table, 0, group_index); + sci_remote_node_table_set_group_index(remote_node_table, 1, group_index); + } else { + /* + * There are two entries in the slot so it must be moved from the dual + * slot table to the tripple slot table. */ + sci_remote_node_table_clear_group_index(remote_node_table, 1, group_index); + sci_remote_node_table_set_group_index(remote_node_table, 2, group_index); + } + + sci_remote_node_table_set_node_index(remote_node_table, remote_node_index); +} + +/** + * + * @remote_node_table: This is the remote node table to which the remote node + * index is to be freed. + * + * This method will release a group of three consecutive remote nodes back to + * the free remote nodes. + */ +static void sci_remote_node_table_release_triple_remote_node( + struct sci_remote_node_table *remote_node_table, + u16 remote_node_index) +{ + u32 group_index; + + group_index = remote_node_index / SCU_STP_REMOTE_NODE_COUNT; + + sci_remote_node_table_set_group_index( + remote_node_table, 2, group_index + ); + + sci_remote_node_table_set_group(remote_node_table, group_index); +} + +/** + * + * @remote_node_table: The remote node table to which the remote node index is + * to be freed. + * @remote_node_count: This is the count of consecutive remote nodes that are + * to be freed. + * + * This method will release the remote node index back into the remote node + * table free pool. + */ +void sci_remote_node_table_release_remote_node_index( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_count, + u16 remote_node_index) +{ + if (remote_node_count == SCU_SSP_REMOTE_NODE_COUNT) { + sci_remote_node_table_release_single_remote_node( + remote_node_table, remote_node_index); + } else if (remote_node_count == SCU_STP_REMOTE_NODE_COUNT) { + sci_remote_node_table_release_triple_remote_node( + remote_node_table, remote_node_index); + } +} + diff --git a/drivers/scsi/isci/remote_node_table.h b/drivers/scsi/isci/remote_node_table.h new file mode 100644 index 0000000..721ab98 --- /dev/null +++ b/drivers/scsi/isci/remote_node_table.h @@ -0,0 +1,188 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCIC_SDS_REMOTE_NODE_TABLE_H_ +#define _SCIC_SDS_REMOTE_NODE_TABLE_H_ + +#include "isci.h" + +/** + * + * + * Remote node sets are sets of remote node index in the remtoe node table The + * SCU hardware requires that STP remote node entries take three consecutive + * remote node index so the table is arranged in sets of three. The bits are + * used as 0111 0111 to make a byte and the bits define the set of three remote + * nodes to use as a sequence. + */ +#define SCIC_SDS_REMOTE_NODE_SETS_PER_BYTE 2 + +/** + * + * + * Since the remote node table is organized as DWORDS take the remote node sets + * in bytes and represent them in DWORDs. The lowest ordered bits are the ones + * used in case full DWORD is not being used. i.e. 0000 0000 0000 0000 0111 + * 0111 0111 0111 // if only a single WORD is in use in the DWORD. + */ +#define SCIC_SDS_REMOTE_NODE_SETS_PER_DWORD \ + (sizeof(u32) * SCIC_SDS_REMOTE_NODE_SETS_PER_BYTE) +/** + * + * + * This is a count of the numeber of remote nodes that can be represented in a + * byte + */ +#define SCIC_SDS_REMOTE_NODES_PER_BYTE \ + (SCU_STP_REMOTE_NODE_COUNT * SCIC_SDS_REMOTE_NODE_SETS_PER_BYTE) + +/** + * + * + * This is a count of the number of remote nodes that can be represented in a + * DWROD + */ +#define SCIC_SDS_REMOTE_NODES_PER_DWORD \ + (sizeof(u32) * SCIC_SDS_REMOTE_NODES_PER_BYTE) + +/** + * + * + * This is the number of bits in a remote node group + */ +#define SCIC_SDS_REMOTE_NODES_BITS_PER_GROUP 4 + +#define SCIC_SDS_REMOTE_NODE_TABLE_INVALID_INDEX (0xFFFFFFFF) +#define SCIC_SDS_REMOTE_NODE_TABLE_FULL_SLOT_VALUE (0x07) +#define SCIC_SDS_REMOTE_NODE_TABLE_EMPTY_SLOT_VALUE (0x00) + +/** + * + * + * Expander attached sata remote node count + */ +#define SCU_STP_REMOTE_NODE_COUNT 3 + +/** + * + * + * Expander or direct attached ssp remote node count + */ +#define SCU_SSP_REMOTE_NODE_COUNT 1 + +/** + * + * + * Direct attached STP remote node count + */ +#define SCU_SATA_REMOTE_NODE_COUNT 1 + +/** + * struct sci_remote_node_table - + * + * + */ +struct sci_remote_node_table { + /** + * This field contains the array size in dwords + */ + u16 available_nodes_array_size; + + /** + * This field contains the array size of the + */ + u16 group_array_size; + + /** + * This field is the array of available remote node entries in bits. + * Because of the way STP remote node data is allocated on the SCU hardware + * the remote nodes must occupy three consecutive remote node context + * entries. For ease of allocation and de-allocation we have broken the + * sets of three into a single nibble. When the STP RNi is allocated all + * of the bits in the nibble are cleared. This math results in a table size + * of MAX_REMOTE_NODES / CONSECUTIVE RNi ENTRIES for STP / 2 entries per byte. + */ + u32 available_remote_nodes[ + (SCI_MAX_REMOTE_DEVICES / SCIC_SDS_REMOTE_NODES_PER_DWORD) + + ((SCI_MAX_REMOTE_DEVICES % SCIC_SDS_REMOTE_NODES_PER_DWORD) != 0)]; + + /** + * This field is the nibble selector for the above table. There are three + * possible selectors each for fast lookup when trying to find one, two or + * three remote node entries. + */ + u32 remote_node_groups[ + SCU_STP_REMOTE_NODE_COUNT][ + (SCI_MAX_REMOTE_DEVICES / (32 * SCU_STP_REMOTE_NODE_COUNT)) + + ((SCI_MAX_REMOTE_DEVICES % (32 * SCU_STP_REMOTE_NODE_COUNT)) != 0)]; + +}; + +/* --------------------------------------------------------------------------- */ + +void sci_remote_node_table_initialize( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_entries); + +u16 sci_remote_node_table_allocate_remote_node( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_count); + +void sci_remote_node_table_release_remote_node_index( + struct sci_remote_node_table *remote_node_table, + u32 remote_node_count, + u16 remote_node_index); + +#endif /* _SCIC_SDS_REMOTE_NODE_TABLE_H_ */ diff --git a/drivers/scsi/isci/request.c b/drivers/scsi/isci/request.c new file mode 100644 index 0000000..a46e07a --- /dev/null +++ b/drivers/scsi/isci/request.c @@ -0,0 +1,3391 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "isci.h" +#include "task.h" +#include "request.h" +#include "scu_completion_codes.h" +#include "scu_event_codes.h" +#include "sas.h" + +static struct scu_sgl_element_pair *to_sgl_element_pair(struct isci_request *ireq, + int idx) +{ + if (idx == 0) + return &ireq->tc->sgl_pair_ab; + else if (idx == 1) + return &ireq->tc->sgl_pair_cd; + else if (idx < 0) + return NULL; + else + return &ireq->sg_table[idx - 2]; +} + +static dma_addr_t to_sgl_element_pair_dma(struct isci_host *ihost, + struct isci_request *ireq, u32 idx) +{ + u32 offset; + + if (idx == 0) { + offset = (void *) &ireq->tc->sgl_pair_ab - + (void *) &ihost->task_context_table[0]; + return ihost->task_context_dma + offset; + } else if (idx == 1) { + offset = (void *) &ireq->tc->sgl_pair_cd - + (void *) &ihost->task_context_table[0]; + return ihost->task_context_dma + offset; + } + + return sci_io_request_get_dma_addr(ireq, &ireq->sg_table[idx - 2]); +} + +static void init_sgl_element(struct scu_sgl_element *e, struct scatterlist *sg) +{ + e->length = sg_dma_len(sg); + e->address_upper = upper_32_bits(sg_dma_address(sg)); + e->address_lower = lower_32_bits(sg_dma_address(sg)); + e->address_modifier = 0; +} + +static void sci_request_build_sgl(struct isci_request *ireq) +{ + struct isci_host *ihost = ireq->isci_host; + struct sas_task *task = isci_request_access_task(ireq); + struct scatterlist *sg = NULL; + dma_addr_t dma_addr; + u32 sg_idx = 0; + struct scu_sgl_element_pair *scu_sg = NULL; + struct scu_sgl_element_pair *prev_sg = NULL; + + if (task->num_scatter > 0) { + sg = task->scatter; + + while (sg) { + scu_sg = to_sgl_element_pair(ireq, sg_idx); + init_sgl_element(&scu_sg->A, sg); + sg = sg_next(sg); + if (sg) { + init_sgl_element(&scu_sg->B, sg); + sg = sg_next(sg); + } else + memset(&scu_sg->B, 0, sizeof(scu_sg->B)); + + if (prev_sg) { + dma_addr = to_sgl_element_pair_dma(ihost, + ireq, + sg_idx); + + prev_sg->next_pair_upper = + upper_32_bits(dma_addr); + prev_sg->next_pair_lower = + lower_32_bits(dma_addr); + } + + prev_sg = scu_sg; + sg_idx++; + } + } else { /* handle when no sg */ + scu_sg = to_sgl_element_pair(ireq, sg_idx); + + dma_addr = dma_map_single(&ihost->pdev->dev, + task->scatter, + task->total_xfer_len, + task->data_dir); + + ireq->zero_scatter_daddr = dma_addr; + + scu_sg->A.length = task->total_xfer_len; + scu_sg->A.address_upper = upper_32_bits(dma_addr); + scu_sg->A.address_lower = lower_32_bits(dma_addr); + } + + if (scu_sg) { + scu_sg->next_pair_upper = 0; + scu_sg->next_pair_lower = 0; + } +} + +static void sci_io_request_build_ssp_command_iu(struct isci_request *ireq) +{ + struct ssp_cmd_iu *cmd_iu; + struct sas_task *task = isci_request_access_task(ireq); + + cmd_iu = &ireq->ssp.cmd; + + memcpy(cmd_iu->LUN, task->ssp_task.LUN, 8); + cmd_iu->add_cdb_len = 0; + cmd_iu->_r_a = 0; + cmd_iu->_r_b = 0; + cmd_iu->en_fburst = 0; /* unsupported */ + cmd_iu->task_prio = task->ssp_task.task_prio; + cmd_iu->task_attr = task->ssp_task.task_attr; + cmd_iu->_r_c = 0; + + sci_swab32_cpy(&cmd_iu->cdb, task->ssp_task.cdb, + sizeof(task->ssp_task.cdb) / sizeof(u32)); +} + +static void sci_task_request_build_ssp_task_iu(struct isci_request *ireq) +{ + struct ssp_task_iu *task_iu; + struct sas_task *task = isci_request_access_task(ireq); + struct isci_tmf *isci_tmf = isci_request_access_tmf(ireq); + + task_iu = &ireq->ssp.tmf; + + memset(task_iu, 0, sizeof(struct ssp_task_iu)); + + memcpy(task_iu->LUN, task->ssp_task.LUN, 8); + + task_iu->task_func = isci_tmf->tmf_code; + task_iu->task_tag = + (ireq->ttype == tmf_task) ? + isci_tmf->io_tag : + SCI_CONTROLLER_INVALID_IO_TAG; +} + +/** + * This method is will fill in the SCU Task Context for any type of SSP request. + * @sci_req: + * @task_context: + * + */ +static void scu_ssp_reqeust_construct_task_context( + struct isci_request *ireq, + struct scu_task_context *task_context) +{ + dma_addr_t dma_addr; + struct isci_remote_device *idev; + struct isci_port *iport; + + idev = ireq->target_device; + iport = idev->owning_port; + + /* Fill in the TC with the its required data */ + task_context->abort = 0; + task_context->priority = 0; + task_context->initiator_request = 1; + task_context->connection_rate = idev->connection_rate; + task_context->protocol_engine_index = ISCI_PEG; + task_context->logical_port_index = iport->physical_port_index; + task_context->protocol_type = SCU_TASK_CONTEXT_PROTOCOL_SSP; + task_context->valid = SCU_TASK_CONTEXT_VALID; + task_context->context_type = SCU_TASK_CONTEXT_TYPE; + + task_context->remote_node_index = idev->rnc.remote_node_index; + task_context->command_code = 0; + + task_context->link_layer_control = 0; + task_context->do_not_dma_ssp_good_response = 1; + task_context->strict_ordering = 0; + task_context->control_frame = 0; + task_context->timeout_enable = 0; + task_context->block_guard_enable = 0; + + task_context->address_modifier = 0; + + /* task_context->type.ssp.tag = ireq->io_tag; */ + task_context->task_phase = 0x01; + + ireq->post_context = (SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC | + (ISCI_PEG << SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_SHIFT) | + (iport->physical_port_index << + SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT) | + ISCI_TAG_TCI(ireq->io_tag)); + + /* + * Copy the physical address for the command buffer to the + * SCU Task Context + */ + dma_addr = sci_io_request_get_dma_addr(ireq, &ireq->ssp.cmd); + + task_context->command_iu_upper = upper_32_bits(dma_addr); + task_context->command_iu_lower = lower_32_bits(dma_addr); + + /* + * Copy the physical address for the response buffer to the + * SCU Task Context + */ + dma_addr = sci_io_request_get_dma_addr(ireq, &ireq->ssp.rsp); + + task_context->response_iu_upper = upper_32_bits(dma_addr); + task_context->response_iu_lower = lower_32_bits(dma_addr); +} + +/** + * This method is will fill in the SCU Task Context for a SSP IO request. + * @sci_req: + * + */ +static void scu_ssp_io_request_construct_task_context(struct isci_request *ireq, + enum dma_data_direction dir, + u32 len) +{ + struct scu_task_context *task_context = ireq->tc; + + scu_ssp_reqeust_construct_task_context(ireq, task_context); + + task_context->ssp_command_iu_length = + sizeof(struct ssp_cmd_iu) / sizeof(u32); + task_context->type.ssp.frame_type = SSP_COMMAND; + + switch (dir) { + case DMA_FROM_DEVICE: + case DMA_NONE: + default: + task_context->task_type = SCU_TASK_TYPE_IOREAD; + break; + case DMA_TO_DEVICE: + task_context->task_type = SCU_TASK_TYPE_IOWRITE; + break; + } + + task_context->transfer_length_bytes = len; + + if (task_context->transfer_length_bytes > 0) + sci_request_build_sgl(ireq); +} + +/** + * This method will fill in the SCU Task Context for a SSP Task request. The + * following important settings are utilized: -# priority == + * SCU_TASK_PRIORITY_HIGH. This ensures that the task request is issued + * ahead of other task destined for the same Remote Node. -# task_type == + * SCU_TASK_TYPE_IOREAD. This simply indicates that a normal request type + * (i.e. non-raw frame) is being utilized to perform task management. -# + * control_frame == 1. This ensures that the proper endianess is set so + * that the bytes are transmitted in the right order for a task frame. + * @sci_req: This parameter specifies the task request object being + * constructed. + * + */ +static void scu_ssp_task_request_construct_task_context(struct isci_request *ireq) +{ + struct scu_task_context *task_context = ireq->tc; + + scu_ssp_reqeust_construct_task_context(ireq, task_context); + + task_context->control_frame = 1; + task_context->priority = SCU_TASK_PRIORITY_HIGH; + task_context->task_type = SCU_TASK_TYPE_RAW_FRAME; + task_context->transfer_length_bytes = 0; + task_context->type.ssp.frame_type = SSP_TASK; + task_context->ssp_command_iu_length = + sizeof(struct ssp_task_iu) / sizeof(u32); +} + +/** + * This method is will fill in the SCU Task Context for any type of SATA + * request. This is called from the various SATA constructors. + * @sci_req: The general IO request object which is to be used in + * constructing the SCU task context. + * @task_context: The buffer pointer for the SCU task context which is being + * constructed. + * + * The general io request construction is complete. The buffer assignment for + * the command buffer is complete. none Revisit task context construction to + * determine what is common for SSP/SMP/STP task context structures. + */ +static void scu_sata_reqeust_construct_task_context( + struct isci_request *ireq, + struct scu_task_context *task_context) +{ + dma_addr_t dma_addr; + struct isci_remote_device *idev; + struct isci_port *iport; + + idev = ireq->target_device; + iport = idev->owning_port; + + /* Fill in the TC with the its required data */ + task_context->abort = 0; + task_context->priority = SCU_TASK_PRIORITY_NORMAL; + task_context->initiator_request = 1; + task_context->connection_rate = idev->connection_rate; + task_context->protocol_engine_index = ISCI_PEG; + task_context->logical_port_index = iport->physical_port_index; + task_context->protocol_type = SCU_TASK_CONTEXT_PROTOCOL_STP; + task_context->valid = SCU_TASK_CONTEXT_VALID; + task_context->context_type = SCU_TASK_CONTEXT_TYPE; + + task_context->remote_node_index = idev->rnc.remote_node_index; + task_context->command_code = 0; + + task_context->link_layer_control = 0; + task_context->do_not_dma_ssp_good_response = 1; + task_context->strict_ordering = 0; + task_context->control_frame = 0; + task_context->timeout_enable = 0; + task_context->block_guard_enable = 0; + + task_context->address_modifier = 0; + task_context->task_phase = 0x01; + + task_context->ssp_command_iu_length = + (sizeof(struct host_to_dev_fis) - sizeof(u32)) / sizeof(u32); + + /* Set the first word of the H2D REG FIS */ + task_context->type.words[0] = *(u32 *)&ireq->stp.cmd; + + ireq->post_context = (SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC | + (ISCI_PEG << SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_SHIFT) | + (iport->physical_port_index << + SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT) | + ISCI_TAG_TCI(ireq->io_tag)); + /* + * Copy the physical address for the command buffer to the SCU Task + * Context. We must offset the command buffer by 4 bytes because the + * first 4 bytes are transfered in the body of the TC. + */ + dma_addr = sci_io_request_get_dma_addr(ireq, + ((char *) &ireq->stp.cmd) + + sizeof(u32)); + + task_context->command_iu_upper = upper_32_bits(dma_addr); + task_context->command_iu_lower = lower_32_bits(dma_addr); + + /* SATA Requests do not have a response buffer */ + task_context->response_iu_upper = 0; + task_context->response_iu_lower = 0; +} + +static void scu_stp_raw_request_construct_task_context(struct isci_request *ireq) +{ + struct scu_task_context *task_context = ireq->tc; + + scu_sata_reqeust_construct_task_context(ireq, task_context); + + task_context->control_frame = 0; + task_context->priority = SCU_TASK_PRIORITY_NORMAL; + task_context->task_type = SCU_TASK_TYPE_SATA_RAW_FRAME; + task_context->type.stp.fis_type = FIS_REGH2D; + task_context->transfer_length_bytes = sizeof(struct host_to_dev_fis) - sizeof(u32); +} + +static enum sci_status sci_stp_pio_request_construct(struct isci_request *ireq, + bool copy_rx_frame) +{ + struct isci_stp_request *stp_req = &ireq->stp.req; + + scu_stp_raw_request_construct_task_context(ireq); + + stp_req->status = 0; + stp_req->sgl.offset = 0; + stp_req->sgl.set = SCU_SGL_ELEMENT_PAIR_A; + + if (copy_rx_frame) { + sci_request_build_sgl(ireq); + stp_req->sgl.index = 0; + } else { + /* The user does not want the data copied to the SGL buffer location */ + stp_req->sgl.index = -1; + } + + return SCI_SUCCESS; +} + +/** + * + * @sci_req: This parameter specifies the request to be constructed as an + * optimized request. + * @optimized_task_type: This parameter specifies whether the request is to be + * an UDMA request or a NCQ request. - A value of 0 indicates UDMA. - A + * value of 1 indicates NCQ. + * + * This method will perform request construction common to all types of STP + * requests that are optimized by the silicon (i.e. UDMA, NCQ). This method + * returns an indication as to whether the construction was successful. + */ +static void sci_stp_optimized_request_construct(struct isci_request *ireq, + u8 optimized_task_type, + u32 len, + enum dma_data_direction dir) +{ + struct scu_task_context *task_context = ireq->tc; + + /* Build the STP task context structure */ + scu_sata_reqeust_construct_task_context(ireq, task_context); + + /* Copy over the SGL elements */ + sci_request_build_sgl(ireq); + + /* Copy over the number of bytes to be transfered */ + task_context->transfer_length_bytes = len; + + if (dir == DMA_TO_DEVICE) { + /* + * The difference between the DMA IN and DMA OUT request task type + * values are consistent with the difference between FPDMA READ + * and FPDMA WRITE values. Add the supplied task type parameter + * to this difference to set the task type properly for this + * DATA OUT (WRITE) case. */ + task_context->task_type = optimized_task_type + (SCU_TASK_TYPE_DMA_OUT + - SCU_TASK_TYPE_DMA_IN); + } else { + /* + * For the DATA IN (READ) case, simply save the supplied + * optimized task type. */ + task_context->task_type = optimized_task_type; + } +} + + + +static enum sci_status +sci_io_request_construct_sata(struct isci_request *ireq, + u32 len, + enum dma_data_direction dir, + bool copy) +{ + enum sci_status status = SCI_SUCCESS; + struct sas_task *task = isci_request_access_task(ireq); + + /* check for management protocols */ + if (ireq->ttype == tmf_task) { + struct isci_tmf *tmf = isci_request_access_tmf(ireq); + + if (tmf->tmf_code == isci_tmf_sata_srst_high || + tmf->tmf_code == isci_tmf_sata_srst_low) { + scu_stp_raw_request_construct_task_context(ireq); + return SCI_SUCCESS; + } else { + dev_err(&ireq->owning_controller->pdev->dev, + "%s: Request 0x%p received un-handled SAT " + "management protocol 0x%x.\n", + __func__, ireq, tmf->tmf_code); + + return SCI_FAILURE; + } + } + + if (!sas_protocol_ata(task->task_proto)) { + dev_err(&ireq->owning_controller->pdev->dev, + "%s: Non-ATA protocol in SATA path: 0x%x\n", + __func__, + task->task_proto); + return SCI_FAILURE; + + } + + /* non data */ + if (task->data_dir == DMA_NONE) { + scu_stp_raw_request_construct_task_context(ireq); + return SCI_SUCCESS; + } + + /* NCQ */ + if (task->ata_task.use_ncq) { + sci_stp_optimized_request_construct(ireq, + SCU_TASK_TYPE_FPDMAQ_READ, + len, dir); + return SCI_SUCCESS; + } + + /* DMA */ + if (task->ata_task.dma_xfer) { + sci_stp_optimized_request_construct(ireq, + SCU_TASK_TYPE_DMA_IN, + len, dir); + return SCI_SUCCESS; + } else /* PIO */ + return sci_stp_pio_request_construct(ireq, copy); + + return status; +} + +static enum sci_status sci_io_request_construct_basic_ssp(struct isci_request *ireq) +{ + struct sas_task *task = isci_request_access_task(ireq); + + ireq->protocol = SCIC_SSP_PROTOCOL; + + scu_ssp_io_request_construct_task_context(ireq, + task->data_dir, + task->total_xfer_len); + + sci_io_request_build_ssp_command_iu(ireq); + + sci_change_state(&ireq->sm, SCI_REQ_CONSTRUCTED); + + return SCI_SUCCESS; +} + +enum sci_status sci_task_request_construct_ssp( + struct isci_request *ireq) +{ + /* Construct the SSP Task SCU Task Context */ + scu_ssp_task_request_construct_task_context(ireq); + + /* Fill in the SSP Task IU */ + sci_task_request_build_ssp_task_iu(ireq); + + sci_change_state(&ireq->sm, SCI_REQ_CONSTRUCTED); + + return SCI_SUCCESS; +} + +static enum sci_status sci_io_request_construct_basic_sata(struct isci_request *ireq) +{ + enum sci_status status; + bool copy = false; + struct sas_task *task = isci_request_access_task(ireq); + + ireq->protocol = SCIC_STP_PROTOCOL; + + copy = (task->data_dir == DMA_NONE) ? false : true; + + status = sci_io_request_construct_sata(ireq, + task->total_xfer_len, + task->data_dir, + copy); + + if (status == SCI_SUCCESS) + sci_change_state(&ireq->sm, SCI_REQ_CONSTRUCTED); + + return status; +} + +enum sci_status sci_task_request_construct_sata(struct isci_request *ireq) +{ + enum sci_status status = SCI_SUCCESS; + + /* check for management protocols */ + if (ireq->ttype == tmf_task) { + struct isci_tmf *tmf = isci_request_access_tmf(ireq); + + if (tmf->tmf_code == isci_tmf_sata_srst_high || + tmf->tmf_code == isci_tmf_sata_srst_low) { + scu_stp_raw_request_construct_task_context(ireq); + } else { + dev_err(&ireq->owning_controller->pdev->dev, + "%s: Request 0x%p received un-handled SAT " + "Protocol 0x%x.\n", + __func__, ireq, tmf->tmf_code); + + return SCI_FAILURE; + } + } + + if (status != SCI_SUCCESS) + return status; + sci_change_state(&ireq->sm, SCI_REQ_CONSTRUCTED); + + return status; +} + +/** + * sci_req_tx_bytes - bytes transferred when reply underruns request + * @sci_req: request that was terminated early + */ +#define SCU_TASK_CONTEXT_SRAM 0x200000 +static u32 sci_req_tx_bytes(struct isci_request *ireq) +{ + struct isci_host *ihost = ireq->owning_controller; + u32 ret_val = 0; + + if (readl(&ihost->smu_registers->address_modifier) == 0) { + void __iomem *scu_reg_base = ihost->scu_registers; + + /* get the bytes of data from the Address == BAR1 + 20002Ch + (256*TCi) where + * BAR1 is the scu_registers + * 0x20002C = 0x200000 + 0x2c + * = start of task context SRAM + offset of (type.ssp.data_offset) + * TCi is the io_tag of struct sci_request + */ + ret_val = readl(scu_reg_base + + (SCU_TASK_CONTEXT_SRAM + offsetof(struct scu_task_context, type.ssp.data_offset)) + + ((sizeof(struct scu_task_context)) * ISCI_TAG_TCI(ireq->io_tag))); + } + + return ret_val; +} + +enum sci_status sci_request_start(struct isci_request *ireq) +{ + enum sci_base_request_states state; + struct scu_task_context *tc = ireq->tc; + struct isci_host *ihost = ireq->owning_controller; + + state = ireq->sm.current_state_id; + if (state != SCI_REQ_CONSTRUCTED) { + dev_warn(&ihost->pdev->dev, + "%s: SCIC IO Request requested to start while in wrong " + "state %d\n", __func__, state); + return SCI_FAILURE_INVALID_STATE; + } + + tc->task_index = ISCI_TAG_TCI(ireq->io_tag); + + switch (tc->protocol_type) { + case SCU_TASK_CONTEXT_PROTOCOL_SMP: + case SCU_TASK_CONTEXT_PROTOCOL_SSP: + /* SSP/SMP Frame */ + tc->type.ssp.tag = ireq->io_tag; + tc->type.ssp.target_port_transfer_tag = 0xFFFF; + break; + + case SCU_TASK_CONTEXT_PROTOCOL_STP: + /* STP/SATA Frame + * tc->type.stp.ncq_tag = ireq->ncq_tag; + */ + break; + + case SCU_TASK_CONTEXT_PROTOCOL_NONE: + /* / @todo When do we set no protocol type? */ + break; + + default: + /* This should never happen since we build the IO + * requests */ + break; + } + + /* Add to the post_context the io tag value */ + ireq->post_context |= ISCI_TAG_TCI(ireq->io_tag); + + /* Everything is good go ahead and change state */ + sci_change_state(&ireq->sm, SCI_REQ_STARTED); + + return SCI_SUCCESS; +} + +enum sci_status +sci_io_request_terminate(struct isci_request *ireq) +{ + enum sci_base_request_states state; + + state = ireq->sm.current_state_id; + + switch (state) { + case SCI_REQ_CONSTRUCTED: + ireq->scu_status = SCU_TASK_DONE_TASK_ABORT; + ireq->sci_status = SCI_FAILURE_IO_TERMINATED; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + return SCI_SUCCESS; + case SCI_REQ_STARTED: + case SCI_REQ_TASK_WAIT_TC_COMP: + case SCI_REQ_SMP_WAIT_RESP: + case SCI_REQ_SMP_WAIT_TC_COMP: + case SCI_REQ_STP_UDMA_WAIT_TC_COMP: + case SCI_REQ_STP_UDMA_WAIT_D2H: + case SCI_REQ_STP_NON_DATA_WAIT_H2D: + case SCI_REQ_STP_NON_DATA_WAIT_D2H: + case SCI_REQ_STP_PIO_WAIT_H2D: + case SCI_REQ_STP_PIO_WAIT_FRAME: + case SCI_REQ_STP_PIO_DATA_IN: + case SCI_REQ_STP_PIO_DATA_OUT: + case SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED: + case SCI_REQ_STP_SOFT_RESET_WAIT_H2D_DIAG: + case SCI_REQ_STP_SOFT_RESET_WAIT_D2H: + sci_change_state(&ireq->sm, SCI_REQ_ABORTING); + return SCI_SUCCESS; + case SCI_REQ_TASK_WAIT_TC_RESP: + sci_change_state(&ireq->sm, SCI_REQ_ABORTING); + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + return SCI_SUCCESS; + case SCI_REQ_ABORTING: + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + return SCI_SUCCESS; + case SCI_REQ_COMPLETED: + default: + dev_warn(&ireq->owning_controller->pdev->dev, + "%s: SCIC IO Request requested to abort while in wrong " + "state %d\n", + __func__, + ireq->sm.current_state_id); + break; + } + + return SCI_FAILURE_INVALID_STATE; +} + +enum sci_status sci_request_complete(struct isci_request *ireq) +{ + enum sci_base_request_states state; + struct isci_host *ihost = ireq->owning_controller; + + state = ireq->sm.current_state_id; + if (WARN_ONCE(state != SCI_REQ_COMPLETED, + "isci: request completion from wrong state (%d)\n", state)) + return SCI_FAILURE_INVALID_STATE; + + if (ireq->saved_rx_frame_index != SCU_INVALID_FRAME_INDEX) + sci_controller_release_frame(ihost, + ireq->saved_rx_frame_index); + + /* XXX can we just stop the machine and remove the 'final' state? */ + sci_change_state(&ireq->sm, SCI_REQ_FINAL); + return SCI_SUCCESS; +} + +enum sci_status sci_io_request_event_handler(struct isci_request *ireq, + u32 event_code) +{ + enum sci_base_request_states state; + struct isci_host *ihost = ireq->owning_controller; + + state = ireq->sm.current_state_id; + + if (state != SCI_REQ_STP_PIO_DATA_IN) { + dev_warn(&ihost->pdev->dev, "%s: (%x) in wrong state %d\n", + __func__, event_code, state); + + return SCI_FAILURE_INVALID_STATE; + } + + switch (scu_get_event_specifier(event_code)) { + case SCU_TASK_DONE_CRC_ERR << SCU_EVENT_SPECIFIC_CODE_SHIFT: + /* We are waiting for data and the SCU has R_ERR the data frame. + * Go back to waiting for the D2H Register FIS + */ + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_WAIT_FRAME); + return SCI_SUCCESS; + default: + dev_err(&ihost->pdev->dev, + "%s: pio request unexpected event %#x\n", + __func__, event_code); + + /* TODO Should we fail the PIO request when we get an + * unexpected event? + */ + return SCI_FAILURE; + } +} + +/* + * This function copies response data for requests returning response data + * instead of sense data. + * @sci_req: This parameter specifies the request object for which to copy + * the response data. + */ +static void sci_io_request_copy_response(struct isci_request *ireq) +{ + void *resp_buf; + u32 len; + struct ssp_response_iu *ssp_response; + struct isci_tmf *isci_tmf = isci_request_access_tmf(ireq); + + ssp_response = &ireq->ssp.rsp; + + resp_buf = &isci_tmf->resp.resp_iu; + + len = min_t(u32, + SSP_RESP_IU_MAX_SIZE, + be32_to_cpu(ssp_response->response_data_len)); + + memcpy(resp_buf, ssp_response->resp_data, len); +} + +static enum sci_status +request_started_state_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + struct ssp_response_iu *resp_iu; + u8 datapres; + + /* TODO: Any SDMA return code of other than 0 is bad decode 0x003C0000 + * to determine SDMA status + */ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + break; + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_EARLY_RESP): { + /* There are times when the SCU hardware will return an early + * response because the io request specified more data than is + * returned by the target device (mode pages, inquiry data, + * etc.). We must check the response stats to see if this is + * truly a failed request or a good request that just got + * completed early. + */ + struct ssp_response_iu *resp = &ireq->ssp.rsp; + ssize_t word_cnt = SSP_RESP_IU_MAX_SIZE / sizeof(u32); + + sci_swab32_cpy(&ireq->ssp.rsp, + &ireq->ssp.rsp, + word_cnt); + + if (resp->status == 0) { + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS_IO_DONE_EARLY; + } else { + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + } + break; + } + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_CHECK_RESPONSE): { + ssize_t word_cnt = SSP_RESP_IU_MAX_SIZE / sizeof(u32); + + sci_swab32_cpy(&ireq->ssp.rsp, + &ireq->ssp.rsp, + word_cnt); + + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + break; + } + + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_RESP_LEN_ERR): + /* TODO With TASK_DONE_RESP_LEN_ERR is the response frame + * guaranteed to be received before this completion status is + * posted? + */ + resp_iu = &ireq->ssp.rsp; + datapres = resp_iu->datapres; + + if (datapres == 1 || datapres == 2) { + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + } else { + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + } + break; + /* only stp device gets suspended. */ + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_ACK_NAK_TO): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_LL_PERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_NAK_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_DATA_LEN_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_LL_ABORT_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_XR_WD_LEN): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_MAX_PLD_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_UNEXP_RESP): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_UNEXP_SDBFIS): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_REG_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SDB_ERR): + if (ireq->protocol == SCIC_STP_PROTOCOL) { + ireq->scu_status = SCU_GET_COMPLETION_TL_STATUS(completion_code) >> + SCU_COMPLETION_TL_STATUS_SHIFT; + ireq->sci_status = SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED; + } else { + ireq->scu_status = SCU_GET_COMPLETION_TL_STATUS(completion_code) >> + SCU_COMPLETION_TL_STATUS_SHIFT; + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + } + break; + + /* both stp/ssp device gets suspended */ + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_LF_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_WRONG_DESTINATION): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_1): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_2): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_3): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_BAD_DESTINATION): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_ZONE_VIOLATION): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_STP_RESOURCES_BUSY): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_PROTOCOL_NOT_SUPPORTED): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_OPEN_REJECT_CONNECTION_RATE_NOT_SUPPORTED): + ireq->scu_status = SCU_GET_COMPLETION_TL_STATUS(completion_code) >> + SCU_COMPLETION_TL_STATUS_SHIFT; + ireq->sci_status = SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED; + break; + + /* neither ssp nor stp gets suspended. */ + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_NAK_CMD_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_UNEXP_XR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_XR_IU_LEN_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SDMA_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_OFFSET_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_EXCESS_DATA): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_RESP_TO_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_UFI_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_FRM_TYPE_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_LL_RX_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_UNEXP_DATA): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_OPEN_FAIL): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_VIIT_ENTRY_NV): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_IIT_ENTRY_NV): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_RNCNV_OUTBOUND): + default: + ireq->scu_status = SCU_GET_COMPLETION_TL_STATUS(completion_code) >> + SCU_COMPLETION_TL_STATUS_SHIFT; + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + break; + } + + /* + * TODO: This is probably wrong for ACK/NAK timeout conditions + */ + + /* In all cases we will treat this as the completion of the IO req. */ + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + return SCI_SUCCESS; +} + +static enum sci_status +request_aborting_state_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case (SCU_TASK_DONE_GOOD << SCU_COMPLETION_TL_STATUS_SHIFT): + case (SCU_TASK_DONE_TASK_ABORT << SCU_COMPLETION_TL_STATUS_SHIFT): + ireq->scu_status = SCU_TASK_DONE_TASK_ABORT; + ireq->sci_status = SCI_FAILURE_IO_TERMINATED; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + + default: + /* Unless we get some strange error wait for the task abort to complete + * TODO: Should there be a state change for this completion? + */ + break; + } + + return SCI_SUCCESS; +} + +static enum sci_status ssp_task_request_await_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_TASK_WAIT_TC_RESP); + break; + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_ACK_NAK_TO): + /* Currently, the decision is to simply allow the task request + * to timeout if the task IU wasn't received successfully. + * There is a potential for receiving multiple task responses if + * we decide to send the task IU again. + */ + dev_warn(&ireq->owning_controller->pdev->dev, + "%s: TaskRequest:0x%p CompletionCode:%x - " + "ACK/NAK timeout\n", __func__, ireq, + completion_code); + + sci_change_state(&ireq->sm, SCI_REQ_TASK_WAIT_TC_RESP); + break; + default: + /* + * All other completion status cause the IO to be complete. + * If a NAK was received, then it is up to the user to retry + * the request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return SCI_SUCCESS; +} + +static enum sci_status +smp_request_await_response_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + /* In the AWAIT RESPONSE state, any TC completion is + * unexpected. but if the TC has success status, we + * complete the IO anyway. + */ + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_RESP_TO_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_UFI_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_FRM_TYPE_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_SMP_LL_RX_ERR): + /* These status has been seen in a specific LSI + * expander, which sometimes is not able to send smp + * response within 2 ms. This causes our hardware break + * the connection and set TC completion with one of + * these SMP_XXX_XX_ERR status. For these type of error, + * we ask ihost user to retry the request. + */ + ireq->scu_status = SCU_TASK_DONE_SMP_RESP_TO_ERR; + ireq->sci_status = SCI_FAILURE_RETRY_REQUIRED; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + default: + /* All other completion status cause the IO to be complete. If a NAK + * was received, then it is up to the user to retry the request + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return SCI_SUCCESS; +} + +static enum sci_status +smp_request_await_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + default: + /* All other completion status cause the IO to be + * complete. If a NAK was received, then it is up to + * the user to retry the request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return SCI_SUCCESS; +} + +static struct scu_sgl_element *pio_sgl_next(struct isci_stp_request *stp_req) +{ + struct scu_sgl_element *sgl; + struct scu_sgl_element_pair *sgl_pair; + struct isci_request *ireq = to_ireq(stp_req); + struct isci_stp_pio_sgl *pio_sgl = &stp_req->sgl; + + sgl_pair = to_sgl_element_pair(ireq, pio_sgl->index); + if (!sgl_pair) + sgl = NULL; + else if (pio_sgl->set == SCU_SGL_ELEMENT_PAIR_A) { + if (sgl_pair->B.address_lower == 0 && + sgl_pair->B.address_upper == 0) { + sgl = NULL; + } else { + pio_sgl->set = SCU_SGL_ELEMENT_PAIR_B; + sgl = &sgl_pair->B; + } + } else { + if (sgl_pair->next_pair_lower == 0 && + sgl_pair->next_pair_upper == 0) { + sgl = NULL; + } else { + pio_sgl->index++; + pio_sgl->set = SCU_SGL_ELEMENT_PAIR_A; + sgl_pair = to_sgl_element_pair(ireq, pio_sgl->index); + sgl = &sgl_pair->A; + } + } + + return sgl; +} + +static enum sci_status +stp_request_non_data_await_h2d_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_STP_NON_DATA_WAIT_D2H); + break; + + default: + /* All other completion status cause the IO to be + * complete. If a NAK was received, then it is up to + * the user to retry the request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return SCI_SUCCESS; +} + +#define SCU_MAX_FRAME_BUFFER_SIZE 0x400 /* 1K is the maximum SCU frame data payload */ + +/* transmit DATA_FIS from (current sgl + offset) for input + * parameter length. current sgl and offset is alreay stored in the IO request + */ +static enum sci_status sci_stp_request_pio_data_out_trasmit_data_frame( + struct isci_request *ireq, + u32 length) +{ + struct isci_stp_request *stp_req = &ireq->stp.req; + struct scu_task_context *task_context = ireq->tc; + struct scu_sgl_element_pair *sgl_pair; + struct scu_sgl_element *current_sgl; + + /* Recycle the TC and reconstruct it for sending out DATA FIS containing + * for the data from current_sgl+offset for the input length + */ + sgl_pair = to_sgl_element_pair(ireq, stp_req->sgl.index); + if (stp_req->sgl.set == SCU_SGL_ELEMENT_PAIR_A) + current_sgl = &sgl_pair->A; + else + current_sgl = &sgl_pair->B; + + /* update the TC */ + task_context->command_iu_upper = current_sgl->address_upper; + task_context->command_iu_lower = current_sgl->address_lower; + task_context->transfer_length_bytes = length; + task_context->type.stp.fis_type = FIS_DATA; + + /* send the new TC out. */ + return sci_controller_continue_io(ireq); +} + +static enum sci_status sci_stp_request_pio_data_out_transmit_data(struct isci_request *ireq) +{ + struct isci_stp_request *stp_req = &ireq->stp.req; + struct scu_sgl_element_pair *sgl_pair; + struct scu_sgl_element *sgl; + enum sci_status status; + u32 offset; + u32 len = 0; + + offset = stp_req->sgl.offset; + sgl_pair = to_sgl_element_pair(ireq, stp_req->sgl.index); + if (WARN_ONCE(!sgl_pair, "%s: null sgl element", __func__)) + return SCI_FAILURE; + + if (stp_req->sgl.set == SCU_SGL_ELEMENT_PAIR_A) { + sgl = &sgl_pair->A; + len = sgl_pair->A.length - offset; + } else { + sgl = &sgl_pair->B; + len = sgl_pair->B.length - offset; + } + + if (stp_req->pio_len == 0) + return SCI_SUCCESS; + + if (stp_req->pio_len >= len) { + status = sci_stp_request_pio_data_out_trasmit_data_frame(ireq, len); + if (status != SCI_SUCCESS) + return status; + stp_req->pio_len -= len; + + /* update the current sgl, offset and save for future */ + sgl = pio_sgl_next(stp_req); + offset = 0; + } else if (stp_req->pio_len < len) { + sci_stp_request_pio_data_out_trasmit_data_frame(ireq, stp_req->pio_len); + + /* Sgl offset will be adjusted and saved for future */ + offset += stp_req->pio_len; + sgl->address_lower += stp_req->pio_len; + stp_req->pio_len = 0; + } + + stp_req->sgl.offset = offset; + + return status; +} + +/** + * + * @stp_request: The request that is used for the SGL processing. + * @data_buffer: The buffer of data to be copied. + * @length: The length of the data transfer. + * + * Copy the data from the buffer for the length specified to the IO reqeust SGL + * specified data region. enum sci_status + */ +static enum sci_status +sci_stp_request_pio_data_in_copy_data_buffer(struct isci_stp_request *stp_req, + u8 *data_buf, u32 len) +{ + struct isci_request *ireq; + u8 *src_addr; + int copy_len; + struct sas_task *task; + struct scatterlist *sg; + void *kaddr; + int total_len = len; + + ireq = to_ireq(stp_req); + task = isci_request_access_task(ireq); + src_addr = data_buf; + + if (task->num_scatter > 0) { + sg = task->scatter; + + while (total_len > 0) { + struct page *page = sg_page(sg); + + copy_len = min_t(int, total_len, sg_dma_len(sg)); + kaddr = kmap_atomic(page, KM_IRQ0); + memcpy(kaddr + sg->offset, src_addr, copy_len); + kunmap_atomic(kaddr, KM_IRQ0); + total_len -= copy_len; + src_addr += copy_len; + sg = sg_next(sg); + } + } else { + BUG_ON(task->total_xfer_len < total_len); + memcpy(task->scatter, src_addr, total_len); + } + + return SCI_SUCCESS; +} + +/** + * + * @sci_req: The PIO DATA IN request that is to receive the data. + * @data_buffer: The buffer to copy from. + * + * Copy the data buffer to the io request data region. enum sci_status + */ +static enum sci_status sci_stp_request_pio_data_in_copy_data( + struct isci_stp_request *stp_req, + u8 *data_buffer) +{ + enum sci_status status; + + /* + * If there is less than 1K remaining in the transfer request + * copy just the data for the transfer */ + if (stp_req->pio_len < SCU_MAX_FRAME_BUFFER_SIZE) { + status = sci_stp_request_pio_data_in_copy_data_buffer( + stp_req, data_buffer, stp_req->pio_len); + + if (status == SCI_SUCCESS) + stp_req->pio_len = 0; + } else { + /* We are transfering the whole frame so copy */ + status = sci_stp_request_pio_data_in_copy_data_buffer( + stp_req, data_buffer, SCU_MAX_FRAME_BUFFER_SIZE); + + if (status == SCI_SUCCESS) + stp_req->pio_len -= SCU_MAX_FRAME_BUFFER_SIZE; + } + + return status; +} + +static enum sci_status +stp_request_pio_await_h2d_completion_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + enum sci_status status = SCI_SUCCESS; + + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_WAIT_FRAME); + break; + + default: + /* All other completion status cause the IO to be + * complete. If a NAK was received, then it is up to + * the user to retry the request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return status; +} + +static enum sci_status +pio_data_out_tx_done_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + enum sci_status status = SCI_SUCCESS; + bool all_frames_transferred = false; + struct isci_stp_request *stp_req = &ireq->stp.req; + + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + /* Transmit data */ + if (stp_req->pio_len != 0) { + status = sci_stp_request_pio_data_out_transmit_data(ireq); + if (status == SCI_SUCCESS) { + if (stp_req->pio_len == 0) + all_frames_transferred = true; + } + } else if (stp_req->pio_len == 0) { + /* + * this will happen if the all data is written at the + * first time after the pio setup fis is received + */ + all_frames_transferred = true; + } + + /* all data transferred. */ + if (all_frames_transferred) { + /* + * Change the state to SCI_REQ_STP_PIO_DATA_IN + * and wait for PIO_SETUP fis / or D2H REg fis. */ + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_WAIT_FRAME); + } + break; + + default: + /* + * All other completion status cause the IO to be complete. + * If a NAK was received, then it is up to the user to retry + * the request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return status; +} + +static enum sci_status sci_stp_request_udma_general_frame_handler(struct isci_request *ireq, + u32 frame_index) +{ + struct isci_host *ihost = ireq->owning_controller; + struct dev_to_host_fis *frame_header; + enum sci_status status; + u32 *frame_buffer; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_header); + + if ((status == SCI_SUCCESS) && + (frame_header->fis_type == FIS_REGD2H)) { + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&frame_buffer); + + sci_controller_copy_sata_response(&ireq->stp.rsp, + frame_header, + frame_buffer); + } + + sci_controller_release_frame(ihost, frame_index); + + return status; +} + +enum sci_status +sci_io_request_frame_handler(struct isci_request *ireq, + u32 frame_index) +{ + struct isci_host *ihost = ireq->owning_controller; + struct isci_stp_request *stp_req = &ireq->stp.req; + enum sci_base_request_states state; + enum sci_status status; + ssize_t word_cnt; + + state = ireq->sm.current_state_id; + switch (state) { + case SCI_REQ_STARTED: { + struct ssp_frame_hdr ssp_hdr; + void *frame_header; + + sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + &frame_header); + + word_cnt = sizeof(struct ssp_frame_hdr) / sizeof(u32); + sci_swab32_cpy(&ssp_hdr, frame_header, word_cnt); + + if (ssp_hdr.frame_type == SSP_RESPONSE) { + struct ssp_response_iu *resp_iu; + ssize_t word_cnt = SSP_RESP_IU_MAX_SIZE / sizeof(u32); + + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&resp_iu); + + sci_swab32_cpy(&ireq->ssp.rsp, resp_iu, word_cnt); + + resp_iu = &ireq->ssp.rsp; + + if (resp_iu->datapres == 0x01 || + resp_iu->datapres == 0x02) { + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + } else { + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + } + } else { + /* not a response frame, why did it get forwarded? */ + dev_err(&ihost->pdev->dev, + "%s: SCIC IO Request 0x%p received unexpected " + "frame %d type 0x%02x\n", __func__, ireq, + frame_index, ssp_hdr.frame_type); + } + + /* + * In any case we are done with this frame buffer return it to + * the controller + */ + sci_controller_release_frame(ihost, frame_index); + + return SCI_SUCCESS; + } + + case SCI_REQ_TASK_WAIT_TC_RESP: + sci_io_request_copy_response(ireq); + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + sci_controller_release_frame(ihost, frame_index); + return SCI_SUCCESS; + + case SCI_REQ_SMP_WAIT_RESP: { + struct smp_resp *rsp_hdr = &ireq->smp.rsp; + void *frame_header; + + sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + &frame_header); + + /* byte swap the header. */ + word_cnt = SMP_RESP_HDR_SZ / sizeof(u32); + sci_swab32_cpy(rsp_hdr, frame_header, word_cnt); + + if (rsp_hdr->frame_type == SMP_RESPONSE) { + void *smp_resp; + + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + &smp_resp); + + word_cnt = (sizeof(struct smp_resp) - SMP_RESP_HDR_SZ) / + sizeof(u32); + + sci_swab32_cpy(((u8 *) rsp_hdr) + SMP_RESP_HDR_SZ, + smp_resp, word_cnt); + + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_SMP_WAIT_TC_COMP); + } else { + /* + * This was not a response frame why did it get + * forwarded? + */ + dev_err(&ihost->pdev->dev, + "%s: SCIC SMP Request 0x%p received unexpected " + "frame %d type 0x%02x\n", + __func__, + ireq, + frame_index, + rsp_hdr->frame_type); + + ireq->scu_status = SCU_TASK_DONE_SMP_FRM_TYPE_ERR; + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + } + + sci_controller_release_frame(ihost, frame_index); + + return SCI_SUCCESS; + } + + case SCI_REQ_STP_UDMA_WAIT_TC_COMP: + return sci_stp_request_udma_general_frame_handler(ireq, + frame_index); + + case SCI_REQ_STP_UDMA_WAIT_D2H: + /* Use the general frame handler to copy the resposne data */ + status = sci_stp_request_udma_general_frame_handler(ireq, frame_index); + + if (status != SCI_SUCCESS) + return status; + + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + return SCI_SUCCESS; + + case SCI_REQ_STP_NON_DATA_WAIT_D2H: { + struct dev_to_host_fis *frame_header; + u32 *frame_buffer; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_header); + + if (status != SCI_SUCCESS) { + dev_err(&ihost->pdev->dev, + "%s: SCIC IO Request 0x%p could not get frame " + "header for frame index %d, status %x\n", + __func__, + stp_req, + frame_index, + status); + + return status; + } + + switch (frame_header->fis_type) { + case FIS_REGD2H: + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&frame_buffer); + + sci_controller_copy_sata_response(&ireq->stp.rsp, + frame_header, + frame_buffer); + + /* The command has completed with error */ + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + break; + + default: + dev_warn(&ihost->pdev->dev, + "%s: IO Request:0x%p Frame Id:%d protocol " + "violation occurred\n", __func__, stp_req, + frame_index); + + ireq->scu_status = SCU_TASK_DONE_UNEXP_FIS; + ireq->sci_status = SCI_FAILURE_PROTOCOL_VIOLATION; + break; + } + + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + + /* Frame has been decoded return it to the controller */ + sci_controller_release_frame(ihost, frame_index); + + return status; + } + + case SCI_REQ_STP_PIO_WAIT_FRAME: { + struct sas_task *task = isci_request_access_task(ireq); + struct dev_to_host_fis *frame_header; + u32 *frame_buffer; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_header); + + if (status != SCI_SUCCESS) { + dev_err(&ihost->pdev->dev, + "%s: SCIC IO Request 0x%p could not get frame " + "header for frame index %d, status %x\n", + __func__, stp_req, frame_index, status); + return status; + } + + switch (frame_header->fis_type) { + case FIS_PIO_SETUP: + /* Get from the frame buffer the PIO Setup Data */ + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&frame_buffer); + + /* Get the data from the PIO Setup The SCU Hardware + * returns first word in the frame_header and the rest + * of the data is in the frame buffer so we need to + * back up one dword + */ + + /* transfer_count: first 16bits in the 4th dword */ + stp_req->pio_len = frame_buffer[3] & 0xffff; + + /* status: 4th byte in the 3rd dword */ + stp_req->status = (frame_buffer[2] >> 24) & 0xff; + + sci_controller_copy_sata_response(&ireq->stp.rsp, + frame_header, + frame_buffer); + + ireq->stp.rsp.status = stp_req->status; + + /* The next state is dependent on whether the + * request was PIO Data-in or Data out + */ + if (task->data_dir == DMA_FROM_DEVICE) { + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_DATA_IN); + } else if (task->data_dir == DMA_TO_DEVICE) { + /* Transmit data */ + status = sci_stp_request_pio_data_out_transmit_data(ireq); + if (status != SCI_SUCCESS) + break; + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_DATA_OUT); + } + break; + + case FIS_SETDEVBITS: + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_WAIT_FRAME); + break; + + case FIS_REGD2H: + if (frame_header->status & ATA_BUSY) { + /* + * Now why is the drive sending a D2H Register + * FIS when it is still busy? Do nothing since + * we are still in the right state. + */ + dev_dbg(&ihost->pdev->dev, + "%s: SCIC PIO Request 0x%p received " + "D2H Register FIS with BSY status " + "0x%x\n", + __func__, + stp_req, + frame_header->status); + break; + } + + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&frame_buffer); + + sci_controller_copy_sata_response(&ireq->stp.req, + frame_header, + frame_buffer); + + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + + default: + /* FIXME: what do we do here? */ + break; + } + + /* Frame is decoded return it to the controller */ + sci_controller_release_frame(ihost, frame_index); + + return status; + } + + case SCI_REQ_STP_PIO_DATA_IN: { + struct dev_to_host_fis *frame_header; + struct sata_fis_data *frame_buffer; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_header); + + if (status != SCI_SUCCESS) { + dev_err(&ihost->pdev->dev, + "%s: SCIC IO Request 0x%p could not get frame " + "header for frame index %d, status %x\n", + __func__, + stp_req, + frame_index, + status); + return status; + } + + if (frame_header->fis_type != FIS_DATA) { + dev_err(&ihost->pdev->dev, + "%s: SCIC PIO Request 0x%p received frame %d " + "with fis type 0x%02x when expecting a data " + "fis.\n", + __func__, + stp_req, + frame_index, + frame_header->fis_type); + + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_FAILURE_IO_REQUIRES_SCSI_ABORT; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + + /* Frame is decoded return it to the controller */ + sci_controller_release_frame(ihost, frame_index); + return status; + } + + if (stp_req->sgl.index < 0) { + ireq->saved_rx_frame_index = frame_index; + stp_req->pio_len = 0; + } else { + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&frame_buffer); + + status = sci_stp_request_pio_data_in_copy_data(stp_req, + (u8 *)frame_buffer); + + /* Frame is decoded return it to the controller */ + sci_controller_release_frame(ihost, frame_index); + } + + /* Check for the end of the transfer, are there more + * bytes remaining for this data transfer + */ + if (status != SCI_SUCCESS || stp_req->pio_len != 0) + return status; + + if ((stp_req->status & ATA_BUSY) == 0) { + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + } else { + sci_change_state(&ireq->sm, SCI_REQ_STP_PIO_WAIT_FRAME); + } + return status; + } + + case SCI_REQ_STP_SOFT_RESET_WAIT_D2H: { + struct dev_to_host_fis *frame_header; + u32 *frame_buffer; + + status = sci_unsolicited_frame_control_get_header(&ihost->uf_control, + frame_index, + (void **)&frame_header); + if (status != SCI_SUCCESS) { + dev_err(&ihost->pdev->dev, + "%s: SCIC IO Request 0x%p could not get frame " + "header for frame index %d, status %x\n", + __func__, + stp_req, + frame_index, + status); + return status; + } + + switch (frame_header->fis_type) { + case FIS_REGD2H: + sci_unsolicited_frame_control_get_buffer(&ihost->uf_control, + frame_index, + (void **)&frame_buffer); + + sci_controller_copy_sata_response(&ireq->stp.rsp, + frame_header, + frame_buffer); + + /* The command has completed with error */ + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + break; + + default: + dev_warn(&ihost->pdev->dev, + "%s: IO Request:0x%p Frame Id:%d protocol " + "violation occurred\n", + __func__, + stp_req, + frame_index); + + ireq->scu_status = SCU_TASK_DONE_UNEXP_FIS; + ireq->sci_status = SCI_FAILURE_PROTOCOL_VIOLATION; + break; + } + + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + + /* Frame has been decoded return it to the controller */ + sci_controller_release_frame(ihost, frame_index); + + return status; + } + case SCI_REQ_ABORTING: + /* + * TODO: Is it even possible to get an unsolicited frame in the + * aborting state? + */ + sci_controller_release_frame(ihost, frame_index); + return SCI_SUCCESS; + + default: + dev_warn(&ihost->pdev->dev, + "%s: SCIC IO Request given unexpected frame %x while " + "in state %d\n", + __func__, + frame_index, + state); + + sci_controller_release_frame(ihost, frame_index); + return SCI_FAILURE_INVALID_STATE; + } +} + +static enum sci_status stp_request_udma_await_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + enum sci_status status = SCI_SUCCESS; + + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_UNEXP_FIS): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_REG_ERR): + /* We must check ther response buffer to see if the D2H + * Register FIS was received before we got the TC + * completion. + */ + if (ireq->stp.rsp.fis_type == FIS_REGD2H) { + sci_remote_device_suspend(ireq->target_device, + SCU_EVENT_SPECIFIC(SCU_NORMALIZE_COMPLETION_STATUS(completion_code))); + + ireq->scu_status = SCU_TASK_DONE_CHECK_RESPONSE; + ireq->sci_status = SCI_FAILURE_IO_RESPONSE_VALID; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + } else { + /* If we have an error completion status for the + * TC then we can expect a D2H register FIS from + * the device so we must change state to wait + * for it + */ + sci_change_state(&ireq->sm, SCI_REQ_STP_UDMA_WAIT_D2H); + } + break; + + /* TODO Check to see if any of these completion status need to + * wait for the device to host register fis. + */ + /* TODO We can retry the command for SCU_TASK_DONE_CMD_LL_R_ERR + * - this comes only for B0 + */ + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_INV_FIS_LEN): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_MAX_PLD_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_LL_R_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_CMD_LL_R_ERR): + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_CRC_ERR): + sci_remote_device_suspend(ireq->target_device, + SCU_EVENT_SPECIFIC(SCU_NORMALIZE_COMPLETION_STATUS(completion_code))); + /* Fall through to the default case */ + default: + /* All other completion status cause the IO to be complete. */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return status; +} + +static enum sci_status +stp_request_soft_reset_await_h2d_asserted_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_STP_SOFT_RESET_WAIT_H2D_DIAG); + break; + + default: + /* + * All other completion status cause the IO to be complete. + * If a NAK was received, then it is up to the user to retry + * the request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return SCI_SUCCESS; +} + +static enum sci_status +stp_request_soft_reset_await_h2d_diagnostic_tc_event(struct isci_request *ireq, + u32 completion_code) +{ + switch (SCU_GET_COMPLETION_TL_STATUS(completion_code)) { + case SCU_MAKE_COMPLETION_STATUS(SCU_TASK_DONE_GOOD): + ireq->scu_status = SCU_TASK_DONE_GOOD; + ireq->sci_status = SCI_SUCCESS; + sci_change_state(&ireq->sm, SCI_REQ_STP_SOFT_RESET_WAIT_D2H); + break; + + default: + /* All other completion status cause the IO to be complete. If + * a NAK was received, then it is up to the user to retry the + * request. + */ + ireq->scu_status = SCU_NORMALIZE_COMPLETION_STATUS(completion_code); + ireq->sci_status = SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR; + sci_change_state(&ireq->sm, SCI_REQ_COMPLETED); + break; + } + + return SCI_SUCCESS; +} + +enum sci_status +sci_io_request_tc_completion(struct isci_request *ireq, + u32 completion_code) +{ + enum sci_base_request_states state; + struct isci_host *ihost = ireq->owning_controller; + + state = ireq->sm.current_state_id; + + switch (state) { + case SCI_REQ_STARTED: + return request_started_state_tc_event(ireq, completion_code); + + case SCI_REQ_TASK_WAIT_TC_COMP: + return ssp_task_request_await_tc_event(ireq, + completion_code); + + case SCI_REQ_SMP_WAIT_RESP: + return smp_request_await_response_tc_event(ireq, + completion_code); + + case SCI_REQ_SMP_WAIT_TC_COMP: + return smp_request_await_tc_event(ireq, completion_code); + + case SCI_REQ_STP_UDMA_WAIT_TC_COMP: + return stp_request_udma_await_tc_event(ireq, + completion_code); + + case SCI_REQ_STP_NON_DATA_WAIT_H2D: + return stp_request_non_data_await_h2d_tc_event(ireq, + completion_code); + + case SCI_REQ_STP_PIO_WAIT_H2D: + return stp_request_pio_await_h2d_completion_tc_event(ireq, + completion_code); + + case SCI_REQ_STP_PIO_DATA_OUT: + return pio_data_out_tx_done_tc_event(ireq, completion_code); + + case SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED: + return stp_request_soft_reset_await_h2d_asserted_tc_event(ireq, + completion_code); + + case SCI_REQ_STP_SOFT_RESET_WAIT_H2D_DIAG: + return stp_request_soft_reset_await_h2d_diagnostic_tc_event(ireq, + completion_code); + + case SCI_REQ_ABORTING: + return request_aborting_state_tc_event(ireq, + completion_code); + + default: + dev_warn(&ihost->pdev->dev, + "%s: SCIC IO Request given task completion " + "notification %x while in wrong state %d\n", + __func__, + completion_code, + state); + return SCI_FAILURE_INVALID_STATE; + } +} + +/** + * isci_request_process_response_iu() - This function sets the status and + * response iu, in the task struct, from the request object for the upper + * layer driver. + * @sas_task: This parameter is the task struct from the upper layer driver. + * @resp_iu: This parameter points to the response iu of the completed request. + * @dev: This parameter specifies the linux device struct. + * + * none. + */ +static void isci_request_process_response_iu( + struct sas_task *task, + struct ssp_response_iu *resp_iu, + struct device *dev) +{ + dev_dbg(dev, + "%s: resp_iu = %p " + "resp_iu->status = 0x%x,\nresp_iu->datapres = %d " + "resp_iu->response_data_len = %x, " + "resp_iu->sense_data_len = %x\nrepsonse data: ", + __func__, + resp_iu, + resp_iu->status, + resp_iu->datapres, + resp_iu->response_data_len, + resp_iu->sense_data_len); + + task->task_status.stat = resp_iu->status; + + /* libsas updates the task status fields based on the response iu. */ + sas_ssp_task_response(dev, task, resp_iu); +} + +/** + * isci_request_set_open_reject_status() - This function prepares the I/O + * completion for OPEN_REJECT conditions. + * @request: This parameter is the completed isci_request object. + * @response_ptr: This parameter specifies the service response for the I/O. + * @status_ptr: This parameter specifies the exec status for the I/O. + * @complete_to_host_ptr: This parameter specifies the action to be taken by + * the LLDD with respect to completing this request or forcing an abort + * condition on the I/O. + * @open_rej_reason: This parameter specifies the encoded reason for the + * abandon-class reject. + * + * none. + */ +static void isci_request_set_open_reject_status( + struct isci_request *request, + struct sas_task *task, + enum service_response *response_ptr, + enum exec_status *status_ptr, + enum isci_completion_selection *complete_to_host_ptr, + enum sas_open_rej_reason open_rej_reason) +{ + /* Task in the target is done. */ + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + *response_ptr = SAS_TASK_UNDELIVERED; + *status_ptr = SAS_OPEN_REJECT; + *complete_to_host_ptr = isci_perform_normal_io_completion; + task->task_status.open_rej_reason = open_rej_reason; +} + +/** + * isci_request_handle_controller_specific_errors() - This function decodes + * controller-specific I/O completion error conditions. + * @request: This parameter is the completed isci_request object. + * @response_ptr: This parameter specifies the service response for the I/O. + * @status_ptr: This parameter specifies the exec status for the I/O. + * @complete_to_host_ptr: This parameter specifies the action to be taken by + * the LLDD with respect to completing this request or forcing an abort + * condition on the I/O. + * + * none. + */ +static void isci_request_handle_controller_specific_errors( + struct isci_remote_device *idev, + struct isci_request *request, + struct sas_task *task, + enum service_response *response_ptr, + enum exec_status *status_ptr, + enum isci_completion_selection *complete_to_host_ptr) +{ + unsigned int cstatus; + + cstatus = request->scu_status; + + dev_dbg(&request->isci_host->pdev->dev, + "%s: %p SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR " + "- controller status = 0x%x\n", + __func__, request, cstatus); + + /* Decode the controller-specific errors; most + * important is to recognize those conditions in which + * the target may still have a task outstanding that + * must be aborted. + * + * Note that there are SCU completion codes being + * named in the decode below for which SCIC has already + * done work to handle them in a way other than as + * a controller-specific completion code; these are left + * in the decode below for completeness sake. + */ + switch (cstatus) { + case SCU_TASK_DONE_DMASETUP_DIRERR: + /* Also SCU_TASK_DONE_SMP_FRM_TYPE_ERR: */ + case SCU_TASK_DONE_XFERCNT_ERR: + /* Also SCU_TASK_DONE_SMP_UFI_ERR: */ + if (task->task_proto == SAS_PROTOCOL_SMP) { + /* SCU_TASK_DONE_SMP_UFI_ERR == Task Done. */ + *response_ptr = SAS_TASK_COMPLETE; + + /* See if the device has been/is being stopped. Note + * that we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + if (!idev) + *status_ptr = SAS_DEVICE_UNKNOWN; + else + *status_ptr = SAS_ABORTED_TASK; + + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + + *complete_to_host_ptr = + isci_perform_normal_io_completion; + } else { + /* Task in the target is not done. */ + *response_ptr = SAS_TASK_UNDELIVERED; + + if (!idev) + *status_ptr = SAS_DEVICE_UNKNOWN; + else + *status_ptr = SAM_STAT_TASK_ABORTED; + + clear_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + + *complete_to_host_ptr = + isci_perform_error_io_completion; + } + + break; + + case SCU_TASK_DONE_CRC_ERR: + case SCU_TASK_DONE_NAK_CMD_ERR: + case SCU_TASK_DONE_EXCESS_DATA: + case SCU_TASK_DONE_UNEXP_FIS: + /* Also SCU_TASK_DONE_UNEXP_RESP: */ + case SCU_TASK_DONE_VIIT_ENTRY_NV: /* TODO - conditions? */ + case SCU_TASK_DONE_IIT_ENTRY_NV: /* TODO - conditions? */ + case SCU_TASK_DONE_RNCNV_OUTBOUND: /* TODO - conditions? */ + /* These are conditions in which the target + * has completed the task, so that no cleanup + * is necessary. + */ + *response_ptr = SAS_TASK_COMPLETE; + + /* See if the device has been/is being stopped. Note + * that we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + if (!idev) + *status_ptr = SAS_DEVICE_UNKNOWN; + else + *status_ptr = SAS_ABORTED_TASK; + + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + + *complete_to_host_ptr = isci_perform_normal_io_completion; + break; + + + /* Note that the only open reject completion codes seen here will be + * abandon-class codes; all others are automatically retried in the SCU. + */ + case SCU_TASK_OPEN_REJECT_WRONG_DESTINATION: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_WRONG_DEST); + break; + + case SCU_TASK_OPEN_REJECT_ZONE_VIOLATION: + + /* Note - the return of AB0 will change when + * libsas implements detection of zone violations. + */ + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_RESV_AB0); + break; + + case SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_1: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_RESV_AB1); + break; + + case SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_2: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_RESV_AB2); + break; + + case SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_3: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_RESV_AB3); + break; + + case SCU_TASK_OPEN_REJECT_BAD_DESTINATION: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_BAD_DEST); + break; + + case SCU_TASK_OPEN_REJECT_STP_RESOURCES_BUSY: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_STP_NORES); + break; + + case SCU_TASK_OPEN_REJECT_PROTOCOL_NOT_SUPPORTED: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_EPROTO); + break; + + case SCU_TASK_OPEN_REJECT_CONNECTION_RATE_NOT_SUPPORTED: + + isci_request_set_open_reject_status( + request, task, response_ptr, status_ptr, + complete_to_host_ptr, SAS_OREJ_CONN_RATE); + break; + + case SCU_TASK_DONE_LL_R_ERR: + /* Also SCU_TASK_DONE_ACK_NAK_TO: */ + case SCU_TASK_DONE_LL_PERR: + case SCU_TASK_DONE_LL_SY_TERM: + /* Also SCU_TASK_DONE_NAK_ERR:*/ + case SCU_TASK_DONE_LL_LF_TERM: + /* Also SCU_TASK_DONE_DATA_LEN_ERR: */ + case SCU_TASK_DONE_LL_ABORT_ERR: + case SCU_TASK_DONE_SEQ_INV_TYPE: + /* Also SCU_TASK_DONE_UNEXP_XR: */ + case SCU_TASK_DONE_XR_IU_LEN_ERR: + case SCU_TASK_DONE_INV_FIS_LEN: + /* Also SCU_TASK_DONE_XR_WD_LEN: */ + case SCU_TASK_DONE_SDMA_ERR: + case SCU_TASK_DONE_OFFSET_ERR: + case SCU_TASK_DONE_MAX_PLD_ERR: + case SCU_TASK_DONE_LF_ERR: + case SCU_TASK_DONE_SMP_RESP_TO_ERR: /* Escalate to dev reset? */ + case SCU_TASK_DONE_SMP_LL_RX_ERR: + case SCU_TASK_DONE_UNEXP_DATA: + case SCU_TASK_DONE_UNEXP_SDBFIS: + case SCU_TASK_DONE_REG_ERR: + case SCU_TASK_DONE_SDB_ERR: + case SCU_TASK_DONE_TASK_ABORT: + default: + /* Task in the target is not done. */ + *response_ptr = SAS_TASK_UNDELIVERED; + *status_ptr = SAM_STAT_TASK_ABORTED; + + if (task->task_proto == SAS_PROTOCOL_SMP) { + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + + *complete_to_host_ptr = isci_perform_normal_io_completion; + } else { + clear_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + + *complete_to_host_ptr = isci_perform_error_io_completion; + } + break; + } +} + +/** + * isci_task_save_for_upper_layer_completion() - This function saves the + * request for later completion to the upper layer driver. + * @host: This parameter is a pointer to the host on which the the request + * should be queued (either as an error or success). + * @request: This parameter is the completed request. + * @response: This parameter is the response code for the completed task. + * @status: This parameter is the status code for the completed task. + * + * none. + */ +static void isci_task_save_for_upper_layer_completion( + struct isci_host *host, + struct isci_request *request, + enum service_response response, + enum exec_status status, + enum isci_completion_selection task_notification_selection) +{ + struct sas_task *task = isci_request_access_task(request); + + task_notification_selection + = isci_task_set_completion_status(task, response, status, + task_notification_selection); + + /* Tasks aborted specifically by a call to the lldd_abort_task + * function should not be completed to the host in the regular path. + */ + switch (task_notification_selection) { + + case isci_perform_normal_io_completion: + + /* Normal notification (task_done) */ + dev_dbg(&host->pdev->dev, + "%s: Normal - task = %p, response=%d (%d), status=%d (%d)\n", + __func__, + task, + task->task_status.resp, response, + task->task_status.stat, status); + /* Add to the completed list. */ + list_add(&request->completed_node, + &host->requests_to_complete); + + /* Take the request off the device's pending request list. */ + list_del_init(&request->dev_node); + break; + + case isci_perform_aborted_io_completion: + /* No notification to libsas because this request is + * already in the abort path. + */ + dev_dbg(&host->pdev->dev, + "%s: Aborted - task = %p, response=%d (%d), status=%d (%d)\n", + __func__, + task, + task->task_status.resp, response, + task->task_status.stat, status); + + /* Wake up whatever process was waiting for this + * request to complete. + */ + WARN_ON(request->io_request_completion == NULL); + + if (request->io_request_completion != NULL) { + + /* Signal whoever is waiting that this + * request is complete. + */ + complete(request->io_request_completion); + } + break; + + case isci_perform_error_io_completion: + /* Use sas_task_abort */ + dev_dbg(&host->pdev->dev, + "%s: Error - task = %p, response=%d (%d), status=%d (%d)\n", + __func__, + task, + task->task_status.resp, response, + task->task_status.stat, status); + /* Add to the aborted list. */ + list_add(&request->completed_node, + &host->requests_to_errorback); + break; + + default: + dev_dbg(&host->pdev->dev, + "%s: Unknown - task = %p, response=%d (%d), status=%d (%d)\n", + __func__, + task, + task->task_status.resp, response, + task->task_status.stat, status); + + /* Add to the error to libsas list. */ + list_add(&request->completed_node, + &host->requests_to_errorback); + break; + } +} + +static void isci_request_process_stp_response(struct sas_task *task, + void *response_buffer) +{ + struct dev_to_host_fis *d2h_reg_fis = response_buffer; + struct task_status_struct *ts = &task->task_status; + struct ata_task_resp *resp = (void *)&ts->buf[0]; + + resp->frame_len = le16_to_cpu(*(__le16 *)(response_buffer + 6)); + memcpy(&resp->ending_fis[0], response_buffer + 16, 24); + ts->buf_valid_size = sizeof(*resp); + + /** + * If the device fault bit is set in the status register, then + * set the sense data and return. + */ + if (d2h_reg_fis->status & ATA_DF) + ts->stat = SAS_PROTO_RESPONSE; + else + ts->stat = SAM_STAT_GOOD; + + ts->resp = SAS_TASK_COMPLETE; +} + +static void isci_request_io_request_complete(struct isci_host *ihost, + struct isci_request *request, + enum sci_io_status completion_status) +{ + struct sas_task *task = isci_request_access_task(request); + struct ssp_response_iu *resp_iu; + void *resp_buf; + unsigned long task_flags; + struct isci_remote_device *idev = isci_lookup_device(task->dev); + enum service_response response = SAS_TASK_UNDELIVERED; + enum exec_status status = SAS_ABORTED_TASK; + enum isci_request_status request_status; + enum isci_completion_selection complete_to_host + = isci_perform_normal_io_completion; + + dev_dbg(&ihost->pdev->dev, + "%s: request = %p, task = %p,\n" + "task->data_dir = %d completion_status = 0x%x\n", + __func__, + request, + task, + task->data_dir, + completion_status); + + spin_lock(&request->state_lock); + request_status = request->status; + + /* Decode the request status. Note that if the request has been + * aborted by a task management function, we don't care + * what the status is. + */ + switch (request_status) { + + case aborted: + /* "aborted" indicates that the request was aborted by a task + * management function, since once a task management request is + * perfomed by the device, the request only completes because + * of the subsequent driver terminate. + * + * Aborted also means an external thread is explicitly managing + * this request, so that we do not complete it up the stack. + * + * The target is still there (since the TMF was successful). + */ + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + response = SAS_TASK_COMPLETE; + + /* See if the device has been/is being stopped. Note + * that we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + if (!idev) + status = SAS_DEVICE_UNKNOWN; + else + status = SAS_ABORTED_TASK; + + complete_to_host = isci_perform_aborted_io_completion; + /* This was an aborted request. */ + + spin_unlock(&request->state_lock); + break; + + case aborting: + /* aborting means that the task management function tried and + * failed to abort the request. We need to note the request + * as SAS_TASK_UNDELIVERED, so that the scsi mid layer marks the + * target as down. + * + * Aborting also means an external thread is explicitly managing + * this request, so that we do not complete it up the stack. + */ + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + response = SAS_TASK_UNDELIVERED; + + if (!idev) + /* The device has been /is being stopped. Note that + * we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + status = SAS_DEVICE_UNKNOWN; + else + status = SAS_PHY_DOWN; + + complete_to_host = isci_perform_aborted_io_completion; + + /* This was an aborted request. */ + + spin_unlock(&request->state_lock); + break; + + case terminating: + + /* This was an terminated request. This happens when + * the I/O is being terminated because of an action on + * the device (reset, tear down, etc.), and the I/O needs + * to be completed up the stack. + */ + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + response = SAS_TASK_UNDELIVERED; + + /* See if the device has been/is being stopped. Note + * that we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + if (!idev) + status = SAS_DEVICE_UNKNOWN; + else + status = SAS_ABORTED_TASK; + + complete_to_host = isci_perform_aborted_io_completion; + + /* This was a terminated request. */ + + spin_unlock(&request->state_lock); + break; + + case dead: + /* This was a terminated request that timed-out during the + * termination process. There is no task to complete to + * libsas. + */ + complete_to_host = isci_perform_normal_io_completion; + spin_unlock(&request->state_lock); + break; + + default: + + /* The request is done from an SCU HW perspective. */ + request->status = completed; + + spin_unlock(&request->state_lock); + + /* This is an active request being completed from the core. */ + switch (completion_status) { + + case SCI_IO_FAILURE_RESPONSE_VALID: + dev_dbg(&ihost->pdev->dev, + "%s: SCI_IO_FAILURE_RESPONSE_VALID (%p/%p)\n", + __func__, + request, + task); + + if (sas_protocol_ata(task->task_proto)) { + resp_buf = &request->stp.rsp; + isci_request_process_stp_response(task, + resp_buf); + } else if (SAS_PROTOCOL_SSP == task->task_proto) { + + /* crack the iu response buffer. */ + resp_iu = &request->ssp.rsp; + isci_request_process_response_iu(task, resp_iu, + &ihost->pdev->dev); + + } else if (SAS_PROTOCOL_SMP == task->task_proto) { + + dev_err(&ihost->pdev->dev, + "%s: SCI_IO_FAILURE_RESPONSE_VALID: " + "SAS_PROTOCOL_SMP protocol\n", + __func__); + + } else + dev_err(&ihost->pdev->dev, + "%s: unknown protocol\n", __func__); + + /* use the task status set in the task struct by the + * isci_request_process_response_iu call. + */ + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + response = task->task_status.resp; + status = task->task_status.stat; + break; + + case SCI_IO_SUCCESS: + case SCI_IO_SUCCESS_IO_DONE_EARLY: + + response = SAS_TASK_COMPLETE; + status = SAM_STAT_GOOD; + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + + if (task->task_proto == SAS_PROTOCOL_SMP) { + void *rsp = &request->smp.rsp; + + dev_dbg(&ihost->pdev->dev, + "%s: SMP protocol completion\n", + __func__); + + sg_copy_from_buffer( + &task->smp_task.smp_resp, 1, + rsp, sizeof(struct smp_resp)); + } else if (completion_status + == SCI_IO_SUCCESS_IO_DONE_EARLY) { + + /* This was an SSP / STP / SATA transfer. + * There is a possibility that less data than + * the maximum was transferred. + */ + u32 transferred_length = sci_req_tx_bytes(request); + + task->task_status.residual + = task->total_xfer_len - transferred_length; + + /* If there were residual bytes, call this an + * underrun. + */ + if (task->task_status.residual != 0) + status = SAS_DATA_UNDERRUN; + + dev_dbg(&ihost->pdev->dev, + "%s: SCI_IO_SUCCESS_IO_DONE_EARLY %d\n", + __func__, + status); + + } else + dev_dbg(&ihost->pdev->dev, + "%s: SCI_IO_SUCCESS\n", + __func__); + + break; + + case SCI_IO_FAILURE_TERMINATED: + dev_dbg(&ihost->pdev->dev, + "%s: SCI_IO_FAILURE_TERMINATED (%p/%p)\n", + __func__, + request, + task); + + /* The request was terminated explicitly. No handling + * is needed in the SCSI error handler path. + */ + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + response = SAS_TASK_UNDELIVERED; + + /* See if the device has been/is being stopped. Note + * that we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + if (!idev) + status = SAS_DEVICE_UNKNOWN; + else + status = SAS_ABORTED_TASK; + + complete_to_host = isci_perform_normal_io_completion; + break; + + case SCI_FAILURE_CONTROLLER_SPECIFIC_IO_ERR: + + isci_request_handle_controller_specific_errors( + idev, request, task, &response, &status, + &complete_to_host); + + break; + + case SCI_IO_FAILURE_REMOTE_DEVICE_RESET_REQUIRED: + /* This is a special case, in that the I/O completion + * is telling us that the device needs a reset. + * In order for the device reset condition to be + * noticed, the I/O has to be handled in the error + * handler. Set the reset flag and cause the + * SCSI error thread to be scheduled. + */ + spin_lock_irqsave(&task->task_state_lock, task_flags); + task->task_state_flags |= SAS_TASK_NEED_DEV_RESET; + spin_unlock_irqrestore(&task->task_state_lock, task_flags); + + /* Fail the I/O. */ + response = SAS_TASK_UNDELIVERED; + status = SAM_STAT_TASK_ABORTED; + + complete_to_host = isci_perform_error_io_completion; + clear_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + break; + + case SCI_FAILURE_RETRY_REQUIRED: + + /* Fail the I/O so it can be retried. */ + response = SAS_TASK_UNDELIVERED; + if (!idev) + status = SAS_DEVICE_UNKNOWN; + else + status = SAS_ABORTED_TASK; + + complete_to_host = isci_perform_normal_io_completion; + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + break; + + + default: + /* Catch any otherwise unhandled error codes here. */ + dev_dbg(&ihost->pdev->dev, + "%s: invalid completion code: 0x%x - " + "isci_request = %p\n", + __func__, completion_status, request); + + response = SAS_TASK_UNDELIVERED; + + /* See if the device has been/is being stopped. Note + * that we ignore the quiesce state, since we are + * concerned about the actual device state. + */ + if (!idev) + status = SAS_DEVICE_UNKNOWN; + else + status = SAS_ABORTED_TASK; + + if (SAS_PROTOCOL_SMP == task->task_proto) { + set_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + complete_to_host = isci_perform_normal_io_completion; + } else { + clear_bit(IREQ_COMPLETE_IN_TARGET, &request->flags); + complete_to_host = isci_perform_error_io_completion; + } + break; + } + break; + } + + switch (task->task_proto) { + case SAS_PROTOCOL_SSP: + if (task->data_dir == DMA_NONE) + break; + if (task->num_scatter == 0) + /* 0 indicates a single dma address */ + dma_unmap_single(&ihost->pdev->dev, + request->zero_scatter_daddr, + task->total_xfer_len, task->data_dir); + else /* unmap the sgl dma addresses */ + dma_unmap_sg(&ihost->pdev->dev, task->scatter, + request->num_sg_entries, task->data_dir); + break; + case SAS_PROTOCOL_SMP: { + struct scatterlist *sg = &task->smp_task.smp_req; + struct smp_req *smp_req; + void *kaddr; + + dma_unmap_sg(&ihost->pdev->dev, sg, 1, DMA_TO_DEVICE); + + /* need to swab it back in case the command buffer is re-used */ + kaddr = kmap_atomic(sg_page(sg), KM_IRQ0); + smp_req = kaddr + sg->offset; + sci_swab32_cpy(smp_req, smp_req, sg->length / sizeof(u32)); + kunmap_atomic(kaddr, KM_IRQ0); + break; + } + default: + break; + } + + /* Put the completed request on the correct list */ + isci_task_save_for_upper_layer_completion(ihost, request, response, + status, complete_to_host + ); + + /* complete the io request to the core. */ + sci_controller_complete_io(ihost, request->target_device, request); + isci_put_device(idev); + + /* set terminated handle so it cannot be completed or + * terminated again, and to cause any calls into abort + * task to recognize the already completed case. + */ + set_bit(IREQ_TERMINATED, &request->flags); +} + +static void sci_request_started_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + struct domain_device *dev = ireq->target_device->domain_dev; + struct sas_task *task; + + /* XXX as hch said always creating an internal sas_task for tmf + * requests would simplify the driver + */ + task = ireq->ttype == io_task ? isci_request_access_task(ireq) : NULL; + + /* all unaccelerated request types (non ssp or ncq) handled with + * substates + */ + if (!task && dev->dev_type == SAS_END_DEV) { + sci_change_state(sm, SCI_REQ_TASK_WAIT_TC_COMP); + } else if (!task && + (isci_request_access_tmf(ireq)->tmf_code == isci_tmf_sata_srst_high || + isci_request_access_tmf(ireq)->tmf_code == isci_tmf_sata_srst_low)) { + sci_change_state(sm, SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED); + } else if (task && task->task_proto == SAS_PROTOCOL_SMP) { + sci_change_state(sm, SCI_REQ_SMP_WAIT_RESP); + } else if (task && sas_protocol_ata(task->task_proto) && + !task->ata_task.use_ncq) { + u32 state; + + if (task->data_dir == DMA_NONE) + state = SCI_REQ_STP_NON_DATA_WAIT_H2D; + else if (task->ata_task.dma_xfer) + state = SCI_REQ_STP_UDMA_WAIT_TC_COMP; + else /* PIO */ + state = SCI_REQ_STP_PIO_WAIT_H2D; + + sci_change_state(sm, state); + } +} + +static void sci_request_completed_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + struct isci_host *ihost = ireq->owning_controller; + + /* Tell the SCI_USER that the IO request is complete */ + if (!test_bit(IREQ_TMF, &ireq->flags)) + isci_request_io_request_complete(ihost, ireq, + ireq->sci_status); + else + isci_task_request_complete(ihost, ireq, ireq->sci_status); +} + +static void sci_request_aborting_state_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + + /* Setting the abort bit in the Task Context is required by the silicon. */ + ireq->tc->abort = 1; +} + +static void sci_stp_request_started_non_data_await_h2d_completion_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + + ireq->target_device->working_request = ireq; +} + +static void sci_stp_request_started_pio_await_h2d_completion_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + + ireq->target_device->working_request = ireq; +} + +static void sci_stp_request_started_soft_reset_await_h2d_asserted_completion_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + + ireq->target_device->working_request = ireq; +} + +static void sci_stp_request_started_soft_reset_await_h2d_diagnostic_completion_enter(struct sci_base_state_machine *sm) +{ + struct isci_request *ireq = container_of(sm, typeof(*ireq), sm); + struct scu_task_context *tc = ireq->tc; + struct host_to_dev_fis *h2d_fis; + enum sci_status status; + + /* Clear the SRST bit */ + h2d_fis = &ireq->stp.cmd; + h2d_fis->control = 0; + + /* Clear the TC control bit */ + tc->control_frame = 0; + + status = sci_controller_continue_io(ireq); + WARN_ONCE(status != SCI_SUCCESS, "isci: continue io failure\n"); +} + +static const struct sci_base_state sci_request_state_table[] = { + [SCI_REQ_INIT] = { }, + [SCI_REQ_CONSTRUCTED] = { }, + [SCI_REQ_STARTED] = { + .enter_state = sci_request_started_state_enter, + }, + [SCI_REQ_STP_NON_DATA_WAIT_H2D] = { + .enter_state = sci_stp_request_started_non_data_await_h2d_completion_enter, + }, + [SCI_REQ_STP_NON_DATA_WAIT_D2H] = { }, + [SCI_REQ_STP_PIO_WAIT_H2D] = { + .enter_state = sci_stp_request_started_pio_await_h2d_completion_enter, + }, + [SCI_REQ_STP_PIO_WAIT_FRAME] = { }, + [SCI_REQ_STP_PIO_DATA_IN] = { }, + [SCI_REQ_STP_PIO_DATA_OUT] = { }, + [SCI_REQ_STP_UDMA_WAIT_TC_COMP] = { }, + [SCI_REQ_STP_UDMA_WAIT_D2H] = { }, + [SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED] = { + .enter_state = sci_stp_request_started_soft_reset_await_h2d_asserted_completion_enter, + }, + [SCI_REQ_STP_SOFT_RESET_WAIT_H2D_DIAG] = { + .enter_state = sci_stp_request_started_soft_reset_await_h2d_diagnostic_completion_enter, + }, + [SCI_REQ_STP_SOFT_RESET_WAIT_D2H] = { }, + [SCI_REQ_TASK_WAIT_TC_COMP] = { }, + [SCI_REQ_TASK_WAIT_TC_RESP] = { }, + [SCI_REQ_SMP_WAIT_RESP] = { }, + [SCI_REQ_SMP_WAIT_TC_COMP] = { }, + [SCI_REQ_COMPLETED] = { + .enter_state = sci_request_completed_state_enter, + }, + [SCI_REQ_ABORTING] = { + .enter_state = sci_request_aborting_state_enter, + }, + [SCI_REQ_FINAL] = { }, +}; + +static void +sci_general_request_construct(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + sci_init_sm(&ireq->sm, sci_request_state_table, SCI_REQ_INIT); + + ireq->target_device = idev; + ireq->protocol = SCIC_NO_PROTOCOL; + ireq->saved_rx_frame_index = SCU_INVALID_FRAME_INDEX; + + ireq->sci_status = SCI_SUCCESS; + ireq->scu_status = 0; + ireq->post_context = 0xFFFFFFFF; +} + +static enum sci_status +sci_io_request_construct(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *ireq) +{ + struct domain_device *dev = idev->domain_dev; + enum sci_status status = SCI_SUCCESS; + + /* Build the common part of the request */ + sci_general_request_construct(ihost, idev, ireq); + + if (idev->rnc.remote_node_index == SCIC_SDS_REMOTE_NODE_CONTEXT_INVALID_INDEX) + return SCI_FAILURE_INVALID_REMOTE_DEVICE; + + if (dev->dev_type == SAS_END_DEV) + /* pass */; + else if (dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) + memset(&ireq->stp.cmd, 0, sizeof(ireq->stp.cmd)); + else if (dev_is_expander(dev)) + /* pass */; + else + return SCI_FAILURE_UNSUPPORTED_PROTOCOL; + + memset(ireq->tc, 0, offsetof(struct scu_task_context, sgl_pair_ab)); + + return status; +} + +enum sci_status sci_task_request_construct(struct isci_host *ihost, + struct isci_remote_device *idev, + u16 io_tag, struct isci_request *ireq) +{ + struct domain_device *dev = idev->domain_dev; + enum sci_status status = SCI_SUCCESS; + + /* Build the common part of the request */ + sci_general_request_construct(ihost, idev, ireq); + + if (dev->dev_type == SAS_END_DEV || + dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) { + set_bit(IREQ_TMF, &ireq->flags); + memset(ireq->tc, 0, sizeof(struct scu_task_context)); + } else + status = SCI_FAILURE_UNSUPPORTED_PROTOCOL; + + return status; +} + +static enum sci_status isci_request_ssp_request_construct( + struct isci_request *request) +{ + enum sci_status status; + + dev_dbg(&request->isci_host->pdev->dev, + "%s: request = %p\n", + __func__, + request); + status = sci_io_request_construct_basic_ssp(request); + return status; +} + +static enum sci_status isci_request_stp_request_construct(struct isci_request *ireq) +{ + struct sas_task *task = isci_request_access_task(ireq); + struct host_to_dev_fis *fis = &ireq->stp.cmd; + struct ata_queued_cmd *qc = task->uldd_task; + enum sci_status status; + + dev_dbg(&ireq->isci_host->pdev->dev, + "%s: ireq = %p\n", + __func__, + ireq); + + memcpy(fis, &task->ata_task.fis, sizeof(struct host_to_dev_fis)); + if (!task->ata_task.device_control_reg_update) + fis->flags |= 0x80; + fis->flags &= 0xF0; + + status = sci_io_request_construct_basic_sata(ireq); + + if (qc && (qc->tf.command == ATA_CMD_FPDMA_WRITE || + qc->tf.command == ATA_CMD_FPDMA_READ)) { + fis->sector_count = qc->tag << 3; + ireq->tc->type.stp.ncq_tag = qc->tag; + } + + return status; +} + +static enum sci_status +sci_io_request_construct_smp(struct device *dev, + struct isci_request *ireq, + struct sas_task *task) +{ + struct scatterlist *sg = &task->smp_task.smp_req; + struct isci_remote_device *idev; + struct scu_task_context *task_context; + struct isci_port *iport; + struct smp_req *smp_req; + void *kaddr; + u8 req_len; + u32 cmd; + + kaddr = kmap_atomic(sg_page(sg), KM_IRQ0); + smp_req = kaddr + sg->offset; + /* + * Look at the SMP requests' header fields; for certain SAS 1.x SMP + * functions under SAS 2.0, a zero request length really indicates + * a non-zero default length. + */ + if (smp_req->req_len == 0) { + switch (smp_req->func) { + case SMP_DISCOVER: + case SMP_REPORT_PHY_ERR_LOG: + case SMP_REPORT_PHY_SATA: + case SMP_REPORT_ROUTE_INFO: + smp_req->req_len = 2; + break; + case SMP_CONF_ROUTE_INFO: + case SMP_PHY_CONTROL: + case SMP_PHY_TEST_FUNCTION: + smp_req->req_len = 9; + break; + /* Default - zero is a valid default for 2.0. */ + } + } + req_len = smp_req->req_len; + sci_swab32_cpy(smp_req, smp_req, sg->length / sizeof(u32)); + cmd = *(u32 *) smp_req; + kunmap_atomic(kaddr, KM_IRQ0); + + if (!dma_map_sg(dev, sg, 1, DMA_TO_DEVICE)) + return SCI_FAILURE; + + ireq->protocol = SCIC_SMP_PROTOCOL; + + /* byte swap the smp request. */ + + task_context = ireq->tc; + + idev = ireq->target_device; + iport = idev->owning_port; + + /* + * Fill in the TC with the its required data + * 00h + */ + task_context->priority = 0; + task_context->initiator_request = 1; + task_context->connection_rate = idev->connection_rate; + task_context->protocol_engine_index = ISCI_PEG; + task_context->logical_port_index = iport->physical_port_index; + task_context->protocol_type = SCU_TASK_CONTEXT_PROTOCOL_SMP; + task_context->abort = 0; + task_context->valid = SCU_TASK_CONTEXT_VALID; + task_context->context_type = SCU_TASK_CONTEXT_TYPE; + + /* 04h */ + task_context->remote_node_index = idev->rnc.remote_node_index; + task_context->command_code = 0; + task_context->task_type = SCU_TASK_TYPE_SMP_REQUEST; + + /* 08h */ + task_context->link_layer_control = 0; + task_context->do_not_dma_ssp_good_response = 1; + task_context->strict_ordering = 0; + task_context->control_frame = 1; + task_context->timeout_enable = 0; + task_context->block_guard_enable = 0; + + /* 0ch */ + task_context->address_modifier = 0; + + /* 10h */ + task_context->ssp_command_iu_length = req_len; + + /* 14h */ + task_context->transfer_length_bytes = 0; + + /* + * 18h ~ 30h, protocol specific + * since commandIU has been build by framework at this point, we just + * copy the frist DWord from command IU to this location. */ + memcpy(&task_context->type.smp, &cmd, sizeof(u32)); + + /* + * 40h + * "For SMP you could program it to zero. We would prefer that way + * so that done code will be consistent." - Venki + */ + task_context->task_phase = 0; + + ireq->post_context = (SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC | + (ISCI_PEG << SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_SHIFT) | + (iport->physical_port_index << + SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT) | + ISCI_TAG_TCI(ireq->io_tag)); + /* + * Copy the physical address for the command buffer to the SCU Task + * Context command buffer should not contain command header. + */ + task_context->command_iu_upper = upper_32_bits(sg_dma_address(sg)); + task_context->command_iu_lower = lower_32_bits(sg_dma_address(sg) + sizeof(u32)); + + /* SMP response comes as UF, so no need to set response IU address. */ + task_context->response_iu_upper = 0; + task_context->response_iu_lower = 0; + + sci_change_state(&ireq->sm, SCI_REQ_CONSTRUCTED); + + return SCI_SUCCESS; +} + +/* + * isci_smp_request_build() - This function builds the smp request. + * @ireq: This parameter points to the isci_request allocated in the + * request construct function. + * + * SCI_SUCCESS on successfull completion, or specific failure code. + */ +static enum sci_status isci_smp_request_build(struct isci_request *ireq) +{ + struct sas_task *task = isci_request_access_task(ireq); + struct device *dev = &ireq->isci_host->pdev->dev; + enum sci_status status = SCI_FAILURE; + + status = sci_io_request_construct_smp(dev, ireq, task); + if (status != SCI_SUCCESS) + dev_dbg(&ireq->isci_host->pdev->dev, + "%s: failed with status = %d\n", + __func__, + status); + + return status; +} + +/** + * isci_io_request_build() - This function builds the io request object. + * @ihost: This parameter specifies the ISCI host object + * @request: This parameter points to the isci_request object allocated in the + * request construct function. + * @sci_device: This parameter is the handle for the sci core's remote device + * object that is the destination for this request. + * + * SCI_SUCCESS on successfull completion, or specific failure code. + */ +static enum sci_status isci_io_request_build(struct isci_host *ihost, + struct isci_request *request, + struct isci_remote_device *idev) +{ + enum sci_status status = SCI_SUCCESS; + struct sas_task *task = isci_request_access_task(request); + + dev_dbg(&ihost->pdev->dev, + "%s: idev = 0x%p; request = %p, " + "num_scatter = %d\n", + __func__, + idev, + request, + task->num_scatter); + + /* map the sgl addresses, if present. + * libata does the mapping for sata devices + * before we get the request. + */ + if (task->num_scatter && + !sas_protocol_ata(task->task_proto) && + !(SAS_PROTOCOL_SMP & task->task_proto)) { + + request->num_sg_entries = dma_map_sg( + &ihost->pdev->dev, + task->scatter, + task->num_scatter, + task->data_dir + ); + + if (request->num_sg_entries == 0) + return SCI_FAILURE_INSUFFICIENT_RESOURCES; + } + + status = sci_io_request_construct(ihost, idev, request); + + if (status != SCI_SUCCESS) { + dev_dbg(&ihost->pdev->dev, + "%s: failed request construct\n", + __func__); + return SCI_FAILURE; + } + + switch (task->task_proto) { + case SAS_PROTOCOL_SMP: + status = isci_smp_request_build(request); + break; + case SAS_PROTOCOL_SSP: + status = isci_request_ssp_request_construct(request); + break; + case SAS_PROTOCOL_SATA: + case SAS_PROTOCOL_STP: + case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP: + status = isci_request_stp_request_construct(request); + break; + default: + dev_dbg(&ihost->pdev->dev, + "%s: unknown protocol\n", __func__); + return SCI_FAILURE; + } + + return SCI_SUCCESS; +} + +static struct isci_request *isci_request_from_tag(struct isci_host *ihost, u16 tag) +{ + struct isci_request *ireq; + + ireq = ihost->reqs[ISCI_TAG_TCI(tag)]; + ireq->io_tag = tag; + ireq->io_request_completion = NULL; + ireq->flags = 0; + ireq->num_sg_entries = 0; + INIT_LIST_HEAD(&ireq->completed_node); + INIT_LIST_HEAD(&ireq->dev_node); + isci_request_change_state(ireq, allocated); + + return ireq; +} + +static struct isci_request *isci_io_request_from_tag(struct isci_host *ihost, + struct sas_task *task, + u16 tag) +{ + struct isci_request *ireq; + + ireq = isci_request_from_tag(ihost, tag); + ireq->ttype_ptr.io_task_ptr = task; + ireq->ttype = io_task; + task->lldd_task = ireq; + + return ireq; +} + +struct isci_request *isci_tmf_request_from_tag(struct isci_host *ihost, + struct isci_tmf *isci_tmf, + u16 tag) +{ + struct isci_request *ireq; + + ireq = isci_request_from_tag(ihost, tag); + ireq->ttype_ptr.tmf_task_ptr = isci_tmf; + ireq->ttype = tmf_task; + + return ireq; +} + +int isci_request_execute(struct isci_host *ihost, struct isci_remote_device *idev, + struct sas_task *task, u16 tag) +{ + enum sci_status status = SCI_FAILURE_UNSUPPORTED_PROTOCOL; + struct isci_request *ireq; + unsigned long flags; + int ret = 0; + + /* do common allocation and init of request object. */ + ireq = isci_io_request_from_tag(ihost, task, tag); + + status = isci_io_request_build(ihost, ireq, idev); + if (status != SCI_SUCCESS) { + dev_dbg(&ihost->pdev->dev, + "%s: request_construct failed - status = 0x%x\n", + __func__, + status); + return status; + } + + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (test_bit(IDEV_IO_NCQERROR, &idev->flags)) { + + if (isci_task_is_ncq_recovery(task)) { + + /* The device is in an NCQ recovery state. Issue the + * request on the task side. Note that it will + * complete on the I/O request side because the + * request was built that way (ie. + * ireq->is_task_management_request is false). + */ + status = sci_controller_start_task(ihost, + idev, + ireq); + } else { + status = SCI_FAILURE; + } + } else { + /* send the request, let the core assign the IO TAG. */ + status = sci_controller_start_io(ihost, idev, + ireq); + } + + if (status != SCI_SUCCESS && + status != SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED) { + dev_dbg(&ihost->pdev->dev, + "%s: failed request start (0x%x)\n", + __func__, status); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + return status; + } + + /* Either I/O started OK, or the core has signaled that + * the device needs a target reset. + * + * In either case, hold onto the I/O for later. + * + * Update it's status and add it to the list in the + * remote device object. + */ + list_add(&ireq->dev_node, &idev->reqs_in_process); + + if (status == SCI_SUCCESS) { + isci_request_change_state(ireq, started); + } else { + /* The request did not really start in the + * hardware, so clear the request handle + * here so no terminations will be done. + */ + set_bit(IREQ_TERMINATED, &ireq->flags); + isci_request_change_state(ireq, completed); + } + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + if (status == + SCI_FAILURE_REMOTE_DEVICE_RESET_REQUIRED) { + /* Signal libsas that we need the SCSI error + * handler thread to work on this I/O and that + * we want a device reset. + */ + spin_lock_irqsave(&task->task_state_lock, flags); + task->task_state_flags |= SAS_TASK_NEED_DEV_RESET; + spin_unlock_irqrestore(&task->task_state_lock, flags); + + /* Cause this task to be scheduled in the SCSI error + * handler thread. + */ + isci_execpath_callback(ihost, task, + sas_task_abort); + + /* Change the status, since we are holding + * the I/O until it is managed by the SCSI + * error handler. + */ + status = SCI_SUCCESS; + } + + return ret; +} diff --git a/drivers/scsi/isci/request.h b/drivers/scsi/isci/request.h new file mode 100644 index 0000000..7a1d5a9 --- /dev/null +++ b/drivers/scsi/isci/request.h @@ -0,0 +1,448 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _ISCI_REQUEST_H_ +#define _ISCI_REQUEST_H_ + +#include "isci.h" +#include "host.h" +#include "scu_task_context.h" + +/** + * struct isci_request_status - This enum defines the possible states of an I/O + * request. + * + * + */ +enum isci_request_status { + unallocated = 0x00, + allocated = 0x01, + started = 0x02, + completed = 0x03, + aborting = 0x04, + aborted = 0x05, + terminating = 0x06, + dead = 0x07 +}; + +enum task_type { + io_task = 0, + tmf_task = 1 +}; + +enum sci_request_protocol { + SCIC_NO_PROTOCOL, + SCIC_SMP_PROTOCOL, + SCIC_SSP_PROTOCOL, + SCIC_STP_PROTOCOL +}; /* XXX remove me, use sas_task.{dev|task_proto} instead */; + +/** + * isci_stp_request - extra request infrastructure to handle pio/atapi protocol + * @pio_len - number of bytes requested at PIO setup + * @status - pio setup ending status value to tell us if we need + * to wait for another fis or if the transfer is complete. Upon + * receipt of a d2h fis this will be the status field of that fis. + * @sgl - track pio transfer progress as we iterate through the sgl + * @device_cdb_len - atapi device advertises it's transfer constraints at setup + */ +struct isci_stp_request { + u32 pio_len; + u8 status; + + struct isci_stp_pio_sgl { + int index; + u8 set; + u32 offset; + } sgl; + u32 device_cdb_len; +}; + +struct isci_request { + enum isci_request_status status; + #define IREQ_COMPLETE_IN_TARGET 0 + #define IREQ_TERMINATED 1 + #define IREQ_TMF 2 + #define IREQ_ACTIVE 3 + unsigned long flags; + /* XXX kill ttype and ttype_ptr, allocate full sas_task */ + enum task_type ttype; + union ttype_ptr_union { + struct sas_task *io_task_ptr; /* When ttype==io_task */ + struct isci_tmf *tmf_task_ptr; /* When ttype==tmf_task */ + } ttype_ptr; + struct isci_host *isci_host; + /* For use in the requests_to_{complete|abort} lists: */ + struct list_head completed_node; + /* For use in the reqs_in_process list: */ + struct list_head dev_node; + spinlock_t state_lock; + dma_addr_t request_daddr; + dma_addr_t zero_scatter_daddr; + unsigned int num_sg_entries; + /* Note: "io_request_completion" is completed in two different ways + * depending on whether this is a TMF or regular request. + * - TMF requests are completed in the thread that started them; + * - regular requests are completed in the request completion callback + * function. + * This difference in operation allows the aborter of a TMF request + * to be sure that once the TMF request completes, the I/O that the + * TMF was aborting is guaranteed to have completed. + * + * XXX kill io_request_completion + */ + struct completion *io_request_completion; + struct sci_base_state_machine sm; + struct isci_host *owning_controller; + struct isci_remote_device *target_device; + u16 io_tag; + enum sci_request_protocol protocol; + u32 scu_status; /* hardware result */ + u32 sci_status; /* upper layer disposition */ + u32 post_context; + struct scu_task_context *tc; + /* could be larger with sg chaining */ + #define SCU_SGL_SIZE ((SCI_MAX_SCATTER_GATHER_ELEMENTS + 1) / 2) + struct scu_sgl_element_pair sg_table[SCU_SGL_SIZE] __attribute__ ((aligned(32))); + /* This field is a pointer to the stored rx frame data. It is used in + * STP internal requests and SMP response frames. If this field is + * non-NULL the saved frame must be released on IO request completion. + */ + u32 saved_rx_frame_index; + + union { + struct { + union { + struct ssp_cmd_iu cmd; + struct ssp_task_iu tmf; + }; + union { + struct ssp_response_iu rsp; + u8 rsp_buf[SSP_RESP_IU_MAX_SIZE]; + }; + } ssp; + struct { + struct smp_resp rsp; + } smp; + struct { + struct isci_stp_request req; + struct host_to_dev_fis cmd; + struct dev_to_host_fis rsp; + } stp; + }; +}; + +static inline struct isci_request *to_ireq(struct isci_stp_request *stp_req) +{ + struct isci_request *ireq; + + ireq = container_of(stp_req, typeof(*ireq), stp.req); + return ireq; +} + +/** + * enum sci_base_request_states - This enumeration depicts all the states for + * the common request state machine. + * + * + */ +enum sci_base_request_states { + /* + * Simply the initial state for the base request state machine. + */ + SCI_REQ_INIT, + + /* + * This state indicates that the request has been constructed. + * This state is entered from the INITIAL state. + */ + SCI_REQ_CONSTRUCTED, + + /* + * This state indicates that the request has been started. This state + * is entered from the CONSTRUCTED state. + */ + SCI_REQ_STARTED, + + SCI_REQ_STP_UDMA_WAIT_TC_COMP, + SCI_REQ_STP_UDMA_WAIT_D2H, + + SCI_REQ_STP_NON_DATA_WAIT_H2D, + SCI_REQ_STP_NON_DATA_WAIT_D2H, + + SCI_REQ_STP_SOFT_RESET_WAIT_H2D_ASSERTED, + SCI_REQ_STP_SOFT_RESET_WAIT_H2D_DIAG, + SCI_REQ_STP_SOFT_RESET_WAIT_D2H, + + /* + * While in this state the IO request object is waiting for the TC + * completion notification for the H2D Register FIS + */ + SCI_REQ_STP_PIO_WAIT_H2D, + + /* + * While in this state the IO request object is waiting for either a + * PIO Setup FIS or a D2H register FIS. The type of frame received is + * based on the result of the prior frame and line conditions. + */ + SCI_REQ_STP_PIO_WAIT_FRAME, + + /* + * While in this state the IO request object is waiting for a DATA + * frame from the device. + */ + SCI_REQ_STP_PIO_DATA_IN, + + /* + * While in this state the IO request object is waiting to transmit + * the next data frame to the device. + */ + SCI_REQ_STP_PIO_DATA_OUT, + + /* + * The AWAIT_TC_COMPLETION sub-state indicates that the started raw + * task management request is waiting for the transmission of the + * initial frame (i.e. command, task, etc.). + */ + SCI_REQ_TASK_WAIT_TC_COMP, + + /* + * This sub-state indicates that the started task management request + * is waiting for the reception of an unsolicited frame + * (i.e. response IU). + */ + SCI_REQ_TASK_WAIT_TC_RESP, + + /* + * This sub-state indicates that the started task management request + * is waiting for the reception of an unsolicited frame + * (i.e. response IU). + */ + SCI_REQ_SMP_WAIT_RESP, + + /* + * The AWAIT_TC_COMPLETION sub-state indicates that the started SMP + * request is waiting for the transmission of the initial frame + * (i.e. command, task, etc.). + */ + SCI_REQ_SMP_WAIT_TC_COMP, + + /* + * This state indicates that the request has completed. + * This state is entered from the STARTED state. This state is entered + * from the ABORTING state. + */ + SCI_REQ_COMPLETED, + + /* + * This state indicates that the request is in the process of being + * terminated/aborted. + * This state is entered from the CONSTRUCTED state. + * This state is entered from the STARTED state. + */ + SCI_REQ_ABORTING, + + /* + * Simply the final state for the base request state machine. + */ + SCI_REQ_FINAL, +}; + +enum sci_status sci_request_start(struct isci_request *ireq); +enum sci_status sci_io_request_terminate(struct isci_request *ireq); +enum sci_status +sci_io_request_event_handler(struct isci_request *ireq, + u32 event_code); +enum sci_status +sci_io_request_frame_handler(struct isci_request *ireq, + u32 frame_index); +enum sci_status +sci_task_request_terminate(struct isci_request *ireq); +extern enum sci_status +sci_request_complete(struct isci_request *ireq); +extern enum sci_status +sci_io_request_tc_completion(struct isci_request *ireq, u32 code); + +/* XXX open code in caller */ +static inline dma_addr_t +sci_io_request_get_dma_addr(struct isci_request *ireq, void *virt_addr) +{ + + char *requested_addr = (char *)virt_addr; + char *base_addr = (char *)ireq; + + BUG_ON(requested_addr < base_addr); + BUG_ON((requested_addr - base_addr) >= sizeof(*ireq)); + + return ireq->request_daddr + (requested_addr - base_addr); +} + +/** + * isci_request_change_state() - This function sets the status of the request + * object. + * @request: This parameter points to the isci_request object + * @status: This Parameter is the new status of the object + * + */ +static inline enum isci_request_status +isci_request_change_state(struct isci_request *isci_request, + enum isci_request_status status) +{ + enum isci_request_status old_state; + unsigned long flags; + + dev_dbg(&isci_request->isci_host->pdev->dev, + "%s: isci_request = %p, state = 0x%x\n", + __func__, + isci_request, + status); + + BUG_ON(isci_request == NULL); + + spin_lock_irqsave(&isci_request->state_lock, flags); + old_state = isci_request->status; + isci_request->status = status; + spin_unlock_irqrestore(&isci_request->state_lock, flags); + + return old_state; +} + +/** + * isci_request_change_started_to_newstate() - This function sets the status of + * the request object. + * @request: This parameter points to the isci_request object + * @status: This Parameter is the new status of the object + * + * state previous to any change. + */ +static inline enum isci_request_status +isci_request_change_started_to_newstate(struct isci_request *isci_request, + struct completion *completion_ptr, + enum isci_request_status newstate) +{ + enum isci_request_status old_state; + unsigned long flags; + + spin_lock_irqsave(&isci_request->state_lock, flags); + + old_state = isci_request->status; + + if (old_state == started || old_state == aborting) { + BUG_ON(isci_request->io_request_completion != NULL); + + isci_request->io_request_completion = completion_ptr; + isci_request->status = newstate; + } + + spin_unlock_irqrestore(&isci_request->state_lock, flags); + + dev_dbg(&isci_request->isci_host->pdev->dev, + "%s: isci_request = %p, old_state = 0x%x\n", + __func__, + isci_request, + old_state); + + return old_state; +} + +/** + * isci_request_change_started_to_aborted() - This function sets the status of + * the request object. + * @request: This parameter points to the isci_request object + * @completion_ptr: This parameter is saved as the kernel completion structure + * signalled when the old request completes. + * + * state previous to any change. + */ +static inline enum isci_request_status +isci_request_change_started_to_aborted(struct isci_request *isci_request, + struct completion *completion_ptr) +{ + return isci_request_change_started_to_newstate(isci_request, + completion_ptr, + aborted); +} + +#define isci_request_access_task(req) ((req)->ttype_ptr.io_task_ptr) + +#define isci_request_access_tmf(req) ((req)->ttype_ptr.tmf_task_ptr) + +struct isci_request *isci_tmf_request_from_tag(struct isci_host *ihost, + struct isci_tmf *isci_tmf, + u16 tag); +int isci_request_execute(struct isci_host *ihost, struct isci_remote_device *idev, + struct sas_task *task, u16 tag); +void isci_terminate_pending_requests(struct isci_host *ihost, + struct isci_remote_device *idev); +enum sci_status +sci_task_request_construct(struct isci_host *ihost, + struct isci_remote_device *idev, + u16 io_tag, + struct isci_request *ireq); +enum sci_status +sci_task_request_construct_ssp(struct isci_request *ireq); +enum sci_status +sci_task_request_construct_sata(struct isci_request *ireq); +void sci_smp_request_copy_response(struct isci_request *ireq); + +static inline int isci_task_is_ncq_recovery(struct sas_task *task) +{ + return (sas_protocol_ata(task->task_proto) && + task->ata_task.fis.command == ATA_CMD_READ_LOG_EXT && + task->ata_task.fis.lbal == ATA_LOG_SATA_NCQ); + +} + +#endif /* !defined(_ISCI_REQUEST_H_) */ diff --git a/drivers/scsi/isci/sas.h b/drivers/scsi/isci/sas.h new file mode 100644 index 0000000..462b151 --- /dev/null +++ b/drivers/scsi/isci/sas.h @@ -0,0 +1,219 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCI_SAS_H_ +#define _SCI_SAS_H_ + +#include <linux/kernel.h> + +/* + * SATA FIS Types These constants depict the various SATA FIS types devined in + * the serial ATA specification. + * XXX: This needs to go into <scsi/sas.h> + */ +#define FIS_REGH2D 0x27 +#define FIS_REGD2H 0x34 +#define FIS_SETDEVBITS 0xA1 +#define FIS_DMA_ACTIVATE 0x39 +#define FIS_DMA_SETUP 0x41 +#define FIS_BIST_ACTIVATE 0x58 +#define FIS_PIO_SETUP 0x5F +#define FIS_DATA 0x46 + +/**************************************************************************/ +#define SSP_RESP_IU_MAX_SIZE 280 + +/* + * contents of the SSP COMMAND INFORMATION UNIT. + * For specific information on each of these individual fields please + * reference the SAS specification SSP transport layer section. + * XXX: This needs to go into <scsi/sas.h> + */ +struct ssp_cmd_iu { + u8 LUN[8]; + u8 add_cdb_len:6; + u8 _r_a:2; + u8 _r_b; + u8 en_fburst:1; + u8 task_prio:4; + u8 task_attr:3; + u8 _r_c; + + u8 cdb[16]; +} __packed; + +/* + * contents of the SSP TASK INFORMATION UNIT. + * For specific information on each of these individual fields please + * reference the SAS specification SSP transport layer section. + * XXX: This needs to go into <scsi/sas.h> + */ +struct ssp_task_iu { + u8 LUN[8]; + u8 _r_a; + u8 task_func; + u8 _r_b[4]; + u16 task_tag; + u8 _r_c[12]; +} __packed; + + +/* + * struct smp_req_phy_id - This structure defines the contents of + * an SMP Request that is comprised of the struct smp_request_header and a + * phy identifier. + * Examples: SMP_REQUEST_DISCOVER, SMP_REQUEST_REPORT_PHY_SATA. + * + * For specific information on each of these individual fields please reference + * the SAS specification. + */ +struct smp_req_phy_id { + u8 _r_a[4]; /* bytes 4-7 */ + + u8 ign_zone_grp:1; /* byte 8 */ + u8 _r_b:7; + + u8 phy_id; /* byte 9 */ + u8 _r_c; /* byte 10 */ + u8 _r_d; /* byte 11 */ +} __packed; + +/* + * struct smp_req_config_route_info - This structure defines the + * contents of an SMP Configure Route Information request. + * + * For specific information on each of these individual fields please reference + * the SAS specification. + */ +struct smp_req_conf_rtinfo { + u16 exp_change_cnt; /* bytes 4-5 */ + u8 exp_rt_idx_hi; /* byte 6 */ + u8 exp_rt_idx; /* byte 7 */ + + u8 _r_a; /* byte 8 */ + u8 phy_id; /* byte 9 */ + u16 _r_b; /* bytes 10-11 */ + + u8 _r_c:7; /* byte 12 */ + u8 dis_rt_entry:1; + u8 _r_d[3]; /* bytes 13-15 */ + + u8 rt_sas_addr[8]; /* bytes 16-23 */ + u8 _r_e[16]; /* bytes 24-39 */ +} __packed; + +/* + * struct smp_req_phycntl - This structure defines the contents of an + * SMP Phy Controller request. + * + * For specific information on each of these individual fields please reference + * the SAS specification. + */ +struct smp_req_phycntl { + u16 exp_change_cnt; /* byte 4-5 */ + + u8 _r_a[3]; /* bytes 6-8 */ + + u8 phy_id; /* byte 9 */ + u8 phy_op; /* byte 10 */ + + u8 upd_pathway:1; /* byte 11 */ + u8 _r_b:7; + + u8 _r_c[12]; /* byte 12-23 */ + + u8 att_dev_name[8]; /* byte 24-31 */ + + u8 _r_d:4; /* byte 32 */ + u8 min_linkrate:4; + + u8 _r_e:4; /* byte 33 */ + u8 max_linkrate:4; + + u8 _r_f[2]; /* byte 34-35 */ + + u8 pathway:4; /* byte 36 */ + u8 _r_g:4; + + u8 _r_h[3]; /* bytes 37-39 */ +} __packed; + +/* + * struct smp_req - This structure simply unionizes the existing request + * structures into a common request type. + * + * XXX: This data structure may need to go to scsi/sas.h + */ +struct smp_req { + u8 type; /* byte 0 */ + u8 func; /* byte 1 */ + u8 alloc_resp_len; /* byte 2 */ + u8 req_len; /* byte 3 */ + u8 req_data[0]; +} __packed; + +#define SMP_RESP_HDR_SZ 4 + +/* + * struct sci_sas_address - This structure depicts how a SAS address is + * represented by SCI. + * XXX convert this to u8 [SAS_ADDR_SIZE] like the rest of libsas + * + */ +struct sci_sas_address { + u32 high; + u32 low; +}; +#endif diff --git a/drivers/scsi/isci/scu_completion_codes.h b/drivers/scsi/isci/scu_completion_codes.h new file mode 100644 index 0000000..c8b329c --- /dev/null +++ b/drivers/scsi/isci/scu_completion_codes.h @@ -0,0 +1,283 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCU_COMPLETION_CODES_HEADER_ +#define _SCU_COMPLETION_CODES_HEADER_ + +/** + * This file contains the constants and macros for the SCU hardware completion + * codes. + * + * + */ + +#define SCU_COMPLETION_TYPE_SHIFT 28 +#define SCU_COMPLETION_TYPE_MASK 0x70000000 + +/** + * SCU_COMPLETION_TYPE() - + * + * This macro constructs an SCU completion type + */ +#define SCU_COMPLETION_TYPE(type) \ + ((u32)(type) << SCU_COMPLETION_TYPE_SHIFT) + +/** + * SCU_COMPLETION_TYPE() - + * + * These macros contain the SCU completion types SCU_COMPLETION_TYPE + */ +#define SCU_COMPLETION_TYPE_TASK SCU_COMPLETION_TYPE(0) +#define SCU_COMPLETION_TYPE_SDMA SCU_COMPLETION_TYPE(1) +#define SCU_COMPLETION_TYPE_UFI SCU_COMPLETION_TYPE(2) +#define SCU_COMPLETION_TYPE_EVENT SCU_COMPLETION_TYPE(3) +#define SCU_COMPLETION_TYPE_NOTIFY SCU_COMPLETION_TYPE(4) + +/** + * + * + * These constants provide the shift and mask values for the various parts of + * an SCU completion code. + */ +#define SCU_COMPLETION_STATUS_MASK 0x0FFC0000 +#define SCU_COMPLETION_TL_STATUS_MASK 0x0FC00000 +#define SCU_COMPLETION_TL_STATUS_SHIFT 22 +#define SCU_COMPLETION_SDMA_STATUS_MASK 0x003C0000 +#define SCU_COMPLETION_PEG_MASK 0x00010000 +#define SCU_COMPLETION_PORT_MASK 0x00007000 +#define SCU_COMPLETION_PE_MASK SCU_COMPLETION_PORT_MASK +#define SCU_COMPLETION_PE_SHIFT 12 +#define SCU_COMPLETION_INDEX_MASK 0x00000FFF + +/** + * SCU_GET_COMPLETION_TYPE() - + * + * This macro returns the SCU completion type. + */ +#define SCU_GET_COMPLETION_TYPE(completion_code) \ + ((completion_code) & SCU_COMPLETION_TYPE_MASK) + +/** + * SCU_GET_COMPLETION_STATUS() - + * + * This macro returns the SCU completion status. + */ +#define SCU_GET_COMPLETION_STATUS(completion_code) \ + ((completion_code) & SCU_COMPLETION_STATUS_MASK) + +/** + * SCU_GET_COMPLETION_TL_STATUS() - + * + * This macro returns the transport layer completion status. + */ +#define SCU_GET_COMPLETION_TL_STATUS(completion_code) \ + ((completion_code) & SCU_COMPLETION_TL_STATUS_MASK) + +/** + * SCU_MAKE_COMPLETION_STATUS() - + * + * This macro takes a completion code and performs the shift and mask + * operations to turn it into a completion code that can be compared to a + * SCU_GET_COMPLETION_TL_STATUS. + */ +#define SCU_MAKE_COMPLETION_STATUS(completion_code) \ + ((u32)(completion_code) << SCU_COMPLETION_TL_STATUS_SHIFT) + +/** + * SCU_NORMALIZE_COMPLETION_STATUS() - + * + * This macro takes a SCU_GET_COMPLETION_TL_STATUS and normalizes it for a + * return code. + */ +#define SCU_NORMALIZE_COMPLETION_STATUS(completion_code) \ + (\ + ((completion_code) & SCU_COMPLETION_TL_STATUS_MASK) \ + >> SCU_COMPLETION_TL_STATUS_SHIFT \ + ) + +/** + * SCU_GET_COMPLETION_SDMA_STATUS() - + * + * This macro returns the SDMA completion status. + */ +#define SCU_GET_COMPLETION_SDMA_STATUS(completion_code) \ + ((completion_code) & SCU_COMPLETION_SDMA_STATUS_MASK) + +/** + * SCU_GET_COMPLETION_PEG() - + * + * This macro returns the Protocol Engine Group from the completion code. + */ +#define SCU_GET_COMPLETION_PEG(completion_code) \ + ((completion_code) & SCU_COMPLETION_PEG_MASK) + +/** + * SCU_GET_COMPLETION_PORT() - + * + * This macro reuturns the logical port index from the completion code. + */ +#define SCU_GET_COMPLETION_PORT(completion_code) \ + ((completion_code) & SCU_COMPLETION_PORT_MASK) + +/** + * SCU_GET_PROTOCOL_ENGINE_INDEX() - + * + * This macro returns the PE index from the completion code. + */ +#define SCU_GET_PROTOCOL_ENGINE_INDEX(completion_code) \ + (((completion_code) & SCU_COMPLETION_PE_MASK) >> SCU_COMPLETION_PE_SHIFT) + +/** + * SCU_GET_COMPLETION_INDEX() - + * + * This macro returns the index of the completion which is either a TCi or an + * RNi depending on the completion type. + */ +#define SCU_GET_COMPLETION_INDEX(completion_code) \ + ((completion_code) & SCU_COMPLETION_INDEX_MASK) + +#define SCU_UNSOLICITED_FRAME_MASK 0x0FFF0000 +#define SCU_UNSOLICITED_FRAME_SHIFT 16 + +/** + * SCU_GET_FRAME_INDEX() - + * + * This macro returns a normalized frame index from an unsolicited frame + * completion. + */ +#define SCU_GET_FRAME_INDEX(completion_code) \ + (\ + ((completion_code) & SCU_UNSOLICITED_FRAME_MASK) \ + >> SCU_UNSOLICITED_FRAME_SHIFT \ + ) + +#define SCU_UNSOLICITED_FRAME_ERROR_MASK 0x00008000 + +/** + * SCU_GET_FRAME_ERROR() - + * + * This macro returns a zero (0) value if there is no frame error otherwise it + * returns non-zero (!0). + */ +#define SCU_GET_FRAME_ERROR(completion_code) \ + ((completion_code) & SCU_UNSOLICITED_FRAME_ERROR_MASK) + +/** + * + * + * These constants represent normalized completion codes which must be shifted + * 18 bits to match it with the hardware completion code. In a 16-bit compiler, + * immediate constants are 16-bit values (the size of an int). If we shift + * those by 18 bits, we completely lose the value. To ensure the value is a + * 32-bit value like we want, each immediate value must be cast to a u32. + */ +#define SCU_TASK_DONE_GOOD ((u32)0x00) +#define SCU_TASK_DONE_CRC_ERR ((u32)0x14) +#define SCU_TASK_DONE_CHECK_RESPONSE ((u32)0x14) +#define SCU_TASK_DONE_GEN_RESPONSE ((u32)0x15) +#define SCU_TASK_DONE_NAK_CMD_ERR ((u32)0x16) +#define SCU_TASK_DONE_CMD_LL_R_ERR ((u32)0x16) +#define SCU_TASK_DONE_LL_R_ERR ((u32)0x17) +#define SCU_TASK_DONE_ACK_NAK_TO ((u32)0x17) +#define SCU_TASK_DONE_LL_PERR ((u32)0x18) +#define SCU_TASK_DONE_LL_SY_TERM ((u32)0x19) +#define SCU_TASK_DONE_NAK_ERR ((u32)0x19) +#define SCU_TASK_DONE_LL_LF_TERM ((u32)0x1A) +#define SCU_TASK_DONE_DATA_LEN_ERR ((u32)0x1A) +#define SCU_TASK_DONE_LL_CL_TERM ((u32)0x1B) +#define SCU_TASK_DONE_LL_ABORT_ERR ((u32)0x1B) +#define SCU_TASK_DONE_SEQ_INV_TYPE ((u32)0x1C) +#define SCU_TASK_DONE_UNEXP_XR ((u32)0x1C) +#define SCU_TASK_DONE_INV_FIS_TYPE ((u32)0x1D) +#define SCU_TASK_DONE_XR_IU_LEN_ERR ((u32)0x1D) +#define SCU_TASK_DONE_INV_FIS_LEN ((u32)0x1E) +#define SCU_TASK_DONE_XR_WD_LEN ((u32)0x1E) +#define SCU_TASK_DONE_SDMA_ERR ((u32)0x1F) +#define SCU_TASK_DONE_OFFSET_ERR ((u32)0x20) +#define SCU_TASK_DONE_MAX_PLD_ERR ((u32)0x21) +#define SCU_TASK_DONE_EXCESS_DATA ((u32)0x22) +#define SCU_TASK_DONE_LF_ERR ((u32)0x23) +#define SCU_TASK_DONE_UNEXP_FIS ((u32)0x24) +#define SCU_TASK_DONE_UNEXP_RESP ((u32)0x24) +#define SCU_TASK_DONE_EARLY_RESP ((u32)0x25) +#define SCU_TASK_DONE_SMP_RESP_TO_ERR ((u32)0x26) +#define SCU_TASK_DONE_DMASETUP_DIRERR ((u32)0x27) +#define SCU_TASK_DONE_SMP_UFI_ERR ((u32)0x27) +#define SCU_TASK_DONE_XFERCNT_ERR ((u32)0x28) +#define SCU_TASK_DONE_SMP_FRM_TYPE_ERR ((u32)0x28) +#define SCU_TASK_DONE_SMP_LL_RX_ERR ((u32)0x29) +#define SCU_TASK_DONE_RESP_LEN_ERR ((u32)0x2A) +#define SCU_TASK_DONE_UNEXP_DATA ((u32)0x2B) +#define SCU_TASK_DONE_OPEN_FAIL ((u32)0x2C) +#define SCU_TASK_DONE_UNEXP_SDBFIS ((u32)0x2D) +#define SCU_TASK_DONE_REG_ERR ((u32)0x2E) +#define SCU_TASK_DONE_SDB_ERR ((u32)0x2F) +#define SCU_TASK_DONE_TASK_ABORT ((u32)0x30) +#define SCU_TASK_DONE_CMD_SDMA_ERR ((U32)0x32) +#define SCU_TASK_DONE_CMD_LL_ABORT_ERR ((U32)0x33) +#define SCU_TASK_OPEN_REJECT_WRONG_DESTINATION ((u32)0x34) +#define SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_1 ((u32)0x35) +#define SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_2 ((u32)0x36) +#define SCU_TASK_OPEN_REJECT_RESERVED_ABANDON_3 ((u32)0x37) +#define SCU_TASK_OPEN_REJECT_BAD_DESTINATION ((u32)0x38) +#define SCU_TASK_OPEN_REJECT_ZONE_VIOLATION ((u32)0x39) +#define SCU_TASK_DONE_VIIT_ENTRY_NV ((u32)0x3A) +#define SCU_TASK_DONE_IIT_ENTRY_NV ((u32)0x3B) +#define SCU_TASK_DONE_RNCNV_OUTBOUND ((u32)0x3C) +#define SCU_TASK_OPEN_REJECT_STP_RESOURCES_BUSY ((u32)0x3D) +#define SCU_TASK_OPEN_REJECT_PROTOCOL_NOT_SUPPORTED ((u32)0x3E) +#define SCU_TASK_OPEN_REJECT_CONNECTION_RATE_NOT_SUPPORTED ((u32)0x3F) + +#endif /* _SCU_COMPLETION_CODES_HEADER_ */ diff --git a/drivers/scsi/isci/scu_event_codes.h b/drivers/scsi/isci/scu_event_codes.h new file mode 100644 index 0000000..36a945a --- /dev/null +++ b/drivers/scsi/isci/scu_event_codes.h @@ -0,0 +1,336 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __SCU_EVENT_CODES_HEADER__ +#define __SCU_EVENT_CODES_HEADER__ + +/** + * This file contains the constants and macros for the SCU event codes. + * + * + */ + +#define SCU_EVENT_TYPE_CODE_SHIFT 24 +#define SCU_EVENT_TYPE_CODE_MASK 0x0F000000 + +#define SCU_EVENT_SPECIFIC_CODE_SHIFT 18 +#define SCU_EVENT_SPECIFIC_CODE_MASK 0x00FC0000 + +#define SCU_EVENT_CODE_MASK \ + (SCU_EVENT_TYPE_CODE_MASK | SCU_EVENT_SPECIFIC_CODE_MASK) + +/** + * SCU_EVENT_TYPE() - + * + * This macro constructs an SCU event type from the type value. + */ +#define SCU_EVENT_TYPE(type) \ + ((u32)(type) << SCU_EVENT_TYPE_CODE_SHIFT) + +/** + * SCU_EVENT_SPECIFIC() - + * + * This macro constructs an SCU event specifier from the code value. + */ +#define SCU_EVENT_SPECIFIC(code) \ + ((u32)(code) << SCU_EVENT_SPECIFIC_CODE_SHIFT) + +/** + * SCU_EVENT_MESSAGE() - + * + * This macro constructs a combines an SCU event type and SCU event specifier + * from the type and code values. + */ +#define SCU_EVENT_MESSAGE(type, code) \ + ((type) | SCU_EVENT_SPECIFIC(code)) + +/** + * SCU_EVENT_TYPE() - + * + * SCU_EVENT_TYPES + */ +#define SCU_EVENT_TYPE_SMU_COMMAND_ERROR SCU_EVENT_TYPE(0x08) +#define SCU_EVENT_TYPE_SMU_PCQ_ERROR SCU_EVENT_TYPE(0x09) +#define SCU_EVENT_TYPE_SMU_ERROR SCU_EVENT_TYPE(0x00) +#define SCU_EVENT_TYPE_TRANSPORT_ERROR SCU_EVENT_TYPE(0x01) +#define SCU_EVENT_TYPE_BROADCAST_CHANGE SCU_EVENT_TYPE(0x02) +#define SCU_EVENT_TYPE_OSSP_EVENT SCU_EVENT_TYPE(0x03) +#define SCU_EVENT_TYPE_FATAL_MEMORY_ERROR SCU_EVENT_TYPE(0x0F) +#define SCU_EVENT_TYPE_RNC_SUSPEND_TX SCU_EVENT_TYPE(0x04) +#define SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX SCU_EVENT_TYPE(0x05) +#define SCU_EVENT_TYPE_RNC_OPS_MISC SCU_EVENT_TYPE(0x06) +#define SCU_EVENT_TYPE_PTX_SCHEDULE_EVENT SCU_EVENT_TYPE(0x07) +#define SCU_EVENT_TYPE_ERR_CNT_EVENT SCU_EVENT_TYPE(0x0A) + +/** + * + * + * SCU_EVENT_SPECIFIERS + */ +#define SCU_EVENT_SPECIFIER_DRIVER_SUSPEND 0x20 +#define SCU_EVENT_SPECIFIER_RNC_RELEASE 0x00 + +/** + * + * + * SMU_COMMAND_EVENTS + */ +#define SCU_EVENT_INVALID_CONTEXT_COMMAND \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_SMU_COMMAND_ERROR, 0x00) + +/** + * + * + * SMU_PCQ_EVENTS + */ +#define SCU_EVENT_UNCORRECTABLE_PCQ_ERROR \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_SMU_PCQ_ERROR, 0x00) + +/** + * + * + * SMU_EVENTS + */ +#define SCU_EVENT_UNCORRECTABLE_REGISTER_WRITE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_SMU_ERROR, 0x02) +#define SCU_EVENT_UNCORRECTABLE_REGISTER_READ \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_SMU_ERROR, 0x03) +#define SCU_EVENT_PCIE_INTERFACE_ERROR \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_SMU_ERROR, 0x04) +#define SCU_EVENT_FUNCTION_LEVEL_RESET \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_SMU_ERROR, 0x05) + +/** + * + * + * TRANSPORT_LEVEL_ERRORS + */ +#define SCU_EVENT_ACK_NAK_TIMEOUT_ERROR \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_TRANSPORT_ERROR, 0x00) + +/** + * + * + * BROADCAST_CHANGE_EVENTS + */ +#define SCU_EVENT_BROADCAST_CHANGE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x01) +#define SCU_EVENT_BROADCAST_RESERVED0 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x02) +#define SCU_EVENT_BROADCAST_RESERVED1 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x03) +#define SCU_EVENT_BROADCAST_SES \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x04) +#define SCU_EVENT_BROADCAST_EXPANDER \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x05) +#define SCU_EVENT_BROADCAST_AEN \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x06) +#define SCU_EVENT_BROADCAST_RESERVED3 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x07) +#define SCU_EVENT_BROADCAST_RESERVED4 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x08) +#define SCU_EVENT_PE_SUSPENDED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_BROADCAST_CHANGE, 0x09) + +/** + * + * + * OSSP_EVENTS + */ +#define SCU_EVENT_PORT_SELECTOR_DETECTED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x10) +#define SCU_EVENT_SENT_PORT_SELECTION \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x11) +#define SCU_EVENT_HARD_RESET_TRANSMITTED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x12) +#define SCU_EVENT_HARD_RESET_RECEIVED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x13) +#define SCU_EVENT_RECEIVED_IDENTIFY_TIMEOUT \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x15) +#define SCU_EVENT_LINK_FAILURE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x16) +#define SCU_EVENT_SATA_SPINUP_HOLD \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x17) +#define SCU_EVENT_SAS_15_SSC \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x18) +#define SCU_EVENT_SAS_15 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x19) +#define SCU_EVENT_SAS_30_SSC \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x1A) +#define SCU_EVENT_SAS_30 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x1B) +#define SCU_EVENT_SAS_60_SSC \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x1C) +#define SCU_EVENT_SAS_60 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x1D) +#define SCU_EVENT_SATA_15_SSC \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x1E) +#define SCU_EVENT_SATA_15 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x1F) +#define SCU_EVENT_SATA_30_SSC \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x20) +#define SCU_EVENT_SATA_30 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x21) +#define SCU_EVENT_SATA_60_SSC \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x22) +#define SCU_EVENT_SATA_60 \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x23) +#define SCU_EVENT_SAS_PHY_DETECTED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x24) +#define SCU_EVENT_SATA_PHY_DETECTED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_OSSP_EVENT, 0x25) + +/** + * + * + * FATAL_INTERNAL_MEMORY_ERROR_EVENTS + */ +#define SCU_EVENT_TSC_RNSC_UNCORRECTABLE_ERROR \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_FATAL_MEMORY_ERROR, 0x00) +#define SCU_EVENT_TC_RNC_UNCORRECTABLE_ERROR \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_FATAL_MEMORY_ERROR, 0x01) +#define SCU_EVENT_ZPT_UNCORRECTABLE_ERROR \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_FATAL_MEMORY_ERROR, 0x02) + +/** + * + * + * REMOTE_NODE_SUSPEND_EVENTS + */ +#define SCU_EVENT_TL_RNC_SUSPEND_TX \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_SUSPEND_TX, 0x00) +#define SCU_EVENT_TL_RNC_SUSPEND_TX_RX \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX, 0x00) +#define SCU_EVENT_DRIVER_POST_RNC_SUSPEND_TX \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_SUSPEND_TX, 0x20) +#define SCU_EVENT_DRIVER_POST_RNC_SUSPEND_TX_RX \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_SUSPEND_TX_RX, 0x20) + +/** + * + * + * REMOTE_NODE_MISC_EVENTS + */ +#define SCU_EVENT_POST_RCN_RELEASE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_OPS_MISC, SCU_EVENT_SPECIFIER_RNC_RELEASE) +#define SCU_EVENT_POST_IT_NEXUS_LOSS_TIMER_ENABLE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_OPS_MISC, 0x01) +#define SCU_EVENT_POST_IT_NEXUS_LOSS_TIMER_DISABLE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_OPS_MISC, 0x02) +#define SCU_EVENT_POST_RNC_COMPLETE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_OPS_MISC, 0x03) +#define SCU_EVENT_POST_RNC_INVALIDATE_COMPLETE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_RNC_OPS_MISC, 0x04) + +/** + * + * + * ERROR_COUNT_EVENT + */ +#define SCU_EVENT_RX_CREDIT_BLOCKED_RECEIVED \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_ERR_CNT_EVENT, 0x00) +#define SCU_EVENT_TX_DONE_CREDIT_TIMEOUT \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_ERR_CNT_EVENT, 0x01) +#define SCU_EVENT_RX_DONE_CREDIT_TIMEOUT \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_ERR_CNT_EVENT, 0x02) + +/** + * scu_get_event_type() - + * + * This macro returns the SCU event type from the event code. + */ +#define scu_get_event_type(event_code) \ + ((event_code) & SCU_EVENT_TYPE_CODE_MASK) + +/** + * scu_get_event_specifier() - + * + * This macro returns the SCU event specifier from the event code. + */ +#define scu_get_event_specifier(event_code) \ + ((event_code) & SCU_EVENT_SPECIFIC_CODE_MASK) + +/** + * scu_get_event_code() - + * + * This macro returns the combined SCU event type and SCU event specifier from + * the event code. + */ +#define scu_get_event_code(event_code) \ + ((event_code) & SCU_EVENT_CODE_MASK) + + +/** + * + * + * PTS_SCHEDULE_EVENT + */ +#define SCU_EVENT_SMP_RESPONSE_NO_PE \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_PTX_SCHEDULE_EVENT, 0x00) +#define SCU_EVENT_SPECIFIC_SMP_RESPONSE_NO_PE \ + scu_get_event_specifier(SCU_EVENT_SMP_RESPONSE_NO_PE) + +#define SCU_EVENT_TASK_TIMEOUT \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_PTX_SCHEDULE_EVENT, 0x01) +#define SCU_EVENT_SPECIFIC_TASK_TIMEOUT \ + scu_get_event_specifier(SCU_EVENT_TASK_TIMEOUT) + +#define SCU_EVENT_IT_NEXUS_TIMEOUT \ + SCU_EVENT_MESSAGE(SCU_EVENT_TYPE_PTX_SCHEDULE_EVENT, 0x02) +#define SCU_EVENT_SPECIFIC_IT_NEXUS_TIMEOUT \ + scu_get_event_specifier(SCU_EVENT_IT_NEXUS_TIMEOUT) + + +#endif /* __SCU_EVENT_CODES_HEADER__ */ diff --git a/drivers/scsi/isci/scu_remote_node_context.h b/drivers/scsi/isci/scu_remote_node_context.h new file mode 100644 index 0000000..33745ad --- /dev/null +++ b/drivers/scsi/isci/scu_remote_node_context.h @@ -0,0 +1,229 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __SCU_REMOTE_NODE_CONTEXT_HEADER__ +#define __SCU_REMOTE_NODE_CONTEXT_HEADER__ + +/** + * This file contains the structures and constatns used by the SCU hardware to + * describe a remote node context. + * + * + */ + +/** + * struct ssp_remote_node_context - This structure contains the SCU hardware + * definition for an SSP remote node. + * + * + */ +struct ssp_remote_node_context { + /* WORD 0 */ + + /** + * This field is the remote node index assigned for this remote node. All + * remote nodes must have a unique remote node index. The value of the remote + * node index can not exceed the maximum number of remote nodes reported in + * the SCU device context capacity register. + */ + u32 remote_node_index:12; + u32 reserved0_1:4; + + /** + * This field tells the SCU hardware how many simultaneous connections that + * this remote node will support. + */ + u32 remote_node_port_width:4; + + /** + * This field tells the SCU hardware which logical port to associate with this + * remote node. + */ + u32 logical_port_index:3; + u32 reserved0_2:5; + + /** + * This field will enable the I_T nexus loss timer for this remote node. + */ + u32 nexus_loss_timer_enable:1; + + /** + * This field is the for driver debug only and is not used. + */ + u32 check_bit:1; + + /** + * This field must be set to true when the hardware DMAs the remote node + * context to the hardware SRAM. When the remote node is being invalidated + * this field must be set to false. + */ + u32 is_valid:1; + + /** + * This field must be set to true. + */ + u32 is_remote_node_context:1; + + /* WORD 1 - 2 */ + + /** + * This is the low word of the remote device SAS Address + */ + u32 remote_sas_address_lo; + + /** + * This field is the high word of the remote device SAS Address + */ + u32 remote_sas_address_hi; + + /* WORD 3 */ + /** + * This field reprensets the function number assigned to this remote device. + * This value must match the virtual function number that is being used to + * communicate to the device. + */ + u32 function_number:8; + u32 reserved3_1:8; + + /** + * This field provides the driver a way to cheat on the arbitration wait time + * for this remote node. + */ + u32 arbitration_wait_time:16; + + /* WORD 4 */ + /** + * This field tells the SCU hardware how long this device may occupy the + * connection before it must be closed. + */ + u32 connection_occupancy_timeout:16; + + /** + * This field tells the SCU hardware how long to maintain a connection when + * there are no frames being transmitted on the link. + */ + u32 connection_inactivity_timeout:16; + + /* WORD 5 */ + /** + * This field allows the driver to cheat on the arbitration wait time for this + * remote node. + */ + u32 initial_arbitration_wait_time:16; + + /** + * This field is tells the hardware what to program for the connection rate in + * the open address frame. See the SAS spec for valid values. + */ + u32 oaf_connection_rate:4; + + /** + * This field tells the SCU hardware what to program for the features in the + * open address frame. See the SAS spec for valid values. + */ + u32 oaf_features:4; + + /** + * This field tells the SCU hardware what to use for the source zone group in + * the open address frame. See the SAS spec for more details on zoning. + */ + u32 oaf_source_zone_group:8; + + /* WORD 6 */ + /** + * This field tells the SCU hardware what to use as the more capibilities in + * the open address frame. See the SAS Spec for details. + */ + u32 oaf_more_compatibility_features; + + /* WORD 7 */ + u32 reserved7; + +}; + +/** + * struct stp_remote_node_context - This structure contains the SCU hardware + * definition for a STP remote node. + * + * STP Targets are not yet supported so this definition is a placeholder until + * we do support them. + */ +struct stp_remote_node_context { + /** + * Placeholder data for the STP remote node. + */ + u32 data[8]; + +}; + +/** + * This union combines the SAS and SATA remote node definitions. + * + * union scu_remote_node_context + */ +union scu_remote_node_context { + /** + * SSP Remote Node + */ + struct ssp_remote_node_context ssp; + + /** + * STP Remote Node + */ + struct stp_remote_node_context stp; + +}; + +#endif /* __SCU_REMOTE_NODE_CONTEXT_HEADER__ */ diff --git a/drivers/scsi/isci/scu_task_context.h b/drivers/scsi/isci/scu_task_context.h new file mode 100644 index 0000000..7df87d9 --- /dev/null +++ b/drivers/scsi/isci/scu_task_context.h @@ -0,0 +1,942 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCU_TASK_CONTEXT_H_ +#define _SCU_TASK_CONTEXT_H_ + +/** + * This file contains the structures and constants for the SCU hardware task + * context. + * + * + */ + + +/** + * enum scu_ssp_task_type - This enumberation defines the various SSP task + * types the SCU hardware will accept. The definition for the various task + * types the SCU hardware will accept can be found in the DS specification. + * + * + */ +typedef enum { + SCU_TASK_TYPE_IOREAD, /* /< IO READ direction or no direction */ + SCU_TASK_TYPE_IOWRITE, /* /< IO Write direction */ + SCU_TASK_TYPE_SMP_REQUEST, /* /< SMP Request type */ + SCU_TASK_TYPE_RESPONSE, /* /< Driver generated response frame (targt mode) */ + SCU_TASK_TYPE_RAW_FRAME, /* /< Raw frame request type */ + SCU_TASK_TYPE_PRIMITIVE /* /< Request for a primitive to be transmitted */ +} scu_ssp_task_type; + +/** + * enum scu_sata_task_type - This enumeration defines the various SATA task + * types the SCU hardware will accept. The definition for the various task + * types the SCU hardware will accept can be found in the DS specification. + * + * + */ +typedef enum { + SCU_TASK_TYPE_DMA_IN, /* /< Read request */ + SCU_TASK_TYPE_FPDMAQ_READ, /* /< NCQ read request */ + SCU_TASK_TYPE_PACKET_DMA_IN, /* /< Packet read request */ + SCU_TASK_TYPE_SATA_RAW_FRAME, /* /< Raw frame request */ + RESERVED_4, + RESERVED_5, + RESERVED_6, + RESERVED_7, + SCU_TASK_TYPE_DMA_OUT, /* /< Write request */ + SCU_TASK_TYPE_FPDMAQ_WRITE, /* /< NCQ write Request */ + SCU_TASK_TYPE_PACKET_DMA_OUT /* /< Packet write request */ +} scu_sata_task_type; + + +/** + * + * + * SCU_CONTEXT_TYPE + */ +#define SCU_TASK_CONTEXT_TYPE 0 +#define SCU_RNC_CONTEXT_TYPE 1 + +/** + * + * + * SCU_TASK_CONTEXT_VALIDITY + */ +#define SCU_TASK_CONTEXT_INVALID 0 +#define SCU_TASK_CONTEXT_VALID 1 + +/** + * + * + * SCU_COMMAND_CODE + */ +#define SCU_COMMAND_CODE_INITIATOR_NEW_TASK 0 +#define SCU_COMMAND_CODE_ACTIVE_TASK 1 +#define SCU_COMMAND_CODE_PRIMITIVE_SEQ_TASK 2 +#define SCU_COMMAND_CODE_TARGET_RAW_FRAMES 3 + +/** + * + * + * SCU_TASK_PRIORITY + */ +/** + * + * + * This priority is used when there is no priority request for this request. + */ +#define SCU_TASK_PRIORITY_NORMAL 0 + +/** + * + * + * This priority indicates that the task should be scheduled to the head of the + * queue. The task will NOT be executed if the TX is suspended for the remote + * node. + */ +#define SCU_TASK_PRIORITY_HEAD_OF_Q 1 + +/** + * + * + * This priority indicates that the task will be executed before all + * SCU_TASK_PRIORITY_NORMAL and SCU_TASK_PRIORITY_HEAD_OF_Q tasks. The task + * WILL be executed if the TX is suspended for the remote node. + */ +#define SCU_TASK_PRIORITY_HIGH 2 + +/** + * + * + * This task priority is reserved and should not be used. + */ +#define SCU_TASK_PRIORITY_RESERVED 3 + +#define SCU_TASK_INITIATOR_MODE 1 +#define SCU_TASK_TARGET_MODE 0 + +#define SCU_TASK_REGULAR 0 +#define SCU_TASK_ABORTED 1 + +/* direction bit defintion */ +/** + * + * + * SATA_DIRECTION + */ +#define SCU_SATA_WRITE_DATA_DIRECTION 0 +#define SCU_SATA_READ_DATA_DIRECTION 1 + +/** + * + * + * SCU_COMMAND_CONTEXT_MACROS These macros provide the mask and shift + * operations to construct the various SCU commands + */ +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_SHIFT 21 +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_MASK 0x00E00000 +#define scu_get_command_request_type(x) \ + ((x) & SCU_CONTEXT_COMMAND_REQUEST_TYPE_MASK) + +#define SCU_CONTEXT_COMMAND_REQUEST_SUBTYPE_SHIFT 18 +#define SCU_CONTEXT_COMMAND_REQUEST_SUBTYPE_MASK 0x001C0000 +#define scu_get_command_request_subtype(x) \ + ((x) & SCU_CONTEXT_COMMAND_REQUEST_SUBTYPE_MASK) + +#define SCU_CONTEXT_COMMAND_REQUEST_FULLTYPE_MASK \ + (\ + SCU_CONTEXT_COMMAND_REQUEST_TYPE_MASK \ + | SCU_CONTEXT_COMMAND_REQUEST_SUBTYPE_MASK \ + ) +#define scu_get_command_request_full_type(x) \ + ((x) & SCU_CONTEXT_COMMAND_REQUEST_FULLTYPE_MASK) + +#define SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_SHIFT 16 +#define SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_MASK 0x00010000 +#define scu_get_command_protocl_engine_group(x) \ + ((x) & SCU_CONTEXT_COMMAND_PROTOCOL_ENGINE_GROUP_MASK) + +#define SCU_CONTEXT_COMMAND_LOGICAL_PORT_SHIFT 12 +#define SCU_CONTEXT_COMMAND_LOGICAL_PORT_MASK 0x00007000 +#define scu_get_command_reqeust_logical_port(x) \ + ((x) & SCU_CONTEXT_COMMAND_LOGICAL_PORT_MASK) + + +#define MAKE_SCU_CONTEXT_COMMAND_TYPE(type) \ + ((u32)(type) << SCU_CONTEXT_COMMAND_REQUEST_TYPE_SHIFT) + +/** + * MAKE_SCU_CONTEXT_COMMAND_TYPE() - + * + * SCU_COMMAND_TYPES These constants provide the grouping of the different SCU + * command types. + */ +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC MAKE_SCU_CONTEXT_COMMAND_TYPE(0) +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_TC MAKE_SCU_CONTEXT_COMMAND_TYPE(1) +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_RNC MAKE_SCU_CONTEXT_COMMAND_TYPE(2) +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_RNC MAKE_SCU_CONTEXT_COMMAND_TYPE(3) +#define SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC MAKE_SCU_CONTEXT_COMMAND_TYPE(6) + +#define MAKE_SCU_CONTEXT_COMMAND_REQUEST(type, command) \ + ((type) | ((command) << SCU_CONTEXT_COMMAND_REQUEST_SUBTYPE_SHIFT)) + +/** + * + * + * SCU_REQUEST_TYPES These constants are the various request types that can be + * posted to the SCU hardware. + */ +#define SCU_CONTEXT_COMMAND_REQUST_POST_TC \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC, 0)) + +#define SCU_CONTEXT_COMMAND_REQUEST_POST_TC_ABORT \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_TC, 1)) + +#define SCU_CONTEXT_COMMAND_REQUST_DUMP_TC \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_TC, 0)) + +#define SCU_CONTEXT_COMMAND_POST_RNC_32 \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_RNC, 0)) + +#define SCU_CONTEXT_COMMAND_POST_RNC_96 \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_RNC, 1)) + +#define SCU_CONTEXT_COMMAND_POST_RNC_INVALIDATE \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_POST_RNC, 2)) + +#define SCU_CONTEXT_COMMAND_DUMP_RNC_32 \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_RNC, 0)) + +#define SCU_CONTEXT_COMMAND_DUMP_RNC_96 \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_DUMP_RNC, 1)) + +#define SCU_CONTEXT_COMMAND_POST_RNC_SUSPEND_TX \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC, 0)) + +#define SCU_CONTEXT_COMMAND_POST_RNC_SUSPEND_TX_RX \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC, 1)) + +#define SCU_CONTEXT_COMMAND_POST_RNC_RESUME \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC, 2)) + +#define SCU_CONTEXT_IT_NEXUS_LOSS_TIMER_ENABLE \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC, 3)) + +#define SCU_CONTEXT_IT_NEXUS_LOSS_TIMER_DISABLE \ + (MAKE_SCU_CONTEXT_COMMAND_REQUEST(SCU_CONTEXT_COMMAND_REQUEST_TYPE_OTHER_RNC, 4)) + +/** + * + * + * SCU_TASK_CONTEXT_PROTOCOL SCU Task context protocol types this is uesd to + * program the SCU Task context protocol field in word 0x00. + */ +#define SCU_TASK_CONTEXT_PROTOCOL_SMP 0x00 +#define SCU_TASK_CONTEXT_PROTOCOL_SSP 0x01 +#define SCU_TASK_CONTEXT_PROTOCOL_STP 0x02 +#define SCU_TASK_CONTEXT_PROTOCOL_NONE 0x07 + +/** + * struct ssp_task_context - This is the SCU hardware definition for an SSP + * request. + * + * + */ +struct ssp_task_context { + /* OFFSET 0x18 */ + u32 reserved00:24; + u32 frame_type:8; + + /* OFFSET 0x1C */ + u32 reserved01; + + /* OFFSET 0x20 */ + u32 fill_bytes:2; + u32 reserved02:6; + u32 changing_data_pointer:1; + u32 retransmit:1; + u32 retry_data_frame:1; + u32 tlr_control:2; + u32 reserved03:19; + + /* OFFSET 0x24 */ + u32 uiRsvd4; + + /* OFFSET 0x28 */ + u32 target_port_transfer_tag:16; + u32 tag:16; + + /* OFFSET 0x2C */ + u32 data_offset; +}; + +/** + * struct stp_task_context - This is the SCU hardware definition for an STP + * request. + * + * + */ +struct stp_task_context { + /* OFFSET 0x18 */ + u32 fis_type:8; + u32 pm_port:4; + u32 reserved0:3; + u32 control:1; + u32 command:8; + u32 features:8; + + /* OFFSET 0x1C */ + u32 reserved1; + + /* OFFSET 0x20 */ + u32 reserved2; + + /* OFFSET 0x24 */ + u32 reserved3; + + /* OFFSET 0x28 */ + u32 ncq_tag:5; + u32 reserved4:27; + + /* OFFSET 0x2C */ + u32 data_offset; /* TODO: What is this used for? */ +}; + +/** + * struct smp_task_context - This is the SCU hardware definition for an SMP + * request. + * + * + */ +struct smp_task_context { + /* OFFSET 0x18 */ + u32 response_length:8; + u32 function_result:8; + u32 function:8; + u32 frame_type:8; + + /* OFFSET 0x1C */ + u32 smp_response_ufi:12; + u32 reserved1:20; + + /* OFFSET 0x20 */ + u32 reserved2; + + /* OFFSET 0x24 */ + u32 reserved3; + + /* OFFSET 0x28 */ + u32 reserved4; + + /* OFFSET 0x2C */ + u32 reserved5; +}; + +/** + * struct primitive_task_context - This is the SCU hardware definition used + * when the driver wants to send a primitive on the link. + * + * + */ +struct primitive_task_context { + /* OFFSET 0x18 */ + /** + * This field is the control word and it must be 0. + */ + u32 control; /* /< must be set to 0 */ + + /* OFFSET 0x1C */ + /** + * This field specifies the primitive that is to be transmitted. + */ + u32 sequence; + + /* OFFSET 0x20 */ + u32 reserved0; + + /* OFFSET 0x24 */ + u32 reserved1; + + /* OFFSET 0x28 */ + u32 reserved2; + + /* OFFSET 0x2C */ + u32 reserved3; +}; + +/** + * The union of the protocols that can be selected in the SCU task context + * field. + * + * protocol_context + */ +union protocol_context { + struct ssp_task_context ssp; + struct stp_task_context stp; + struct smp_task_context smp; + struct primitive_task_context primitive; + u32 words[6]; +}; + +/** + * struct scu_sgl_element - This structure represents a single SCU defined SGL + * element. SCU SGLs contain a 64 bit address with the maximum data transfer + * being 24 bits in size. The SGL can not cross a 4GB boundary. + * + * struct scu_sgl_element + */ +struct scu_sgl_element { + /** + * This field is the upper 32 bits of the 64 bit physical address. + */ + u32 address_upper; + + /** + * This field is the lower 32 bits of the 64 bit physical address. + */ + u32 address_lower; + + /** + * This field is the number of bytes to transfer. + */ + u32 length:24; + + /** + * This field is the address modifier to be used when a virtual function is + * requesting a data transfer. + */ + u32 address_modifier:8; + +}; + +#define SCU_SGL_ELEMENT_PAIR_A 0 +#define SCU_SGL_ELEMENT_PAIR_B 1 + +/** + * struct scu_sgl_element_pair - This structure is the SCU hardware definition + * of a pair of SGL elements. The SCU hardware always works on SGL pairs. + * They are refered to in the DS specification as SGL A and SGL B. Each SGL + * pair is followed by the address of the next pair. + * + * + */ +struct scu_sgl_element_pair { + /* OFFSET 0x60-0x68 */ + /** + * This field is the SGL element A of the SGL pair. + */ + struct scu_sgl_element A; + + /* OFFSET 0x6C-0x74 */ + /** + * This field is the SGL element B of the SGL pair. + */ + struct scu_sgl_element B; + + /* OFFSET 0x78-0x7C */ + /** + * This field is the upper 32 bits of the 64 bit address to the next SGL + * element pair. + */ + u32 next_pair_upper; + + /** + * This field is the lower 32 bits of the 64 bit address to the next SGL + * element pair. + */ + u32 next_pair_lower; + +}; + +/** + * struct transport_snapshot - This structure is the SCU hardware scratch area + * for the task context. This is set to 0 by the driver but can be read by + * issuing a dump TC request to the SCU. + * + * + */ +struct transport_snapshot { + /* OFFSET 0x48 */ + u32 xfer_rdy_write_data_length; + + /* OFFSET 0x4C */ + u32 data_offset; + + /* OFFSET 0x50 */ + u32 data_transfer_size:24; + u32 reserved_50_0:8; + + /* OFFSET 0x54 */ + u32 next_initiator_write_data_offset; + + /* OFFSET 0x58 */ + u32 next_initiator_write_data_xfer_size:24; + u32 reserved_58_0:8; +}; + +/** + * struct scu_task_context - This structure defines the contents of the SCU + * silicon task context. It lays out all of the fields according to the + * expected order and location for the Storage Controller unit. + * + * + */ +struct scu_task_context { + /* OFFSET 0x00 ------ */ + /** + * This field must be encoded to one of the valid SCU task priority values + * - SCU_TASK_PRIORITY_NORMAL + * - SCU_TASK_PRIORITY_HEAD_OF_Q + * - SCU_TASK_PRIORITY_HIGH + */ + u32 priority:2; + + /** + * This field must be set to true if this is an initiator generated request. + * Until target mode is supported all task requests are initiator requests. + */ + u32 initiator_request:1; + + /** + * This field must be set to one of the valid connection rates valid values + * are 0x8, 0x9, and 0xA. + */ + u32 connection_rate:4; + + /** + * This field muse be programed when generating an SMP response since the SMP + * connection remains open until the SMP response is generated. + */ + u32 protocol_engine_index:3; + + /** + * This field must contain the logical port for the task request. + */ + u32 logical_port_index:3; + + /** + * This field must be set to one of the SCU_TASK_CONTEXT_PROTOCOL values + * - SCU_TASK_CONTEXT_PROTOCOL_SMP + * - SCU_TASK_CONTEXT_PROTOCOL_SSP + * - SCU_TASK_CONTEXT_PROTOCOL_STP + * - SCU_TASK_CONTEXT_PROTOCOL_NONE + */ + u32 protocol_type:3; + + /** + * This filed must be set to the TCi allocated for this task + */ + u32 task_index:12; + + /** + * This field is reserved and must be set to 0x00 + */ + u32 reserved_00_0:1; + + /** + * For a normal task request this must be set to 0. If this is an abort of + * this task request it must be set to 1. + */ + u32 abort:1; + + /** + * This field must be set to true for the SCU hardware to process the task. + */ + u32 valid:1; + + /** + * This field must be set to SCU_TASK_CONTEXT_TYPE + */ + u32 context_type:1; + + /* OFFSET 0x04 */ + /** + * This field contains the RNi that is the target of this request. + */ + u32 remote_node_index:12; + + /** + * This field is programmed if this is a mirrored request, which we are not + * using, in which case it is the RNi for the mirrored target. + */ + u32 mirrored_node_index:12; + + /** + * This field is programmed with the direction of the SATA reqeust + * - SCU_SATA_WRITE_DATA_DIRECTION + * - SCU_SATA_READ_DATA_DIRECTION + */ + u32 sata_direction:1; + + /** + * This field is programmsed with one of the following SCU_COMMAND_CODE + * - SCU_COMMAND_CODE_INITIATOR_NEW_TASK + * - SCU_COMMAND_CODE_ACTIVE_TASK + * - SCU_COMMAND_CODE_PRIMITIVE_SEQ_TASK + * - SCU_COMMAND_CODE_TARGET_RAW_FRAMES + */ + u32 command_code:2; + + /** + * This field is set to true if the remote node should be suspended. + * This bit is only valid for SSP & SMP target devices. + */ + u32 suspend_node:1; + + /** + * This field is programmed with one of the following command type codes + * + * For SAS requests use the scu_ssp_task_type + * - SCU_TASK_TYPE_IOREAD + * - SCU_TASK_TYPE_IOWRITE + * - SCU_TASK_TYPE_SMP_REQUEST + * - SCU_TASK_TYPE_RESPONSE + * - SCU_TASK_TYPE_RAW_FRAME + * - SCU_TASK_TYPE_PRIMITIVE + * + * For SATA requests use the scu_sata_task_type + * - SCU_TASK_TYPE_DMA_IN + * - SCU_TASK_TYPE_FPDMAQ_READ + * - SCU_TASK_TYPE_PACKET_DMA_IN + * - SCU_TASK_TYPE_SATA_RAW_FRAME + * - SCU_TASK_TYPE_DMA_OUT + * - SCU_TASK_TYPE_FPDMAQ_WRITE + * - SCU_TASK_TYPE_PACKET_DMA_OUT + */ + u32 task_type:4; + + /* OFFSET 0x08 */ + /** + * This field is reserved and the must be set to 0x00 + */ + u32 link_layer_control:8; /* presently all reserved */ + + /** + * This field is set to true when TLR is to be enabled + */ + u32 ssp_tlr_enable:1; + + /** + * This is field specifies if the SCU DMAs a response frame to host + * memory for good response frames when operating in target mode. + */ + u32 dma_ssp_target_good_response:1; + + /** + * This field indicates if the SCU should DMA the response frame to + * host memory. + */ + u32 do_not_dma_ssp_good_response:1; + + /** + * This field is set to true when strict ordering is to be enabled + */ + u32 strict_ordering:1; + + /** + * This field indicates the type of endianess to be utilized for the + * frame. command, task, and response frames utilized control_frame + * set to 1. + */ + u32 control_frame:1; + + /** + * This field is reserved and the driver should set to 0x00 + */ + u32 tl_control_reserved:3; + + /** + * This field is set to true when the SCU hardware task timeout control is to + * be enabled + */ + u32 timeout_enable:1; + + /** + * This field is reserved and the driver should set it to 0x00 + */ + u32 pts_control_reserved:7; + + /** + * This field should be set to true when block guard is to be enabled + */ + u32 block_guard_enable:1; + + /** + * This field is reserved and the driver should set to 0x00 + */ + u32 sdma_control_reserved:7; + + /* OFFSET 0x0C */ + /** + * This field is the address modifier for this io request it should be + * programmed with the virtual function that is making the request. + */ + u32 address_modifier:16; + + /** + * @todo What we support mirrored SMP response frame? + */ + u32 mirrored_protocol_engine:3; /* mirrored protocol Engine Index */ + + /** + * If this is a mirrored request the logical port index for the mirrored RNi + * must be programmed. + */ + u32 mirrored_logical_port:4; /* mirrored local port index */ + + /** + * This field is reserved and the driver must set it to 0x00 + */ + u32 reserved_0C_0:8; + + /** + * This field must be set to true if the mirrored request processing is to be + * enabled. + */ + u32 mirror_request_enable:1; /* Mirrored request Enable */ + + /* OFFSET 0x10 */ + /** + * This field is the command iu length in dwords + */ + u32 ssp_command_iu_length:8; + + /** + * This is the target TLR enable bit it must be set to 0 when creatning the + * task context. + */ + u32 xfer_ready_tlr_enable:1; + + /** + * This field is reserved and the driver must set it to 0x00 + */ + u32 reserved_10_0:7; + + /** + * This is the maximum burst size that the SCU hardware will send in one + * connection its value is (N x 512) and N must be a multiple of 2. If the + * value is 0x00 then maximum burst size is disabled. + */ + u32 ssp_max_burst_size:16; + + /* OFFSET 0x14 */ + /** + * This filed is set to the number of bytes to be transfered in the request. + */ + u32 transfer_length_bytes:24; /* In terms of bytes */ + + /** + * This field is reserved and the driver should set it to 0x00 + */ + u32 reserved_14_0:8; + + /* OFFSET 0x18-0x2C */ + /** + * This union provides for the protocol specif part of the SCU Task Context. + */ + union protocol_context type; + + /* OFFSET 0x30-0x34 */ + /** + * This field is the upper 32 bits of the 64 bit physical address of the + * command iu buffer + */ + u32 command_iu_upper; + + /** + * This field is the lower 32 bits of the 64 bit physical address of the + * command iu buffer + */ + u32 command_iu_lower; + + /* OFFSET 0x38-0x3C */ + /** + * This field is the upper 32 bits of the 64 bit physical address of the + * response iu buffer + */ + u32 response_iu_upper; + + /** + * This field is the lower 32 bits of the 64 bit physical address of the + * response iu buffer + */ + u32 response_iu_lower; + + /* OFFSET 0x40 */ + /** + * This field is set to the task phase of the SCU hardware. The driver must + * set this to 0x01 + */ + u32 task_phase:8; + + /** + * This field is set to the transport layer task status. The driver must set + * this to 0x00 + */ + u32 task_status:8; + + /** + * This field is used during initiator write TLR + */ + u32 previous_extended_tag:4; + + /** + * This field is set the maximum number of retries for a STP non-data FIS + */ + u32 stp_retry_count:2; + + /** + * This field is reserved and the driver must set it to 0x00 + */ + u32 reserved_40_1:2; + + /** + * This field is used by the SCU TL to determine when to take a snapshot when + * tranmitting read data frames. + * - 0x00 The entire IO + * - 0x01 32k + * - 0x02 64k + * - 0x04 128k + * - 0x08 256k + */ + u32 ssp_tlr_threshold:4; + + /** + * This field is reserved and the driver must set it to 0x00 + */ + u32 reserved_40_2:4; + + /* OFFSET 0x44 */ + u32 write_data_length; /* read only set to 0 */ + + /* OFFSET 0x48-0x58 */ + struct transport_snapshot snapshot; /* read only set to 0 */ + + /* OFFSET 0x5C */ + u32 block_protection_enable:1; + u32 block_size:2; + u32 block_protection_function:2; + u32 reserved_5C_0:9; + u32 active_sgl_element:2; /* read only set to 0 */ + u32 sgl_exhausted:1; /* read only set to 0 */ + u32 payload_data_transfer_error:4; /* read only set to 0 */ + u32 frame_buffer_offset:11; /* read only set to 0 */ + + /* OFFSET 0x60-0x7C */ + /** + * This field is the first SGL element pair found in the TC data structure. + */ + struct scu_sgl_element_pair sgl_pair_ab; + /* OFFSET 0x80-0x9C */ + /** + * This field is the second SGL element pair found in the TC data structure. + */ + struct scu_sgl_element_pair sgl_pair_cd; + + /* OFFSET 0xA0-BC */ + struct scu_sgl_element_pair sgl_snapshot_ac; + + /* OFFSET 0xC0 */ + u32 active_sgl_element_pair; /* read only set to 0 */ + + /* OFFSET 0xC4-0xCC */ + u32 reserved_C4_CC[3]; + + /* OFFSET 0xD0 */ + u32 intermediate_crc_value:16; + u32 initial_crc_seed:16; + + /* OFFSET 0xD4 */ + u32 application_tag_for_verify:16; + u32 application_tag_for_generate:16; + + /* OFFSET 0xD8 */ + u32 reference_tag_seed_for_verify_function; + + /* OFFSET 0xDC */ + u32 reserved_DC; + + /* OFFSET 0xE0 */ + u32 reserved_E0_0:16; + u32 application_tag_mask_for_generate:16; + + /* OFFSET 0xE4 */ + u32 block_protection_control:16; + u32 application_tag_mask_for_verify:16; + + /* OFFSET 0xE8 */ + u32 block_protection_error:8; + u32 reserved_E8_0:24; + + /* OFFSET 0xEC */ + u32 reference_tag_seed_for_verify; + + /* OFFSET 0xF0 */ + u32 intermediate_crc_valid_snapshot:16; + u32 reserved_F0_0:16; + + /* OFFSET 0xF4 */ + u32 reference_tag_seed_for_verify_function_snapshot; + + /* OFFSET 0xF8 */ + u32 snapshot_of_reserved_dword_DC_of_tc; + + /* OFFSET 0xFC */ + u32 reference_tag_seed_for_generate_function_snapshot; + +}; + +#endif /* _SCU_TASK_CONTEXT_H_ */ diff --git a/drivers/scsi/isci/task.c b/drivers/scsi/isci/task.c new file mode 100644 index 0000000..d6bcdd0 --- /dev/null +++ b/drivers/scsi/isci/task.c @@ -0,0 +1,1676 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/completion.h> +#include <linux/irqflags.h> +#include "sas.h" +#include <scsi/libsas.h> +#include "remote_device.h" +#include "remote_node_context.h" +#include "isci.h" +#include "request.h" +#include "task.h" +#include "host.h" + +/** +* isci_task_refuse() - complete the request to the upper layer driver in +* the case where an I/O needs to be completed back in the submit path. +* @ihost: host on which the the request was queued +* @task: request to complete +* @response: response code for the completed task. +* @status: status code for the completed task. +* +*/ +static void isci_task_refuse(struct isci_host *ihost, struct sas_task *task, + enum service_response response, + enum exec_status status) + +{ + enum isci_completion_selection disposition; + + disposition = isci_perform_normal_io_completion; + disposition = isci_task_set_completion_status(task, response, status, + disposition); + + /* Tasks aborted specifically by a call to the lldd_abort_task + * function should not be completed to the host in the regular path. + */ + switch (disposition) { + case isci_perform_normal_io_completion: + /* Normal notification (task_done) */ + dev_dbg(&ihost->pdev->dev, + "%s: Normal - task = %p, response=%d, " + "status=%d\n", + __func__, task, response, status); + + task->lldd_task = NULL; + + isci_execpath_callback(ihost, task, task->task_done); + break; + + case isci_perform_aborted_io_completion: + /* + * No notification because this request is already in the + * abort path. + */ + dev_dbg(&ihost->pdev->dev, + "%s: Aborted - task = %p, response=%d, " + "status=%d\n", + __func__, task, response, status); + break; + + case isci_perform_error_io_completion: + /* Use sas_task_abort */ + dev_dbg(&ihost->pdev->dev, + "%s: Error - task = %p, response=%d, " + "status=%d\n", + __func__, task, response, status); + + isci_execpath_callback(ihost, task, sas_task_abort); + break; + + default: + dev_dbg(&ihost->pdev->dev, + "%s: isci task notification default case!", + __func__); + sas_task_abort(task); + break; + } +} + +#define for_each_sas_task(num, task) \ + for (; num > 0; num--,\ + task = list_entry(task->list.next, struct sas_task, list)) + + +static inline int isci_device_io_ready(struct isci_remote_device *idev, + struct sas_task *task) +{ + return idev ? test_bit(IDEV_IO_READY, &idev->flags) || + (test_bit(IDEV_IO_NCQERROR, &idev->flags) && + isci_task_is_ncq_recovery(task)) + : 0; +} +/** + * isci_task_execute_task() - This function is one of the SAS Domain Template + * functions. This function is called by libsas to send a task down to + * hardware. + * @task: This parameter specifies the SAS task to send. + * @num: This parameter specifies the number of tasks to queue. + * @gfp_flags: This parameter specifies the context of this call. + * + * status, zero indicates success. + */ +int isci_task_execute_task(struct sas_task *task, int num, gfp_t gfp_flags) +{ + struct isci_host *ihost = dev_to_ihost(task->dev); + struct isci_remote_device *idev; + unsigned long flags; + bool io_ready; + u16 tag; + + dev_dbg(&ihost->pdev->dev, "%s: num=%d\n", __func__, num); + + for_each_sas_task(num, task) { + enum sci_status status = SCI_FAILURE; + + spin_lock_irqsave(&ihost->scic_lock, flags); + idev = isci_lookup_device(task->dev); + io_ready = isci_device_io_ready(idev, task); + tag = isci_alloc_tag(ihost); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + dev_dbg(&ihost->pdev->dev, + "task: %p, num: %d dev: %p idev: %p:%#lx cmd = %p\n", + task, num, task->dev, idev, idev ? idev->flags : 0, + task->uldd_task); + + if (!idev) { + isci_task_refuse(ihost, task, SAS_TASK_UNDELIVERED, + SAS_DEVICE_UNKNOWN); + } else if (!io_ready || tag == SCI_CONTROLLER_INVALID_IO_TAG) { + /* Indicate QUEUE_FULL so that the scsi midlayer + * retries. + */ + isci_task_refuse(ihost, task, SAS_TASK_COMPLETE, + SAS_QUEUE_FULL); + } else { + /* There is a device and it's ready for I/O. */ + spin_lock_irqsave(&task->task_state_lock, flags); + + if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { + /* The I/O was aborted. */ + spin_unlock_irqrestore(&task->task_state_lock, + flags); + + isci_task_refuse(ihost, task, + SAS_TASK_UNDELIVERED, + SAM_STAT_TASK_ABORTED); + } else { + task->task_state_flags |= SAS_TASK_AT_INITIATOR; + spin_unlock_irqrestore(&task->task_state_lock, flags); + + /* build and send the request. */ + status = isci_request_execute(ihost, idev, task, tag); + + if (status != SCI_SUCCESS) { + + spin_lock_irqsave(&task->task_state_lock, flags); + /* Did not really start this command. */ + task->task_state_flags &= ~SAS_TASK_AT_INITIATOR; + spin_unlock_irqrestore(&task->task_state_lock, flags); + + /* Indicate QUEUE_FULL so that the scsi + * midlayer retries. if the request + * failed for remote device reasons, + * it gets returned as + * SAS_TASK_UNDELIVERED next time + * through. + */ + isci_task_refuse(ihost, task, + SAS_TASK_COMPLETE, + SAS_QUEUE_FULL); + } + } + } + if (status != SCI_SUCCESS && tag != SCI_CONTROLLER_INVALID_IO_TAG) { + spin_lock_irqsave(&ihost->scic_lock, flags); + /* command never hit the device, so just free + * the tci and skip the sequence increment + */ + isci_tci_free(ihost, ISCI_TAG_TCI(tag)); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + } + isci_put_device(idev); + } + return 0; +} + +static enum sci_status isci_sata_management_task_request_build(struct isci_request *ireq) +{ + struct isci_tmf *isci_tmf; + enum sci_status status; + + if (tmf_task != ireq->ttype) + return SCI_FAILURE; + + isci_tmf = isci_request_access_tmf(ireq); + + switch (isci_tmf->tmf_code) { + + case isci_tmf_sata_srst_high: + case isci_tmf_sata_srst_low: { + struct host_to_dev_fis *fis = &ireq->stp.cmd; + + memset(fis, 0, sizeof(*fis)); + + fis->fis_type = 0x27; + fis->flags &= ~0x80; + fis->flags &= 0xF0; + if (isci_tmf->tmf_code == isci_tmf_sata_srst_high) + fis->control |= ATA_SRST; + else + fis->control &= ~ATA_SRST; + break; + } + /* other management commnd go here... */ + default: + return SCI_FAILURE; + } + + /* core builds the protocol specific request + * based on the h2d fis. + */ + status = sci_task_request_construct_sata(ireq); + + return status; +} + +static struct isci_request *isci_task_request_build(struct isci_host *ihost, + struct isci_remote_device *idev, + u16 tag, struct isci_tmf *isci_tmf) +{ + enum sci_status status = SCI_FAILURE; + struct isci_request *ireq = NULL; + struct domain_device *dev; + + dev_dbg(&ihost->pdev->dev, + "%s: isci_tmf = %p\n", __func__, isci_tmf); + + dev = idev->domain_dev; + + /* do common allocation and init of request object. */ + ireq = isci_tmf_request_from_tag(ihost, isci_tmf, tag); + if (!ireq) + return NULL; + + /* let the core do it's construct. */ + status = sci_task_request_construct(ihost, idev, tag, + ireq); + + if (status != SCI_SUCCESS) { + dev_warn(&ihost->pdev->dev, + "%s: sci_task_request_construct failed - " + "status = 0x%x\n", + __func__, + status); + return NULL; + } + + /* XXX convert to get this from task->tproto like other drivers */ + if (dev->dev_type == SAS_END_DEV) { + isci_tmf->proto = SAS_PROTOCOL_SSP; + status = sci_task_request_construct_ssp(ireq); + if (status != SCI_SUCCESS) + return NULL; + } + + if (dev->dev_type == SATA_DEV || (dev->tproto & SAS_PROTOCOL_STP)) { + isci_tmf->proto = SAS_PROTOCOL_SATA; + status = isci_sata_management_task_request_build(ireq); + + if (status != SCI_SUCCESS) + return NULL; + } + return ireq; +} + +static int isci_task_execute_tmf(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_tmf *tmf, unsigned long timeout_ms) +{ + DECLARE_COMPLETION_ONSTACK(completion); + enum sci_task_status status = SCI_TASK_FAILURE; + struct isci_request *ireq; + int ret = TMF_RESP_FUNC_FAILED; + unsigned long flags; + unsigned long timeleft; + u16 tag; + + spin_lock_irqsave(&ihost->scic_lock, flags); + tag = isci_alloc_tag(ihost); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + if (tag == SCI_CONTROLLER_INVALID_IO_TAG) + return ret; + + /* sanity check, return TMF_RESP_FUNC_FAILED + * if the device is not there and ready. + */ + if (!idev || + (!test_bit(IDEV_IO_READY, &idev->flags) && + !test_bit(IDEV_IO_NCQERROR, &idev->flags))) { + dev_dbg(&ihost->pdev->dev, + "%s: idev = %p not ready (%#lx)\n", + __func__, + idev, idev ? idev->flags : 0); + goto err_tci; + } else + dev_dbg(&ihost->pdev->dev, + "%s: idev = %p\n", + __func__, idev); + + /* Assign the pointer to the TMF's completion kernel wait structure. */ + tmf->complete = &completion; + + ireq = isci_task_request_build(ihost, idev, tag, tmf); + if (!ireq) + goto err_tci; + + spin_lock_irqsave(&ihost->scic_lock, flags); + + /* start the TMF io. */ + status = sci_controller_start_task(ihost, idev, ireq); + + if (status != SCI_TASK_SUCCESS) { + dev_dbg(&ihost->pdev->dev, + "%s: start_io failed - status = 0x%x, request = %p\n", + __func__, + status, + ireq); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + goto err_tci; + } + + if (tmf->cb_state_func != NULL) + tmf->cb_state_func(isci_tmf_started, tmf, tmf->cb_data); + + isci_request_change_state(ireq, started); + + /* add the request to the remote device request list. */ + list_add(&ireq->dev_node, &idev->reqs_in_process); + + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + /* Wait for the TMF to complete, or a timeout. */ + timeleft = wait_for_completion_timeout(&completion, + msecs_to_jiffies(timeout_ms)); + + if (timeleft == 0) { + spin_lock_irqsave(&ihost->scic_lock, flags); + + if (tmf->cb_state_func != NULL) + tmf->cb_state_func(isci_tmf_timed_out, tmf, tmf->cb_data); + + sci_controller_terminate_request(ihost, + idev, + ireq); + + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + wait_for_completion(tmf->complete); + } + + isci_print_tmf(tmf); + + if (tmf->status == SCI_SUCCESS) + ret = TMF_RESP_FUNC_COMPLETE; + else if (tmf->status == SCI_FAILURE_IO_RESPONSE_VALID) { + dev_dbg(&ihost->pdev->dev, + "%s: tmf.status == " + "SCI_FAILURE_IO_RESPONSE_VALID\n", + __func__); + ret = TMF_RESP_FUNC_COMPLETE; + } + /* Else - leave the default "failed" status alone. */ + + dev_dbg(&ihost->pdev->dev, + "%s: completed request = %p\n", + __func__, + ireq); + + return ret; + + err_tci: + spin_lock_irqsave(&ihost->scic_lock, flags); + isci_tci_free(ihost, ISCI_TAG_TCI(tag)); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + return ret; +} + +static void isci_task_build_tmf(struct isci_tmf *tmf, + enum isci_tmf_function_codes code, + void (*tmf_sent_cb)(enum isci_tmf_cb_state, + struct isci_tmf *, + void *), + void *cb_data) +{ + memset(tmf, 0, sizeof(*tmf)); + + tmf->tmf_code = code; + tmf->cb_state_func = tmf_sent_cb; + tmf->cb_data = cb_data; +} + +static void isci_task_build_abort_task_tmf(struct isci_tmf *tmf, + enum isci_tmf_function_codes code, + void (*tmf_sent_cb)(enum isci_tmf_cb_state, + struct isci_tmf *, + void *), + struct isci_request *old_request) +{ + isci_task_build_tmf(tmf, code, tmf_sent_cb, old_request); + tmf->io_tag = old_request->io_tag; +} + +/** + * isci_task_validate_request_to_abort() - This function checks the given I/O + * against the "started" state. If the request is still "started", it's + * state is changed to aborted. NOTE: isci_host->scic_lock MUST BE HELD + * BEFORE CALLING THIS FUNCTION. + * @isci_request: This parameter specifies the request object to control. + * @isci_host: This parameter specifies the ISCI host object + * @isci_device: This is the device to which the request is pending. + * @aborted_io_completion: This is a completion structure that will be added to + * the request in case it is changed to aborting; this completion is + * triggered when the request is fully completed. + * + * Either "started" on successful change of the task status to "aborted", or + * "unallocated" if the task cannot be controlled. + */ +static enum isci_request_status isci_task_validate_request_to_abort( + struct isci_request *isci_request, + struct isci_host *isci_host, + struct isci_remote_device *isci_device, + struct completion *aborted_io_completion) +{ + enum isci_request_status old_state = unallocated; + + /* Only abort the task if it's in the + * device's request_in_process list + */ + if (isci_request && !list_empty(&isci_request->dev_node)) { + old_state = isci_request_change_started_to_aborted( + isci_request, aborted_io_completion); + + } + + return old_state; +} + +/** +* isci_request_cleanup_completed_loiterer() - This function will take care of +* the final cleanup on any request which has been explicitly terminated. +* @isci_host: This parameter specifies the ISCI host object +* @isci_device: This is the device to which the request is pending. +* @isci_request: This parameter specifies the terminated request object. +* @task: This parameter is the libsas I/O request. +*/ +static void isci_request_cleanup_completed_loiterer( + struct isci_host *isci_host, + struct isci_remote_device *isci_device, + struct isci_request *isci_request, + struct sas_task *task) +{ + unsigned long flags; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_device=%p, request=%p, task=%p\n", + __func__, isci_device, isci_request, task); + + if (task != NULL) { + + spin_lock_irqsave(&task->task_state_lock, flags); + task->lldd_task = NULL; + + task->task_state_flags &= ~SAS_TASK_NEED_DEV_RESET; + + isci_set_task_doneflags(task); + + /* If this task is not in the abort path, call task_done. */ + if (!(task->task_state_flags & SAS_TASK_STATE_ABORTED)) { + + spin_unlock_irqrestore(&task->task_state_lock, flags); + task->task_done(task); + } else + spin_unlock_irqrestore(&task->task_state_lock, flags); + } + + if (isci_request != NULL) { + spin_lock_irqsave(&isci_host->scic_lock, flags); + list_del_init(&isci_request->dev_node); + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + } +} + +/** + * isci_terminate_request_core() - This function will terminate the given + * request, and wait for it to complete. This function must only be called + * from a thread that can wait. Note that the request is terminated and + * completed (back to the host, if started there). + * @ihost: This SCU. + * @idev: The target. + * @isci_request: The I/O request to be terminated. + * + */ +static void isci_terminate_request_core(struct isci_host *ihost, + struct isci_remote_device *idev, + struct isci_request *isci_request) +{ + enum sci_status status = SCI_SUCCESS; + bool was_terminated = false; + bool needs_cleanup_handling = false; + enum isci_request_status request_status; + unsigned long flags; + unsigned long termination_completed = 1; + struct completion *io_request_completion; + struct sas_task *task; + + dev_dbg(&ihost->pdev->dev, + "%s: device = %p; request = %p\n", + __func__, idev, isci_request); + + spin_lock_irqsave(&ihost->scic_lock, flags); + + io_request_completion = isci_request->io_request_completion; + + task = (isci_request->ttype == io_task) + ? isci_request_access_task(isci_request) + : NULL; + + /* Note that we are not going to control + * the target to abort the request. + */ + set_bit(IREQ_COMPLETE_IN_TARGET, &isci_request->flags); + + /* Make sure the request wasn't just sitting around signalling + * device condition (if the request handle is NULL, then the + * request completed but needed additional handling here). + */ + if (!test_bit(IREQ_TERMINATED, &isci_request->flags)) { + was_terminated = true; + needs_cleanup_handling = true; + status = sci_controller_terminate_request(ihost, + idev, + isci_request); + } + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + /* + * The only time the request to terminate will + * fail is when the io request is completed and + * being aborted. + */ + if (status != SCI_SUCCESS) { + dev_dbg(&ihost->pdev->dev, + "%s: sci_controller_terminate_request" + " returned = 0x%x\n", + __func__, status); + + isci_request->io_request_completion = NULL; + + } else { + if (was_terminated) { + dev_dbg(&ihost->pdev->dev, + "%s: before completion wait (%p/%p)\n", + __func__, isci_request, io_request_completion); + + /* Wait here for the request to complete. */ + #define TERMINATION_TIMEOUT_MSEC 500 + termination_completed + = wait_for_completion_timeout( + io_request_completion, + msecs_to_jiffies(TERMINATION_TIMEOUT_MSEC)); + + if (!termination_completed) { + + /* The request to terminate has timed out. */ + spin_lock_irqsave(&ihost->scic_lock, + flags); + + /* Check for state changes. */ + if (!test_bit(IREQ_TERMINATED, &isci_request->flags)) { + + /* The best we can do is to have the + * request die a silent death if it + * ever really completes. + * + * Set the request state to "dead", + * and clear the task pointer so that + * an actual completion event callback + * doesn't do anything. + */ + isci_request->status = dead; + isci_request->io_request_completion + = NULL; + + if (isci_request->ttype == io_task) { + + /* Break links with the + * sas_task. + */ + isci_request->ttype_ptr.io_task_ptr + = NULL; + } + } else + termination_completed = 1; + + spin_unlock_irqrestore(&ihost->scic_lock, + flags); + + if (!termination_completed) { + + dev_dbg(&ihost->pdev->dev, + "%s: *** Timeout waiting for " + "termination(%p/%p)\n", + __func__, io_request_completion, + isci_request); + + /* The request can no longer be referenced + * safely since it may go away if the + * termination every really does complete. + */ + isci_request = NULL; + } + } + if (termination_completed) + dev_dbg(&ihost->pdev->dev, + "%s: after completion wait (%p/%p)\n", + __func__, isci_request, io_request_completion); + } + + if (termination_completed) { + + isci_request->io_request_completion = NULL; + + /* Peek at the status of the request. This will tell + * us if there was special handling on the request such that it + * needs to be detached and freed here. + */ + spin_lock_irqsave(&isci_request->state_lock, flags); + request_status = isci_request->status; + + if ((isci_request->ttype == io_task) /* TMFs are in their own thread */ + && ((request_status == aborted) + || (request_status == aborting) + || (request_status == terminating) + || (request_status == completed) + || (request_status == dead) + ) + ) { + + /* The completion routine won't free a request in + * the aborted/aborting/etc. states, so we do + * it here. + */ + needs_cleanup_handling = true; + } + spin_unlock_irqrestore(&isci_request->state_lock, flags); + + } + if (needs_cleanup_handling) + isci_request_cleanup_completed_loiterer( + ihost, idev, isci_request, task); + } +} + +/** + * isci_terminate_pending_requests() - This function will change the all of the + * requests on the given device's state to "aborting", will terminate the + * requests, and wait for them to complete. This function must only be + * called from a thread that can wait. Note that the requests are all + * terminated and completed (back to the host, if started there). + * @isci_host: This parameter specifies SCU. + * @idev: This parameter specifies the target. + * + */ +void isci_terminate_pending_requests(struct isci_host *ihost, + struct isci_remote_device *idev) +{ + struct completion request_completion; + enum isci_request_status old_state; + unsigned long flags; + LIST_HEAD(list); + + spin_lock_irqsave(&ihost->scic_lock, flags); + list_splice_init(&idev->reqs_in_process, &list); + + /* assumes that isci_terminate_request_core deletes from the list */ + while (!list_empty(&list)) { + struct isci_request *ireq = list_entry(list.next, typeof(*ireq), dev_node); + + /* Change state to "terminating" if it is currently + * "started". + */ + old_state = isci_request_change_started_to_newstate(ireq, + &request_completion, + terminating); + switch (old_state) { + case started: + case completed: + case aborting: + break; + default: + /* termination in progress, or otherwise dispositioned. + * We know the request was on 'list' so should be safe + * to move it back to reqs_in_process + */ + list_move(&ireq->dev_node, &idev->reqs_in_process); + ireq = NULL; + break; + } + + if (!ireq) + continue; + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + init_completion(&request_completion); + + dev_dbg(&ihost->pdev->dev, + "%s: idev=%p request=%p; task=%p old_state=%d\n", + __func__, idev, ireq, + ireq->ttype == io_task ? isci_request_access_task(ireq) : NULL, + old_state); + + /* If the old_state is started: + * This request was not already being aborted. If it had been, + * then the aborting I/O (ie. the TMF request) would not be in + * the aborting state, and thus would be terminated here. Note + * that since the TMF completion's call to the kernel function + * "complete()" does not happen until the pending I/O request + * terminate fully completes, we do not have to implement a + * special wait here for already aborting requests - the + * termination of the TMF request will force the request + * to finish it's already started terminate. + * + * If old_state == completed: + * This request completed from the SCU hardware perspective + * and now just needs cleaning up in terms of freeing the + * request and potentially calling up to libsas. + * + * If old_state == aborting: + * This request has already gone through a TMF timeout, but may + * not have been terminated; needs cleaning up at least. + */ + isci_terminate_request_core(ihost, idev, ireq); + spin_lock_irqsave(&ihost->scic_lock, flags); + } + spin_unlock_irqrestore(&ihost->scic_lock, flags); +} + +/** + * isci_task_send_lu_reset_sas() - This function is called by of the SAS Domain + * Template functions. + * @lun: This parameter specifies the lun to be reset. + * + * status, zero indicates success. + */ +static int isci_task_send_lu_reset_sas( + struct isci_host *isci_host, + struct isci_remote_device *isci_device, + u8 *lun) +{ + struct isci_tmf tmf; + int ret = TMF_RESP_FUNC_FAILED; + + dev_dbg(&isci_host->pdev->dev, + "%s: isci_host = %p, isci_device = %p\n", + __func__, isci_host, isci_device); + /* Send the LUN reset to the target. By the time the call returns, + * the TMF has fully exected in the target (in which case the return + * value is "TMF_RESP_FUNC_COMPLETE", or the request timed-out (or + * was otherwise unable to be executed ("TMF_RESP_FUNC_FAILED"). + */ + isci_task_build_tmf(&tmf, isci_tmf_ssp_lun_reset, NULL, NULL); + + #define ISCI_LU_RESET_TIMEOUT_MS 2000 /* 2 second timeout. */ + ret = isci_task_execute_tmf(isci_host, isci_device, &tmf, ISCI_LU_RESET_TIMEOUT_MS); + + if (ret == TMF_RESP_FUNC_COMPLETE) + dev_dbg(&isci_host->pdev->dev, + "%s: %p: TMF_LU_RESET passed\n", + __func__, isci_device); + else + dev_dbg(&isci_host->pdev->dev, + "%s: %p: TMF_LU_RESET failed (%x)\n", + __func__, isci_device, ret); + + return ret; +} + +static int isci_task_send_lu_reset_sata(struct isci_host *ihost, + struct isci_remote_device *idev, u8 *lun) +{ + int ret = TMF_RESP_FUNC_FAILED; + struct isci_tmf tmf; + + /* Send the soft reset to the target */ + #define ISCI_SRST_TIMEOUT_MS 25000 /* 25 second timeout. */ + isci_task_build_tmf(&tmf, isci_tmf_sata_srst_high, NULL, NULL); + + ret = isci_task_execute_tmf(ihost, idev, &tmf, ISCI_SRST_TIMEOUT_MS); + + if (ret != TMF_RESP_FUNC_COMPLETE) { + dev_dbg(&ihost->pdev->dev, + "%s: Assert SRST failed (%p) = %x", + __func__, idev, ret); + + /* Return the failure so that the LUN reset is escalated + * to a target reset. + */ + } + return ret; +} + +/** + * isci_task_lu_reset() - This function is one of the SAS Domain Template + * functions. This is one of the Task Management functoins called by libsas, + * to reset the given lun. Note the assumption that while this call is + * executing, no I/O will be sent by the host to the device. + * @lun: This parameter specifies the lun to be reset. + * + * status, zero indicates success. + */ +int isci_task_lu_reset(struct domain_device *domain_device, u8 *lun) +{ + struct isci_host *isci_host = dev_to_ihost(domain_device); + struct isci_remote_device *isci_device; + unsigned long flags; + int ret; + + spin_lock_irqsave(&isci_host->scic_lock, flags); + isci_device = isci_lookup_device(domain_device); + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + + dev_dbg(&isci_host->pdev->dev, + "%s: domain_device=%p, isci_host=%p; isci_device=%p\n", + __func__, domain_device, isci_host, isci_device); + + if (isci_device) + set_bit(IDEV_EH, &isci_device->flags); + + /* If there is a device reset pending on any request in the + * device's list, fail this LUN reset request in order to + * escalate to the device reset. + */ + if (!isci_device || + isci_device_is_reset_pending(isci_host, isci_device)) { + dev_dbg(&isci_host->pdev->dev, + "%s: No dev (%p), or " + "RESET PENDING: domain_device=%p\n", + __func__, isci_device, domain_device); + ret = TMF_RESP_FUNC_FAILED; + goto out; + } + + /* Send the task management part of the reset. */ + if (sas_protocol_ata(domain_device->tproto)) { + ret = isci_task_send_lu_reset_sata(isci_host, isci_device, lun); + } else + ret = isci_task_send_lu_reset_sas(isci_host, isci_device, lun); + + /* If the LUN reset worked, all the I/O can now be terminated. */ + if (ret == TMF_RESP_FUNC_COMPLETE) + /* Terminate all I/O now. */ + isci_terminate_pending_requests(isci_host, + isci_device); + + out: + isci_put_device(isci_device); + return ret; +} + + +/* int (*lldd_clear_nexus_port)(struct asd_sas_port *); */ +int isci_task_clear_nexus_port(struct asd_sas_port *port) +{ + return TMF_RESP_FUNC_FAILED; +} + + + +int isci_task_clear_nexus_ha(struct sas_ha_struct *ha) +{ + return TMF_RESP_FUNC_FAILED; +} + +/* Task Management Functions. Must be called from process context. */ + +/** + * isci_abort_task_process_cb() - This is a helper function for the abort task + * TMF command. It manages the request state with respect to the successful + * transmission / completion of the abort task request. + * @cb_state: This parameter specifies when this function was called - after + * the TMF request has been started and after it has timed-out. + * @tmf: This parameter specifies the TMF in progress. + * + * + */ +static void isci_abort_task_process_cb( + enum isci_tmf_cb_state cb_state, + struct isci_tmf *tmf, + void *cb_data) +{ + struct isci_request *old_request; + + old_request = (struct isci_request *)cb_data; + + dev_dbg(&old_request->isci_host->pdev->dev, + "%s: tmf=%p, old_request=%p\n", + __func__, tmf, old_request); + + switch (cb_state) { + + case isci_tmf_started: + /* The TMF has been started. Nothing to do here, since the + * request state was already set to "aborted" by the abort + * task function. + */ + if ((old_request->status != aborted) + && (old_request->status != completed)) + dev_dbg(&old_request->isci_host->pdev->dev, + "%s: Bad request status (%d): tmf=%p, old_request=%p\n", + __func__, old_request->status, tmf, old_request); + break; + + case isci_tmf_timed_out: + + /* Set the task's state to "aborting", since the abort task + * function thread set it to "aborted" (above) in anticipation + * of the task management request working correctly. Since the + * timeout has now fired, the TMF request failed. We set the + * state such that the request completion will indicate the + * device is no longer present. + */ + isci_request_change_state(old_request, aborting); + break; + + default: + dev_dbg(&old_request->isci_host->pdev->dev, + "%s: Bad cb_state (%d): tmf=%p, old_request=%p\n", + __func__, cb_state, tmf, old_request); + break; + } +} + +/** + * isci_task_abort_task() - This function is one of the SAS Domain Template + * functions. This function is called by libsas to abort a specified task. + * @task: This parameter specifies the SAS task to abort. + * + * status, zero indicates success. + */ +int isci_task_abort_task(struct sas_task *task) +{ + struct isci_host *isci_host = dev_to_ihost(task->dev); + DECLARE_COMPLETION_ONSTACK(aborted_io_completion); + struct isci_request *old_request = NULL; + enum isci_request_status old_state; + struct isci_remote_device *isci_device = NULL; + struct isci_tmf tmf; + int ret = TMF_RESP_FUNC_FAILED; + unsigned long flags; + bool any_dev_reset = false; + + /* Get the isci_request reference from the task. Note that + * this check does not depend on the pending request list + * in the device, because tasks driving resets may land here + * after completion in the core. + */ + spin_lock_irqsave(&isci_host->scic_lock, flags); + spin_lock(&task->task_state_lock); + + old_request = task->lldd_task; + + /* If task is already done, the request isn't valid */ + if (!(task->task_state_flags & SAS_TASK_STATE_DONE) && + (task->task_state_flags & SAS_TASK_AT_INITIATOR) && + old_request) + isci_device = isci_lookup_device(task->dev); + + spin_unlock(&task->task_state_lock); + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + + dev_dbg(&isci_host->pdev->dev, + "%s: task = %p\n", __func__, task); + + if (!isci_device || !old_request) + goto out; + + set_bit(IDEV_EH, &isci_device->flags); + + /* This version of the driver will fail abort requests for + * SATA/STP. Failing the abort request this way will cause the + * SCSI error handler thread to escalate to LUN reset + */ + if (sas_protocol_ata(task->task_proto)) { + dev_dbg(&isci_host->pdev->dev, + " task %p is for a STP/SATA device;" + " returning TMF_RESP_FUNC_FAILED\n" + " to cause a LUN reset...\n", task); + goto out; + } + + dev_dbg(&isci_host->pdev->dev, + "%s: old_request == %p\n", __func__, old_request); + + any_dev_reset = isci_device_is_reset_pending(isci_host, isci_device); + + spin_lock_irqsave(&task->task_state_lock, flags); + + any_dev_reset = any_dev_reset || (task->task_state_flags & SAS_TASK_NEED_DEV_RESET); + + /* If the extraction of the request reference from the task + * failed, then the request has been completed (or if there is a + * pending reset then this abort request function must be failed + * in order to escalate to the target reset). + */ + if ((old_request == NULL) || any_dev_reset) { + + /* If the device reset task flag is set, fail the task + * management request. Otherwise, the original request + * has completed. + */ + if (any_dev_reset) { + + /* Turn off the task's DONE to make sure this + * task is escalated to a target reset. + */ + task->task_state_flags &= ~SAS_TASK_STATE_DONE; + + /* Make the reset happen as soon as possible. */ + task->task_state_flags |= SAS_TASK_NEED_DEV_RESET; + + spin_unlock_irqrestore(&task->task_state_lock, flags); + + /* Fail the task management request in order to + * escalate to the target reset. + */ + ret = TMF_RESP_FUNC_FAILED; + + dev_dbg(&isci_host->pdev->dev, + "%s: Failing task abort in order to " + "escalate to target reset because\n" + "SAS_TASK_NEED_DEV_RESET is set for " + "task %p on dev %p\n", + __func__, task, isci_device); + + + } else { + /* The request has already completed and there + * is nothing to do here other than to set the task + * done bit, and indicate that the task abort function + * was sucessful. + */ + isci_set_task_doneflags(task); + + spin_unlock_irqrestore(&task->task_state_lock, flags); + + ret = TMF_RESP_FUNC_COMPLETE; + + dev_dbg(&isci_host->pdev->dev, + "%s: abort task not needed for %p\n", + __func__, task); + } + goto out; + } else { + spin_unlock_irqrestore(&task->task_state_lock, flags); + } + + spin_lock_irqsave(&isci_host->scic_lock, flags); + + /* Check the request status and change to "aborted" if currently + * "starting"; if true then set the I/O kernel completion + * struct that will be triggered when the request completes. + */ + old_state = isci_task_validate_request_to_abort( + old_request, isci_host, isci_device, + &aborted_io_completion); + if ((old_state != started) && + (old_state != completed) && + (old_state != aborting)) { + + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + + /* The request was already being handled by someone else (because + * they got to set the state away from started). + */ + dev_dbg(&isci_host->pdev->dev, + "%s: device = %p; old_request %p already being aborted\n", + __func__, + isci_device, old_request); + ret = TMF_RESP_FUNC_COMPLETE; + goto out; + } + if (task->task_proto == SAS_PROTOCOL_SMP || + test_bit(IREQ_COMPLETE_IN_TARGET, &old_request->flags)) { + + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + + dev_dbg(&isci_host->pdev->dev, + "%s: SMP request (%d)" + " or complete_in_target (%d), thus no TMF\n", + __func__, (task->task_proto == SAS_PROTOCOL_SMP), + test_bit(IREQ_COMPLETE_IN_TARGET, &old_request->flags)); + + /* Set the state on the task. */ + isci_task_all_done(task); + + ret = TMF_RESP_FUNC_COMPLETE; + + /* Stopping and SMP devices are not sent a TMF, and are not + * reset, but the outstanding I/O request is terminated below. + */ + } else { + /* Fill in the tmf stucture */ + isci_task_build_abort_task_tmf(&tmf, isci_tmf_ssp_task_abort, + isci_abort_task_process_cb, + old_request); + + spin_unlock_irqrestore(&isci_host->scic_lock, flags); + + #define ISCI_ABORT_TASK_TIMEOUT_MS 500 /* half second timeout. */ + ret = isci_task_execute_tmf(isci_host, isci_device, &tmf, + ISCI_ABORT_TASK_TIMEOUT_MS); + + if (ret != TMF_RESP_FUNC_COMPLETE) + dev_dbg(&isci_host->pdev->dev, + "%s: isci_task_send_tmf failed\n", + __func__); + } + if (ret == TMF_RESP_FUNC_COMPLETE) { + set_bit(IREQ_COMPLETE_IN_TARGET, &old_request->flags); + + /* Clean up the request on our side, and wait for the aborted + * I/O to complete. + */ + isci_terminate_request_core(isci_host, isci_device, old_request); + } + + /* Make sure we do not leave a reference to aborted_io_completion */ + old_request->io_request_completion = NULL; + out: + isci_put_device(isci_device); + return ret; +} + +/** + * isci_task_abort_task_set() - This function is one of the SAS Domain Template + * functions. This is one of the Task Management functoins called by libsas, + * to abort all task for the given lun. + * @d_device: This parameter specifies the domain device associated with this + * request. + * @lun: This parameter specifies the lun associated with this request. + * + * status, zero indicates success. + */ +int isci_task_abort_task_set( + struct domain_device *d_device, + u8 *lun) +{ + return TMF_RESP_FUNC_FAILED; +} + + +/** + * isci_task_clear_aca() - This function is one of the SAS Domain Template + * functions. This is one of the Task Management functoins called by libsas. + * @d_device: This parameter specifies the domain device associated with this + * request. + * @lun: This parameter specifies the lun associated with this request. + * + * status, zero indicates success. + */ +int isci_task_clear_aca( + struct domain_device *d_device, + u8 *lun) +{ + return TMF_RESP_FUNC_FAILED; +} + + + +/** + * isci_task_clear_task_set() - This function is one of the SAS Domain Template + * functions. This is one of the Task Management functoins called by libsas. + * @d_device: This parameter specifies the domain device associated with this + * request. + * @lun: This parameter specifies the lun associated with this request. + * + * status, zero indicates success. + */ +int isci_task_clear_task_set( + struct domain_device *d_device, + u8 *lun) +{ + return TMF_RESP_FUNC_FAILED; +} + + +/** + * isci_task_query_task() - This function is implemented to cause libsas to + * correctly escalate the failed abort to a LUN or target reset (this is + * because sas_scsi_find_task libsas function does not correctly interpret + * all return codes from the abort task call). When TMF_RESP_FUNC_SUCC is + * returned, libsas turns this into a LUN reset; when FUNC_FAILED is + * returned, libsas will turn this into a target reset + * @task: This parameter specifies the sas task being queried. + * @lun: This parameter specifies the lun associated with this request. + * + * status, zero indicates success. + */ +int isci_task_query_task( + struct sas_task *task) +{ + /* See if there is a pending device reset for this device. */ + if (task->task_state_flags & SAS_TASK_NEED_DEV_RESET) + return TMF_RESP_FUNC_FAILED; + else + return TMF_RESP_FUNC_SUCC; +} + +/* + * isci_task_request_complete() - This function is called by the sci core when + * an task request completes. + * @ihost: This parameter specifies the ISCI host object + * @ireq: This parameter is the completed isci_request object. + * @completion_status: This parameter specifies the completion status from the + * sci core. + * + * none. + */ +void +isci_task_request_complete(struct isci_host *ihost, + struct isci_request *ireq, + enum sci_task_status completion_status) +{ + struct isci_tmf *tmf = isci_request_access_tmf(ireq); + struct completion *tmf_complete; + + dev_dbg(&ihost->pdev->dev, + "%s: request = %p, status=%d\n", + __func__, ireq, completion_status); + + isci_request_change_state(ireq, completed); + + tmf->status = completion_status; + set_bit(IREQ_COMPLETE_IN_TARGET, &ireq->flags); + + if (tmf->proto == SAS_PROTOCOL_SSP) { + memcpy(&tmf->resp.resp_iu, + &ireq->ssp.rsp, + SSP_RESP_IU_MAX_SIZE); + } else if (tmf->proto == SAS_PROTOCOL_SATA) { + memcpy(&tmf->resp.d2h_fis, + &ireq->stp.rsp, + sizeof(struct dev_to_host_fis)); + } + + /* PRINT_TMF( ((struct isci_tmf *)request->task)); */ + tmf_complete = tmf->complete; + + sci_controller_complete_io(ihost, ireq->target_device, ireq); + /* set the 'terminated' flag handle to make sure it cannot be terminated + * or completed again. + */ + set_bit(IREQ_TERMINATED, &ireq->flags); + + isci_request_change_state(ireq, unallocated); + list_del_init(&ireq->dev_node); + + /* The task management part completes last. */ + complete(tmf_complete); +} + +static void isci_smp_task_timedout(unsigned long _task) +{ + struct sas_task *task = (void *) _task; + unsigned long flags; + + spin_lock_irqsave(&task->task_state_lock, flags); + if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) + task->task_state_flags |= SAS_TASK_STATE_ABORTED; + spin_unlock_irqrestore(&task->task_state_lock, flags); + + complete(&task->completion); +} + +static void isci_smp_task_done(struct sas_task *task) +{ + if (!del_timer(&task->timer)) + return; + complete(&task->completion); +} + +static struct sas_task *isci_alloc_task(void) +{ + struct sas_task *task = kzalloc(sizeof(*task), GFP_KERNEL); + + if (task) { + INIT_LIST_HEAD(&task->list); + spin_lock_init(&task->task_state_lock); + task->task_state_flags = SAS_TASK_STATE_PENDING; + init_timer(&task->timer); + init_completion(&task->completion); + } + + return task; +} + +static void isci_free_task(struct isci_host *ihost, struct sas_task *task) +{ + if (task) { + BUG_ON(!list_empty(&task->list)); + kfree(task); + } +} + +static int isci_smp_execute_task(struct isci_host *ihost, + struct domain_device *dev, void *req, + int req_size, void *resp, int resp_size) +{ + int res, retry; + struct sas_task *task = NULL; + + for (retry = 0; retry < 3; retry++) { + task = isci_alloc_task(); + if (!task) + return -ENOMEM; + + task->dev = dev; + task->task_proto = dev->tproto; + sg_init_one(&task->smp_task.smp_req, req, req_size); + sg_init_one(&task->smp_task.smp_resp, resp, resp_size); + + task->task_done = isci_smp_task_done; + + task->timer.data = (unsigned long) task; + task->timer.function = isci_smp_task_timedout; + task->timer.expires = jiffies + 10*HZ; + add_timer(&task->timer); + + res = isci_task_execute_task(task, 1, GFP_KERNEL); + + if (res) { + del_timer(&task->timer); + dev_dbg(&ihost->pdev->dev, + "%s: executing SMP task failed:%d\n", + __func__, res); + goto ex_err; + } + + wait_for_completion(&task->completion); + res = -ECOMM; + if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) { + dev_dbg(&ihost->pdev->dev, + "%s: smp task timed out or aborted\n", + __func__); + isci_task_abort_task(task); + if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) { + dev_dbg(&ihost->pdev->dev, + "%s: SMP task aborted and not done\n", + __func__); + goto ex_err; + } + } + if (task->task_status.resp == SAS_TASK_COMPLETE && + task->task_status.stat == SAM_STAT_GOOD) { + res = 0; + break; + } + if (task->task_status.resp == SAS_TASK_COMPLETE && + task->task_status.stat == SAS_DATA_UNDERRUN) { + /* no error, but return the number of bytes of + * underrun */ + res = task->task_status.residual; + break; + } + if (task->task_status.resp == SAS_TASK_COMPLETE && + task->task_status.stat == SAS_DATA_OVERRUN) { + res = -EMSGSIZE; + break; + } else { + dev_dbg(&ihost->pdev->dev, + "%s: task to dev %016llx response: 0x%x " + "status 0x%x\n", __func__, + SAS_ADDR(dev->sas_addr), + task->task_status.resp, + task->task_status.stat); + isci_free_task(ihost, task); + task = NULL; + } + } +ex_err: + BUG_ON(retry == 3 && task != NULL); + isci_free_task(ihost, task); + return res; +} + +#define DISCOVER_REQ_SIZE 16 +#define DISCOVER_RESP_SIZE 56 + +int isci_smp_get_phy_attached_dev_type(struct isci_host *ihost, + struct domain_device *dev, + int phy_id, int *adt) +{ + struct smp_resp *disc_resp; + u8 *disc_req; + int res; + + disc_resp = kzalloc(DISCOVER_RESP_SIZE, GFP_KERNEL); + if (!disc_resp) + return -ENOMEM; + + disc_req = kzalloc(DISCOVER_REQ_SIZE, GFP_KERNEL); + if (disc_req) { + disc_req[0] = SMP_REQUEST; + disc_req[1] = SMP_DISCOVER; + disc_req[9] = phy_id; + } else { + kfree(disc_resp); + return -ENOMEM; + } + res = isci_smp_execute_task(ihost, dev, disc_req, DISCOVER_REQ_SIZE, + disc_resp, DISCOVER_RESP_SIZE); + if (!res) { + if (disc_resp->result != SMP_RESP_FUNC_ACC) + res = disc_resp->result; + else + *adt = disc_resp->disc.attached_dev_type; + } + kfree(disc_req); + kfree(disc_resp); + + return res; +} + +static void isci_wait_for_smp_phy_reset(struct isci_remote_device *idev, int phy_num) +{ + struct domain_device *dev = idev->domain_dev; + struct isci_port *iport = idev->isci_port; + struct isci_host *ihost = iport->isci_host; + int res, iteration = 0, attached_device_type; + #define STP_WAIT_MSECS 25000 + unsigned long tmo = msecs_to_jiffies(STP_WAIT_MSECS); + unsigned long deadline = jiffies + tmo; + enum { + SMP_PHYWAIT_PHYDOWN, + SMP_PHYWAIT_PHYUP, + SMP_PHYWAIT_DONE + } phy_state = SMP_PHYWAIT_PHYDOWN; + + /* While there is time, wait for the phy to go away and come back */ + while (time_is_after_jiffies(deadline) && phy_state != SMP_PHYWAIT_DONE) { + int event = atomic_read(&iport->event); + + ++iteration; + + tmo = wait_event_timeout(ihost->eventq, + event != atomic_read(&iport->event) || + !test_bit(IPORT_BCN_BLOCKED, &iport->flags), + tmo); + /* link down, stop polling */ + if (!test_bit(IPORT_BCN_BLOCKED, &iport->flags)) + break; + + dev_dbg(&ihost->pdev->dev, + "%s: iport %p, iteration %d," + " phase %d: time_remaining %lu, bcns = %d\n", + __func__, iport, iteration, phy_state, + tmo, test_bit(IPORT_BCN_PENDING, &iport->flags)); + + res = isci_smp_get_phy_attached_dev_type(ihost, dev, phy_num, + &attached_device_type); + tmo = deadline - jiffies; + + if (res) { + dev_dbg(&ihost->pdev->dev, + "%s: iteration %d, phase %d:" + " SMP error=%d, time_remaining=%lu\n", + __func__, iteration, phy_state, res, tmo); + break; + } + dev_dbg(&ihost->pdev->dev, + "%s: iport %p, iteration %d," + " phase %d: time_remaining %lu, bcns = %d, " + "attdevtype = %x\n", + __func__, iport, iteration, phy_state, + tmo, test_bit(IPORT_BCN_PENDING, &iport->flags), + attached_device_type); + + switch (phy_state) { + case SMP_PHYWAIT_PHYDOWN: + /* Has the device gone away? */ + if (!attached_device_type) + phy_state = SMP_PHYWAIT_PHYUP; + + break; + + case SMP_PHYWAIT_PHYUP: + /* Has the device come back? */ + if (attached_device_type) + phy_state = SMP_PHYWAIT_DONE; + break; + + case SMP_PHYWAIT_DONE: + break; + } + + } + dev_dbg(&ihost->pdev->dev, "%s: done\n", __func__); +} + +static int isci_reset_device(struct isci_host *ihost, + struct isci_remote_device *idev) +{ + struct sas_phy *phy = sas_find_local_phy(idev->domain_dev); + struct isci_port *iport = idev->isci_port; + enum sci_status status; + unsigned long flags; + int rc; + + dev_dbg(&ihost->pdev->dev, "%s: idev %p\n", __func__, idev); + + spin_lock_irqsave(&ihost->scic_lock, flags); + status = sci_remote_device_reset(idev); + if (status != SCI_SUCCESS) { + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + dev_dbg(&ihost->pdev->dev, + "%s: sci_remote_device_reset(%p) returned %d!\n", + __func__, idev, status); + + return TMF_RESP_FUNC_FAILED; + } + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + /* Make sure all pending requests are able to be fully terminated. */ + isci_device_clear_reset_pending(ihost, idev); + + /* If this is a device on an expander, disable BCN processing. */ + if (!scsi_is_sas_phy_local(phy)) + set_bit(IPORT_BCN_BLOCKED, &iport->flags); + + rc = sas_phy_reset(phy, true); + + /* Terminate in-progress I/O now. */ + isci_remote_device_nuke_requests(ihost, idev); + + /* Since all pending TCs have been cleaned, resume the RNC. */ + spin_lock_irqsave(&ihost->scic_lock, flags); + status = sci_remote_device_reset_complete(idev); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + /* If this is a device on an expander, bring the phy back up. */ + if (!scsi_is_sas_phy_local(phy)) { + /* A phy reset will cause the device to go away then reappear. + * Since libsas will take action on incoming BCNs (eg. remove + * a device going through an SMP phy-control driven reset), + * we need to wait until the phy comes back up before letting + * discovery proceed in libsas. + */ + isci_wait_for_smp_phy_reset(idev, phy->number); + + spin_lock_irqsave(&ihost->scic_lock, flags); + isci_port_bcn_enable(ihost, idev->isci_port); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + } + + if (status != SCI_SUCCESS) { + dev_dbg(&ihost->pdev->dev, + "%s: sci_remote_device_reset_complete(%p) " + "returned %d!\n", __func__, idev, status); + } + + dev_dbg(&ihost->pdev->dev, "%s: idev %p complete.\n", __func__, idev); + + return rc; +} + +int isci_task_I_T_nexus_reset(struct domain_device *dev) +{ + struct isci_host *ihost = dev_to_ihost(dev); + struct isci_remote_device *idev; + unsigned long flags; + int ret; + + spin_lock_irqsave(&ihost->scic_lock, flags); + idev = isci_lookup_device(dev); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + if (!idev || !test_bit(IDEV_EH, &idev->flags)) { + ret = TMF_RESP_FUNC_COMPLETE; + goto out; + } + + ret = isci_reset_device(ihost, idev); + out: + isci_put_device(idev); + return ret; +} + +int isci_bus_reset_handler(struct scsi_cmnd *cmd) +{ + struct domain_device *dev = sdev_to_domain_dev(cmd->device); + struct isci_host *ihost = dev_to_ihost(dev); + struct isci_remote_device *idev; + unsigned long flags; + int ret; + + spin_lock_irqsave(&ihost->scic_lock, flags); + idev = isci_lookup_device(dev); + spin_unlock_irqrestore(&ihost->scic_lock, flags); + + if (!idev) { + ret = TMF_RESP_FUNC_COMPLETE; + goto out; + } + + ret = isci_reset_device(ihost, idev); + out: + isci_put_device(idev); + return ret; +} diff --git a/drivers/scsi/isci/task.h b/drivers/scsi/isci/task.h new file mode 100644 index 0000000..4a7fa90 --- /dev/null +++ b/drivers/scsi/isci/task.h @@ -0,0 +1,367 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ +#ifndef _ISCI_TASK_H_ +#define _ISCI_TASK_H_ + +#include <scsi/sas_ata.h> +#include "host.h" + +struct isci_request; + +/** + * enum isci_tmf_cb_state - This enum defines the possible states in which the + * TMF callback function is invoked during the TMF execution process. + * + * + */ +enum isci_tmf_cb_state { + + isci_tmf_init_state = 0, + isci_tmf_started, + isci_tmf_timed_out +}; + +/** + * enum isci_tmf_function_codes - This enum defines the possible preparations + * of task management requests. + * + * + */ +enum isci_tmf_function_codes { + + isci_tmf_func_none = 0, + isci_tmf_ssp_task_abort = TMF_ABORT_TASK, + isci_tmf_ssp_lun_reset = TMF_LU_RESET, + isci_tmf_sata_srst_high = TMF_LU_RESET + 0x100, /* Non SCSI */ + isci_tmf_sata_srst_low = TMF_LU_RESET + 0x101 /* Non SCSI */ +}; +/** + * struct isci_tmf - This class represents the task management object which + * acts as an interface to libsas for processing task management requests + * + * + */ +struct isci_tmf { + + struct completion *complete; + enum sas_protocol proto; + union { + struct ssp_response_iu resp_iu; + struct dev_to_host_fis d2h_fis; + u8 rsp_buf[SSP_RESP_IU_MAX_SIZE]; + } resp; + unsigned char lun[8]; + u16 io_tag; + struct isci_remote_device *device; + enum isci_tmf_function_codes tmf_code; + int status; + + /* The optional callback function allows the user process to + * track the TMF transmit / timeout conditions. + */ + void (*cb_state_func)( + enum isci_tmf_cb_state, + struct isci_tmf *, void *); + void *cb_data; + +}; + +static inline void isci_print_tmf(struct isci_tmf *tmf) +{ + if (SAS_PROTOCOL_SATA == tmf->proto) + dev_dbg(&tmf->device->isci_port->isci_host->pdev->dev, + "%s: status = %x\n" + "tmf->resp.d2h_fis.status = %x\n" + "tmf->resp.d2h_fis.error = %x\n", + __func__, + tmf->status, + tmf->resp.d2h_fis.status, + tmf->resp.d2h_fis.error); + else + dev_dbg(&tmf->device->isci_port->isci_host->pdev->dev, + "%s: status = %x\n" + "tmf->resp.resp_iu.data_present = %x\n" + "tmf->resp.resp_iu.status = %x\n" + "tmf->resp.resp_iu.data_length = %x\n" + "tmf->resp.resp_iu.data[0] = %x\n" + "tmf->resp.resp_iu.data[1] = %x\n" + "tmf->resp.resp_iu.data[2] = %x\n" + "tmf->resp.resp_iu.data[3] = %x\n", + __func__, + tmf->status, + tmf->resp.resp_iu.datapres, + tmf->resp.resp_iu.status, + be32_to_cpu(tmf->resp.resp_iu.response_data_len), + tmf->resp.resp_iu.resp_data[0], + tmf->resp.resp_iu.resp_data[1], + tmf->resp.resp_iu.resp_data[2], + tmf->resp.resp_iu.resp_data[3]); +} + + +int isci_task_execute_task( + struct sas_task *task, + int num, + gfp_t gfp_flags); + +int isci_task_abort_task( + struct sas_task *task); + +int isci_task_abort_task_set( + struct domain_device *d_device, + u8 *lun); + +int isci_task_clear_aca( + struct domain_device *d_device, + u8 *lun); + +int isci_task_clear_task_set( + struct domain_device *d_device, + u8 *lun); + +int isci_task_query_task( + struct sas_task *task); + +int isci_task_lu_reset( + struct domain_device *d_device, + u8 *lun); + +int isci_task_clear_nexus_port( + struct asd_sas_port *port); + +int isci_task_clear_nexus_ha( + struct sas_ha_struct *ha); + +int isci_task_I_T_nexus_reset( + struct domain_device *d_device); + +void isci_task_request_complete( + struct isci_host *isci_host, + struct isci_request *request, + enum sci_task_status completion_status); + +u16 isci_task_ssp_request_get_io_tag_to_manage( + struct isci_request *request); + +u8 isci_task_ssp_request_get_function( + struct isci_request *request); + + +void *isci_task_ssp_request_get_response_data_address( + struct isci_request *request); + +u32 isci_task_ssp_request_get_response_data_length( + struct isci_request *request); + +int isci_queuecommand( + struct scsi_cmnd *scsi_cmd, + void (*donefunc)(struct scsi_cmnd *)); + +int isci_bus_reset_handler(struct scsi_cmnd *cmd); + +/** + * enum isci_completion_selection - This enum defines the possible actions to + * take with respect to a given request's notification back to libsas. + * + * + */ +enum isci_completion_selection { + + isci_perform_normal_io_completion, /* Normal notify (task_done) */ + isci_perform_aborted_io_completion, /* No notification. */ + isci_perform_error_io_completion /* Use sas_task_abort */ +}; + +static inline void isci_set_task_doneflags( + struct sas_task *task) +{ + /* Since no futher action will be taken on this task, + * make sure to mark it complete from the lldd perspective. + */ + task->task_state_flags |= SAS_TASK_STATE_DONE; + task->task_state_flags &= ~SAS_TASK_AT_INITIATOR; + task->task_state_flags &= ~SAS_TASK_STATE_PENDING; +} +/** + * isci_task_all_done() - This function clears the task bits to indicate the + * LLDD is done with the task. + * + * + */ +static inline void isci_task_all_done( + struct sas_task *task) +{ + unsigned long flags; + + /* Since no futher action will be taken on this task, + * make sure to mark it complete from the lldd perspective. + */ + spin_lock_irqsave(&task->task_state_lock, flags); + isci_set_task_doneflags(task); + spin_unlock_irqrestore(&task->task_state_lock, flags); +} + +/** + * isci_task_set_completion_status() - This function sets the completion status + * for the request. + * @task: This parameter is the completed request. + * @response: This parameter is the response code for the completed task. + * @status: This parameter is the status code for the completed task. + * +* @return The new notification mode for the request. +*/ +static inline enum isci_completion_selection +isci_task_set_completion_status( + struct sas_task *task, + enum service_response response, + enum exec_status status, + enum isci_completion_selection task_notification_selection) +{ + unsigned long flags; + + spin_lock_irqsave(&task->task_state_lock, flags); + + /* If a device reset is being indicated, make sure the I/O + * is in the error path. + */ + if (task->task_state_flags & SAS_TASK_NEED_DEV_RESET) { + /* Fail the I/O to make sure it goes into the error path. */ + response = SAS_TASK_UNDELIVERED; + status = SAM_STAT_TASK_ABORTED; + + task_notification_selection = isci_perform_error_io_completion; + } + task->task_status.resp = response; + task->task_status.stat = status; + + switch (task_notification_selection) { + + case isci_perform_error_io_completion: + + if (task->task_proto == SAS_PROTOCOL_SMP) { + /* There is no error escalation in the SMP case. + * Convert to a normal completion to avoid the + * timeout in the discovery path and to let the + * next action take place quickly. + */ + task_notification_selection + = isci_perform_normal_io_completion; + + /* Fall through to the normal case... */ + } else { + /* Use sas_task_abort */ + /* Leave SAS_TASK_STATE_DONE clear + * Leave SAS_TASK_AT_INITIATOR set. + */ + break; + } + + case isci_perform_aborted_io_completion: + /* This path can occur with task-managed requests as well as + * requests terminated because of LUN or device resets. + */ + /* Fall through to the normal case... */ + case isci_perform_normal_io_completion: + /* Normal notification (task_done) */ + isci_set_task_doneflags(task); + break; + default: + WARN_ONCE(1, "unknown task_notification_selection: %d\n", + task_notification_selection); + break; + } + + spin_unlock_irqrestore(&task->task_state_lock, flags); + + return task_notification_selection; + +} +/** +* isci_execpath_callback() - This function is called from the task +* execute path when the task needs to callback libsas about the submit-time +* task failure. The callback occurs either through the task's done function +* or through sas_task_abort. In the case of regular non-discovery SATA/STP I/O +* requests, libsas takes the host lock before calling execute task. Therefore +* in this situation the host lock must be managed before calling the func. +* +* @ihost: This parameter is the controller to which the I/O request was sent. +* @task: This parameter is the I/O request. +* @func: This parameter is the function to call in the correct context. +* @status: This parameter is the status code for the completed task. +* +*/ +static inline void isci_execpath_callback(struct isci_host *ihost, + struct sas_task *task, + void (*func)(struct sas_task *)) +{ + struct domain_device *dev = task->dev; + + if (dev_is_sata(dev) && task->uldd_task) { + unsigned long flags; + + /* Since we are still in the submit path, and since + * libsas takes the host lock on behalf of SATA + * devices before I/O starts (in the non-discovery case), + * we need to unlock before we can call the callback function. + */ + raw_local_irq_save(flags); + spin_unlock(dev->sata_dev.ap->lock); + func(task); + spin_lock(dev->sata_dev.ap->lock); + raw_local_irq_restore(flags); + } else + func(task); +} +#endif /* !defined(_SCI_TASK_H_) */ diff --git a/drivers/scsi/isci/unsolicited_frame_control.c b/drivers/scsi/isci/unsolicited_frame_control.c new file mode 100644 index 0000000..e9e1e2a --- /dev/null +++ b/drivers/scsi/isci/unsolicited_frame_control.c @@ -0,0 +1,225 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include "host.h" +#include "unsolicited_frame_control.h" +#include "registers.h" + +int sci_unsolicited_frame_control_construct(struct isci_host *ihost) +{ + struct sci_unsolicited_frame_control *uf_control = &ihost->uf_control; + struct sci_unsolicited_frame *uf; + u32 buf_len, header_len, i; + dma_addr_t dma; + size_t size; + void *virt; + + /* + * Prepare all of the memory sizes for the UF headers, UF address + * table, and UF buffers themselves. + */ + buf_len = SCU_MAX_UNSOLICITED_FRAMES * SCU_UNSOLICITED_FRAME_BUFFER_SIZE; + header_len = SCU_MAX_UNSOLICITED_FRAMES * sizeof(struct scu_unsolicited_frame_header); + size = buf_len + header_len + SCU_MAX_UNSOLICITED_FRAMES * sizeof(dma_addr_t); + + /* + * The Unsolicited Frame buffers are set at the start of the UF + * memory descriptor entry. The headers and address table will be + * placed after the buffers. + */ + virt = dmam_alloc_coherent(&ihost->pdev->dev, size, &dma, GFP_KERNEL); + if (!virt) + return -ENOMEM; + + /* + * Program the location of the UF header table into the SCU. + * Notes: + * - The address must align on a 64-byte boundary. Guaranteed to be + * on 64-byte boundary already 1KB boundary for unsolicited frames. + * - Program unused header entries to overlap with the last + * unsolicited frame. The silicon will never DMA to these unused + * headers, since we program the UF address table pointers to + * NULL. + */ + uf_control->headers.physical_address = dma + buf_len; + uf_control->headers.array = virt + buf_len; + + /* + * Program the location of the UF address table into the SCU. + * Notes: + * - The address must align on a 64-bit boundary. Guaranteed to be on 64 + * byte boundary already due to above programming headers being on a + * 64-bit boundary and headers are on a 64-bytes in size. + */ + uf_control->address_table.physical_address = dma + buf_len + header_len; + uf_control->address_table.array = virt + buf_len + header_len; + uf_control->get = 0; + + /* + * UF buffer requirements are: + * - The last entry in the UF queue is not NULL. + * - There is a power of 2 number of entries (NULL or not-NULL) + * programmed into the queue. + * - Aligned on a 1KB boundary. */ + + /* + * Program the actual used UF buffers into the UF address table and + * the controller's array of UFs. + */ + for (i = 0; i < SCU_MAX_UNSOLICITED_FRAMES; i++) { + uf = &uf_control->buffers.array[i]; + + uf_control->address_table.array[i] = dma; + + uf->buffer = virt; + uf->header = &uf_control->headers.array[i]; + uf->state = UNSOLICITED_FRAME_EMPTY; + + /* + * Increment the address of the physical and virtual memory + * pointers. Everything is aligned on 1k boundary with an + * increment of 1k. + */ + virt += SCU_UNSOLICITED_FRAME_BUFFER_SIZE; + dma += SCU_UNSOLICITED_FRAME_BUFFER_SIZE; + } + + return 0; +} + +enum sci_status sci_unsolicited_frame_control_get_header(struct sci_unsolicited_frame_control *uf_control, + u32 frame_index, + void **frame_header) +{ + if (frame_index < SCU_MAX_UNSOLICITED_FRAMES) { + /* Skip the first word in the frame since this is a controll word used + * by the hardware. + */ + *frame_header = &uf_control->buffers.array[frame_index].header->data; + + return SCI_SUCCESS; + } + + return SCI_FAILURE_INVALID_PARAMETER_VALUE; +} + +enum sci_status sci_unsolicited_frame_control_get_buffer(struct sci_unsolicited_frame_control *uf_control, + u32 frame_index, + void **frame_buffer) +{ + if (frame_index < SCU_MAX_UNSOLICITED_FRAMES) { + *frame_buffer = uf_control->buffers.array[frame_index].buffer; + + return SCI_SUCCESS; + } + + return SCI_FAILURE_INVALID_PARAMETER_VALUE; +} + +bool sci_unsolicited_frame_control_release_frame(struct sci_unsolicited_frame_control *uf_control, + u32 frame_index) +{ + u32 frame_get; + u32 frame_cycle; + + frame_get = uf_control->get & (SCU_MAX_UNSOLICITED_FRAMES - 1); + frame_cycle = uf_control->get & SCU_MAX_UNSOLICITED_FRAMES; + + /* + * In the event there are NULL entries in the UF table, we need to + * advance the get pointer in order to find out if this frame should + * be released (i.e. update the get pointer) + */ + while (lower_32_bits(uf_control->address_table.array[frame_get]) == 0 && + upper_32_bits(uf_control->address_table.array[frame_get]) == 0 && + frame_get < SCU_MAX_UNSOLICITED_FRAMES) + frame_get++; + + /* + * The table has a NULL entry as it's last element. This is + * illegal. + */ + BUG_ON(frame_get >= SCU_MAX_UNSOLICITED_FRAMES); + if (frame_index >= SCU_MAX_UNSOLICITED_FRAMES) + return false; + + uf_control->buffers.array[frame_index].state = UNSOLICITED_FRAME_RELEASED; + + if (frame_get != frame_index) { + /* + * Frames remain in use until we advance the get pointer + * so there is nothing we can do here + */ + return false; + } + + /* + * The frame index is equal to the current get pointer so we + * can now free up all of the frame entries that + */ + while (uf_control->buffers.array[frame_get].state == UNSOLICITED_FRAME_RELEASED) { + uf_control->buffers.array[frame_get].state = UNSOLICITED_FRAME_EMPTY; + + if (frame_get+1 == SCU_MAX_UNSOLICITED_FRAMES-1) { + frame_cycle ^= SCU_MAX_UNSOLICITED_FRAMES; + frame_get = 0; + } else + frame_get++; + } + + uf_control->get = SCU_UFQGP_GEN_BIT(ENABLE_BIT) | frame_cycle | frame_get; + + return true; +} diff --git a/drivers/scsi/isci/unsolicited_frame_control.h b/drivers/scsi/isci/unsolicited_frame_control.h new file mode 100644 index 0000000..31cb950 --- /dev/null +++ b/drivers/scsi/isci/unsolicited_frame_control.h @@ -0,0 +1,278 @@ +/* + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + * The full GNU General Public License is included in this distribution + * in the file called LICENSE.GPL. + * + * BSD LICENSE + * + * Copyright(c) 2008 - 2011 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _SCIC_SDS_UNSOLICITED_FRAME_CONTROL_H_ +#define _SCIC_SDS_UNSOLICITED_FRAME_CONTROL_H_ + +#include "isci.h" + +#define SCU_UNSOLICITED_FRAME_HEADER_DATA_DWORDS 15 + +/** + * struct scu_unsolicited_frame_header - + * + * This structure delineates the format of an unsolicited frame header. The + * first DWORD are UF attributes defined by the silicon architecture. The data + * depicts actual header information received on the link. + */ +struct scu_unsolicited_frame_header { + /** + * This field indicates if there is an Initiator Index Table entry with + * which this header is associated. + */ + u32 iit_exists:1; + + /** + * This field simply indicates the protocol type (i.e. SSP, STP, SMP). + */ + u32 protocol_type:3; + + /** + * This field indicates if the frame is an address frame (IAF or OAF) + * or if it is a information unit frame. + */ + u32 is_address_frame:1; + + /** + * This field simply indicates the connection rate at which the frame + * was received. + */ + u32 connection_rate:4; + + u32 reserved:23; + + /** + * This field represents the actual header data received on the link. + */ + u32 data[SCU_UNSOLICITED_FRAME_HEADER_DATA_DWORDS]; + +}; + + + +/** + * enum unsolicited_frame_state - + * + * This enumeration represents the current unsolicited frame state. The + * controller object can not updtate the hardware unsolicited frame put pointer + * unless it has already processed the priror unsolicited frames. + */ +enum unsolicited_frame_state { + /** + * This state is when the frame is empty and not in use. It is + * different from the released state in that the hardware could DMA + * data to this frame buffer. + */ + UNSOLICITED_FRAME_EMPTY, + + /** + * This state is set when the frame buffer is in use by by some + * object in the system. + */ + UNSOLICITED_FRAME_IN_USE, + + /** + * This state is set when the frame is returned to the free pool + * but one or more frames prior to this one are still in use. + * Once all of the frame before this one are freed it will go to + * the empty state. + */ + UNSOLICITED_FRAME_RELEASED, + + UNSOLICITED_FRAME_MAX_STATES +}; + +/** + * struct sci_unsolicited_frame - + * + * This is the unsolicited frame data structure it acts as the container for + * the current frame state, frame header and frame buffer. + */ +struct sci_unsolicited_frame { + /** + * This field contains the current frame state + */ + enum unsolicited_frame_state state; + + /** + * This field points to the frame header data. + */ + struct scu_unsolicited_frame_header *header; + + /** + * This field points to the frame buffer data. + */ + void *buffer; + +}; + +/** + * struct sci_uf_header_array - + * + * This structure contains all of the unsolicited frame header information. + */ +struct sci_uf_header_array { + /** + * This field is represents a virtual pointer to the start + * address of the UF address table. The table contains + * 64-bit pointers as required by the hardware. + */ + struct scu_unsolicited_frame_header *array; + + /** + * This field specifies the physical address location for the UF + * buffer array. + */ + dma_addr_t physical_address; + +}; + +/** + * struct sci_uf_buffer_array - + * + * This structure contains all of the unsolicited frame buffer (actual payload) + * information. + */ +struct sci_uf_buffer_array { + /** + * This field is the unsolicited frame data its used to manage + * the data for the unsolicited frame requests. It also represents + * the virtual address location that corresponds to the + * physical_address field. + */ + struct sci_unsolicited_frame array[SCU_MAX_UNSOLICITED_FRAMES]; + + /** + * This field specifies the physical address location for the UF + * buffer array. + */ + dma_addr_t physical_address; +}; + +/** + * struct sci_uf_address_table_array - + * + * This object maintains all of the unsolicited frame address table specific + * data. The address table is a collection of 64-bit pointers that point to + * 1KB buffers into which the silicon will DMA unsolicited frames. + */ +struct sci_uf_address_table_array { + /** + * This field represents a virtual pointer that refers to the + * starting address of the UF address table. + * 64-bit pointers are required by the hardware. + */ + dma_addr_t *array; + + /** + * This field specifies the physical address location for the UF + * address table. + */ + dma_addr_t physical_address; + +}; + +/** + * struct sci_unsolicited_frame_control - + * + * This object contains all of the data necessary to handle unsolicited frames. + */ +struct sci_unsolicited_frame_control { + /** + * This field is the software copy of the unsolicited frame queue + * get pointer. The controller object writes this value to the + * hardware to let the hardware put more unsolicited frame entries. + */ + u32 get; + + /** + * This field contains all of the unsolicited frame header + * specific fields. + */ + struct sci_uf_header_array headers; + + /** + * This field contains all of the unsolicited frame buffer + * specific fields. + */ + struct sci_uf_buffer_array buffers; + + /** + * This field contains all of the unsolicited frame address table + * specific fields. + */ + struct sci_uf_address_table_array address_table; + +}; + +struct isci_host; + +int sci_unsolicited_frame_control_construct(struct isci_host *ihost); + +enum sci_status sci_unsolicited_frame_control_get_header( + struct sci_unsolicited_frame_control *uf_control, + u32 frame_index, + void **frame_header); + +enum sci_status sci_unsolicited_frame_control_get_buffer( + struct sci_unsolicited_frame_control *uf_control, + u32 frame_index, + void **frame_buffer); + +bool sci_unsolicited_frame_control_release_frame( + struct sci_unsolicited_frame_control *uf_control, + u32 frame_index); + +#endif /* _SCIC_SDS_UNSOLICITED_FRAME_CONTROL_H_ */ diff --git a/drivers/spi/spi_s3c64xx.c b/drivers/spi/spi_s3c64xx.c index 795828b..8945e20 100644 --- a/drivers/spi/spi_s3c64xx.c +++ b/drivers/spi/spi_s3c64xx.c @@ -116,9 +116,7 @@ (((i)->fifo_lvl_mask + 1))) \ ? 1 : 0) -#define S3C64XX_SPI_ST_TX_DONE(v, i) ((((v) >> (i)->rx_lvl_offset) & \ - (((i)->fifo_lvl_mask + 1) << 1)) \ - ? 1 : 0) +#define S3C64XX_SPI_ST_TX_DONE(v, i) (((v) & (1 << (i)->tx_st_done)) ? 1 : 0) #define TX_FIFO_LVL(v, i) (((v) >> 6) & (i)->fifo_lvl_mask) #define RX_FIFO_LVL(v, i) (((v) >> (i)->rx_lvl_offset) & (i)->fifo_lvl_mask) diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c index 2a20dab..d6620ad 100644 --- a/drivers/ssb/driver_pcicore.c +++ b/drivers/ssb/driver_pcicore.c @@ -516,8 +516,17 @@ static void ssb_pcicore_pcie_setup_workarounds(struct ssb_pcicore *pc) static void ssb_pcicore_init_clientmode(struct ssb_pcicore *pc) { + ssb_pcicore_fix_sprom_core_index(pc); + /* Disable PCI interrupts. */ ssb_write32(pc->dev, SSB_INTVEC, 0); + + /* Additional PCIe always once-executed workarounds */ + if (pc->dev->id.coreid == SSB_DEV_PCIE) { + ssb_pcicore_serdes_workaround(pc); + /* TODO: ASPM */ + /* TODO: Clock Request Update */ + } } void ssb_pcicore_init(struct ssb_pcicore *pc) @@ -529,8 +538,6 @@ void ssb_pcicore_init(struct ssb_pcicore *pc) if (!ssb_device_is_enabled(dev)) ssb_device_enable(dev, 0); - ssb_pcicore_fix_sprom_core_index(pc); - #ifdef CONFIG_SSB_PCICORE_HOSTMODE pc->hostmode = pcicore_is_in_hostmode(pc); if (pc->hostmode) @@ -538,13 +545,6 @@ void ssb_pcicore_init(struct ssb_pcicore *pc) #endif /* CONFIG_SSB_PCICORE_HOSTMODE */ if (!pc->hostmode) ssb_pcicore_init_clientmode(pc); - - /* Additional PCIe always once-executed workarounds */ - if (dev->id.coreid == SSB_DEV_PCIE) { - ssb_pcicore_serdes_workaround(pc); - /* TODO: ASPM */ - /* TODO: Clock Request Update */ - } } static u32 ssb_pcie_read(struct ssb_pcicore *pc, u32 address) diff --git a/drivers/staging/brcm80211/Kconfig b/drivers/staging/brcm80211/Kconfig index f4cf9b2..379cf16 100644 --- a/drivers/staging/brcm80211/Kconfig +++ b/drivers/staging/brcm80211/Kconfig @@ -7,6 +7,7 @@ config BRCMSMAC default n depends on PCI depends on WLAN && MAC80211 + depends on X86 || MIPS select BRCMUTIL select FW_LOADER select CRC_CCITT @@ -20,6 +21,7 @@ config BRCMFMAC default n depends on MMC depends on WLAN && CFG80211 + depends on X86 || MIPS select BRCMUTIL select FW_LOADER select WIRELESS_EXT diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig index 1502d80..20008a4 100644 --- a/drivers/staging/comedi/Kconfig +++ b/drivers/staging/comedi/Kconfig @@ -2,6 +2,7 @@ config COMEDI tristate "Data acquisition support (comedi)" default N depends on m + depends on BROKEN || FRV || M32R || MN10300 || SUPERH || TILE || X86 ---help--- Enable support a wide range of data acquisition devices for Linux. @@ -160,6 +161,7 @@ config COMEDI_PCL730 config COMEDI_PCL812 tristate "Advantech PCL-812/813 and ADlink ACL-8112/8113/8113/8216" + depends on VIRT_TO_BUS default N ---help--- Enable support for Advantech PCL-812/PG, PCL-813/B, ADLink @@ -171,6 +173,7 @@ config COMEDI_PCL812 config COMEDI_PCL816 tristate "Advantech PCL-814 and PCL-816 ISA card support" + depends on VIRT_TO_BUS default N ---help--- Enable support for Advantech PCL-814 and PCL-816 ISA cards @@ -180,6 +183,7 @@ config COMEDI_PCL816 config COMEDI_PCL818 tristate "Advantech PCL-718 and PCL-818 ISA card support" + depends on VIRT_TO_BUS default N ---help--- Enable support for Advantech PCL-818 ISA cards @@ -269,6 +273,7 @@ config COMEDI_DAS800 config COMEDI_DAS1800 tristate "DAS1800 and compatible ISA card support" + depends on VIRT_TO_BUS select COMEDI_FC default N ---help--- @@ -340,6 +345,7 @@ config COMEDI_DT2817 config COMEDI_DT282X tristate "Data Translation DT2821 series and DT-EZ ISA card support" select COMEDI_FC + depends on VIRT_TO_BUS default N ---help--- Enable support for Data Translation DT2821 series including DT-EZ @@ -419,6 +425,7 @@ config COMEDI_ADQ12B config COMEDI_NI_AT_A2150 tristate "NI AT-A2150 ISA card support" depends on COMEDI_NI_COMMON + depends on VIRT_TO_BUS default N ---help--- Enable support for National Instruments AT-A2150 cards @@ -536,6 +543,7 @@ if COMEDI_PCI_DRIVERS && PCI config COMEDI_ADDI_APCI_035 tristate "ADDI-DATA APCI_035 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_035 cards @@ -545,6 +553,7 @@ config COMEDI_ADDI_APCI_035 config COMEDI_ADDI_APCI_1032 tristate "ADDI-DATA APCI_1032 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_1032 cards @@ -554,6 +563,7 @@ config COMEDI_ADDI_APCI_1032 config COMEDI_ADDI_APCI_1500 tristate "ADDI-DATA APCI_1500 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_1500 cards @@ -563,6 +573,7 @@ config COMEDI_ADDI_APCI_1500 config COMEDI_ADDI_APCI_1516 tristate "ADDI-DATA APCI_1516 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_1516 cards @@ -572,6 +583,7 @@ config COMEDI_ADDI_APCI_1516 config COMEDI_ADDI_APCI_1564 tristate "ADDI-DATA APCI_1564 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_1564 cards @@ -581,6 +593,7 @@ config COMEDI_ADDI_APCI_1564 config COMEDI_ADDI_APCI_16XX tristate "ADDI-DATA APCI_16xx support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_16xx cards @@ -590,6 +603,7 @@ config COMEDI_ADDI_APCI_16XX config COMEDI_ADDI_APCI_2016 tristate "ADDI-DATA APCI_2016 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_2016 cards @@ -599,6 +613,7 @@ config COMEDI_ADDI_APCI_2016 config COMEDI_ADDI_APCI_2032 tristate "ADDI-DATA APCI_2032 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_2032 cards @@ -608,6 +623,7 @@ config COMEDI_ADDI_APCI_2032 config COMEDI_ADDI_APCI_2200 tristate "ADDI-DATA APCI_2200 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_2200 cards @@ -617,6 +633,7 @@ config COMEDI_ADDI_APCI_2200 config COMEDI_ADDI_APCI_3001 tristate "ADDI-DATA APCI_3001 support" + depends on VIRT_TO_BUS select COMEDI_FC default N ---help--- @@ -627,6 +644,7 @@ config COMEDI_ADDI_APCI_3001 config COMEDI_ADDI_APCI_3120 tristate "ADDI-DATA APCI_3520 support" + depends on VIRT_TO_BUS select COMEDI_FC default N ---help--- @@ -637,6 +655,7 @@ config COMEDI_ADDI_APCI_3120 config COMEDI_ADDI_APCI_3501 tristate "ADDI-DATA APCI_3501 support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_3501 cards @@ -646,6 +665,7 @@ config COMEDI_ADDI_APCI_3501 config COMEDI_ADDI_APCI_3XXX tristate "ADDI-DATA APCI_3xxx support" + depends on VIRT_TO_BUS default N ---help--- Enable support for ADDI-DATA APCI_3xxx cards @@ -712,6 +732,7 @@ config COMEDI_ADL_PCI9111 config COMEDI_ADL_PCI9118 tristate "ADLink PCI-9118DG, PCI-9118HG, PCI-9118HR support" select COMEDI_FC + depends on VIRT_TO_BUS default N ---help--- Enable support for ADlink PCI-9118DG, PCI-9118HG, PCI-9118HR cards @@ -1287,6 +1308,7 @@ config COMEDI_NI_LABPC depends on COMEDI_MITE select COMEDI_8255 select COMEDI_FC + depends on VIRT_TO_BUS default N ---help--- Enable support for National Instruments Lab-PC and compatibles diff --git a/drivers/staging/iio/Kconfig b/drivers/staging/iio/Kconfig index f96d5b5..d329635 100644 --- a/drivers/staging/iio/Kconfig +++ b/drivers/staging/iio/Kconfig @@ -4,7 +4,7 @@ menuconfig IIO tristate "Industrial I/O support" - depends on !S390 + depends on GENERIC_HARDIRQS help The industrial I/O subsystem provides a unified framework for drivers for many different types of embedded sensors using a diff --git a/drivers/staging/iio/accel/adis16204.h b/drivers/staging/iio/accel/adis16204.h index 5310a42..1690c0d 100644 --- a/drivers/staging/iio/accel/adis16204.h +++ b/drivers/staging/iio/accel/adis16204.h @@ -84,7 +84,6 @@ struct adis16204_state { int adis16204_set_irq(struct iio_dev *indio_dev, bool enable); -#ifdef CONFIG_IIO_RING_BUFFER enum adis16204_scan { ADIS16204_SCAN_SUPPLY, ADIS16204_SCAN_ACC_X, @@ -93,6 +92,7 @@ enum adis16204_scan { ADIS16204_SCAN_TEMP, }; +#ifdef CONFIG_IIO_RING_BUFFER void adis16204_remove_trigger(struct iio_dev *indio_dev); int adis16204_probe_trigger(struct iio_dev *indio_dev); diff --git a/drivers/staging/iio/accel/adis16209.h b/drivers/staging/iio/accel/adis16209.h index 58d08db..3153cbe 100644 --- a/drivers/staging/iio/accel/adis16209.h +++ b/drivers/staging/iio/accel/adis16209.h @@ -121,8 +121,6 @@ struct adis16209_state { int adis16209_set_irq(struct iio_dev *indio_dev, bool enable); -#ifdef CONFIG_IIO_RING_BUFFER - #define ADIS16209_SCAN_SUPPLY 0 #define ADIS16209_SCAN_ACC_X 1 #define ADIS16209_SCAN_ACC_Y 2 @@ -132,6 +130,8 @@ int adis16209_set_irq(struct iio_dev *indio_dev, bool enable); #define ADIS16209_SCAN_INCLI_Y 6 #define ADIS16209_SCAN_ROT 7 +#ifdef CONFIG_IIO_RING_BUFFER + void adis16209_remove_trigger(struct iio_dev *indio_dev); int adis16209_probe_trigger(struct iio_dev *indio_dev); diff --git a/drivers/staging/iio/gyro/adis16260.h b/drivers/staging/iio/gyro/adis16260.h index 702dc98..24bf70e 100644 --- a/drivers/staging/iio/gyro/adis16260.h +++ b/drivers/staging/iio/gyro/adis16260.h @@ -104,7 +104,6 @@ struct adis16260_state { int adis16260_set_irq(struct iio_dev *indio_dev, bool enable); -#ifdef CONFIG_IIO_RING_BUFFER /* At the moment triggers are only used for ring buffer * filling. This may change! */ @@ -115,6 +114,7 @@ int adis16260_set_irq(struct iio_dev *indio_dev, bool enable); #define ADIS16260_SCAN_TEMP 3 #define ADIS16260_SCAN_ANGL 4 +#ifdef CONFIG_IIO_RING_BUFFER void adis16260_remove_trigger(struct iio_dev *indio_dev); int adis16260_probe_trigger(struct iio_dev *indio_dev); diff --git a/drivers/staging/iio/imu/adis16400.h b/drivers/staging/iio/imu/adis16400.h index db184d1..e87715b 100644 --- a/drivers/staging/iio/imu/adis16400.h +++ b/drivers/staging/iio/imu/adis16400.h @@ -158,7 +158,6 @@ struct adis16400_state { int adis16400_set_irq(struct iio_dev *indio_dev, bool enable); -#ifdef CONFIG_IIO_RING_BUFFER /* At the moment triggers are only used for ring buffer * filling. This may change! */ @@ -182,6 +181,7 @@ int adis16400_set_irq(struct iio_dev *indio_dev, bool enable); #define ADIS16300_SCAN_INCLI_X 12 #define ADIS16300_SCAN_INCLI_Y 13 +#ifdef CONFIG_IIO_RING_BUFFER void adis16400_remove_trigger(struct iio_dev *indio_dev); int adis16400_probe_trigger(struct iio_dev *indio_dev); diff --git a/drivers/staging/lirc/lirc_imon.c b/drivers/staging/lirc/lirc_imon.c index 4039eda..4a9e563 100644 --- a/drivers/staging/lirc/lirc_imon.c +++ b/drivers/staging/lirc/lirc_imon.c @@ -672,8 +672,6 @@ static void imon_incoming_packet(struct imon_context *context, static void usb_rx_callback(struct urb *urb) { struct imon_context *context; - unsigned char *buf; - int len; int intfnum = 0; if (!urb) @@ -683,9 +681,6 @@ static void usb_rx_callback(struct urb *urb) if (!context) return; - buf = urb->transfer_buffer; - len = urb->actual_length; - switch (urb->status) { case -ENOENT: /* usbcore unlink successful! */ return; @@ -728,7 +723,6 @@ static int imon_probe(struct usb_interface *interface, int ir_ep_found = 0; int alloc_status = 0; int vfd_proto_6p = 0; - int code_length; struct imon_context *context = NULL; int i; u16 vendor, product; @@ -749,8 +743,6 @@ static int imon_probe(struct usb_interface *interface, else context->display = 1; - code_length = BUF_CHUNK_SIZE * 8; - usbdev = usb_get_dev(interface_to_usbdev(interface)); iface_desc = interface->cur_altsetting; num_endpts = iface_desc->desc.bNumEndpoints; @@ -856,7 +848,7 @@ static int imon_probe(struct usb_interface *interface, strcpy(driver->name, MOD_NAME); driver->minor = -1; - driver->code_length = sizeof(int) * 8; + driver->code_length = BUF_CHUNK_SIZE * 8; driver->sample_rate = 0; driver->features = LIRC_CAN_REC_MODE2; driver->data = context; diff --git a/drivers/staging/lirc/lirc_serial.c b/drivers/staging/lirc/lirc_serial.c index 4a3cca0..805df91 100644 --- a/drivers/staging/lirc/lirc_serial.c +++ b/drivers/staging/lirc/lirc_serial.c @@ -838,7 +838,23 @@ static int hardware_init_port(void) static int init_port(void) { - int i, nlow, nhigh; + int i, nlow, nhigh, result; + + result = request_irq(irq, irq_handler, + IRQF_DISABLED | (share_irq ? IRQF_SHARED : 0), + LIRC_DRIVER_NAME, (void *)&hardware); + + switch (result) { + case -EBUSY: + printk(KERN_ERR LIRC_DRIVER_NAME ": IRQ %d busy\n", irq); + return -EBUSY; + case -EINVAL: + printk(KERN_ERR LIRC_DRIVER_NAME + ": Bad irq number or handler\n"); + return -EINVAL; + default: + break; + }; /* Reserve io region. */ /* @@ -893,34 +909,17 @@ static int init_port(void) printk(KERN_INFO LIRC_DRIVER_NAME ": Manually using active " "%s receiver\n", sense ? "low" : "high"); + dprintk("Interrupt %d, port %04x obtained\n", irq, io); return 0; } static int set_use_inc(void *data) { - int result; unsigned long flags; /* initialize timestamp */ do_gettimeofday(&lasttv); - result = request_irq(irq, irq_handler, - IRQF_DISABLED | (share_irq ? IRQF_SHARED : 0), - LIRC_DRIVER_NAME, (void *)&hardware); - - switch (result) { - case -EBUSY: - printk(KERN_ERR LIRC_DRIVER_NAME ": IRQ %d busy\n", irq); - return -EBUSY; - case -EINVAL: - printk(KERN_ERR LIRC_DRIVER_NAME - ": Bad irq number or handler\n"); - return -EINVAL; - default: - dprintk("Interrupt %d, port %04x obtained\n", irq, io); - break; - } - spin_lock_irqsave(&hardware[type].lock, flags); /* Set DLAB 0. */ @@ -945,10 +944,6 @@ static void set_use_dec(void *data) soutp(UART_IER, sinp(UART_IER) & (~(UART_IER_MSI|UART_IER_RLSI|UART_IER_THRI|UART_IER_RDI))); spin_unlock_irqrestore(&hardware[type].lock, flags); - - free_irq(irq, (void *)&hardware); - - dprintk("freed IRQ %d\n", irq); } static ssize_t lirc_write(struct file *file, const char *buf, @@ -1256,6 +1251,9 @@ exit_serial_exit: static void __exit lirc_serial_exit_module(void) { lirc_serial_exit(); + + free_irq(irq, (void *)&hardware); + if (iommap != 0) release_mem_region(iommap, 8 << ioshift); else diff --git a/drivers/staging/lirc/lirc_sir.c b/drivers/staging/lirc/lirc_sir.c index a7b46f2..0d38645 100644 --- a/drivers/staging/lirc/lirc_sir.c +++ b/drivers/staging/lirc/lirc_sir.c @@ -739,23 +739,16 @@ static void send_space(unsigned long len) static void send_pulse(unsigned long len) { long bytes_out = len / TIME_CONST; - long time_left; - time_left = (long)len - (long)bytes_out * (long)TIME_CONST; - if (bytes_out == 0) { + if (bytes_out == 0) bytes_out++; - time_left = 0; - } + while (bytes_out--) { outb(PULSE, io + UART_TX); /* FIXME treba seriozne cakanie z char/serial.c */ while (!(inb(io + UART_LSR) & UART_LSR_THRE)) ; } -#if 0 - if (time_left > 0) - safe_udelay(time_left); -#endif } #endif diff --git a/drivers/staging/lirc/lirc_zilog.c b/drivers/staging/lirc/lirc_zilog.c index dd6a57c..4e051f6 100644 --- a/drivers/staging/lirc/lirc_zilog.c +++ b/drivers/staging/lirc/lirc_zilog.c @@ -475,14 +475,14 @@ static int lirc_thread(void *arg) dprintk("poll thread started\n"); while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + /* if device not opened, we can sleep half a second */ if (atomic_read(&ir->open_count) == 0) { schedule_timeout(HZ/2); continue; } - set_current_state(TASK_INTERRUPTIBLE); - /* * This is ~113*2 + 24 + jitter (2*repeat gap + code length). * We use this interval as the chip resets every time you poll diff --git a/drivers/staging/mei/init.c b/drivers/staging/mei/init.c index d1ffa32..685fcf6 100644 --- a/drivers/staging/mei/init.c +++ b/drivers/staging/mei/init.c @@ -189,7 +189,7 @@ int mei_hw_init(struct mei_device *dev) mutex_lock(&dev->device_lock); } - if (!err && !dev->recvd_msg) { + if (err <= 0 && !dev->recvd_msg) { dev->mei_state = MEI_DISABLED; dev_dbg(&dev->pdev->dev, "wait_event_interruptible_timeout failed" diff --git a/drivers/staging/mei/wd.c b/drivers/staging/mei/wd.c index 2564b03..fff53d0 100644 --- a/drivers/staging/mei/wd.c +++ b/drivers/staging/mei/wd.c @@ -169,10 +169,15 @@ int mei_wd_stop(struct mei_device *dev, bool preserve) ret = wait_event_interruptible_timeout(dev->wait_stop_wd, dev->wd_stopped, 10 * HZ); mutex_lock(&dev->device_lock); - if (!dev->wd_stopped) - dev_dbg(&dev->pdev->dev, "stop wd failed to complete.\n"); - else - dev_dbg(&dev->pdev->dev, "stop wd complete.\n"); + if (dev->wd_stopped) { + dev_dbg(&dev->pdev->dev, "stop wd complete ret=%d.\n", ret); + ret = 0; + } else { + if (!ret) + ret = -ETIMEDOUT; + dev_warn(&dev->pdev->dev, + "stop wd failed to complete ret=%d.\n", ret); + } if (preserve) dev->wd_timeout = wd_timeout; diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index dee2a2c..70c2e7f 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -386,7 +386,7 @@ static int tcm_loop_device_reset(struct scsi_cmnd *sc) */ se_cmd->se_tmr_req = core_tmr_alloc_req(se_cmd, (void *)tl_tmr, TMR_LUN_RESET); - if (!se_cmd->se_tmr_req) + if (IS_ERR(se_cmd->se_tmr_req)) goto release; /* * Locate the underlying TCM struct se_lun from sc->device->lun @@ -1017,6 +1017,7 @@ static int tcm_loop_make_nexus( struct se_portal_group *se_tpg; struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba; struct tcm_loop_nexus *tl_nexus; + int ret = -ENOMEM; if (tl_tpg->tl_hba->tl_nexus) { printk(KERN_INFO "tl_tpg->tl_hba->tl_nexus already exists\n"); @@ -1033,8 +1034,10 @@ static int tcm_loop_make_nexus( * Initialize the struct se_session pointer */ tl_nexus->se_sess = transport_init_session(); - if (!tl_nexus->se_sess) + if (IS_ERR(tl_nexus->se_sess)) { + ret = PTR_ERR(tl_nexus->se_sess); goto out; + } /* * Since we are running in 'demo mode' this call with generate a * struct se_node_acl for the tcm_loop struct se_portal_group with the SCSI @@ -1060,7 +1063,7 @@ static int tcm_loop_make_nexus( out: kfree(tl_nexus); - return -ENOMEM; + return ret; } static int tcm_loop_drop_nexus( @@ -1140,7 +1143,7 @@ static ssize_t tcm_loop_tpg_store_nexus( * the fabric protocol_id set in tcm_loop_make_scsi_hba(), and call * tcm_loop_make_nexus() */ - if (strlen(page) > TL_WWN_ADDR_LEN) { + if (strlen(page) >= TL_WWN_ADDR_LEN) { printk(KERN_ERR "Emulated NAA Sas Address: %s, exceeds" " max: %d\n", page, TL_WWN_ADDR_LEN); return -EINVAL; @@ -1321,7 +1324,7 @@ struct se_wwn *tcm_loop_make_scsi_hba( return ERR_PTR(-EINVAL); check_len: - if (strlen(name) > TL_WWN_ADDR_LEN) { + if (strlen(name) >= TL_WWN_ADDR_LEN) { printk(KERN_ERR "Emulated NAA %s Address: %s, exceeds" " max: %d\n", name, tcm_loop_dump_proto_id(tl_hba), TL_WWN_ADDR_LEN); diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index ee6fad9..25c1f49 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -304,7 +304,7 @@ struct target_fabric_configfs *target_fabric_configfs_init( printk(KERN_ERR "Unable to locate passed fabric name\n"); return NULL; } - if (strlen(name) > TARGET_FABRIC_NAME_SIZE) { + if (strlen(name) >= TARGET_FABRIC_NAME_SIZE) { printk(KERN_ERR "Passed name: %s exceeds TARGET_FABRIC" "_NAME_SIZE\n", name); return NULL; @@ -312,7 +312,7 @@ struct target_fabric_configfs *target_fabric_configfs_init( tf = kzalloc(sizeof(struct target_fabric_configfs), GFP_KERNEL); if (!(tf)) - return ERR_PTR(-ENOMEM); + return NULL; INIT_LIST_HEAD(&tf->tf_list); atomic_set(&tf->tf_access_cnt, 0); @@ -851,7 +851,7 @@ static ssize_t target_core_dev_wwn_store_attr_vpd_unit_serial( return -EOPNOTSUPP; } - if ((strlen(page) + 1) > INQUIRY_VPD_SERIAL_LEN) { + if (strlen(page) >= INQUIRY_VPD_SERIAL_LEN) { printk(KERN_ERR "Emulated VPD Unit Serial exceeds" " INQUIRY_VPD_SERIAL_LEN: %d\n", INQUIRY_VPD_SERIAL_LEN); return -EOVERFLOW; @@ -917,7 +917,7 @@ static ssize_t target_core_dev_wwn_show_attr_vpd_protocol_identifier( transport_dump_vpd_proto_id(vpd, buf, VPD_TMP_BUF_SIZE); - if ((len + strlen(buf) > PAGE_SIZE)) + if ((len + strlen(buf) >= PAGE_SIZE)) break; len += sprintf(page+len, "%s", buf); @@ -962,19 +962,19 @@ static ssize_t target_core_dev_wwn_show_attr_##_name( \ \ memset(buf, 0, VPD_TMP_BUF_SIZE); \ transport_dump_vpd_assoc(vpd, buf, VPD_TMP_BUF_SIZE); \ - if ((len + strlen(buf) > PAGE_SIZE)) \ + if ((len + strlen(buf) >= PAGE_SIZE)) \ break; \ len += sprintf(page+len, "%s", buf); \ \ memset(buf, 0, VPD_TMP_BUF_SIZE); \ transport_dump_vpd_ident_type(vpd, buf, VPD_TMP_BUF_SIZE); \ - if ((len + strlen(buf) > PAGE_SIZE)) \ + if ((len + strlen(buf) >= PAGE_SIZE)) \ break; \ len += sprintf(page+len, "%s", buf); \ \ memset(buf, 0, VPD_TMP_BUF_SIZE); \ transport_dump_vpd_ident(vpd, buf, VPD_TMP_BUF_SIZE); \ - if ((len + strlen(buf) > PAGE_SIZE)) \ + if ((len + strlen(buf) >= PAGE_SIZE)) \ break; \ len += sprintf(page+len, "%s", buf); \ } \ @@ -1299,7 +1299,7 @@ static ssize_t target_core_dev_pr_show_attr_res_pr_registered_i_pts( &i_buf[0] : "", pr_reg->pr_res_key, pr_reg->pr_res_generation); - if ((len + strlen(buf) > PAGE_SIZE)) + if ((len + strlen(buf) >= PAGE_SIZE)) break; len += sprintf(page+len, "%s", buf); @@ -1496,7 +1496,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( ret = -ENOMEM; goto out; } - if (strlen(i_port) > PR_APTPL_MAX_IPORT_LEN) { + if (strlen(i_port) >= PR_APTPL_MAX_IPORT_LEN) { printk(KERN_ERR "APTPL metadata initiator_node=" " exceeds PR_APTPL_MAX_IPORT_LEN: %d\n", PR_APTPL_MAX_IPORT_LEN); @@ -1510,7 +1510,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( ret = -ENOMEM; goto out; } - if (strlen(isid) > PR_REG_ISID_LEN) { + if (strlen(isid) >= PR_REG_ISID_LEN) { printk(KERN_ERR "APTPL metadata initiator_isid" "= exceeds PR_REG_ISID_LEN: %d\n", PR_REG_ISID_LEN); @@ -1571,7 +1571,7 @@ static ssize_t target_core_dev_pr_store_attr_res_aptpl_metadata( ret = -ENOMEM; goto out; } - if (strlen(t_port) > PR_APTPL_MAX_TPORT_LEN) { + if (strlen(t_port) >= PR_APTPL_MAX_TPORT_LEN) { printk(KERN_ERR "APTPL metadata target_node=" " exceeds PR_APTPL_MAX_TPORT_LEN: %d\n", PR_APTPL_MAX_TPORT_LEN); @@ -3052,7 +3052,7 @@ static struct config_group *target_core_call_addhbatotarget( int ret; memset(buf, 0, TARGET_CORE_NAME_MAX_LEN); - if (strlen(name) > TARGET_CORE_NAME_MAX_LEN) { + if (strlen(name) >= TARGET_CORE_NAME_MAX_LEN) { printk(KERN_ERR "Passed *name strlen(): %d exceeds" " TARGET_CORE_NAME_MAX_LEN: %d\n", (int)strlen(name), TARGET_CORE_NAME_MAX_LEN); diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c index 8407f9c..ba698ea 100644 --- a/drivers/target/target_core_device.c +++ b/drivers/target/target_core_device.c @@ -192,7 +192,7 @@ int transport_get_lun_for_tmr( &SE_NODE_ACL(se_sess)->device_list[unpacked_lun]; if (deve->lun_flags & TRANSPORT_LUNFLAGS_INITIATOR_ACCESS) { se_lun = se_cmd->se_lun = se_tmr->tmr_lun = deve->se_lun; - dev = se_tmr->tmr_dev = se_lun->lun_se_dev; + dev = se_lun->lun_se_dev; se_cmd->pr_res_key = deve->pr_res_key; se_cmd->orig_fe_lun = unpacked_lun; se_cmd->se_orig_obj_ptr = SE_LUN(se_cmd)->lun_se_dev; @@ -216,6 +216,7 @@ int transport_get_lun_for_tmr( se_cmd->se_cmd_flags |= SCF_SCSI_CDB_EXCEPTION; return -1; } + se_tmr->tmr_dev = dev; spin_lock(&dev->se_tmr_lock); list_add_tail(&se_tmr->tmr_list, &dev->dev_tmr_list); @@ -1430,7 +1431,7 @@ struct se_lun_acl *core_dev_init_initiator_node_lun_acl( struct se_lun_acl *lacl; struct se_node_acl *nacl; - if (strlen(initiatorname) > TRANSPORT_IQN_LEN) { + if (strlen(initiatorname) >= TRANSPORT_IQN_LEN) { printk(KERN_ERR "%s InitiatorName exceeds maximum size.\n", TPG_TFO(tpg)->get_fabric_name()); *ret = -EOVERFLOW; diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index a79f518..b662db3 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -1916,7 +1916,7 @@ static int __core_scsi3_update_aptpl_buf( pr_reg->pr_res_mapped_lun); } - if ((len + strlen(tmp) > pr_aptpl_buf_len)) { + if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { printk(KERN_ERR "Unable to update renaming" " APTPL metadata\n"); spin_unlock(&T10_RES(su_dev)->registration_lock); @@ -1934,7 +1934,7 @@ static int __core_scsi3_update_aptpl_buf( TPG_TFO(tpg)->tpg_get_tag(tpg), lun->lun_sep->sep_rtpi, lun->unpacked_lun, reg_count); - if ((len + strlen(tmp) > pr_aptpl_buf_len)) { + if ((len + strlen(tmp) >= pr_aptpl_buf_len)) { printk(KERN_ERR "Unable to update renaming" " APTPL metadata\n"); spin_unlock(&T10_RES(su_dev)->registration_lock); @@ -1986,7 +1986,7 @@ static int __core_scsi3_write_aptpl_to_file( memset(iov, 0, sizeof(struct iovec)); memset(path, 0, 512); - if (strlen(&wwn->unit_serial[0]) > 512) { + if (strlen(&wwn->unit_serial[0]) >= 512) { printk(KERN_ERR "WWN value for struct se_device does not fit" " into path buffer\n"); return -1; diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index 59b8b9c..179063d 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -75,10 +75,16 @@ void core_tmr_release_req( { struct se_device *dev = tmr->tmr_dev; + if (!dev) { + kmem_cache_free(se_tmr_req_cache, tmr); + return; + } + spin_lock(&dev->se_tmr_lock); list_del(&tmr->tmr_list); - kmem_cache_free(se_tmr_req_cache, tmr); spin_unlock(&dev->se_tmr_lock); + + kmem_cache_free(se_tmr_req_cache, tmr); } static void core_tmr_handle_tas_abort( diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 4dafeb8..4b9b716 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -536,13 +536,13 @@ EXPORT_SYMBOL(transport_register_session); void transport_deregister_session_configfs(struct se_session *se_sess) { struct se_node_acl *se_nacl; - + unsigned long flags; /* * Used by struct se_node_acl's under ConfigFS to locate active struct se_session */ se_nacl = se_sess->se_node_acl; if ((se_nacl)) { - spin_lock_irq(&se_nacl->nacl_sess_lock); + spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags); list_del(&se_sess->sess_acl_list); /* * If the session list is empty, then clear the pointer. @@ -556,7 +556,7 @@ void transport_deregister_session_configfs(struct se_session *se_sess) se_nacl->acl_sess_list.prev, struct se_session, sess_acl_list); } - spin_unlock_irq(&se_nacl->nacl_sess_lock); + spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags); } } EXPORT_SYMBOL(transport_deregister_session_configfs); diff --git a/drivers/target/tcm_fc/tcm_fc.h b/drivers/target/tcm_fc/tcm_fc.h index defff32..7b82f1b 100644 --- a/drivers/target/tcm_fc/tcm_fc.h +++ b/drivers/target/tcm_fc/tcm_fc.h @@ -144,7 +144,7 @@ enum ft_cmd_state { */ struct ft_cmd { enum ft_cmd_state state; - u16 lun; /* LUN from request */ + u32 lun; /* LUN from request */ struct ft_sess *sess; /* session held for cmd */ struct fc_seq *seq; /* sequence in exchange mgr */ struct se_cmd se_cmd; /* Local TCM I/O descriptor */ diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c index c056a11..b2a1067 100644 --- a/drivers/target/tcm_fc/tfc_cmd.c +++ b/drivers/target/tcm_fc/tfc_cmd.c @@ -94,29 +94,6 @@ void ft_dump_cmd(struct ft_cmd *cmd, const char *caller) 16, 4, cmd->cdb, MAX_COMMAND_SIZE, 0); } -/* - * Get LUN from CDB. - */ -static int ft_get_lun_for_cmd(struct ft_cmd *cmd, u8 *lunp) -{ - u64 lun; - - lun = lunp[1]; - switch (lunp[0] >> 6) { - case 0: - break; - case 1: - lun |= (lunp[0] & 0x3f) << 8; - break; - default: - return -1; - } - if (lun >= TRANSPORT_MAX_LUNS_PER_TPG) - return -1; - cmd->lun = lun; - return transport_get_lun_for_cmd(&cmd->se_cmd, NULL, lun); -} - static void ft_queue_cmd(struct ft_sess *sess, struct ft_cmd *cmd) { struct se_queue_obj *qobj; @@ -418,6 +395,7 @@ static void ft_send_tm(struct ft_cmd *cmd) { struct se_tmr_req *tmr; struct fcp_cmnd *fcp; + struct ft_sess *sess; u8 tm_func; fcp = fc_frame_payload_get(cmd->req_frame, sizeof(*fcp)); @@ -425,13 +403,6 @@ static void ft_send_tm(struct ft_cmd *cmd) switch (fcp->fc_tm_flags) { case FCP_TMF_LUN_RESET: tm_func = TMR_LUN_RESET; - if (ft_get_lun_for_cmd(cmd, fcp->fc_lun) < 0) { - ft_dump_cmd(cmd, __func__); - transport_send_check_condition_and_sense(&cmd->se_cmd, - cmd->se_cmd.scsi_sense_reason, 0); - ft_sess_put(cmd->sess); - return; - } break; case FCP_TMF_TGT_RESET: tm_func = TMR_TARGET_WARM_RESET; @@ -463,6 +434,36 @@ static void ft_send_tm(struct ft_cmd *cmd) return; } cmd->se_cmd.se_tmr_req = tmr; + + switch (fcp->fc_tm_flags) { + case FCP_TMF_LUN_RESET: + cmd->lun = scsilun_to_int((struct scsi_lun *)fcp->fc_lun); + if (transport_get_lun_for_tmr(&cmd->se_cmd, cmd->lun) < 0) { + /* + * Make sure to clean up newly allocated TMR request + * since "unable to handle TMR request because failed + * to get to LUN" + */ + FT_TM_DBG("Failed to get LUN for TMR func %d, " + "se_cmd %p, unpacked_lun %d\n", + tm_func, &cmd->se_cmd, cmd->lun); + ft_dump_cmd(cmd, __func__); + sess = cmd->sess; + transport_send_check_condition_and_sense(&cmd->se_cmd, + cmd->se_cmd.scsi_sense_reason, 0); + transport_generic_free_cmd(&cmd->se_cmd, 0, 1, 0); + ft_sess_put(sess); + return; + } + break; + case FCP_TMF_TGT_RESET: + case FCP_TMF_CLR_TASK_SET: + case FCP_TMF_ABT_TASK_SET: + case FCP_TMF_CLR_ACA: + break; + default: + return; + } transport_generic_handle_tmr(&cmd->se_cmd); } @@ -635,7 +636,8 @@ static void ft_send_cmd(struct ft_cmd *cmd) fc_seq_exch(cmd->seq)->lp->tt.seq_set_resp(cmd->seq, ft_recv_seq, cmd); - ret = ft_get_lun_for_cmd(cmd, fcp->fc_lun); + cmd->lun = scsilun_to_int((struct scsi_lun *)fcp->fc_lun); + ret = transport_get_lun_for_cmd(&cmd->se_cmd, NULL, cmd->lun); if (ret < 0) { ft_dump_cmd(cmd, __func__); transport_send_check_condition_and_sense(&cmd->se_cmd, diff --git a/drivers/target/tcm_fc/tfc_io.c b/drivers/target/tcm_fc/tfc_io.c index 4c3c0ef..8c4a240 100644 --- a/drivers/target/tcm_fc/tfc_io.c +++ b/drivers/target/tcm_fc/tfc_io.c @@ -203,7 +203,7 @@ int ft_queue_data_in(struct se_cmd *se_cmd) /* XXX For now, initiator will retry */ if (printk_ratelimit()) printk(KERN_ERR "%s: Failed to send frame %p, " - "xid <0x%x>, remaining <0x%x>, " + "xid <0x%x>, remaining %zu, " "lso_max <0x%x>\n", __func__, fp, ep->xid, remaining, lport->lso_max); diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c index a3bd57f..7491e21 100644 --- a/drivers/target/tcm_fc/tfc_sess.c +++ b/drivers/target/tcm_fc/tfc_sess.c @@ -229,7 +229,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id, return NULL; sess->se_sess = transport_init_session(); - if (!sess->se_sess) { + if (IS_ERR(sess->se_sess)) { kfree(sess); return NULL; } @@ -332,7 +332,7 @@ void ft_sess_close(struct se_session *se_sess) lport = sess->tport->lport; port_id = sess->port_id; if (port_id == -1) { - mutex_lock(&ft_lport_lock); + mutex_unlock(&ft_lport_lock); return; } FT_SESS_DBG("port_id %x\n", port_id); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 09e8c7d..19b4ae0 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -875,7 +875,8 @@ static int gsm_dlci_data_output_framed(struct gsm_mux *gsm, *dp++ = last << 7 | first << 6 | 1; /* EA */ len--; } - memcpy(dp, skb_pull(dlci->skb, len), len); + memcpy(dp, dlci->skb->data, len); + skb_pull(dlci->skb, len); __gsm_data_queue(dlci, msg); if (last) dlci->skb = NULL; @@ -984,10 +985,22 @@ static void gsm_control_reply(struct gsm_mux *gsm, int cmd, u8 *data, */ static void gsm_process_modem(struct tty_struct *tty, struct gsm_dlci *dlci, - u32 modem) + u32 modem, int clen) { int mlines = 0; - u8 brk = modem >> 6; + u8 brk = 0; + + /* The modem status command can either contain one octet (v.24 signals) + or two octets (v.24 signals + break signals). The length field will + either be 2 or 3 respectively. This is specified in section + 5.4.6.3.7 of the 27.010 mux spec. */ + + if (clen == 2) + modem = modem & 0x7f; + else { + brk = modem & 0x7f; + modem = (modem >> 7) & 0x7f; + }; /* Flow control/ready to communicate */ if (modem & MDM_FC) { @@ -1061,7 +1074,7 @@ static void gsm_control_modem(struct gsm_mux *gsm, u8 *data, int clen) return; } tty = tty_port_tty_get(&dlci->port); - gsm_process_modem(tty, dlci, modem); + gsm_process_modem(tty, dlci, modem, clen); if (tty) { tty_wakeup(tty); tty_kref_put(tty); @@ -1482,12 +1495,13 @@ static void gsm_dlci_begin_close(struct gsm_dlci *dlci) * open we shovel the bits down it, if not we drop them. */ -static void gsm_dlci_data(struct gsm_dlci *dlci, u8 *data, int len) +static void gsm_dlci_data(struct gsm_dlci *dlci, u8 *data, int clen) { /* krefs .. */ struct tty_port *port = &dlci->port; struct tty_struct *tty = tty_port_tty_get(port); unsigned int modem = 0; + int len = clen; if (debug & 16) pr_debug("%d bytes for tty %p\n", len, tty); @@ -1507,7 +1521,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, u8 *data, int len) if (len == 0) return; } - gsm_process_modem(tty, dlci, modem); + gsm_process_modem(tty, dlci, modem, clen); /* Line state will go via DLCI 0 controls only */ case 1: default: diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 0ad3288..c3954fb 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1815,6 +1815,7 @@ do_it_again: /* FIXME: does n_tty_set_room need locking ? */ n_tty_set_room(tty); timeout = schedule_timeout(timeout); + BUG_ON(!tty->read_buf); continue; } __set_current_state(TASK_RUNNING); diff --git a/drivers/tty/serial/8250.c b/drivers/tty/serial/8250.c index b40f7b9..b4129f5 100644 --- a/drivers/tty/serial/8250.c +++ b/drivers/tty/serial/8250.c @@ -3318,6 +3318,7 @@ void serial8250_unregister_port(int line) uart->port.flags &= ~UPF_BOOT_AUTOCONF; uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; + uart->capabilities = uart_config[uart->port.type].flags; uart_add_one_port(&serial8250_reg, &uart->port); } else { uart->port.dev = NULL; diff --git a/drivers/tty/serial/8250_pci.c b/drivers/tty/serial/8250_pci.c index 4b4968a..f41b425 100644 --- a/drivers/tty/serial/8250_pci.c +++ b/drivers/tty/serial/8250_pci.c @@ -973,7 +973,7 @@ ce4100_serial_setup(struct serial_private *priv, static int pci_omegapci_setup(struct serial_private *priv, - struct pciserial_board *board, + const struct pciserial_board *board, struct uart_port *port, int idx) { return setup_port(priv, port, 2, idx * 8, 0); @@ -994,6 +994,15 @@ static int skip_tx_en_setup(struct serial_private *priv, return pci_default_setup(priv, board, port, idx); } +static int pci_eg20t_init(struct pci_dev *dev) +{ +#if defined(CONFIG_SERIAL_PCH_UART) || defined(CONFIG_SERIAL_PCH_UART_MODULE) + return -ENODEV; +#else + return 0; +#endif +} + /* This should be in linux/pci_ids.h */ #define PCI_VENDOR_ID_SBSMODULARIO 0x124B #define PCI_SUBVENDOR_ID_SBSMODULARIO 0x124B @@ -1446,6 +1455,56 @@ static struct pci_serial_quirk pci_serial_quirks[] __refdata = { .init = pci_oxsemi_tornado_init, .setup = pci_default_setup, }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = 0x8811, + .init = pci_eg20t_init, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = 0x8812, + .init = pci_eg20t_init, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = 0x8813, + .init = pci_eg20t_init, + }, + { + .vendor = PCI_VENDOR_ID_INTEL, + .device = 0x8814, + .init = pci_eg20t_init, + }, + { + .vendor = 0x10DB, + .device = 0x8027, + .init = pci_eg20t_init, + }, + { + .vendor = 0x10DB, + .device = 0x8028, + .init = pci_eg20t_init, + }, + { + .vendor = 0x10DB, + .device = 0x8029, + .init = pci_eg20t_init, + }, + { + .vendor = 0x10DB, + .device = 0x800C, + .init = pci_eg20t_init, + }, + { + .vendor = 0x10DB, + .device = 0x800D, + .init = pci_eg20t_init, + }, + { + .vendor = 0x10DB, + .device = 0x800D, + .init = pci_eg20t_init, + }, /* * Cronyx Omega PCI (PLX-chip based) */ diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 8dc0541..f5f6831 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -50,6 +50,7 @@ #include <linux/dmaengine.h> #include <linux/dma-mapping.h> #include <linux/scatterlist.h> +#include <linux/delay.h> #include <asm/io.h> #include <asm/sizes.h> @@ -65,6 +66,30 @@ #define UART_DR_ERROR (UART011_DR_OE|UART011_DR_BE|UART011_DR_PE|UART011_DR_FE) #define UART_DUMMY_DR_RX (1 << 16) + +#define UART_WA_SAVE_NR 14 + +static void pl011_lockup_wa(unsigned long data); +static const u32 uart_wa_reg[UART_WA_SAVE_NR] = { + ST_UART011_DMAWM, + ST_UART011_TIMEOUT, + ST_UART011_LCRH_RX, + UART011_IBRD, + UART011_FBRD, + ST_UART011_LCRH_TX, + UART011_IFLS, + ST_UART011_XFCR, + ST_UART011_XON1, + ST_UART011_XON2, + ST_UART011_XOFF1, + ST_UART011_XOFF2, + UART011_CR, + UART011_IMSC +}; + +static u32 uart_wa_regdata[UART_WA_SAVE_NR]; +static DECLARE_TASKLET(pl011_lockup_tlet, pl011_lockup_wa, 0); + /* There is by now at least one vendor with differing details, so handle it */ struct vendor_data { unsigned int ifls; @@ -72,6 +97,7 @@ struct vendor_data { unsigned int lcrh_tx; unsigned int lcrh_rx; bool oversampling; + bool interrupt_may_hang; /* vendor-specific */ bool dma_threshold; }; @@ -90,9 +116,12 @@ static struct vendor_data vendor_st = { .lcrh_tx = ST_UART011_LCRH_TX, .lcrh_rx = ST_UART011_LCRH_RX, .oversampling = true, + .interrupt_may_hang = true, .dma_threshold = true, }; +static struct uart_amba_port *amba_ports[UART_NR]; + /* Deals with DMA transactions */ struct pl011_sgbuf { @@ -132,6 +161,7 @@ struct uart_amba_port { unsigned int lcrh_rx; /* vendor-specific */ bool autorts; char type[12]; + bool interrupt_may_hang; /* vendor-specific */ #ifdef CONFIG_DMA_ENGINE /* DMA stuff */ bool using_tx_dma; @@ -1008,6 +1038,68 @@ static inline bool pl011_dma_rx_running(struct uart_amba_port *uap) #endif +/* + * pl011_lockup_wa + * This workaround aims to break the deadlock situation + * when after long transfer over uart in hardware flow + * control, uart interrupt registers cannot be cleared. + * Hence uart transfer gets blocked. + * + * It is seen that during such deadlock condition ICR + * don't get cleared even on multiple write. This leads + * pass_counter to decrease and finally reach zero. This + * can be taken as trigger point to run this UART_BT_WA. + * + */ +static void pl011_lockup_wa(unsigned long data) +{ + struct uart_amba_port *uap = amba_ports[0]; + void __iomem *base = uap->port.membase; + struct circ_buf *xmit = &uap->port.state->xmit; + struct tty_struct *tty = uap->port.state->port.tty; + int buf_empty_retries = 200; + int loop; + + /* Stop HCI layer from submitting data for tx */ + tty->hw_stopped = 1; + while (!uart_circ_empty(xmit)) { + if (buf_empty_retries-- == 0) + break; + udelay(100); + } + + /* Backup registers */ + for (loop = 0; loop < UART_WA_SAVE_NR; loop++) + uart_wa_regdata[loop] = readl(base + uart_wa_reg[loop]); + + /* Disable UART so that FIFO data is flushed out */ + writew(0x00, uap->port.membase + UART011_CR); + + /* Soft reset UART module */ + if (uap->port.dev->platform_data) { + struct amba_pl011_data *plat; + + plat = uap->port.dev->platform_data; + if (plat->reset) + plat->reset(); + } + + /* Restore registers */ + for (loop = 0; loop < UART_WA_SAVE_NR; loop++) + writew(uart_wa_regdata[loop] , + uap->port.membase + uart_wa_reg[loop]); + + /* Initialise the old status of the modem signals */ + uap->old_status = readw(uap->port.membase + UART01x_FR) & + UART01x_FR_MODEM_ANY; + + if (readl(base + UART011_MIS) & 0x2) + printk(KERN_EMERG "UART_BT_WA: ***FAILED***\n"); + + /* Start Tx/Rx */ + tty->hw_stopped = 0; +} + static void pl011_stop_tx(struct uart_port *port) { struct uart_amba_port *uap = (struct uart_amba_port *)port; @@ -1158,8 +1250,11 @@ static irqreturn_t pl011_int(int irq, void *dev_id) if (status & UART011_TXIS) pl011_tx_chars(uap); - if (pass_counter-- == 0) + if (pass_counter-- == 0) { + if (uap->interrupt_may_hang) + tasklet_schedule(&pl011_lockup_tlet); break; + } status = readw(uap->port.membase + UART011_MIS); } while (status != 0); @@ -1339,6 +1434,14 @@ static int pl011_startup(struct uart_port *port) writew(uap->im, uap->port.membase + UART011_IMSC); spin_unlock_irq(&uap->port.lock); + if (uap->port.dev->platform_data) { + struct amba_pl011_data *plat; + + plat = uap->port.dev->platform_data; + if (plat->init) + plat->init(); + } + return 0; clk_dis: @@ -1394,6 +1497,15 @@ static void pl011_shutdown(struct uart_port *port) * Shut down the clock producer */ clk_disable(uap->clk); + + if (uap->port.dev->platform_data) { + struct amba_pl011_data *plat; + + plat = uap->port.dev->platform_data; + if (plat->exit) + plat->exit(); + } + } static void @@ -1700,6 +1812,14 @@ static int __init pl011_console_setup(struct console *co, char *options) if (!uap) return -ENODEV; + if (uap->port.dev->platform_data) { + struct amba_pl011_data *plat; + + plat = uap->port.dev->platform_data; + if (plat->init) + plat->init(); + } + uap->port.uartclk = clk_get_rate(uap->clk); if (options) @@ -1774,6 +1894,7 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id) uap->lcrh_rx = vendor->lcrh_rx; uap->lcrh_tx = vendor->lcrh_tx; uap->fifosize = vendor->fifosize; + uap->interrupt_may_hang = vendor->interrupt_may_hang; uap->port.dev = &dev->dev; uap->port.mapbase = dev->res.start; uap->port.membase = base; diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index 6d5d6e6..af9b781 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -1709,12 +1709,13 @@ static int atmel_serial_resume(struct platform_device *pdev) static int __devinit atmel_serial_probe(struct platform_device *pdev) { struct atmel_uart_port *port; + struct atmel_uart_data *pdata = pdev->dev.platform_data; void *data; int ret; BUILD_BUG_ON(ATMEL_SERIAL_RINGSIZE & (ATMEL_SERIAL_RINGSIZE - 1)); - port = &atmel_ports[pdev->id]; + port = &atmel_ports[pdata->num]; port->backup_imr = 0; atmel_init_port(port, pdev); diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index a1a0e55..c0b68b9 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -250,6 +250,20 @@ static void bcm_uart_do_rx(struct uart_port *port) /* get overrun/fifo empty information from ier * register */ iestat = bcm_uart_readl(port, UART_IR_REG); + + if (unlikely(iestat & UART_IR_STAT(UART_IR_RXOVER))) { + unsigned int val; + + /* fifo reset is required to clear + * interrupt */ + val = bcm_uart_readl(port, UART_CTL_REG); + val |= UART_CTL_RSTRXFIFO_MASK; + bcm_uart_writel(port, val, UART_CTL_REG); + + port->icount.overrun++; + tty_insert_flip_char(tty, 0, TTY_OVERRUN); + } + if (!(iestat & UART_IR_STAT(UART_IR_RXNOTEMPTY))) break; @@ -284,10 +298,6 @@ static void bcm_uart_do_rx(struct uart_port *port) if (uart_handle_sysrq_char(port, c)) continue; - if (unlikely(iestat & UART_IR_STAT(UART_IR_RXOVER))) { - port->icount.overrun++; - tty_insert_flip_char(tty, 0, TTY_OVERRUN); - } if ((cstat & port->ignore_status_mask) == 0) tty_insert_flip_char(tty, c, flag); diff --git a/drivers/tty/serial/jsm/jsm_driver.c b/drivers/tty/serial/jsm/jsm_driver.c index 18f5484..96da178 100644 --- a/drivers/tty/serial/jsm/jsm_driver.c +++ b/drivers/tty/serial/jsm/jsm_driver.c @@ -125,7 +125,7 @@ static int __devinit jsm_probe_one(struct pci_dev *pdev, const struct pci_device brd->bd_uart_offset = 0x200; brd->bd_dividend = 921600; - brd->re_map_membase = ioremap(brd->membase, 0x1000); + brd->re_map_membase = ioremap(brd->membase, pci_resource_len(pdev, 0)); if (!brd->re_map_membase) { dev_err(&pdev->dev, "card has no PCI Memory resources, " diff --git a/drivers/tty/serial/mrst_max3110.c b/drivers/tty/serial/mrst_max3110.c index 1bd2845..a764bf9 100644 --- a/drivers/tty/serial/mrst_max3110.c +++ b/drivers/tty/serial/mrst_max3110.c @@ -421,7 +421,6 @@ static int max3110_main_thread(void *_max) int ret = 0; struct circ_buf *xmit = &max->con_xmit; - init_waitqueue_head(wq); pr_info(PR_FMT "start main thread\n"); do { @@ -823,7 +822,7 @@ static int __devinit serial_m3110_probe(struct spi_device *spi) res = RC_TAG; ret = max3110_write_then_read(max, (u8 *)&res, (u8 *)&res, 2, 0); if (ret < 0 || res == 0 || res == 0xffff) { - printk(KERN_ERR "MAX3111 deemed not present (conf reg %04x)", + dev_dbg(&spi->dev, "MAX3111 deemed not present (conf reg %04x)", res); ret = -ENODEV; goto err_get_page; @@ -838,6 +837,8 @@ static int __devinit serial_m3110_probe(struct spi_device *spi) max->con_xmit.head = 0; max->con_xmit.tail = 0; + init_waitqueue_head(&max->wq); + max->main_thread = kthread_run(max3110_main_thread, max, "max3110_main"); if (IS_ERR(max->main_thread)) { diff --git a/drivers/tty/serial/s5pv210.c b/drivers/tty/serial/s5pv210.c index fb2619f..dd194dc 100644 --- a/drivers/tty/serial/s5pv210.c +++ b/drivers/tty/serial/s5pv210.c @@ -30,7 +30,7 @@ static int s5pv210_serial_setsource(struct uart_port *port, struct s3c2410_uartcfg *cfg = port->dev->platform_data; unsigned long ucon = rd_regl(port, S3C2410_UCON); - if ((cfg->clocks_size) == 1) + if (cfg->flags & NO_NEED_CHECK_CLKSRC) return 0; if (strcmp(clk->name, "pclk") == 0) @@ -55,7 +55,7 @@ static int s5pv210_serial_getsource(struct uart_port *port, clk->divisor = 1; - if ((cfg->clocks_size) == 1) + if (cfg->flags & NO_NEED_CHECK_CLKSRC) return 0; switch (ucon & S5PV210_UCON_CLKMASK) { diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index 5d01d32..ef925d5 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -555,7 +555,7 @@ static void tty_ldisc_flush_works(struct tty_struct *tty) static int tty_ldisc_wait_idle(struct tty_struct *tty) { int ret; - ret = wait_event_interruptible_timeout(tty_ldisc_idle, + ret = wait_event_timeout(tty_ldisc_idle, atomic_read(&tty->ldisc->users) == 1, 5 * HZ); if (ret < 0) return ret; @@ -763,6 +763,8 @@ static int tty_ldisc_reinit(struct tty_struct *tty, int ldisc) if (IS_ERR(ld)) return -1; + WARN_ON_ONCE(tty_ldisc_wait_idle(tty)); + tty_ldisc_close(tty, tty->ldisc); tty_ldisc_put(tty->ldisc); tty->ldisc = NULL; diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index e35a176..34e3da5 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -375,7 +375,7 @@ static int usb_unbind_interface(struct device *dev) * Just re-enable it without affecting the endpoint toggles. */ usb_enable_interface(udev, intf, false); - } else if (!error && !intf->dev.power.in_suspend) { + } else if (!error && !intf->dev.power.is_prepared) { r = usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); if (r < 0) @@ -960,7 +960,7 @@ void usb_rebind_intf(struct usb_interface *intf) } /* Try to rebind the interface */ - if (!intf->dev.power.in_suspend) { + if (!intf->dev.power.is_prepared) { intf->needs_binding = 0; rc = device_attach(&intf->dev); if (rc < 0) @@ -1107,7 +1107,7 @@ static int usb_resume_interface(struct usb_device *udev, if (intf->condition == USB_INTERFACE_UNBOUND) { /* Carry out a deferred switch to altsetting 0 */ - if (intf->needs_altsetting0 && !intf->dev.power.in_suspend) { + if (intf->needs_altsetting0 && !intf->dev.power.is_prepared) { usb_set_interface(udev, intf->altsetting[0]. desc.bInterfaceNumber, 0); intf->needs_altsetting0 = 0; @@ -1187,13 +1187,22 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg) for (i = n - 1; i >= 0; --i) { intf = udev->actconfig->interface[i]; status = usb_suspend_interface(udev, intf, msg); + + /* Ignore errors during system sleep transitions */ + if (!(msg.event & PM_EVENT_AUTO)) + status = 0; if (status != 0) break; } } - if (status == 0) + if (status == 0) { status = usb_suspend_device(udev, msg); + /* Again, ignore errors during system sleep transitions */ + if (!(msg.event & PM_EVENT_AUTO)) + status = 0; + } + /* If the suspend failed, resume interfaces that did get suspended */ if (status != 0) { msg.event ^= (PM_EVENT_SUSPEND | PM_EVENT_RESUME); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 90ae175..a428aa0 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1634,6 +1634,7 @@ void usb_disconnect(struct usb_device **pdev) { struct usb_device *udev = *pdev; int i; + struct usb_hcd *hcd = bus_to_hcd(udev->bus); if (!udev) { pr_debug ("%s nodev\n", __func__); @@ -1661,7 +1662,9 @@ void usb_disconnect(struct usb_device **pdev) * so that the hardware is now fully quiesced. */ dev_dbg (&udev->dev, "unregistering device\n"); + mutex_lock(hcd->bandwidth_mutex); usb_disable_device(udev, 0); + mutex_unlock(hcd->bandwidth_mutex); usb_hcd_synchronize_unlinks(udev); usb_remove_ep_devs(&udev->ep0); @@ -2362,6 +2365,10 @@ int usb_port_suspend(struct usb_device *udev, pm_message_t msg) USB_DEVICE_REMOTE_WAKEUP, 0, NULL, 0, USB_CTRL_SET_TIMEOUT); + + /* System sleep transitions should never fail */ + if (!(msg.event & PM_EVENT_AUTO)) + status = 0; } else { /* device has up to 10 msec to fully suspend */ dev_dbg(&udev->dev, "usb %ssuspend\n", @@ -2611,16 +2618,15 @@ static int hub_suspend(struct usb_interface *intf, pm_message_t msg) struct usb_device *hdev = hub->hdev; unsigned port1; - /* fail if children aren't already suspended */ + /* Warn if children aren't already suspended */ for (port1 = 1; port1 <= hdev->maxchild; port1++) { struct usb_device *udev; udev = hdev->children [port1-1]; if (udev && udev->can_submit) { - if (!(msg.event & PM_EVENT_AUTO)) - dev_dbg(&intf->dev, "port %d nyet suspended\n", - port1); - return -EBUSY; + dev_warn(&intf->dev, "port %d nyet suspended\n", port1); + if (msg.event & PM_EVENT_AUTO) + return -EBUSY; } } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 5701e85..0b5ec23 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1135,15 +1135,26 @@ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf, * Deallocates hcd/hardware state for the endpoints (nuking all or most * pending urbs) and usbcore state for the interfaces, so that usbcore * must usb_set_configuration() before any interfaces could be used. + * + * Must be called with hcd->bandwidth_mutex held. */ void usb_disable_device(struct usb_device *dev, int skip_ep0) { int i; + struct usb_hcd *hcd = bus_to_hcd(dev->bus); /* getting rid of interfaces will disconnect * any drivers bound to them (a key side effect) */ if (dev->actconfig) { + /* + * FIXME: In order to avoid self-deadlock involving the + * bandwidth_mutex, we have to mark all the interfaces + * before unregistering any of them. + */ + for (i = 0; i < dev->actconfig->desc.bNumInterfaces; i++) + dev->actconfig->interface[i]->unregistering = 1; + for (i = 0; i < dev->actconfig->desc.bNumInterfaces; i++) { struct usb_interface *interface; @@ -1153,7 +1164,6 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0) continue; dev_dbg(&dev->dev, "unregistering interface %s\n", dev_name(&interface->dev)); - interface->unregistering = 1; remove_intf_ep_devs(interface); device_del(&interface->dev); } @@ -1172,6 +1182,16 @@ void usb_disable_device(struct usb_device *dev, int skip_ep0) dev_dbg(&dev->dev, "%s nuking %s URBs\n", __func__, skip_ep0 ? "non-ep0" : "all"); + if (hcd->driver->check_bandwidth) { + /* First pass: Cancel URBs, leave endpoint pointers intact. */ + for (i = skip_ep0; i < 16; ++i) { + usb_disable_endpoint(dev, i, false); + usb_disable_endpoint(dev, i + USB_DIR_IN, false); + } + /* Remove endpoints from the host controller internal state */ + usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL); + /* Second pass: remove endpoint pointers */ + } for (i = skip_ep0; i < 16; ++i) { usb_disable_endpoint(dev, i, true); usb_disable_endpoint(dev, i + USB_DIR_IN, true); @@ -1273,6 +1293,8 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate) interface); return -EINVAL; } + if (iface->unregistering) + return -ENODEV; alt = usb_altnum_to_altsetting(iface, alternate); if (!alt) { @@ -1727,6 +1749,7 @@ free_interfaces: /* if it's already configured, clear out old state first. * getting rid of old interfaces means unbinding their drivers. */ + mutex_lock(hcd->bandwidth_mutex); if (dev->state != USB_STATE_ADDRESS) usb_disable_device(dev, 1); /* Skip ep0 */ @@ -1739,7 +1762,6 @@ free_interfaces: * host controller will not allow submissions to dropped endpoints. If * this call fails, the device state is unchanged. */ - mutex_lock(hcd->bandwidth_mutex); ret = usb_hcd_alloc_bandwidth(dev, cp, NULL, NULL); if (ret < 0) { mutex_unlock(hcd->bandwidth_mutex); diff --git a/drivers/usb/gadget/fsl_udc_core.c b/drivers/usb/gadget/fsl_udc_core.c index 2cd9a60..4e48331 100644 --- a/drivers/usb/gadget/fsl_udc_core.c +++ b/drivers/usb/gadget/fsl_udc_core.c @@ -46,7 +46,6 @@ #include <asm/system.h> #include <asm/unaligned.h> #include <asm/dma.h> -#include <asm/cacheflush.h> #include "fsl_usb2_udc.h" @@ -118,6 +117,17 @@ static void (*_fsl_writel)(u32 v, unsigned __iomem *p); #define fsl_readl(p) (*_fsl_readl)((p)) #define fsl_writel(v, p) (*_fsl_writel)((v), (p)) +static inline void fsl_set_accessors(struct fsl_usb2_platform_data *pdata) +{ + if (pdata->big_endian_mmio) { + _fsl_readl = _fsl_readl_be; + _fsl_writel = _fsl_writel_be; + } else { + _fsl_readl = _fsl_readl_le; + _fsl_writel = _fsl_writel_le; + } +} + static inline u32 cpu_to_hc32(const u32 x) { return udc_controller->pdata->big_endian_desc @@ -132,6 +142,8 @@ static inline u32 hc32_to_cpu(const u32 x) : le32_to_cpu((__force __le32)x); } #else /* !CONFIG_PPC32 */ +static inline void fsl_set_accessors(struct fsl_usb2_platform_data *pdata) {} + #define fsl_readl(addr) readl(addr) #define fsl_writel(val32, addr) writel(val32, addr) #define cpu_to_hc32(x) cpu_to_le32(x) @@ -1277,6 +1289,11 @@ static int ep0_prime_status(struct fsl_udc *udc, int direction) req->req.complete = NULL; req->dtd_count = 0; + req->req.dma = dma_map_single(ep->udc->gadget.dev.parent, + req->req.buf, req->req.length, + ep_is_in(ep) ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + req->mapped = 1; + if (fsl_req_to_dtd(req) == 0) fsl_queue_td(ep, req); else @@ -1348,9 +1365,6 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value, /* Fill in the reqest structure */ *((u16 *) req->req.buf) = cpu_to_le16(tmp); - /* flush cache for the req buffer */ - flush_dcache_range((u32)req->req.buf, (u32)req->req.buf + 8); - req->ep = ep; req->req.length = 2; req->req.status = -EINPROGRESS; @@ -1358,6 +1372,11 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value, req->req.complete = NULL; req->dtd_count = 0; + req->req.dma = dma_map_single(ep->udc->gadget.dev.parent, + req->req.buf, req->req.length, + ep_is_in(ep) ? DMA_TO_DEVICE : DMA_FROM_DEVICE); + req->mapped = 1; + /* prime the data phase */ if ((fsl_req_to_dtd(req) == 0)) fsl_queue_td(ep, req); @@ -2354,7 +2373,6 @@ static int __init struct_udc_setup(struct fsl_udc *udc, struct fsl_req, req); /* allocate a small amount of memory to get valid address */ udc->status_req->req.buf = kmalloc(8, GFP_KERNEL); - udc->status_req->req.dma = virt_to_phys(udc->status_req->req.buf); udc->resume_state = USB_STATE_NOTATTACHED; udc->usb_state = USB_STATE_POWERED; @@ -2470,13 +2488,7 @@ static int __init fsl_udc_probe(struct platform_device *pdev) } /* Set accessors only after pdata->init() ! */ - if (pdata->big_endian_mmio) { - _fsl_readl = _fsl_readl_be; - _fsl_writel = _fsl_writel_be; - } else { - _fsl_readl = _fsl_readl_le; - _fsl_writel = _fsl_writel_le; - } + fsl_set_accessors(pdata); #ifndef CONFIG_ARCH_MXC if (pdata->have_sysif_regs) diff --git a/drivers/usb/host/ehci-ath79.c b/drivers/usb/host/ehci-ath79.c index 98cc8a1..aa248c2 100644 --- a/drivers/usb/host/ehci-ath79.c +++ b/drivers/usb/host/ehci-ath79.c @@ -44,7 +44,6 @@ static int ehci_ath79_init(struct usb_hcd *hcd) struct ehci_hcd *ehci = hcd_to_ehci(hcd); struct platform_device *pdev = to_platform_device(hcd->self.controller); const struct platform_device_id *id; - int hclength; int ret; id = platform_get_device_id(pdev); @@ -53,20 +52,23 @@ static int ehci_ath79_init(struct usb_hcd *hcd) return -EINVAL; } - hclength = HC_LENGTH(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase)); switch (id->driver_data) { case EHCI_ATH79_IP_V1: ehci->has_synopsys_hc_bug = 1; ehci->caps = hcd->regs; - ehci->regs = hcd->regs + hclength; + ehci->regs = hcd->regs + + HC_LENGTH(ehci, + ehci_readl(ehci, &ehci->caps->hc_capbase)); break; case EHCI_ATH79_IP_V2: hcd->has_tt = 1; ehci->caps = hcd->regs + 0x100; - ehci->regs = hcd->regs + 0x100 + hclength; + ehci->regs = hcd->regs + 0x100 + + HC_LENGTH(ehci, + ehci_readl(ehci, &ehci->caps->hc_capbase)); break; default: diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index b435ed6..f8030ee 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -1,4 +1,8 @@ /* + * Enhanced Host Controller Interface (EHCI) driver for USB. + * + * Maintainer: Alan Stern <stern@rowland.harvard.edu> + * * Copyright (c) 2000-2004 by David Brownell * * This program is free software; you can redistribute it and/or modify it diff --git a/drivers/usb/host/isp1760-hcd.c b/drivers/usb/host/isp1760-hcd.c index c9e6e45..55d3d58 100644 --- a/drivers/usb/host/isp1760-hcd.c +++ b/drivers/usb/host/isp1760-hcd.c @@ -1555,7 +1555,7 @@ static void kill_transfer(struct usb_hcd *hcd, struct urb *urb, /* We need to forcefully reclaim the slot since some transfers never return, e.g. interrupt transfers and NAKed bulk transfers. */ - if (usb_pipebulk(urb->pipe)) { + if (usb_pipecontrol(urb->pipe) || usb_pipebulk(urb->pipe)) { skip_map = reg_read32(hcd->regs, HC_ATL_PTD_SKIPMAP_REG); skip_map |= (1 << qh->slot); reg_write32(hcd->regs, HC_ATL_PTD_SKIPMAP_REG, skip_map); diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index 9aa10bd..f9cf3f0 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -1,5 +1,7 @@ /* - * OHCI HCD (Host Controller Driver) for USB. + * Open Host Controller Interface (OHCI) driver for USB. + * + * Maintainer: Alan Stern <stern@rowland.harvard.edu> * * (C) Copyright 1999 Roman Weissgaerber <weissg@vienna.at> * (C) Copyright 2000-2004 David Brownell <dbrownell@users.sourceforge.net> diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c index db6f8b9..4586369 100644 --- a/drivers/usb/host/r8a66597-hcd.c +++ b/drivers/usb/host/r8a66597-hcd.c @@ -2517,6 +2517,7 @@ static int __devinit r8a66597_probe(struct platform_device *pdev) INIT_LIST_HEAD(&r8a66597->child_device); hcd->rsrc_start = res->start; + hcd->has_tt = 1; ret = usb_add_hcd(hcd, irq, IRQF_DISABLED | irq_trigger); if (ret != 0) { diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 0f8e1d2..fcb7f7e 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1215,8 +1215,6 @@ int xhci_endpoint_init(struct xhci_hcd *xhci, ep_ctx->ep_info2 |= cpu_to_le32(MAX_PACKET(max_packet)); /* dig out max burst from ep companion desc */ max_packet = ep->ss_ep_comp.bMaxBurst; - if (!max_packet) - xhci_warn(xhci, "WARN no SS endpoint bMaxBurst\n"); ep_ctx->ep_info2 |= cpu_to_le32(MAX_BURST(max_packet)); break; case USB_SPEED_HIGH: diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 17541d0..cb16de2 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -29,6 +29,9 @@ #define PCI_VENDOR_ID_FRESCO_LOGIC 0x1b73 #define PCI_DEVICE_ID_FRESCO_LOGIC_PDK 0x1000 +#define PCI_VENDOR_ID_ETRON 0x1b6f +#define PCI_DEVICE_ID_ASROCK_P67 0x7023 + static const char hcd_name[] = "xhci_hcd"; /* called after powerup, by probe or system-pm "wakeup" */ @@ -134,6 +137,11 @@ static int xhci_pci_setup(struct usb_hcd *hcd) xhci->quirks |= XHCI_EP_LIMIT_QUIRK; xhci->limit_active_eps = 64; } + if (pdev->vendor == PCI_VENDOR_ID_ETRON && + pdev->device == PCI_DEVICE_ID_ASROCK_P67) { + xhci->quirks |= XHCI_RESET_ON_RESUME; + xhci_dbg(xhci, "QUIRK: Resetting on resume\n"); + } /* Make sure the HC is halted. */ retval = xhci_halt(xhci); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 800f417..70cacbb 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1733,6 +1733,7 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, frame->status = -EOVERFLOW; skip_td = true; break; + case COMP_DEV_ERR: case COMP_STALL: frame->status = -EPROTO; skip_td = true; @@ -1767,9 +1768,6 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, } } - if ((idx == urb_priv->length - 1) && *status == -EINPROGRESS) - *status = 0; - return finish_td(xhci, td, event_trb, event, ep, status, false); } @@ -1787,8 +1785,7 @@ static int skip_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td, idx = urb_priv->td_cnt; frame = &td->urb->iso_frame_desc[idx]; - /* The transfer is partly done */ - *status = -EXDEV; + /* The transfer is partly done. */ frame->status = -EXDEV; /* calc actual length */ @@ -2016,6 +2013,10 @@ static int handle_tx_event(struct xhci_hcd *xhci, TRB_TO_SLOT_ID(le32_to_cpu(event->flags)), ep_index); goto cleanup; + case COMP_DEV_ERR: + xhci_warn(xhci, "WARN: detect an incompatible device"); + status = -EPROTO; + break; case COMP_MISSED_INT: /* * When encounter missed service error, one or more isoc tds @@ -2063,6 +2064,20 @@ static int handle_tx_event(struct xhci_hcd *xhci, /* Is this a TRB in the currently executing TD? */ event_seg = trb_in_td(ep_ring->deq_seg, ep_ring->dequeue, td->last_trb, event_dma); + + /* + * Skip the Force Stopped Event. The event_trb(event_dma) of FSE + * is not in the current TD pointed by ep_ring->dequeue because + * that the hardware dequeue pointer still at the previous TRB + * of the current TD. The previous TRB maybe a Link TD or the + * last TRB of the previous TD. The command completion handle + * will take care the rest. + */ + if (!event_seg && trb_comp_code == COMP_STOP_INVAL) { + ret = 0; + goto cleanup; + } + if (!event_seg) { if (!ep->skip || !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) { @@ -2158,6 +2173,11 @@ cleanup: urb->transfer_buffer_length, status); spin_unlock(&xhci->lock); + /* EHCI, UHCI, and OHCI always unconditionally set the + * urb->status of an isochronous endpoint to 0. + */ + if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) + status = 0; usb_hcd_giveback_urb(bus_to_hcd(urb->dev->bus), urb, status); spin_lock(&xhci->lock); } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 06e7023..f5fe1ac 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -759,6 +759,8 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) msleep(100); spin_lock_irq(&xhci->lock); + if (xhci->quirks & XHCI_RESET_ON_RESUME) + hibernated = true; if (!hibernated) { /* step 1: restore register */ @@ -1401,6 +1403,7 @@ int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, u32 added_ctxs; unsigned int last_ctx; u32 new_add_flags, new_drop_flags, new_slot_info; + struct xhci_virt_device *virt_dev; int ret = 0; ret = xhci_check_args(hcd, udev, ep, 1, true, __func__); @@ -1425,11 +1428,25 @@ int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, return 0; } - in_ctx = xhci->devs[udev->slot_id]->in_ctx; - out_ctx = xhci->devs[udev->slot_id]->out_ctx; + virt_dev = xhci->devs[udev->slot_id]; + in_ctx = virt_dev->in_ctx; + out_ctx = virt_dev->out_ctx; ctrl_ctx = xhci_get_input_control_ctx(xhci, in_ctx); ep_index = xhci_get_endpoint_index(&ep->desc); ep_ctx = xhci_get_ep_ctx(xhci, out_ctx, ep_index); + + /* If this endpoint is already in use, and the upper layers are trying + * to add it again without dropping it, reject the addition. + */ + if (virt_dev->eps[ep_index].ring && + !(le32_to_cpu(ctrl_ctx->drop_flags) & + xhci_get_endpoint_flag(&ep->desc))) { + xhci_warn(xhci, "Trying to add endpoint 0x%x " + "without dropping it.\n", + (unsigned int) ep->desc.bEndpointAddress); + return -EINVAL; + } + /* If the HCD has already noted the endpoint is enabled, * ignore this request. */ @@ -1445,8 +1462,7 @@ int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev, * process context, not interrupt context (or so documenation * for usb_set_interface() and usb_set_configuration() claim). */ - if (xhci_endpoint_init(xhci, xhci->devs[udev->slot_id], - udev, ep, GFP_NOIO) < 0) { + if (xhci_endpoint_init(xhci, virt_dev, udev, ep, GFP_NOIO) < 0) { dev_dbg(&udev->dev, "%s - could not initialize ep %#x\n", __func__, ep->desc.bEndpointAddress); return -ENOMEM; @@ -1537,6 +1553,11 @@ static int xhci_configure_endpoint_result(struct xhci_hcd *xhci, "and endpoint is not disabled.\n"); ret = -EINVAL; break; + case COMP_DEV_ERR: + dev_warn(&udev->dev, "ERROR: Incompatible device for endpoint " + "configure command.\n"); + ret = -ENODEV; + break; case COMP_SUCCESS: dev_dbg(&udev->dev, "Successful Endpoint Configure command\n"); ret = 0; @@ -1571,6 +1592,11 @@ static int xhci_evaluate_context_result(struct xhci_hcd *xhci, xhci_dbg_ctx(xhci, virt_dev->out_ctx, 1); ret = -EINVAL; break; + case COMP_DEV_ERR: + dev_warn(&udev->dev, "ERROR: Incompatible device for evaluate " + "context command.\n"); + ret = -ENODEV; + break; case COMP_MEL_ERR: /* Max Exit Latency too large error */ dev_warn(&udev->dev, "WARN: Max Exit Latency too large\n"); @@ -2853,6 +2879,11 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev) dev_warn(&udev->dev, "Device not responding to set address.\n"); ret = -EPROTO; break; + case COMP_DEV_ERR: + dev_warn(&udev->dev, "ERROR: Incompatible device for address " + "device command.\n"); + ret = -ENODEV; + break; case COMP_SUCCESS: xhci_dbg(xhci, "Successful Address Device command\n"); break; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 7d1ea3b..d8bbf5c 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -874,6 +874,8 @@ struct xhci_transfer_event { #define COMP_PING_ERR 20 /* Event Ring is full */ #define COMP_ER_FULL 21 +/* Incompatible Device Error */ +#define COMP_DEV_ERR 22 /* Missed Service Error - HC couldn't service an isoc ep within interval */ #define COMP_MISSED_INT 23 /* Successfully stopped command ring */ @@ -1308,6 +1310,7 @@ struct xhci_hcd { */ #define XHCI_EP_LIMIT_QUIRK (1 << 5) #define XHCI_BROKEN_MSI (1 << 6) +#define XHCI_RESET_ON_RESUME (1 << 7) unsigned int num_active_eps; unsigned int limit_active_eps; /* There are two roothubs to keep track of bus suspend info for */ diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 0a50a35..6aeb363 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1524,6 +1524,12 @@ static void musb_gadget_fifo_flush(struct usb_ep *ep) csr = musb_readw(epio, MUSB_TXCSR); if (csr & MUSB_TXCSR_FIFONOTEMPTY) { csr |= MUSB_TXCSR_FLUSHFIFO | MUSB_TXCSR_P_WZC_BITS; + /* + * Setting both TXPKTRDY and FLUSHFIFO makes controller + * to interrupt current FIFO loading, but not flushing + * the already loaded ones. + */ + csr &= ~MUSB_TXCSR_TXPKTRDY; musb_writew(epio, MUSB_TXCSR, csr); /* REVISIT may be inappropriate w/o FIFONOTEMPTY ... */ musb_writew(epio, MUSB_TXCSR, csr); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 7295e31..8b2473f 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -1575,7 +1575,7 @@ void musb_host_rx(struct musb *musb, u8 epnum) /* even if there was an error, we did the dma * for iso_frame_desc->length */ - if (d->status != EILSEQ && d->status != -EOVERFLOW) + if (d->status != -EILSEQ && d->status != -EOVERFLOW) d->status = 0; if (++qh->iso_idx >= urb->number_of_packets) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 1627289..2e06b90 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -179,6 +179,7 @@ static struct usb_device_id id_table_combined [] = { { USB_DEVICE(FTDI_VID, FTDI_232RL_PID) }, { USB_DEVICE(FTDI_VID, FTDI_8U2232C_PID) }, { USB_DEVICE(FTDI_VID, FTDI_4232H_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_232H_PID) }, { USB_DEVICE(FTDI_VID, FTDI_MICRO_CHAMELEON_PID) }, { USB_DEVICE(FTDI_VID, FTDI_RELAIS_PID) }, { USB_DEVICE(FTDI_VID, FTDI_OPENDCC_PID) }, @@ -848,7 +849,8 @@ static const char *ftdi_chip_name[] = { [FT2232C] = "FT2232C", [FT232RL] = "FT232RL", [FT2232H] = "FT2232H", - [FT4232H] = "FT4232H" + [FT4232H] = "FT4232H", + [FT232H] = "FT232H" }; @@ -1168,6 +1170,7 @@ static __u32 get_ftdi_divisor(struct tty_struct *tty, break; case FT2232H: /* FT2232H chip */ case FT4232H: /* FT4232H chip */ + case FT232H: /* FT232H chip */ if ((baud <= 12000000) & (baud >= 1200)) { div_value = ftdi_2232h_baud_to_divisor(baud); } else if (baud < 1200) { @@ -1429,9 +1432,12 @@ static void ftdi_determine_type(struct usb_serial_port *port) } else if (version < 0x600) { /* Assume it's an FT232BM (or FT245BM) */ priv->chip_type = FT232BM; - } else { - /* Assume it's an FT232R */ + } else if (version < 0x900) { + /* Assume it's an FT232RL */ priv->chip_type = FT232RL; + } else { + /* Assume it's an FT232H */ + priv->chip_type = FT232H; } dev_info(&udev->dev, "Detected %s\n", ftdi_chip_name[priv->chip_type]); } @@ -1559,7 +1565,8 @@ static int create_sysfs_attrs(struct usb_serial_port *port) priv->chip_type == FT2232C || priv->chip_type == FT232RL || priv->chip_type == FT2232H || - priv->chip_type == FT4232H)) { + priv->chip_type == FT4232H || + priv->chip_type == FT232H)) { retval = device_create_file(&port->dev, &dev_attr_latency_timer); } @@ -1580,7 +1587,8 @@ static void remove_sysfs_attrs(struct usb_serial_port *port) priv->chip_type == FT2232C || priv->chip_type == FT232RL || priv->chip_type == FT2232H || - priv->chip_type == FT4232H) { + priv->chip_type == FT4232H || + priv->chip_type == FT232H) { device_remove_file(&port->dev, &dev_attr_latency_timer); } } @@ -2212,6 +2220,7 @@ static int ftdi_tiocmget(struct tty_struct *tty) case FT232RL: case FT2232H: case FT4232H: + case FT232H: len = 2; break; default: diff --git a/drivers/usb/serial/ftdi_sio.h b/drivers/usb/serial/ftdi_sio.h index 213fe3d..19584fa 100644 --- a/drivers/usb/serial/ftdi_sio.h +++ b/drivers/usb/serial/ftdi_sio.h @@ -156,7 +156,8 @@ enum ftdi_chip_type { FT2232C = 4, FT232RL = 5, FT2232H = 6, - FT4232H = 7 + FT4232H = 7, + FT232H = 8 }; enum ftdi_sio_baudrate { diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index ab1fcdf..19156d1 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -22,6 +22,7 @@ #define FTDI_8U232AM_ALT_PID 0x6006 /* FTDI's alternate PID for above */ #define FTDI_8U2232C_PID 0x6010 /* Dual channel device */ #define FTDI_4232H_PID 0x6011 /* Quad channel hi-speed device */ +#define FTDI_232H_PID 0x6014 /* Single channel hi-speed device */ #define FTDI_SIO_PID 0x8372 /* Product Id SIO application of 8U100AX */ #define FTDI_232RL_PID 0xFBFA /* Product ID for FT232RL */ diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index c6d92a5..ea84456 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -1745,6 +1745,7 @@ static int ti_download_firmware(struct ti_device *tdev) } if (fw_p->size > TI_FIRMWARE_BUF_SIZE) { dev_err(&dev->dev, "%s - firmware too large %zu\n", __func__, fw_p->size); + release_firmware(fw_p); return -ENOENT; } diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c index 5fc983c..cf03ad0 100644 --- a/drivers/video/amba-clcd.c +++ b/drivers/video/amba-clcd.c @@ -447,6 +447,8 @@ static int clcdfb_register(struct clcd_fb *fb) goto out; } + fb->fb.device = &fb->dev->dev; + fb->fb.fix.mmio_start = fb->dev->res.start; fb->fb.fix.mmio_len = resource_size(&fb->dev->res); diff --git a/drivers/video/fsl-diu-fb.c b/drivers/video/fsl-diu-fb.c index bedf5be..0acc7d6 100644 --- a/drivers/video/fsl-diu-fb.c +++ b/drivers/video/fsl-diu-fb.c @@ -555,8 +555,6 @@ static void adjust_aoi_size_position(struct fb_var_screeninfo *var, static int fsl_diu_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { - unsigned long htotal, vtotal; - pr_debug("check_var xres: %d\n", var->xres); pr_debug("check_var yres: %d\n", var->yres); @@ -635,20 +633,6 @@ static int fsl_diu_check_var(struct fb_var_screeninfo *var, break; } - /* If the pixclock is below the minimum spec'd value then set to - * refresh rate for 60Hz since this is supported by most monitors. - * Refer to Documentation/fb/ for calculations. - */ - if ((var->pixclock < MIN_PIX_CLK) || (var->pixclock > MAX_PIX_CLK)) { - htotal = var->xres + var->right_margin + var->hsync_len + - var->left_margin; - vtotal = var->yres + var->lower_margin + var->vsync_len + - var->upper_margin; - var->pixclock = (vtotal * htotal * 6UL) / 100UL; - var->pixclock = KHZ2PICOS(var->pixclock); - pr_debug("pixclock set for 60Hz refresh = %u ps\n", - var->pixclock); - } var->height = -1; var->width = -1; diff --git a/drivers/video/geode/gx1fb_core.c b/drivers/video/geode/gx1fb_core.c index c6b554f..5a5d092 100644 --- a/drivers/video/geode/gx1fb_core.c +++ b/drivers/video/geode/gx1fb_core.c @@ -29,7 +29,7 @@ static int crt_option = 1; static char panel_option[32] = ""; /* Modes relevant to the GX1 (taken from modedb.c) */ -static const struct fb_videomode __initdata gx1_modedb[] = { +static const struct fb_videomode __devinitdata gx1_modedb[] = { /* 640x480-60 VESA */ { NULL, 60, 640, 480, 39682, 48, 16, 33, 10, 96, 2, 0, FB_VMODE_NONINTERLACED, FB_MODE_IS_VESA }, @@ -195,7 +195,7 @@ static int gx1fb_blank(int blank_mode, struct fb_info *info) return par->vid_ops->blank_display(info, blank_mode); } -static int __init gx1fb_map_video_memory(struct fb_info *info, struct pci_dev *dev) +static int __devinit gx1fb_map_video_memory(struct fb_info *info, struct pci_dev *dev) { struct geodefb_par *par = info->par; unsigned gx_base; @@ -268,7 +268,7 @@ static struct fb_ops gx1fb_ops = { .fb_imageblit = cfb_imageblit, }; -static struct fb_info * __init gx1fb_init_fbinfo(struct device *dev) +static struct fb_info * __devinit gx1fb_init_fbinfo(struct device *dev) { struct geodefb_par *par; struct fb_info *info; @@ -318,7 +318,7 @@ static struct fb_info * __init gx1fb_init_fbinfo(struct device *dev) return info; } -static int __init gx1fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int __devinit gx1fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct geodefb_par *par; struct fb_info *info; @@ -382,7 +382,7 @@ static int __init gx1fb_probe(struct pci_dev *pdev, const struct pci_device_id * return ret; } -static void gx1fb_remove(struct pci_dev *pdev) +static void __devexit gx1fb_remove(struct pci_dev *pdev) { struct fb_info *info = pci_get_drvdata(pdev); struct geodefb_par *par = info->par; @@ -441,7 +441,7 @@ static struct pci_driver gx1fb_driver = { .name = "gx1fb", .id_table = gx1fb_id_table, .probe = gx1fb_probe, - .remove = gx1fb_remove, + .remove = __devexit_p(gx1fb_remove), }; static int __init gx1fb_init(void) @@ -456,7 +456,7 @@ static int __init gx1fb_init(void) return pci_register_driver(&gx1fb_driver); } -static void __exit gx1fb_cleanup(void) +static void __devexit gx1fb_cleanup(void) { pci_unregister_driver(&gx1fb_driver); } diff --git a/drivers/video/hecubafb.c b/drivers/video/hecubafb.c index fbef15f..614251a 100644 --- a/drivers/video/hecubafb.c +++ b/drivers/video/hecubafb.c @@ -233,7 +233,7 @@ static int __devinit hecubafb_probe(struct platform_device *dev) videomemory = vzalloc(videomemorysize); if (!videomemory) - return retval; + goto err_videomem_alloc; info = framebuffer_alloc(sizeof(struct hecubafb_par), &dev->dev); if (!info) @@ -275,6 +275,7 @@ err_fbreg: framebuffer_release(info); err_fballoc: vfree(videomemory); +err_videomem_alloc: module_put(board->owner); return retval; } diff --git a/drivers/video/sh_mobile_meram.c b/drivers/video/sh_mobile_meram.c index 9170c82..cc7d732 100644 --- a/drivers/video/sh_mobile_meram.c +++ b/drivers/video/sh_mobile_meram.c @@ -218,7 +218,7 @@ static inline void meram_get_next_icb_addr(struct sh_mobile_meram_info *pdata, icb_offset = 0xc0000000 | (cfg->current_reg << 23); *icb_addr_y = icb_offset | (cfg->icb[0].marker_icb << 24); - if ((*icb_addr_c) && is_nvcolor(cfg->pixelformat)) + if (is_nvcolor(cfg->pixelformat)) *icb_addr_c = icb_offset | (cfg->icb[1].marker_icb << 24); } diff --git a/drivers/video/sm501fb.c b/drivers/video/sm501fb.c index 87f0be1..6294dca 100644 --- a/drivers/video/sm501fb.c +++ b/drivers/video/sm501fb.c @@ -1664,7 +1664,7 @@ static void sm501fb_stop(struct sm501fb_info *info) resource_size(info->regs_res)); } -static int sm501fb_init_fb(struct fb_info *fb, +static int __devinit sm501fb_init_fb(struct fb_info *fb, enum sm501_controller head, const char *fbname) { diff --git a/drivers/video/udlfb.c b/drivers/video/udlfb.c index 52b0f3e..816a4fd 100644 --- a/drivers/video/udlfb.c +++ b/drivers/video/udlfb.c @@ -1233,8 +1233,12 @@ static int dlfb_setup_modes(struct dlfb_data *dev, if (dlfb_is_valid_mode(&info->monspecs.modedb[i], info)) fb_add_videomode(&info->monspecs.modedb[i], &info->modelist); - else /* if we've removed top/best mode */ - info->monspecs.misc &= ~FB_MISC_1ST_DETAIL; + else { + if (i == 0) + /* if we've removed top/best mode */ + info->monspecs.misc + &= ~FB_MISC_1ST_DETAIL; + } } default_vmode = fb_find_best_display(&info->monspecs, diff --git a/drivers/video/vesafb.c b/drivers/video/vesafb.c index a99bbe8..501b340 100644 --- a/drivers/video/vesafb.c +++ b/drivers/video/vesafb.c @@ -175,6 +175,7 @@ static int vesafb_setcolreg(unsigned regno, unsigned red, unsigned green, static void vesafb_destroy(struct fb_info *info) { + fb_dealloc_cmap(&info->cmap); if (info->screen_base) iounmap(info->screen_base); release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size); diff --git a/drivers/w1/masters/ds1wm.c b/drivers/w1/masters/ds1wm.c index ad57593..a0c8965 100644 --- a/drivers/w1/masters/ds1wm.c +++ b/drivers/w1/masters/ds1wm.c @@ -109,6 +109,7 @@ struct ds1wm_data { /* byte to write that makes all intr disabled, */ /* considering active_state (IAS) (optimization) */ u8 int_en_reg_none; + unsigned int reset_recover_delay; /* see ds1wm.h */ }; static inline void ds1wm_write_register(struct ds1wm_data *ds1wm_data, u32 reg, @@ -187,6 +188,9 @@ static int ds1wm_reset(struct ds1wm_data *ds1wm_data) return 1; } + if (ds1wm_data->reset_recover_delay) + msleep(ds1wm_data->reset_recover_delay); + return 0; } @@ -490,6 +494,7 @@ static int ds1wm_probe(struct platform_device *pdev) } ds1wm_data->irq = res->start; ds1wm_data->int_en_reg_none = (plat->active_high ? DS1WM_INTEN_IAS : 0); + ds1wm_data->reset_recover_delay = plat->reset_recover_delay; if (res->flags & IORESOURCE_IRQ_HIGHEDGE) irq_set_irq_type(ds1wm_data->irq, IRQ_TYPE_EDGE_RISING); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 022f9eb..21d816e 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -535,8 +535,7 @@ config I6300ESB_WDT config INTEL_SCU_WATCHDOG bool "Intel SCU Watchdog for Mobile Platforms" - depends on WATCHDOG - depends on INTEL_SCU_IPC + depends on X86_MRST ---help--- Hardware driver for the watchdog time built into the Intel SCU for Intel Mobile Platforms. @@ -600,8 +599,7 @@ config IT87_WDT config HP_WATCHDOG tristate "HP ProLiant iLO2+ Hardware Watchdog Timer" - depends on X86 - default m + depends on X86 && PCI help A software monitoring watchdog and NMI sourcing driver. This driver will detect lockups and provide a stack trace. This is a driver that diff --git a/drivers/watchdog/at32ap700x_wdt.c b/drivers/watchdog/at32ap700x_wdt.c index 750bc52..4ca5d40 100644 --- a/drivers/watchdog/at32ap700x_wdt.c +++ b/drivers/watchdog/at32ap700x_wdt.c @@ -448,7 +448,7 @@ static void __exit at32_wdt_exit(void) } module_exit(at32_wdt_exit); -MODULE_AUTHOR("Hans-Christian Egtvedt <hcegtvedt@atmel.com>"); +MODULE_AUTHOR("Hans-Christian Egtvedt <egtvedt@samfundet.no>"); MODULE_DESCRIPTION("Watchdog driver for Atmel AT32AP700X"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c index 29a7cd4..b146082 100644 --- a/drivers/watchdog/gef_wdt.c +++ b/drivers/watchdog/gef_wdt.c @@ -329,4 +329,4 @@ MODULE_AUTHOR("Martyn Welch <martyn.welch@ge.com>"); MODULE_DESCRIPTION("GE watchdog driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR); -MODULE_ALIAS("platform: gef_wdt"); +MODULE_ALIAS("platform:gef_wdt"); diff --git a/drivers/watchdog/intel_scu_watchdog.c b/drivers/watchdog/intel_scu_watchdog.c index 919bdd1..ba43860 100644 --- a/drivers/watchdog/intel_scu_watchdog.c +++ b/drivers/watchdog/intel_scu_watchdog.c @@ -42,7 +42,6 @@ #include <linux/sched.h> #include <linux/signal.h> #include <linux/sfi.h> -#include <linux/types.h> #include <asm/irq.h> #include <asm/atomic.h> #include <asm/intel_scu_ipc.h> diff --git a/drivers/watchdog/mtx-1_wdt.c b/drivers/watchdog/mtx-1_wdt.c index 1479dc4..0430e09 100644 --- a/drivers/watchdog/mtx-1_wdt.c +++ b/drivers/watchdog/mtx-1_wdt.c @@ -66,23 +66,18 @@ static struct { int default_ticks; unsigned long inuse; unsigned gpio; - int gstate; + unsigned int gstate; } mtx1_wdt_device; static void mtx1_wdt_trigger(unsigned long unused) { - u32 tmp; - spin_lock(&mtx1_wdt_device.lock); if (mtx1_wdt_device.running) ticks--; /* toggle wdt gpio */ - mtx1_wdt_device.gstate = ~mtx1_wdt_device.gstate; - if (mtx1_wdt_device.gstate) - gpio_direction_output(mtx1_wdt_device.gpio, 1); - else - gpio_direction_input(mtx1_wdt_device.gpio); + mtx1_wdt_device.gstate = !mtx1_wdt_device.gstate; + gpio_set_value(mtx1_wdt_device.gpio, mtx1_wdt_device.gstate); if (mtx1_wdt_device.queue && ticks) mod_timer(&mtx1_wdt_device.timer, jiffies + MTX1_WDT_INTERVAL); @@ -105,7 +100,7 @@ static void mtx1_wdt_start(void) if (!mtx1_wdt_device.queue) { mtx1_wdt_device.queue = 1; mtx1_wdt_device.gstate = 1; - gpio_direction_output(mtx1_wdt_device.gpio, 1); + gpio_set_value(mtx1_wdt_device.gpio, 1); mod_timer(&mtx1_wdt_device.timer, jiffies + MTX1_WDT_INTERVAL); } mtx1_wdt_device.running++; @@ -120,7 +115,7 @@ static int mtx1_wdt_stop(void) if (mtx1_wdt_device.queue) { mtx1_wdt_device.queue = 0; mtx1_wdt_device.gstate = 0; - gpio_direction_output(mtx1_wdt_device.gpio, 0); + gpio_set_value(mtx1_wdt_device.gpio, 0); } ticks = mtx1_wdt_device.default_ticks; spin_unlock_irqrestore(&mtx1_wdt_device.lock, flags); @@ -214,6 +209,12 @@ static int __devinit mtx1_wdt_probe(struct platform_device *pdev) int ret; mtx1_wdt_device.gpio = pdev->resource[0].start; + ret = gpio_request_one(mtx1_wdt_device.gpio, + GPIOF_OUT_INIT_HIGH, "mtx1-wdt"); + if (ret < 0) { + dev_err(&pdev->dev, "failed to request gpio"); + return ret; + } spin_lock_init(&mtx1_wdt_device.lock); init_completion(&mtx1_wdt_device.stop); @@ -239,11 +240,13 @@ static int __devexit mtx1_wdt_remove(struct platform_device *pdev) mtx1_wdt_device.queue = 0; wait_for_completion(&mtx1_wdt_device.stop); } + + gpio_free(mtx1_wdt_device.gpio); misc_deregister(&mtx1_wdt_misc); return 0; } -static struct platform_driver mtx1_wdt = { +static struct platform_driver mtx1_wdt_driver = { .probe = mtx1_wdt_probe, .remove = __devexit_p(mtx1_wdt_remove), .driver.name = "mtx1-wdt", @@ -252,12 +255,12 @@ static struct platform_driver mtx1_wdt = { static int __init mtx1_wdt_init(void) { - return platform_driver_register(&mtx1_wdt); + return platform_driver_register(&mtx1_wdt_driver); } static void __exit mtx1_wdt_exit(void) { - platform_driver_unregister(&mtx1_wdt); + platform_driver_unregister(&mtx1_wdt_driver); } module_init(mtx1_wdt_init); diff --git a/drivers/watchdog/wm831x_wdt.c b/drivers/watchdog/wm831x_wdt.c index 8c4b2d5..871caea 100644 --- a/drivers/watchdog/wm831x_wdt.c +++ b/drivers/watchdog/wm831x_wdt.c @@ -320,6 +320,11 @@ static int __devinit wm831x_wdt_probe(struct platform_device *pdev) struct wm831x_watchdog_pdata *pdata; int reg, ret; + if (wm831x) { + dev_err(&pdev->dev, "wm831x watchdog already registered\n"); + return -EBUSY; + } + wm831x = dev_get_drvdata(pdev->dev.parent); ret = wm831x_reg_read(wm831x, WM831X_WATCHDOG); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 30df85d..da70f5c 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -615,11 +615,6 @@ static int find_irq_by_gsi(unsigned gsi) return -1; } -int xen_allocate_pirq_gsi(unsigned gsi) -{ - return gsi; -} - /* * Do not make any assumptions regarding the relationship between the * IRQ number returned here and the Xen pirq argument. @@ -1693,6 +1688,6 @@ void __init xen_init_IRQ(void) } else { irq_ctx_init(smp_processor_id()); if (xen_initial_domain()) - xen_setup_pirqs(); + pci_xen_initial_domain(); } } diff --git a/firmware/Makefile b/firmware/Makefile index 0d15a3d..5f43bfb 100644 --- a/firmware/Makefile +++ b/firmware/Makefile @@ -82,6 +82,7 @@ fw-shipped-$(CONFIG_SERIAL_8250_CS) += cis/MT5634ZLX.cis cis/RS-COM-2P.cis \ fw-shipped-$(CONFIG_PCMCIA_SMC91C92) += ositech/Xilinx7OD.bin fw-shipped-$(CONFIG_SCSI_ADVANSYS) += advansys/mcode.bin advansys/38C1600.bin \ advansys/3550.bin advansys/38C0800.bin +fw-shipped-$(CONFIG_SCSI_ISCI) += isci/isci_firmware.bin fw-shipped-$(CONFIG_SCSI_QLOGIC_1280) += qlogic/1040.bin qlogic/1280.bin \ qlogic/12160.bin fw-shipped-$(CONFIG_SCSI_QLOGICPTI) += qlogic/isp1000.bin diff --git a/firmware/isci/isci_firmware.bin.ihex b/firmware/isci/isci_firmware.bin.ihex new file mode 100644 index 0000000..2e66195 --- /dev/null +++ b/firmware/isci/isci_firmware.bin.ihex @@ -0,0 +1,16 @@ +:10000000495343554F454D42E80018100002000087 +:1000100000000000000000000101000000000000DE +:10002000FFFFCF5F0100000008DD0B0000FC0F00A8 +:10003000097C0B006EFC0A00FFFFCF5F010000008F +:1000400008DD0B0000FC0F00097C0B006EFC0A00B1 +:10005000FFFFCF5F0100000008DD0B0000FC0F0078 +:10006000097C0B006EFC0A00FFFFCF5F010000005F +:1000700008DD0B0000FC0F00097C0B006EFC0A0081 +:100080000101000000000000FFFFCF5F0200000040 +:1000900008DD0B0000FC0F00097C0B006EFC0A0061 +:1000A000FFFFCF5F0200000008DD0B0000FC0F0027 +:1000B000097C0B006EFC0A00FFFFCF5F020000000E +:1000C00008DD0B0000FC0F00097C0B006EFC0A0031 +:1000D000FFFFCF5F0200000008DD0B0000FC0F00F7 +:0800E000097C0B006EFC0A0014 +:00000001FF diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 63039ed..2bc5dc6 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1864,6 +1864,7 @@ cleanup: kfree(psinfo); kfree(notes); kfree(fpu); + kfree(shdr4extnum); #ifdef ELF_CORE_COPY_XFPREGS kfree(xfpu); #endif diff --git a/fs/block_dev.c b/fs/block_dev.c index 1a2421f..610e8e0 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -762,7 +762,19 @@ static struct block_device *bd_start_claiming(struct block_device *bdev, if (!disk) return ERR_PTR(-ENXIO); - whole = bdget_disk(disk, 0); + /* + * Normally, @bdev should equal what's returned from bdget_disk() + * if partno is 0; however, some drivers (floppy) use multiple + * bdev's for the same physical device and @bdev may be one of the + * aliases. Keep @bdev if partno is 0. This means claimer + * tracking is broken for those devices but it has always been that + * way. + */ + if (partno) + whole = bdget_disk(disk, 0); + else + whole = bdgrab(bdev); + module_put(disk->fops->owner); put_disk(disk); if (!whole) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3006287..3b859a3 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -19,7 +19,6 @@ #ifndef __BTRFS_CTREE__ #define __BTRFS_CTREE__ -#include <linux/version.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/fs.h> @@ -1336,6 +1335,11 @@ struct btrfs_ioctl_defrag_range_args { */ #define BTRFS_STRING_ITEM_KEY 253 +/* + * Flags for mount options. + * + * Note: don't forget to add new options to btrfs_show_options() + */ #define BTRFS_MOUNT_NODATASUM (1 << 0) #define BTRFS_MOUNT_NODATACOW (1 << 1) #define BTRFS_MOUNT_NOBARRIER (1 << 2) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index f1cbd02..98c68e6 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -82,19 +82,16 @@ static inline struct btrfs_delayed_root *btrfs_get_delayed_root( return root->fs_info->delayed_root; } -static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( - struct inode *inode) +static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode) { - struct btrfs_delayed_node *node; struct btrfs_inode *btrfs_inode = BTRFS_I(inode); struct btrfs_root *root = btrfs_inode->root; u64 ino = btrfs_ino(inode); - int ret; + struct btrfs_delayed_node *node; -again: node = ACCESS_ONCE(btrfs_inode->delayed_node); if (node) { - atomic_inc(&node->refs); /* can be accessed */ + atomic_inc(&node->refs); return node; } @@ -102,8 +99,10 @@ again: node = radix_tree_lookup(&root->delayed_nodes_tree, ino); if (node) { if (btrfs_inode->delayed_node) { + atomic_inc(&node->refs); /* can be accessed */ + BUG_ON(btrfs_inode->delayed_node != node); spin_unlock(&root->inode_lock); - goto again; + return node; } btrfs_inode->delayed_node = node; atomic_inc(&node->refs); /* can be accessed */ @@ -113,6 +112,23 @@ again: } spin_unlock(&root->inode_lock); + return NULL; +} + +static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node( + struct inode *inode) +{ + struct btrfs_delayed_node *node; + struct btrfs_inode *btrfs_inode = BTRFS_I(inode); + struct btrfs_root *root = btrfs_inode->root; + u64 ino = btrfs_ino(inode); + int ret; + +again: + node = btrfs_get_delayed_node(inode); + if (node) + return node; + node = kmem_cache_alloc(delayed_node_cache, GFP_NOFS); if (!node) return ERR_PTR(-ENOMEM); @@ -548,19 +564,6 @@ struct btrfs_delayed_item *__btrfs_next_delayed_item( return next; } -static inline struct btrfs_delayed_node *btrfs_get_delayed_node( - struct inode *inode) -{ - struct btrfs_inode *btrfs_inode = BTRFS_I(inode); - struct btrfs_delayed_node *delayed_node; - - delayed_node = btrfs_inode->delayed_node; - if (delayed_node) - atomic_inc(&delayed_node->refs); - - return delayed_node; -} - static inline struct btrfs_root *btrfs_get_fs_root(struct btrfs_root *root, u64 root_id) { @@ -1404,8 +1407,7 @@ end: int btrfs_inode_delayed_dir_index_count(struct inode *inode) { - struct btrfs_delayed_node *delayed_node = BTRFS_I(inode)->delayed_node; - int ret = 0; + struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode); if (!delayed_node) return -ENOENT; @@ -1415,11 +1417,14 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode) * a new directory index is added into the delayed node and index_cnt * is updated now. So we needn't lock the delayed node. */ - if (!delayed_node->index_cnt) + if (!delayed_node->index_cnt) { + btrfs_release_delayed_node(delayed_node); return -EINVAL; + } BTRFS_I(inode)->index_cnt = delayed_node->index_cnt; - return ret; + btrfs_release_delayed_node(delayed_node); + return 0; } void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, @@ -1613,6 +1618,57 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, inode->i_ctime.tv_nsec); } +int btrfs_fill_inode(struct inode *inode, u32 *rdev) +{ + struct btrfs_delayed_node *delayed_node; + struct btrfs_inode_item *inode_item; + struct btrfs_timespec *tspec; + + delayed_node = btrfs_get_delayed_node(inode); + if (!delayed_node) + return -ENOENT; + + mutex_lock(&delayed_node->mutex); + if (!delayed_node->inode_dirty) { + mutex_unlock(&delayed_node->mutex); + btrfs_release_delayed_node(delayed_node); + return -ENOENT; + } + + inode_item = &delayed_node->inode_item; + + inode->i_uid = btrfs_stack_inode_uid(inode_item); + inode->i_gid = btrfs_stack_inode_gid(inode_item); + btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); + inode->i_mode = btrfs_stack_inode_mode(inode_item); + inode->i_nlink = btrfs_stack_inode_nlink(inode_item); + inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); + BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item); + BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item); + inode->i_rdev = 0; + *rdev = btrfs_stack_inode_rdev(inode_item); + BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item); + + tspec = btrfs_inode_atime(inode_item); + inode->i_atime.tv_sec = btrfs_stack_timespec_sec(tspec); + inode->i_atime.tv_nsec = btrfs_stack_timespec_nsec(tspec); + + tspec = btrfs_inode_mtime(inode_item); + inode->i_mtime.tv_sec = btrfs_stack_timespec_sec(tspec); + inode->i_mtime.tv_nsec = btrfs_stack_timespec_nsec(tspec); + + tspec = btrfs_inode_ctime(inode_item); + inode->i_ctime.tv_sec = btrfs_stack_timespec_sec(tspec); + inode->i_ctime.tv_nsec = btrfs_stack_timespec_nsec(tspec); + + inode->i_generation = BTRFS_I(inode)->generation; + BTRFS_I(inode)->index_cnt = (u64)-1; + + mutex_unlock(&delayed_node->mutex); + btrfs_release_delayed_node(delayed_node); + return 0; +} + int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode) { diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index d1a6a29..8d27af4 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -119,6 +119,7 @@ void btrfs_kill_delayed_inode_items(struct inode *inode); int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); +int btrfs_fill_inode(struct inode *inode, u32 *rdev); /* Used for drop dead root */ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1f61bf5..71cd456 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4842,7 +4842,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, u64 num_bytes, u64 empty_size, u64 search_start, u64 search_end, u64 hint_byte, struct btrfs_key *ins, - int data) + u64 data) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -4869,7 +4869,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans, space_info = __find_space_info(root->fs_info, data); if (!space_info) { - printk(KERN_ERR "No space info for %d\n", data); + printk(KERN_ERR "No space info for %llu\n", data); return -ENOSPC; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 9f985a4..bf0d615 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1893,9 +1893,12 @@ void __btrfs_remove_free_space_cache_locked(struct btrfs_free_space_ctl *ctl) while ((node = rb_last(&ctl->free_space_offset)) != NULL) { info = rb_entry(node, struct btrfs_free_space, offset_index); - unlink_free_space(ctl, info); - kfree(info->bitmap); - kmem_cache_free(btrfs_free_space_cachep, info); + if (!info->bitmap) { + unlink_free_space(ctl, info); + kmem_cache_free(btrfs_free_space_cachep, info); + } else { + free_bitmap(ctl, info); + } if (need_resched()) { spin_unlock(&ctl->tree_lock); cond_resched(); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0a9b10c..3601f0a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2509,6 +2509,11 @@ static void btrfs_read_locked_inode(struct inode *inode) int maybe_acls; u32 rdev; int ret; + bool filled = false; + + ret = btrfs_fill_inode(inode, &rdev); + if (!ret) + filled = true; path = btrfs_alloc_path(); BUG_ON(!path); @@ -2520,6 +2525,10 @@ static void btrfs_read_locked_inode(struct inode *inode) goto make_bad; leaf = path->nodes[0]; + + if (filled) + goto cache_acl; + inode_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item); if (!leaf->map_token) @@ -2556,7 +2565,7 @@ static void btrfs_read_locked_inode(struct inode *inode) BTRFS_I(inode)->index_cnt = (u64)-1; BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item); - +cache_acl: /* * try to precache a NULL acl entry for files that don't have * any xattrs or acls @@ -2572,7 +2581,6 @@ static void btrfs_read_locked_inode(struct inode *inode) } btrfs_free_path(path); - inode_item = NULL; switch (inode->i_mode & S_IFMT) { case S_IFREG: @@ -2670,12 +2678,14 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, int ret; /* - * If root is tree root, it means this inode is used to - * store free space information. And these inodes are updated - * when committing the transaction, so they needn't delaye to - * be updated, or deadlock will occured. + * If the inode is a free space inode, we can deadlock during commit + * if we put it into the delayed code. + * + * The data relocation inode should also be directly updated + * without delay */ - if (!is_free_space_inode(root, inode)) { + if (!is_free_space_inode(root, inode) + && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { ret = btrfs_delayed_update_inode(trans, root, inode); if (!ret) btrfs_set_inode_last_trans(trans, inode); @@ -4520,6 +4530,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, inode_tree_add(inode); trace_btrfs_inode_new(inode); + btrfs_set_inode_last_trans(trans, inode); return inode; fail: diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0bb4ebb..15634d4 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -723,6 +723,12 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",clear_cache"); if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED)) seq_puts(seq, ",user_subvol_rm_allowed"); + if (btrfs_test_opt(root, ENOSPC_DEBUG)) + seq_puts(seq, ",enospc_debug"); + if (btrfs_test_opt(root, AUTO_DEFRAG)) + seq_puts(seq, ",autodefrag"); + if (btrfs_test_opt(root, INODE_MAP_CACHE)) + seq_puts(seq, ",inode_cache"); return 0; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1efa56e..19450bc 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2098,7 +2098,8 @@ int btrfs_balance(struct btrfs_root *dev_root) chunk_root->root_key.objectid, found_key.objectid, found_key.offset); - BUG_ON(ret && ret != -ENOSPC); + if (ret && ret != -ENOSPC) + goto error; key.offset = found_key.offset - 1; } ret = 0; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 9542f07..4698a5c 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -290,7 +290,6 @@ static int striped_read(struct inode *inode, struct ceph_inode_info *ci = ceph_inode(inode); u64 pos, this_len; int io_align, page_align; - int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */ int left, pages_left; int read; struct page **page_pos; @@ -326,12 +325,11 @@ more: ret, hit_stripe ? " HITSTRIPE" : "", was_short ? " SHORT" : ""); if (ret > 0) { - int didpages = - ((pos & ~PAGE_CACHE_MASK) + ret) >> PAGE_CACHE_SHIFT; + int didpages = (page_align + ret) >> PAGE_CACHE_SHIFT; if (read < pos - off) { dout(" zero gap %llu to %llu\n", off + read, pos); - ceph_zero_page_vector_range(page_off + read, + ceph_zero_page_vector_range(page_align + read, pos - off - read, pages); } pos += ret; @@ -356,7 +354,7 @@ more: left = inode->i_size - pos; dout("zero tail %d\n", left); - ceph_zero_page_vector_range(page_off + read, left, + ceph_zero_page_vector_range(page_align + read, left, pages); read += left; } @@ -478,9 +476,6 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, else pos = *offset; - io_align = pos & ~PAGE_MASK; - buf_align = (unsigned long)data & ~PAGE_MASK; - ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left); if (ret < 0) return ret; @@ -504,6 +499,8 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data, * boundary. this isn't atomic, unfortunately. :( */ more: + io_align = pos & ~PAGE_MASK; + buf_align = (unsigned long)data & ~PAGE_MASK; len = left; if (file->f_flags & O_DIRECT) { /* write from beginning of first page, regardless of @@ -593,6 +590,7 @@ out: pos += len; written += len; left -= len; + data += written; if (left) goto more; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 79743d1..0c1d917 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1438,12 +1438,15 @@ char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, struct dentry *temp; char *path; int len, pos; + unsigned seq; if (dentry == NULL) return ERR_PTR(-EINVAL); retry: len = 0; + seq = read_seqbegin(&rename_lock); + rcu_read_lock(); for (temp = dentry; !IS_ROOT(temp);) { struct inode *inode = temp->d_inode; if (inode && ceph_snap(inode) == CEPH_SNAPDIR) @@ -1455,10 +1458,12 @@ retry: len += 1 + temp->d_name.len; temp = temp->d_parent; if (temp == NULL) { + rcu_read_unlock(); pr_err("build_path corrupt dentry %p\n", dentry); return ERR_PTR(-EINVAL); } } + rcu_read_unlock(); if (len) len--; /* no leading '/' */ @@ -1467,9 +1472,12 @@ retry: return ERR_PTR(-ENOMEM); pos = len; path[pos] = 0; /* trailing null */ + rcu_read_lock(); for (temp = dentry; !IS_ROOT(temp) && pos != 0; ) { - struct inode *inode = temp->d_inode; + struct inode *inode; + spin_lock(&temp->d_lock); + inode = temp->d_inode; if (inode && ceph_snap(inode) == CEPH_SNAPDIR) { dout("build_path path+%d: %p SNAPDIR\n", pos, temp); @@ -1478,21 +1486,26 @@ retry: break; } else { pos -= temp->d_name.len; - if (pos < 0) + if (pos < 0) { + spin_unlock(&temp->d_lock); break; + } strncpy(path + pos, temp->d_name.name, temp->d_name.len); } + spin_unlock(&temp->d_lock); if (pos) path[--pos] = '/'; temp = temp->d_parent; if (temp == NULL) { + rcu_read_unlock(); pr_err("build_path corrupt dentry\n"); kfree(path); return ERR_PTR(-EINVAL); } } - if (pos != 0) { + rcu_read_unlock(); + if (pos != 0 || read_seqretry(&rename_lock, seq)) { pr_err("build_path did not end path lookup where " "expected, namelen is %d, pos is %d\n", len, pos); /* presumably this is only possible if racing with a diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 53ed1ad..f66cc16 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -156,6 +156,6 @@ config CIFS_ACL config CIFS_NFSD_EXPORT bool "Allow nfsd to export CIFS file system (EXPERIMENTAL)" - depends on CIFS && EXPERIMENTAL + depends on CIFS && EXPERIMENTAL && BROKEN help Allows NFS server to export a CIFS mounted share (nfsd over cifs) diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index ffb1459..7260e11 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -42,6 +42,7 @@ #define CIFS_MOUNT_MULTIUSER 0x20000 /* multiuser mount */ #define CIFS_MOUNT_STRICT_IO 0x40000 /* strict cache mode */ #define CIFS_MOUNT_RWPIDFORWARD 0x80000 /* use pid forwarding for rw */ +#define CIFS_MOUNT_POSIXACL 0x100000 /* mirror of MS_POSIXACL in mnt_cifs_flags */ struct cifs_sb_info { struct rb_root tlink_tree; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 2f0c586..bc4b12c 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -35,6 +35,7 @@ #include <linux/delay.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/namei.h> #include <net/ipv6.h> #include "cifsfs.h" #include "cifspdu.h" @@ -104,8 +105,7 @@ cifs_sb_deactive(struct super_block *sb) } static int -cifs_read_super(struct super_block *sb, struct smb_vol *volume_info, - const char *devname, int silent) +cifs_read_super(struct super_block *sb) { struct inode *inode; struct cifs_sb_info *cifs_sb; @@ -113,22 +113,16 @@ cifs_read_super(struct super_block *sb, struct smb_vol *volume_info, cifs_sb = CIFS_SB(sb); - spin_lock_init(&cifs_sb->tlink_tree_lock); - cifs_sb->tlink_tree = RB_ROOT; + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL) + sb->s_flags |= MS_POSIXACL; - rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); - if (rc) - return rc; - - cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages; + if (cifs_sb_master_tcon(cifs_sb)->ses->capabilities & CAP_LARGE_FILES) + sb->s_maxbytes = MAX_LFS_FILESIZE; + else + sb->s_maxbytes = MAX_NON_LFS; - rc = cifs_mount(sb, cifs_sb, volume_info, devname); - - if (rc) { - if (!silent) - cERROR(1, "cifs_mount failed w/return code = %d", rc); - goto out_mount_failed; - } + /* BB FIXME fix time_gran to be larger for LANMAN sessions */ + sb->s_time_gran = 100; sb->s_magic = CIFS_MAGIC_NUMBER; sb->s_op = &cifs_super_ops; @@ -170,37 +164,14 @@ out_no_root: if (inode) iput(inode); - cifs_umount(sb, cifs_sb); - -out_mount_failed: - bdi_destroy(&cifs_sb->bdi); return rc; } -static void -cifs_put_super(struct super_block *sb) +static void cifs_kill_sb(struct super_block *sb) { - int rc = 0; - struct cifs_sb_info *cifs_sb; - - cFYI(1, "In cifs_put_super"); - cifs_sb = CIFS_SB(sb); - if (cifs_sb == NULL) { - cFYI(1, "Empty cifs superblock info passed to unmount"); - return; - } - - rc = cifs_umount(sb, cifs_sb); - if (rc) - cERROR(1, "cifs_umount failed with return code %d", rc); - if (cifs_sb->mountdata) { - kfree(cifs_sb->mountdata); - cifs_sb->mountdata = NULL; - } - - unload_nls(cifs_sb->local_nls); - bdi_destroy(&cifs_sb->bdi); - kfree(cifs_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); + kill_anon_super(sb); + cifs_umount(cifs_sb); } static int @@ -548,7 +519,6 @@ static int cifs_drop_inode(struct inode *inode) } static const struct super_operations cifs_super_ops = { - .put_super = cifs_put_super, .statfs = cifs_statfs, .alloc_inode = cifs_alloc_inode, .destroy_inode = cifs_destroy_inode, @@ -573,91 +543,55 @@ static const struct super_operations cifs_super_ops = { static struct dentry * cifs_get_root(struct smb_vol *vol, struct super_block *sb) { - int xid, rc; - struct inode *inode; - struct qstr name; - struct dentry *dparent = NULL, *dchild = NULL, *alias; + struct dentry *dentry; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - unsigned int i, full_len, len; - char *full_path = NULL, *pstart; + char *full_path = NULL; + char *s, *p; char sep; + int xid; full_path = cifs_build_path_to_root(vol, cifs_sb, cifs_sb_master_tcon(cifs_sb)); if (full_path == NULL) - return NULL; + return ERR_PTR(-ENOMEM); cFYI(1, "Get root dentry for %s", full_path); xid = GetXid(); sep = CIFS_DIR_SEP(cifs_sb); - dparent = dget(sb->s_root); - full_len = strlen(full_path); - full_path[full_len] = sep; - pstart = full_path + 1; - - for (i = 1, len = 0; i <= full_len; i++) { - if (full_path[i] != sep || !len) { - len++; - continue; - } - - full_path[i] = 0; - cFYI(1, "get dentry for %s", pstart); - - name.name = pstart; - name.len = len; - name.hash = full_name_hash(pstart, len); - dchild = d_lookup(dparent, &name); - if (dchild == NULL) { - cFYI(1, "not exists"); - dchild = d_alloc(dparent, &name); - if (dchild == NULL) { - dput(dparent); - dparent = NULL; - goto out; - } - } - - cFYI(1, "get inode"); - if (dchild->d_inode == NULL) { - cFYI(1, "not exists"); - inode = NULL; - if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext) - rc = cifs_get_inode_info_unix(&inode, full_path, - sb, xid); - else - rc = cifs_get_inode_info(&inode, full_path, - NULL, sb, xid, NULL); - if (rc) { - dput(dchild); - dput(dparent); - dparent = NULL; - goto out; - } - alias = d_materialise_unique(dchild, inode); - if (alias != NULL) { - dput(dchild); - if (IS_ERR(alias)) { - dput(dparent); - dparent = NULL; - goto out; - } - dchild = alias; - } - } - cFYI(1, "parent %p, child %p", dparent, dchild); - - dput(dparent); - dparent = dchild; - len = 0; - pstart = full_path + i + 1; - full_path[i] = sep; - } -out: + dentry = dget(sb->s_root); + p = s = full_path; + + do { + struct inode *dir = dentry->d_inode; + struct dentry *child; + + /* skip separators */ + while (*s == sep) + s++; + if (!*s) + break; + p = s++; + /* next separator */ + while (*s && *s != sep) + s++; + + mutex_lock(&dir->i_mutex); + child = lookup_one_len(p, dentry, s - p); + mutex_unlock(&dir->i_mutex); + dput(dentry); + dentry = child; + } while (!IS_ERR(dentry)); _FreeXid(xid); kfree(full_path); - return dparent; + return dentry; +} + +static int cifs_set_super(struct super_block *sb, void *data) +{ + struct cifs_mnt_data *mnt_data = data; + sb->s_fs_info = mnt_data->cifs_sb; + return set_anon_super(sb, NULL); } static struct dentry * @@ -673,82 +607,80 @@ cifs_do_mount(struct file_system_type *fs_type, cFYI(1, "Devname: %s flags: %d ", dev_name, flags); - rc = cifs_setup_volume_info(&volume_info, (char *)data, dev_name); - if (rc) - return ERR_PTR(rc); + volume_info = cifs_get_volume_info((char *)data, dev_name); + if (IS_ERR(volume_info)) + return ERR_CAST(volume_info); cifs_sb = kzalloc(sizeof(struct cifs_sb_info), GFP_KERNEL); if (cifs_sb == NULL) { root = ERR_PTR(-ENOMEM); - goto out; + goto out_nls; + } + + cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL); + if (cifs_sb->mountdata == NULL) { + root = ERR_PTR(-ENOMEM); + goto out_cifs_sb; } cifs_setup_cifs_sb(volume_info, cifs_sb); + rc = cifs_mount(cifs_sb, volume_info); + if (rc) { + if (!(flags & MS_SILENT)) + cERROR(1, "cifs_mount failed w/return code = %d", rc); + root = ERR_PTR(rc); + goto out_mountdata; + } + mnt_data.vol = volume_info; mnt_data.cifs_sb = cifs_sb; mnt_data.flags = flags; - sb = sget(fs_type, cifs_match_super, set_anon_super, &mnt_data); + sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data); if (IS_ERR(sb)) { root = ERR_CAST(sb); - goto out_cifs_sb; + cifs_umount(cifs_sb); + goto out; } - if (sb->s_fs_info) { + if (sb->s_root) { cFYI(1, "Use existing superblock"); - goto out_shared; - } - - /* - * Copy mount params for use in submounts. Better to do - * the copy here and deal with the error before cleanup gets - * complicated post-mount. - */ - cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL); - if (cifs_sb->mountdata == NULL) { - root = ERR_PTR(-ENOMEM); - goto out_super; - } - - sb->s_flags = flags; - /* BB should we make this contingent on mount parm? */ - sb->s_flags |= MS_NODIRATIME | MS_NOATIME; - sb->s_fs_info = cifs_sb; + cifs_umount(cifs_sb); + } else { + sb->s_flags = flags; + /* BB should we make this contingent on mount parm? */ + sb->s_flags |= MS_NODIRATIME | MS_NOATIME; + + rc = cifs_read_super(sb); + if (rc) { + root = ERR_PTR(rc); + goto out_super; + } - rc = cifs_read_super(sb, volume_info, dev_name, - flags & MS_SILENT ? 1 : 0); - if (rc) { - root = ERR_PTR(rc); - goto out_super; + sb->s_flags |= MS_ACTIVE; } - sb->s_flags |= MS_ACTIVE; - root = cifs_get_root(volume_info, sb); - if (root == NULL) + if (IS_ERR(root)) goto out_super; cFYI(1, "dentry root is: %p", root); goto out; -out_shared: - root = cifs_get_root(volume_info, sb); - if (root) - cFYI(1, "dentry root is: %p", root); - goto out; - out_super: - kfree(cifs_sb->mountdata); deactivate_locked_super(sb); +out: + cifs_cleanup_volume_info(volume_info); + return root; +out_mountdata: + kfree(cifs_sb->mountdata); out_cifs_sb: - unload_nls(cifs_sb->local_nls); kfree(cifs_sb); - -out: - cifs_cleanup_volume_info(&volume_info); - return root; +out_nls: + unload_nls(volume_info->local_nls); + goto out; } static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, @@ -837,7 +769,7 @@ struct file_system_type cifs_fs_type = { .owner = THIS_MODULE, .name = "cifs", .mount = cifs_do_mount, - .kill_sb = kill_anon_super, + .kill_sb = cifs_kill_sb, /* .fs_flags */ }; const struct inode_operations cifs_dir_inode_ops = { diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 0900e16..036ca83 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -129,5 +129,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "1.73" +#define CIFS_VERSION "1.74" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 953f844..8df28e9 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -154,12 +154,11 @@ extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *, extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, struct cifs_sb_info *cifs_sb); extern int cifs_match_super(struct super_block *, void *); -extern void cifs_cleanup_volume_info(struct smb_vol **pvolume_info); -extern int cifs_setup_volume_info(struct smb_vol **pvolume_info, - char *mount_data, const char *devname); -extern int cifs_mount(struct super_block *, struct cifs_sb_info *, - struct smb_vol *, const char *); -extern int cifs_umount(struct super_block *, struct cifs_sb_info *); +extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info); +extern struct smb_vol *cifs_get_volume_info(char *mount_data, + const char *devname); +extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *); +extern void cifs_umount(struct cifs_sb_info *); extern void cifs_dfs_release_automount_timer(void); void cifs_proc_init(void); void cifs_proc_clean(void); @@ -218,7 +217,8 @@ extern int get_dfs_path(int xid, struct cifs_ses *pSesInfo, struct dfs_info3_param **preferrals, int remap); extern void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon, - struct super_block *sb, struct smb_vol *vol); + struct cifs_sb_info *cifs_sb, + struct smb_vol *vol); extern int CIFSSMBQFSInfo(const int xid, struct cifs_tcon *tcon, struct kstatfs *FSData); extern int SMBOldQFSInfo(const int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 12cf72d..ccc1afa 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -65,6 +65,8 @@ static int ip_connect(struct TCP_Server_Info *server); static int generic_ip_connect(struct TCP_Server_Info *server); static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); static void cifs_prune_tlinks(struct work_struct *work); +static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, + const char *devname); /* * cifs tcp session reconnection @@ -2240,8 +2242,8 @@ cifs_match_super(struct super_block *sb, void *data) rc = compare_mount_options(sb, mnt_data); out: - cifs_put_tlink(tlink); spin_unlock(&cifs_tcp_ses_lock); + cifs_put_tlink(tlink); return rc; } @@ -2474,14 +2476,6 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) return rc; - rc = socket->ops->connect(socket, saddr, slen, 0); - if (rc < 0) { - cFYI(1, "Error %d connecting to server", rc); - sock_release(socket); - server->ssocket = NULL; - return rc; - } - /* * Eventually check for other socket options to change from * the default. sock_setsockopt not used because it expects @@ -2510,6 +2504,14 @@ generic_ip_connect(struct TCP_Server_Info *server) socket->sk->sk_sndbuf, socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo); + rc = socket->ops->connect(socket, saddr, slen, 0); + if (rc < 0) { + cFYI(1, "Error %d connecting to server", rc); + sock_release(socket); + server->ssocket = NULL; + return rc; + } + if (sport == htons(RFC1001_PORT)) rc = ip_rfc1001_connect(server); @@ -2546,7 +2548,7 @@ ip_connect(struct TCP_Server_Info *server) } void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon, - struct super_block *sb, struct smb_vol *vol_info) + struct cifs_sb_info *cifs_sb, struct smb_vol *vol_info) { /* if we are reconnecting then should we check to see if * any requested capabilities changed locally e.g. via @@ -2600,22 +2602,23 @@ void reset_cifs_unix_caps(int xid, struct cifs_tcon *tcon, cap &= ~CIFS_UNIX_POSIX_ACL_CAP; else if (CIFS_UNIX_POSIX_ACL_CAP & cap) { cFYI(1, "negotiated posix acl support"); - if (sb) - sb->s_flags |= MS_POSIXACL; + if (cifs_sb) + cifs_sb->mnt_cifs_flags |= + CIFS_MOUNT_POSIXACL; } if (vol_info && vol_info->posix_paths == 0) cap &= ~CIFS_UNIX_POSIX_PATHNAMES_CAP; else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) { cFYI(1, "negotiate posix pathnames"); - if (sb) - CIFS_SB(sb)->mnt_cifs_flags |= + if (cifs_sb) + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; } - if (sb && (CIFS_SB(sb)->rsize > 127 * 1024)) { + if (cifs_sb && (cifs_sb->rsize > 127 * 1024)) { if ((cap & CIFS_UNIX_LARGE_READ_CAP) == 0) { - CIFS_SB(sb)->rsize = 127 * 1024; + cifs_sb->rsize = 127 * 1024; cFYI(DBG2, "larger reads not supported by srv"); } } @@ -2662,6 +2665,9 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, { INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks); + spin_lock_init(&cifs_sb->tlink_tree_lock); + cifs_sb->tlink_tree = RB_ROOT; + if (pvolume_info->rsize > CIFSMaxBufSize) { cERROR(1, "rsize %d too large, using MaxBufSize", pvolume_info->rsize); @@ -2750,21 +2756,21 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, /* * When the server supports very large writes via POSIX extensions, we can - * allow up to 2^24 - PAGE_CACHE_SIZE. + * allow up to 2^24-1, minus the size of a WRITE_AND_X header, not including + * the RFC1001 length. * * Note that this might make for "interesting" allocation problems during - * writeback however (as we have to allocate an array of pointers for the - * pages). A 16M write means ~32kb page array with PAGE_CACHE_SIZE == 4096. + * writeback however as we have to allocate an array of pointers for the + * pages. A 16M write means ~32kb page array with PAGE_CACHE_SIZE == 4096. */ -#define CIFS_MAX_WSIZE ((1<<24) - PAGE_CACHE_SIZE) +#define CIFS_MAX_WSIZE ((1<<24) - 1 - sizeof(WRITE_REQ) + 4) /* - * When the server doesn't allow large posix writes, default to a wsize of - * 128k - PAGE_CACHE_SIZE -- one page less than the largest frame size - * described in RFC1001. This allows space for the header without going over - * that by default. + * When the server doesn't allow large posix writes, only allow a wsize of + * 128k minus the size of the WRITE_AND_X header. That allows for a write up + * to the maximum size described by RFC1002. */ -#define CIFS_MAX_RFC1001_WSIZE (128 * 1024 - PAGE_CACHE_SIZE) +#define CIFS_MAX_RFC1002_WSIZE (128 * 1024 - sizeof(WRITE_REQ) + 4) /* * The default wsize is 1M. find_get_pages seems to return a maximum of 256 @@ -2783,11 +2789,18 @@ cifs_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) /* can server support 24-bit write sizes? (via UNIX extensions) */ if (!tcon->unix_ext || !(unix_cap & CIFS_UNIX_LARGE_WRITE_CAP)) - wsize = min_t(unsigned int, wsize, CIFS_MAX_RFC1001_WSIZE); + wsize = min_t(unsigned int, wsize, CIFS_MAX_RFC1002_WSIZE); - /* no CAP_LARGE_WRITE_X? Limit it to 16 bits */ - if (!(server->capabilities & CAP_LARGE_WRITE_X)) - wsize = min_t(unsigned int, wsize, USHRT_MAX); + /* + * no CAP_LARGE_WRITE_X or is signing enabled without CAP_UNIX set? + * Limit it to max buffer offered by the server, minus the size of the + * WRITEX header, not including the 4 byte RFC1001 length. + */ + if (!(server->capabilities & CAP_LARGE_WRITE_X) || + (!(server->capabilities & CAP_UNIX) && + (server->sec_mode & (SECMODE_SIGN_ENABLED|SECMODE_SIGN_REQUIRED)))) + wsize = min_t(unsigned int, wsize, + server->maxBuf - sizeof(WRITE_REQ) + 4); /* hard limit of CIFS_MAX_WSIZE */ wsize = min_t(unsigned int, wsize, CIFS_MAX_WSIZE); @@ -2819,15 +2832,9 @@ is_path_accessible(int xid, struct cifs_tcon *tcon, return rc; } -void -cifs_cleanup_volume_info(struct smb_vol **pvolume_info) +static void +cleanup_volume_info_contents(struct smb_vol *volume_info) { - struct smb_vol *volume_info; - - if (!pvolume_info || !*pvolume_info) - return; - - volume_info = *pvolume_info; kfree(volume_info->username); kzfree(volume_info->password); kfree(volume_info->UNC); @@ -2835,28 +2842,44 @@ cifs_cleanup_volume_info(struct smb_vol **pvolume_info) kfree(volume_info->domainname); kfree(volume_info->iocharset); kfree(volume_info->prepath); +} + +void +cifs_cleanup_volume_info(struct smb_vol *volume_info) +{ + if (!volume_info) + return; + cleanup_volume_info_contents(volume_info); kfree(volume_info); - *pvolume_info = NULL; - return; } + #ifdef CONFIG_CIFS_DFS_UPCALL /* build_path_to_root returns full path to root when * we do not have an exiting connection (tcon) */ static char * -build_unc_path_to_root(const struct smb_vol *volume_info, +build_unc_path_to_root(const struct smb_vol *vol, const struct cifs_sb_info *cifs_sb) { - char *full_path; + char *full_path, *pos; + unsigned int pplen = vol->prepath ? strlen(vol->prepath) : 0; + unsigned int unc_len = strnlen(vol->UNC, MAX_TREE_SIZE + 1); - int unc_len = strnlen(volume_info->UNC, MAX_TREE_SIZE + 1); - full_path = kmalloc(unc_len + 1, GFP_KERNEL); + full_path = kmalloc(unc_len + pplen + 1, GFP_KERNEL); if (full_path == NULL) return ERR_PTR(-ENOMEM); - strncpy(full_path, volume_info->UNC, unc_len); - full_path[unc_len] = 0; /* add trailing null */ + strncpy(full_path, vol->UNC, unc_len); + pos = full_path + unc_len; + + if (pplen) { + strncpy(pos, vol->prepath, pplen); + pos += pplen; + } + + *pos = '\0'; /* add trailing null */ convert_delimiter(full_path, CIFS_DIR_SEP(cifs_sb)); + cFYI(1, "%s: full_path=%s", __func__, full_path); return full_path; } @@ -2899,15 +2922,18 @@ expand_dfs_referral(int xid, struct cifs_ses *pSesInfo, &fake_devname); free_dfs_info_array(referrals, num_referrals); - kfree(fake_devname); - - if (cifs_sb->mountdata != NULL) - kfree(cifs_sb->mountdata); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; + } else { + cleanup_volume_info_contents(volume_info); + memset(volume_info, '\0', sizeof(*volume_info)); + rc = cifs_setup_volume_info(volume_info, mdata, + fake_devname); } + kfree(fake_devname); + kfree(cifs_sb->mountdata); cifs_sb->mountdata = mdata; } kfree(full_path); @@ -2915,29 +2941,20 @@ expand_dfs_referral(int xid, struct cifs_ses *pSesInfo, } #endif -int cifs_setup_volume_info(struct smb_vol **pvolume_info, char *mount_data, - const char *devname) +static int +cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, + const char *devname) { - struct smb_vol *volume_info; int rc = 0; - *pvolume_info = NULL; - - volume_info = kzalloc(sizeof(struct smb_vol), GFP_KERNEL); - if (!volume_info) { - rc = -ENOMEM; - goto out; - } - - if (cifs_parse_mount_options(mount_data, devname, - volume_info)) { - rc = -EINVAL; - goto out; - } + if (cifs_parse_mount_options(mount_data, devname, volume_info)) + return -EINVAL; if (volume_info->nullauth) { cFYI(1, "null user"); - volume_info->username = ""; + volume_info->username = kzalloc(1, GFP_KERNEL); + if (volume_info->username == NULL) + return -ENOMEM; } else if (volume_info->username) { /* BB fixme parse for domain name here */ cFYI(1, "Username: %s", volume_info->username); @@ -2945,8 +2962,7 @@ int cifs_setup_volume_info(struct smb_vol **pvolume_info, char *mount_data, cifserror("No username specified"); /* In userspace mount helper we can get user name from alternate locations such as env variables and files on disk */ - rc = -EINVAL; - goto out; + return -EINVAL; } /* this is needed for ASCII cp to Unicode converts */ @@ -2958,21 +2974,34 @@ int cifs_setup_volume_info(struct smb_vol **pvolume_info, char *mount_data, if (volume_info->local_nls == NULL) { cERROR(1, "CIFS mount error: iocharset %s not found", volume_info->iocharset); - rc = -ELIBACC; - goto out; + return -ELIBACC; } } - *pvolume_info = volume_info; - return rc; -out: - cifs_cleanup_volume_info(&volume_info); return rc; } +struct smb_vol * +cifs_get_volume_info(char *mount_data, const char *devname) +{ + int rc; + struct smb_vol *volume_info; + + volume_info = kzalloc(sizeof(struct smb_vol), GFP_KERNEL); + if (!volume_info) + return ERR_PTR(-ENOMEM); + + rc = cifs_setup_volume_info(volume_info, mount_data, devname); + if (rc) { + cifs_cleanup_volume_info(volume_info); + volume_info = ERR_PTR(rc); + } + + return volume_info; +} + int -cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, - struct smb_vol *volume_info, const char *devname) +cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) { int rc = 0; int xid; @@ -2983,6 +3012,15 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb, struct tcon_link *tlink; #ifdef CONFIG_CIFS_DFS_UPCALL int referral_walks_count = 0; +#endif + + rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs", BDI_CAP_MAP_COPY); + if (rc) + return rc; + + cifs_sb->bdi.ra_pages = default_backing_dev_info.ra_pages; + +#ifdef CONFIG_CIFS_DFS_UPCALL try_mount_again: /* cleanup activities if we're chasing a referral */ if (referral_walks_count) { @@ -2991,7 +3029,6 @@ try_mount_again: else if (pSesInfo) cifs_put_smb_ses(pSesInfo); - cifs_cleanup_volume_info(&volume_info); FreeXid(xid); } #endif @@ -3007,6 +3044,7 @@ try_mount_again: srvTcp = cifs_get_tcp_session(volume_info); if (IS_ERR(srvTcp)) { rc = PTR_ERR(srvTcp); + bdi_destroy(&cifs_sb->bdi); goto out; } @@ -3018,14 +3056,6 @@ try_mount_again: goto mount_fail_check; } - if (pSesInfo->capabilities & CAP_LARGE_FILES) - sb->s_maxbytes = MAX_LFS_FILESIZE; - else - sb->s_maxbytes = MAX_NON_LFS; - - /* BB FIXME fix time_gran to be larger for LANMAN sessions */ - sb->s_time_gran = 100; - /* search for existing tcon to this server share */ tcon = cifs_get_tcon(pSesInfo, volume_info); if (IS_ERR(tcon)) { @@ -3038,7 +3068,7 @@ try_mount_again: if (tcon->ses->capabilities & CAP_UNIX) { /* reset of caps checks mount to see if unix extensions disabled for just this mount */ - reset_cifs_unix_caps(xid, tcon, sb, volume_info); + reset_cifs_unix_caps(xid, tcon, cifs_sb, volume_info); if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && (le64_to_cpu(tcon->fsUnixInfo.Capability) & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { @@ -3161,6 +3191,7 @@ mount_fail_check: cifs_put_smb_ses(pSesInfo); else cifs_put_tcp_session(srvTcp); + bdi_destroy(&cifs_sb->bdi); goto out; } @@ -3335,8 +3366,8 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses, return rc; } -int -cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) +void +cifs_umount(struct cifs_sb_info *cifs_sb) { struct rb_root *root = &cifs_sb->tlink_tree; struct rb_node *node; @@ -3357,7 +3388,10 @@ cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb) } spin_unlock(&cifs_sb->tlink_tree_lock); - return 0; + bdi_destroy(&cifs_sb->bdi); + kfree(cifs_sb->mountdata); + unload_nls(cifs_sb->local_nls); + kfree(cifs_sb); } int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses) @@ -3451,7 +3485,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, uid_t fsuid) goto out; } - snprintf(username, MAX_USERNAME_SIZE, "krb50x%x", fsuid); + snprintf(username, sizeof(username), "krb50x%x", fsuid); vol_info->username = username; vol_info->local_nls = cifs_sb->local_nls; vol_info->linux_uid = fsuid; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 81914df..fa8c21d 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -55,6 +55,7 @@ build_path_from_dentry(struct dentry *direntry) char dirsep; struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + unsigned seq; if (direntry == NULL) return NULL; /* not much we can do if dentry is freed and @@ -68,22 +69,29 @@ build_path_from_dentry(struct dentry *direntry) dfsplen = 0; cifs_bp_rename_retry: namelen = dfsplen; + seq = read_seqbegin(&rename_lock); + rcu_read_lock(); for (temp = direntry; !IS_ROOT(temp);) { namelen += (1 + temp->d_name.len); temp = temp->d_parent; if (temp == NULL) { cERROR(1, "corrupt dentry"); + rcu_read_unlock(); return NULL; } } + rcu_read_unlock(); full_path = kmalloc(namelen+1, GFP_KERNEL); if (full_path == NULL) return full_path; full_path[namelen] = 0; /* trailing null */ + rcu_read_lock(); for (temp = direntry; !IS_ROOT(temp);) { + spin_lock(&temp->d_lock); namelen -= 1 + temp->d_name.len; if (namelen < 0) { + spin_unlock(&temp->d_lock); break; } else { full_path[namelen] = dirsep; @@ -91,14 +99,17 @@ cifs_bp_rename_retry: temp->d_name.len); cFYI(0, "name: %s", full_path + namelen); } + spin_unlock(&temp->d_lock); temp = temp->d_parent; if (temp == NULL) { cERROR(1, "corrupt dentry"); + rcu_read_unlock(); kfree(full_path); return NULL; } } - if (namelen != dfsplen) { + rcu_read_unlock(); + if (namelen != dfsplen || read_seqretry(&rename_lock, seq)) { cERROR(1, "did not end path lookup where expected namelen is %d", namelen); /* presumably this is only possible if racing with a rename diff --git a/fs/cifs/file.c b/fs/cifs/file.c index bb71471..a9b4a24 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1737,7 +1737,7 @@ cifs_iovec_read(struct file *file, const struct iovec *iov, io_parms.pid = pid; io_parms.tcon = pTcon; io_parms.offset = *poffset; - io_parms.length = len; + io_parms.length = cur_len; rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &read_data, &buf_type); pSMBr = (struct smb_com_read_rsp *)read_data; diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 8166966..42e5363 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -92,6 +92,7 @@ static void cifs_fscache_disable_inode_cookie(struct inode *inode) if (cifsi->fscache) { cFYI(1, "%s: (0x%p)", __func__, cifsi->fscache); + fscache_uncache_all_inode_pages(cifsi->fscache, inode); fscache_relinquish_cookie(cifsi->fscache, 1); cifsi->fscache = NULL; } diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 3892ab8..d3e6196 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -428,8 +428,7 @@ static void build_ntlmssp_negotiate_blob(unsigned char *pbuffer, (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { flags |= NTLMSSP_NEGOTIATE_SIGN; if (!ses->server->session_estab) - flags |= NTLMSSP_NEGOTIATE_KEY_XCH | - NTLMSSP_NEGOTIATE_EXTENDED_SEC; + flags |= NTLMSSP_NEGOTIATE_KEY_XCH; } sec_blob->NegotiateFlags = cpu_to_le32(flags); @@ -465,10 +464,11 @@ static int build_ntlmssp_auth_blob(unsigned char *pbuffer, NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC; if (ses->server->sec_mode & - (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) + (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) { flags |= NTLMSSP_NEGOTIATE_SIGN; - if (ses->server->sec_mode & SECMODE_SIGN_REQUIRED) - flags |= NTLMSSP_NEGOTIATE_ALWAYS_SIGN; + if (!ses->server->session_estab) + flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + } tmp = pbuffer + sizeof(AUTHENTICATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index 1525d5e..1c5b770 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -90,12 +90,10 @@ smbhash(unsigned char *out, const unsigned char *in, unsigned char *key) sg_init_one(&sgout, out, 8); rc = crypto_blkcipher_encrypt(&desc, &sgout, &sgin, 8); - if (rc) { + if (rc) cERROR(1, "could not encrypt crypt key rc: %d\n", rc); - crypto_free_blkcipher(tfm_des); - goto smbhash_err; - } + crypto_free_blkcipher(tfm_des); smbhash_err: return rc; } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index e141939..739fb59 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -37,7 +37,7 @@ static DEFINE_MUTEX(read_mutex); /* These macros may change in future, to provide better st_ino semantics. */ #define OFFSET(x) ((x)->i_ino) -static unsigned long cramino(struct cramfs_inode *cino, unsigned int offset) +static unsigned long cramino(const struct cramfs_inode *cino, unsigned int offset) { if (!cino->offset) return offset + 1; @@ -61,7 +61,7 @@ static unsigned long cramino(struct cramfs_inode *cino, unsigned int offset) } static struct inode *get_cramfs_inode(struct super_block *sb, - struct cramfs_inode *cramfs_inode, unsigned int offset) + const struct cramfs_inode *cramfs_inode, unsigned int offset) { struct inode *inode; static struct timespec zerotime; @@ -317,7 +317,7 @@ static int cramfs_fill_super(struct super_block *sb, void *data, int silent) /* Set it all up.. */ sb->s_op = &cramfs_ops; root = get_cramfs_inode(sb, &super.root, 0); - if (!root) + if (IS_ERR(root)) goto out; sb->s_root = d_alloc_root(root); if (!sb->s_root) { @@ -423,6 +423,7 @@ static int cramfs_readdir(struct file *filp, void *dirent, filldir_t filldir) static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { unsigned int offset = 0; + struct inode *inode = NULL; int sorted; mutex_lock(&read_mutex); @@ -449,8 +450,8 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s for (;;) { if (!namelen) { - mutex_unlock(&read_mutex); - return ERR_PTR(-EIO); + inode = ERR_PTR(-EIO); + goto out; } if (name[namelen-1]) break; @@ -462,17 +463,18 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s if (retval > 0) continue; if (!retval) { - struct cramfs_inode entry = *de; - mutex_unlock(&read_mutex); - d_add(dentry, get_cramfs_inode(dir->i_sb, &entry, dir_off)); - return NULL; + inode = get_cramfs_inode(dir->i_sb, de, dir_off); + break; } /* else (retval < 0) */ if (sorted) break; } +out: mutex_unlock(&read_mutex); - d_add(dentry, NULL); + if (IS_ERR(inode)) + return ERR_CAST(inode); + d_add(dentry, inode); return NULL; } diff --git a/fs/dcache.c b/fs/dcache.c index 37f72ee..fbdcbca 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1813,8 +1813,6 @@ seqretry: tname = dentry->d_name.name; i = dentry->d_inode; prefetch(tname); - if (i) - prefetch(i); /* * This seqcount check is required to ensure name and * len are loaded atomically, so as not to walk off the @@ -2213,14 +2211,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry, * The hash value has to match the hash queue that the dentry is on.. */ /* - * d_move - move a dentry + * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative - * dcache entries should not be moved in this way. + * dcache entries should not be moved in this way. Caller hold + * rename_lock. */ -void d_move(struct dentry * dentry, struct dentry * target) +static void __d_move(struct dentry * dentry, struct dentry * target) { if (!dentry->d_inode) printk(KERN_WARNING "VFS: moving negative dcache entry\n"); @@ -2228,8 +2227,6 @@ void d_move(struct dentry * dentry, struct dentry * target) BUG_ON(d_ancestor(dentry, target)); BUG_ON(d_ancestor(target, dentry)); - write_seqlock(&rename_lock); - dentry_lock_for_move(dentry, target); write_seqcount_begin(&dentry->d_seq); @@ -2275,6 +2272,20 @@ void d_move(struct dentry * dentry, struct dentry * target) spin_unlock(&target->d_lock); fsnotify_d_move(dentry); spin_unlock(&dentry->d_lock); +} + +/* + * d_move - move a dentry + * @dentry: entry to move + * @target: new dentry + * + * Update the dcache to reflect the move of a file name. Negative + * dcache entries should not be moved in this way. + */ +void d_move(struct dentry *dentry, struct dentry *target) +{ + write_seqlock(&rename_lock); + __d_move(dentry, target); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); @@ -2302,7 +2313,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding - * dentry->d_parent->d_inode->i_mutex and the inode->i_lock + * dentry->d_parent->d_inode->i_mutex, inode->i_lock and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... @@ -2317,11 +2328,6 @@ static struct dentry *__d_unalias(struct inode *inode, if (alias->d_parent == dentry->d_parent) goto out_unalias; - /* Check for loops */ - ret = ERR_PTR(-ELOOP); - if (d_ancestor(alias, dentry)) - goto out_err; - /* See lock_rename() */ ret = ERR_PTR(-EBUSY); if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) @@ -2331,7 +2337,7 @@ static struct dentry *__d_unalias(struct inode *inode, goto out_err; m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: - d_move(alias, dentry); + __d_move(alias, dentry); ret = alias; out_err: spin_unlock(&inode->i_lock); @@ -2416,15 +2422,24 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode) alias = __d_find_alias(inode, 0); if (alias) { actual = alias; - /* Is this an anonymous mountpoint that we could splice - * into our tree? */ - if (IS_ROOT(alias)) { + write_seqlock(&rename_lock); + + if (d_ancestor(alias, dentry)) { + /* Check for loops */ + actual = ERR_PTR(-ELOOP); + } else if (IS_ROOT(alias)) { + /* Is this an anonymous mountpoint that we + * could splice into our tree? */ __d_materialise_dentry(dentry, alias); + write_sequnlock(&rename_lock); __d_drop(alias); goto found; + } else { + /* Nope, but we must(!) avoid directory + * aliasing */ + actual = __d_unalias(inode, dentry, alias); } - /* Nope, but we must(!) avoid directory aliasing */ - actual = __d_unalias(inode, dentry, alias); + write_sequnlock(&rename_lock); if (IS_ERR(actual)) dput(alias); goto out_nolock; diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index abc49f2..90e5997 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -14,17 +14,9 @@ #include "dlm_internal.h" #include "lock.h" #include "user.h" -#include "ast.h" - -#define WAKE_ASTS 0 - -static uint64_t ast_seq_count; -static struct list_head ast_queue; -static spinlock_t ast_queue_lock; -static struct task_struct * astd_task; -static unsigned long astd_wakeflags; -static struct mutex astd_running; +static uint64_t dlm_cb_seq; +static spinlock_t dlm_cb_seq_spin; static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb) { @@ -57,21 +49,13 @@ static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb) } } -void dlm_del_ast(struct dlm_lkb *lkb) -{ - spin_lock(&ast_queue_lock); - if (!list_empty(&lkb->lkb_astqueue)) - list_del_init(&lkb->lkb_astqueue); - spin_unlock(&ast_queue_lock); -} - int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, uint32_t sbflags, uint64_t seq) { struct dlm_ls *ls = lkb->lkb_resource->res_ls; uint64_t prev_seq; int prev_mode; - int i; + int i, rv; for (i = 0; i < DLM_CALLBACKS_SIZE; i++) { if (lkb->lkb_callbacks[i].seq) @@ -100,7 +84,8 @@ int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, mode, (unsigned long long)prev_seq, prev_mode); - return 0; + rv = 0; + goto out; } } @@ -109,6 +94,7 @@ int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, lkb->lkb_callbacks[i].mode = mode; lkb->lkb_callbacks[i].sb_status = status; lkb->lkb_callbacks[i].sb_flags = (sbflags & 0x000000FF); + rv = 0; break; } @@ -117,21 +103,24 @@ int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, lkb->lkb_id, (unsigned long long)seq, flags, mode, status, sbflags); dlm_dump_lkb_callbacks(lkb); - return -1; + rv = -1; + goto out; } - - return 0; + out: + return rv; } int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_callback *cb, int *resid) { - int i; + int i, rv; *resid = 0; - if (!lkb->lkb_callbacks[0].seq) - return -ENOENT; + if (!lkb->lkb_callbacks[0].seq) { + rv = -ENOENT; + goto out; + } /* oldest undelivered cb is callbacks[0] */ @@ -163,7 +152,8 @@ int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb, cb->mode, (unsigned long long)lkb->lkb_last_cast.seq, lkb->lkb_last_cast.mode); - return 0; + rv = 0; + goto out; } } @@ -176,171 +166,150 @@ int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb, memcpy(&lkb->lkb_last_bast, cb, sizeof(struct dlm_callback)); lkb->lkb_last_bast_time = ktime_get(); } - - return 0; + rv = 0; + out: + return rv; } -void dlm_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, - uint32_t sbflags) +void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, + uint32_t sbflags) { - uint64_t seq; + struct dlm_ls *ls = lkb->lkb_resource->res_ls; + uint64_t new_seq, prev_seq; int rv; - spin_lock(&ast_queue_lock); - - seq = ++ast_seq_count; + spin_lock(&dlm_cb_seq_spin); + new_seq = ++dlm_cb_seq; + spin_unlock(&dlm_cb_seq_spin); if (lkb->lkb_flags & DLM_IFL_USER) { - spin_unlock(&ast_queue_lock); - dlm_user_add_ast(lkb, flags, mode, status, sbflags, seq); + dlm_user_add_ast(lkb, flags, mode, status, sbflags, new_seq); return; } - rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, seq); - if (rv < 0) { - spin_unlock(&ast_queue_lock); - return; - } + mutex_lock(&lkb->lkb_cb_mutex); + prev_seq = lkb->lkb_callbacks[0].seq; - if (list_empty(&lkb->lkb_astqueue)) { + rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, new_seq); + if (rv < 0) + goto out; + + if (!prev_seq) { kref_get(&lkb->lkb_ref); - list_add_tail(&lkb->lkb_astqueue, &ast_queue); - } - spin_unlock(&ast_queue_lock); - set_bit(WAKE_ASTS, &astd_wakeflags); - wake_up_process(astd_task); + if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) { + mutex_lock(&ls->ls_cb_mutex); + list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay); + mutex_unlock(&ls->ls_cb_mutex); + } else { + queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); + } + } + out: + mutex_unlock(&lkb->lkb_cb_mutex); } -static void process_asts(void) +void dlm_callback_work(struct work_struct *work) { - struct dlm_ls *ls = NULL; - struct dlm_rsb *r = NULL; - struct dlm_lkb *lkb; + struct dlm_lkb *lkb = container_of(work, struct dlm_lkb, lkb_cb_work); + struct dlm_ls *ls = lkb->lkb_resource->res_ls; void (*castfn) (void *astparam); void (*bastfn) (void *astparam, int mode); struct dlm_callback callbacks[DLM_CALLBACKS_SIZE]; int i, rv, resid; -repeat: - spin_lock(&ast_queue_lock); - list_for_each_entry(lkb, &ast_queue, lkb_astqueue) { - r = lkb->lkb_resource; - ls = r->res_ls; + memset(&callbacks, 0, sizeof(callbacks)); - if (dlm_locking_stopped(ls)) - continue; - - /* we remove from astqueue list and remove everything in - lkb_callbacks before releasing the spinlock so empty - lkb_astqueue is always consistent with empty lkb_callbacks */ - - list_del_init(&lkb->lkb_astqueue); - - castfn = lkb->lkb_astfn; - bastfn = lkb->lkb_bastfn; + mutex_lock(&lkb->lkb_cb_mutex); + if (!lkb->lkb_callbacks[0].seq) { + /* no callback work exists, shouldn't happen */ + log_error(ls, "dlm_callback_work %x no work", lkb->lkb_id); + dlm_print_lkb(lkb); + dlm_dump_lkb_callbacks(lkb); + } - memset(&callbacks, 0, sizeof(callbacks)); + for (i = 0; i < DLM_CALLBACKS_SIZE; i++) { + rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid); + if (rv < 0) + break; + } - for (i = 0; i < DLM_CALLBACKS_SIZE; i++) { - rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid); - if (rv < 0) - break; - } - spin_unlock(&ast_queue_lock); + if (resid) { + /* cbs remain, loop should have removed all, shouldn't happen */ + log_error(ls, "dlm_callback_work %x resid %d", lkb->lkb_id, + resid); + dlm_print_lkb(lkb); + dlm_dump_lkb_callbacks(lkb); + } + mutex_unlock(&lkb->lkb_cb_mutex); - if (resid) { - /* shouldn't happen, for loop should have removed all */ - log_error(ls, "callback resid %d lkb %x", - resid, lkb->lkb_id); - } + castfn = lkb->lkb_astfn; + bastfn = lkb->lkb_bastfn; - for (i = 0; i < DLM_CALLBACKS_SIZE; i++) { - if (!callbacks[i].seq) - break; - if (callbacks[i].flags & DLM_CB_SKIP) { - continue; - } else if (callbacks[i].flags & DLM_CB_BAST) { - bastfn(lkb->lkb_astparam, callbacks[i].mode); - } else if (callbacks[i].flags & DLM_CB_CAST) { - lkb->lkb_lksb->sb_status = callbacks[i].sb_status; - lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags; - castfn(lkb->lkb_astparam); - } + for (i = 0; i < DLM_CALLBACKS_SIZE; i++) { + if (!callbacks[i].seq) + break; + if (callbacks[i].flags & DLM_CB_SKIP) { + continue; + } else if (callbacks[i].flags & DLM_CB_BAST) { + bastfn(lkb->lkb_astparam, callbacks[i].mode); + } else if (callbacks[i].flags & DLM_CB_CAST) { + lkb->lkb_lksb->sb_status = callbacks[i].sb_status; + lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags; + castfn(lkb->lkb_astparam); } - - /* removes ref for ast_queue, may cause lkb to be freed */ - dlm_put_lkb(lkb); - - cond_resched(); - goto repeat; } - spin_unlock(&ast_queue_lock); -} - -static inline int no_asts(void) -{ - int ret; - spin_lock(&ast_queue_lock); - ret = list_empty(&ast_queue); - spin_unlock(&ast_queue_lock); - return ret; + /* undo kref_get from dlm_add_callback, may cause lkb to be freed */ + dlm_put_lkb(lkb); } -static int dlm_astd(void *data) +int dlm_callback_start(struct dlm_ls *ls) { - while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - if (!test_bit(WAKE_ASTS, &astd_wakeflags)) - schedule(); - set_current_state(TASK_RUNNING); - - mutex_lock(&astd_running); - if (test_and_clear_bit(WAKE_ASTS, &astd_wakeflags)) - process_asts(); - mutex_unlock(&astd_running); + ls->ls_callback_wq = alloc_workqueue("dlm_callback", + WQ_UNBOUND | + WQ_MEM_RECLAIM | + WQ_NON_REENTRANT, + 0); + if (!ls->ls_callback_wq) { + log_print("can't start dlm_callback workqueue"); + return -ENOMEM; } return 0; } -void dlm_astd_wake(void) +void dlm_callback_stop(struct dlm_ls *ls) { - if (!no_asts()) { - set_bit(WAKE_ASTS, &astd_wakeflags); - wake_up_process(astd_task); - } + if (ls->ls_callback_wq) + destroy_workqueue(ls->ls_callback_wq); } -int dlm_astd_start(void) +void dlm_callback_suspend(struct dlm_ls *ls) { - struct task_struct *p; - int error = 0; - - INIT_LIST_HEAD(&ast_queue); - spin_lock_init(&ast_queue_lock); - mutex_init(&astd_running); - - p = kthread_run(dlm_astd, NULL, "dlm_astd"); - if (IS_ERR(p)) - error = PTR_ERR(p); - else - astd_task = p; - return error; -} + set_bit(LSFL_CB_DELAY, &ls->ls_flags); -void dlm_astd_stop(void) -{ - kthread_stop(astd_task); + if (ls->ls_callback_wq) + flush_workqueue(ls->ls_callback_wq); } -void dlm_astd_suspend(void) +void dlm_callback_resume(struct dlm_ls *ls) { - mutex_lock(&astd_running); -} + struct dlm_lkb *lkb, *safe; + int count = 0; -void dlm_astd_resume(void) -{ - mutex_unlock(&astd_running); + clear_bit(LSFL_CB_DELAY, &ls->ls_flags); + + if (!ls->ls_callback_wq) + return; + + mutex_lock(&ls->ls_cb_mutex); + list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) { + list_del_init(&lkb->lkb_cb_list); + queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); + count++; + } + mutex_unlock(&ls->ls_cb_mutex); + + log_debug(ls, "dlm_callback_resume %d", count); } diff --git a/fs/dlm/ast.h b/fs/dlm/ast.h index 8aa89c9..757b551 100644 --- a/fs/dlm/ast.h +++ b/fs/dlm/ast.h @@ -18,14 +18,15 @@ int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, uint32_t sbflags, uint64_t seq); int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb, struct dlm_callback *cb, int *resid); -void dlm_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, - uint32_t sbflags); +void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status, + uint32_t sbflags); -void dlm_astd_wake(void); -int dlm_astd_start(void); -void dlm_astd_stop(void); -void dlm_astd_suspend(void); -void dlm_astd_resume(void); +void dlm_callback_work(struct work_struct *work); +int dlm_callback_start(struct dlm_ls *ls); +void dlm_callback_stop(struct dlm_ls *ls); +void dlm_callback_suspend(struct dlm_ls *ls); +void dlm_callback_resume(struct dlm_ls *ls); #endif + diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 9b026ea..6cf72fc 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -28,7 +28,8 @@ * /config/dlm/<cluster>/spaces/<space>/nodes/<node>/weight * /config/dlm/<cluster>/comms/<comm>/nodeid * /config/dlm/<cluster>/comms/<comm>/local - * /config/dlm/<cluster>/comms/<comm>/addr + * /config/dlm/<cluster>/comms/<comm>/addr (write only) + * /config/dlm/<cluster>/comms/<comm>/addr_list (read only) * The <cluster> level is useless, but I haven't figured out how to avoid it. */ @@ -80,6 +81,7 @@ static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf, size_t len); static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len); +static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf); static ssize_t node_nodeid_read(struct dlm_node *nd, char *buf); static ssize_t node_nodeid_write(struct dlm_node *nd, const char *buf, size_t len); @@ -92,7 +94,6 @@ struct dlm_cluster { unsigned int cl_tcp_port; unsigned int cl_buffer_size; unsigned int cl_rsbtbl_size; - unsigned int cl_lkbtbl_size; unsigned int cl_dirtbl_size; unsigned int cl_recover_timer; unsigned int cl_toss_secs; @@ -101,13 +102,13 @@ struct dlm_cluster { unsigned int cl_protocol; unsigned int cl_timewarn_cs; unsigned int cl_waitwarn_us; + unsigned int cl_new_rsb_count; }; enum { CLUSTER_ATTR_TCP_PORT = 0, CLUSTER_ATTR_BUFFER_SIZE, CLUSTER_ATTR_RSBTBL_SIZE, - CLUSTER_ATTR_LKBTBL_SIZE, CLUSTER_ATTR_DIRTBL_SIZE, CLUSTER_ATTR_RECOVER_TIMER, CLUSTER_ATTR_TOSS_SECS, @@ -116,6 +117,7 @@ enum { CLUSTER_ATTR_PROTOCOL, CLUSTER_ATTR_TIMEWARN_CS, CLUSTER_ATTR_WAITWARN_US, + CLUSTER_ATTR_NEW_RSB_COUNT, }; struct cluster_attribute { @@ -160,7 +162,6 @@ __CONFIGFS_ATTR(name, 0644, name##_read, name##_write) CLUSTER_ATTR(tcp_port, 1); CLUSTER_ATTR(buffer_size, 1); CLUSTER_ATTR(rsbtbl_size, 1); -CLUSTER_ATTR(lkbtbl_size, 1); CLUSTER_ATTR(dirtbl_size, 1); CLUSTER_ATTR(recover_timer, 1); CLUSTER_ATTR(toss_secs, 1); @@ -169,12 +170,12 @@ CLUSTER_ATTR(log_debug, 0); CLUSTER_ATTR(protocol, 0); CLUSTER_ATTR(timewarn_cs, 1); CLUSTER_ATTR(waitwarn_us, 0); +CLUSTER_ATTR(new_rsb_count, 0); static struct configfs_attribute *cluster_attrs[] = { [CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr, [CLUSTER_ATTR_BUFFER_SIZE] = &cluster_attr_buffer_size.attr, [CLUSTER_ATTR_RSBTBL_SIZE] = &cluster_attr_rsbtbl_size.attr, - [CLUSTER_ATTR_LKBTBL_SIZE] = &cluster_attr_lkbtbl_size.attr, [CLUSTER_ATTR_DIRTBL_SIZE] = &cluster_attr_dirtbl_size.attr, [CLUSTER_ATTR_RECOVER_TIMER] = &cluster_attr_recover_timer.attr, [CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs.attr, @@ -183,6 +184,7 @@ static struct configfs_attribute *cluster_attrs[] = { [CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr, [CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs.attr, [CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us.attr, + [CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count.attr, NULL, }; @@ -190,6 +192,7 @@ enum { COMM_ATTR_NODEID = 0, COMM_ATTR_LOCAL, COMM_ATTR_ADDR, + COMM_ATTR_ADDR_LIST, }; struct comm_attribute { @@ -217,14 +220,22 @@ static struct comm_attribute comm_attr_local = { static struct comm_attribute comm_attr_addr = { .attr = { .ca_owner = THIS_MODULE, .ca_name = "addr", - .ca_mode = S_IRUGO | S_IWUSR }, + .ca_mode = S_IWUSR }, .store = comm_addr_write, }; +static struct comm_attribute comm_attr_addr_list = { + .attr = { .ca_owner = THIS_MODULE, + .ca_name = "addr_list", + .ca_mode = S_IRUGO }, + .show = comm_addr_list_read, +}; + static struct configfs_attribute *comm_attrs[] = { [COMM_ATTR_NODEID] = &comm_attr_nodeid.attr, [COMM_ATTR_LOCAL] = &comm_attr_local.attr, [COMM_ATTR_ADDR] = &comm_attr_addr.attr, + [COMM_ATTR_ADDR_LIST] = &comm_attr_addr_list.attr, NULL, }; @@ -435,7 +446,6 @@ static struct config_group *make_cluster(struct config_group *g, cl->cl_tcp_port = dlm_config.ci_tcp_port; cl->cl_buffer_size = dlm_config.ci_buffer_size; cl->cl_rsbtbl_size = dlm_config.ci_rsbtbl_size; - cl->cl_lkbtbl_size = dlm_config.ci_lkbtbl_size; cl->cl_dirtbl_size = dlm_config.ci_dirtbl_size; cl->cl_recover_timer = dlm_config.ci_recover_timer; cl->cl_toss_secs = dlm_config.ci_toss_secs; @@ -444,6 +454,7 @@ static struct config_group *make_cluster(struct config_group *g, cl->cl_protocol = dlm_config.ci_protocol; cl->cl_timewarn_cs = dlm_config.ci_timewarn_cs; cl->cl_waitwarn_us = dlm_config.ci_waitwarn_us; + cl->cl_new_rsb_count = dlm_config.ci_new_rsb_count; space_list = &sps->ss_group; comm_list = &cms->cs_group; @@ -720,6 +731,50 @@ static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len) return len; } +static ssize_t comm_addr_list_read(struct dlm_comm *cm, char *buf) +{ + ssize_t s; + ssize_t allowance; + int i; + struct sockaddr_storage *addr; + struct sockaddr_in *addr_in; + struct sockaddr_in6 *addr_in6; + + /* Taken from ip6_addr_string() defined in lib/vsprintf.c */ + char buf0[sizeof("AF_INET6 xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255\n")]; + + + /* Derived from SIMPLE_ATTR_SIZE of fs/configfs/file.c */ + allowance = 4096; + buf[0] = '\0'; + + for (i = 0; i < cm->addr_count; i++) { + addr = cm->addr[i]; + + switch(addr->ss_family) { + case AF_INET: + addr_in = (struct sockaddr_in *)addr; + s = sprintf(buf0, "AF_INET %pI4\n", &addr_in->sin_addr.s_addr); + break; + case AF_INET6: + addr_in6 = (struct sockaddr_in6 *)addr; + s = sprintf(buf0, "AF_INET6 %pI6\n", &addr_in6->sin6_addr); + break; + default: + s = sprintf(buf0, "%s\n", "<UNKNOWN>"); + break; + } + allowance -= s; + if (allowance >= 0) + strcat(buf, buf0); + else { + allowance += s; + break; + } + } + return 4096 - allowance; +} + static ssize_t show_node(struct config_item *i, struct configfs_attribute *a, char *buf) { @@ -983,7 +1038,6 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num) #define DEFAULT_TCP_PORT 21064 #define DEFAULT_BUFFER_SIZE 4096 #define DEFAULT_RSBTBL_SIZE 1024 -#define DEFAULT_LKBTBL_SIZE 1024 #define DEFAULT_DIRTBL_SIZE 1024 #define DEFAULT_RECOVER_TIMER 5 #define DEFAULT_TOSS_SECS 10 @@ -992,12 +1046,12 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num) #define DEFAULT_PROTOCOL 0 #define DEFAULT_TIMEWARN_CS 500 /* 5 sec = 500 centiseconds */ #define DEFAULT_WAITWARN_US 0 +#define DEFAULT_NEW_RSB_COUNT 128 struct dlm_config_info dlm_config = { .ci_tcp_port = DEFAULT_TCP_PORT, .ci_buffer_size = DEFAULT_BUFFER_SIZE, .ci_rsbtbl_size = DEFAULT_RSBTBL_SIZE, - .ci_lkbtbl_size = DEFAULT_LKBTBL_SIZE, .ci_dirtbl_size = DEFAULT_DIRTBL_SIZE, .ci_recover_timer = DEFAULT_RECOVER_TIMER, .ci_toss_secs = DEFAULT_TOSS_SECS, @@ -1005,6 +1059,7 @@ struct dlm_config_info dlm_config = { .ci_log_debug = DEFAULT_LOG_DEBUG, .ci_protocol = DEFAULT_PROTOCOL, .ci_timewarn_cs = DEFAULT_TIMEWARN_CS, - .ci_waitwarn_us = DEFAULT_WAITWARN_US + .ci_waitwarn_us = DEFAULT_WAITWARN_US, + .ci_new_rsb_count = DEFAULT_NEW_RSB_COUNT }; diff --git a/fs/dlm/config.h b/fs/dlm/config.h index dd0ce24..3099d0d 100644 --- a/fs/dlm/config.h +++ b/fs/dlm/config.h @@ -20,7 +20,6 @@ struct dlm_config_info { int ci_tcp_port; int ci_buffer_size; int ci_rsbtbl_size; - int ci_lkbtbl_size; int ci_dirtbl_size; int ci_recover_timer; int ci_toss_secs; @@ -29,6 +28,7 @@ struct dlm_config_info { int ci_protocol; int ci_timewarn_cs; int ci_waitwarn_us; + int ci_new_rsb_count; }; extern struct dlm_config_info dlm_config; diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 0262451..fe2860c 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -37,6 +37,7 @@ #include <linux/jhash.h> #include <linux/miscdevice.h> #include <linux/mutex.h> +#include <linux/idr.h> #include <asm/uaccess.h> #include <linux/dlm.h> @@ -52,7 +53,6 @@ struct dlm_ls; struct dlm_lkb; struct dlm_rsb; struct dlm_member; -struct dlm_lkbtable; struct dlm_rsbtable; struct dlm_dirtable; struct dlm_direntry; @@ -108,11 +108,6 @@ struct dlm_rsbtable { spinlock_t lock; }; -struct dlm_lkbtable { - struct list_head list; - rwlock_t lock; - uint16_t counter; -}; /* * Lockspace member (per node in a ls) @@ -248,17 +243,18 @@ struct dlm_lkb { int8_t lkb_wait_count; int lkb_wait_nodeid; /* for debugging */ - struct list_head lkb_idtbl_list; /* lockspace lkbtbl */ struct list_head lkb_statequeue; /* rsb g/c/w list */ struct list_head lkb_rsb_lookup; /* waiting for rsb lookup */ struct list_head lkb_wait_reply; /* waiting for remote reply */ - struct list_head lkb_astqueue; /* need ast to be sent */ struct list_head lkb_ownqueue; /* list of locks for a process */ struct list_head lkb_time_list; ktime_t lkb_timestamp; ktime_t lkb_wait_time; unsigned long lkb_timeout_cs; + struct mutex lkb_cb_mutex; + struct work_struct lkb_cb_work; + struct list_head lkb_cb_list; /* for ls_cb_delay or proc->asts */ struct dlm_callback lkb_callbacks[DLM_CALLBACKS_SIZE]; struct dlm_callback lkb_last_cast; struct dlm_callback lkb_last_bast; @@ -299,7 +295,7 @@ struct dlm_rsb { int res_recover_locks_count; char *res_lvbptr; - char res_name[1]; + char res_name[DLM_RESNAME_MAXLEN+1]; }; /* find_rsb() flags */ @@ -465,12 +461,12 @@ struct dlm_ls { unsigned long ls_scan_time; struct kobject ls_kobj; + struct idr ls_lkbidr; + spinlock_t ls_lkbidr_spin; + struct dlm_rsbtable *ls_rsbtbl; uint32_t ls_rsbtbl_size; - struct dlm_lkbtable *ls_lkbtbl; - uint32_t ls_lkbtbl_size; - struct dlm_dirtable *ls_dirtbl; uint32_t ls_dirtbl_size; @@ -483,6 +479,10 @@ struct dlm_ls { struct mutex ls_timeout_mutex; struct list_head ls_timeout; + spinlock_t ls_new_rsb_spin; + int ls_new_rsb_count; + struct list_head ls_new_rsb; /* new rsb structs */ + struct list_head ls_nodes; /* current nodes in ls */ struct list_head ls_nodes_gone; /* dead node list, recovery */ int ls_num_nodes; /* number of nodes in ls */ @@ -506,8 +506,12 @@ struct dlm_ls { struct miscdevice ls_device; + struct workqueue_struct *ls_callback_wq; + /* recovery related */ + struct mutex ls_cb_mutex; + struct list_head ls_cb_delay; /* save for queue_work later */ struct timer_list ls_timer; struct task_struct *ls_recoverd_task; struct mutex ls_recoverd_active; @@ -544,6 +548,7 @@ struct dlm_ls { #define LSFL_RCOM_WAIT 4 #define LSFL_UEVENT_WAIT 5 #define LSFL_TIMEWARN 6 +#define LSFL_CB_DELAY 7 /* much of this is just saving user space pointers associated with the lock that we pass back to the user lib with an ast */ diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index f71d0b5..83b5e32 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -305,7 +305,7 @@ static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv) rv = -EDEADLK; } - dlm_add_ast(lkb, DLM_CB_CAST, lkb->lkb_grmode, rv, lkb->lkb_sbflags); + dlm_add_cb(lkb, DLM_CB_CAST, lkb->lkb_grmode, rv, lkb->lkb_sbflags); } static inline void queue_cast_overlap(struct dlm_rsb *r, struct dlm_lkb *lkb) @@ -319,7 +319,7 @@ static void queue_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rqmode) if (is_master_copy(lkb)) { send_bast(r, lkb, rqmode); } else { - dlm_add_ast(lkb, DLM_CB_BAST, rqmode, 0, 0); + dlm_add_cb(lkb, DLM_CB_BAST, rqmode, 0, 0); } } @@ -327,19 +327,68 @@ static void queue_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rqmode) * Basic operations on rsb's and lkb's */ -static struct dlm_rsb *create_rsb(struct dlm_ls *ls, char *name, int len) +static int pre_rsb_struct(struct dlm_ls *ls) +{ + struct dlm_rsb *r1, *r2; + int count = 0; + + spin_lock(&ls->ls_new_rsb_spin); + if (ls->ls_new_rsb_count > dlm_config.ci_new_rsb_count / 2) { + spin_unlock(&ls->ls_new_rsb_spin); + return 0; + } + spin_unlock(&ls->ls_new_rsb_spin); + + r1 = dlm_allocate_rsb(ls); + r2 = dlm_allocate_rsb(ls); + + spin_lock(&ls->ls_new_rsb_spin); + if (r1) { + list_add(&r1->res_hashchain, &ls->ls_new_rsb); + ls->ls_new_rsb_count++; + } + if (r2) { + list_add(&r2->res_hashchain, &ls->ls_new_rsb); + ls->ls_new_rsb_count++; + } + count = ls->ls_new_rsb_count; + spin_unlock(&ls->ls_new_rsb_spin); + + if (!count) + return -ENOMEM; + return 0; +} + +/* If ls->ls_new_rsb is empty, return -EAGAIN, so the caller can + unlock any spinlocks, go back and call pre_rsb_struct again. + Otherwise, take an rsb off the list and return it. */ + +static int get_rsb_struct(struct dlm_ls *ls, char *name, int len, + struct dlm_rsb **r_ret) { struct dlm_rsb *r; + int count; - r = dlm_allocate_rsb(ls, len); - if (!r) - return NULL; + spin_lock(&ls->ls_new_rsb_spin); + if (list_empty(&ls->ls_new_rsb)) { + count = ls->ls_new_rsb_count; + spin_unlock(&ls->ls_new_rsb_spin); + log_debug(ls, "find_rsb retry %d %d %s", + count, dlm_config.ci_new_rsb_count, name); + return -EAGAIN; + } + + r = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb, res_hashchain); + list_del(&r->res_hashchain); + ls->ls_new_rsb_count--; + spin_unlock(&ls->ls_new_rsb_spin); r->res_ls = ls; r->res_length = len; memcpy(r->res_name, name, len); mutex_init(&r->res_mutex); + INIT_LIST_HEAD(&r->res_hashchain); INIT_LIST_HEAD(&r->res_lookup); INIT_LIST_HEAD(&r->res_grantqueue); INIT_LIST_HEAD(&r->res_convertqueue); @@ -347,7 +396,8 @@ static struct dlm_rsb *create_rsb(struct dlm_ls *ls, char *name, int len) INIT_LIST_HEAD(&r->res_root_list); INIT_LIST_HEAD(&r->res_recover_list); - return r; + *r_ret = r; + return 0; } static int search_rsb_list(struct list_head *head, char *name, int len, @@ -405,16 +455,6 @@ static int _search_rsb(struct dlm_ls *ls, char *name, int len, int b, return error; } -static int search_rsb(struct dlm_ls *ls, char *name, int len, int b, - unsigned int flags, struct dlm_rsb **r_ret) -{ - int error; - spin_lock(&ls->ls_rsbtbl[b].lock); - error = _search_rsb(ls, name, len, b, flags, r_ret); - spin_unlock(&ls->ls_rsbtbl[b].lock); - return error; -} - /* * Find rsb in rsbtbl and potentially create/add one * @@ -432,35 +472,48 @@ static int search_rsb(struct dlm_ls *ls, char *name, int len, int b, static int find_rsb(struct dlm_ls *ls, char *name, int namelen, unsigned int flags, struct dlm_rsb **r_ret) { - struct dlm_rsb *r = NULL, *tmp; + struct dlm_rsb *r = NULL; uint32_t hash, bucket; - int error = -EINVAL; + int error; - if (namelen > DLM_RESNAME_MAXLEN) + if (namelen > DLM_RESNAME_MAXLEN) { + error = -EINVAL; goto out; + } if (dlm_no_directory(ls)) flags |= R_CREATE; - error = 0; hash = jhash(name, namelen, 0); bucket = hash & (ls->ls_rsbtbl_size - 1); - error = search_rsb(ls, name, namelen, bucket, flags, &r); + retry: + if (flags & R_CREATE) { + error = pre_rsb_struct(ls); + if (error < 0) + goto out; + } + + spin_lock(&ls->ls_rsbtbl[bucket].lock); + + error = _search_rsb(ls, name, namelen, bucket, flags, &r); if (!error) - goto out; + goto out_unlock; if (error == -EBADR && !(flags & R_CREATE)) - goto out; + goto out_unlock; /* the rsb was found but wasn't a master copy */ if (error == -ENOTBLK) - goto out; + goto out_unlock; - error = -ENOMEM; - r = create_rsb(ls, name, namelen); - if (!r) - goto out; + error = get_rsb_struct(ls, name, namelen, &r); + if (error == -EAGAIN) { + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + goto retry; + } + if (error) + goto out_unlock; r->res_hash = hash; r->res_bucket = bucket; @@ -474,18 +527,10 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen, nodeid = 0; r->res_nodeid = nodeid; } - - spin_lock(&ls->ls_rsbtbl[bucket].lock); - error = _search_rsb(ls, name, namelen, bucket, 0, &tmp); - if (!error) { - spin_unlock(&ls->ls_rsbtbl[bucket].lock); - dlm_free_rsb(r); - r = tmp; - goto out; - } list_add(&r->res_hashchain, &ls->ls_rsbtbl[bucket].list); - spin_unlock(&ls->ls_rsbtbl[bucket].lock); error = 0; + out_unlock: + spin_unlock(&ls->ls_rsbtbl[bucket].lock); out: *r_ret = r; return error; @@ -580,9 +625,8 @@ static void detach_lkb(struct dlm_lkb *lkb) static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) { - struct dlm_lkb *lkb, *tmp; - uint32_t lkid = 0; - uint16_t bucket; + struct dlm_lkb *lkb; + int rv, id; lkb = dlm_allocate_lkb(ls); if (!lkb) @@ -594,60 +638,42 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) INIT_LIST_HEAD(&lkb->lkb_ownqueue); INIT_LIST_HEAD(&lkb->lkb_rsb_lookup); INIT_LIST_HEAD(&lkb->lkb_time_list); - INIT_LIST_HEAD(&lkb->lkb_astqueue); + INIT_LIST_HEAD(&lkb->lkb_cb_list); + mutex_init(&lkb->lkb_cb_mutex); + INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work); - get_random_bytes(&bucket, sizeof(bucket)); - bucket &= (ls->ls_lkbtbl_size - 1); - - write_lock(&ls->ls_lkbtbl[bucket].lock); + retry: + rv = idr_pre_get(&ls->ls_lkbidr, GFP_NOFS); + if (!rv) + return -ENOMEM; - /* counter can roll over so we must verify lkid is not in use */ + spin_lock(&ls->ls_lkbidr_spin); + rv = idr_get_new_above(&ls->ls_lkbidr, lkb, 1, &id); + if (!rv) + lkb->lkb_id = id; + spin_unlock(&ls->ls_lkbidr_spin); - while (lkid == 0) { - lkid = (bucket << 16) | ls->ls_lkbtbl[bucket].counter++; + if (rv == -EAGAIN) + goto retry; - list_for_each_entry(tmp, &ls->ls_lkbtbl[bucket].list, - lkb_idtbl_list) { - if (tmp->lkb_id != lkid) - continue; - lkid = 0; - break; - } + if (rv < 0) { + log_error(ls, "create_lkb idr error %d", rv); + return rv; } - lkb->lkb_id = lkid; - list_add(&lkb->lkb_idtbl_list, &ls->ls_lkbtbl[bucket].list); - write_unlock(&ls->ls_lkbtbl[bucket].lock); - *lkb_ret = lkb; return 0; } -static struct dlm_lkb *__find_lkb(struct dlm_ls *ls, uint32_t lkid) -{ - struct dlm_lkb *lkb; - uint16_t bucket = (lkid >> 16); - - list_for_each_entry(lkb, &ls->ls_lkbtbl[bucket].list, lkb_idtbl_list) { - if (lkb->lkb_id == lkid) - return lkb; - } - return NULL; -} - static int find_lkb(struct dlm_ls *ls, uint32_t lkid, struct dlm_lkb **lkb_ret) { struct dlm_lkb *lkb; - uint16_t bucket = (lkid >> 16); - - if (bucket >= ls->ls_lkbtbl_size) - return -EBADSLT; - read_lock(&ls->ls_lkbtbl[bucket].lock); - lkb = __find_lkb(ls, lkid); + spin_lock(&ls->ls_lkbidr_spin); + lkb = idr_find(&ls->ls_lkbidr, lkid); if (lkb) kref_get(&lkb->lkb_ref); - read_unlock(&ls->ls_lkbtbl[bucket].lock); + spin_unlock(&ls->ls_lkbidr_spin); *lkb_ret = lkb; return lkb ? 0 : -ENOENT; @@ -668,12 +694,12 @@ static void kill_lkb(struct kref *kref) static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb) { - uint16_t bucket = (lkb->lkb_id >> 16); + uint32_t lkid = lkb->lkb_id; - write_lock(&ls->ls_lkbtbl[bucket].lock); + spin_lock(&ls->ls_lkbidr_spin); if (kref_put(&lkb->lkb_ref, kill_lkb)) { - list_del(&lkb->lkb_idtbl_list); - write_unlock(&ls->ls_lkbtbl[bucket].lock); + idr_remove(&ls->ls_lkbidr, lkid); + spin_unlock(&ls->ls_lkbidr_spin); detach_lkb(lkb); @@ -683,7 +709,7 @@ static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb) dlm_free_lkb(lkb); return 1; } else { - write_unlock(&ls->ls_lkbtbl[bucket].lock); + spin_unlock(&ls->ls_lkbidr_spin); return 0; } } @@ -849,9 +875,7 @@ void dlm_scan_waiters(struct dlm_ls *ls) if (!num_nodes) { num_nodes = ls->ls_num_nodes; - warned = kmalloc(GFP_KERNEL, num_nodes * sizeof(int)); - if (warned) - memset(warned, 0, num_nodes * sizeof(int)); + warned = kzalloc(num_nodes * sizeof(int), GFP_KERNEL); } if (!warned) continue; @@ -863,9 +887,7 @@ void dlm_scan_waiters(struct dlm_ls *ls) dlm_config.ci_waitwarn_us, lkb->lkb_wait_nodeid); } mutex_unlock(&ls->ls_waiters_mutex); - - if (warned) - kfree(warned); + kfree(warned); if (debug_expired) log_debug(ls, "scan_waiters %u warn %u over %d us max %lld us", @@ -2401,9 +2423,6 @@ static int do_convert(struct dlm_rsb *r, struct dlm_lkb *lkb) if (deadlk) { /* it's left on the granted queue */ - log_debug(r->res_ls, "deadlock %x node %d sts%d g%d r%d %s", - lkb->lkb_id, lkb->lkb_nodeid, lkb->lkb_status, - lkb->lkb_grmode, lkb->lkb_rqmode, r->res_name); revert_lock(r, lkb); queue_cast(r, lkb, -EDEADLK); error = -EDEADLK; @@ -3993,8 +4012,6 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms) default: log_error(ls, "unknown message type %d", ms->m_type); } - - dlm_astd_wake(); } /* If the lockspace is in recovery mode (locking stopped), then normal @@ -4133,7 +4150,7 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) struct dlm_message *ms_stub; int wait_type, stub_unlock_result, stub_cancel_result; - ms_stub = kmalloc(GFP_KERNEL, sizeof(struct dlm_message)); + ms_stub = kmalloc(sizeof(struct dlm_message), GFP_KERNEL); if (!ms_stub) { log_error(ls, "dlm_recover_waiters_pre no mem"); return; @@ -4809,7 +4826,7 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp, goto out_put; spin_lock(&ua->proc->locks_spin); - /* dlm_user_add_ast() may have already taken lkb off the proc list */ + /* dlm_user_add_cb() may have already taken lkb off the proc list */ if (!list_empty(&lkb->lkb_ownqueue)) list_move(&lkb->lkb_ownqueue, &ua->proc->unlocking); spin_unlock(&ua->proc->locks_spin); @@ -4946,7 +4963,7 @@ static int unlock_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb) /* We have to release clear_proc_locks mutex before calling unlock_proc_lock() (which does lock_rsb) due to deadlock with receiving a message that does - lock_rsb followed by dlm_user_add_ast() */ + lock_rsb followed by dlm_user_add_cb() */ static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls, struct dlm_user_proc *proc) @@ -4969,7 +4986,7 @@ static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls, return lkb; } -/* The ls_clear_proc_locks mutex protects against dlm_user_add_asts() which +/* The ls_clear_proc_locks mutex protects against dlm_user_add_cb() which 1) references lkb->ua which we free here and 2) adds lkbs to proc->asts, which we clear here. */ @@ -5011,10 +5028,10 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc) dlm_put_lkb(lkb); } - list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) { + list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_cb_list) { memset(&lkb->lkb_callbacks, 0, sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE); - list_del_init(&lkb->lkb_astqueue); + list_del_init(&lkb->lkb_cb_list); dlm_put_lkb(lkb); } @@ -5053,10 +5070,10 @@ static void purge_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc) spin_unlock(&proc->locks_spin); spin_lock(&proc->asts_spin); - list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) { + list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_cb_list) { memset(&lkb->lkb_callbacks, 0, sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE); - list_del_init(&lkb->lkb_astqueue); + list_del_init(&lkb->lkb_cb_list); dlm_put_lkb(lkb); } spin_unlock(&proc->asts_spin); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 14cbf40..a1d8f1a 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -15,7 +15,6 @@ #include "lockspace.h" #include "member.h" #include "recoverd.h" -#include "ast.h" #include "dir.h" #include "lowcomms.h" #include "config.h" @@ -24,6 +23,7 @@ #include "recover.h" #include "requestqueue.h" #include "user.h" +#include "ast.h" static int ls_count; static struct mutex ls_lock; @@ -359,17 +359,10 @@ static int threads_start(void) { int error; - /* Thread which process lock requests for all lockspace's */ - error = dlm_astd_start(); - if (error) { - log_print("cannot start dlm_astd thread %d", error); - goto fail; - } - error = dlm_scand_start(); if (error) { log_print("cannot start dlm_scand thread %d", error); - goto astd_fail; + goto fail; } /* Thread for sending/receiving messages for all lockspace's */ @@ -383,8 +376,6 @@ static int threads_start(void) scand_fail: dlm_scand_stop(); - astd_fail: - dlm_astd_stop(); fail: return error; } @@ -393,7 +384,6 @@ static void threads_stop(void) { dlm_scand_stop(); dlm_lowcomms_stop(); - dlm_astd_stop(); } static int new_lockspace(const char *name, int namelen, void **lockspace, @@ -463,7 +453,7 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, size = dlm_config.ci_rsbtbl_size; ls->ls_rsbtbl_size = size; - ls->ls_rsbtbl = kmalloc(sizeof(struct dlm_rsbtable) * size, GFP_NOFS); + ls->ls_rsbtbl = vmalloc(sizeof(struct dlm_rsbtable) * size); if (!ls->ls_rsbtbl) goto out_lsfree; for (i = 0; i < size; i++) { @@ -472,22 +462,13 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, spin_lock_init(&ls->ls_rsbtbl[i].lock); } - size = dlm_config.ci_lkbtbl_size; - ls->ls_lkbtbl_size = size; - - ls->ls_lkbtbl = kmalloc(sizeof(struct dlm_lkbtable) * size, GFP_NOFS); - if (!ls->ls_lkbtbl) - goto out_rsbfree; - for (i = 0; i < size; i++) { - INIT_LIST_HEAD(&ls->ls_lkbtbl[i].list); - rwlock_init(&ls->ls_lkbtbl[i].lock); - ls->ls_lkbtbl[i].counter = 1; - } + idr_init(&ls->ls_lkbidr); + spin_lock_init(&ls->ls_lkbidr_spin); size = dlm_config.ci_dirtbl_size; ls->ls_dirtbl_size = size; - ls->ls_dirtbl = kmalloc(sizeof(struct dlm_dirtable) * size, GFP_NOFS); + ls->ls_dirtbl = vmalloc(sizeof(struct dlm_dirtable) * size); if (!ls->ls_dirtbl) goto out_lkbfree; for (i = 0; i < size; i++) { @@ -502,6 +483,9 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, INIT_LIST_HEAD(&ls->ls_timeout); mutex_init(&ls->ls_timeout_mutex); + INIT_LIST_HEAD(&ls->ls_new_rsb); + spin_lock_init(&ls->ls_new_rsb_spin); + INIT_LIST_HEAD(&ls->ls_nodes); INIT_LIST_HEAD(&ls->ls_nodes_gone); ls->ls_num_nodes = 0; @@ -520,6 +504,9 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, init_completion(&ls->ls_members_done); ls->ls_members_result = -1; + mutex_init(&ls->ls_cb_mutex); + INIT_LIST_HEAD(&ls->ls_cb_delay); + ls->ls_recoverd_task = NULL; mutex_init(&ls->ls_recoverd_active); spin_lock_init(&ls->ls_recover_lock); @@ -553,18 +540,26 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, list_add(&ls->ls_list, &lslist); spin_unlock(&lslist_lock); + if (flags & DLM_LSFL_FS) { + error = dlm_callback_start(ls); + if (error) { + log_error(ls, "can't start dlm_callback %d", error); + goto out_delist; + } + } + /* needs to find ls in lslist */ error = dlm_recoverd_start(ls); if (error) { log_error(ls, "can't start dlm_recoverd %d", error); - goto out_delist; + goto out_callback; } ls->ls_kobj.kset = dlm_kset; error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL, "%s", ls->ls_name); if (error) - goto out_stop; + goto out_recoverd; kobject_uevent(&ls->ls_kobj, KOBJ_ADD); /* let kobject handle freeing of ls if there's an error */ @@ -578,7 +573,7 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, error = do_uevent(ls, 1); if (error) - goto out_stop; + goto out_recoverd; wait_for_completion(&ls->ls_members_done); error = ls->ls_members_result; @@ -595,19 +590,20 @@ static int new_lockspace(const char *name, int namelen, void **lockspace, do_uevent(ls, 0); dlm_clear_members(ls); kfree(ls->ls_node_array); - out_stop: + out_recoverd: dlm_recoverd_stop(ls); + out_callback: + dlm_callback_stop(ls); out_delist: spin_lock(&lslist_lock); list_del(&ls->ls_list); spin_unlock(&lslist_lock); kfree(ls->ls_recover_buf); out_dirfree: - kfree(ls->ls_dirtbl); + vfree(ls->ls_dirtbl); out_lkbfree: - kfree(ls->ls_lkbtbl); - out_rsbfree: - kfree(ls->ls_rsbtbl); + idr_destroy(&ls->ls_lkbidr); + vfree(ls->ls_rsbtbl); out_lsfree: if (do_unreg) kobject_put(&ls->ls_kobj); @@ -641,50 +637,64 @@ int dlm_new_lockspace(const char *name, int namelen, void **lockspace, return error; } -/* Return 1 if the lockspace still has active remote locks, - * 2 if the lockspace still has active local locks. - */ -static int lockspace_busy(struct dlm_ls *ls) -{ - int i, lkb_found = 0; - struct dlm_lkb *lkb; - - /* NOTE: We check the lockidtbl here rather than the resource table. - This is because there may be LKBs queued as ASTs that have been - unlinked from their RSBs and are pending deletion once the AST has - been delivered */ - - for (i = 0; i < ls->ls_lkbtbl_size; i++) { - read_lock(&ls->ls_lkbtbl[i].lock); - if (!list_empty(&ls->ls_lkbtbl[i].list)) { - lkb_found = 1; - list_for_each_entry(lkb, &ls->ls_lkbtbl[i].list, - lkb_idtbl_list) { - if (!lkb->lkb_nodeid) { - read_unlock(&ls->ls_lkbtbl[i].lock); - return 2; - } - } - } - read_unlock(&ls->ls_lkbtbl[i].lock); +static int lkb_idr_is_local(int id, void *p, void *data) +{ + struct dlm_lkb *lkb = p; + + if (!lkb->lkb_nodeid) + return 1; + return 0; +} + +static int lkb_idr_is_any(int id, void *p, void *data) +{ + return 1; +} + +static int lkb_idr_free(int id, void *p, void *data) +{ + struct dlm_lkb *lkb = p; + + if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY) + dlm_free_lvb(lkb->lkb_lvbptr); + + dlm_free_lkb(lkb); + return 0; +} + +/* NOTE: We check the lkbidr here rather than the resource table. + This is because there may be LKBs queued as ASTs that have been unlinked + from their RSBs and are pending deletion once the AST has been delivered */ + +static int lockspace_busy(struct dlm_ls *ls, int force) +{ + int rv; + + spin_lock(&ls->ls_lkbidr_spin); + if (force == 0) { + rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_any, ls); + } else if (force == 1) { + rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_local, ls); + } else { + rv = 0; } - return lkb_found; + spin_unlock(&ls->ls_lkbidr_spin); + return rv; } static int release_lockspace(struct dlm_ls *ls, int force) { - struct dlm_lkb *lkb; struct dlm_rsb *rsb; struct list_head *head; int i, busy, rv; - busy = lockspace_busy(ls); + busy = lockspace_busy(ls, force); spin_lock(&lslist_lock); if (ls->ls_create_count == 1) { - if (busy > force) + if (busy) { rv = -EBUSY; - else { + } else { /* remove_lockspace takes ls off lslist */ ls->ls_create_count = 0; rv = 0; @@ -708,12 +718,12 @@ static int release_lockspace(struct dlm_ls *ls, int force) dlm_recoverd_stop(ls); + dlm_callback_stop(ls); + remove_lockspace(ls); dlm_delete_debug_file(ls); - dlm_astd_suspend(); - kfree(ls->ls_recover_buf); /* @@ -721,31 +731,15 @@ static int release_lockspace(struct dlm_ls *ls, int force) */ dlm_dir_clear(ls); - kfree(ls->ls_dirtbl); + vfree(ls->ls_dirtbl); /* - * Free all lkb's on lkbtbl[] lists. + * Free all lkb's in idr */ - for (i = 0; i < ls->ls_lkbtbl_size; i++) { - head = &ls->ls_lkbtbl[i].list; - while (!list_empty(head)) { - lkb = list_entry(head->next, struct dlm_lkb, - lkb_idtbl_list); - - list_del(&lkb->lkb_idtbl_list); - - dlm_del_ast(lkb); - - if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY) - dlm_free_lvb(lkb->lkb_lvbptr); - - dlm_free_lkb(lkb); - } - } - dlm_astd_resume(); - - kfree(ls->ls_lkbtbl); + idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls); + idr_remove_all(&ls->ls_lkbidr); + idr_destroy(&ls->ls_lkbidr); /* * Free all rsb's on rsbtbl[] lists @@ -770,7 +764,14 @@ static int release_lockspace(struct dlm_ls *ls, int force) } } - kfree(ls->ls_rsbtbl); + vfree(ls->ls_rsbtbl); + + while (!list_empty(&ls->ls_new_rsb)) { + rsb = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb, + res_hashchain); + list_del(&rsb->res_hashchain); + dlm_free_rsb(rsb); + } /* * Free structures on any other lists diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 5e2c71f..990626e 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -512,12 +512,10 @@ static void process_sctp_notification(struct connection *con, } make_sockaddr(&prim.ssp_addr, 0, &addr_len); if (dlm_addr_to_nodeid(&prim.ssp_addr, &nodeid)) { - int i; unsigned char *b=(unsigned char *)&prim.ssp_addr; log_print("reject connect from unknown addr"); - for (i=0; i<sizeof(struct sockaddr_storage);i++) - printk("%02x ", b[i]); - printk("\n"); + print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, + b, sizeof(struct sockaddr_storage)); sctp_send_shutdown(prim.ssp_assoc_id); return; } @@ -748,7 +746,10 @@ static int tcp_accept_from_sock(struct connection *con) /* Get the new node's NODEID */ make_sockaddr(&peeraddr, 0, &len); if (dlm_addr_to_nodeid(&peeraddr, &nodeid)) { + unsigned char *b=(unsigned char *)&peeraddr; log_print("connect from non cluster node"); + print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, + b, sizeof(struct sockaddr_storage)); sock_release(newsock); mutex_unlock(&con->sock_mutex); return -1; diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c index 8e0d00d..da64df7 100644 --- a/fs/dlm/memory.c +++ b/fs/dlm/memory.c @@ -16,6 +16,7 @@ #include "memory.h" static struct kmem_cache *lkb_cache; +static struct kmem_cache *rsb_cache; int __init dlm_memory_init(void) @@ -26,6 +27,14 @@ int __init dlm_memory_init(void) __alignof__(struct dlm_lkb), 0, NULL); if (!lkb_cache) ret = -ENOMEM; + + rsb_cache = kmem_cache_create("dlm_rsb", sizeof(struct dlm_rsb), + __alignof__(struct dlm_rsb), 0, NULL); + if (!rsb_cache) { + kmem_cache_destroy(lkb_cache); + ret = -ENOMEM; + } + return ret; } @@ -33,6 +42,8 @@ void dlm_memory_exit(void) { if (lkb_cache) kmem_cache_destroy(lkb_cache); + if (rsb_cache) + kmem_cache_destroy(rsb_cache); } char *dlm_allocate_lvb(struct dlm_ls *ls) @@ -48,16 +59,11 @@ void dlm_free_lvb(char *p) kfree(p); } -/* FIXME: have some minimal space built-in to rsb for the name and - kmalloc a separate name if needed, like dentries are done */ - -struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen) +struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls) { struct dlm_rsb *r; - DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,); - - r = kzalloc(sizeof(*r) + namelen, GFP_NOFS); + r = kmem_cache_zalloc(rsb_cache, GFP_NOFS); return r; } @@ -65,7 +71,7 @@ void dlm_free_rsb(struct dlm_rsb *r) { if (r->res_lvbptr) dlm_free_lvb(r->res_lvbptr); - kfree(r); + kmem_cache_free(rsb_cache, r); } struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls) diff --git a/fs/dlm/memory.h b/fs/dlm/memory.h index 485fb29..177c11c 100644 --- a/fs/dlm/memory.h +++ b/fs/dlm/memory.h @@ -16,7 +16,7 @@ int dlm_memory_init(void); void dlm_memory_exit(void); -struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen); +struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls); void dlm_free_rsb(struct dlm_rsb *r); struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls); void dlm_free_lkb(struct dlm_lkb *l); diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index fd677c8..774da3c 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -58,13 +58,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) mutex_lock(&ls->ls_recoverd_active); - /* - * Suspending and resuming dlm_astd ensures that no lkb's from this ls - * will be processed by dlm_astd during recovery. - */ - - dlm_astd_suspend(); - dlm_astd_resume(); + dlm_callback_suspend(ls); /* * Free non-master tossed rsb's. Master rsb's are kept on toss @@ -202,6 +196,8 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) dlm_adjust_timeouts(ls); + dlm_callback_resume(ls); + error = enable_locking(ls, rv->seq); if (error) { log_debug(ls, "enable_locking failed %d", error); @@ -222,8 +218,6 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) dlm_grant_after_purge(ls); - dlm_astd_wake(); - log_debug(ls, "recover %llx done: %u ms", (unsigned long long)rv->seq, jiffies_to_msecs(jiffies - start)); diff --git a/fs/dlm/user.c b/fs/dlm/user.c index e96bf3e..d8ea607 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -213,9 +213,9 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode, goto out; } - if (list_empty(&lkb->lkb_astqueue)) { + if (list_empty(&lkb->lkb_cb_list)) { kref_get(&lkb->lkb_ref); - list_add_tail(&lkb->lkb_astqueue, &proc->asts); + list_add_tail(&lkb->lkb_cb_list, &proc->asts); wake_up_interruptible(&proc->wait); } spin_unlock(&proc->asts_spin); @@ -832,24 +832,24 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, } /* if we empty lkb_callbacks, we don't want to unlock the spinlock - without removing lkb_astqueue; so empty lkb_astqueue is always + without removing lkb_cb_list; so empty lkb_cb_list is always consistent with empty lkb_callbacks */ - lkb = list_entry(proc->asts.next, struct dlm_lkb, lkb_astqueue); + lkb = list_entry(proc->asts.next, struct dlm_lkb, lkb_cb_list); rv = dlm_rem_lkb_callback(lkb->lkb_resource->res_ls, lkb, &cb, &resid); if (rv < 0) { /* this shouldn't happen; lkb should have been removed from list when resid was zero */ log_print("dlm_rem_lkb_callback empty %x", lkb->lkb_id); - list_del_init(&lkb->lkb_astqueue); + list_del_init(&lkb->lkb_cb_list); spin_unlock(&proc->asts_spin); /* removes ref for proc->asts, may cause lkb to be freed */ dlm_put_lkb(lkb); goto try_another; } if (!resid) - list_del_init(&lkb->lkb_astqueue); + list_del_init(&lkb->lkb_cb_list); spin_unlock(&proc->asts_spin); if (cb.flags & DLM_CB_SKIP) { diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 06065bd..c57bedd 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -913,7 +913,7 @@ struct dentry *exofs_get_parent(struct dentry *child) unsigned long ino = exofs_parent_ino(child); if (!ino) - return NULL; + return ERR_PTR(-ESTALE); return d_obtain_alias(exofs_iget(child->d_inode->i_sb, ino)); } diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 2e29abb..095c36f 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -125,7 +125,7 @@ struct ext4_ext_path { * positive retcode - signal for ext4_ext_walk_space(), see below * callback must return valid extent (passed or newly created) */ -typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, +typedef int (*ext_prepare_callback)(struct inode *, ext4_lblk_t, struct ext4_ext_cache *, struct ext4_extent *, void *); @@ -133,8 +133,11 @@ typedef int (*ext_prepare_callback)(struct inode *, struct ext4_ext_path *, #define EXT_BREAK 1 #define EXT_REPEAT 2 -/* Maximum logical block in a file; ext4_extent's ee_block is __le32 */ -#define EXT_MAX_BLOCK 0xffffffff +/* + * Maximum number of logical blocks in a file; ext4_extent's ee_block is + * __le32. + */ +#define EXT_MAX_BLOCKS 0xffffffff /* * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5199bac..f815cc8 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1408,7 +1408,7 @@ got_index: /* * ext4_ext_next_allocated_block: - * returns allocated block in subsequent extent or EXT_MAX_BLOCK. + * returns allocated block in subsequent extent or EXT_MAX_BLOCKS. * NOTE: it considers block number from index entry as * allocated block. Thus, index entries have to be consistent * with leaves. @@ -1422,7 +1422,7 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) depth = path->p_depth; if (depth == 0 && path->p_ext == NULL) - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; while (depth >= 0) { if (depth == path->p_depth) { @@ -1439,12 +1439,12 @@ ext4_ext_next_allocated_block(struct ext4_ext_path *path) depth--; } - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; } /* * ext4_ext_next_leaf_block: - * returns first allocated block from next leaf or EXT_MAX_BLOCK + * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, struct ext4_ext_path *path) @@ -1456,7 +1456,7 @@ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, /* zero-tree has no leaf blocks at all */ if (depth == 0) - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; /* go to index block */ depth--; @@ -1469,7 +1469,7 @@ static ext4_lblk_t ext4_ext_next_leaf_block(struct inode *inode, depth--; } - return EXT_MAX_BLOCK; + return EXT_MAX_BLOCKS; } /* @@ -1677,13 +1677,13 @@ static unsigned int ext4_ext_check_overlap(struct inode *inode, */ if (b2 < b1) { b2 = ext4_ext_next_allocated_block(path); - if (b2 == EXT_MAX_BLOCK) + if (b2 == EXT_MAX_BLOCKS) goto out; } /* check for wrap through zero on extent logical start block*/ if (b1 + len1 < b1) { - len1 = EXT_MAX_BLOCK - b1; + len1 = EXT_MAX_BLOCKS - b1; newext->ee_len = cpu_to_le16(len1); ret = 1; } @@ -1767,7 +1767,7 @@ repeat: fex = EXT_LAST_EXTENT(eh); next = ext4_ext_next_leaf_block(inode, path); if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block) - && next != EXT_MAX_BLOCK) { + && next != EXT_MAX_BLOCKS) { ext_debug("next leaf block - %d\n", next); BUG_ON(npath != NULL); npath = ext4_ext_find_extent(inode, next, NULL); @@ -1887,7 +1887,7 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, BUG_ON(func == NULL); BUG_ON(inode == NULL); - while (block < last && block != EXT_MAX_BLOCK) { + while (block < last && block != EXT_MAX_BLOCKS) { num = last - block; /* find extent for this block */ down_read(&EXT4_I(inode)->i_data_sem); @@ -1958,7 +1958,7 @@ static int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block, err = -EIO; break; } - err = func(inode, path, &cbex, ex, cbdata); + err = func(inode, next, &cbex, ex, cbdata); ext4_ext_drop_refs(path); if (err < 0) @@ -2020,7 +2020,7 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, if (ex == NULL) { /* there is no extent yet, so gap is [0;-] */ lblock = 0; - len = EXT_MAX_BLOCK; + len = EXT_MAX_BLOCKS; ext_debug("cache gap(whole file):"); } else if (block < le32_to_cpu(ex->ee_block)) { lblock = block; @@ -2350,7 +2350,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * never happen because at least one of the end points * needs to be on the edge of the extent. */ - if (end == EXT_MAX_BLOCK) { + if (end == EXT_MAX_BLOCKS - 1) { ext_debug(" bad truncate %u:%u\n", start, end); block = 0; @@ -2398,7 +2398,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * If this is a truncate, this condition * should never happen */ - if (end == EXT_MAX_BLOCK) { + if (end == EXT_MAX_BLOCKS - 1) { ext_debug(" bad truncate %u:%u\n", start, end); err = -EIO; @@ -2478,7 +2478,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * we need to remove it from the leaf */ if (num == 0) { - if (end != EXT_MAX_BLOCK) { + if (end != EXT_MAX_BLOCKS - 1) { /* * For hole punching, we need to scoot all the * extents up when an extent is removed so that @@ -3699,7 +3699,7 @@ void ext4_ext_truncate(struct inode *inode) last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); - err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCK); + err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); /* In a multi-transaction truncate, we only make the final * transaction synchronous. @@ -3914,14 +3914,13 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset, /* * Callback function called for each extent to gather FIEMAP information. */ -static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path, +static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next, struct ext4_ext_cache *newex, struct ext4_extent *ex, void *data) { __u64 logical; __u64 physical; __u64 length; - loff_t size; __u32 flags = 0; int ret = 0; struct fiemap_extent_info *fieinfo = data; @@ -4103,8 +4102,7 @@ found_delayed_extent: if (ex && ext4_ext_is_uninitialized(ex)) flags |= FIEMAP_EXTENT_UNWRITTEN; - size = i_size_read(inode); - if (logical + length >= size) + if (next == EXT_MAX_BLOCKS) flags |= FIEMAP_EXTENT_LAST; ret = fiemap_fill_next_extent(fieinfo, logical, physical, @@ -4347,8 +4345,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, start_blk = start >> inode->i_sb->s_blocksize_bits; last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; - if (last_blk >= EXT_MAX_BLOCK) - last_blk = EXT_MAX_BLOCK-1; + if (last_blk >= EXT_MAX_BLOCKS) + last_blk = EXT_MAX_BLOCKS-1; len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a5763e3..e3126c0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2634,7 +2634,7 @@ static int ext4_writepage(struct page *page, struct buffer_head *page_bufs = NULL; struct inode *inode = page->mapping->host; - trace_ext4_writepage(inode, page); + trace_ext4_writepage(page); size = i_size_read(inode); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 859f2ae..6ed859d 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3578,8 +3578,8 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh, free += next - bit; trace_ext4_mballoc_discard(sb, NULL, group, bit, next - bit); - trace_ext4_mb_release_inode_pa(sb, pa->pa_inode, pa, - grp_blk_start + bit, next - bit); + trace_ext4_mb_release_inode_pa(pa, grp_blk_start + bit, + next - bit); mb_free_blocks(pa->pa_inode, e4b, bit, next - bit); bit = next + 1; } @@ -3608,7 +3608,7 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b, ext4_group_t group; ext4_grpblk_t bit; - trace_ext4_mb_release_group_pa(sb, pa); + trace_ext4_mb_release_group_pa(pa); BUG_ON(pa->pa_deleted == 0); ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit); BUG_ON(group != e4b->bd_group && pa->pa_len != 0); @@ -4448,7 +4448,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, * @inode: inode * @block: start physical block to free * @count: number of blocks to count - * @metadata: Are these metadata blocks + * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 2b8304b..f57455a 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -1002,12 +1002,12 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - if ((orig_start > EXT_MAX_BLOCK) || - (donor_start > EXT_MAX_BLOCK) || - (*len > EXT_MAX_BLOCK) || - (orig_start + *len > EXT_MAX_BLOCK)) { + if ((orig_start >= EXT_MAX_BLOCKS) || + (donor_start >= EXT_MAX_BLOCKS) || + (*len > EXT_MAX_BLOCKS) || + (orig_start + *len >= EXT_MAX_BLOCKS)) { ext4_debug("ext4 move extent: Can't handle over [%u] blocks " - "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCK, + "[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cc5c157..9ea71aa 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2243,6 +2243,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, * in the vfs. ext4 inode has 48 bits of i_block in fsblock units, * so that won't be a limiting factor. * + * However there is other limiting factor. We do store extents in the form + * of starting block and length, hence the resulting length of the extent + * covering maximum file size must fit into on-disk format containers as + * well. Given that length is always by 1 unit bigger than max unit (because + * we count 0 as well) we have to lower the s_maxbytes by one fs block. + * * Note, this does *not* consider any metadata overhead for vfs i_blocks. */ static loff_t ext4_max_size(int blkbits, int has_huge_files) @@ -2264,10 +2270,13 @@ static loff_t ext4_max_size(int blkbits, int has_huge_files) upper_limit <<= blkbits; } - /* 32-bit extent-start container, ee_block */ - res = 1LL << 32; + /* + * 32-bit extent-start container, ee_block. We lower the maxbytes + * by one fs block, so ee_len can cover the extent of maximum file + * size + */ + res = (1LL << 32) - 1; res <<= blkbits; - res -= 1; /* Sanity check against vm- & vfs- imposed limits */ if (res > upper_limit) diff --git a/fs/fscache/page.c b/fs/fscache/page.c index a2a5d19..3f7a59b 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -954,3 +954,43 @@ void fscache_mark_pages_cached(struct fscache_retrieval *op, pagevec_reinit(pagevec); } EXPORT_SYMBOL(fscache_mark_pages_cached); + +/* + * Uncache all the pages in an inode that are marked PG_fscache, assuming them + * to be associated with the given cookie. + */ +void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, + struct inode *inode) +{ + struct address_space *mapping = inode->i_mapping; + struct pagevec pvec; + pgoff_t next; + int i; + + _enter("%p,%p", cookie, inode); + + if (!mapping || mapping->nrpages == 0) { + _leave(" [no pages]"); + return; + } + + pagevec_init(&pvec, 0); + next = 0; + do { + if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) + break; + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *page = pvec.pages[i]; + next = page->index; + if (PageFsCache(page)) { + __fscache_wait_on_page_write(cookie, page); + __fscache_uncache_page(cookie, page); + } + } + pagevec_release(&pvec); + cond_resched(); + } while (++next); + + _leave(""); +} +EXPORT_SYMBOL(__fscache_uncache_all_inode_pages); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 802ac5e..f9fbbe9 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1069,6 +1069,7 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) return 0; gfs2_log_lock(sdp); + spin_lock(&sdp->sd_ail_lock); head = bh = page_buffers(page); do { if (atomic_read(&bh->b_count)) @@ -1080,6 +1081,7 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) goto not_possible; bh = bh->b_this_page; } while(bh != head); + spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); head = bh = page_buffers(page); @@ -1112,6 +1114,7 @@ not_possible: /* Should never happen */ WARN_ON(buffer_dirty(bh)); WARN_ON(buffer_pinned(bh)); cannot_release: + spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); return 0; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index e65493a..42e477f 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -854,11 +854,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, blen++; else { if (bstart) { - if (metadata) - __gfs2_free_meta(ip, bstart, blen); - else - __gfs2_free_data(ip, bstart, blen); - + __gfs2_free_blocks(ip, bstart, blen, metadata); btotal += blen; } @@ -870,11 +866,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh, gfs2_add_inode_blocks(&ip->i_inode, -1); } if (bstart) { - if (metadata) - __gfs2_free_meta(ip, bstart, blen); - else - __gfs2_free_data(ip, bstart, blen); - + __gfs2_free_blocks(ip, bstart, blen, metadata); btotal += blen; } diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 091ee47..1cc2f8e 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -339,6 +339,67 @@ fail: return (copied) ? copied : error; } +/** + * gfs2_dir_get_hash_table - Get pointer to the dir hash table + * @ip: The inode in question + * + * Returns: The hash table or an error + */ + +static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) +{ + struct inode *inode = &ip->i_inode; + int ret; + u32 hsize; + __be64 *hc; + + BUG_ON(!(ip->i_diskflags & GFS2_DIF_EXHASH)); + + hc = ip->i_hash_cache; + if (hc) + return hc; + + hsize = 1 << ip->i_depth; + hsize *= sizeof(__be64); + if (hsize != i_size_read(&ip->i_inode)) { + gfs2_consist_inode(ip); + return ERR_PTR(-EIO); + } + + hc = kmalloc(hsize, GFP_NOFS); + ret = -ENOMEM; + if (hc == NULL) + return ERR_PTR(-ENOMEM); + + ret = gfs2_dir_read_data(ip, (char *)hc, 0, hsize, 1); + if (ret < 0) { + kfree(hc); + return ERR_PTR(ret); + } + + spin_lock(&inode->i_lock); + if (ip->i_hash_cache) + kfree(hc); + else + ip->i_hash_cache = hc; + spin_unlock(&inode->i_lock); + + return ip->i_hash_cache; +} + +/** + * gfs2_dir_hash_inval - Invalidate dir hash + * @ip: The directory inode + * + * Must be called with an exclusive glock, or during glock invalidation. + */ +void gfs2_dir_hash_inval(struct gfs2_inode *ip) +{ + __be64 *hc = ip->i_hash_cache; + ip->i_hash_cache = NULL; + kfree(hc); +} + static inline int gfs2_dirent_sentinel(const struct gfs2_dirent *dent) { return dent->de_inum.no_addr == 0 || dent->de_inum.no_formal_ino == 0; @@ -686,17 +747,12 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no, static int get_leaf_nr(struct gfs2_inode *dip, u32 index, u64 *leaf_out) { - __be64 leaf_no; - int error; - - error = gfs2_dir_read_data(dip, (char *)&leaf_no, - index * sizeof(__be64), - sizeof(__be64), 0); - if (error != sizeof(u64)) - return (error < 0) ? error : -EIO; - - *leaf_out = be64_to_cpu(leaf_no); + __be64 *hash; + hash = gfs2_dir_get_hash_table(dip); + if (IS_ERR(hash)) + return PTR_ERR(hash); + *leaf_out = be64_to_cpu(*(hash + index)); return 0; } @@ -966,6 +1022,8 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name) for (x = 0; x < half_len; x++) lp[x] = cpu_to_be64(bn); + gfs2_dir_hash_inval(dip); + error = gfs2_dir_write_data(dip, (char *)lp, start * sizeof(u64), half_len * sizeof(u64)); if (error != half_len * sizeof(u64)) { @@ -1052,70 +1110,54 @@ fail_brelse: static int dir_double_exhash(struct gfs2_inode *dip) { - struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct buffer_head *dibh; u32 hsize; - u64 *buf; - u64 *from, *to; - u64 block; - u64 disksize = i_size_read(&dip->i_inode); + u32 hsize_bytes; + __be64 *hc; + __be64 *hc2, *h; int x; int error = 0; hsize = 1 << dip->i_depth; - if (hsize * sizeof(u64) != disksize) { - gfs2_consist_inode(dip); - return -EIO; - } + hsize_bytes = hsize * sizeof(__be64); - /* Allocate both the "from" and "to" buffers in one big chunk */ + hc = gfs2_dir_get_hash_table(dip); + if (IS_ERR(hc)) + return PTR_ERR(hc); - buf = kcalloc(3, sdp->sd_hash_bsize, GFP_NOFS); - if (!buf) + h = hc2 = kmalloc(hsize_bytes * 2, GFP_NOFS); + if (!hc2) return -ENOMEM; - for (block = disksize >> sdp->sd_hash_bsize_shift; block--;) { - error = gfs2_dir_read_data(dip, (char *)buf, - block * sdp->sd_hash_bsize, - sdp->sd_hash_bsize, 1); - if (error != sdp->sd_hash_bsize) { - if (error >= 0) - error = -EIO; - goto fail; - } - - from = buf; - to = (u64 *)((char *)buf + sdp->sd_hash_bsize); - - for (x = sdp->sd_hash_ptrs; x--; from++) { - *to++ = *from; /* No endianess worries */ - *to++ = *from; - } + error = gfs2_meta_inode_buffer(dip, &dibh); + if (error) + goto out_kfree; - error = gfs2_dir_write_data(dip, - (char *)buf + sdp->sd_hash_bsize, - block * sdp->sd_sb.sb_bsize, - sdp->sd_sb.sb_bsize); - if (error != sdp->sd_sb.sb_bsize) { - if (error >= 0) - error = -EIO; - goto fail; - } + for (x = 0; x < hsize; x++) { + *h++ = *hc; + *h++ = *hc; + hc++; } - kfree(buf); - - error = gfs2_meta_inode_buffer(dip, &dibh); - if (!gfs2_assert_withdraw(sdp, !error)) { - dip->i_depth++; - gfs2_dinode_out(dip, dibh->b_data); - brelse(dibh); - } + error = gfs2_dir_write_data(dip, (char *)hc2, 0, hsize_bytes * 2); + if (error != (hsize_bytes * 2)) + goto fail; - return error; + gfs2_dir_hash_inval(dip); + dip->i_hash_cache = hc2; + dip->i_depth++; + gfs2_dinode_out(dip, dibh->b_data); + brelse(dibh); + return 0; fail: - kfree(buf); + /* Replace original hash table & size */ + gfs2_dir_write_data(dip, (char *)hc, 0, hsize_bytes); + i_size_write(&dip->i_inode, hsize_bytes); + gfs2_dinode_out(dip, dibh->b_data); + brelse(dibh); +out_kfree: + kfree(hc2); return error; } @@ -1348,6 +1390,7 @@ out: return error; } + /** * dir_e_read - Reads the entries from a directory into a filldir buffer * @dip: dinode pointer @@ -1362,9 +1405,7 @@ static int dir_e_read(struct inode *inode, u64 *offset, void *opaque, filldir_t filldir) { struct gfs2_inode *dip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); u32 hsize, len = 0; - u32 ht_offset, lp_offset, ht_offset_cur = -1; u32 hash, index; __be64 *lp; int copied = 0; @@ -1372,37 +1413,17 @@ static int dir_e_read(struct inode *inode, u64 *offset, void *opaque, unsigned depth = 0; hsize = 1 << dip->i_depth; - if (hsize * sizeof(u64) != i_size_read(inode)) { - gfs2_consist_inode(dip); - return -EIO; - } - hash = gfs2_dir_offset2hash(*offset); index = hash >> (32 - dip->i_depth); - lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS); - if (!lp) - return -ENOMEM; + lp = gfs2_dir_get_hash_table(dip); + if (IS_ERR(lp)) + return PTR_ERR(lp); while (index < hsize) { - lp_offset = index & (sdp->sd_hash_ptrs - 1); - ht_offset = index - lp_offset; - - if (ht_offset_cur != ht_offset) { - error = gfs2_dir_read_data(dip, (char *)lp, - ht_offset * sizeof(__be64), - sdp->sd_hash_bsize, 1); - if (error != sdp->sd_hash_bsize) { - if (error >= 0) - error = -EIO; - goto out; - } - ht_offset_cur = ht_offset; - } - error = gfs2_dir_read_leaf(inode, offset, opaque, filldir, &copied, &depth, - be64_to_cpu(lp[lp_offset])); + be64_to_cpu(lp[index])); if (error) break; @@ -1410,8 +1431,6 @@ static int dir_e_read(struct inode *inode, u64 *offset, void *opaque, index = (index & ~(len - 1)) + len; } -out: - kfree(lp); if (error > 0) error = 0; return error; @@ -1914,43 +1933,22 @@ out: int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip) { - struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode); struct buffer_head *bh; struct gfs2_leaf *leaf; u32 hsize, len; - u32 ht_offset, lp_offset, ht_offset_cur = -1; u32 index = 0, next_index; __be64 *lp; u64 leaf_no; int error = 0, last; hsize = 1 << dip->i_depth; - if (hsize * sizeof(u64) != i_size_read(&dip->i_inode)) { - gfs2_consist_inode(dip); - return -EIO; - } - lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS); - if (!lp) - return -ENOMEM; + lp = gfs2_dir_get_hash_table(dip); + if (IS_ERR(lp)) + return PTR_ERR(lp); while (index < hsize) { - lp_offset = index & (sdp->sd_hash_ptrs - 1); - ht_offset = index - lp_offset; - - if (ht_offset_cur != ht_offset) { - error = gfs2_dir_read_data(dip, (char *)lp, - ht_offset * sizeof(__be64), - sdp->sd_hash_bsize, 1); - if (error != sdp->sd_hash_bsize) { - if (error >= 0) - error = -EIO; - goto out; - } - ht_offset_cur = ht_offset; - } - - leaf_no = be64_to_cpu(lp[lp_offset]); + leaf_no = be64_to_cpu(lp[index]); if (leaf_no) { error = get_leaf(dip, leaf_no, &bh); if (error) @@ -1976,7 +1974,6 @@ int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip) } out: - kfree(lp); return error; } diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h index e686af1..ff5772f 100644 --- a/fs/gfs2/dir.h +++ b/fs/gfs2/dir.h @@ -35,6 +35,7 @@ extern int gfs2_diradd_alloc_required(struct inode *dir, const struct qstr *filename); extern int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block, struct buffer_head **bhp); +extern void gfs2_dir_hash_inval(struct gfs2_inode *ip); static inline u32 gfs2_disk_hash(const char *data, int len) { diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index a9f5cbe..bc2590e 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -174,7 +174,9 @@ void gfs2_set_inode_flags(struct inode *inode) struct gfs2_inode *ip = GFS2_I(inode); unsigned int flags = inode->i_flags; - flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_NOSEC); + if ((ip->i_eattr == 0) && !is_sxid(inode->i_mode)) + inode->i_flags |= S_NOSEC; if (ip->i_diskflags & GFS2_DIF_IMMUTABLE) flags |= S_IMMUTABLE; if (ip->i_diskflags & GFS2_DIF_APPENDONLY) diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 1c1336e..88e8a23 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -409,6 +409,10 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state) if (held1 && held2 && list_empty(&gl->gl_holders)) clear_bit(GLF_QUEUED, &gl->gl_flags); + if (new_state != gl->gl_target) + /* shorten our minimum hold time */ + gl->gl_hold_time = max(gl->gl_hold_time - GL_GLOCK_HOLD_DECR, + GL_GLOCK_MIN_HOLD); gl->gl_state = new_state; gl->gl_tchange = jiffies; } @@ -668,7 +672,7 @@ static void glock_work_func(struct work_struct *work) gl->gl_demote_state != LM_ST_EXCLUSIVE) { unsigned long holdtime, now = jiffies; - holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time; + holdtime = gl->gl_tchange + gl->gl_hold_time; if (time_before(now, holdtime)) delay = holdtime - now; @@ -679,9 +683,14 @@ static void glock_work_func(struct work_struct *work) } run_queue(gl, 0); spin_unlock(&gl->gl_spin); - if (!delay || - queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) + if (!delay) gfs2_glock_put(gl); + else { + if (gl->gl_name.ln_type != LM_TYPE_INODE) + delay = 0; + if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) + gfs2_glock_put(gl); + } if (drop_ref) gfs2_glock_put(gl); } @@ -743,6 +752,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_tchange = jiffies; gl->gl_object = NULL; gl->gl_sbd = sdp; + gl->gl_hold_time = GL_GLOCK_DFT_HOLD; INIT_DELAYED_WORK(&gl->gl_work, glock_work_func); INIT_WORK(&gl->gl_delete, delete_work_func); @@ -855,8 +865,15 @@ static int gfs2_glock_demote_wait(void *word) static void wait_on_holder(struct gfs2_holder *gh) { + unsigned long time1 = jiffies; + might_sleep(); wait_on_bit(&gh->gh_iflags, HIF_WAIT, gfs2_glock_holder_wait, TASK_UNINTERRUPTIBLE); + if (time_after(jiffies, time1 + HZ)) /* have we waited > a second? */ + /* Lengthen the minimum hold time. */ + gh->gh_gl->gl_hold_time = min(gh->gh_gl->gl_hold_time + + GL_GLOCK_HOLD_INCR, + GL_GLOCK_MAX_HOLD); } static void wait_on_demote(struct gfs2_glock *gl) @@ -1093,8 +1110,9 @@ void gfs2_glock_dq(struct gfs2_holder *gh) gfs2_glock_hold(gl); if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && - !test_bit(GLF_DEMOTE, &gl->gl_flags)) - delay = gl->gl_ops->go_min_hold_time; + !test_bit(GLF_DEMOTE, &gl->gl_flags) && + gl->gl_name.ln_type == LM_TYPE_INODE) + delay = gl->gl_hold_time; if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) gfs2_glock_put(gl); } @@ -1273,12 +1291,13 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) unsigned long now = jiffies; gfs2_glock_hold(gl); - holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time; - if (test_bit(GLF_QUEUED, &gl->gl_flags)) { + holdtime = gl->gl_tchange + gl->gl_hold_time; + if (test_bit(GLF_QUEUED, &gl->gl_flags) && + gl->gl_name.ln_type == LM_TYPE_INODE) { if (time_before(now, holdtime)) delay = holdtime - now; if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags)) - delay = gl->gl_ops->go_min_hold_time; + delay = gl->gl_hold_time; } spin_lock(&gl->gl_spin); @@ -1667,7 +1686,7 @@ static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl) dtime *= 1000000/HZ; /* demote time in uSec */ if (!test_bit(GLF_DEMOTE, &gl->gl_flags)) dtime = 0; - gfs2_print_dbg(seq, "G: s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d v:%d r:%d\n", + gfs2_print_dbg(seq, "G: s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d v:%d r:%d m:%ld\n", state2str(gl->gl_state), gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, @@ -1676,7 +1695,7 @@ static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl) state2str(gl->gl_demote_state), dtime, atomic_read(&gl->gl_ail_count), atomic_read(&gl->gl_revokes), - atomic_read(&gl->gl_ref)); + atomic_read(&gl->gl_ref), gl->gl_hold_time); list_for_each_entry(gh, &gl->gl_holders, gh_list) { error = dump_holder(seq, gh); diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 6b2f757..6670711 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -113,6 +113,12 @@ enum { #define GLR_TRYFAILED 13 +#define GL_GLOCK_MAX_HOLD (long)(HZ / 5) +#define GL_GLOCK_DFT_HOLD (long)(HZ / 5) +#define GL_GLOCK_MIN_HOLD (long)(10) +#define GL_GLOCK_HOLD_INCR (long)(HZ / 20) +#define GL_GLOCK_HOLD_DECR (long)(HZ / 40) + struct lm_lockops { const char *lm_proto_name; int (*lm_mount) (struct gfs2_sbd *sdp, const char *fsname); diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 8ef70f4..da21eca 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -26,6 +26,7 @@ #include "rgrp.h" #include "util.h" #include "trans.h" +#include "dir.h" /** * __gfs2_ail_flush - remove all buffers for a given lock from the AIL @@ -47,10 +48,10 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl) bd_ail_gl_list); bh = bd->bd_bh; gfs2_remove_from_ail(bd); - spin_unlock(&sdp->sd_ail_lock); - bd->bd_bh = NULL; bh->b_private = NULL; + spin_unlock(&sdp->sd_ail_lock); + bd->bd_blkno = bh->b_blocknr; gfs2_log_lock(sdp); gfs2_assert_withdraw(sdp, !buffer_busy(bh)); @@ -218,11 +219,14 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) if (ip) { set_bit(GIF_INVALID, &ip->i_flags); forget_all_cached_acls(&ip->i_inode); + gfs2_dir_hash_inval(ip); } } - if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) + if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) { + gfs2_log_flush(gl->gl_sbd, NULL); gl->gl_sbd->sd_rindex_uptodate = 0; + } if (ip && S_ISREG(ip->i_inode.i_mode)) truncate_inode_pages(ip->i_inode.i_mapping, 0); } @@ -314,6 +318,8 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) ip->i_generation = be64_to_cpu(str->di_generation); ip->i_diskflags = be32_to_cpu(str->di_flags); + ip->i_eattr = be64_to_cpu(str->di_eattr); + /* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */ gfs2_set_inode_flags(&ip->i_inode); height = be16_to_cpu(str->di_height); if (unlikely(height > GFS2_MAX_META_HEIGHT)) @@ -326,7 +332,6 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) ip->i_depth = (u8)depth; ip->i_entries = be32_to_cpu(str->di_entries); - ip->i_eattr = be64_to_cpu(str->di_eattr); if (S_ISREG(ip->i_inode.i_mode)) gfs2_set_aops(&ip->i_inode); @@ -547,7 +552,6 @@ const struct gfs2_glock_operations gfs2_inode_glops = { .go_lock = inode_go_lock, .go_dump = inode_go_dump, .go_type = LM_TYPE_INODE, - .go_min_hold_time = HZ / 5, .go_flags = GLOF_ASPACE, }; @@ -558,7 +562,6 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_unlock = rgrp_go_unlock, .go_dump = gfs2_rgrp_dump, .go_type = LM_TYPE_RGRP, - .go_min_hold_time = HZ / 5, .go_flags = GLOF_ASPACE, }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 0a064e9..892ac37 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -17,6 +17,7 @@ #include <linux/buffer_head.h> #include <linux/rcupdate.h> #include <linux/rculist_bl.h> +#include <linux/completion.h> #define DIO_WAIT 0x00000010 #define DIO_METADATA 0x00000020 @@ -162,7 +163,6 @@ struct gfs2_glock_operations { int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl); void (*go_callback) (struct gfs2_glock *gl); const int go_type; - const unsigned long go_min_hold_time; const unsigned long go_flags; #define GLOF_ASPACE 1 }; @@ -220,6 +220,7 @@ struct gfs2_glock { unsigned int gl_hash; unsigned long gl_demote_time; /* time of first demote request */ + long gl_hold_time; struct list_head gl_holders; const struct gfs2_glock_operations *gl_ops; @@ -284,6 +285,7 @@ struct gfs2_inode { u64 i_goal; /* goal block for allocations */ struct rw_semaphore i_rw_mutex; struct list_head i_trunc_list; + __be64 *i_hash_cache; u32 i_entries; u32 i_diskflags; u8 i_height; @@ -546,6 +548,7 @@ struct gfs2_sbd { struct gfs2_glock *sd_trans_gl; wait_queue_head_t sd_glock_wait; atomic_t sd_glock_disposal; + struct completion sd_locking_init; /* Inode Stuff */ diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 903115f..85c6292 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -903,6 +903,7 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp) if (gfs2_ail1_empty(sdp)) break; } + gfs2_log_flush(sdp, NULL); } static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index c2b34cd..29e1ace 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -41,6 +41,7 @@ static void gfs2_init_inode_once(void *foo) init_rwsem(&ip->i_rw_mutex); INIT_LIST_HEAD(&ip->i_trunc_list); ip->i_alloc = NULL; + ip->i_hash_cache = NULL; } static void gfs2_init_glock_once(void *foo) diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 8ac9ae1..516516e 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -72,6 +72,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) init_waitqueue_head(&sdp->sd_glock_wait); atomic_set(&sdp->sd_glock_disposal, 0); + init_completion(&sdp->sd_locking_init); spin_lock_init(&sdp->sd_statfs_spin); spin_lock_init(&sdp->sd_rindex_spin); @@ -1017,11 +1018,13 @@ hostdata_error: fsname++; if (lm->lm_mount == NULL) { fs_info(sdp, "Now mounting FS...\n"); + complete(&sdp->sd_locking_init); return 0; } ret = lm->lm_mount(sdp, fsname); if (ret == 0) fs_info(sdp, "Joined cluster. Now mounting FS...\n"); + complete(&sdp->sd_locking_init); return ret; } @@ -1091,6 +1094,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent if (sdp->sd_args.ar_nobarrier) set_bit(SDF_NOBARRIERS, &sdp->sd_flags); + sb->s_flags |= MS_NOSEC; sb->s_magic = GFS2_MAGIC; sb->s_op = &gfs2_super_ops; sb->s_d_op = &gfs2_dops; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 9b780df..7f8af1e 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1607,14 +1607,15 @@ rgrp_error: } /** - * gfs2_free_data - free a contiguous run of data block(s) + * __gfs2_free_blocks - free a contiguous run of block(s) * @ip: the inode these blocks are being freed from * @bstart: first block of a run of contiguous blocks * @blen: the length of the block run + * @meta: 1 if the blocks represent metadata * */ -void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen) +void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *rgd; @@ -1631,54 +1632,11 @@ void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen) gfs2_trans_add_rg(rgd); /* Directories keep their data in the metadata address space */ - if (ip->i_depth) + if (meta || ip->i_depth) gfs2_meta_wipe(ip, bstart, blen); } /** - * gfs2_free_data - free a contiguous run of data block(s) - * @ip: the inode these blocks are being freed from - * @bstart: first block of a run of contiguous blocks - * @blen: the length of the block run - * - */ - -void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - - __gfs2_free_data(ip, bstart, blen); - gfs2_statfs_change(sdp, 0, +blen, 0); - gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid); -} - -/** - * gfs2_free_meta - free a contiguous run of data block(s) - * @ip: the inode these blocks are being freed from - * @bstart: first block of a run of contiguous blocks - * @blen: the length of the block run - * - */ - -void __gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen) -{ - struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct gfs2_rgrpd *rgd; - - rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE); - if (!rgd) - return; - trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE); - rgd->rd_free += blen; - - gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); - gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); - - gfs2_trans_add_rg(rgd); - gfs2_meta_wipe(ip, bstart, blen); -} - -/** * gfs2_free_meta - free a contiguous run of data block(s) * @ip: the inode these blocks are being freed from * @bstart: first block of a run of contiguous blocks @@ -1690,7 +1648,7 @@ void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - __gfs2_free_meta(ip, bstart, blen); + __gfs2_free_blocks(ip, bstart, blen, 1); gfs2_statfs_change(sdp, 0, +blen, 0); gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid); } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index a80e303..d253f9a 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -52,9 +52,7 @@ extern int gfs2_ri_update(struct gfs2_inode *ip); extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n); extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation); -extern void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen); -extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen); -extern void __gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); +extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta); extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen); extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip); extern void gfs2_unlink_di(struct inode *inode); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index ed540e7..b7beadd 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -757,13 +757,17 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc) struct timespec atime; struct gfs2_dinode *di; int ret = -EAGAIN; + int unlock_required = 0; /* Skip timestamp update, if this is from a memalloc */ if (current->flags & PF_MEMALLOC) goto do_flush; - ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - if (ret) - goto do_flush; + if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { + ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); + if (ret) + goto do_flush; + unlock_required = 1; + } ret = gfs2_trans_begin(sdp, RES_DINODE, 0); if (ret) goto do_unlock; @@ -780,7 +784,8 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc) } gfs2_trans_end(sdp); do_unlock: - gfs2_glock_dq_uninit(&gh); + if (unlock_required) + gfs2_glock_dq_uninit(&gh); do_flush: if (wbc->sync_mode == WB_SYNC_ALL) gfs2_log_flush(GFS2_SB(inode), ip->i_gl); @@ -1427,7 +1432,20 @@ out: return error; } -/* +/** + * gfs2_evict_inode - Remove an inode from cache + * @inode: The inode to evict + * + * There are three cases to consider: + * 1. i_nlink == 0, we are final opener (and must deallocate) + * 2. i_nlink == 0, we are not the final opener (and cannot deallocate) + * 3. i_nlink > 0 + * + * If the fs is read only, then we have to treat all cases as per #3 + * since we are unable to do any deallocation. The inode will be + * deallocated by the next read/write node to attempt an allocation + * in the same resource group + * * We have to (at the moment) hold the inodes main lock to cover * the gap between unlocking the shared lock on the iopen lock and * taking the exclusive lock. I'd rather do a shared -> exclusive @@ -1470,6 +1488,8 @@ static void gfs2_evict_inode(struct inode *inode) if (error) goto out_truncate; + /* Case 1 starts here */ + if (S_ISDIR(inode->i_mode) && (ip->i_diskflags & GFS2_DIF_EXHASH)) { error = gfs2_dir_exhash_dealloc(ip); @@ -1493,13 +1513,16 @@ static void gfs2_evict_inode(struct inode *inode) goto out_unlock; out_truncate: + /* Case 2 starts here */ error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); if (error) goto out_unlock; - gfs2_final_release_pages(ip); + /* Needs to be done before glock release & also in a transaction */ + truncate_inode_pages(&inode->i_data, 0); gfs2_trans_end(sdp); out_unlock: + /* Error path for case 1 */ if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) gfs2_glock_dq(&ip->i_iopen_gh); gfs2_holder_uninit(&ip->i_iopen_gh); @@ -1507,9 +1530,10 @@ out_unlock: if (error && error != GLR_TRYFAILED && error != -EROFS) fs_warn(sdp, "gfs2_evict_inode: %d\n", error); out: + /* Case 3 starts here */ truncate_inode_pages(&inode->i_data, 0); end_writeback(inode); - + gfs2_dir_hash_inval(ip); ip->i_gl->gl_object = NULL; gfs2_glock_add_to_lru(ip->i_gl); gfs2_glock_put(ip->i_gl); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index e20eab3..443cabc 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -338,6 +338,9 @@ static ssize_t lkfirst_store(struct gfs2_sbd *sdp, const char *buf, size_t len) rv = sscanf(buf, "%u", &first); if (rv != 1 || first > 1) return -EINVAL; + rv = wait_for_completion_killable(&sdp->sd_locking_init); + if (rv) + return rv; spin_lock(&sdp->sd_jindex_spin); rv = -EBUSY; if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0) @@ -414,7 +417,9 @@ static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len) rv = sscanf(buf, "%d", &jid); if (rv != 1) return -EINVAL; - + rv = wait_for_completion_killable(&sdp->sd_locking_init); + if (rv) + return rv; spin_lock(&sdp->sd_jindex_spin); rv = -EINVAL; if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 2312de3..2a734cf 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -43,6 +43,10 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec) node->tree->node_size - (rec + 1) * 2); if (!recoff) return 0; + if (recoff > node->tree->node_size - 2) { + printk(KERN_ERR "hfs: recoff %d too large\n", recoff); + return 0; + } retval = hfs_bnode_read_u16(node, recoff) + 2; if (retval > node->tree->max_key_len + 2) { diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index b4ba1b3..4dfbfec 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -212,7 +212,9 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir, dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink); - hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + if (err) + return err; hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL); entry_size = hfsplus_fill_cat_thread(sb, &entry, @@ -269,7 +271,9 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str) dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid); - hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + if (err) + return err; if (!str) { int len; @@ -347,12 +351,14 @@ int hfsplus_rename_cat(u32 cnid, struct hfs_find_data src_fd, dst_fd; hfsplus_cat_entry entry; int entry_size, type; - int err = 0; + int err; dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name, dst_dir->i_ino, dst_name->name); - hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd); + err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd); + if (err) + return err; dst_fd = src_fd; /* find the old dir entry and read the data */ diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 4df5059..25b2443 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -38,7 +38,9 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry, sb = dir->i_sb; dentry->d_fsdata = NULL; - hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + if (err) + return ERR_PTR(err); hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name); again: err = hfs_brec_read(&fd, &entry, sizeof(entry)); @@ -132,7 +134,9 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) if (filp->f_pos >= inode->i_size) return 0; - hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + if (err) + return err; hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL); err = hfs_brec_find(&fd); if (err) diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index b1991a2..5849e3e 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -119,22 +119,31 @@ static void __hfsplus_ext_write_extent(struct inode *inode, set_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags); } -static void hfsplus_ext_write_extent_locked(struct inode *inode) +static int hfsplus_ext_write_extent_locked(struct inode *inode) { + int res; + if (HFSPLUS_I(inode)->extent_state & HFSPLUS_EXT_DIRTY) { struct hfs_find_data fd; - hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); + if (res) + return res; __hfsplus_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } + return 0; } -void hfsplus_ext_write_extent(struct inode *inode) +int hfsplus_ext_write_extent(struct inode *inode) { + int res; + mutex_lock(&HFSPLUS_I(inode)->extents_lock); - hfsplus_ext_write_extent_locked(inode); + res = hfsplus_ext_write_extent_locked(inode); mutex_unlock(&HFSPLUS_I(inode)->extents_lock); + + return res; } static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd, @@ -194,9 +203,11 @@ static int hfsplus_ext_read_extent(struct inode *inode, u32 block) block < hip->cached_start + hip->cached_blocks) return 0; - hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); - res = __hfsplus_ext_cache_extent(&fd, inode, block); - hfs_find_exit(&fd); + res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); + if (!res) { + res = __hfsplus_ext_cache_extent(&fd, inode, block); + hfs_find_exit(&fd); + } return res; } @@ -209,6 +220,7 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res = -EIO; u32 ablock, dblock, mask; + sector_t sector; int was_dirty = 0; int shift; @@ -255,10 +267,12 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock, done: dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock); + mask = (1 << sbi->fs_shift) - 1; - map_bh(bh_result, sb, - (dblock << sbi->fs_shift) + sbi->blockoffset + - (iblock & mask)); + sector = ((sector_t)dblock << sbi->fs_shift) + + sbi->blockoffset + (iblock & mask); + map_bh(bh_result, sb, sector); + if (create) { set_buffer_new(bh_result); hip->phys_size += sb->s_blocksize; @@ -371,7 +385,9 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid, if (total_blocks == blocks) return 0; - hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); + res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); + if (res) + return res; do { res = __hfsplus_ext_read_extent(&fd, ext_entry, cnid, total_blocks, type); @@ -469,7 +485,9 @@ out: insert_extent: dprint(DBG_EXTENT, "insert new extent\n"); - hfsplus_ext_write_extent_locked(inode); + res = hfsplus_ext_write_extent_locked(inode); + if (res) + goto out; memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec)); hip->cached_extents[0].start_block = cpu_to_be32(start); @@ -500,7 +518,6 @@ void hfsplus_file_truncate(struct inode *inode) struct page *page; void *fsdata; u32 size = inode->i_size; - int res; res = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_UNINTERRUPTIBLE, @@ -523,7 +540,12 @@ void hfsplus_file_truncate(struct inode *inode) goto out; mutex_lock(&hip->extents_lock); - hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); + res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); + if (res) { + mutex_unlock(&hip->extents_lock); + /* XXX: We lack error handling of hfsplus_file_truncate() */ + return; + } while (1) { if (alloc_cnt == hip->first_blocks) { hfsplus_free_extents(sb, hip->first_extents, diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h index d685752..81dfd1e 100644 --- a/fs/hfsplus/hfsplus_fs.h +++ b/fs/hfsplus/hfsplus_fs.h @@ -13,6 +13,7 @@ #include <linux/fs.h> #include <linux/mutex.h> #include <linux/buffer_head.h> +#include <linux/blkdev.h> #include "hfsplus_raw.h" #define DBG_BNODE_REFS 0x00000001 @@ -110,7 +111,9 @@ struct hfsplus_vh; struct hfs_btree; struct hfsplus_sb_info { + void *s_vhdr_buf; struct hfsplus_vh *s_vhdr; + void *s_backup_vhdr_buf; struct hfsplus_vh *s_backup_vhdr; struct hfs_btree *ext_tree; struct hfs_btree *cat_tree; @@ -258,6 +261,15 @@ struct hfsplus_readdir_data { struct hfsplus_cat_key key; }; +/* + * Find minimum acceptible I/O size for an hfsplus sb. + */ +static inline unsigned short hfsplus_min_io_size(struct super_block *sb) +{ + return max_t(unsigned short, bdev_logical_block_size(sb->s_bdev), + HFSPLUS_SECTOR_SIZE); +} + #define hfs_btree_open hfsplus_btree_open #define hfs_btree_close hfsplus_btree_close #define hfs_btree_write hfsplus_btree_write @@ -374,7 +386,7 @@ extern const struct file_operations hfsplus_dir_operations; /* extents.c */ int hfsplus_ext_cmp_key(const hfsplus_btree_key *, const hfsplus_btree_key *); -void hfsplus_ext_write_extent(struct inode *); +int hfsplus_ext_write_extent(struct inode *); int hfsplus_get_block(struct inode *, sector_t, struct buffer_head *, int); int hfsplus_free_fork(struct super_block *, u32, struct hfsplus_fork_raw *, int); @@ -436,8 +448,8 @@ int hfsplus_compare_dentry(const struct dentry *parent, /* wrapper.c */ int hfsplus_read_wrapper(struct super_block *); int hfs_part_find(struct super_block *, sector_t *, sector_t *); -int hfsplus_submit_bio(struct block_device *bdev, sector_t sector, - void *data, int rw); +int hfsplus_submit_bio(struct super_block *sb, sector_t sector, + void *buf, void **data, int rw); /* time macros */ #define __hfsp_mt2ut(t) (be32_to_cpu(t) - 2082844800U) diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b248a6cf..010cd36 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -195,11 +195,13 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, hip->flags = 0; set_bit(HFSPLUS_I_RSRC, &hip->flags); - hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); - err = hfsplus_find_cat(sb, dir->i_ino, &fd); - if (!err) - err = hfsplus_cat_read_inode(inode, &fd); - hfs_find_exit(&fd); + err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd); + if (!err) { + err = hfsplus_find_cat(sb, dir->i_ino, &fd); + if (!err) + err = hfsplus_cat_read_inode(inode, &fd); + hfs_find_exit(&fd); + } if (err) { iput(inode); return ERR_PTR(err); diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c index 40ad88c..eb355d8 100644 --- a/fs/hfsplus/part_tbl.c +++ b/fs/hfsplus/part_tbl.c @@ -88,11 +88,12 @@ static int hfs_parse_old_pmap(struct super_block *sb, struct old_pmap *pm, return -ENOENT; } -static int hfs_parse_new_pmap(struct super_block *sb, struct new_pmap *pm, - sector_t *part_start, sector_t *part_size) +static int hfs_parse_new_pmap(struct super_block *sb, void *buf, + struct new_pmap *pm, sector_t *part_start, sector_t *part_size) { struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); int size = be32_to_cpu(pm->pmMapBlkCnt); + int buf_size = hfsplus_min_io_size(sb); int res; int i = 0; @@ -107,11 +108,14 @@ static int hfs_parse_new_pmap(struct super_block *sb, struct new_pmap *pm, if (++i >= size) return -ENOENT; - res = hfsplus_submit_bio(sb->s_bdev, - *part_start + HFS_PMAP_BLK + i, - pm, READ); - if (res) - return res; + pm = (struct new_pmap *)((u8 *)pm + HFSPLUS_SECTOR_SIZE); + if ((u8 *)pm - (u8 *)buf >= buf_size) { + res = hfsplus_submit_bio(sb, + *part_start + HFS_PMAP_BLK + i, + buf, (void **)&pm, READ); + if (res) + return res; + } } while (pm->pmSig == cpu_to_be16(HFS_NEW_PMAP_MAGIC)); return -ENOENT; @@ -124,15 +128,15 @@ static int hfs_parse_new_pmap(struct super_block *sb, struct new_pmap *pm, int hfs_part_find(struct super_block *sb, sector_t *part_start, sector_t *part_size) { - void *data; + void *buf, *data; int res; - data = kmalloc(HFSPLUS_SECTOR_SIZE, GFP_KERNEL); - if (!data) + buf = kmalloc(hfsplus_min_io_size(sb), GFP_KERNEL); + if (!buf) return -ENOMEM; - res = hfsplus_submit_bio(sb->s_bdev, *part_start + HFS_PMAP_BLK, - data, READ); + res = hfsplus_submit_bio(sb, *part_start + HFS_PMAP_BLK, + buf, &data, READ); if (res) goto out; @@ -141,13 +145,13 @@ int hfs_part_find(struct super_block *sb, res = hfs_parse_old_pmap(sb, data, part_start, part_size); break; case HFS_NEW_PMAP_MAGIC: - res = hfs_parse_new_pmap(sb, data, part_start, part_size); + res = hfs_parse_new_pmap(sb, buf, data, part_start, part_size); break; default: res = -ENOENT; break; } out: - kfree(data); + kfree(buf); return res; } diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index b49b555..c106ca2 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -73,11 +73,13 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino) if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID || inode->i_ino == HFSPLUS_ROOT_CNID) { - hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); - err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); - if (!err) - err = hfsplus_cat_read_inode(inode, &fd); - hfs_find_exit(&fd); + err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd); + if (!err) { + err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd); + if (!err) + err = hfsplus_cat_read_inode(inode, &fd); + hfs_find_exit(&fd); + } } else { err = hfsplus_system_read_inode(inode); } @@ -133,9 +135,13 @@ static int hfsplus_system_write_inode(struct inode *inode) static int hfsplus_write_inode(struct inode *inode, struct writeback_control *wbc) { + int err; + dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino); - hfsplus_ext_write_extent(inode); + err = hfsplus_ext_write_extent(inode); + if (err) + return err; if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID || inode->i_ino == HFSPLUS_ROOT_CNID) @@ -197,17 +203,17 @@ int hfsplus_sync_fs(struct super_block *sb, int wait) write_backup = 1; } - error2 = hfsplus_submit_bio(sb->s_bdev, + error2 = hfsplus_submit_bio(sb, sbi->part_start + HFSPLUS_VOLHEAD_SECTOR, - sbi->s_vhdr, WRITE_SYNC); + sbi->s_vhdr_buf, NULL, WRITE_SYNC); if (!error) error = error2; if (!write_backup) goto out; - error2 = hfsplus_submit_bio(sb->s_bdev, + error2 = hfsplus_submit_bio(sb, sbi->part_start + sbi->sect_count - 2, - sbi->s_backup_vhdr, WRITE_SYNC); + sbi->s_backup_vhdr_buf, NULL, WRITE_SYNC); if (!error) error2 = error; out: @@ -251,8 +257,8 @@ static void hfsplus_put_super(struct super_block *sb) hfs_btree_close(sbi->ext_tree); iput(sbi->alloc_file); iput(sbi->hidden_dir); - kfree(sbi->s_vhdr); - kfree(sbi->s_backup_vhdr); + kfree(sbi->s_vhdr_buf); + kfree(sbi->s_backup_vhdr_buf); unload_nls(sbi->nls); kfree(sb->s_fs_info); sb->s_fs_info = NULL; @@ -393,6 +399,13 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) if (!sbi->rsrc_clump_blocks) sbi->rsrc_clump_blocks = 1; + err = generic_check_addressable(sbi->alloc_blksz_shift, + sbi->total_blocks); + if (err) { + printk(KERN_ERR "hfs: filesystem size too large.\n"); + goto out_free_vhdr; + } + /* Set up operations so we can load metadata */ sb->s_op = &hfsplus_sops; sb->s_maxbytes = MAX_LFS_FILESIZE; @@ -417,6 +430,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= MS_RDONLY; } + err = -EINVAL; + /* Load metadata objects (B*Trees) */ sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID); if (!sbi->ext_tree) { @@ -447,7 +462,9 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1; str.name = HFSP_HIDDENDIR_NAME; - hfs_find_init(sbi->cat_tree, &fd); + err = hfs_find_init(sbi->cat_tree, &fd); + if (err) + goto out_put_root; hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str); if (!hfs_brec_read(&fd, &entry, sizeof(entry))) { hfs_find_exit(&fd); @@ -500,7 +517,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) out_put_hidden_dir: iput(sbi->hidden_dir); out_put_root: - iput(sbi->alloc_file); + iput(root); out_put_alloc_file: iput(sbi->alloc_file); out_close_cat_tree: diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c index a3f0bfc..a32998f 100644 --- a/fs/hfsplus/unicode.c +++ b/fs/hfsplus/unicode.c @@ -142,7 +142,11 @@ int hfsplus_uni2asc(struct super_block *sb, /* search for single decomposed char */ if (likely(compose)) ce1 = hfsplus_compose_lookup(hfsplus_compose_table, c0); - if (ce1 && (cc = ce1[0])) { + if (ce1) + cc = ce1[0]; + else + cc = 0; + if (cc) { /* start of a possibly decomposed Hangul char */ if (cc != 0xffff) goto done; @@ -209,7 +213,8 @@ int hfsplus_uni2asc(struct super_block *sb, i++; ce2 = ce1; } - if ((cc = ce2[0])) { + cc = ce2[0]; + if (cc) { ip += i; ustrlen -= i; goto done; @@ -301,7 +306,11 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr, while (outlen < HFSPLUS_MAX_STRLEN && len > 0) { size = asc2unichar(sb, astr, len, &c); - if (decompose && (dstr = decompose_unichar(c, &dsize))) { + if (decompose) + dstr = decompose_unichar(c, &dsize); + else + dstr = NULL; + if (dstr) { if (outlen + dsize > HFSPLUS_MAX_STRLEN) break; do { @@ -346,15 +355,23 @@ int hfsplus_hash_dentry(const struct dentry *dentry, const struct inode *inode, astr += size; len -= size; - if (decompose && (dstr = decompose_unichar(c, &dsize))) { + if (decompose) + dstr = decompose_unichar(c, &dsize); + else + dstr = NULL; + if (dstr) { do { c2 = *dstr++; - if (!casefold || (c2 = case_fold(c2))) + if (casefold) + c2 = case_fold(c2); + if (!casefold || c2) hash = partial_name_hash(c2, hash); } while (--dsize > 0); } else { c2 = c; - if (!casefold || (c2 = case_fold(c2))) + if (casefold) + c2 = case_fold(c2); + if (!casefold || c2) hash = partial_name_hash(c2, hash); } } @@ -422,12 +439,14 @@ int hfsplus_compare_dentry(const struct dentry *parent, c1 = *dstr1; c2 = *dstr2; if (casefold) { - if (!(c1 = case_fold(c1))) { + c1 = case_fold(c1); + if (!c1) { dstr1++; dsize1--; continue; } - if (!(c2 = case_fold(c2))) { + c2 = case_fold(c2); + if (!c2) { dstr2++; dsize2--; continue; diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 3031d81..10e515a 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -31,31 +31,77 @@ static void hfsplus_end_io_sync(struct bio *bio, int err) complete(bio->bi_private); } -int hfsplus_submit_bio(struct block_device *bdev, sector_t sector, - void *data, int rw) +/* + * hfsplus_submit_bio - Perfrom block I/O + * @sb: super block of volume for I/O + * @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes + * @buf: buffer for I/O + * @data: output pointer for location of requested data + * @rw: direction of I/O + * + * The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than + * HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads + * @data will return a pointer to the start of the requested sector, + * which may not be the same location as @buf. + * + * If @sector is not aligned to the bdev logical block size it will + * be rounded down. For writes this means that @buf should contain data + * that starts at the rounded-down address. As long as the data was + * read using hfsplus_submit_bio() and the same buffer is used things + * will work correctly. + */ +int hfsplus_submit_bio(struct super_block *sb, sector_t sector, + void *buf, void **data, int rw) { DECLARE_COMPLETION_ONSTACK(wait); struct bio *bio; + int ret = 0; + unsigned int io_size; + loff_t start; + int offset; + + /* + * Align sector to hardware sector size and find offset. We + * assume that io_size is a power of two, which _should_ + * be true. + */ + io_size = hfsplus_min_io_size(sb); + start = (loff_t)sector << HFSPLUS_SECTOR_SHIFT; + offset = start & (io_size - 1); + sector &= ~((io_size >> HFSPLUS_SECTOR_SHIFT) - 1); bio = bio_alloc(GFP_NOIO, 1); bio->bi_sector = sector; - bio->bi_bdev = bdev; + bio->bi_bdev = sb->s_bdev; bio->bi_end_io = hfsplus_end_io_sync; bio->bi_private = &wait; - /* - * We always submit one sector at a time, so bio_add_page must not fail. - */ - if (bio_add_page(bio, virt_to_page(data), HFSPLUS_SECTOR_SIZE, - offset_in_page(data)) != HFSPLUS_SECTOR_SIZE) - BUG(); + if (!(rw & WRITE) && data) + *data = (u8 *)buf + offset; + + while (io_size > 0) { + unsigned int page_offset = offset_in_page(buf); + unsigned int len = min_t(unsigned int, PAGE_SIZE - page_offset, + io_size); + + ret = bio_add_page(bio, virt_to_page(buf), len, page_offset); + if (ret != len) { + ret = -EIO; + goto out; + } + io_size -= len; + buf = (u8 *)buf + len; + } submit_bio(rw, bio); wait_for_completion(&wait); if (!bio_flagged(bio, BIO_UPTODATE)) - return -EIO; - return 0; + ret = -EIO; + +out: + bio_put(bio); + return ret < 0 ? ret : 0; } static int hfsplus_read_mdb(void *bufptr, struct hfsplus_wd *wd) @@ -138,23 +184,19 @@ int hfsplus_read_wrapper(struct super_block *sb) if (hfsplus_get_last_session(sb, &part_start, &part_size)) goto out; - if ((u64)part_start + part_size > 0x100000000ULL) { - pr_err("hfs: volumes larger than 2TB are not supported yet\n"); - goto out; - } error = -ENOMEM; - sbi->s_vhdr = kmalloc(HFSPLUS_SECTOR_SIZE, GFP_KERNEL); - if (!sbi->s_vhdr) + sbi->s_vhdr_buf = kmalloc(hfsplus_min_io_size(sb), GFP_KERNEL); + if (!sbi->s_vhdr_buf) goto out; - sbi->s_backup_vhdr = kmalloc(HFSPLUS_SECTOR_SIZE, GFP_KERNEL); - if (!sbi->s_backup_vhdr) + sbi->s_backup_vhdr_buf = kmalloc(hfsplus_min_io_size(sb), GFP_KERNEL); + if (!sbi->s_backup_vhdr_buf) goto out_free_vhdr; reread: - error = hfsplus_submit_bio(sb->s_bdev, - part_start + HFSPLUS_VOLHEAD_SECTOR, - sbi->s_vhdr, READ); + error = hfsplus_submit_bio(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, + sbi->s_vhdr_buf, (void **)&sbi->s_vhdr, + READ); if (error) goto out_free_backup_vhdr; @@ -169,8 +211,9 @@ reread: if (!hfsplus_read_mdb(sbi->s_vhdr, &wd)) goto out_free_backup_vhdr; wd.ablk_size >>= HFSPLUS_SECTOR_SHIFT; - part_start += wd.ablk_start + wd.embed_start * wd.ablk_size; - part_size = wd.embed_count * wd.ablk_size; + part_start += (sector_t)wd.ablk_start + + (sector_t)wd.embed_start * wd.ablk_size; + part_size = (sector_t)wd.embed_count * wd.ablk_size; goto reread; default: /* @@ -183,9 +226,9 @@ reread: goto reread; } - error = hfsplus_submit_bio(sb->s_bdev, - part_start + part_size - 2, - sbi->s_backup_vhdr, READ); + error = hfsplus_submit_bio(sb, part_start + part_size - 2, + sbi->s_backup_vhdr_buf, + (void **)&sbi->s_backup_vhdr, READ); if (error) goto out_free_backup_vhdr; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 87ed48e..85c098a 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -139,7 +139,8 @@ static int file_removed(struct dentry *dentry, const char *file) static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry, struct nameidata *nd) { - struct dentry *proc_dentry, *new, *parent; + struct dentry *proc_dentry, *parent; + struct qstr *name = &dentry->d_name; struct inode *inode; int err, deleted; @@ -149,23 +150,9 @@ static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry, else if (deleted) return ERR_PTR(-ENOENT); - err = -ENOMEM; parent = HPPFS_I(ino)->proc_dentry; mutex_lock(&parent->d_inode->i_mutex); - proc_dentry = d_lookup(parent, &dentry->d_name); - if (proc_dentry == NULL) { - proc_dentry = d_alloc(parent, &dentry->d_name); - if (proc_dentry == NULL) { - mutex_unlock(&parent->d_inode->i_mutex); - goto out; - } - new = (*parent->d_inode->i_op->lookup)(parent->d_inode, - proc_dentry, NULL); - if (new) { - dput(proc_dentry); - proc_dentry = new; - } - } + proc_dentry = lookup_one_len(name->name, parent, name->len); mutex_unlock(&parent->d_inode->i_mutex); if (IS_ERR(proc_dentry)) @@ -174,13 +161,11 @@ static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry, err = -ENOMEM; inode = get_inode(ino->i_sb, proc_dentry); if (!inode) - goto out_dput; + goto out; d_add(dentry, inode); return NULL; - out_dput: - dput(proc_dentry); out: return ERR_PTR(err); } @@ -690,8 +675,10 @@ static struct inode *get_inode(struct super_block *sb, struct dentry *dentry) struct inode *proc_ino = dentry->d_inode; struct inode *inode = new_inode(sb); - if (!inode) + if (!inode) { + dput(dentry); return ERR_PTR(-ENOMEM); + } if (S_ISDIR(dentry->d_inode->i_mode)) { inode->i_op = &hppfs_dir_iops; @@ -704,7 +691,7 @@ static struct inode *get_inode(struct super_block *sb, struct dentry *dentry) inode->i_fop = &hppfs_file_fops; } - HPPFS_I(inode)->proc_dentry = dget(dentry); + HPPFS_I(inode)->proc_dentry = dentry; inode->i_uid = proc_ino->i_uid; inode->i_gid = proc_ino->i_gid; @@ -737,7 +724,7 @@ static int hppfs_fill_super(struct super_block *sb, void *d, int silent) sb->s_fs_info = proc_mnt; err = -ENOMEM; - root_inode = get_inode(sb, proc_mnt->mnt_sb->s_root); + root_inode = get_inode(sb, dget(proc_mnt->mnt_sb->s_root)); if (!root_inode) goto out_mntput; @@ -423,7 +423,14 @@ EXPORT_SYMBOL(remove_inode_hash); void end_writeback(struct inode *inode) { might_sleep(); + /* + * We have to cycle tree_lock here because reclaim can be still in the + * process of removing the last page (in __delete_from_page_cache()) + * and we must not free mapping under it. + */ + spin_lock_irq(&inode->i_data.tree_lock); BUG_ON(inode->i_data.nrpages); + spin_unlock_irq(&inode->i_data.tree_lock); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 6a79fd0..2c62c5a 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -97,10 +97,14 @@ static int __try_to_free_cp_buf(struct journal_head *jh) if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh) && !buffer_write_io_error(bh)) { + /* + * Get our reference so that bh cannot be freed before + * we unlock it + */ + get_bh(bh); JBUFFER_TRACE(jh, "remove from checkpoint list"); ret = __jbd2_journal_remove_checkpoint(jh) + 1; jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); BUFFER_TRACE(bh, "release"); __brelse(bh); } else { @@ -223,8 +227,8 @@ restart: spin_lock(&journal->j_list_lock); goto restart; } + get_bh(bh); if (buffer_locked(bh)) { - atomic_inc(&bh->b_count); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); wait_on_buffer(bh); @@ -243,7 +247,6 @@ restart: */ released = __jbd2_journal_remove_checkpoint(jh); jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); __brelse(bh); } @@ -284,7 +287,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, int ret = 0; if (buffer_locked(bh)) { - atomic_inc(&bh->b_count); + get_bh(bh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); wait_on_buffer(bh); @@ -316,12 +319,12 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh, ret = 1; if (unlikely(buffer_write_io_error(bh))) ret = -EIO; + get_bh(bh); J_ASSERT_JH(jh, !buffer_jbddirty(bh)); BUFFER_TRACE(bh, "remove from checkpoint"); __jbd2_journal_remove_checkpoint(jh); spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); __brelse(bh); } else { /* @@ -554,7 +557,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* * journal_clean_one_cp_list * - * Find all the written-back checkpoint buffers in the given list and release them. + * Find all the written-back checkpoint buffers in the given list and + * release them. * * Called with the journal locked. * Called with j_list_lock held. @@ -663,8 +667,8 @@ out: * checkpoint lists. * * The function returns 1 if it frees the transaction, 0 otherwise. + * The function can free jh and bh. * - * This function is called with the journal locked. * This function is called with j_list_lock held. * This function is called with jbd_lock_bh_state(jh2bh(jh)) */ @@ -684,13 +688,14 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) } journal = transaction->t_journal; + JBUFFER_TRACE(jh, "removing from transaction"); __buffer_unlink(jh); jh->b_cp_transaction = NULL; + jbd2_journal_put_journal_head(jh); if (transaction->t_checkpoint_list != NULL || transaction->t_checkpoint_io_list != NULL) goto out; - JBUFFER_TRACE(jh, "transaction has no more buffers"); /* * There is one special case to worry about: if we have just pulled the @@ -701,10 +706,8 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) * The locking here around t_state is a bit sleazy. * See the comment at the end of jbd2_journal_commit_transaction(). */ - if (transaction->t_state != T_FINISHED) { - JBUFFER_TRACE(jh, "belongs to running/committing transaction"); + if (transaction->t_state != T_FINISHED) goto out; - } /* OK, that was the last buffer for the transaction: we can now safely remove this transaction from the log */ @@ -723,7 +726,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) wake_up(&journal->j_wait_logspace); ret = 1; out: - JBUFFER_TRACE(jh, "exit"); return ret; } @@ -742,6 +744,8 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh, J_ASSERT_JH(jh, buffer_dirty(jh2bh(jh)) || buffer_jbddirty(jh2bh(jh))); J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + /* Get reference for checkpointing transaction */ + jbd2_journal_grab_journal_head(jh2bh(jh)); jh->b_cp_transaction = transaction; if (!transaction->t_checkpoint_list) { diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7f21cf3..eef6979 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -848,10 +848,16 @@ restart_loop: while (commit_transaction->t_forget) { transaction_t *cp_transaction; struct buffer_head *bh; + int try_to_free = 0; jh = commit_transaction->t_forget; spin_unlock(&journal->j_list_lock); bh = jh2bh(jh); + /* + * Get a reference so that bh cannot be freed before we are + * done with it. + */ + get_bh(bh); jbd_lock_bh_state(bh); J_ASSERT_JH(jh, jh->b_transaction == commit_transaction); @@ -914,28 +920,27 @@ restart_loop: __jbd2_journal_insert_checkpoint(jh, commit_transaction); if (is_journal_aborted(journal)) clear_buffer_jbddirty(bh); - JBUFFER_TRACE(jh, "refile for checkpoint writeback"); - __jbd2_journal_refile_buffer(jh); - jbd_unlock_bh_state(bh); } else { J_ASSERT_BH(bh, !buffer_dirty(bh)); - /* The buffer on BJ_Forget list and not jbddirty means + /* + * The buffer on BJ_Forget list and not jbddirty means * it has been freed by this transaction and hence it * could not have been reallocated until this * transaction has committed. *BUT* it could be * reallocated once we have written all the data to * disk and before we process the buffer on BJ_Forget - * list. */ - JBUFFER_TRACE(jh, "refile or unfile freed buffer"); - __jbd2_journal_refile_buffer(jh); - if (!jh->b_transaction) { - jbd_unlock_bh_state(bh); - /* needs a brelse */ - jbd2_journal_remove_journal_head(bh); - release_buffer_page(bh); - } else - jbd_unlock_bh_state(bh); + * list. + */ + if (!jh->b_next_transaction) + try_to_free = 1; } + JBUFFER_TRACE(jh, "refile or unfile buffer"); + __jbd2_journal_refile_buffer(jh); + jbd_unlock_bh_state(bh); + if (try_to_free) + release_buffer_page(bh); /* Drops bh reference */ + else + __brelse(bh); cond_resched_lock(&journal->j_list_lock); } spin_unlock(&journal->j_list_lock); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 9a78269..0dfa5b5 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2078,10 +2078,9 @@ static void journal_free_journal_head(struct journal_head *jh) * When a buffer has its BH_JBD bit set it is immune from being released by * core kernel code, mainly via ->b_count. * - * A journal_head may be detached from its buffer_head when the journal_head's - * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL. - * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the - * journal_head can be dropped if needed. + * A journal_head is detached from its buffer_head when the journal_head's + * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint + * transaction (b_cp_transaction) hold their references to b_jcount. * * Various places in the kernel want to attach a journal_head to a buffer_head * _before_ attaching the journal_head to a transaction. To protect the @@ -2094,17 +2093,16 @@ static void journal_free_journal_head(struct journal_head *jh) * (Attach a journal_head if needed. Increments b_jcount) * struct journal_head *jh = jbd2_journal_add_journal_head(bh); * ... + * (Get another reference for transaction) + * jbd2_journal_grab_journal_head(bh); * jh->b_transaction = xxx; + * (Put original reference) * jbd2_journal_put_journal_head(jh); - * - * Now, the journal_head's b_jcount is zero, but it is safe from being released - * because it has a non-zero b_transaction. */ /* * Give a buffer_head a journal_head. * - * Doesn't need the journal lock. * May sleep. */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) @@ -2168,61 +2166,29 @@ static void __journal_remove_journal_head(struct buffer_head *bh) struct journal_head *jh = bh2jh(bh); J_ASSERT_JH(jh, jh->b_jcount >= 0); - - get_bh(bh); - if (jh->b_jcount == 0) { - if (jh->b_transaction == NULL && - jh->b_next_transaction == NULL && - jh->b_cp_transaction == NULL) { - J_ASSERT_JH(jh, jh->b_jlist == BJ_None); - J_ASSERT_BH(bh, buffer_jbd(bh)); - J_ASSERT_BH(bh, jh2bh(jh) == bh); - BUFFER_TRACE(bh, "remove journal_head"); - if (jh->b_frozen_data) { - printk(KERN_WARNING "%s: freeing " - "b_frozen_data\n", - __func__); - jbd2_free(jh->b_frozen_data, bh->b_size); - } - if (jh->b_committed_data) { - printk(KERN_WARNING "%s: freeing " - "b_committed_data\n", - __func__); - jbd2_free(jh->b_committed_data, bh->b_size); - } - bh->b_private = NULL; - jh->b_bh = NULL; /* debug, really */ - clear_buffer_jbd(bh); - __brelse(bh); - journal_free_journal_head(jh); - } else { - BUFFER_TRACE(bh, "journal_head was locked"); - } + J_ASSERT_JH(jh, jh->b_transaction == NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + J_ASSERT_JH(jh, jh->b_jlist == BJ_None); + J_ASSERT_BH(bh, buffer_jbd(bh)); + J_ASSERT_BH(bh, jh2bh(jh) == bh); + BUFFER_TRACE(bh, "remove journal_head"); + if (jh->b_frozen_data) { + printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); + jbd2_free(jh->b_frozen_data, bh->b_size); } + if (jh->b_committed_data) { + printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__); + jbd2_free(jh->b_committed_data, bh->b_size); + } + bh->b_private = NULL; + jh->b_bh = NULL; /* debug, really */ + clear_buffer_jbd(bh); + journal_free_journal_head(jh); } /* - * jbd2_journal_remove_journal_head(): if the buffer isn't attached to a transaction - * and has a zero b_jcount then remove and release its journal_head. If we did - * see that the buffer is not used by any transaction we also "logically" - * decrement ->b_count. - * - * We in fact take an additional increment on ->b_count as a convenience, - * because the caller usually wants to do additional things with the bh - * after calling here. - * The caller of jbd2_journal_remove_journal_head() *must* run __brelse(bh) at some - * time. Once the caller has run __brelse(), the buffer is eligible for - * reaping by try_to_free_buffers(). - */ -void jbd2_journal_remove_journal_head(struct buffer_head *bh) -{ - jbd_lock_bh_journal_head(bh); - __journal_remove_journal_head(bh); - jbd_unlock_bh_journal_head(bh); -} - -/* - * Drop a reference on the passed journal_head. If it fell to zero then try to + * Drop a reference on the passed journal_head. If it fell to zero then * release the journal_head from the buffer_head. */ void jbd2_journal_put_journal_head(struct journal_head *jh) @@ -2232,11 +2198,12 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) jbd_lock_bh_journal_head(bh); J_ASSERT_JH(jh, jh->b_jcount > 0); --jh->b_jcount; - if (!jh->b_jcount && !jh->b_transaction) { + if (!jh->b_jcount) { __journal_remove_journal_head(bh); + jbd_unlock_bh_journal_head(bh); __brelse(bh); - } - jbd_unlock_bh_journal_head(bh); + } else + jbd_unlock_bh_journal_head(bh); } /* diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 3eec82d..2d71094 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -30,6 +30,7 @@ #include <linux/module.h> static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh); +static void __jbd2_journal_unfile_buffer(struct journal_head *jh); /* * jbd2_get_transaction: obtain a new transaction_t object. @@ -764,7 +765,6 @@ repeat: if (!jh->b_transaction) { JBUFFER_TRACE(jh, "no transaction"); J_ASSERT_JH(jh, !jh->b_next_transaction); - jh->b_transaction = transaction; JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); @@ -814,7 +814,6 @@ out: * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes - * @credits: variable that will receive credits for the buffer * * Returns an error code or 0 on success. * @@ -896,8 +895,6 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) * committed and so it's safe to clear the dirty bit. */ clear_buffer_dirty(jh2bh(jh)); - jh->b_transaction = transaction; - /* first access by this transaction */ jh->b_modified = 0; @@ -932,7 +929,6 @@ out: * non-rewindable consequences * @handle: transaction * @bh: buffer to undo - * @credits: store the number of taken credits here (if not NULL) * * Sometimes there is a need to distinguish between metadata which has * been committed to disk and that which has not. The ext3fs code uses @@ -1232,8 +1228,6 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) __jbd2_journal_file_buffer(jh, transaction, BJ_Forget); } else { __jbd2_journal_unfile_buffer(jh); - jbd2_journal_remove_journal_head(bh); - __brelse(bh); if (!buffer_jbd(bh)) { spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); @@ -1556,19 +1550,32 @@ void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) mark_buffer_dirty(bh); /* Expose it to the VM */ } -void __jbd2_journal_unfile_buffer(struct journal_head *jh) +/* + * Remove buffer from all transactions. + * + * Called with bh_state lock and j_list_lock + * + * jh and bh may be already freed when this function returns. + */ +static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; + jbd2_journal_put_journal_head(jh); } void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh) { - jbd_lock_bh_state(jh2bh(jh)); + struct buffer_head *bh = jh2bh(jh); + + /* Get reference so that buffer cannot be freed before we unlock it */ + get_bh(bh); + jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); __jbd2_journal_unfile_buffer(jh); spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(jh2bh(jh)); + jbd_unlock_bh_state(bh); + __brelse(bh); } /* @@ -1595,8 +1602,6 @@ __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh) if (jh->b_jlist == BJ_None) { JBUFFER_TRACE(jh, "remove from checkpoint list"); __jbd2_journal_remove_checkpoint(jh); - jbd2_journal_remove_journal_head(bh); - __brelse(bh); } } spin_unlock(&journal->j_list_lock); @@ -1659,7 +1664,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, /* * We take our own ref against the journal_head here to avoid * having to add tons of locking around each instance of - * jbd2_journal_remove_journal_head() and * jbd2_journal_put_journal_head(). */ jh = jbd2_journal_grab_journal_head(bh); @@ -1697,10 +1701,9 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) int may_free = 1; struct buffer_head *bh = jh2bh(jh); - __jbd2_journal_unfile_buffer(jh); - if (jh->b_cp_transaction) { JBUFFER_TRACE(jh, "on running+cp transaction"); + __jbd2_journal_temp_unlink_buffer(jh); /* * We don't want to write the buffer anymore, clear the * bit so that we don't confuse checks in @@ -1711,8 +1714,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) may_free = 0; } else { JBUFFER_TRACE(jh, "on running transaction"); - jbd2_journal_remove_journal_head(bh); - __brelse(bh); + __jbd2_journal_unfile_buffer(jh); } return may_free; } @@ -1990,6 +1992,8 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, if (jh->b_transaction) __jbd2_journal_temp_unlink_buffer(jh); + else + jbd2_journal_grab_journal_head(bh); jh->b_transaction = transaction; switch (jlist) { @@ -2041,9 +2045,10 @@ void jbd2_journal_file_buffer(struct journal_head *jh, * already started to be used by a subsequent transaction, refile the * buffer on that transaction's metadata list. * - * Called under journal->j_list_lock - * + * Called under j_list_lock * Called under jbd_lock_bh_state(jh2bh(jh)) + * + * jh and bh may be already free when this function returns */ void __jbd2_journal_refile_buffer(struct journal_head *jh) { @@ -2067,6 +2072,11 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); + /* + * We set b_transaction here because b_next_transaction will inherit + * our jh reference and thus __jbd2_journal_file_buffer() must not + * take a new one. + */ jh->b_transaction = jh->b_next_transaction; jh->b_next_transaction = NULL; if (buffer_freed(bh)) @@ -2083,30 +2093,21 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh) } /* - * For the unlocked version of this call, also make sure that any - * hanging journal_head is cleaned up if necessary. - * - * __jbd2_journal_refile_buffer is usually called as part of a single locked - * operation on a buffer_head, in which the caller is probably going to - * be hooking the journal_head onto other lists. In that case it is up - * to the caller to remove the journal_head if necessary. For the - * unlocked jbd2_journal_refile_buffer call, the caller isn't going to be - * doing anything else to the buffer so we need to do the cleanup - * ourselves to avoid a jh leak. - * - * *** The journal_head may be freed by this call! *** + * __jbd2_journal_refile_buffer() with necessary locking added. We take our + * bh reference so that we can safely unlock bh. + * + * The jh and bh may be freed by this call. */ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) { struct buffer_head *bh = jh2bh(jh); + /* Get reference so that buffer cannot be freed before we unlock it */ + get_bh(bh); jbd_lock_bh_state(bh); spin_lock(&journal->j_list_lock); - __jbd2_journal_refile_buffer(jh); jbd_unlock_bh_state(bh); - jbd2_journal_remove_journal_head(bh); - spin_unlock(&journal->j_list_lock); __brelse(bh); } diff --git a/fs/jfs/file.c b/fs/jfs/file.c index c5ce6c1..2f3f531 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -66,9 +66,9 @@ static int jfs_open(struct inode *inode, struct file *file) struct jfs_inode_info *ji = JFS_IP(inode); spin_lock_irq(&ji->ag_lock); if (ji->active_ag == -1) { - ji->active_ag = ji->agno; - atomic_inc( - &JFS_SBI(inode->i_sb)->bmap->db_active[ji->agno]); + struct jfs_sb_info *jfs_sb = JFS_SBI(inode->i_sb); + ji->active_ag = BLKTOAG(addressPXD(&ji->ixpxd), jfs_sb); + atomic_inc( &jfs_sb->bmap->db_active[ji->active_ag]); } spin_unlock_irq(&ji->ag_lock); } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index ed53a47..b78b2f9 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -397,7 +397,7 @@ int diRead(struct inode *ip) release_metapage(mp); /* set the ag for the inode */ - JFS_IP(ip)->agno = BLKTOAG(agstart, sbi); + JFS_IP(ip)->agstart = agstart; JFS_IP(ip)->active_ag = -1; return (rc); @@ -901,7 +901,7 @@ int diFree(struct inode *ip) /* get the allocation group for this ino. */ - agno = JFS_IP(ip)->agno; + agno = BLKTOAG(JFS_IP(ip)->agstart, JFS_SBI(ip->i_sb)); /* Lock the AG specific inode map information */ @@ -1315,12 +1315,11 @@ int diFree(struct inode *ip) static inline void diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) { - struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); struct jfs_inode_info *jfs_ip = JFS_IP(ip); ip->i_ino = (iagno << L2INOSPERIAG) + ino; jfs_ip->ixpxd = iagp->inoext[extno]; - jfs_ip->agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + jfs_ip->agstart = le64_to_cpu(iagp->agstart); jfs_ip->active_ag = -1; } @@ -1379,7 +1378,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) */ /* get the ag number of this iag */ - agno = JFS_IP(pip)->agno; + agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb)); if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) { /* @@ -2921,10 +2920,9 @@ int diExtendFS(struct inode *ipimap, struct inode *ipbmap) continue; } - /* agstart that computes to the same ag is treated as same; */ agstart = le64_to_cpu(iagp->agstart); - /* iagp->agstart = agstart & ~(mp->db_agsize - 1); */ n = agstart >> mp->db_agl2size; + iagp->agstart = cpu_to_le64((s64)n << mp->db_agl2size); /* compute backed inodes */ numinos = (EXTSPERIAG - le32_to_cpu(iagp->nfreeexts)) diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 1439f11..584a4a1 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -50,8 +50,9 @@ struct jfs_inode_info { short btindex; /* btpage entry index*/ struct inode *ipimap; /* inode map */ unsigned long cflag; /* commit flags */ + u64 agstart; /* agstart of the containing IAG */ u16 bxflag; /* xflag of pseudo buffer? */ - unchar agno; /* ag number */ + unchar pad; signed char active_ag; /* ag currently allocating from */ lid_t blid; /* lid of pseudo buffer? */ lid_t atlhead; /* anonymous tlock list head */ diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 8ea5efb..8d0c1c7 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -80,7 +80,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) int log_formatted = 0; struct inode *iplist[1]; struct jfs_superblock *j_sb, *j_sb2; - uint old_agsize; + s64 old_agsize; int agsizechanged = 0; struct buffer_head *bh, *bh2; @@ -822,7 +822,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - val = simple_strtol(attr->set_buf, NULL, 0); + val = simple_strtoll(attr->set_buf, NULL, 0); ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index adb45ec..e374050 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -708,7 +708,13 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data) if (task->tk_status < 0) { dprintk("lockd: unlock failed (err = %d)\n", -task->tk_status); - goto retry_rebind; + switch (task->tk_status) { + case -EACCES: + case -EIO: + goto die; + default: + goto retry_rebind; + } } if (status == NLM_LCK_DENIED_GRACE_PERIOD) { rpc_delay(task, NLMCLNT_GRACE_WAIT); @@ -160,10 +160,28 @@ EXPORT_SYMBOL_GPL(unlock_flocks); static struct kmem_cache *filelock_cache __read_mostly; +static void locks_init_lock_always(struct file_lock *fl) +{ + fl->fl_next = NULL; + fl->fl_fasync = NULL; + fl->fl_owner = NULL; + fl->fl_pid = 0; + fl->fl_nspid = NULL; + fl->fl_file = NULL; + fl->fl_flags = 0; + fl->fl_type = 0; + fl->fl_start = fl->fl_end = 0; +} + /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { - return kmem_cache_alloc(filelock_cache, GFP_KERNEL); + struct file_lock *fl = kmem_cache_alloc(filelock_cache, GFP_KERNEL); + + if (fl) + locks_init_lock_always(fl); + + return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); @@ -200,17 +218,9 @@ void locks_init_lock(struct file_lock *fl) INIT_LIST_HEAD(&fl->fl_link); INIT_LIST_HEAD(&fl->fl_block); init_waitqueue_head(&fl->fl_wait); - fl->fl_next = NULL; - fl->fl_fasync = NULL; - fl->fl_owner = NULL; - fl->fl_pid = 0; - fl->fl_nspid = NULL; - fl->fl_file = NULL; - fl->fl_flags = 0; - fl->fl_type = 0; - fl->fl_start = fl->fl_end = 0; fl->fl_ops = NULL; fl->fl_lmops = NULL; + locks_init_lock_always(fl); } EXPORT_SYMBOL(locks_init_lock); @@ -433,6 +433,8 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) goto err_parent; BUG_ON(nd->inode != parent->d_inode); } else { + if (dentry->d_parent != parent) + goto err_parent; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (!__d_rcu_to_refcount(dentry, nd->seq)) goto err_child; @@ -940,7 +942,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ - *inode = path->dentry->d_inode; if (unlikely(managed_dentry_might_block(path->dentry))) return false; @@ -953,6 +954,12 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, path->mnt = mounted; path->dentry = mounted->mnt_root; nd->seq = read_seqcount_begin(&path->dentry->d_seq); + /* + * Update the inode too. We don't need to re-check the + * dentry sequence number here after this d_inode read, + * because a mount-point is always pinned. + */ + *inode = path->dentry->d_inode; } return true; } diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index ce153a6..419119c 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -259,12 +259,10 @@ static void nfs_fscache_disable_inode_cookie(struct inode *inode) dfprintk(FSCACHE, "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode)); - /* Need to invalidate any mapped pages that were read in before - * turning off the cache. + /* Need to uncache any pages attached to this inode that + * fscache knows about before turning off the cache. */ - if (inode->i_mapping && inode->i_mapping->nrpages) - invalidate_inode_pages2(inode->i_mapping); - + fscache_uncache_all_inode_pages(NFS_I(inode)->fscache, inode); nfs_fscache_zap_inode_cookie(inode); } } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 144f2a3..6f4850d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -256,7 +256,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) nfs_attr_check_mountpoint(sb, fattr); - if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0 && (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) + if (((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) && + !nfs_attr_use_mounted_on_fileid(fattr)) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; @@ -1294,7 +1295,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (new_isize != cur_isize) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ - if (nfsi->npages == 0 || new_isize > cur_isize) { + if ((nfsi->npages == 0 && !test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) || + new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b9056cb..2a55347 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -45,6 +45,17 @@ static inline void nfs_attr_check_mountpoint(struct super_block *parent, struct fattr->valid |= NFS_ATTR_FATTR_MOUNTPOINT; } +static inline int nfs_attr_use_mounted_on_fileid(struct nfs_fattr *fattr) +{ + if (((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) == 0) || + (((fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT) == 0) && + ((fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) == 0))) + return 0; + + fattr->fileid = fattr->mounted_on_fileid; + return 1; +} + struct nfs_clone_mount { const struct super_block *sb; const struct dentry *dentry; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 4269088..f9d03ab 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -30,6 +30,7 @@ */ #include <linux/nfs_fs.h> +#include <linux/nfs_page.h> #include "internal.h" #include "nfs4filelayout.h" @@ -397,7 +398,6 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) * this offset and save the original offset. */ data->args.offset = filelayout_get_dserver_offset(lseg, offset); - data->mds_offset = offset; /* Perform an asynchronous write */ status = nfs_initiate_write(data, ds->ds_clp->cl_rpcclient, @@ -552,13 +552,18 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo, __func__, nfl_util, fl->num_fh, fl->first_stripe_index, fl->pattern_offset); - if (!fl->num_fh) + /* Note that a zero value for num_fh is legal for STRIPE_SPARSE. + * Futher checking is done in filelayout_check_layout */ + if (fl->num_fh < 0 || fl->num_fh > + max(NFS4_PNFS_MAX_STRIPE_CNT, NFS4_PNFS_MAX_MULTI_CNT)) goto out_err; - fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), - gfp_flags); - if (!fl->fh_array) - goto out_err; + if (fl->num_fh > 0) { + fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), + gfp_flags); + if (!fl->fh_array) + goto out_err; + } for (i = 0; i < fl->num_fh; i++) { /* Do we want to use a mempool here? */ @@ -661,8 +666,9 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, u64 p_stripe, r_stripe; u32 stripe_unit; - if (!pnfs_generic_pg_test(pgio, prev, req)) - return 0; + if (!pnfs_generic_pg_test(pgio, prev, req) || + !nfs_generic_pg_test(pgio, prev, req)) + return false; if (!pgio->pg_lseg) return 1; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d2c4b59..5879b23 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2265,12 +2265,14 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, return nfs4_map_errors(status); } +static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); /* * Get locations and (maybe) other attributes of a referral. * Note that we'll actually follow the referral later when * we detect fsid mismatch in inode revalidation */ -static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct nfs_fattr *fattr, struct nfs_fh *fhandle) +static int nfs4_get_referral(struct inode *dir, const struct qstr *name, + struct nfs_fattr *fattr, struct nfs_fh *fhandle) { int status = -ENOMEM; struct page *page = NULL; @@ -2288,15 +2290,16 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct goto out; /* Make sure server returned a different fsid for the referral */ if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) { - dprintk("%s: server did not return a different fsid for a referral at %s\n", __func__, name->name); + dprintk("%s: server did not return a different fsid for" + " a referral at %s\n", __func__, name->name); status = -EIO; goto out; } + /* Fixup attributes for the nfs_lookup() call to nfs_fhget() */ + nfs_fixup_referral_attributes(&locations->fattr); + /* replace the lookup nfs_fattr with the locations nfs_fattr */ memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr)); - fattr->valid |= NFS_ATTR_FATTR_V4_REFERRAL; - if (!fattr->mode) - fattr->mode = S_IFDIR; memset(fhandle, 0, sizeof(struct nfs_fh)); out: if (page) @@ -4667,11 +4670,15 @@ static size_t nfs4_xattr_list_nfs4_acl(struct dentry *dentry, char *list, return len; } +/* + * nfs_fhget will use either the mounted_on_fileid or the fileid + */ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr) { - if (!((fattr->valid & NFS_ATTR_FATTR_FILEID) && - (fattr->valid & NFS_ATTR_FATTR_FSID) && - (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL))) + if (!(((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) || + (fattr->valid & NFS_ATTR_FATTR_FILEID)) && + (fattr->valid & NFS_ATTR_FATTR_FSID) && + (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL))) return; fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | @@ -4686,7 +4693,6 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, struct nfs_server *server = NFS_SERVER(dir); u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, - [1] = FATTR4_WORD1_MOUNTED_ON_FILEID, }; struct nfs4_fs_locations_arg args = { .dir_fh = NFS_FH(dir), @@ -4705,11 +4711,18 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, int status; dprintk("%s: start\n", __func__); + + /* Ask for the fileid of the absent filesystem if mounted_on_fileid + * is not supported */ + if (NFS_SERVER(dir)->attr_bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) + bitmask[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID; + else + bitmask[0] |= FATTR4_WORD0_FILEID; + nfs_fattr_init(&fs_locations->fattr); fs_locations->server = server; fs_locations->nlocations = 0; status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); - nfs_fixup_referral_attributes(&fs_locations->fattr); dprintk("%s: returned status = %d\n", __func__, status); return status; } @@ -5098,7 +5111,6 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) if (mxresp_sz == 0) mxresp_sz = NFS_MAX_FILE_IO_SIZE; /* Fore channel attributes */ - args->fc_attrs.headerpadsz = 0; args->fc_attrs.max_rqst_sz = mxrqst_sz; args->fc_attrs.max_resp_sz = mxresp_sz; args->fc_attrs.max_ops = NFS4_MAX_OPS; @@ -5111,7 +5123,6 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) args->fc_attrs.max_ops, args->fc_attrs.max_reqs); /* Back channel attributes */ - args->bc_attrs.headerpadsz = 0; args->bc_attrs.max_rqst_sz = PAGE_SIZE; args->bc_attrs.max_resp_sz = PAGE_SIZE; args->bc_attrs.max_resp_sz_cached = 0; @@ -5131,8 +5142,6 @@ static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args struct nfs4_channel_attrs *sent = &args->fc_attrs; struct nfs4_channel_attrs *rcvd = &session->fc_attrs; - if (rcvd->headerpadsz > sent->headerpadsz) - return -EINVAL; if (rcvd->max_resp_sz > sent->max_resp_sz) return -EINVAL; /* @@ -5697,6 +5706,7 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) { struct nfs4_layoutreturn *lrp = calldata; struct nfs_server *server; + struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout; dprintk("--> %s\n", __func__); @@ -5708,16 +5718,15 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) nfs_restart_rpc(task, lrp->clp); return; } + spin_lock(&lo->plh_inode->i_lock); if (task->tk_status == 0) { - struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout; - if (lrp->res.lrs_present) { - spin_lock(&lo->plh_inode->i_lock); pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - spin_unlock(&lo->plh_inode->i_lock); } else BUG_ON(!list_empty(&lo->plh_segs)); } + lo->plh_block_lgets--; + spin_unlock(&lo->plh_inode->i_lock); dprintk("<-- %s\n", __func__); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d869a5e..e6e8f3b 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -91,7 +91,7 @@ static int nfs4_stat_to_errno(int); #define encode_getfh_maxsz (op_encode_hdr_maxsz) #define decode_getfh_maxsz (op_decode_hdr_maxsz + 1 + \ ((3+NFS4_FHSIZE) >> 2)) -#define nfs4_fattr_bitmap_maxsz 3 +#define nfs4_fattr_bitmap_maxsz 4 #define encode_getattr_maxsz (op_encode_hdr_maxsz + nfs4_fattr_bitmap_maxsz) #define nfs4_name_maxsz (1 + ((3 + NFS4_MAXNAMLEN) >> 2)) #define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2)) @@ -255,7 +255,7 @@ static int nfs4_stat_to_errno(int); #define decode_fs_locations_maxsz \ (0) #define encode_secinfo_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) -#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 4 + (NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN))) +#define decode_secinfo_maxsz (op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4)) #if defined(CONFIG_NFS_V4_1) #define NFS4_MAX_MACHINE_NAME_LEN (64) @@ -1725,7 +1725,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(args->flags); /*flags */ /* Fore Channel */ - *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(0); /* header padding size */ *p++ = cpu_to_be32(args->fc_attrs.max_rqst_sz); /* max req size */ *p++ = cpu_to_be32(args->fc_attrs.max_resp_sz); /* max resp size */ *p++ = cpu_to_be32(max_resp_sz_cached); /* Max resp sz cached */ @@ -1734,7 +1734,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(0); /* rdmachannel_attrs */ /* Back Channel */ - *p++ = cpu_to_be32(args->fc_attrs.headerpadsz); /* header padding size */ + *p++ = cpu_to_be32(0); /* header padding size */ *p++ = cpu_to_be32(args->bc_attrs.max_rqst_sz); /* max req size */ *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz); /* max resp size */ *p++ = cpu_to_be32(args->bc_attrs.max_resp_sz_cached); /* Max resp sz cached */ @@ -3098,7 +3098,7 @@ out_overflow: return -EIO; } -static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap) +static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap, int32_t *res) { __be32 *p; @@ -3109,7 +3109,7 @@ static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap) if (unlikely(!p)) goto out_overflow; bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR; - return -be32_to_cpup(p); + *res = -be32_to_cpup(p); } return 0; out_overflow: @@ -4070,6 +4070,7 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, int status; umode_t fmode = 0; uint32_t type; + int32_t err; status = decode_attr_type(xdr, bitmap, &type); if (status < 0) @@ -4095,13 +4096,12 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; - status = decode_attr_error(xdr, bitmap); - if (status == -NFS4ERR_WRONGSEC) { - nfs_fixup_secinfo_attributes(fattr, fh); - status = 0; - } + err = 0; + status = decode_attr_error(xdr, bitmap, &err); if (status < 0) goto xdr_error; + if (err == -NFS4ERR_WRONGSEC) + nfs_fixup_secinfo_attributes(fattr, fh); status = decode_attr_filehandle(xdr, bitmap, fh); if (status < 0) @@ -4997,12 +4997,14 @@ static int decode_chan_attrs(struct xdr_stream *xdr, struct nfs4_channel_attrs *attrs) { __be32 *p; - u32 nr_attrs; + u32 nr_attrs, val; p = xdr_inline_decode(xdr, 28); if (unlikely(!p)) goto out_overflow; - attrs->headerpadsz = be32_to_cpup(p++); + val = be32_to_cpup(p++); /* headerpadsz */ + if (val) + return -EINVAL; /* no support for header padding yet */ attrs->max_rqst_sz = be32_to_cpup(p++); attrs->max_resp_sz = be32_to_cpup(p++); attrs->max_resp_sz_cached = be32_to_cpup(p++); diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 9cf208d..8ff2ea3 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -108,7 +108,6 @@ _dev_list_add(const struct nfs_server *nfss, de = n; } - atomic_inc(&de->id_node.ref); return de; } @@ -1001,6 +1000,9 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, if (!pnfs_generic_pg_test(pgio, prev, req)) return false; + if (pgio->pg_lseg == NULL) + return true; + return pgio->pg_count + req->wb_bytes <= OBJIO_LSEG(pgio->pg_lseg)->max_io_size; } diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index dc3956c..1d06f8e 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -291,7 +291,7 @@ objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync) struct nfs_read_data *rdata; state->status = status; - dprintk("%s: Begin status=%ld eof=%d\n", __func__, status, eof); + dprintk("%s: Begin status=%zd eof=%d\n", __func__, status, eof); rdata = state->rpcdata; rdata->task.tk_status = status; if (status >= 0) { diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 7913961..0098557 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -204,7 +204,7 @@ nfs_wait_on_request(struct nfs_page *req) TASK_UNINTERRUPTIBLE); } -static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) +bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req) { /* * FIXME: ideally we should be able to coalesce all requests @@ -218,6 +218,7 @@ static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_p return desc->pg_count + req->wb_bytes <= desc->pg_bsize; } +EXPORT_SYMBOL_GPL(nfs_generic_pg_test); /** * nfs_pageio_init - initialise a page io descriptor diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8c1309d..29c0ca7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -634,14 +634,16 @@ _pnfs_return_layout(struct inode *ino) spin_lock(&ino->i_lock); lo = nfsi->layout; - if (!lo || !mark_matching_lsegs_invalid(lo, &tmp_list, NULL)) { + if (!lo) { spin_unlock(&ino->i_lock); - dprintk("%s: no layout segments to return\n", __func__); - goto out; + dprintk("%s: no layout to return\n", __func__); + return status; } stateid = nfsi->layout->plh_stateid; /* Reference matched in nfs4_layoutreturn_release */ get_layout_hdr(lo); + mark_matching_lsegs_invalid(lo, &tmp_list, NULL); + lo->plh_block_lgets++; spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); @@ -650,6 +652,9 @@ _pnfs_return_layout(struct inode *ino) lrp = kzalloc(sizeof(*lrp), GFP_KERNEL); if (unlikely(lrp == NULL)) { status = -ENOMEM; + set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags); + set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags); + put_layout_hdr(lo); goto out; } @@ -887,7 +892,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, ret = get_lseg(lseg); break; } - if (cmp_layout(range, &lseg->pls_range) > 0) + if (lseg->pls_range.offset > range->offset) break; } @@ -1059,23 +1064,36 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, gfp_flags = GFP_NOFS; } - if (pgio->pg_count == prev->wb_bytes) { + if (pgio->pg_lseg == NULL) { + if (pgio->pg_count != prev->wb_bytes) + return true; /* This is first coelesce call for a series of nfs_pages */ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, prev->wb_context, - req_offset(req), + req_offset(prev), pgio->pg_count, access_type, gfp_flags); - return true; + if (pgio->pg_lseg == NULL) + return true; } - if (pgio->pg_lseg && - req_offset(req) > end_offset(pgio->pg_lseg->pls_range.offset, - pgio->pg_lseg->pls_range.length)) - return false; - - return true; + /* + * Test if a nfs_page is fully contained in the pnfs_layout_range. + * Note that this test makes several assumptions: + * - that the previous nfs_page in the struct nfs_pageio_descriptor + * is known to lie within the range. + * - that the nfs_page being tested is known to be contiguous with the + * previous nfs_page. + * - Layout ranges are page aligned, so we only have to test the + * start offset of the request. + * + * Please also note that 'end_offset' is actually the offset of the + * first byte that lies outside the pnfs_layout_range. FIXME? + * + */ + return req_offset(req) < end_offset(pgio->pg_lseg->pls_range.offset, + pgio->pg_lseg->pls_range.length); } EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 48d0a8e..96bf4e6 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -186,6 +186,7 @@ int pnfs_ld_read_done(struct nfs_read_data *); /* pnfs_dev.c */ struct nfs4_deviceid_node { struct hlist_node node; + struct hlist_node tmpnode; const struct pnfs_layoutdriver_type *ld; const struct nfs_client *nfs_client; struct nfs4_deviceid deviceid; diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index c65e133..f0f8e1e 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -174,6 +174,7 @@ nfs4_init_deviceid_node(struct nfs4_deviceid_node *d, const struct nfs4_deviceid *id) { INIT_HLIST_NODE(&d->node); + INIT_HLIST_NODE(&d->tmpnode); d->ld = ld; d->nfs_client = nfs_client; d->deviceid = *id; @@ -208,6 +209,7 @@ nfs4_insert_deviceid_node(struct nfs4_deviceid_node *new) hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]); spin_unlock(&nfs4_deviceid_lock); + atomic_inc(&new->ref); return new; } @@ -238,24 +240,29 @@ static void _deviceid_purge_client(const struct nfs_client *clp, long hash) { struct nfs4_deviceid_node *d; - struct hlist_node *n, *next; + struct hlist_node *n; HLIST_HEAD(tmp); + spin_lock(&nfs4_deviceid_lock); rcu_read_lock(); hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node) if (d->nfs_client == clp && atomic_read(&d->ref)) { hlist_del_init_rcu(&d->node); - hlist_add_head(&d->node, &tmp); + hlist_add_head(&d->tmpnode, &tmp); } rcu_read_unlock(); + spin_unlock(&nfs4_deviceid_lock); if (hlist_empty(&tmp)) return; synchronize_rcu(); - hlist_for_each_entry_safe(d, n, next, &tmp, node) + while (!hlist_empty(&tmp)) { + d = hlist_entry(tmp.first, struct nfs4_deviceid_node, tmpnode); + hlist_del(&d->tmpnode); if (atomic_dec_and_test(&d->ref)) d->ld->free_deviceid_node(d); + } } void @@ -263,8 +270,8 @@ nfs4_deviceid_purge_client(const struct nfs_client *clp) { long h; - spin_lock(&nfs4_deviceid_lock); + if (!(clp->cl_exchange_flags & EXCHGID4_FLAG_USE_PNFS_MDS)) + return; for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++) _deviceid_purge_client(clp, h); - spin_unlock(&nfs4_deviceid_lock); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index e268e3b..7271680 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -864,6 +864,8 @@ static int nfs_write_rpcsetup(struct nfs_page *req, data->args.fh = NFS_FH(inode); data->args.offset = req_offset(req) + offset; + /* pnfs_set_layoutcommit needs this */ + data->mds_offset = data->args.offset; data->args.pgbase = req->wb_pgbase + offset; data->args.pages = data->pagevec; data->args.count = count; diff --git a/fs/omfs/file.c b/fs/omfs/file.c index d738a7e..2c6d952 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -4,7 +4,6 @@ * Released under GPL v2. */ -#include <linux/version.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/buffer_head.h> diff --git a/fs/proc/base.c b/fs/proc/base.c index 8a84210..fc5bc27 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2708,6 +2708,9 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole) struct task_io_accounting acct = task->ioac; unsigned long flags; + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + return -EACCES; + if (whole && lock_task_sighand(task, &flags)) { struct task_struct *t = task; @@ -2839,7 +2842,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING - INF("io", S_IRUGO, proc_tgid_io_accounting), + INF("io", S_IRUSR, proc_tgid_io_accounting), #endif #ifdef CONFIG_HARDWALL INF("hardwall", S_IRUGO, proc_pid_hardwall), @@ -3181,7 +3184,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING - INF("io", S_IRUGO, proc_tid_io_accounting), + INF("io", S_IRUSR, proc_tid_io_accounting), #endif #ifdef CONFIG_HARDWALL INF("hardwall", S_IRUGO, proc_pid_hardwall), diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index f0511e8..eed9942 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -27,14 +27,18 @@ static unsigned long romfs_get_unmapped_area(struct file *file, { struct inode *inode = file->f_mapping->host; struct mtd_info *mtd = inode->i_sb->s_mtd; - unsigned long isize, offset; + unsigned long isize, offset, maxpages, lpages; if (!mtd) goto cant_map_directly; + /* the mapping mustn't extend beyond the EOF */ + lpages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; isize = i_size_read(inode); offset = pgoff << PAGE_SHIFT; - if (offset > isize || len > isize || offset > isize - len) + + maxpages = (isize + PAGE_SIZE - 1) >> PAGE_SHIFT; + if ((pgoff >= maxpages) || (maxpages - pgoff < lpages)) return (unsigned long) -EINVAL; /* we need to call down to the MTD layer to do the actual mapping */ diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index 87cd0ea..fb3b5c8 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -78,7 +78,7 @@ static int nothing_to_commit(struct ubifs_info *c) * If the root TNC node is dirty, we definitely have something to * commit. */ - if (c->zroot.znode && test_bit(DIRTY_ZNODE, &c->zroot.znode->flags)) + if (c->zroot.znode && ubifs_zn_dirty(c->zroot.znode)) return 0; /* @@ -418,7 +418,7 @@ int ubifs_run_commit(struct ubifs_info *c) spin_lock(&c->cs_lock); if (c->cmt_state == COMMIT_BROKEN) { - err = -EINVAL; + err = -EROFS; goto out; } @@ -444,7 +444,7 @@ int ubifs_run_commit(struct ubifs_info *c) * re-check it. */ if (c->cmt_state == COMMIT_BROKEN) { - err = -EINVAL; + err = -EROFS; goto out_cmt_unlock; } @@ -576,7 +576,7 @@ int dbg_check_old_index(struct ubifs_info *c, struct ubifs_zbranch *zroot) struct idx_node *i; size_t sz; - if (!(ubifs_chk_flags & UBIFS_CHK_OLD_IDX)) + if (!dbg_is_chk_index(c)) return 0; INIT_LIST_HEAD(&list); diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 0bb2bce..eef109a 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -27,13 +27,12 @@ * various local functions of those subsystems. */ -#define UBIFS_DBG_PRESERVE_UBI - -#include "ubifs.h" #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/debugfs.h> #include <linux/math64.h> +#include <linux/uaccess.h> +#include <linux/random.h> +#include "ubifs.h" #ifdef CONFIG_UBIFS_FS_DEBUG @@ -42,15 +41,6 @@ DEFINE_SPINLOCK(dbg_lock); static char dbg_key_buf0[128]; static char dbg_key_buf1[128]; -unsigned int ubifs_chk_flags; -unsigned int ubifs_tst_flags; - -module_param_named(debug_chks, ubifs_chk_flags, uint, S_IRUGO | S_IWUSR); -module_param_named(debug_tsts, ubifs_tst_flags, uint, S_IRUGO | S_IWUSR); - -MODULE_PARM_DESC(debug_chks, "Debug check flags"); -MODULE_PARM_DESC(debug_tsts, "Debug special test flags"); - static const char *get_key_fmt(int fmt) { switch (fmt) { @@ -91,6 +81,28 @@ static const char *get_key_type(int type) } } +static const char *get_dent_type(int type) +{ + switch (type) { + case UBIFS_ITYPE_REG: + return "file"; + case UBIFS_ITYPE_DIR: + return "dir"; + case UBIFS_ITYPE_LNK: + return "symlink"; + case UBIFS_ITYPE_BLK: + return "blkdev"; + case UBIFS_ITYPE_CHR: + return "char dev"; + case UBIFS_ITYPE_FIFO: + return "fifo"; + case UBIFS_ITYPE_SOCK: + return "socket"; + default: + return "unknown/invalid type"; + } +} + static void sprintf_key(const struct ubifs_info *c, const union ubifs_key *key, char *buffer) { @@ -234,9 +246,13 @@ static void dump_ch(const struct ubifs_ch *ch) printk(KERN_DEBUG "\tlen %u\n", le32_to_cpu(ch->len)); } -void dbg_dump_inode(const struct ubifs_info *c, const struct inode *inode) +void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode) { const struct ubifs_inode *ui = ubifs_inode(inode); + struct qstr nm = { .name = NULL }; + union ubifs_key key; + struct ubifs_dent_node *dent, *pdent = NULL; + int count = 2; printk(KERN_DEBUG "Dump in-memory inode:"); printk(KERN_DEBUG "\tinode %lu\n", inode->i_ino); @@ -270,6 +286,32 @@ void dbg_dump_inode(const struct ubifs_info *c, const struct inode *inode) printk(KERN_DEBUG "\tlast_page_read %lu\n", ui->last_page_read); printk(KERN_DEBUG "\tread_in_a_row %lu\n", ui->read_in_a_row); printk(KERN_DEBUG "\tdata_len %d\n", ui->data_len); + + if (!S_ISDIR(inode->i_mode)) + return; + + printk(KERN_DEBUG "List of directory entries:\n"); + ubifs_assert(!mutex_is_locked(&c->tnc_mutex)); + + lowest_dent_key(c, &key, inode->i_ino); + while (1) { + dent = ubifs_tnc_next_ent(c, &key, &nm); + if (IS_ERR(dent)) { + if (PTR_ERR(dent) != -ENOENT) + printk(KERN_DEBUG "error %ld\n", PTR_ERR(dent)); + break; + } + + printk(KERN_DEBUG "\t%d: %s (%s)\n", + count++, dent->name, get_dent_type(dent->type)); + + nm.name = dent->name; + nm.len = le16_to_cpu(dent->nlen); + kfree(pdent); + pdent = dent; + key_read(c, &dent->key, &key); + } + kfree(pdent); } void dbg_dump_node(const struct ubifs_info *c, const void *node) @@ -278,7 +320,7 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node) union ubifs_key key; const struct ubifs_ch *ch = node; - if (dbg_failure_mode) + if (dbg_is_tst_rcvry(c)) return; /* If the magic is incorrect, just hexdump the first bytes */ @@ -834,7 +876,7 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum) struct ubifs_scan_node *snod; void *buf; - if (dbg_failure_mode) + if (dbg_is_tst_rcvry(c)) return; printk(KERN_DEBUG "(pid %d) start dumping LEB %d\n", @@ -1080,6 +1122,7 @@ out: /** * dbg_check_synced_i_size - check synchronized inode size. + * @c: UBIFS file-system description object * @inode: inode to check * * If inode is clean, synchronized inode size has to be equivalent to current @@ -1087,12 +1130,12 @@ out: * has to be locked). Returns %0 if synchronized inode size if correct, and * %-EINVAL if not. */ -int dbg_check_synced_i_size(struct inode *inode) +int dbg_check_synced_i_size(const struct ubifs_info *c, struct inode *inode) { int err = 0; struct ubifs_inode *ui = ubifs_inode(inode); - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; if (!S_ISREG(inode->i_mode)) return 0; @@ -1125,7 +1168,7 @@ int dbg_check_synced_i_size(struct inode *inode) * Note, it is good idea to make sure the @dir->i_mutex is locked before * calling this function. */ -int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir) +int dbg_check_dir(struct ubifs_info *c, const struct inode *dir) { unsigned int nlink = 2; union ubifs_key key; @@ -1133,7 +1176,7 @@ int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir) struct qstr nm = { .name = NULL }; loff_t size = UBIFS_INO_NODE_SZ; - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; if (!S_ISDIR(dir->i_mode)) @@ -1167,12 +1210,14 @@ int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir) "but calculated size is %llu", dir->i_ino, (unsigned long long)i_size_read(dir), (unsigned long long)size); + dbg_dump_inode(c, dir); dump_stack(); return -EINVAL; } if (dir->i_nlink != nlink) { ubifs_err("directory inode %lu has nlink %u, but calculated " "nlink is %u", dir->i_ino, dir->i_nlink, nlink); + dbg_dump_inode(c, dir); dump_stack(); return -EINVAL; } @@ -1489,7 +1534,7 @@ int dbg_check_tnc(struct ubifs_info *c, int extra) long clean_cnt = 0, dirty_cnt = 0; int err, last; - if (!(ubifs_chk_flags & UBIFS_CHK_TNC)) + if (!dbg_is_chk_index(c)) return 0; ubifs_assert(mutex_is_locked(&c->tnc_mutex)); @@ -1736,7 +1781,7 @@ int dbg_check_idx_size(struct ubifs_info *c, long long idx_size) int err; long long calc = 0; - if (!(ubifs_chk_flags & UBIFS_CHK_IDX_SZ)) + if (!dbg_is_chk_index(c)) return 0; err = dbg_walk_index(c, NULL, add_size, &calc); @@ -2312,7 +2357,7 @@ int dbg_check_filesystem(struct ubifs_info *c) int err; struct fsck_data fsckd; - if (!(ubifs_chk_flags & UBIFS_CHK_FS)) + if (!dbg_is_chk_fs(c)) return 0; fsckd.inodes = RB_ROOT; @@ -2347,7 +2392,7 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) struct list_head *cur; struct ubifs_scan_node *sa, *sb; - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; for (cur = head->next; cur->next != head; cur = cur->next) { @@ -2414,7 +2459,7 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) struct list_head *cur; struct ubifs_scan_node *sa, *sb; - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; for (cur = head->next; cur->next != head; cur = cur->next) { @@ -2491,214 +2536,141 @@ error_dump: return 0; } -int dbg_force_in_the_gaps(void) +static inline int chance(unsigned int n, unsigned int out_of) { - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) - return 0; + return !!((random32() % out_of) + 1 <= n); - return !(random32() & 7); } -/* Failure mode for recovery testing */ - -#define chance(n, d) (simple_rand() <= (n) * 32768LL / (d)) - -struct failure_mode_info { - struct list_head list; - struct ubifs_info *c; -}; - -static LIST_HEAD(fmi_list); -static DEFINE_SPINLOCK(fmi_lock); - -static unsigned int next; - -static int simple_rand(void) -{ - if (next == 0) - next = current->pid; - next = next * 1103515245 + 12345; - return (next >> 16) & 32767; -} - -static void failure_mode_init(struct ubifs_info *c) -{ - struct failure_mode_info *fmi; - - fmi = kmalloc(sizeof(struct failure_mode_info), GFP_NOFS); - if (!fmi) { - ubifs_err("Failed to register failure mode - no memory"); - return; - } - fmi->c = c; - spin_lock(&fmi_lock); - list_add_tail(&fmi->list, &fmi_list); - spin_unlock(&fmi_lock); -} - -static void failure_mode_exit(struct ubifs_info *c) +static int power_cut_emulated(struct ubifs_info *c, int lnum, int write) { - struct failure_mode_info *fmi, *tmp; - - spin_lock(&fmi_lock); - list_for_each_entry_safe(fmi, tmp, &fmi_list, list) - if (fmi->c == c) { - list_del(&fmi->list); - kfree(fmi); - } - spin_unlock(&fmi_lock); -} - -static struct ubifs_info *dbg_find_info(struct ubi_volume_desc *desc) -{ - struct failure_mode_info *fmi; - - spin_lock(&fmi_lock); - list_for_each_entry(fmi, &fmi_list, list) - if (fmi->c->ubi == desc) { - struct ubifs_info *c = fmi->c; - - spin_unlock(&fmi_lock); - return c; - } - spin_unlock(&fmi_lock); - return NULL; -} - -static int in_failure_mode(struct ubi_volume_desc *desc) -{ - struct ubifs_info *c = dbg_find_info(desc); - - if (c && dbg_failure_mode) - return c->dbg->failure_mode; - return 0; -} + struct ubifs_debug_info *d = c->dbg; -static int do_fail(struct ubi_volume_desc *desc, int lnum, int write) -{ - struct ubifs_info *c = dbg_find_info(desc); - struct ubifs_debug_info *d; + ubifs_assert(dbg_is_tst_rcvry(c)); - if (!c || !dbg_failure_mode) - return 0; - d = c->dbg; - if (d->failure_mode) - return 1; - if (!d->fail_cnt) { - /* First call - decide delay to failure */ + if (!d->pc_cnt) { + /* First call - decide delay to the power cut */ if (chance(1, 2)) { - unsigned int delay = 1 << (simple_rand() >> 11); + unsigned long delay; if (chance(1, 2)) { - d->fail_delay = 1; - d->fail_timeout = jiffies + - msecs_to_jiffies(delay); - dbg_rcvry("failing after %ums", delay); + d->pc_delay = 1; + /* Fail withing 1 minute */ + delay = random32() % 60000; + d->pc_timeout = jiffies; + d->pc_timeout += msecs_to_jiffies(delay); + ubifs_warn("failing after %lums", delay); } else { - d->fail_delay = 2; - d->fail_cnt_max = delay; - dbg_rcvry("failing after %u calls", delay); + d->pc_delay = 2; + delay = random32() % 10000; + /* Fail within 10000 operations */ + d->pc_cnt_max = delay; + ubifs_warn("failing after %lu calls", delay); } } - d->fail_cnt += 1; + + d->pc_cnt += 1; } + /* Determine if failure delay has expired */ - if (d->fail_delay == 1) { - if (time_before(jiffies, d->fail_timeout)) + if (d->pc_delay == 1 && time_before(jiffies, d->pc_timeout)) return 0; - } else if (d->fail_delay == 2) - if (d->fail_cnt++ < d->fail_cnt_max) + if (d->pc_delay == 2 && d->pc_cnt++ < d->pc_cnt_max) return 0; + if (lnum == UBIFS_SB_LNUM) { - if (write) { - if (chance(1, 2)) - return 0; - } else if (chance(19, 20)) + if (write && chance(1, 2)) + return 0; + if (chance(19, 20)) return 0; - dbg_rcvry("failing in super block LEB %d", lnum); + ubifs_warn("failing in super block LEB %d", lnum); } else if (lnum == UBIFS_MST_LNUM || lnum == UBIFS_MST_LNUM + 1) { if (chance(19, 20)) return 0; - dbg_rcvry("failing in master LEB %d", lnum); + ubifs_warn("failing in master LEB %d", lnum); } else if (lnum >= UBIFS_LOG_LNUM && lnum <= c->log_last) { - if (write) { - if (chance(99, 100)) - return 0; - } else if (chance(399, 400)) + if (write && chance(99, 100)) return 0; - dbg_rcvry("failing in log LEB %d", lnum); + if (chance(399, 400)) + return 0; + ubifs_warn("failing in log LEB %d", lnum); } else if (lnum >= c->lpt_first && lnum <= c->lpt_last) { - if (write) { - if (chance(7, 8)) - return 0; - } else if (chance(19, 20)) + if (write && chance(7, 8)) return 0; - dbg_rcvry("failing in LPT LEB %d", lnum); + if (chance(19, 20)) + return 0; + ubifs_warn("failing in LPT LEB %d", lnum); } else if (lnum >= c->orph_first && lnum <= c->orph_last) { - if (write) { - if (chance(1, 2)) - return 0; - } else if (chance(9, 10)) + if (write && chance(1, 2)) + return 0; + if (chance(9, 10)) return 0; - dbg_rcvry("failing in orphan LEB %d", lnum); + ubifs_warn("failing in orphan LEB %d", lnum); } else if (lnum == c->ihead_lnum) { if (chance(99, 100)) return 0; - dbg_rcvry("failing in index head LEB %d", lnum); + ubifs_warn("failing in index head LEB %d", lnum); } else if (c->jheads && lnum == c->jheads[GCHD].wbuf.lnum) { if (chance(9, 10)) return 0; - dbg_rcvry("failing in GC head LEB %d", lnum); + ubifs_warn("failing in GC head LEB %d", lnum); } else if (write && !RB_EMPTY_ROOT(&c->buds) && !ubifs_search_bud(c, lnum)) { if (chance(19, 20)) return 0; - dbg_rcvry("failing in non-bud LEB %d", lnum); + ubifs_warn("failing in non-bud LEB %d", lnum); } else if (c->cmt_state == COMMIT_RUNNING_BACKGROUND || c->cmt_state == COMMIT_RUNNING_REQUIRED) { if (chance(999, 1000)) return 0; - dbg_rcvry("failing in bud LEB %d commit running", lnum); + ubifs_warn("failing in bud LEB %d commit running", lnum); } else { if (chance(9999, 10000)) return 0; - dbg_rcvry("failing in bud LEB %d commit not running", lnum); + ubifs_warn("failing in bud LEB %d commit not running", lnum); } - ubifs_err("*** SETTING FAILURE MODE ON (LEB %d) ***", lnum); - d->failure_mode = 1; + + d->pc_happened = 1; + ubifs_warn("========== Power cut emulated =========="); dump_stack(); return 1; } -static void cut_data(const void *buf, int len) +static void cut_data(const void *buf, unsigned int len) { - int flen, i; + unsigned int from, to, i, ffs = chance(1, 2); unsigned char *p = (void *)buf; - flen = (len * (long long)simple_rand()) >> 15; - for (i = flen; i < len; i++) - p[i] = 0xff; -} + from = random32() % (len + 1); + if (chance(1, 2)) + to = random32() % (len - from + 1); + else + to = len; -int dbg_leb_read(struct ubi_volume_desc *desc, int lnum, char *buf, int offset, - int len, int check) -{ - if (in_failure_mode(desc)) - return -EROFS; - return ubi_leb_read(desc, lnum, buf, offset, len, check); + if (from < to) + ubifs_warn("filled bytes %u-%u with %s", from, to - 1, + ffs ? "0xFFs" : "random data"); + + if (ffs) + for (i = from; i < to; i++) + p[i] = 0xFF; + else + for (i = from; i < to; i++) + p[i] = random32() % 0x100; } -int dbg_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf, - int offset, int len, int dtype) +int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, + int offs, int len, int dtype) { int err, failing; - if (in_failure_mode(desc)) + if (c->dbg->pc_happened) return -EROFS; - failing = do_fail(desc, lnum, 1); + + failing = power_cut_emulated(c, lnum, 1); if (failing) cut_data(buf, len); - err = ubi_leb_write(desc, lnum, buf, offset, len, dtype); + err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype); if (err) return err; if (failing) @@ -2706,162 +2678,207 @@ int dbg_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf, return 0; } -int dbg_leb_change(struct ubi_volume_desc *desc, int lnum, const void *buf, +int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, int dtype) { int err; - if (do_fail(desc, lnum, 1)) + if (c->dbg->pc_happened) return -EROFS; - err = ubi_leb_change(desc, lnum, buf, len, dtype); + if (power_cut_emulated(c, lnum, 1)) + return -EROFS; + err = ubi_leb_change(c->ubi, lnum, buf, len, dtype); if (err) return err; - if (do_fail(desc, lnum, 1)) + if (power_cut_emulated(c, lnum, 1)) return -EROFS; return 0; } -int dbg_leb_erase(struct ubi_volume_desc *desc, int lnum) +int dbg_leb_unmap(struct ubifs_info *c, int lnum) { int err; - if (do_fail(desc, lnum, 0)) + if (c->dbg->pc_happened) + return -EROFS; + if (power_cut_emulated(c, lnum, 0)) return -EROFS; - err = ubi_leb_erase(desc, lnum); + err = ubi_leb_unmap(c->ubi, lnum); if (err) return err; - if (do_fail(desc, lnum, 0)) + if (power_cut_emulated(c, lnum, 0)) return -EROFS; return 0; } -int dbg_leb_unmap(struct ubi_volume_desc *desc, int lnum) +int dbg_leb_map(struct ubifs_info *c, int lnum, int dtype) { int err; - if (do_fail(desc, lnum, 0)) + if (c->dbg->pc_happened) return -EROFS; - err = ubi_leb_unmap(desc, lnum); + if (power_cut_emulated(c, lnum, 0)) + return -EROFS; + err = ubi_leb_map(c->ubi, lnum, dtype); if (err) return err; - if (do_fail(desc, lnum, 0)) + if (power_cut_emulated(c, lnum, 0)) return -EROFS; return 0; } -int dbg_is_mapped(struct ubi_volume_desc *desc, int lnum) -{ - if (in_failure_mode(desc)) - return -EROFS; - return ubi_is_mapped(desc, lnum); -} +/* + * Root directory for UBIFS stuff in debugfs. Contains sub-directories which + * contain the stuff specific to particular file-system mounts. + */ +static struct dentry *dfs_rootdir; -int dbg_leb_map(struct ubi_volume_desc *desc, int lnum, int dtype) +static int dfs_file_open(struct inode *inode, struct file *file) { - int err; - - if (do_fail(desc, lnum, 0)) - return -EROFS; - err = ubi_leb_map(desc, lnum, dtype); - if (err) - return err; - if (do_fail(desc, lnum, 0)) - return -EROFS; - return 0; + file->private_data = inode->i_private; + return nonseekable_open(inode, file); } /** - * ubifs_debugging_init - initialize UBIFS debugging. - * @c: UBIFS file-system description object + * provide_user_output - provide output to the user reading a debugfs file. + * @val: boolean value for the answer + * @u: the buffer to store the answer at + * @count: size of the buffer + * @ppos: position in the @u output buffer * - * This function initializes debugging-related data for the file system. - * Returns zero in case of success and a negative error code in case of + * This is a simple helper function which stores @val boolean value in the user + * buffer when the user reads one of UBIFS debugfs files. Returns amount of + * bytes written to @u in case of success and a negative error code in case of * failure. */ -int ubifs_debugging_init(struct ubifs_info *c) +static int provide_user_output(int val, char __user *u, size_t count, + loff_t *ppos) { - c->dbg = kzalloc(sizeof(struct ubifs_debug_info), GFP_KERNEL); - if (!c->dbg) - return -ENOMEM; + char buf[3]; - failure_mode_init(c); - return 0; + if (val) + buf[0] = '1'; + else + buf[0] = '0'; + buf[1] = '\n'; + buf[2] = 0x00; + + return simple_read_from_buffer(u, count, ppos, buf, 2); } -/** - * ubifs_debugging_exit - free debugging data. - * @c: UBIFS file-system description object - */ -void ubifs_debugging_exit(struct ubifs_info *c) +static ssize_t dfs_file_read(struct file *file, char __user *u, size_t count, + loff_t *ppos) { - failure_mode_exit(c); - kfree(c->dbg); -} + struct dentry *dent = file->f_path.dentry; + struct ubifs_info *c = file->private_data; + struct ubifs_debug_info *d = c->dbg; + int val; + + if (dent == d->dfs_chk_gen) + val = d->chk_gen; + else if (dent == d->dfs_chk_index) + val = d->chk_index; + else if (dent == d->dfs_chk_orph) + val = d->chk_orph; + else if (dent == d->dfs_chk_lprops) + val = d->chk_lprops; + else if (dent == d->dfs_chk_fs) + val = d->chk_fs; + else if (dent == d->dfs_tst_rcvry) + val = d->tst_rcvry; + else + return -EINVAL; -/* - * Root directory for UBIFS stuff in debugfs. Contains sub-directories which - * contain the stuff specific to particular file-system mounts. - */ -static struct dentry *dfs_rootdir; + return provide_user_output(val, u, count, ppos); +} /** - * dbg_debugfs_init - initialize debugfs file-system. + * interpret_user_input - interpret user debugfs file input. + * @u: user-provided buffer with the input + * @count: buffer size * - * UBIFS uses debugfs file-system to expose various debugging knobs to - * user-space. This function creates "ubifs" directory in the debugfs - * file-system. Returns zero in case of success and a negative error code in - * case of failure. + * This is a helper function which interpret user input to a boolean UBIFS + * debugfs file. Returns %0 or %1 in case of success and a negative error code + * in case of failure. */ -int dbg_debugfs_init(void) +static int interpret_user_input(const char __user *u, size_t count) { - dfs_rootdir = debugfs_create_dir("ubifs", NULL); - if (IS_ERR(dfs_rootdir)) { - int err = PTR_ERR(dfs_rootdir); - ubifs_err("cannot create \"ubifs\" debugfs directory, " - "error %d\n", err); - return err; - } + size_t buf_size; + char buf[8]; - return 0; -} + buf_size = min_t(size_t, count, (sizeof(buf) - 1)); + if (copy_from_user(buf, u, buf_size)) + return -EFAULT; -/** - * dbg_debugfs_exit - remove the "ubifs" directory from debugfs file-system. - */ -void dbg_debugfs_exit(void) -{ - debugfs_remove(dfs_rootdir); -} + if (buf[0] == '1') + return 1; + else if (buf[0] == '0') + return 0; -static int open_debugfs_file(struct inode *inode, struct file *file) -{ - file->private_data = inode->i_private; - return nonseekable_open(inode, file); + return -EINVAL; } -static ssize_t write_debugfs_file(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t dfs_file_write(struct file *file, const char __user *u, + size_t count, loff_t *ppos) { struct ubifs_info *c = file->private_data; struct ubifs_debug_info *d = c->dbg; + struct dentry *dent = file->f_path.dentry; + int val; - if (file->f_path.dentry == d->dfs_dump_lprops) + /* + * TODO: this is racy - the file-system might have already been + * unmounted and we'd oops in this case. The plan is to fix it with + * help of 'iterate_supers_type()' which we should have in v3.0: when + * a debugfs opened, we rember FS's UUID in file->private_data. Then + * whenever we access the FS via a debugfs file, we iterate all UBIFS + * superblocks and fine the one with the same UUID, and take the + * locking right. + * + * The other way to go suggested by Al Viro is to create a separate + * 'ubifs-debug' file-system instead. + */ + if (file->f_path.dentry == d->dfs_dump_lprops) { dbg_dump_lprops(c); - else if (file->f_path.dentry == d->dfs_dump_budg) + return count; + } + if (file->f_path.dentry == d->dfs_dump_budg) { dbg_dump_budg(c, &c->bi); - else if (file->f_path.dentry == d->dfs_dump_tnc) { + return count; + } + if (file->f_path.dentry == d->dfs_dump_tnc) { mutex_lock(&c->tnc_mutex); dbg_dump_tnc(c); mutex_unlock(&c->tnc_mutex); - } else + return count; + } + + val = interpret_user_input(u, count); + if (val < 0) + return val; + + if (dent == d->dfs_chk_gen) + d->chk_gen = val; + else if (dent == d->dfs_chk_index) + d->chk_index = val; + else if (dent == d->dfs_chk_orph) + d->chk_orph = val; + else if (dent == d->dfs_chk_lprops) + d->chk_lprops = val; + else if (dent == d->dfs_chk_fs) + d->chk_fs = val; + else if (dent == d->dfs_tst_rcvry) + d->tst_rcvry = val; + else return -EINVAL; return count; } static const struct file_operations dfs_fops = { - .open = open_debugfs_file, - .write = write_debugfs_file, + .open = dfs_file_open, + .read = dfs_file_read, + .write = dfs_file_write, .owner = THIS_MODULE, .llseek = no_llseek, }; @@ -2880,12 +2897,20 @@ static const struct file_operations dfs_fops = { */ int dbg_debugfs_init_fs(struct ubifs_info *c) { - int err; + int err, n; const char *fname; struct dentry *dent; struct ubifs_debug_info *d = c->dbg; - sprintf(d->dfs_dir_name, "ubi%d_%d", c->vi.ubi_num, c->vi.vol_id); + n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME, + c->vi.ubi_num, c->vi.vol_id); + if (n == UBIFS_DFS_DIR_LEN) { + /* The array size is too small */ + fname = UBIFS_DFS_DIR_NAME; + dent = ERR_PTR(-EINVAL); + goto out; + } + fname = d->dfs_dir_name; dent = debugfs_create_dir(fname, dfs_rootdir); if (IS_ERR_OR_NULL(dent)) @@ -2910,13 +2935,55 @@ int dbg_debugfs_init_fs(struct ubifs_info *c) goto out_remove; d->dfs_dump_tnc = dent; + fname = "chk_general"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_gen = dent; + + fname = "chk_index"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_index = dent; + + fname = "chk_orphans"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_orph = dent; + + fname = "chk_lprops"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_lprops = dent; + + fname = "chk_fs"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_chk_fs = dent; + + fname = "tst_recovery"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, + &dfs_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + d->dfs_tst_rcvry = dent; + return 0; out_remove: debugfs_remove_recursive(d->dfs_dir); out: err = dent ? PTR_ERR(dent) : -ENODEV; - ubifs_err("cannot create \"%s\" debugfs directory, error %d\n", + ubifs_err("cannot create \"%s\" debugfs file or directory, error %d\n", fname, err); return err; } @@ -2930,4 +2997,179 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c) debugfs_remove_recursive(c->dbg->dfs_dir); } +struct ubifs_global_debug_info ubifs_dbg; + +static struct dentry *dfs_chk_gen; +static struct dentry *dfs_chk_index; +static struct dentry *dfs_chk_orph; +static struct dentry *dfs_chk_lprops; +static struct dentry *dfs_chk_fs; +static struct dentry *dfs_tst_rcvry; + +static ssize_t dfs_global_file_read(struct file *file, char __user *u, + size_t count, loff_t *ppos) +{ + struct dentry *dent = file->f_path.dentry; + int val; + + if (dent == dfs_chk_gen) + val = ubifs_dbg.chk_gen; + else if (dent == dfs_chk_index) + val = ubifs_dbg.chk_index; + else if (dent == dfs_chk_orph) + val = ubifs_dbg.chk_orph; + else if (dent == dfs_chk_lprops) + val = ubifs_dbg.chk_lprops; + else if (dent == dfs_chk_fs) + val = ubifs_dbg.chk_fs; + else if (dent == dfs_tst_rcvry) + val = ubifs_dbg.tst_rcvry; + else + return -EINVAL; + + return provide_user_output(val, u, count, ppos); +} + +static ssize_t dfs_global_file_write(struct file *file, const char __user *u, + size_t count, loff_t *ppos) +{ + struct dentry *dent = file->f_path.dentry; + int val; + + val = interpret_user_input(u, count); + if (val < 0) + return val; + + if (dent == dfs_chk_gen) + ubifs_dbg.chk_gen = val; + else if (dent == dfs_chk_index) + ubifs_dbg.chk_index = val; + else if (dent == dfs_chk_orph) + ubifs_dbg.chk_orph = val; + else if (dent == dfs_chk_lprops) + ubifs_dbg.chk_lprops = val; + else if (dent == dfs_chk_fs) + ubifs_dbg.chk_fs = val; + else if (dent == dfs_tst_rcvry) + ubifs_dbg.tst_rcvry = val; + else + return -EINVAL; + + return count; +} + +static const struct file_operations dfs_global_fops = { + .read = dfs_global_file_read, + .write = dfs_global_file_write, + .owner = THIS_MODULE, + .llseek = no_llseek, +}; + +/** + * dbg_debugfs_init - initialize debugfs file-system. + * + * UBIFS uses debugfs file-system to expose various debugging knobs to + * user-space. This function creates "ubifs" directory in the debugfs + * file-system. Returns zero in case of success and a negative error code in + * case of failure. + */ +int dbg_debugfs_init(void) +{ + int err; + const char *fname; + struct dentry *dent; + + fname = "ubifs"; + dent = debugfs_create_dir(fname, NULL); + if (IS_ERR_OR_NULL(dent)) + goto out; + dfs_rootdir = dent; + + fname = "chk_general"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, + &dfs_global_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + dfs_chk_gen = dent; + + fname = "chk_index"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, + &dfs_global_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + dfs_chk_index = dent; + + fname = "chk_orphans"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, + &dfs_global_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + dfs_chk_orph = dent; + + fname = "chk_lprops"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, + &dfs_global_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + dfs_chk_lprops = dent; + + fname = "chk_fs"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, + &dfs_global_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + dfs_chk_fs = dent; + + fname = "tst_recovery"; + dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, + &dfs_global_fops); + if (IS_ERR_OR_NULL(dent)) + goto out_remove; + dfs_tst_rcvry = dent; + + return 0; + +out_remove: + debugfs_remove_recursive(dfs_rootdir); +out: + err = dent ? PTR_ERR(dent) : -ENODEV; + ubifs_err("cannot create \"%s\" debugfs file or directory, error %d\n", + fname, err); + return err; +} + +/** + * dbg_debugfs_exit - remove the "ubifs" directory from debugfs file-system. + */ +void dbg_debugfs_exit(void) +{ + debugfs_remove_recursive(dfs_rootdir); +} + +/** + * ubifs_debugging_init - initialize UBIFS debugging. + * @c: UBIFS file-system description object + * + * This function initializes debugging-related data for the file system. + * Returns zero in case of success and a negative error code in case of + * failure. + */ +int ubifs_debugging_init(struct ubifs_info *c) +{ + c->dbg = kzalloc(sizeof(struct ubifs_debug_info), GFP_KERNEL); + if (!c->dbg) + return -ENOMEM; + + return 0; +} + +/** + * ubifs_debugging_exit - free debugging data. + * @c: UBIFS file-system description object + */ +void ubifs_debugging_exit(struct ubifs_info *c) +{ + kfree(c->dbg); +} + #endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index a811ac4..45174b5 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -31,18 +31,25 @@ typedef int (*dbg_znode_callback)(struct ubifs_info *c, #ifdef CONFIG_UBIFS_FS_DEBUG -#include <linux/random.h> +/* + * The UBIFS debugfs directory name pattern and maximum name length (3 for "ubi" + * + 1 for "_" and plus 2x2 for 2 UBI numbers and 1 for the trailing zero byte. + */ +#define UBIFS_DFS_DIR_NAME "ubi%d_%d" +#define UBIFS_DFS_DIR_LEN (3 + 1 + 2*2 + 1) /** * ubifs_debug_info - per-FS debugging information. * @old_zroot: old index root - used by 'dbg_check_old_index()' * @old_zroot_level: old index root level - used by 'dbg_check_old_index()' * @old_zroot_sqnum: old index root sqnum - used by 'dbg_check_old_index()' - * @failure_mode: failure mode for recovery testing - * @fail_delay: 0=>don't delay, 1=>delay a time, 2=>delay a number of calls - * @fail_timeout: time in jiffies when delay of failure mode expires - * @fail_cnt: current number of calls to failure mode I/O functions - * @fail_cnt_max: number of calls by which to delay failure mode + * + * @pc_happened: non-zero if an emulated power cut happened + * @pc_delay: 0=>don't delay, 1=>delay a time, 2=>delay a number of calls + * @pc_timeout: time in jiffies when delay of failure mode expires + * @pc_cnt: current number of calls to failure mode I/O functions + * @pc_cnt_max: number of calls by which to delay failure mode + * * @chk_lpt_sz: used by LPT tree size checker * @chk_lpt_sz2: used by LPT tree size checker * @chk_lpt_wastage: used by LPT tree size checker @@ -56,21 +63,36 @@ typedef int (*dbg_znode_callback)(struct ubifs_info *c, * @saved_free: saved amount of free space * @saved_idx_gc_cnt: saved value of @c->idx_gc_cnt * + * @chk_gen: if general extra checks are enabled + * @chk_index: if index xtra checks are enabled + * @chk_orph: if orphans extra checks are enabled + * @chk_lprops: if lprops extra checks are enabled + * @chk_fs: if UBIFS contents extra checks are enabled + * @tst_rcvry: if UBIFS recovery testing mode enabled + * * @dfs_dir_name: name of debugfs directory containing this file-system's files * @dfs_dir: direntry object of the file-system debugfs directory * @dfs_dump_lprops: "dump lprops" debugfs knob * @dfs_dump_budg: "dump budgeting information" debugfs knob * @dfs_dump_tnc: "dump TNC" debugfs knob + * @dfs_chk_gen: debugfs knob to enable UBIFS general extra checks + * @dfs_chk_index: debugfs knob to enable UBIFS index extra checks + * @dfs_chk_orph: debugfs knob to enable UBIFS orphans extra checks + * @dfs_chk_lprops: debugfs knob to enable UBIFS LEP properties extra checks + * @dfs_chk_fs: debugfs knob to enable UBIFS contents extra checks + * @dfs_tst_rcvry: debugfs knob to enable UBIFS recovery testing */ struct ubifs_debug_info { struct ubifs_zbranch old_zroot; int old_zroot_level; unsigned long long old_zroot_sqnum; - int failure_mode; - int fail_delay; - unsigned long fail_timeout; - unsigned int fail_cnt; - unsigned int fail_cnt_max; + + int pc_happened; + int pc_delay; + unsigned long pc_timeout; + unsigned int pc_cnt; + unsigned int pc_cnt_max; + long long chk_lpt_sz; long long chk_lpt_sz2; long long chk_lpt_wastage; @@ -84,11 +106,43 @@ struct ubifs_debug_info { long long saved_free; int saved_idx_gc_cnt; - char dfs_dir_name[100]; + unsigned int chk_gen:1; + unsigned int chk_index:1; + unsigned int chk_orph:1; + unsigned int chk_lprops:1; + unsigned int chk_fs:1; + unsigned int tst_rcvry:1; + + char dfs_dir_name[UBIFS_DFS_DIR_LEN + 1]; struct dentry *dfs_dir; struct dentry *dfs_dump_lprops; struct dentry *dfs_dump_budg; struct dentry *dfs_dump_tnc; + struct dentry *dfs_chk_gen; + struct dentry *dfs_chk_index; + struct dentry *dfs_chk_orph; + struct dentry *dfs_chk_lprops; + struct dentry *dfs_chk_fs; + struct dentry *dfs_tst_rcvry; +}; + +/** + * ubifs_global_debug_info - global (not per-FS) UBIFS debugging information. + * + * @chk_gen: if general extra checks are enabled + * @chk_index: if index xtra checks are enabled + * @chk_orph: if orphans extra checks are enabled + * @chk_lprops: if lprops extra checks are enabled + * @chk_fs: if UBIFS contents extra checks are enabled + * @tst_rcvry: if UBIFS recovery testing mode enabled + */ +struct ubifs_global_debug_info { + unsigned int chk_gen:1; + unsigned int chk_index:1; + unsigned int chk_orph:1; + unsigned int chk_lprops:1; + unsigned int chk_fs:1; + unsigned int tst_rcvry:1; }; #define ubifs_assert(expr) do { \ @@ -127,6 +181,8 @@ const char *dbg_key_str1(const struct ubifs_info *c, #define DBGKEY(key) dbg_key_str0(c, (key)) #define DBGKEY1(key) dbg_key_str1(c, (key)) +extern spinlock_t dbg_lock; + #define ubifs_dbg_msg(type, fmt, ...) do { \ spin_lock(&dbg_lock); \ pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__); \ @@ -162,41 +218,36 @@ const char *dbg_key_str1(const struct ubifs_info *c, /* Additional recovery messages */ #define dbg_rcvry(fmt, ...) ubifs_dbg_msg("rcvry", fmt, ##__VA_ARGS__) -/* - * Debugging check flags. - * - * UBIFS_CHK_GEN: general checks - * UBIFS_CHK_TNC: check TNC - * UBIFS_CHK_IDX_SZ: check index size - * UBIFS_CHK_ORPH: check orphans - * UBIFS_CHK_OLD_IDX: check the old index - * UBIFS_CHK_LPROPS: check lprops - * UBIFS_CHK_FS: check the file-system - */ -enum { - UBIFS_CHK_GEN = 0x1, - UBIFS_CHK_TNC = 0x2, - UBIFS_CHK_IDX_SZ = 0x4, - UBIFS_CHK_ORPH = 0x8, - UBIFS_CHK_OLD_IDX = 0x10, - UBIFS_CHK_LPROPS = 0x20, - UBIFS_CHK_FS = 0x40, -}; - -/* - * Special testing flags. - * - * UBIFS_TST_RCVRY: failure mode for recovery testing - */ -enum { - UBIFS_TST_RCVRY = 0x4, -}; - -extern spinlock_t dbg_lock; +extern struct ubifs_global_debug_info ubifs_dbg; -extern unsigned int ubifs_msg_flags; -extern unsigned int ubifs_chk_flags; -extern unsigned int ubifs_tst_flags; +static inline int dbg_is_chk_gen(const struct ubifs_info *c) +{ + return !!(ubifs_dbg.chk_gen || c->dbg->chk_gen); +} +static inline int dbg_is_chk_index(const struct ubifs_info *c) +{ + return !!(ubifs_dbg.chk_index || c->dbg->chk_index); +} +static inline int dbg_is_chk_orph(const struct ubifs_info *c) +{ + return !!(ubifs_dbg.chk_orph || c->dbg->chk_orph); +} +static inline int dbg_is_chk_lprops(const struct ubifs_info *c) +{ + return !!(ubifs_dbg.chk_lprops || c->dbg->chk_lprops); +} +static inline int dbg_is_chk_fs(const struct ubifs_info *c) +{ + return !!(ubifs_dbg.chk_fs || c->dbg->chk_fs); +} +static inline int dbg_is_tst_rcvry(const struct ubifs_info *c) +{ + return !!(ubifs_dbg.tst_rcvry || c->dbg->tst_rcvry); +} +static inline int dbg_is_power_cut(const struct ubifs_info *c) +{ + return !!c->dbg->pc_happened; +} int ubifs_debugging_init(struct ubifs_info *c); void ubifs_debugging_exit(struct ubifs_info *c); @@ -207,7 +258,7 @@ const char *dbg_cstate(int cmt_state); const char *dbg_jhead(int jhead); const char *dbg_get_key_dump(const struct ubifs_info *c, const union ubifs_key *key); -void dbg_dump_inode(const struct ubifs_info *c, const struct inode *inode); +void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode); void dbg_dump_node(const struct ubifs_info *c, const void *node); void dbg_dump_lpt_node(const struct ubifs_info *c, void *node, int lnum, int offs); @@ -240,8 +291,8 @@ int dbg_check_cats(struct ubifs_info *c); int dbg_check_ltab(struct ubifs_info *c); int dbg_chk_lpt_free_spc(struct ubifs_info *c); int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len); -int dbg_check_synced_i_size(struct inode *inode); -int dbg_check_dir_size(struct ubifs_info *c, const struct inode *dir); +int dbg_check_synced_i_size(const struct ubifs_info *c, struct inode *inode); +int dbg_check_dir(struct ubifs_info *c, const struct inode *dir); int dbg_check_tnc(struct ubifs_info *c, int extra); int dbg_check_idx_size(struct ubifs_info *c, long long idx_size); int dbg_check_filesystem(struct ubifs_info *c); @@ -254,54 +305,12 @@ int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode, int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head); int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head); -/* Force the use of in-the-gaps method for testing */ -static inline int dbg_force_in_the_gaps_enabled(void) -{ - return ubifs_chk_flags & UBIFS_CHK_GEN; -} -int dbg_force_in_the_gaps(void); - -/* Failure mode for recovery testing */ -#define dbg_failure_mode (ubifs_tst_flags & UBIFS_TST_RCVRY) - -#ifndef UBIFS_DBG_PRESERVE_UBI -#define ubi_leb_read dbg_leb_read -#define ubi_leb_write dbg_leb_write -#define ubi_leb_change dbg_leb_change -#define ubi_leb_erase dbg_leb_erase -#define ubi_leb_unmap dbg_leb_unmap -#define ubi_is_mapped dbg_is_mapped -#define ubi_leb_map dbg_leb_map -#endif - -int dbg_leb_read(struct ubi_volume_desc *desc, int lnum, char *buf, int offset, - int len, int check); -int dbg_leb_write(struct ubi_volume_desc *desc, int lnum, const void *buf, - int offset, int len, int dtype); -int dbg_leb_change(struct ubi_volume_desc *desc, int lnum, const void *buf, - int len, int dtype); -int dbg_leb_erase(struct ubi_volume_desc *desc, int lnum); -int dbg_leb_unmap(struct ubi_volume_desc *desc, int lnum); -int dbg_is_mapped(struct ubi_volume_desc *desc, int lnum); -int dbg_leb_map(struct ubi_volume_desc *desc, int lnum, int dtype); - -static inline int dbg_read(struct ubi_volume_desc *desc, int lnum, char *buf, - int offset, int len) -{ - return dbg_leb_read(desc, lnum, buf, offset, len, 0); -} - -static inline int dbg_write(struct ubi_volume_desc *desc, int lnum, - const void *buf, int offset, int len) -{ - return dbg_leb_write(desc, lnum, buf, offset, len, UBI_UNKNOWN); -} - -static inline int dbg_change(struct ubi_volume_desc *desc, int lnum, - const void *buf, int len) -{ - return dbg_leb_change(desc, lnum, buf, len, UBI_UNKNOWN); -} +int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, + int len, int dtype); +int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, + int dtype); +int dbg_leb_unmap(struct ubifs_info *c, int lnum); +int dbg_leb_map(struct ubifs_info *c, int lnum, int dtype); /* Debugfs-related stuff */ int dbg_debugfs_init(void); @@ -313,7 +322,7 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c); /* Use "if (0)" to make compiler check arguments even if debugging is off */ #define ubifs_assert(expr) do { \ - if (0 && (expr)) \ + if (0) \ printk(KERN_CRIT "UBIFS assert failed in %s at %u (pid %d)\n", \ __func__, __LINE__, current->pid); \ } while (0) @@ -323,6 +332,9 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c); ubifs_err(fmt, ##__VA_ARGS__); \ } while (0) +#define DBGKEY(key) ((char *)(key)) +#define DBGKEY1(key) ((char *)(key)) + #define ubifs_dbg_msg(fmt, ...) do { \ if (0) \ pr_debug(fmt "\n", ##__VA_ARGS__); \ @@ -346,9 +358,6 @@ void dbg_debugfs_exit_fs(struct ubifs_info *c); #define dbg_scan(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) #define dbg_rcvry(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define DBGKEY(key) ((char *)(key)) -#define DBGKEY1(key) ((char *)(key)) - static inline int ubifs_debugging_init(struct ubifs_info *c) { return 0; } static inline void ubifs_debugging_exit(struct ubifs_info *c) { return; } static inline const char *dbg_ntype(int type) { return ""; } @@ -357,7 +366,7 @@ static inline const char *dbg_jhead(int jhead) { return ""; } static inline const char * dbg_get_key_dump(const struct ubifs_info *c, const union ubifs_key *key) { return ""; } -static inline void dbg_dump_inode(const struct ubifs_info *c, +static inline void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode) { return; } static inline void dbg_dump_node(const struct ubifs_info *c, const void *node) { return; } @@ -409,9 +418,11 @@ static inline int dbg_check_ltab(struct ubifs_info *c) { return 0; } static inline int dbg_chk_lpt_free_spc(struct ubifs_info *c) { return 0; } static inline int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) { return 0; } -static inline int dbg_check_synced_i_size(struct inode *inode) { return 0; } -static inline int dbg_check_dir_size(struct ubifs_info *c, - const struct inode *dir) { return 0; } +static inline int +dbg_check_synced_i_size(const struct ubifs_info *c, + struct inode *inode) { return 0; } +static inline int dbg_check_dir(struct ubifs_info *c, + const struct inode *dir) { return 0; } static inline int dbg_check_tnc(struct ubifs_info *c, int extra) { return 0; } static inline int dbg_check_idx_size(struct ubifs_info *c, long long idx_size) { return 0; } @@ -431,9 +442,23 @@ static inline int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) { return 0; } -static inline int dbg_force_in_the_gaps(void) { return 0; } -#define dbg_force_in_the_gaps_enabled() 0 -#define dbg_failure_mode 0 +static inline int dbg_leb_write(struct ubifs_info *c, int lnum, + const void *buf, int offset, + int len, int dtype) { return 0; } +static inline int dbg_leb_change(struct ubifs_info *c, int lnum, + const void *buf, int len, + int dtype) { return 0; } +static inline int dbg_leb_unmap(struct ubifs_info *c, int lnum) { return 0; } +static inline int dbg_leb_map(struct ubifs_info *c, int lnum, + int dtype) { return 0; } + +static inline int dbg_is_chk_gen(const struct ubifs_info *c) { return 0; } +static inline int dbg_is_chk_index(const struct ubifs_info *c) { return 0; } +static inline int dbg_is_chk_orph(const struct ubifs_info *c) { return 0; } +static inline int dbg_is_chk_lprops(const struct ubifs_info *c) { return 0; } +static inline int dbg_is_chk_fs(const struct ubifs_info *c) { return 0; } +static inline int dbg_is_tst_rcvry(const struct ubifs_info *c) { return 0; } +static inline int dbg_is_power_cut(const struct ubifs_info *c) { return 0; } static inline int dbg_debugfs_init(void) { return 0; } static inline void dbg_debugfs_exit(void) { return; } diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index ef5abd3..6834920 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -102,7 +102,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, * UBIFS has to fully control "clean <-> dirty" transitions of inodes * to make budgeting work. */ - inode->i_flags |= (S_NOCMTIME); + inode->i_flags |= S_NOCMTIME; inode_init_owner(inode, dir, mode); inode->i_mtime = inode->i_atime = inode->i_ctime = @@ -172,9 +172,11 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, #ifdef CONFIG_UBIFS_FS_DEBUG -static int dbg_check_name(struct ubifs_dent_node *dent, struct qstr *nm) +static int dbg_check_name(const struct ubifs_info *c, + const struct ubifs_dent_node *dent, + const struct qstr *nm) { - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; if (le16_to_cpu(dent->nlen) != nm->len) return -EINVAL; @@ -185,7 +187,7 @@ static int dbg_check_name(struct ubifs_dent_node *dent, struct qstr *nm) #else -#define dbg_check_name(dent, nm) 0 +#define dbg_check_name(c, dent, nm) 0 #endif @@ -219,7 +221,7 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, goto out; } - if (dbg_check_name(dent, &dentry->d_name)) { + if (dbg_check_name(c, dent, &dentry->d_name)) { err = -EINVAL; goto out; } @@ -522,7 +524,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir, ubifs_assert(mutex_is_locked(&dir->i_mutex)); ubifs_assert(mutex_is_locked(&inode->i_mutex)); - err = dbg_check_synced_i_size(inode); + err = dbg_check_synced_i_size(c, inode); if (err) return err; @@ -577,7 +579,7 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry) inode->i_nlink, dir->i_ino); ubifs_assert(mutex_is_locked(&dir->i_mutex)); ubifs_assert(mutex_is_locked(&inode->i_mutex)); - err = dbg_check_synced_i_size(inode); + err = dbg_check_synced_i_size(c, inode); if (err) return err; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5e7fccf..7cf738a 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1263,7 +1263,7 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) if (err) return err; - err = dbg_check_synced_i_size(inode); + err = dbg_check_synced_i_size(c, inode); if (err) return err; diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 3be645e..9228950 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -86,8 +86,125 @@ void ubifs_ro_mode(struct ubifs_info *c, int err) c->no_chk_data_crc = 0; c->vfs_sb->s_flags |= MS_RDONLY; ubifs_warn("switched to read-only mode, error %d", err); + dump_stack(); + } +} + +/* + * Below are simple wrappers over UBI I/O functions which include some + * additional checks and UBIFS debugging stuff. See corresponding UBI function + * for more information. + */ + +int ubifs_leb_read(const struct ubifs_info *c, int lnum, void *buf, int offs, + int len, int even_ebadmsg) +{ + int err; + + err = ubi_read(c->ubi, lnum, buf, offs, len); + /* + * In case of %-EBADMSG print the error message only if the + * @even_ebadmsg is true. + */ + if (err && (err != -EBADMSG || even_ebadmsg)) { + ubifs_err("reading %d bytes from LEB %d:%d failed, error %d", + len, lnum, offs, err); + dbg_dump_stack(); + } + return err; +} + +int ubifs_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, + int len, int dtype) +{ + int err; + + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) + return -EROFS; + if (!dbg_is_tst_rcvry(c)) + err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype); + else + err = dbg_leb_write(c, lnum, buf, offs, len, dtype); + if (err) { + ubifs_err("writing %d bytes to LEB %d:%d failed, error %d", + len, lnum, offs, err); + ubifs_ro_mode(c, err); + dbg_dump_stack(); + } + return err; +} + +int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, + int dtype) +{ + int err; + + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) + return -EROFS; + if (!dbg_is_tst_rcvry(c)) + err = ubi_leb_change(c->ubi, lnum, buf, len, dtype); + else + err = dbg_leb_change(c, lnum, buf, len, dtype); + if (err) { + ubifs_err("changing %d bytes in LEB %d failed, error %d", + len, lnum, err); + ubifs_ro_mode(c, err); + dbg_dump_stack(); + } + return err; +} + +int ubifs_leb_unmap(struct ubifs_info *c, int lnum) +{ + int err; + + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) + return -EROFS; + if (!dbg_is_tst_rcvry(c)) + err = ubi_leb_unmap(c->ubi, lnum); + else + err = dbg_leb_unmap(c, lnum); + if (err) { + ubifs_err("unmap LEB %d failed, error %d", lnum, err); + ubifs_ro_mode(c, err); + dbg_dump_stack(); + } + return err; +} + +int ubifs_leb_map(struct ubifs_info *c, int lnum, int dtype) +{ + int err; + + ubifs_assert(!c->ro_media && !c->ro_mount); + if (c->ro_error) + return -EROFS; + if (!dbg_is_tst_rcvry(c)) + err = ubi_leb_map(c->ubi, lnum, dtype); + else + err = dbg_leb_map(c, lnum, dtype); + if (err) { + ubifs_err("mapping LEB %d failed, error %d", lnum, err); + ubifs_ro_mode(c, err); + dbg_dump_stack(); + } + return err; +} + +int ubifs_is_mapped(const struct ubifs_info *c, int lnum) +{ + int err; + + err = ubi_is_mapped(c->ubi, lnum); + if (err < 0) { + ubifs_err("ubi_is_mapped failed for LEB %d, error %d", + lnum, err); dbg_dump_stack(); } + return err; } /** @@ -406,14 +523,10 @@ int ubifs_wbuf_sync_nolock(struct ubifs_wbuf *wbuf) dirt = sync_len - wbuf->used; if (dirt) ubifs_pad(c, wbuf->buf + wbuf->used, dirt); - err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf, wbuf->offs, - sync_len, wbuf->dtype); - if (err) { - ubifs_err("cannot write %d bytes to LEB %d:%d", - sync_len, wbuf->lnum, wbuf->offs); - dbg_dump_stack(); + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, sync_len, + wbuf->dtype); + if (err) return err; - } spin_lock(&wbuf->lock); wbuf->offs += sync_len; @@ -605,9 +718,9 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) if (aligned_len == wbuf->avail) { dbg_io("flush jhead %s wbuf to LEB %d:%d", dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs); - err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf, - wbuf->offs, wbuf->size, - wbuf->dtype); + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, + wbuf->offs, wbuf->size, + wbuf->dtype); if (err) goto out; @@ -642,8 +755,8 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) dbg_io("flush jhead %s wbuf to LEB %d:%d", dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs); memcpy(wbuf->buf + wbuf->used, buf, wbuf->avail); - err = ubi_leb_write(c->ubi, wbuf->lnum, wbuf->buf, wbuf->offs, - wbuf->size, wbuf->dtype); + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, + wbuf->size, wbuf->dtype); if (err) goto out; @@ -661,8 +774,8 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) */ dbg_io("write %d bytes to LEB %d:%d", wbuf->size, wbuf->lnum, wbuf->offs); - err = ubi_leb_write(c->ubi, wbuf->lnum, buf, wbuf->offs, - wbuf->size, wbuf->dtype); + err = ubifs_leb_write(c, wbuf->lnum, buf, wbuf->offs, + wbuf->size, wbuf->dtype); if (err) goto out; @@ -683,8 +796,8 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) n <<= c->max_write_shift; dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum, wbuf->offs); - err = ubi_leb_write(c->ubi, wbuf->lnum, buf + written, - wbuf->offs, n, wbuf->dtype); + err = ubifs_leb_write(c, wbuf->lnum, buf + written, + wbuf->offs, n, wbuf->dtype); if (err) goto out; wbuf->offs += n; @@ -766,13 +879,9 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, return -EROFS; ubifs_prepare_node(c, buf, len, 1); - err = ubi_leb_write(c->ubi, lnum, buf, offs, buf_len, dtype); - if (err) { - ubifs_err("cannot write %d bytes to LEB %d:%d, error %d", - buf_len, lnum, offs, err); + err = ubifs_leb_write(c, lnum, buf, offs, buf_len, dtype); + if (err) dbg_dump_node(c, buf); - dbg_dump_stack(); - } return err; } @@ -824,13 +933,9 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, if (rlen > 0) { /* Read everything that goes before write-buffer */ - err = ubi_read(c->ubi, lnum, buf, offs, rlen); - if (err && err != -EBADMSG) { - ubifs_err("failed to read node %d from LEB %d:%d, " - "error %d", type, lnum, offs, err); - dbg_dump_stack(); + err = ubifs_leb_read(c, lnum, buf, offs, rlen, 0); + if (err && err != -EBADMSG) return err; - } } if (type != ch->node_type) { @@ -885,12 +990,9 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len, ubifs_assert(!(offs & 7) && offs < c->leb_size); ubifs_assert(type >= 0 && type < UBIFS_NODE_TYPES_CNT); - err = ubi_read(c->ubi, lnum, buf, offs, len); - if (err && err != -EBADMSG) { - ubifs_err("cannot read node %d from LEB %d:%d, error %d", - type, lnum, offs, err); + err = ubifs_leb_read(c, lnum, buf, offs, len, 0); + if (err && err != -EBADMSG) return err; - } if (type != ch->node_type) { ubifs_err("bad node type (%d but expected %d)", diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index affea94..f9fd068 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -262,7 +262,7 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) * an unclean reboot, because the target LEB might have been * unmapped, but not yet physically erased. */ - err = ubi_leb_map(c->ubi, bud->lnum, UBI_SHORTTERM); + err = ubifs_leb_map(c, bud->lnum, UBI_SHORTTERM); if (err) goto out_unlock; } @@ -283,8 +283,6 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) return 0; out_unlock: - if (err != -EAGAIN) - ubifs_ro_mode(c, err); mutex_unlock(&c->log_mutex); kfree(ref); kfree(bud); @@ -752,7 +750,7 @@ static int dbg_check_bud_bytes(struct ubifs_info *c) struct ubifs_bud *bud; long long bud_bytes = 0; - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; spin_lock(&c->buds_lock); diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 667884f..f8a181e 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -504,7 +504,7 @@ static int is_lprops_dirty(struct ubifs_info *c, struct ubifs_lprops *lprops) pnode = (struct ubifs_pnode *)container_of(lprops - pos, struct ubifs_pnode, lprops[0]); - return !test_bit(COW_ZNODE, &pnode->flags) && + return !test_bit(COW_CNODE, &pnode->flags) && test_bit(DIRTY_CNODE, &pnode->flags); } @@ -860,7 +860,7 @@ int dbg_check_cats(struct ubifs_info *c) struct list_head *pos; int i, cat; - if (!(ubifs_chk_flags & (UBIFS_CHK_GEN | UBIFS_CHK_LPROPS))) + if (!dbg_is_chk_gen(c) && !dbg_is_chk_lprops(c)) return 0; list_for_each_entry(lprops, &c->empty_list, list) { @@ -958,7 +958,7 @@ void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat, { int i = 0, j, err = 0; - if (!(ubifs_chk_flags & (UBIFS_CHK_GEN | UBIFS_CHK_LPROPS))) + if (!dbg_is_chk_gen(c) && !dbg_is_chk_lprops(c)) return; for (i = 0; i < heap->cnt; i++) { @@ -1262,7 +1262,7 @@ int dbg_check_lprops(struct ubifs_info *c) int i, err; struct ubifs_lp_stats lst; - if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS)) + if (!dbg_is_chk_lprops(c)) return 0; /* diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index ef5155e..6189c74 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -701,8 +701,8 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, alen = ALIGN(len, c->min_io_size); set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubi_leb_change(c->ubi, lnum++, buf, alen, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen, + UBI_SHORTTERM); if (err) goto out; p = buf; @@ -732,8 +732,8 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubi_leb_change(c->ubi, lnum++, buf, alen, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen, + UBI_SHORTTERM); if (err) goto out; p = buf; @@ -780,8 +780,8 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, alen = ALIGN(len, c->min_io_size); set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubi_leb_change(c->ubi, lnum++, buf, alen, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen, + UBI_SHORTTERM); if (err) goto out; p = buf; @@ -806,7 +806,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, alen = ALIGN(len, c->min_io_size); set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubi_leb_change(c->ubi, lnum++, buf, alen, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen, UBI_SHORTTERM); if (err) goto out; p = buf; @@ -826,7 +826,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, /* Write remaining buffer */ memset(p, 0xff, alen - len); - err = ubi_leb_change(c->ubi, lnum, buf, alen, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum, buf, alen, UBI_SHORTTERM); if (err) goto out; @@ -1222,7 +1222,7 @@ int ubifs_read_nnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) if (c->big_lpt) nnode->num = calc_nnode_num_from_parent(c, parent, iip); } else { - err = ubi_read(c->ubi, lnum, buf, offs, c->nnode_sz); + err = ubifs_leb_read(c, lnum, buf, offs, c->nnode_sz, 1); if (err) goto out; err = ubifs_unpack_nnode(c, buf, nnode); @@ -1247,6 +1247,7 @@ int ubifs_read_nnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) out: ubifs_err("error %d reading nnode at %d:%d", err, lnum, offs); + dbg_dump_stack(); kfree(nnode); return err; } @@ -1290,7 +1291,7 @@ static int read_pnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) lprops->flags = ubifs_categorize_lprops(c, lprops); } } else { - err = ubi_read(c->ubi, lnum, buf, offs, c->pnode_sz); + err = ubifs_leb_read(c, lnum, buf, offs, c->pnode_sz, 1); if (err) goto out; err = unpack_pnode(c, buf, pnode); @@ -1312,6 +1313,7 @@ static int read_pnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) out: ubifs_err("error %d reading pnode at %d:%d", err, lnum, offs); dbg_dump_pnode(c, pnode, parent, iip); + dbg_dump_stack(); dbg_msg("calc num: %d", calc_pnode_num_from_parent(c, parent, iip)); kfree(pnode); return err; @@ -1331,7 +1333,7 @@ static int read_ltab(struct ubifs_info *c) buf = vmalloc(c->ltab_sz); if (!buf) return -ENOMEM; - err = ubi_read(c->ubi, c->ltab_lnum, buf, c->ltab_offs, c->ltab_sz); + err = ubifs_leb_read(c, c->ltab_lnum, buf, c->ltab_offs, c->ltab_sz, 1); if (err) goto out; err = unpack_ltab(c, buf); @@ -1354,7 +1356,8 @@ static int read_lsave(struct ubifs_info *c) buf = vmalloc(c->lsave_sz); if (!buf) return -ENOMEM; - err = ubi_read(c->ubi, c->lsave_lnum, buf, c->lsave_offs, c->lsave_sz); + err = ubifs_leb_read(c, c->lsave_lnum, buf, c->lsave_offs, + c->lsave_sz, 1); if (err) goto out; err = unpack_lsave(c, buf); @@ -1814,8 +1817,8 @@ static struct ubifs_nnode *scan_get_nnode(struct ubifs_info *c, if (c->big_lpt) nnode->num = calc_nnode_num_from_parent(c, parent, iip); } else { - err = ubi_read(c->ubi, branch->lnum, buf, branch->offs, - c->nnode_sz); + err = ubifs_leb_read(c, branch->lnum, buf, branch->offs, + c->nnode_sz, 1); if (err) return ERR_PTR(err); err = ubifs_unpack_nnode(c, buf, nnode); @@ -1883,8 +1886,8 @@ static struct ubifs_pnode *scan_get_pnode(struct ubifs_info *c, ubifs_assert(branch->lnum >= c->lpt_first && branch->lnum <= c->lpt_last); ubifs_assert(branch->offs >= 0 && branch->offs < c->leb_size); - err = ubi_read(c->ubi, branch->lnum, buf, branch->offs, - c->pnode_sz); + err = ubifs_leb_read(c, branch->lnum, buf, branch->offs, + c->pnode_sz, 1); if (err) return ERR_PTR(err); err = unpack_pnode(c, buf, pnode); @@ -2224,7 +2227,7 @@ int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode, struct ubifs_cnode *cn; int num, iip = 0, err; - if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS)) + if (!dbg_is_chk_lprops(c)) return 0; while (cnode) { diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index dfcb574..cddd6bd 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -27,6 +27,7 @@ #include <linux/crc16.h> #include <linux/slab.h> +#include <linux/random.h> #include "ubifs.h" #ifdef CONFIG_UBIFS_FS_DEBUG @@ -116,8 +117,8 @@ static int get_cnodes_to_commit(struct ubifs_info *c) return 0; cnt += 1; while (1) { - ubifs_assert(!test_bit(COW_ZNODE, &cnode->flags)); - __set_bit(COW_ZNODE, &cnode->flags); + ubifs_assert(!test_bit(COW_CNODE, &cnode->flags)); + __set_bit(COW_CNODE, &cnode->flags); cnext = next_dirty_cnode(cnode); if (!cnext) { cnode->cnext = c->lpt_cnext; @@ -465,7 +466,7 @@ static int write_cnodes(struct ubifs_info *c) */ clear_bit(DIRTY_CNODE, &cnode->flags); smp_mb__before_clear_bit(); - clear_bit(COW_ZNODE, &cnode->flags); + clear_bit(COW_CNODE, &cnode->flags); smp_mb__after_clear_bit(); offs += len; dbg_chk_lpt_sz(c, 1, len); @@ -1160,11 +1161,11 @@ static int lpt_gc_lnum(struct ubifs_info *c, int lnum) void *buf = c->lpt_buf; dbg_lp("LEB %d", lnum); - err = ubi_read(c->ubi, lnum, buf, 0, c->leb_size); - if (err) { - ubifs_err("cannot read LEB %d, error %d", lnum, err); + + err = ubifs_leb_read(c, lnum, buf, 0, c->leb_size, 1); + if (err) return err; - } + while (1) { if (!is_a_node(c, buf, len)) { int pad_len; @@ -1640,7 +1641,7 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum) int ret; void *buf, *p; - if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS)) + if (!dbg_is_chk_lprops(c)) return 0; buf = p = __vmalloc(c->leb_size, GFP_NOFS, PAGE_KERNEL); @@ -1650,11 +1651,11 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum) } dbg_lp("LEB %d", lnum); - err = ubi_read(c->ubi, lnum, buf, 0, c->leb_size); - if (err) { - dbg_msg("ubi_read failed, LEB %d, error %d", lnum, err); + + err = ubifs_leb_read(c, lnum, buf, 0, c->leb_size, 1); + if (err) goto out; - } + while (1) { if (!is_a_node(c, p, len)) { int i, pad_len; @@ -1711,7 +1712,7 @@ int dbg_check_ltab(struct ubifs_info *c) { int lnum, err, i, cnt; - if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS)) + if (!dbg_is_chk_lprops(c)) return 0; /* Bring the entire tree into memory */ @@ -1754,7 +1755,7 @@ int dbg_chk_lpt_free_spc(struct ubifs_info *c) long long free = 0; int i; - if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS)) + if (!dbg_is_chk_lprops(c)) return 0; for (i = 0; i < c->lpt_lebs; i++) { @@ -1796,7 +1797,7 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) long long chk_lpt_sz, lpt_sz; int err = 0; - if (!(ubifs_chk_flags & UBIFS_CHK_LPROPS)) + if (!dbg_is_chk_lprops(c)) return 0; switch (action) { @@ -1901,11 +1902,10 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum) return; } - err = ubi_read(c->ubi, lnum, buf, 0, c->leb_size); - if (err) { - ubifs_err("cannot read LEB %d, error %d", lnum, err); + err = ubifs_leb_read(c, lnum, buf, 0, c->leb_size, 1); + if (err) goto out; - } + while (1) { offs = c->leb_size - len; if (!is_a_node(c, p, len)) { @@ -2019,7 +2019,7 @@ static int dbg_populate_lsave(struct ubifs_info *c) struct ubifs_lpt_heap *heap; int i; - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; if (random32() & 3) return 0; diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index 0b5296a..ee7cb5e 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -39,6 +39,29 @@ static inline int ubifs_zn_dirty(const struct ubifs_znode *znode) } /** + * ubifs_zn_obsolete - check if znode is obsolete. + * @znode: znode to check + * + * This helper function returns %1 if @znode is obsolete and %0 otherwise. + */ +static inline int ubifs_zn_obsolete(const struct ubifs_znode *znode) +{ + return !!test_bit(OBSOLETE_ZNODE, &znode->flags); +} + +/** + * ubifs_zn_cow - check if znode has to be copied on write. + * @znode: znode to check + * + * This helper function returns %1 if @znode is has COW flag set and %0 + * otherwise. + */ +static inline int ubifs_zn_cow(const struct ubifs_znode *znode) +{ + return !!test_bit(COW_ZNODE, &znode->flags); +} + +/** * ubifs_wake_up_bgt - wake up background thread. * @c: UBIFS file-system description object */ @@ -122,86 +145,6 @@ static inline int ubifs_wbuf_sync(struct ubifs_wbuf *wbuf) } /** - * ubifs_leb_unmap - unmap an LEB. - * @c: UBIFS file-system description object - * @lnum: LEB number to unmap - * - * This function returns %0 on success and a negative error code on failure. - */ -static inline int ubifs_leb_unmap(const struct ubifs_info *c, int lnum) -{ - int err; - - ubifs_assert(!c->ro_media && !c->ro_mount); - if (c->ro_error) - return -EROFS; - err = ubi_leb_unmap(c->ubi, lnum); - if (err) { - ubifs_err("unmap LEB %d failed, error %d", lnum, err); - return err; - } - - return 0; -} - -/** - * ubifs_leb_write - write to a LEB. - * @c: UBIFS file-system description object - * @lnum: LEB number to write - * @buf: buffer to write from - * @offs: offset within LEB to write to - * @len: length to write - * @dtype: data type - * - * This function returns %0 on success and a negative error code on failure. - */ -static inline int ubifs_leb_write(const struct ubifs_info *c, int lnum, - const void *buf, int offs, int len, int dtype) -{ - int err; - - ubifs_assert(!c->ro_media && !c->ro_mount); - if (c->ro_error) - return -EROFS; - err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype); - if (err) { - ubifs_err("writing %d bytes at %d:%d, error %d", - len, lnum, offs, err); - return err; - } - - return 0; -} - -/** - * ubifs_leb_change - atomic LEB change. - * @c: UBIFS file-system description object - * @lnum: LEB number to write - * @buf: buffer to write from - * @len: length to write - * @dtype: data type - * - * This function returns %0 on success and a negative error code on failure. - */ -static inline int ubifs_leb_change(const struct ubifs_info *c, int lnum, - const void *buf, int len, int dtype) -{ - int err; - - ubifs_assert(!c->ro_media && !c->ro_mount); - if (c->ro_error) - return -EROFS; - err = ubi_leb_change(c->ubi, lnum, buf, len, dtype); - if (err) { - ubifs_err("changing %d bytes in LEB %d, error %d", - len, lnum, err); - return err; - } - - return 0; -} - -/** * ubifs_encode_dev - encode device node IDs. * @dev: UBIFS device node information * @rdev: device IDs to encode diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index a5422ff..c542c73 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -929,7 +929,7 @@ static int dbg_check_orphans(struct ubifs_info *c) struct check_info ci; int err; - if (!(ubifs_chk_flags & UBIFS_CHK_ORPH)) + if (!dbg_is_chk_orph(c)) return 0; ci.last_ino = 0; diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index 783d8e0..af02790 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -117,7 +117,7 @@ static int get_master_node(const struct ubifs_info *c, int lnum, void **pbuf, if (!sbuf) return -ENOMEM; - err = ubi_read(c->ubi, lnum, sbuf, 0, c->leb_size); + err = ubifs_leb_read(c, lnum, sbuf, 0, c->leb_size, 0); if (err && err != -EBADMSG) goto out_free; @@ -213,10 +213,10 @@ static int write_rcvrd_mst_node(struct ubifs_info *c, mst->flags |= cpu_to_le32(UBIFS_MST_RCVRY); ubifs_prepare_node(c, mst, UBIFS_MST_NODE_SZ, 1); - err = ubi_leb_change(c->ubi, lnum, mst, sz, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum, mst, sz, UBI_SHORTTERM); if (err) goto out; - err = ubi_leb_change(c->ubi, lnum + 1, mst, sz, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum + 1, mst, sz, UBI_SHORTTERM); if (err) goto out; out: @@ -274,7 +274,8 @@ int ubifs_recover_master_node(struct ubifs_info *c) if (cor1) goto out_err; mst = mst1; - } else if (offs1 == 0 && offs2 + sz >= c->leb_size) { + } else if (offs1 == 0 && + c->leb_size - offs2 - sz < sz) { /* 1st LEB was unmapped and written, 2nd not */ if (cor1) goto out_err; @@ -539,8 +540,8 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb, int len = ALIGN(endpt, c->min_io_size); if (start) { - err = ubi_read(c->ubi, lnum, sleb->buf, 0, - start); + err = ubifs_leb_read(c, lnum, sleb->buf, 0, + start, 1); if (err) return err; } @@ -554,8 +555,8 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ubifs_pad(c, buf, pad_len); } } - err = ubi_leb_change(c->ubi, lnum, sleb->buf, len, - UBI_UNKNOWN); + err = ubifs_leb_change(c, lnum, sleb->buf, len, + UBI_UNKNOWN); if (err) return err; } @@ -819,7 +820,8 @@ static int get_cs_sqnum(struct ubifs_info *c, int lnum, int offs, return -ENOMEM; if (c->leb_size - offs < UBIFS_CS_NODE_SZ) goto out_err; - err = ubi_read(c->ubi, lnum, (void *)cs_node, offs, UBIFS_CS_NODE_SZ); + err = ubifs_leb_read(c, lnum, (void *)cs_node, offs, + UBIFS_CS_NODE_SZ, 0); if (err && err != -EBADMSG) goto out_free; ret = ubifs_scan_a_node(c, cs_node, UBIFS_CS_NODE_SZ, lnum, offs, 0); @@ -919,8 +921,7 @@ struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum, * * This function returns %0 on success and a negative error code on failure. */ -static int recover_head(const struct ubifs_info *c, int lnum, int offs, - void *sbuf) +static int recover_head(struct ubifs_info *c, int lnum, int offs, void *sbuf) { int len = c->max_write_size, err; @@ -931,15 +932,15 @@ static int recover_head(const struct ubifs_info *c, int lnum, int offs, return 0; /* Read at the head location and check it is empty flash */ - err = ubi_read(c->ubi, lnum, sbuf, offs, len); + err = ubifs_leb_read(c, lnum, sbuf, offs, len, 1); if (err || !is_empty(sbuf, len)) { dbg_rcvry("cleaning head at %d:%d", lnum, offs); if (offs == 0) return ubifs_leb_unmap(c, lnum); - err = ubi_read(c->ubi, lnum, sbuf, 0, offs); + err = ubifs_leb_read(c, lnum, sbuf, 0, offs, 1); if (err) return err; - return ubi_leb_change(c->ubi, lnum, sbuf, offs, UBI_UNKNOWN); + return ubifs_leb_change(c, lnum, sbuf, offs, UBI_UNKNOWN); } return 0; @@ -962,7 +963,7 @@ static int recover_head(const struct ubifs_info *c, int lnum, int offs, * * This function returns %0 on success and a negative error code on failure. */ -int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf) +int ubifs_recover_inl_heads(struct ubifs_info *c, void *sbuf) { int err; @@ -993,7 +994,7 @@ int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf) * * This function returns %0 on success and a negative error code on failure. */ -static int clean_an_unclean_leb(const struct ubifs_info *c, +static int clean_an_unclean_leb(struct ubifs_info *c, struct ubifs_unclean_leb *ucleb, void *sbuf) { int err, lnum = ucleb->lnum, offs = 0, len = ucleb->endpt, quiet = 1; @@ -1009,7 +1010,7 @@ static int clean_an_unclean_leb(const struct ubifs_info *c, return 0; } - err = ubi_read(c->ubi, lnum, buf, offs, len); + err = ubifs_leb_read(c, lnum, buf, offs, len, 0); if (err && err != -EBADMSG) return err; @@ -1069,7 +1070,7 @@ static int clean_an_unclean_leb(const struct ubifs_info *c, } /* Write back the LEB atomically */ - err = ubi_leb_change(c->ubi, lnum, sbuf, len, UBI_UNKNOWN); + err = ubifs_leb_change(c, lnum, sbuf, len, UBI_UNKNOWN); if (err) return err; @@ -1089,7 +1090,7 @@ static int clean_an_unclean_leb(const struct ubifs_info *c, * * This function returns %0 on success and a negative error code on failure. */ -int ubifs_clean_lebs(const struct ubifs_info *c, void *sbuf) +int ubifs_clean_lebs(struct ubifs_info *c, void *sbuf) { dbg_rcvry("recovery"); while (!list_empty(&c->unclean_leb_list)) { @@ -1454,7 +1455,7 @@ static int fix_size_in_place(struct ubifs_info *c, struct size_entry *e) if (i_size >= e->d_size) return 0; /* Read the LEB */ - err = ubi_read(c->ubi, lnum, c->sbuf, 0, c->leb_size); + err = ubifs_leb_read(c, lnum, c->sbuf, 0, c->leb_size, 1); if (err) goto out; /* Change the size field and recalculate the CRC */ @@ -1470,7 +1471,7 @@ static int fix_size_in_place(struct ubifs_info *c, struct size_entry *e) len -= 1; len = ALIGN(len + 1, c->min_io_size); /* Atomically write the fixed LEB back again */ - err = ubi_leb_change(c->ubi, lnum, c->sbuf, len, UBI_UNKNOWN); + err = ubifs_leb_change(c, lnum, c->sbuf, len, UBI_UNKNOWN); if (err) goto out; dbg_rcvry("inode %lu at %d:%d size %lld -> %lld", diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 5e97161..ccabaf1 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -523,8 +523,7 @@ static int is_last_bud(struct ubifs_info *c, struct ubifs_bud *bud) if (!list_is_last(&next->list, &jh->buds_list)) return 0; - err = ubi_read(c->ubi, next->lnum, (char *)&data, - next->start, 4); + err = ubifs_leb_read(c, next->lnum, (char *)&data, next->start, 4, 1); if (err) return 0; diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index c606f01..93d938a 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -674,15 +674,15 @@ static int fixup_leb(struct ubifs_info *c, int lnum, int len) if (len == 0) { dbg_mnt("unmap empty LEB %d", lnum); - return ubi_leb_unmap(c->ubi, lnum); + return ubifs_leb_unmap(c, lnum); } dbg_mnt("fixup LEB %d, data len %d", lnum, len); - err = ubi_read(c->ubi, lnum, c->sbuf, 0, len); + err = ubifs_leb_read(c, lnum, c->sbuf, 0, len, 1); if (err) return err; - return ubi_leb_change(c->ubi, lnum, c->sbuf, len, UBI_UNKNOWN); + return ubifs_leb_change(c, lnum, c->sbuf, len, UBI_UNKNOWN); } /** diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index 36216b4..37383e8 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -148,7 +148,7 @@ struct ubifs_scan_leb *ubifs_start_scan(const struct ubifs_info *c, int lnum, INIT_LIST_HEAD(&sleb->nodes); sleb->buf = sbuf; - err = ubi_read(c->ubi, lnum, sbuf + offs, offs, c->leb_size - offs); + err = ubifs_leb_read(c, lnum, sbuf + offs, offs, c->leb_size - offs, 0); if (err && err != -EBADMSG) { ubifs_err("cannot read %d bytes from LEB %d:%d," " error %d", c->leb_size - offs, lnum, offs, err); @@ -240,7 +240,7 @@ void ubifs_scanned_corruption(const struct ubifs_info *c, int lnum, int offs, int len; ubifs_err("corruption at LEB %d:%d", lnum, offs); - if (dbg_failure_mode) + if (dbg_is_tst_rcvry(c)) return; len = c->leb_size - offs; if (len > 8192) diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 529be05..b281212 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -85,7 +85,7 @@ static int validate_inode(struct ubifs_info *c, const struct inode *inode) if (ui->data_len < 0 || ui->data_len > UBIFS_MAX_INO_DATA) return 4; - if (ui->xattr && (inode->i_mode & S_IFMT) != S_IFREG) + if (ui->xattr && !S_ISREG(inode->i_mode)) return 5; if (!ubifs_compr_present(ui->compr_type)) { @@ -94,7 +94,7 @@ static int validate_inode(struct ubifs_info *c, const struct inode *inode) ubifs_compr_name(ui->compr_type)); } - err = dbg_check_dir_size(c, inode); + err = dbg_check_dir(c, inode); return err; } @@ -914,7 +914,7 @@ static int check_volume_empty(struct ubifs_info *c) c->empty = 1; for (lnum = 0; lnum < c->leb_cnt; lnum++) { - err = ubi_is_mapped(c->ubi, lnum); + err = ubifs_is_mapped(c, lnum); if (unlikely(err < 0)) return err; if (err == 1) { diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 91b4213..0667386 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -223,7 +223,7 @@ static struct ubifs_znode *copy_znode(struct ubifs_info *c, __set_bit(DIRTY_ZNODE, &zn->flags); __clear_bit(COW_ZNODE, &zn->flags); - ubifs_assert(!test_bit(OBSOLETE_ZNODE, &znode->flags)); + ubifs_assert(!ubifs_zn_obsolete(znode)); __set_bit(OBSOLETE_ZNODE, &znode->flags); if (znode->level != 0) { @@ -271,7 +271,7 @@ static struct ubifs_znode *dirty_cow_znode(struct ubifs_info *c, struct ubifs_znode *zn; int err; - if (!test_bit(COW_ZNODE, &znode->flags)) { + if (!ubifs_zn_cow(znode)) { /* znode is not being committed */ if (!test_and_set_bit(DIRTY_ZNODE, &znode->flags)) { atomic_long_inc(&c->dirty_zn_cnt); @@ -462,7 +462,7 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type, dbg_io("LEB %d:%d, %s, length %d", lnum, offs, dbg_ntype(type), len); - err = ubi_read(c->ubi, lnum, buf, offs, len); + err = ubifs_leb_read(c, lnum, buf, offs, len, 1); if (err) { ubifs_err("cannot read node type %d from LEB %d:%d, error %d", type, lnum, offs, err); @@ -1666,7 +1666,7 @@ static int read_wbuf(struct ubifs_wbuf *wbuf, void *buf, int len, int lnum, if (!overlap) { /* We may safely unlock the write-buffer and read the data */ spin_unlock(&wbuf->lock); - return ubi_read(c->ubi, lnum, buf, offs, len); + return ubifs_leb_read(c, lnum, buf, offs, len, 0); } /* Don't read under wbuf */ @@ -1680,7 +1680,7 @@ static int read_wbuf(struct ubifs_wbuf *wbuf, void *buf, int len, int lnum, if (rlen > 0) /* Read everything that goes before write-buffer */ - return ubi_read(c->ubi, lnum, buf, offs, rlen); + return ubifs_leb_read(c, lnum, buf, offs, rlen, 0); return 0; } @@ -1767,7 +1767,7 @@ int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu) if (wbuf) err = read_wbuf(wbuf, bu->buf, len, lnum, offs); else - err = ubi_read(c->ubi, lnum, bu->buf, offs, len); + err = ubifs_leb_read(c, lnum, bu->buf, offs, len, 0); /* Check for a race with GC */ if (maybe_leb_gced(c, lnum, bu->gc_seq)) @@ -2423,7 +2423,7 @@ static int tnc_delete(struct ubifs_info *c, struct ubifs_znode *znode, int n) */ do { - ubifs_assert(!test_bit(OBSOLETE_ZNODE, &znode->flags)); + ubifs_assert(!ubifs_zn_obsolete(znode)); ubifs_assert(ubifs_zn_dirty(znode)); zp = znode->parent; @@ -2479,9 +2479,8 @@ static int tnc_delete(struct ubifs_info *c, struct ubifs_znode *znode, int n) c->zroot.offs = zbr->offs; c->zroot.len = zbr->len; c->zroot.znode = znode; - ubifs_assert(!test_bit(OBSOLETE_ZNODE, - &zp->flags)); - ubifs_assert(test_bit(DIRTY_ZNODE, &zp->flags)); + ubifs_assert(!ubifs_zn_obsolete(zp)); + ubifs_assert(ubifs_zn_dirty(zp)); atomic_long_dec(&c->dirty_zn_cnt); if (zp->cnext) { @@ -2865,7 +2864,7 @@ static void tnc_destroy_cnext(struct ubifs_info *c) struct ubifs_znode *znode = cnext; cnext = cnext->cnext; - if (test_bit(OBSOLETE_ZNODE, &znode->flags)) + if (ubifs_zn_obsolete(znode)) kfree(znode); } while (cnext && cnext != c->cnext); } @@ -3301,7 +3300,7 @@ int dbg_check_inode_size(struct ubifs_info *c, const struct inode *inode, if (!S_ISREG(inode->i_mode)) return 0; - if (!(ubifs_chk_flags & UBIFS_CHK_GEN)) + if (!dbg_is_chk_gen(c)) return 0; block = (size + UBIFS_BLOCK_SIZE - 1) >> UBIFS_BLOCK_SHIFT; @@ -3337,9 +3336,10 @@ out_dump: ubifs_err("inode %lu has size %lld, but there are data at offset %lld " "(data key %s)", (unsigned long)inode->i_ino, size, ((loff_t)block) << UBIFS_BLOCK_SHIFT, DBGKEY(key)); + mutex_unlock(&c->tnc_mutex); dbg_dump_inode(c, inode); dbg_dump_stack(); - err = -EINVAL; + return -EINVAL; out_unlock: mutex_unlock(&c->tnc_mutex); diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index 41920f3..4c15f07 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -22,6 +22,7 @@ /* This file implements TNC functions for committing */ +#include <linux/random.h> #include "ubifs.h" /** @@ -87,8 +88,12 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, atomic_long_dec(&c->dirty_zn_cnt); ubifs_assert(ubifs_zn_dirty(znode)); - ubifs_assert(test_bit(COW_ZNODE, &znode->flags)); + ubifs_assert(ubifs_zn_cow(znode)); + /* + * Note, unlike 'write_index()' we do not add memory barriers here + * because this function is called with @c->tnc_mutex locked. + */ __clear_bit(DIRTY_ZNODE, &znode->flags); __clear_bit(COW_ZNODE, &znode->flags); @@ -377,7 +382,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) c->gap_lebs = NULL; return err; } - if (dbg_force_in_the_gaps_enabled()) { + if (!dbg_is_chk_index(c)) { /* * Do not print scary warnings if the debugging * option which forces in-the-gaps is enabled. @@ -491,25 +496,6 @@ static int layout_in_empty_space(struct ubifs_info *c) else next_len = ubifs_idx_node_sz(c, cnext->child_cnt); - if (c->min_io_size == 1) { - buf_offs += ALIGN(len, 8); - if (next_len) { - if (buf_offs + next_len <= c->leb_size) - continue; - err = ubifs_update_one_lp(c, lnum, 0, - c->leb_size - buf_offs, 0, 0); - if (err) - return err; - lnum = -1; - continue; - } - err = ubifs_update_one_lp(c, lnum, - c->leb_size - buf_offs, 0, 0, 0); - if (err) - return err; - break; - } - /* Update buffer positions */ wlen = used + len; used += ALIGN(len, 8); @@ -658,7 +644,7 @@ static int get_znodes_to_commit(struct ubifs_info *c) } cnt += 1; while (1) { - ubifs_assert(!test_bit(COW_ZNODE, &znode->flags)); + ubifs_assert(!ubifs_zn_cow(znode)); __set_bit(COW_ZNODE, &znode->flags); znode->alt = 0; cnext = find_next_dirty(znode); @@ -704,7 +690,7 @@ static int alloc_idx_lebs(struct ubifs_info *c, int cnt) c->ilebs[c->ileb_cnt++] = lnum; dbg_cmt("LEB %d", lnum); } - if (dbg_force_in_the_gaps()) + if (dbg_is_chk_index(c) && !(random32() & 7)) return -ENOSPC; return 0; } @@ -830,7 +816,7 @@ static int write_index(struct ubifs_info *c) struct ubifs_idx_node *idx; struct ubifs_znode *znode, *cnext; int i, lnum, offs, len, next_len, buf_len, buf_offs, used; - int avail, wlen, err, lnum_pos = 0; + int avail, wlen, err, lnum_pos = 0, blen, nxt_offs; cnext = c->enext; if (!cnext) @@ -907,7 +893,7 @@ static int write_index(struct ubifs_info *c) cnext = znode->cnext; ubifs_assert(ubifs_zn_dirty(znode)); - ubifs_assert(test_bit(COW_ZNODE, &znode->flags)); + ubifs_assert(ubifs_zn_cow(znode)); /* * It is important that other threads should see %DIRTY_ZNODE @@ -922,6 +908,28 @@ static int write_index(struct ubifs_info *c) clear_bit(COW_ZNODE, &znode->flags); smp_mb__after_clear_bit(); + /* + * We have marked the znode as clean but have not updated the + * @c->clean_zn_cnt counter. If this znode becomes dirty again + * before 'free_obsolete_znodes()' is called, then + * @c->clean_zn_cnt will be decremented before it gets + * incremented (resulting in 2 decrements for the same znode). + * This means that @c->clean_zn_cnt may become negative for a + * while. + * + * Q: why we cannot increment @c->clean_zn_cnt? + * A: because we do not have the @c->tnc_mutex locked, and the + * following code would be racy and buggy: + * + * if (!ubifs_zn_obsolete(znode)) { + * atomic_long_inc(&c->clean_zn_cnt); + * atomic_long_inc(&ubifs_clean_zn_cnt); + * } + * + * Thus, we just delay the @c->clean_zn_cnt update until we + * have the mutex locked. + */ + /* Do not access znode from this point on */ /* Update buffer positions */ @@ -938,65 +946,38 @@ static int write_index(struct ubifs_info *c) else next_len = ubifs_idx_node_sz(c, cnext->child_cnt); - if (c->min_io_size == 1) { - /* - * Write the prepared index node immediately if there is - * no minimum IO size - */ - err = ubifs_leb_write(c, lnum, c->cbuf, buf_offs, - wlen, UBI_SHORTTERM); - if (err) - return err; - buf_offs += ALIGN(wlen, 8); - if (next_len) { - used = 0; - avail = buf_len; - if (buf_offs + next_len > c->leb_size) { - err = ubifs_update_one_lp(c, lnum, - LPROPS_NC, 0, 0, LPROPS_TAKEN); - if (err) - return err; - lnum = -1; - } + nxt_offs = buf_offs + used + next_len; + if (next_len && nxt_offs <= c->leb_size) { + if (avail > 0) continue; - } + else + blen = buf_len; } else { - int blen, nxt_offs = buf_offs + used + next_len; - - if (next_len && nxt_offs <= c->leb_size) { - if (avail > 0) - continue; - else - blen = buf_len; - } else { - wlen = ALIGN(wlen, 8); - blen = ALIGN(wlen, c->min_io_size); - ubifs_pad(c, c->cbuf + wlen, blen - wlen); - } - /* - * The buffer is full or there are no more znodes - * to do - */ - err = ubifs_leb_write(c, lnum, c->cbuf, buf_offs, - blen, UBI_SHORTTERM); - if (err) - return err; - buf_offs += blen; - if (next_len) { - if (nxt_offs > c->leb_size) { - err = ubifs_update_one_lp(c, lnum, - LPROPS_NC, 0, 0, LPROPS_TAKEN); - if (err) - return err; - lnum = -1; - } - used -= blen; - if (used < 0) - used = 0; - avail = buf_len - used; - memmove(c->cbuf, c->cbuf + blen, used); - continue; + wlen = ALIGN(wlen, 8); + blen = ALIGN(wlen, c->min_io_size); + ubifs_pad(c, c->cbuf + wlen, blen - wlen); + } + + /* The buffer is full or there are no more znodes to do */ + err = ubifs_leb_write(c, lnum, c->cbuf, buf_offs, blen, + UBI_SHORTTERM); + if (err) + return err; + buf_offs += blen; + if (next_len) { + if (nxt_offs > c->leb_size) { + err = ubifs_update_one_lp(c, lnum, LPROPS_NC, 0, + 0, LPROPS_TAKEN); + if (err) + return err; + lnum = -1; } + used -= blen; + if (used < 0) + used = 0; + avail = buf_len - used; + memmove(c->cbuf, c->cbuf + blen, used); + continue; } break; } @@ -1029,7 +1010,7 @@ static void free_obsolete_znodes(struct ubifs_info *c) do { znode = cnext; cnext = znode->cnext; - if (test_bit(OBSOLETE_ZNODE, &znode->flags)) + if (ubifs_zn_obsolete(znode)) kfree(znode); else { znode->cnext = NULL; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index f79983d..702b792 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -230,14 +230,14 @@ enum { * LPT cnode flag bits. * * DIRTY_CNODE: cnode is dirty - * COW_CNODE: cnode is being committed and must be copied before writing * OBSOLETE_CNODE: cnode is being committed and has been copied (or deleted), - * so it can (and must) be freed when the commit is finished + * so it can (and must) be freed when the commit is finished + * COW_CNODE: cnode is being committed and must be copied before writing */ enum { DIRTY_CNODE = 0, - COW_CNODE = 1, - OBSOLETE_CNODE = 2, + OBSOLETE_CNODE = 1, + COW_CNODE = 2, }; /* @@ -1468,6 +1468,15 @@ extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT]; /* io.c */ void ubifs_ro_mode(struct ubifs_info *c, int err); +int ubifs_leb_read(const struct ubifs_info *c, int lnum, void *buf, int offs, + int len, int even_ebadmsg); +int ubifs_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, + int len, int dtype); +int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, + int dtype); +int ubifs_leb_unmap(struct ubifs_info *c, int lnum); +int ubifs_leb_map(struct ubifs_info *c, int lnum, int dtype); +int ubifs_is_mapped(const struct ubifs_info *c, int lnum); int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len); int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs, int dtype); @@ -1747,8 +1756,8 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf, int jhead); struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf); -int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf); -int ubifs_clean_lebs(const struct ubifs_info *c, void *sbuf); +int ubifs_recover_inl_heads(struct ubifs_info *c, void *sbuf); +int ubifs_clean_lebs(struct ubifs_info *c, void *sbuf); int ubifs_rcvry_gc_commit(struct ubifs_info *c); int ubifs_recover_size_accum(struct ubifs_info *c, union ubifs_key *key, int deletion, loff_t new_size); diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c index 29309e2..b57aab9 100644 --- a/fs/ufs/namei.c +++ b/fs/ufs/namei.c @@ -56,16 +56,12 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, stru lock_ufs(dir->i_sb); ino = ufs_inode_by_name(dir, &dentry->d_name); - if (ino) { + if (ino) inode = ufs_iget(dir->i_sb, ino); - if (IS_ERR(inode)) { - unlock_ufs(dir->i_sb); - return ERR_CAST(inode); - } - } unlock_ufs(dir->i_sb); - d_add(dentry, inode); - return NULL; + if (IS_ERR(inode)) + return ERR_CAST(inode); + return d_splice_alias(inode, dentry); } /* diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 284a7c8..75bb316 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -88,8 +88,6 @@ xfs-y += xfs_alloc.o \ xfs_vnodeops.o \ xfs_rw.o -xfs-$(CONFIG_XFS_TRACE) += xfs_btree_trace.o - # Objects in linux/ xfs-y += $(addprefix $(XFS_LINUX)/, \ kmem.o \ diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c index 39f4f80..115ac69 100644 --- a/fs/xfs/linux-2.6/xfs_acl.c +++ b/fs/xfs/linux-2.6/xfs_acl.c @@ -264,7 +264,7 @@ xfs_set_mode(struct inode *inode, mode_t mode) iattr.ia_mode = mode; iattr.ia_ctime = current_fs_time(inode->i_sb); - error = -xfs_setattr(XFS_I(inode), &iattr, XFS_ATTR_NOACL); + error = -xfs_setattr_nonsize(XFS_I(inode), &iattr, XFS_ATTR_NOACL); } return error; diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 79ce38b..26384fe 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -181,6 +181,7 @@ xfs_setfilesize( isize = xfs_ioend_new_eof(ioend); if (isize) { + trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size); ip->i_d.di_size = isize; xfs_mark_inode_dirty(ip); } @@ -894,11 +895,6 @@ out_invalidate: * For unwritten space on the page we need to start the conversion to * regular allocated space. * For any other dirty buffer heads on the page we should flush them. - * - * If we detect that a transaction would be required to flush the page, we - * have to check the process flags first, if we are already in a transaction - * or disk I/O during allocations is off, we need to fail the writepage and - * redirty the page. */ STATIC int xfs_vm_writepage( @@ -906,7 +902,6 @@ xfs_vm_writepage( struct writeback_control *wbc) { struct inode *inode = page->mapping->host; - int delalloc, unwritten; struct buffer_head *bh, *head; struct xfs_bmbt_irec imap; xfs_ioend_t *ioend = NULL, *iohead = NULL; @@ -938,15 +933,10 @@ xfs_vm_writepage( goto redirty; /* - * We need a transaction if there are delalloc or unwritten buffers - * on the page. - * - * If we need a transaction and the process flags say we are already - * in a transaction, or no IO is allowed then mark the page dirty - * again and leave the page as is. + * Given that we do not allow direct reclaim to call us, we should + * never be called while in a filesystem transaction. */ - xfs_count_page_state(page, &delalloc, &unwritten); - if ((current->flags & PF_FSTRANS) && (delalloc || unwritten)) + if (WARN_ON(current->flags & PF_FSTRANS)) goto redirty; /* Is this page beyond the end of the file? */ @@ -970,7 +960,7 @@ xfs_vm_writepage( offset = page_offset(page); type = IO_OVERWRITE; - if (wbc->sync_mode == WB_SYNC_NONE && wbc->nonblocking) + if (wbc->sync_mode == WB_SYNC_NONE) nonblocking = 1; do { diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 5e68099..b2b4119 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -499,16 +499,14 @@ found: spin_unlock(&pag->pag_buf_lock); xfs_perag_put(pag); - if (xfs_buf_cond_lock(bp)) { - /* failed, so wait for the lock if requested. */ - if (!(flags & XBF_TRYLOCK)) { - xfs_buf_lock(bp); - XFS_STATS_INC(xb_get_locked_waited); - } else { + if (!xfs_buf_trylock(bp)) { + if (flags & XBF_TRYLOCK) { xfs_buf_rele(bp); XFS_STATS_INC(xb_busy_locked); return NULL; } + xfs_buf_lock(bp); + XFS_STATS_INC(xb_get_locked_waited); } /* @@ -594,10 +592,8 @@ _xfs_buf_read( ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE))); ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL); - bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | \ - XBF_READ_AHEAD | _XBF_RUN_QUEUES); - bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | \ - XBF_READ_AHEAD | _XBF_RUN_QUEUES); + bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD); + bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); status = xfs_buf_iorequest(bp); if (status || XFS_BUF_ISERROR(bp) || (flags & XBF_ASYNC)) @@ -681,7 +677,6 @@ xfs_buf_read_uncached( return NULL; /* set up the buffer for a read IO */ - xfs_buf_lock(bp); XFS_BUF_SET_ADDR(bp, daddr); XFS_BUF_READ(bp); XFS_BUF_BUSY(bp); @@ -816,8 +811,6 @@ xfs_buf_get_uncached( goto fail_free_mem; } - xfs_buf_unlock(bp); - trace_xfs_buf_get_uncached(bp, _RET_IP_); return bp; @@ -896,8 +889,8 @@ xfs_buf_rele( * to push on stale inode buffers. */ int -xfs_buf_cond_lock( - xfs_buf_t *bp) +xfs_buf_trylock( + struct xfs_buf *bp) { int locked; @@ -907,15 +900,8 @@ xfs_buf_cond_lock( else if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) xfs_log_force(bp->b_target->bt_mount, 0); - trace_xfs_buf_cond_lock(bp, _RET_IP_); - return locked ? 0 : -EBUSY; -} - -int -xfs_buf_lock_value( - xfs_buf_t *bp) -{ - return bp->b_sema.count; + trace_xfs_buf_trylock(bp, _RET_IP_); + return locked; } /* @@ -929,7 +915,7 @@ xfs_buf_lock_value( */ void xfs_buf_lock( - xfs_buf_t *bp) + struct xfs_buf *bp) { trace_xfs_buf_lock(bp, _RET_IP_); @@ -950,7 +936,7 @@ xfs_buf_lock( */ void xfs_buf_unlock( - xfs_buf_t *bp) + struct xfs_buf *bp) { if ((bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)) == XBF_DELWRI) { atomic_inc(&bp->b_hold); @@ -1121,7 +1107,7 @@ xfs_bioerror_relse( XFS_BUF_UNDELAYWRITE(bp); XFS_BUF_DONE(bp); XFS_BUF_STALE(bp); - XFS_BUF_CLR_IODONE_FUNC(bp); + bp->b_iodone = NULL; if (!(fl & XBF_ASYNC)) { /* * Mark b_error and B_ERROR _both_. @@ -1223,23 +1209,21 @@ _xfs_buf_ioapply( total_nr_pages = bp->b_page_count; map_i = 0; - if (bp->b_flags & XBF_ORDERED) { - ASSERT(!(bp->b_flags & XBF_READ)); - rw = WRITE_FLUSH_FUA; - } else if (bp->b_flags & XBF_LOG_BUFFER) { - ASSERT(!(bp->b_flags & XBF_READ_AHEAD)); - bp->b_flags &= ~_XBF_RUN_QUEUES; - rw = (bp->b_flags & XBF_WRITE) ? WRITE_SYNC : READ_SYNC; - } else if (bp->b_flags & _XBF_RUN_QUEUES) { - ASSERT(!(bp->b_flags & XBF_READ_AHEAD)); - bp->b_flags &= ~_XBF_RUN_QUEUES; - rw = (bp->b_flags & XBF_WRITE) ? WRITE_META : READ_META; + if (bp->b_flags & XBF_WRITE) { + if (bp->b_flags & XBF_SYNCIO) + rw = WRITE_SYNC; + else + rw = WRITE; + if (bp->b_flags & XBF_FUA) + rw |= REQ_FUA; + if (bp->b_flags & XBF_FLUSH) + rw |= REQ_FLUSH; + } else if (bp->b_flags & XBF_READ_AHEAD) { + rw = READA; } else { - rw = (bp->b_flags & XBF_WRITE) ? WRITE : - (bp->b_flags & XBF_READ_AHEAD) ? READA : READ; + rw = READ; } - next_chunk: atomic_inc(&bp->b_io_remaining); nr_pages = BIO_MAX_SECTORS >> (PAGE_SHIFT - BBSHIFT); @@ -1694,15 +1678,14 @@ xfs_buf_delwri_split( list_for_each_entry_safe(bp, n, dwq, b_list) { ASSERT(bp->b_flags & XBF_DELWRI); - if (!XFS_BUF_ISPINNED(bp) && !xfs_buf_cond_lock(bp)) { + if (!XFS_BUF_ISPINNED(bp) && xfs_buf_trylock(bp)) { if (!force && time_before(jiffies, bp->b_queuetime + age)) { xfs_buf_unlock(bp); break; } - bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q| - _XBF_RUN_QUEUES); + bp->b_flags &= ~(XBF_DELWRI | _XBF_DELWRI_Q); bp->b_flags |= XBF_WRITE; list_move_tail(&bp->b_list, list); trace_xfs_buf_delwri_split(bp, _RET_IP_); @@ -1738,14 +1721,6 @@ xfs_buf_cmp( return 0; } -void -xfs_buf_delwri_sort( - xfs_buftarg_t *target, - struct list_head *list) -{ - list_sort(NULL, list, xfs_buf_cmp); -} - STATIC int xfsbufd( void *data) diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index 50a7d5f..6a83b46 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -46,43 +46,46 @@ typedef enum { #define XBF_READ (1 << 0) /* buffer intended for reading from device */ #define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ -#define XBF_MAPPED (1 << 2) /* buffer mapped (b_addr valid) */ +#define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ +#define XBF_MAPPED (1 << 3) /* buffer mapped (b_addr valid) */ #define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ #define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ #define XBF_DELWRI (1 << 6) /* buffer has dirty pages */ #define XBF_STALE (1 << 7) /* buffer has been staled, do not find it */ -#define XBF_ORDERED (1 << 11)/* use ordered writes */ -#define XBF_READ_AHEAD (1 << 12)/* asynchronous read-ahead */ -#define XBF_LOG_BUFFER (1 << 13)/* this is a buffer used for the log */ + +/* I/O hints for the BIO layer */ +#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ +#define XBF_FUA (1 << 11)/* force cache write through mode */ +#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ /* flags used only as arguments to access routines */ -#define XBF_LOCK (1 << 14)/* lock requested */ -#define XBF_TRYLOCK (1 << 15)/* lock requested, but do not wait */ -#define XBF_DONT_BLOCK (1 << 16)/* do not block in current thread */ +#define XBF_LOCK (1 << 15)/* lock requested */ +#define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ +#define XBF_DONT_BLOCK (1 << 17)/* do not block in current thread */ /* flags used only internally */ -#define _XBF_PAGES (1 << 18)/* backed by refcounted pages */ -#define _XBF_RUN_QUEUES (1 << 19)/* run block device task queue */ -#define _XBF_KMEM (1 << 20)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 21)/* buffer on delwri queue */ +#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ +#define _XBF_KMEM (1 << 21)/* backed by heap memory */ +#define _XBF_DELWRI_Q (1 << 22)/* buffer on delwri queue */ typedef unsigned int xfs_buf_flags_t; #define XFS_BUF_FLAGS \ { XBF_READ, "READ" }, \ { XBF_WRITE, "WRITE" }, \ + { XBF_READ_AHEAD, "READ_AHEAD" }, \ { XBF_MAPPED, "MAPPED" }, \ { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ { XBF_DELWRI, "DELWRI" }, \ { XBF_STALE, "STALE" }, \ - { XBF_ORDERED, "ORDERED" }, \ - { XBF_READ_AHEAD, "READ_AHEAD" }, \ + { XBF_SYNCIO, "SYNCIO" }, \ + { XBF_FUA, "FUA" }, \ + { XBF_FLUSH, "FLUSH" }, \ { XBF_LOCK, "LOCK" }, /* should never be set */\ { XBF_TRYLOCK, "TRYLOCK" }, /* ditto */\ { XBF_DONT_BLOCK, "DONT_BLOCK" }, /* ditto */\ { _XBF_PAGES, "PAGES" }, \ - { _XBF_RUN_QUEUES, "RUN_QUEUES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" } @@ -91,11 +94,6 @@ typedef enum { XBT_FORCE_FLUSH = 1, } xfs_buftarg_flags_t; -typedef struct xfs_bufhash { - struct list_head bh_list; - spinlock_t bh_lock; -} xfs_bufhash_t; - typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; @@ -151,7 +149,7 @@ typedef struct xfs_buf { xfs_buf_iodone_t b_iodone; /* I/O completion function */ struct completion b_iowait; /* queue for I/O waiters */ void *b_fspriv; - void *b_fspriv2; + struct xfs_trans *b_transp; struct page **b_pages; /* array of page pointers */ struct page *b_page_array[XB_PAGES]; /* inline pages */ unsigned long b_queuetime; /* time buffer was queued */ @@ -192,10 +190,11 @@ extern void xfs_buf_free(xfs_buf_t *); extern void xfs_buf_rele(xfs_buf_t *); /* Locking and Unlocking Buffers */ -extern int xfs_buf_cond_lock(xfs_buf_t *); -extern int xfs_buf_lock_value(xfs_buf_t *); +extern int xfs_buf_trylock(xfs_buf_t *); extern void xfs_buf_lock(xfs_buf_t *); extern void xfs_buf_unlock(xfs_buf_t *); +#define xfs_buf_islocked(bp) \ + ((bp)->b_sema.count <= 0) /* Buffer Read and Write Routines */ extern int xfs_bwrite(struct xfs_mount *mp, struct xfs_buf *bp); @@ -234,8 +233,9 @@ extern void xfs_buf_terminate(void); #define XFS_BUF_BFLAGS(bp) ((bp)->b_flags) -#define XFS_BUF_ZEROFLAGS(bp) ((bp)->b_flags &= \ - ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI|XBF_ORDERED)) +#define XFS_BUF_ZEROFLAGS(bp) \ + ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI| \ + XBF_SYNCIO|XBF_FUA|XBF_FLUSH)) void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_STALE(bp) xfs_buf_stale(bp); @@ -267,10 +267,6 @@ void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_UNASYNC(bp) ((bp)->b_flags &= ~XBF_ASYNC) #define XFS_BUF_ISASYNC(bp) ((bp)->b_flags & XBF_ASYNC) -#define XFS_BUF_ORDERED(bp) ((bp)->b_flags |= XBF_ORDERED) -#define XFS_BUF_UNORDERED(bp) ((bp)->b_flags &= ~XBF_ORDERED) -#define XFS_BUF_ISORDERED(bp) ((bp)->b_flags & XBF_ORDERED) - #define XFS_BUF_HOLD(bp) xfs_buf_hold(bp) #define XFS_BUF_READ(bp) ((bp)->b_flags |= XBF_READ) #define XFS_BUF_UNREAD(bp) ((bp)->b_flags &= ~XBF_READ) @@ -280,14 +276,6 @@ void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_UNWRITE(bp) ((bp)->b_flags &= ~XBF_WRITE) #define XFS_BUF_ISWRITE(bp) ((bp)->b_flags & XBF_WRITE) -#define XFS_BUF_IODONE_FUNC(bp) ((bp)->b_iodone) -#define XFS_BUF_SET_IODONE_FUNC(bp, func) ((bp)->b_iodone = (func)) -#define XFS_BUF_CLR_IODONE_FUNC(bp) ((bp)->b_iodone = NULL) - -#define XFS_BUF_FSPRIVATE(bp, type) ((type)(bp)->b_fspriv) -#define XFS_BUF_SET_FSPRIVATE(bp, val) ((bp)->b_fspriv = (void*)(val)) -#define XFS_BUF_FSPRIVATE2(bp, type) ((type)(bp)->b_fspriv2) -#define XFS_BUF_SET_FSPRIVATE2(bp, val) ((bp)->b_fspriv2 = (void*)(val)) #define XFS_BUF_SET_START(bp) do { } while (0) #define XFS_BUF_PTR(bp) (xfs_caddr_t)((bp)->b_addr) @@ -313,10 +301,6 @@ xfs_buf_set_ref( #define XFS_BUF_ISPINNED(bp) atomic_read(&((bp)->b_pin_count)) -#define XFS_BUF_VALUSEMA(bp) xfs_buf_lock_value(bp) -#define XFS_BUF_CPSEMA(bp) (xfs_buf_cond_lock(bp) == 0) -#define XFS_BUF_VSEMA(bp) xfs_buf_unlock(bp) -#define XFS_BUF_PSEMA(bp,x) xfs_buf_lock(bp) #define XFS_BUF_FINISH_IOWAIT(bp) complete(&bp->b_iowait); #define XFS_BUF_SET_TARGET(bp, target) ((bp)->b_target = (target)) diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c index f4f878f..75e5d32 100644 --- a/fs/xfs/linux-2.6/xfs_export.c +++ b/fs/xfs/linux-2.6/xfs_export.c @@ -151,14 +151,14 @@ xfs_nfs_get_inode( * We don't use ESTALE directly down the chain to not * confuse applications using bulkstat that expect EINVAL. */ - if (error == EINVAL) + if (error == EINVAL || error == ENOENT) error = ESTALE; return ERR_PTR(-error); } if (ip->i_d.di_gen != generation) { IRELE(ip); - return ERR_PTR(-ENOENT); + return ERR_PTR(-ESTALE); } return VFS_I(ip); diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index 7f782af..8073f61 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -944,7 +944,7 @@ xfs_file_fallocate( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = new_size; - error = -xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK); + error = -xfs_setattr_size(ip, &iattr, XFS_ATTR_NOLOCK); } out_unlock: diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c index d44d92c..501e4f6 100644 --- a/fs/xfs/linux-2.6/xfs_iops.c +++ b/fs/xfs/linux-2.6/xfs_iops.c @@ -39,6 +39,7 @@ #include "xfs_buf_item.h" #include "xfs_utils.h" #include "xfs_vnodeops.h" +#include "xfs_inode_item.h" #include "xfs_trace.h" #include <linux/capability.h> @@ -497,12 +498,442 @@ xfs_vn_getattr( return 0; } +int +xfs_setattr_nonsize( + struct xfs_inode *ip, + struct iattr *iattr, + int flags) +{ + xfs_mount_t *mp = ip->i_mount; + struct inode *inode = VFS_I(ip); + int mask = iattr->ia_valid; + xfs_trans_t *tp; + int error; + uid_t uid = 0, iuid = 0; + gid_t gid = 0, igid = 0; + struct xfs_dquot *udqp = NULL, *gdqp = NULL; + struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL; + + trace_xfs_setattr(ip); + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return XFS_ERROR(EROFS); + + if (XFS_FORCED_SHUTDOWN(mp)) + return XFS_ERROR(EIO); + + error = -inode_change_ok(inode, iattr); + if (error) + return XFS_ERROR(error); + + ASSERT((mask & ATTR_SIZE) == 0); + + /* + * If disk quotas is on, we make sure that the dquots do exist on disk, + * before we start any other transactions. Trying to do this later + * is messy. We don't care to take a readlock to look at the ids + * in inode here, because we can't hold it across the trans_reserve. + * If the IDs do change before we take the ilock, we're covered + * because the i_*dquot fields will get updated anyway. + */ + if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) { + uint qflags = 0; + + if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) { + uid = iattr->ia_uid; + qflags |= XFS_QMOPT_UQUOTA; + } else { + uid = ip->i_d.di_uid; + } + if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) { + gid = iattr->ia_gid; + qflags |= XFS_QMOPT_GQUOTA; + } else { + gid = ip->i_d.di_gid; + } + + /* + * We take a reference when we initialize udqp and gdqp, + * so it is important that we never blindly double trip on + * the same variable. See xfs_create() for an example. + */ + ASSERT(udqp == NULL); + ASSERT(gdqp == NULL); + error = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip), + qflags, &udqp, &gdqp); + if (error) + return error; + } + + tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); + error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0); + if (error) + goto out_dqrele; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + + /* + * Change file ownership. Must be the owner or privileged. + */ + if (mask & (ATTR_UID|ATTR_GID)) { + /* + * These IDs could have changed since we last looked at them. + * But, we're assured that if the ownership did change + * while we didn't have the inode locked, inode's dquot(s) + * would have changed also. + */ + iuid = ip->i_d.di_uid; + igid = ip->i_d.di_gid; + gid = (mask & ATTR_GID) ? iattr->ia_gid : igid; + uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid; + + /* + * Do a quota reservation only if uid/gid is actually + * going to change. + */ + if (XFS_IS_QUOTA_RUNNING(mp) && + ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) || + (XFS_IS_GQUOTA_ON(mp) && igid != gid))) { + ASSERT(tp); + error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, + capable(CAP_FOWNER) ? + XFS_QMOPT_FORCE_RES : 0); + if (error) /* out of quota */ + goto out_trans_cancel; + } + } + + xfs_trans_ijoin(tp, ip); + + /* + * Change file ownership. Must be the owner or privileged. + */ + if (mask & (ATTR_UID|ATTR_GID)) { + /* + * CAP_FSETID overrides the following restrictions: + * + * The set-user-ID and set-group-ID bits of a file will be + * cleared upon successful return from chown() + */ + if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && + !capable(CAP_FSETID)) + ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); + + /* + * Change the ownerships and register quota modifications + * in the transaction. + */ + if (iuid != uid) { + if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) { + ASSERT(mask & ATTR_UID); + ASSERT(udqp); + olddquot1 = xfs_qm_vop_chown(tp, ip, + &ip->i_udquot, udqp); + } + ip->i_d.di_uid = uid; + inode->i_uid = uid; + } + if (igid != gid) { + if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) { + ASSERT(!XFS_IS_PQUOTA_ON(mp)); + ASSERT(mask & ATTR_GID); + ASSERT(gdqp); + olddquot2 = xfs_qm_vop_chown(tp, ip, + &ip->i_gdquot, gdqp); + } + ip->i_d.di_gid = gid; + inode->i_gid = gid; + } + } + + /* + * Change file access modes. + */ + if (mask & ATTR_MODE) { + umode_t mode = iattr->ia_mode; + + if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) + mode &= ~S_ISGID; + + ip->i_d.di_mode &= S_IFMT; + ip->i_d.di_mode |= mode & ~S_IFMT; + + inode->i_mode &= S_IFMT; + inode->i_mode |= mode & ~S_IFMT; + } + + /* + * Change file access or modified times. + */ + if (mask & ATTR_ATIME) { + inode->i_atime = iattr->ia_atime; + ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec; + ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec; + ip->i_update_core = 1; + } + if (mask & ATTR_CTIME) { + inode->i_ctime = iattr->ia_ctime; + ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; + ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec; + ip->i_update_core = 1; + } + if (mask & ATTR_MTIME) { + inode->i_mtime = iattr->ia_mtime; + ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; + ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; + ip->i_update_core = 1; + } + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + XFS_STATS_INC(xs_ig_attrchg); + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(tp); + error = xfs_trans_commit(tp, 0); + + xfs_iunlock(ip, XFS_ILOCK_EXCL); + + /* + * Release any dquot(s) the inode had kept before chown. + */ + xfs_qm_dqrele(olddquot1); + xfs_qm_dqrele(olddquot2); + xfs_qm_dqrele(udqp); + xfs_qm_dqrele(gdqp); + + if (error) + return XFS_ERROR(error); + + /* + * XXX(hch): Updating the ACL entries is not atomic vs the i_mode + * update. We could avoid this with linked transactions + * and passing down the transaction pointer all the way + * to attr_set. No previous user of the generic + * Posix ACL code seems to care about this issue either. + */ + if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) { + error = -xfs_acl_chmod(inode); + if (error) + return XFS_ERROR(error); + } + + return 0; + +out_trans_cancel: + xfs_trans_cancel(tp, 0); + xfs_iunlock(ip, XFS_ILOCK_EXCL); +out_dqrele: + xfs_qm_dqrele(udqp); + xfs_qm_dqrele(gdqp); + return error; +} + +/* + * Truncate file. Must have write permission and not be a directory. + */ +int +xfs_setattr_size( + struct xfs_inode *ip, + struct iattr *iattr, + int flags) +{ + struct xfs_mount *mp = ip->i_mount; + struct inode *inode = VFS_I(ip); + int mask = iattr->ia_valid; + struct xfs_trans *tp; + int error; + uint lock_flags; + uint commit_flags = 0; + + trace_xfs_setattr(ip); + + if (mp->m_flags & XFS_MOUNT_RDONLY) + return XFS_ERROR(EROFS); + + if (XFS_FORCED_SHUTDOWN(mp)) + return XFS_ERROR(EIO); + + error = -inode_change_ok(inode, iattr); + if (error) + return XFS_ERROR(error); + + ASSERT(S_ISREG(ip->i_d.di_mode)); + ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| + ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID| + ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + + lock_flags = XFS_ILOCK_EXCL; + if (!(flags & XFS_ATTR_NOLOCK)) + lock_flags |= XFS_IOLOCK_EXCL; + xfs_ilock(ip, lock_flags); + + /* + * Short circuit the truncate case for zero length files. + */ + if (iattr->ia_size == 0 && + ip->i_size == 0 && ip->i_d.di_nextents == 0) { + if (!(mask & (ATTR_CTIME|ATTR_MTIME))) + goto out_unlock; + + /* + * Use the regular setattr path to update the timestamps. + */ + xfs_iunlock(ip, lock_flags); + iattr->ia_valid &= ~ATTR_SIZE; + return xfs_setattr_nonsize(ip, iattr, 0); + } + + /* + * Make sure that the dquots are attached to the inode. + */ + error = xfs_qm_dqattach_locked(ip, 0); + if (error) + goto out_unlock; + + /* + * Now we can make the changes. Before we join the inode to the + * transaction, take care of the part of the truncation that must be + * done without the inode lock. This needs to be done before joining + * the inode to the transaction, because the inode cannot be unlocked + * once it is a part of the transaction. + */ + if (iattr->ia_size > ip->i_size) { + /* + * Do the first part of growing a file: zero any data in the + * last block that is beyond the old EOF. We need to do this + * before the inode is joined to the transaction to modify + * i_size. + */ + error = xfs_zero_eof(ip, iattr->ia_size, ip->i_size); + if (error) + goto out_unlock; + } + xfs_iunlock(ip, XFS_ILOCK_EXCL); + lock_flags &= ~XFS_ILOCK_EXCL; + + /* + * We are going to log the inode size change in this transaction so + * any previous writes that are beyond the on disk EOF and the new + * EOF that have not been written out need to be written here. If we + * do not write the data out, we expose ourselves to the null files + * problem. + * + * Only flush from the on disk size to the smaller of the in memory + * file size or the new size as that's the range we really care about + * here and prevents waiting for other data not within the range we + * care about here. + */ + if (ip->i_size != ip->i_d.di_size && iattr->ia_size > ip->i_d.di_size) { + error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size, + XBF_ASYNC, FI_NONE); + if (error) + goto out_unlock; + } + + /* + * Wait for all I/O to complete. + */ + xfs_ioend_wait(ip); + + error = -block_truncate_page(inode->i_mapping, iattr->ia_size, + xfs_get_blocks); + if (error) + goto out_unlock; + + tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE); + error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, + XFS_TRANS_PERM_LOG_RES, + XFS_ITRUNCATE_LOG_COUNT); + if (error) + goto out_trans_cancel; + + truncate_setsize(inode, iattr->ia_size); + + commit_flags = XFS_TRANS_RELEASE_LOG_RES; + lock_flags |= XFS_ILOCK_EXCL; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + + xfs_trans_ijoin(tp, ip); + + /* + * Only change the c/mtime if we are changing the size or we are + * explicitly asked to change it. This handles the semantic difference + * between truncate() and ftruncate() as implemented in the VFS. + * + * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a + * special case where we need to update the times despite not having + * these flags set. For all other operations the VFS set these flags + * explicitly if it wants a timestamp update. + */ + if (iattr->ia_size != ip->i_size && + (!(mask & (ATTR_CTIME | ATTR_MTIME)))) { + iattr->ia_ctime = iattr->ia_mtime = + current_fs_time(inode->i_sb); + mask |= ATTR_CTIME | ATTR_MTIME; + } + + if (iattr->ia_size > ip->i_size) { + ip->i_d.di_size = iattr->ia_size; + ip->i_size = iattr->ia_size; + } else if (iattr->ia_size <= ip->i_size || + (iattr->ia_size == 0 && ip->i_d.di_nextents)) { + error = xfs_itruncate_data(&tp, ip, iattr->ia_size); + if (error) + goto out_trans_abort; + + /* + * Truncated "down", so we're removing references to old data + * here - if we delay flushing for a long time, we expose + * ourselves unduly to the notorious NULL files problem. So, + * we mark this inode and flush it when the file is closed, + * and do not wait the usual (long) time for writeout. + */ + xfs_iflags_set(ip, XFS_ITRUNCATED); + } + + if (mask & ATTR_CTIME) { + inode->i_ctime = iattr->ia_ctime; + ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; + ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec; + ip->i_update_core = 1; + } + if (mask & ATTR_MTIME) { + inode->i_mtime = iattr->ia_mtime; + ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; + ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; + ip->i_update_core = 1; + } + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + XFS_STATS_INC(xs_ig_attrchg); + + if (mp->m_flags & XFS_MOUNT_WSYNC) + xfs_trans_set_sync(tp); + + error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); +out_unlock: + if (lock_flags) + xfs_iunlock(ip, lock_flags); + return error; + +out_trans_abort: + commit_flags |= XFS_TRANS_ABORT; +out_trans_cancel: + xfs_trans_cancel(tp, commit_flags); + goto out_unlock; +} + STATIC int xfs_vn_setattr( struct dentry *dentry, struct iattr *iattr) { - return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0); + if (iattr->ia_valid & ATTR_SIZE) + return -xfs_setattr_size(XFS_I(dentry->d_inode), iattr, 0); + return -xfs_setattr_nonsize(XFS_I(dentry->d_inode), iattr, 0); } #define XFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR) diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h index 8633521..d42f814 100644 --- a/fs/xfs/linux-2.6/xfs_linux.h +++ b/fs/xfs/linux-2.6/xfs_linux.h @@ -33,7 +33,6 @@ #endif #include <xfs_types.h> -#include <xfs_arch.h> #include <kmem.h> #include <mrlock.h> @@ -88,6 +87,12 @@ #include <xfs_buf.h> #include <xfs_message.h> +#ifdef __BIG_ENDIAN +#define XFS_NATIVE_HOST 1 +#else +#undef XFS_NATIVE_HOST +#endif + /* * Feature macros (disable/enable) */ diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index a1a881e..25fd2cd 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -33,7 +33,6 @@ #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_btree.h" -#include "xfs_btree_trace.h" #include "xfs_ialloc.h" #include "xfs_bmap.h" #include "xfs_rtalloc.h" @@ -1412,37 +1411,35 @@ xfs_fs_fill_super( sb->s_time_gran = 1; set_posix_acl_flag(sb); - error = xfs_syncd_init(mp); - if (error) - goto out_filestream_unmount; - xfs_inode_shrinker_register(mp); error = xfs_mountfs(mp); if (error) - goto out_syncd_stop; + goto out_filestream_unmount; + + error = xfs_syncd_init(mp); + if (error) + goto out_unmount; root = igrab(VFS_I(mp->m_rootip)); if (!root) { error = ENOENT; - goto fail_unmount; + goto out_syncd_stop; } if (is_bad_inode(root)) { error = EINVAL; - goto fail_vnrele; + goto out_syncd_stop; } sb->s_root = d_alloc_root(root); if (!sb->s_root) { error = ENOMEM; - goto fail_vnrele; + goto out_iput; } return 0; - out_syncd_stop: - xfs_inode_shrinker_unregister(mp); - xfs_syncd_stop(mp); out_filestream_unmount: + xfs_inode_shrinker_unregister(mp); xfs_filestream_unmount(mp); out_free_sb: xfs_freesb(mp); @@ -1456,17 +1453,12 @@ xfs_fs_fill_super( out: return -error; - fail_vnrele: - if (sb->s_root) { - dput(sb->s_root); - sb->s_root = NULL; - } else { - iput(root); - } - - fail_unmount: - xfs_inode_shrinker_unregister(mp); + out_iput: + iput(root); + out_syncd_stop: xfs_syncd_stop(mp); + out_unmount: + xfs_inode_shrinker_unregister(mp); /* * Blow away any referenced inode in the filestreams cache. diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c index 8ecad5f..5cc158e 100644 --- a/fs/xfs/linux-2.6/xfs_sync.c +++ b/fs/xfs/linux-2.6/xfs_sync.c @@ -359,14 +359,12 @@ xfs_quiesce_data( { int error, error2 = 0; - /* push non-blocking */ - xfs_sync_data(mp, 0); xfs_qm_sync(mp, SYNC_TRYLOCK); - - /* push and block till complete */ - xfs_sync_data(mp, SYNC_WAIT); xfs_qm_sync(mp, SYNC_WAIT); + /* force out the newly dirtied log buffers */ + xfs_log_force(mp, XFS_LOG_SYNC); + /* write superblock and hoover up shutdown errors */ error = xfs_sync_fsdata(mp); @@ -436,7 +434,7 @@ xfs_quiesce_attr( WARN_ON(atomic_read(&mp->m_active_trans) != 0); /* Push the superblock and write an unmount record */ - error = xfs_log_sbcount(mp, 1); + error = xfs_log_sbcount(mp); if (error) xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. " "Frozen image may not be consistent."); diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h index e3a6ad2..e914fd6 100644 --- a/fs/xfs/linux-2.6/xfs_sync.h +++ b/fs/xfs/linux-2.6/xfs_sync.h @@ -21,14 +21,6 @@ struct xfs_mount; struct xfs_perag; -typedef struct xfs_sync_work { - struct list_head w_list; - struct xfs_mount *w_mount; - void *w_data; /* syncer routine argument */ - void (*w_syncer)(struct xfs_mount *, void *); - struct completion *w_completion; -} xfs_sync_work_t; - #define SYNC_WAIT 0x0001 /* wait for i/o to complete */ #define SYNC_TRYLOCK 0x0002 /* only try to lock inodes */ diff --git a/fs/xfs/linux-2.6/xfs_trace.h b/fs/xfs/linux-2.6/xfs_trace.h index d48b7a5..fda0708 100644 --- a/fs/xfs/linux-2.6/xfs_trace.h +++ b/fs/xfs/linux-2.6/xfs_trace.h @@ -293,7 +293,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class, __entry->buffer_length = bp->b_buffer_length; __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); - __entry->lockval = xfs_buf_lock_value(bp); + __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; __entry->caller_ip = caller_ip; ), @@ -323,7 +323,7 @@ DEFINE_BUF_EVENT(xfs_buf_bawrite); DEFINE_BUF_EVENT(xfs_buf_bdwrite); DEFINE_BUF_EVENT(xfs_buf_lock); DEFINE_BUF_EVENT(xfs_buf_lock_done); -DEFINE_BUF_EVENT(xfs_buf_cond_lock); +DEFINE_BUF_EVENT(xfs_buf_trylock); DEFINE_BUF_EVENT(xfs_buf_unlock); DEFINE_BUF_EVENT(xfs_buf_iowait); DEFINE_BUF_EVENT(xfs_buf_iowait_done); @@ -366,7 +366,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class, __entry->flags = flags; __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); - __entry->lockval = xfs_buf_lock_value(bp); + __entry->lockval = bp->b_sema.count; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " @@ -409,7 +409,7 @@ TRACE_EVENT(xfs_buf_ioerror, __entry->buffer_length = bp->b_buffer_length; __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); - __entry->lockval = xfs_buf_lock_value(bp); + __entry->lockval = bp->b_sema.count; __entry->error = error; __entry->flags = bp->b_flags; __entry->caller_ip = caller_ip; @@ -454,7 +454,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class, __entry->buf_flags = bip->bli_buf->b_flags; __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count); - __entry->buf_lockval = xfs_buf_lock_value(bip->bli_buf); + __entry->buf_lockval = bip->bli_buf->b_sema.count; __entry->li_desc = bip->bli_item.li_desc; __entry->li_flags = bip->bli_item.li_flags; ), @@ -998,7 +998,8 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) - __field(loff_t, size) + __field(loff_t, isize) + __field(loff_t, disize) __field(loff_t, new_size) __field(loff_t, offset) __field(size_t, count) @@ -1006,16 +1007,18 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = ip->i_ino; - __entry->size = ip->i_d.di_size; + __entry->isize = ip->i_size; + __entry->disize = ip->i_d.di_size; __entry->new_size = ip->i_new_size; __entry->offset = offset; __entry->count = count; ), - TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx " + TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx new_size 0x%llx " "offset 0x%llx count %zd", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, - __entry->size, + __entry->isize, + __entry->disize, __entry->new_size, __entry->offset, __entry->count) @@ -1028,40 +1031,7 @@ DEFINE_EVENT(xfs_simple_io_class, name, \ DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc); DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert); DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound); - - -TRACE_EVENT(xfs_itruncate_start, - TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size, int flag, - xfs_off_t toss_start, xfs_off_t toss_finish), - TP_ARGS(ip, new_size, flag, toss_start, toss_finish), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(xfs_ino_t, ino) - __field(xfs_fsize_t, size) - __field(xfs_fsize_t, new_size) - __field(xfs_off_t, toss_start) - __field(xfs_off_t, toss_finish) - __field(int, flag) - ), - TP_fast_assign( - __entry->dev = VFS_I(ip)->i_sb->s_dev; - __entry->ino = ip->i_ino; - __entry->size = ip->i_d.di_size; - __entry->new_size = new_size; - __entry->toss_start = toss_start; - __entry->toss_finish = toss_finish; - __entry->flag = flag; - ), - TP_printk("dev %d:%d ino 0x%llx %s size 0x%llx new_size 0x%llx " - "toss start 0x%llx toss finish 0x%llx", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __print_flags(__entry->flag, "|", XFS_ITRUNC_FLAGS), - __entry->size, - __entry->new_size, - __entry->toss_start, - __entry->toss_finish) -); +DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize); DECLARE_EVENT_CLASS(xfs_itrunc_class, TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), @@ -1089,8 +1059,8 @@ DECLARE_EVENT_CLASS(xfs_itrunc_class, DEFINE_EVENT(xfs_itrunc_class, name, \ TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), \ TP_ARGS(ip, new_size)) -DEFINE_ITRUNC_EVENT(xfs_itruncate_finish_start); -DEFINE_ITRUNC_EVENT(xfs_itruncate_finish_end); +DEFINE_ITRUNC_EVENT(xfs_itruncate_data_start); +DEFINE_ITRUNC_EVENT(xfs_itruncate_data_end); TRACE_EVENT(xfs_pagecache_inval, TP_PROTO(struct xfs_inode *ip, xfs_off_t start, xfs_off_t finish), diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c index 6fa2146..837f311 100644 --- a/fs/xfs/quota/xfs_dquot.c +++ b/fs/xfs/quota/xfs_dquot.c @@ -220,7 +220,7 @@ xfs_qm_adjust_dqtimers( { ASSERT(d->d_id); -#ifdef QUOTADEBUG +#ifdef DEBUG if (d->d_blk_hardlimit) ASSERT(be64_to_cpu(d->d_blk_softlimit) <= be64_to_cpu(d->d_blk_hardlimit)); @@ -231,6 +231,7 @@ xfs_qm_adjust_dqtimers( ASSERT(be64_to_cpu(d->d_rtb_softlimit) <= be64_to_cpu(d->d_rtb_hardlimit)); #endif + if (!d->d_btimer) { if ((d->d_blk_softlimit && (be64_to_cpu(d->d_bcount) >= @@ -318,7 +319,7 @@ xfs_qm_init_dquot_blk( ASSERT(tp); ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); d = (xfs_dqblk_t *)XFS_BUF_PTR(bp); @@ -534,7 +535,7 @@ xfs_qm_dqtobp( } ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); /* * calculate the location of the dquot inside the buffer. @@ -622,7 +623,7 @@ xfs_qm_dqread( * brelse it because we have the changes incore. */ ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); xfs_trans_brelse(tp, bp); return (error); @@ -1423,45 +1424,6 @@ xfs_qm_dqpurge( } -#ifdef QUOTADEBUG -void -xfs_qm_dqprint(xfs_dquot_t *dqp) -{ - struct xfs_mount *mp = dqp->q_mount; - - xfs_debug(mp, "-----------KERNEL DQUOT----------------"); - xfs_debug(mp, "---- dquotID = %d", - (int)be32_to_cpu(dqp->q_core.d_id)); - xfs_debug(mp, "---- type = %s", DQFLAGTO_TYPESTR(dqp)); - xfs_debug(mp, "---- fs = 0x%p", dqp->q_mount); - xfs_debug(mp, "---- blkno = 0x%x", (int) dqp->q_blkno); - xfs_debug(mp, "---- boffset = 0x%x", (int) dqp->q_bufoffset); - xfs_debug(mp, "---- blkhlimit = %Lu (0x%x)", - be64_to_cpu(dqp->q_core.d_blk_hardlimit), - (int)be64_to_cpu(dqp->q_core.d_blk_hardlimit)); - xfs_debug(mp, "---- blkslimit = %Lu (0x%x)", - be64_to_cpu(dqp->q_core.d_blk_softlimit), - (int)be64_to_cpu(dqp->q_core.d_blk_softlimit)); - xfs_debug(mp, "---- inohlimit = %Lu (0x%x)", - be64_to_cpu(dqp->q_core.d_ino_hardlimit), - (int)be64_to_cpu(dqp->q_core.d_ino_hardlimit)); - xfs_debug(mp, "---- inoslimit = %Lu (0x%x)", - be64_to_cpu(dqp->q_core.d_ino_softlimit), - (int)be64_to_cpu(dqp->q_core.d_ino_softlimit)); - xfs_debug(mp, "---- bcount = %Lu (0x%x)", - be64_to_cpu(dqp->q_core.d_bcount), - (int)be64_to_cpu(dqp->q_core.d_bcount)); - xfs_debug(mp, "---- icount = %Lu (0x%x)", - be64_to_cpu(dqp->q_core.d_icount), - (int)be64_to_cpu(dqp->q_core.d_icount)); - xfs_debug(mp, "---- btimer = %d", - (int)be32_to_cpu(dqp->q_core.d_btimer)); - xfs_debug(mp, "---- itimer = %d", - (int)be32_to_cpu(dqp->q_core.d_itimer)); - xfs_debug(mp, "---------------------------"); -} -#endif - /* * Give the buffer a little push if it is incore and * wait on the flush lock. diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/quota/xfs_dquot.h index 5da3a23..34b7e94 100644 --- a/fs/xfs/quota/xfs_dquot.h +++ b/fs/xfs/quota/xfs_dquot.h @@ -116,12 +116,6 @@ static inline void xfs_dqfunlock(xfs_dquot_t *dqp) (XFS_IS_UQUOTA_ON((d)->q_mount)) : \ (XFS_IS_OQUOTA_ON((d)->q_mount)))) -#ifdef QUOTADEBUG -extern void xfs_qm_dqprint(xfs_dquot_t *); -#else -#define xfs_qm_dqprint(a) -#endif - extern void xfs_qm_dqdestroy(xfs_dquot_t *); extern int xfs_qm_dqflush(xfs_dquot_t *, uint); extern int xfs_qm_dqpurge(xfs_dquot_t *); diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c index b94dace..46e54ad 100644 --- a/fs/xfs/quota/xfs_qm.c +++ b/fs/xfs/quota/xfs_qm.c @@ -67,32 +67,6 @@ static struct shrinker xfs_qm_shaker = { .seeks = DEFAULT_SEEKS, }; -#ifdef DEBUG -extern struct mutex qcheck_lock; -#endif - -#ifdef QUOTADEBUG -static void -xfs_qm_dquot_list_print( - struct xfs_mount *mp) -{ - xfs_dquot_t *dqp; - int i = 0; - - list_for_each_entry(dqp, &mp->m_quotainfo->qi_dqlist_lock, qi_mplist) { - xfs_debug(mp, " %d. \"%d (%s)\" " - "bcnt = %lld, icnt = %lld, refs = %d", - i++, be32_to_cpu(dqp->q_core.d_id), - DQFLAGTO_TYPESTR(dqp), - (long long)be64_to_cpu(dqp->q_core.d_bcount), - (long long)be64_to_cpu(dqp->q_core.d_icount), - dqp->q_nrefs); - } -} -#else -static void xfs_qm_dquot_list_print(struct xfs_mount *mp) { } -#endif - /* * Initialize the XQM structure. * Note that there is not one quota manager per file system. @@ -165,9 +139,6 @@ xfs_Gqm_init(void) atomic_set(&xqm->qm_totaldquots, 0); xqm->qm_dqfree_ratio = XFS_QM_DQFREE_RATIO; xqm->qm_nrefs = 0; -#ifdef DEBUG - mutex_init(&qcheck_lock); -#endif return xqm; out_free_udqhash: @@ -204,9 +175,6 @@ xfs_qm_destroy( mutex_lock(&xqm->qm_dqfrlist_lock); list_for_each_entry_safe(dqp, n, &xqm->qm_dqfrlist, q_freelist) { xfs_dqlock(dqp); -#ifdef QUOTADEBUG - xfs_debug(dqp->q_mount, "FREELIST destroy 0x%p", dqp); -#endif list_del_init(&dqp->q_freelist); xfs_Gqm->qm_dqfrlist_cnt--; xfs_dqunlock(dqp); @@ -214,9 +182,6 @@ xfs_qm_destroy( } mutex_unlock(&xqm->qm_dqfrlist_lock); mutex_destroy(&xqm->qm_dqfrlist_lock); -#ifdef DEBUG - mutex_destroy(&qcheck_lock); -#endif kmem_free(xqm); } @@ -409,11 +374,6 @@ xfs_qm_mount_quotas( xfs_warn(mp, "Failed to initialize disk quotas."); return; } - -#ifdef QUOTADEBUG - if (XFS_IS_QUOTA_ON(mp)) - xfs_qm_internalqcheck(mp); -#endif } /* @@ -866,8 +826,8 @@ xfs_qm_dqattach_locked( } done: -#ifdef QUOTADEBUG - if (! error) { +#ifdef DEBUG + if (!error) { if (XFS_IS_UQUOTA_ON(mp)) ASSERT(ip->i_udquot); if (XFS_IS_OQUOTA_ON(mp)) @@ -1733,8 +1693,6 @@ xfs_qm_quotacheck( mp->m_qflags &= ~(XFS_OQUOTA_CHKD | XFS_UQUOTA_CHKD); mp->m_qflags |= flags; - xfs_qm_dquot_list_print(mp); - error_return: if (error) { xfs_warn(mp, @@ -2096,9 +2054,6 @@ xfs_qm_write_sb_changes( xfs_trans_t *tp; int error; -#ifdef QUOTADEBUG - xfs_notice(mp, "Writing superblock quota changes"); -#endif tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE); if ((error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/quota/xfs_qm.h index 567b29b..43b9abe 100644 --- a/fs/xfs/quota/xfs_qm.h +++ b/fs/xfs/quota/xfs_qm.h @@ -163,10 +163,4 @@ extern int xfs_qm_scall_getqstat(xfs_mount_t *, fs_quota_stat_t *); extern int xfs_qm_scall_quotaon(xfs_mount_t *, uint); extern int xfs_qm_scall_quotaoff(xfs_mount_t *, uint); -#ifdef DEBUG -extern int xfs_qm_internalqcheck(xfs_mount_t *); -#else -#define xfs_qm_internalqcheck(mp) (0) -#endif - #endif /* __XFS_QM_H__ */ diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c index 2dadb15..609246f 100644 --- a/fs/xfs/quota/xfs_qm_syscalls.c +++ b/fs/xfs/quota/xfs_qm_syscalls.c @@ -263,7 +263,7 @@ xfs_qm_scall_trunc_qfile( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip); - error = xfs_itruncate_finish(&tp, ip, 0, XFS_DATA_FORK, 1); + error = xfs_itruncate_data(&tp, ip, 0); if (error) { xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); @@ -622,7 +622,6 @@ xfs_qm_scall_setqlim( xfs_trans_log_dquot(tp, dqp); error = xfs_trans_commit(tp, 0); - xfs_qm_dqprint(dqp); xfs_qm_dqrele(dqp); out_unlock: @@ -657,7 +656,6 @@ xfs_qm_scall_getquota( xfs_qm_dqput(dqp); return XFS_ERROR(ENOENT); } - /* xfs_qm_dqprint(dqp); */ /* * Convert the disk dquot to the exportable format */ @@ -906,354 +904,3 @@ xfs_qm_dqrele_all_inodes( ASSERT(mp->m_quotainfo); xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags); } - -/*------------------------------------------------------------------------*/ -#ifdef DEBUG -/* - * This contains all the test functions for XFS disk quotas. - * Currently it does a quota accounting check. ie. it walks through - * all inodes in the file system, calculating the dquot accounting fields, - * and prints out any inconsistencies. - */ -xfs_dqhash_t *qmtest_udqtab; -xfs_dqhash_t *qmtest_gdqtab; -int qmtest_hashmask; -int qmtest_nfails; -struct mutex qcheck_lock; - -#define DQTEST_HASHVAL(mp, id) (((__psunsigned_t)(mp) + \ - (__psunsigned_t)(id)) & \ - (qmtest_hashmask - 1)) - -#define DQTEST_HASH(mp, id, type) ((type & XFS_DQ_USER) ? \ - (qmtest_udqtab + \ - DQTEST_HASHVAL(mp, id)) : \ - (qmtest_gdqtab + \ - DQTEST_HASHVAL(mp, id))) - -#define DQTEST_LIST_PRINT(l, NXT, title) \ -{ \ - xfs_dqtest_t *dqp; int i = 0;\ - xfs_debug(NULL, "%s (#%d)", title, (int) (l)->qh_nelems); \ - for (dqp = (xfs_dqtest_t *)(l)->qh_next; dqp != NULL; \ - dqp = (xfs_dqtest_t *)dqp->NXT) { \ - xfs_debug(dqp->q_mount, \ - " %d. \"%d (%s)\" bcnt = %d, icnt = %d", \ - ++i, dqp->d_id, DQFLAGTO_TYPESTR(dqp), \ - dqp->d_bcount, dqp->d_icount); } \ -} - -typedef struct dqtest { - uint dq_flags; /* various flags (XFS_DQ_*) */ - struct list_head q_hashlist; - xfs_dqhash_t *q_hash; /* the hashchain header */ - xfs_mount_t *q_mount; /* filesystem this relates to */ - xfs_dqid_t d_id; /* user id or group id */ - xfs_qcnt_t d_bcount; /* # disk blocks owned by the user */ - xfs_qcnt_t d_icount; /* # inodes owned by the user */ -} xfs_dqtest_t; - -STATIC void -xfs_qm_hashinsert(xfs_dqhash_t *h, xfs_dqtest_t *dqp) -{ - list_add(&dqp->q_hashlist, &h->qh_list); - h->qh_version++; - h->qh_nelems++; -} -STATIC void -xfs_qm_dqtest_print( - struct xfs_mount *mp, - struct dqtest *d) -{ - xfs_debug(mp, "-----------DQTEST DQUOT----------------"); - xfs_debug(mp, "---- dquot ID = %d", d->d_id); - xfs_debug(mp, "---- fs = 0x%p", d->q_mount); - xfs_debug(mp, "---- bcount = %Lu (0x%x)", - d->d_bcount, (int)d->d_bcount); - xfs_debug(mp, "---- icount = %Lu (0x%x)", - d->d_icount, (int)d->d_icount); - xfs_debug(mp, "---------------------------"); -} - -STATIC void -xfs_qm_dqtest_failed( - xfs_dqtest_t *d, - xfs_dquot_t *dqp, - char *reason, - xfs_qcnt_t a, - xfs_qcnt_t b, - int error) -{ - qmtest_nfails++; - if (error) - xfs_debug(dqp->q_mount, - "quotacheck failed id=%d, err=%d\nreason: %s", - d->d_id, error, reason); - else - xfs_debug(dqp->q_mount, - "quotacheck failed id=%d (%s) [%d != %d]", - d->d_id, reason, (int)a, (int)b); - xfs_qm_dqtest_print(dqp->q_mount, d); - if (dqp) - xfs_qm_dqprint(dqp); -} - -STATIC int -xfs_dqtest_cmp2( - xfs_dqtest_t *d, - xfs_dquot_t *dqp) -{ - int err = 0; - if (be64_to_cpu(dqp->q_core.d_icount) != d->d_icount) { - xfs_qm_dqtest_failed(d, dqp, "icount mismatch", - be64_to_cpu(dqp->q_core.d_icount), - d->d_icount, 0); - err++; - } - if (be64_to_cpu(dqp->q_core.d_bcount) != d->d_bcount) { - xfs_qm_dqtest_failed(d, dqp, "bcount mismatch", - be64_to_cpu(dqp->q_core.d_bcount), - d->d_bcount, 0); - err++; - } - if (dqp->q_core.d_blk_softlimit && - be64_to_cpu(dqp->q_core.d_bcount) >= - be64_to_cpu(dqp->q_core.d_blk_softlimit)) { - if (!dqp->q_core.d_btimer && dqp->q_core.d_id) { - xfs_debug(dqp->q_mount, - "%d [%s] BLK TIMER NOT STARTED", - d->d_id, DQFLAGTO_TYPESTR(d)); - err++; - } - } - if (dqp->q_core.d_ino_softlimit && - be64_to_cpu(dqp->q_core.d_icount) >= - be64_to_cpu(dqp->q_core.d_ino_softlimit)) { - if (!dqp->q_core.d_itimer && dqp->q_core.d_id) { - xfs_debug(dqp->q_mount, - "%d [%s] INO TIMER NOT STARTED", - d->d_id, DQFLAGTO_TYPESTR(d)); - err++; - } - } -#ifdef QUOTADEBUG - if (!err) { - xfs_debug(dqp->q_mount, "%d [%s] qchecked", - d->d_id, DQFLAGTO_TYPESTR(d)); - } -#endif - return (err); -} - -STATIC void -xfs_dqtest_cmp( - xfs_dqtest_t *d) -{ - xfs_dquot_t *dqp; - int error; - - /* xfs_qm_dqtest_print(d); */ - if ((error = xfs_qm_dqget(d->q_mount, NULL, d->d_id, d->dq_flags, 0, - &dqp))) { - xfs_qm_dqtest_failed(d, NULL, "dqget failed", 0, 0, error); - return; - } - xfs_dqtest_cmp2(d, dqp); - xfs_qm_dqput(dqp); -} - -STATIC int -xfs_qm_internalqcheck_dqget( - xfs_mount_t *mp, - xfs_dqid_t id, - uint type, - xfs_dqtest_t **O_dq) -{ - xfs_dqtest_t *d; - xfs_dqhash_t *h; - - h = DQTEST_HASH(mp, id, type); - list_for_each_entry(d, &h->qh_list, q_hashlist) { - if (d->d_id == id && mp == d->q_mount) { - *O_dq = d; - return (0); - } - } - d = kmem_zalloc(sizeof(xfs_dqtest_t), KM_SLEEP); - d->dq_flags = type; - d->d_id = id; - d->q_mount = mp; - d->q_hash = h; - INIT_LIST_HEAD(&d->q_hashlist); - xfs_qm_hashinsert(h, d); - *O_dq = d; - return (0); -} - -STATIC void -xfs_qm_internalqcheck_get_dquots( - xfs_mount_t *mp, - xfs_dqid_t uid, - xfs_dqid_t projid, - xfs_dqid_t gid, - xfs_dqtest_t **ud, - xfs_dqtest_t **gd) -{ - if (XFS_IS_UQUOTA_ON(mp)) - xfs_qm_internalqcheck_dqget(mp, uid, XFS_DQ_USER, ud); - if (XFS_IS_GQUOTA_ON(mp)) - xfs_qm_internalqcheck_dqget(mp, gid, XFS_DQ_GROUP, gd); - else if (XFS_IS_PQUOTA_ON(mp)) - xfs_qm_internalqcheck_dqget(mp, projid, XFS_DQ_PROJ, gd); -} - - -STATIC void -xfs_qm_internalqcheck_dqadjust( - xfs_inode_t *ip, - xfs_dqtest_t *d) -{ - d->d_icount++; - d->d_bcount += (xfs_qcnt_t)ip->i_d.di_nblocks; -} - -STATIC int -xfs_qm_internalqcheck_adjust( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - void __user *buffer, /* not used */ - int ubsize, /* not used */ - int *ubused, /* not used */ - int *res) /* bulkstat result code */ -{ - xfs_inode_t *ip; - xfs_dqtest_t *ud, *gd; - uint lock_flags; - boolean_t ipreleased; - int error; - - ASSERT(XFS_IS_QUOTA_RUNNING(mp)); - - if (ino == mp->m_sb.sb_uquotino || ino == mp->m_sb.sb_gquotino) { - *res = BULKSTAT_RV_NOTHING; - xfs_debug(mp, "%s: ino=%llu, uqino=%llu, gqino=%llu\n", - __func__, (unsigned long long) ino, - (unsigned long long) mp->m_sb.sb_uquotino, - (unsigned long long) mp->m_sb.sb_gquotino); - return XFS_ERROR(EINVAL); - } - ipreleased = B_FALSE; - again: - lock_flags = XFS_ILOCK_SHARED; - if ((error = xfs_iget(mp, NULL, ino, 0, lock_flags, &ip))) { - *res = BULKSTAT_RV_NOTHING; - return (error); - } - - /* - * This inode can have blocks after eof which can get released - * when we send it to inactive. Since we don't check the dquot - * until the after all our calculations are done, we must get rid - * of those now. - */ - if (! ipreleased) { - xfs_iunlock(ip, lock_flags); - IRELE(ip); - ipreleased = B_TRUE; - goto again; - } - xfs_qm_internalqcheck_get_dquots(mp, - (xfs_dqid_t) ip->i_d.di_uid, - (xfs_dqid_t) xfs_get_projid(ip), - (xfs_dqid_t) ip->i_d.di_gid, - &ud, &gd); - if (XFS_IS_UQUOTA_ON(mp)) { - ASSERT(ud); - xfs_qm_internalqcheck_dqadjust(ip, ud); - } - if (XFS_IS_OQUOTA_ON(mp)) { - ASSERT(gd); - xfs_qm_internalqcheck_dqadjust(ip, gd); - } - xfs_iunlock(ip, lock_flags); - IRELE(ip); - *res = BULKSTAT_RV_DIDONE; - return (0); -} - - -/* PRIVATE, debugging */ -int -xfs_qm_internalqcheck( - xfs_mount_t *mp) -{ - xfs_ino_t lastino; - int done, count; - int i; - int error; - - lastino = 0; - qmtest_hashmask = 32; - count = 5; - done = 0; - qmtest_nfails = 0; - - if (! XFS_IS_QUOTA_ON(mp)) - return XFS_ERROR(ESRCH); - - xfs_log_force(mp, XFS_LOG_SYNC); - XFS_bflush(mp->m_ddev_targp); - xfs_log_force(mp, XFS_LOG_SYNC); - XFS_bflush(mp->m_ddev_targp); - - mutex_lock(&qcheck_lock); - /* There should be absolutely no quota activity while this - is going on. */ - qmtest_udqtab = kmem_zalloc(qmtest_hashmask * - sizeof(xfs_dqhash_t), KM_SLEEP); - qmtest_gdqtab = kmem_zalloc(qmtest_hashmask * - sizeof(xfs_dqhash_t), KM_SLEEP); - do { - /* - * Iterate thru all the inodes in the file system, - * adjusting the corresponding dquot counters - */ - error = xfs_bulkstat(mp, &lastino, &count, - xfs_qm_internalqcheck_adjust, - 0, NULL, &done); - if (error) { - xfs_debug(mp, "Bulkstat returned error 0x%x", error); - break; - } - } while (!done); - - xfs_debug(mp, "Checking results against system dquots"); - for (i = 0; i < qmtest_hashmask; i++) { - xfs_dqtest_t *d, *n; - xfs_dqhash_t *h; - - h = &qmtest_udqtab[i]; - list_for_each_entry_safe(d, n, &h->qh_list, q_hashlist) { - xfs_dqtest_cmp(d); - kmem_free(d); - } - h = &qmtest_gdqtab[i]; - list_for_each_entry_safe(d, n, &h->qh_list, q_hashlist) { - xfs_dqtest_cmp(d); - kmem_free(d); - } - } - - if (qmtest_nfails) { - xfs_debug(mp, "******** quotacheck failed ********"); - xfs_debug(mp, "failures = %d", qmtest_nfails); - } else { - xfs_debug(mp, "******** quotacheck successful! ********"); - } - kmem_free(qmtest_udqtab); - kmem_free(qmtest_gdqtab); - mutex_unlock(&qcheck_lock); - return (qmtest_nfails); -} - -#endif /* DEBUG */ diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/quota/xfs_trans_dquot.c index 2a36487..4d00ee6 100644 --- a/fs/xfs/quota/xfs_trans_dquot.c +++ b/fs/xfs/quota/xfs_trans_dquot.c @@ -59,7 +59,7 @@ xfs_trans_dqjoin( xfs_trans_add_item(tp, &dqp->q_logitem.qli_item); /* - * Initialize i_transp so we can later determine if this dquot is + * Initialize d_transp so we can later determine if this dquot is * associated with this transaction. */ dqp->q_transp = tp; @@ -387,18 +387,18 @@ xfs_trans_apply_dquot_deltas( qtrx->qt_delbcnt_delta; totalrtbdelta = qtrx->qt_rtbcount_delta + qtrx->qt_delrtb_delta; -#ifdef QUOTADEBUG +#ifdef DEBUG if (totalbdelta < 0) ASSERT(be64_to_cpu(d->d_bcount) >= - (xfs_qcnt_t) -totalbdelta); + -totalbdelta); if (totalrtbdelta < 0) ASSERT(be64_to_cpu(d->d_rtbcount) >= - (xfs_qcnt_t) -totalrtbdelta); + -totalrtbdelta); if (qtrx->qt_icount_delta < 0) ASSERT(be64_to_cpu(d->d_icount) >= - (xfs_qcnt_t) -qtrx->qt_icount_delta); + -qtrx->qt_icount_delta); #endif if (totalbdelta) be64_add_cpu(&d->d_bcount, (xfs_qcnt_t)totalbdelta); @@ -642,11 +642,6 @@ xfs_trans_dqresv( ((XFS_IS_UQUOTA_ENFORCED(dqp->q_mount) && XFS_QM_ISUDQ(dqp)) || (XFS_IS_OQUOTA_ENFORCED(dqp->q_mount) && (XFS_QM_ISPDQ(dqp) || XFS_QM_ISGDQ(dqp))))) { -#ifdef QUOTADEBUG - xfs_debug(mp, - "BLK Res: nblks=%ld + resbcount=%Ld > hardlimit=%Ld?", - nblks, *resbcountp, hardlimit); -#endif if (nblks > 0) { /* * dquot is locked already. See if we'd go over the diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h index 5ad8ad3..53ec3ea 100644 --- a/fs/xfs/xfs.h +++ b/fs/xfs/xfs.h @@ -22,7 +22,6 @@ #define STATIC #define DEBUG 1 #define XFS_BUF_LOCK_TRACKING 1 -/* #define QUOTADEBUG 1 */ #endif #include <linux-2.6/xfs_linux.h> diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 95862bb..1e00b3e 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -570,9 +570,7 @@ xfs_alloc_ag_vextent_exact( xfs_agblock_t tbno; /* start block of trimmed extent */ xfs_extlen_t tlen; /* length of trimmed extent */ xfs_agblock_t tend; /* end block of trimmed extent */ - xfs_agblock_t end; /* end of allocated extent */ int i; /* success/failure of operation */ - xfs_extlen_t rlen; /* length of returned extent */ ASSERT(args->alignment == 1); @@ -625,18 +623,16 @@ xfs_alloc_ag_vextent_exact( * * Fix the length according to mod and prod if given. */ - end = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen); - args->len = end - args->agbno; + args->len = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen) + - args->agbno; xfs_alloc_fix_len(args); if (!xfs_alloc_fix_minleft(args)) goto not_found; - rlen = args->len; - ASSERT(args->agbno + rlen <= tend); - end = args->agbno + rlen; + ASSERT(args->agbno + args->len <= tend); /* - * We are allocating agbno for rlen [agbno .. end] + * We are allocating agbno for args->len * Allocate/initialize a cursor for the by-size btree. */ cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp, @@ -2127,7 +2123,7 @@ xfs_read_agf( * Validate the magic number of the agf block. */ agf_ok = - be32_to_cpu(agf->agf_magicnum) == XFS_AGF_MAGIC && + agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) && XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) && be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) && be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) && diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c index 2b35188..ffb3386 100644 --- a/fs/xfs/xfs_alloc_btree.c +++ b/fs/xfs/xfs_alloc_btree.c @@ -31,7 +31,6 @@ #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_btree.h" -#include "xfs_btree_trace.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -311,72 +310,6 @@ xfs_allocbt_recs_inorder( } #endif /* DEBUG */ -#ifdef XFS_BTREE_TRACE -ktrace_t *xfs_allocbt_trace_buf; - -STATIC void -xfs_allocbt_trace_enter( - struct xfs_btree_cur *cur, - const char *func, - char *s, - int type, - int line, - __psunsigned_t a0, - __psunsigned_t a1, - __psunsigned_t a2, - __psunsigned_t a3, - __psunsigned_t a4, - __psunsigned_t a5, - __psunsigned_t a6, - __psunsigned_t a7, - __psunsigned_t a8, - __psunsigned_t a9, - __psunsigned_t a10) -{ - ktrace_enter(xfs_allocbt_trace_buf, (void *)(__psint_t)type, - (void *)func, (void *)s, NULL, (void *)cur, - (void *)a0, (void *)a1, (void *)a2, (void *)a3, - (void *)a4, (void *)a5, (void *)a6, (void *)a7, - (void *)a8, (void *)a9, (void *)a10); -} - -STATIC void -xfs_allocbt_trace_cursor( - struct xfs_btree_cur *cur, - __uint32_t *s0, - __uint64_t *l0, - __uint64_t *l1) -{ - *s0 = cur->bc_private.a.agno; - *l0 = cur->bc_rec.a.ar_startblock; - *l1 = cur->bc_rec.a.ar_blockcount; -} - -STATIC void -xfs_allocbt_trace_key( - struct xfs_btree_cur *cur, - union xfs_btree_key *key, - __uint64_t *l0, - __uint64_t *l1) -{ - *l0 = be32_to_cpu(key->alloc.ar_startblock); - *l1 = be32_to_cpu(key->alloc.ar_blockcount); -} - -STATIC void -xfs_allocbt_trace_record( - struct xfs_btree_cur *cur, - union xfs_btree_rec *rec, - __uint64_t *l0, - __uint64_t *l1, - __uint64_t *l2) -{ - *l0 = be32_to_cpu(rec->alloc.ar_startblock); - *l1 = be32_to_cpu(rec->alloc.ar_blockcount); - *l2 = 0; -} -#endif /* XFS_BTREE_TRACE */ - static const struct xfs_btree_ops xfs_allocbt_ops = { .rec_len = sizeof(xfs_alloc_rec_t), .key_len = sizeof(xfs_alloc_key_t), @@ -393,18 +326,10 @@ static const struct xfs_btree_ops xfs_allocbt_ops = { .init_rec_from_cur = xfs_allocbt_init_rec_from_cur, .init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur, .key_diff = xfs_allocbt_key_diff, - #ifdef DEBUG .keys_inorder = xfs_allocbt_keys_inorder, .recs_inorder = xfs_allocbt_recs_inorder, #endif - -#ifdef XFS_BTREE_TRACE - .trace_enter = xfs_allocbt_trace_enter, - .trace_cursor = xfs_allocbt_trace_cursor, - .trace_key = xfs_allocbt_trace_key, - .trace_record = xfs_allocbt_trace_record, -#endif }; /* @@ -427,13 +352,16 @@ xfs_allocbt_init_cursor( cur->bc_tp = tp; cur->bc_mp = mp; - cur->bc_nlevels = be32_to_cpu(agf->agf_levels[btnum]); cur->bc_btnum = btnum; cur->bc_blocklog = mp->m_sb.sb_blocklog; - cur->bc_ops = &xfs_allocbt_ops; - if (btnum == XFS_BTNUM_CNT) + + if (btnum == XFS_BTNUM_CNT) { + cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]); cur->bc_flags = XFS_BTREE_LASTREC_UPDATE; + } else { + cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]); + } cur->bc_private.a.agbp = agbp; cur->bc_private.a.agno = agno; diff --git a/fs/xfs/xfs_arch.h b/fs/xfs/xfs_arch.h deleted file mode 100644 index 0902249..0000000 --- a/fs/xfs/xfs_arch.h +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_ARCH_H__ -#define __XFS_ARCH_H__ - -#ifndef XFS_BIG_INUMS -# error XFS_BIG_INUMS must be defined true or false -#endif - -#ifdef __KERNEL__ - -#include <asm/byteorder.h> - -#ifdef __BIG_ENDIAN -#define XFS_NATIVE_HOST 1 -#else -#undef XFS_NATIVE_HOST -#endif - -#else /* __KERNEL__ */ - -#if __BYTE_ORDER == __BIG_ENDIAN -#define XFS_NATIVE_HOST 1 -#else -#undef XFS_NATIVE_HOST -#endif - -#ifdef XFS_NATIVE_HOST -#define cpu_to_be16(val) ((__force __be16)(__u16)(val)) -#define cpu_to_be32(val) ((__force __be32)(__u32)(val)) -#define cpu_to_be64(val) ((__force __be64)(__u64)(val)) -#define be16_to_cpu(val) ((__force __u16)(__be16)(val)) -#define be32_to_cpu(val) ((__force __u32)(__be32)(val)) -#define be64_to_cpu(val) ((__force __u64)(__be64)(val)) -#else -#define cpu_to_be16(val) ((__force __be16)__swab16((__u16)(val))) -#define cpu_to_be32(val) ((__force __be32)__swab32((__u32)(val))) -#define cpu_to_be64(val) ((__force __be64)__swab64((__u64)(val))) -#define be16_to_cpu(val) (__swab16((__force __u16)(__be16)(val))) -#define be32_to_cpu(val) (__swab32((__force __u32)(__be32)(val))) -#define be64_to_cpu(val) (__swab64((__force __u64)(__be64)(val))) -#endif - -static inline void be16_add_cpu(__be16 *a, __s16 b) -{ - *a = cpu_to_be16(be16_to_cpu(*a) + b); -} - -static inline void be32_add_cpu(__be32 *a, __s32 b) -{ - *a = cpu_to_be32(be32_to_cpu(*a) + b); -} - -static inline void be64_add_cpu(__be64 *a, __s64 b) -{ - *a = cpu_to_be64(be64_to_cpu(*a) + b); -} - -#endif /* __KERNEL__ */ - -/* - * get and set integers from potentially unaligned locations - */ - -#define INT_GET_UNALIGNED_16_BE(pointer) \ - ((__u16)((((__u8*)(pointer))[0] << 8) | (((__u8*)(pointer))[1]))) -#define INT_SET_UNALIGNED_16_BE(pointer,value) \ - { \ - ((__u8*)(pointer))[0] = (((value) >> 8) & 0xff); \ - ((__u8*)(pointer))[1] = (((value) ) & 0xff); \ - } - -/* - * In directories inode numbers are stored as unaligned arrays of unsigned - * 8bit integers on disk. - * - * For v1 directories or v2 directories that contain inode numbers that - * do not fit into 32bit the array has eight members, but the first member - * is always zero: - * - * |unused|48-55|40-47|32-39|24-31|16-23| 8-15| 0- 7| - * - * For v2 directories that only contain entries with inode numbers that fit - * into 32bits a four-member array is used: - * - * |24-31|16-23| 8-15| 0- 7| - */ - -#define XFS_GET_DIR_INO4(di) \ - (((__u32)(di).i[0] << 24) | ((di).i[1] << 16) | ((di).i[2] << 8) | ((di).i[3])) - -#define XFS_PUT_DIR_INO4(from, di) \ -do { \ - (di).i[0] = (((from) & 0xff000000ULL) >> 24); \ - (di).i[1] = (((from) & 0x00ff0000ULL) >> 16); \ - (di).i[2] = (((from) & 0x0000ff00ULL) >> 8); \ - (di).i[3] = ((from) & 0x000000ffULL); \ -} while (0) - -#define XFS_DI_HI(di) \ - (((__u32)(di).i[1] << 16) | ((di).i[2] << 8) | ((di).i[3])) -#define XFS_DI_LO(di) \ - (((__u32)(di).i[4] << 24) | ((di).i[5] << 16) | ((di).i[6] << 8) | ((di).i[7])) - -#define XFS_GET_DIR_INO8(di) \ - (((xfs_ino_t)XFS_DI_LO(di) & 0xffffffffULL) | \ - ((xfs_ino_t)XFS_DI_HI(di) << 32)) - -#define XFS_PUT_DIR_INO8(from, di) \ -do { \ - (di).i[0] = 0; \ - (di).i[1] = (((from) & 0x00ff000000000000ULL) >> 48); \ - (di).i[2] = (((from) & 0x0000ff0000000000ULL) >> 40); \ - (di).i[3] = (((from) & 0x000000ff00000000ULL) >> 32); \ - (di).i[4] = (((from) & 0x00000000ff000000ULL) >> 24); \ - (di).i[5] = (((from) & 0x0000000000ff0000ULL) >> 16); \ - (di).i[6] = (((from) & 0x000000000000ff00ULL) >> 8); \ - (di).i[7] = ((from) & 0x00000000000000ffULL); \ -} while (0) - -#endif /* __XFS_ARCH_H__ */ diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index c863753..cbae424 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -490,6 +490,13 @@ xfs_attr_remove_int(xfs_inode_t *dp, struct xfs_name *name, int flags) args.whichfork = XFS_ATTR_FORK; /* + * we have no control over the attribute names that userspace passes us + * to remove, so we have to allow the name lookup prior to attribute + * removal to fail. + */ + args.op_flags = XFS_DA_OP_OKNOENT; + + /* * Attach the dquots to the inode. */ error = xfs_qm_dqattach(dp, 0); @@ -815,17 +822,21 @@ xfs_attr_inactive(xfs_inode_t *dp) error = xfs_attr_root_inactive(&trans, dp); if (error) goto out; + /* - * signal synchronous inactive transactions unless this - * is a synchronous mount filesystem in which case we - * know that we're here because we've been called out of - * xfs_inactive which means that the last reference is gone - * and the unlink transaction has already hit the disk so - * async inactive transactions are safe. + * Signal synchronous inactive transactions unless this is a + * synchronous mount filesystem in which case we know that we're here + * because we've been called out of xfs_inactive which means that the + * last reference is gone and the unlink transaction has already hit + * the disk so async inactive transactions are safe. */ - if ((error = xfs_itruncate_finish(&trans, dp, 0LL, XFS_ATTR_FORK, - (!(mp->m_flags & XFS_MOUNT_WSYNC) - ? 1 : 0)))) + if (!(mp->m_flags & XFS_MOUNT_WSYNC)) { + if (dp->i_d.di_anextents > 0) + xfs_trans_set_sync(trans); + } + + error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); + if (error) goto out; /* @@ -1192,7 +1203,7 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context) return XFS_ERROR(error); ASSERT(bp != NULL); leaf = bp->data; - if (unlikely(be16_to_cpu(leaf->hdr.info.magic) != XFS_ATTR_LEAF_MAGIC)) { + if (unlikely(leaf->hdr.info.magic != cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) { XFS_CORRUPTION_ERROR("xfs_attr_leaf_list", XFS_ERRLEVEL_LOW, context->dp->i_mount, leaf); xfs_da_brelse(NULL, bp); @@ -1599,9 +1610,8 @@ xfs_attr_node_removename(xfs_da_args_t *args) XFS_ATTR_FORK); if (error) goto out; - ASSERT(be16_to_cpu(((xfs_attr_leafblock_t *) - bp->data)->hdr.info.magic) - == XFS_ATTR_LEAF_MAGIC); + ASSERT((((xfs_attr_leafblock_t *)bp->data)->hdr.info.magic) == + cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) { xfs_bmap_init(args->flist, args->firstblock); @@ -1866,11 +1876,11 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) return(XFS_ERROR(EFSCORRUPTED)); } node = bp->data; - if (be16_to_cpu(node->hdr.info.magic) - == XFS_ATTR_LEAF_MAGIC) + if (node->hdr.info.magic == + cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) break; - if (unlikely(be16_to_cpu(node->hdr.info.magic) - != XFS_DA_NODE_MAGIC)) { + if (unlikely(node->hdr.info.magic != + cpu_to_be16(XFS_DA_NODE_MAGIC))) { XFS_CORRUPTION_ERROR("xfs_attr_node_list(3)", XFS_ERRLEVEL_LOW, context->dp->i_mount, @@ -1905,8 +1915,8 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) */ for (;;) { leaf = bp->data; - if (unlikely(be16_to_cpu(leaf->hdr.info.magic) - != XFS_ATTR_LEAF_MAGIC)) { + if (unlikely(leaf->hdr.info.magic != + cpu_to_be16(XFS_ATTR_LEAF_MAGIC))) { XFS_CORRUPTION_ERROR("xfs_attr_node_list(4)", XFS_ERRLEVEL_LOW, context->dp->i_mount, leaf); diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 71e90dc2..8fad960 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -731,7 +731,7 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp) int bytes, i; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); entry = &leaf->entries[0]; bytes = sizeof(struct xfs_attr_sf_hdr); @@ -777,7 +777,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff) ASSERT(bp != NULL); memcpy(tmpbuffer, bp->data, XFS_LBSIZE(dp->i_mount)); leaf = (xfs_attr_leafblock_t *)tmpbuffer; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); memset(bp->data, 0, XFS_LBSIZE(dp->i_mount)); /* @@ -872,7 +872,7 @@ xfs_attr_leaf_to_node(xfs_da_args_t *args) goto out; node = bp1->data; leaf = bp2->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); /* both on-disk, don't endian-flip twice */ node->btree[0].hashval = leaf->entries[be16_to_cpu(leaf->hdr.count)-1 ].hashval; @@ -997,7 +997,7 @@ xfs_attr_leaf_add(xfs_dabuf_t *bp, xfs_da_args_t *args) int tablesize, entsize, sum, tmp, i; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT((args->index >= 0) && (args->index <= be16_to_cpu(leaf->hdr.count))); hdr = &leaf->hdr; @@ -1070,7 +1070,7 @@ xfs_attr_leaf_add_work(xfs_dabuf_t *bp, xfs_da_args_t *args, int mapindex) int tmp, i; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); hdr = &leaf->hdr; ASSERT((mapindex >= 0) && (mapindex < XFS_ATTR_LEAF_MAPSIZE)); ASSERT((args->index >= 0) && (args->index <= be16_to_cpu(hdr->count))); @@ -1256,8 +1256,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, ASSERT(blk2->magic == XFS_ATTR_LEAF_MAGIC); leaf1 = blk1->bp->data; leaf2 = blk2->bp->data; - ASSERT(be16_to_cpu(leaf1->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); - ASSERT(be16_to_cpu(leaf2->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); args = state->args; /* @@ -1533,7 +1533,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action) */ blk = &state->path.blk[ state->path.active-1 ]; info = blk->bp->data; - ASSERT(be16_to_cpu(info->magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); leaf = (xfs_attr_leafblock_t *)info; count = be16_to_cpu(leaf->hdr.count); bytes = sizeof(xfs_attr_leaf_hdr_t) + @@ -1596,7 +1596,7 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action) bytes = state->blocksize - (state->blocksize>>2); bytes -= be16_to_cpu(leaf->hdr.usedbytes); leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); count += be16_to_cpu(leaf->hdr.count); bytes -= be16_to_cpu(leaf->hdr.usedbytes); bytes -= count * sizeof(xfs_attr_leaf_entry_t); @@ -1650,7 +1650,7 @@ xfs_attr_leaf_remove(xfs_dabuf_t *bp, xfs_da_args_t *args) xfs_mount_t *mp; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); hdr = &leaf->hdr; mp = args->trans->t_mountp; ASSERT((be16_to_cpu(hdr->count) > 0) @@ -1813,8 +1813,8 @@ xfs_attr_leaf_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk, ASSERT(save_blk->magic == XFS_ATTR_LEAF_MAGIC); drop_leaf = drop_blk->bp->data; save_leaf = save_blk->bp->data; - ASSERT(be16_to_cpu(drop_leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); - ASSERT(be16_to_cpu(save_leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); drop_hdr = &drop_leaf->hdr; save_hdr = &save_leaf->hdr; @@ -1915,7 +1915,7 @@ xfs_attr_leaf_lookup_int(xfs_dabuf_t *bp, xfs_da_args_t *args) xfs_dahash_t hashval; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(be16_to_cpu(leaf->hdr.count) < (XFS_LBSIZE(args->dp->i_mount)/8)); @@ -2019,7 +2019,7 @@ xfs_attr_leaf_getvalue(xfs_dabuf_t *bp, xfs_da_args_t *args) xfs_attr_leaf_name_remote_t *name_rmt; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(be16_to_cpu(leaf->hdr.count) < (XFS_LBSIZE(args->dp->i_mount)/8)); ASSERT(args->index < be16_to_cpu(leaf->hdr.count)); @@ -2087,8 +2087,8 @@ xfs_attr_leaf_moveents(xfs_attr_leafblock_t *leaf_s, int start_s, /* * Set up environment. */ - ASSERT(be16_to_cpu(leaf_s->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); - ASSERT(be16_to_cpu(leaf_d->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf_s->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + ASSERT(leaf_d->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); hdr_s = &leaf_s->hdr; hdr_d = &leaf_d->hdr; ASSERT((be16_to_cpu(hdr_s->count) > 0) && @@ -2222,8 +2222,8 @@ xfs_attr_leaf_order(xfs_dabuf_t *leaf1_bp, xfs_dabuf_t *leaf2_bp) leaf1 = leaf1_bp->data; leaf2 = leaf2_bp->data; - ASSERT((be16_to_cpu(leaf1->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC) && - (be16_to_cpu(leaf2->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC)); + ASSERT((leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) && + (leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC))); if ((be16_to_cpu(leaf1->hdr.count) > 0) && (be16_to_cpu(leaf2->hdr.count) > 0) && ((be32_to_cpu(leaf2->entries[0].hashval) < @@ -2246,7 +2246,7 @@ xfs_attr_leaf_lasthash(xfs_dabuf_t *bp, int *count) xfs_attr_leafblock_t *leaf; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); if (count) *count = be16_to_cpu(leaf->hdr.count); if (!leaf->hdr.count) @@ -2265,7 +2265,7 @@ xfs_attr_leaf_entsize(xfs_attr_leafblock_t *leaf, int index) xfs_attr_leaf_name_remote_t *name_rmt; int size; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); if (leaf->entries[index].flags & XFS_ATTR_LOCAL) { name_loc = xfs_attr_leaf_name_local(leaf, index); size = xfs_attr_leaf_entsize_local(name_loc->namelen, @@ -2451,7 +2451,7 @@ xfs_attr_leaf_clearflag(xfs_da_args_t *args) ASSERT(bp != NULL); leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(args->index < be16_to_cpu(leaf->hdr.count)); ASSERT(args->index >= 0); entry = &leaf->entries[ args->index ]; @@ -2515,7 +2515,7 @@ xfs_attr_leaf_setflag(xfs_da_args_t *args) ASSERT(bp != NULL); leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(args->index < be16_to_cpu(leaf->hdr.count)); ASSERT(args->index >= 0); entry = &leaf->entries[ args->index ]; @@ -2585,13 +2585,13 @@ xfs_attr_leaf_flipflags(xfs_da_args_t *args) } leaf1 = bp1->data; - ASSERT(be16_to_cpu(leaf1->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(args->index < be16_to_cpu(leaf1->hdr.count)); ASSERT(args->index >= 0); entry1 = &leaf1->entries[ args->index ]; leaf2 = bp2->data; - ASSERT(be16_to_cpu(leaf2->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(args->index2 < be16_to_cpu(leaf2->hdr.count)); ASSERT(args->index2 >= 0); entry2 = &leaf2->entries[ args->index2 ]; @@ -2689,9 +2689,9 @@ xfs_attr_root_inactive(xfs_trans_t **trans, xfs_inode_t *dp) * This is a depth-first traversal! */ info = bp->data; - if (be16_to_cpu(info->magic) == XFS_DA_NODE_MAGIC) { + if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) { error = xfs_attr_node_inactive(trans, dp, bp, 1); - } else if (be16_to_cpu(info->magic) == XFS_ATTR_LEAF_MAGIC) { + } else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) { error = xfs_attr_leaf_inactive(trans, dp, bp); } else { error = XFS_ERROR(EIO); @@ -2739,7 +2739,7 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp, } node = bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); parent_blkno = xfs_da_blkno(bp); /* save for re-read later */ count = be16_to_cpu(node->hdr.count); if (!count) { @@ -2773,10 +2773,10 @@ xfs_attr_node_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp, * Invalidate the subtree, however we have to. */ info = child_bp->data; - if (be16_to_cpu(info->magic) == XFS_DA_NODE_MAGIC) { + if (info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) { error = xfs_attr_node_inactive(trans, dp, child_bp, level+1); - } else if (be16_to_cpu(info->magic) == XFS_ATTR_LEAF_MAGIC) { + } else if (info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)) { error = xfs_attr_leaf_inactive(trans, dp, child_bp); } else { @@ -2836,7 +2836,7 @@ xfs_attr_leaf_inactive(xfs_trans_t **trans, xfs_inode_t *dp, xfs_dabuf_t *bp) int error, count, size, tmp, i; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); /* * Count the number of "remote" value extents. diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index e546a33..c51a3f9 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -29,15 +29,11 @@ #include "xfs_bmap_btree.h" #include "xfs_alloc_btree.h" #include "xfs_ialloc_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_mount.h" #include "xfs_itable.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" #include "xfs_inode_item.h" #include "xfs_extfree_item.h" #include "xfs_alloc.h" @@ -94,6 +90,7 @@ xfs_bmap_add_attrfork_local( */ STATIC int /* error */ xfs_bmap_add_extent_delay_real( + struct xfs_trans *tp, /* transaction pointer */ xfs_inode_t *ip, /* incore inode pointer */ xfs_extnum_t *idx, /* extent number to update/insert */ xfs_btree_cur_t **curp, /* if *curp is null, not a btree */ @@ -439,6 +436,7 @@ xfs_bmap_add_attrfork_local( */ STATIC int /* error */ xfs_bmap_add_extent( + struct xfs_trans *tp, /* transaction pointer */ xfs_inode_t *ip, /* incore inode pointer */ xfs_extnum_t *idx, /* extent number to update/insert */ xfs_btree_cur_t **curp, /* if *curp is null, not a btree */ @@ -524,7 +522,7 @@ xfs_bmap_add_extent( if (cur) ASSERT(cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL); - error = xfs_bmap_add_extent_delay_real(ip, + error = xfs_bmap_add_extent_delay_real(tp, ip, idx, &cur, new, &da_new, first, flist, &logflags); } else { @@ -561,7 +559,7 @@ xfs_bmap_add_extent( int tmp_logflags; /* partial log flag return val */ ASSERT(cur == NULL); - error = xfs_bmap_extents_to_btree(ip->i_transp, ip, first, + error = xfs_bmap_extents_to_btree(tp, ip, first, flist, &cur, da_old > 0, &tmp_logflags, whichfork); logflags |= tmp_logflags; if (error) @@ -604,6 +602,7 @@ done: */ STATIC int /* error */ xfs_bmap_add_extent_delay_real( + struct xfs_trans *tp, /* transaction pointer */ xfs_inode_t *ip, /* incore inode pointer */ xfs_extnum_t *idx, /* extent number to update/insert */ xfs_btree_cur_t **curp, /* if *curp is null, not a btree */ @@ -901,7 +900,7 @@ xfs_bmap_add_extent_delay_real( } if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && ip->i_d.di_nextents > ip->i_df.if_ext_max) { - error = xfs_bmap_extents_to_btree(ip->i_transp, ip, + error = xfs_bmap_extents_to_btree(tp, ip, first, flist, &cur, 1, &tmp_rval, XFS_DATA_FORK); rval |= tmp_rval; @@ -984,7 +983,7 @@ xfs_bmap_add_extent_delay_real( } if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && ip->i_d.di_nextents > ip->i_df.if_ext_max) { - error = xfs_bmap_extents_to_btree(ip->i_transp, ip, + error = xfs_bmap_extents_to_btree(tp, ip, first, flist, &cur, 1, &tmp_rval, XFS_DATA_FORK); rval |= tmp_rval; @@ -1052,7 +1051,7 @@ xfs_bmap_add_extent_delay_real( } if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS && ip->i_d.di_nextents > ip->i_df.if_ext_max) { - error = xfs_bmap_extents_to_btree(ip->i_transp, ip, + error = xfs_bmap_extents_to_btree(tp, ip, first, flist, &cur, 1, &tmp_rval, XFS_DATA_FORK); rval |= tmp_rval; @@ -2871,8 +2870,8 @@ xfs_bmap_del_extent( len = del->br_blockcount; do_div(bno, mp->m_sb.sb_rextsize); do_div(len, mp->m_sb.sb_rextsize); - if ((error = xfs_rtfree_extent(ip->i_transp, bno, - (xfs_extlen_t)len))) + error = xfs_rtfree_extent(tp, bno, (xfs_extlen_t)len); + if (error) goto done; do_fx = 0; nblks = len * mp->m_sb.sb_rextsize; @@ -4080,7 +4079,7 @@ xfs_bmap_sanity_check( { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - if (be32_to_cpu(block->bb_magic) != XFS_BMAP_MAGIC || + if (block->bb_magic != cpu_to_be32(XFS_BMAP_MAGIC) || be16_to_cpu(block->bb_level) != level || be16_to_cpu(block->bb_numrecs) == 0 || be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0]) @@ -4662,7 +4661,7 @@ xfs_bmapi( if (!wasdelay && (flags & XFS_BMAPI_PREALLOC)) got.br_state = XFS_EXT_UNWRITTEN; } - error = xfs_bmap_add_extent(ip, &lastx, &cur, &got, + error = xfs_bmap_add_extent(tp, ip, &lastx, &cur, &got, firstblock, flist, &tmp_logflags, whichfork); logflags |= tmp_logflags; @@ -4763,7 +4762,7 @@ xfs_bmapi( mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN) ? XFS_EXT_NORM : XFS_EXT_UNWRITTEN; - error = xfs_bmap_add_extent(ip, &lastx, &cur, mval, + error = xfs_bmap_add_extent(tp, ip, &lastx, &cur, mval, firstblock, flist, &tmp_logflags, whichfork); logflags |= tmp_logflags; @@ -5117,7 +5116,7 @@ xfs_bunmapi( del.br_blockcount = mod; } del.br_state = XFS_EXT_UNWRITTEN; - error = xfs_bmap_add_extent(ip, &lastx, &cur, &del, + error = xfs_bmap_add_extent(tp, ip, &lastx, &cur, &del, firstblock, flist, &logflags, XFS_DATA_FORK); if (error) @@ -5175,18 +5174,18 @@ xfs_bunmapi( } prev.br_state = XFS_EXT_UNWRITTEN; lastx--; - error = xfs_bmap_add_extent(ip, &lastx, &cur, - &prev, firstblock, flist, &logflags, - XFS_DATA_FORK); + error = xfs_bmap_add_extent(tp, ip, &lastx, + &cur, &prev, firstblock, flist, + &logflags, XFS_DATA_FORK); if (error) goto error0; goto nodelete; } else { ASSERT(del.br_state == XFS_EXT_NORM); del.br_state = XFS_EXT_UNWRITTEN; - error = xfs_bmap_add_extent(ip, &lastx, &cur, - &del, firstblock, flist, &logflags, - XFS_DATA_FORK); + error = xfs_bmap_add_extent(tp, ip, &lastx, + &cur, &del, firstblock, flist, + &logflags, XFS_DATA_FORK); if (error) goto error0; goto nodelete; diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c index 87d3c10..e2f5d59 100644 --- a/fs/xfs/xfs_bmap_btree.c +++ b/fs/xfs/xfs_bmap_btree.c @@ -33,7 +33,6 @@ #include "xfs_inode_item.h" #include "xfs_alloc.h" #include "xfs_btree.h" -#include "xfs_btree_trace.h" #include "xfs_itable.h" #include "xfs_bmap.h" #include "xfs_error.h" @@ -425,10 +424,10 @@ xfs_bmbt_to_bmdr( xfs_bmbt_key_t *tkp; __be64 *tpp; - ASSERT(be32_to_cpu(rblock->bb_magic) == XFS_BMAP_MAGIC); - ASSERT(be64_to_cpu(rblock->bb_u.l.bb_leftsib) == NULLDFSBNO); - ASSERT(be64_to_cpu(rblock->bb_u.l.bb_rightsib) == NULLDFSBNO); - ASSERT(be16_to_cpu(rblock->bb_level) > 0); + ASSERT(rblock->bb_magic == cpu_to_be32(XFS_BMAP_MAGIC)); + ASSERT(rblock->bb_u.l.bb_leftsib == cpu_to_be64(NULLDFSBNO)); + ASSERT(rblock->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO)); + ASSERT(rblock->bb_level != 0); dblock->bb_level = rblock->bb_level; dblock->bb_numrecs = rblock->bb_numrecs; dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0); @@ -732,95 +731,6 @@ xfs_bmbt_recs_inorder( } #endif /* DEBUG */ -#ifdef XFS_BTREE_TRACE -ktrace_t *xfs_bmbt_trace_buf; - -STATIC void -xfs_bmbt_trace_enter( - struct xfs_btree_cur *cur, - const char *func, - char *s, - int type, - int line, - __psunsigned_t a0, - __psunsigned_t a1, - __psunsigned_t a2, - __psunsigned_t a3, - __psunsigned_t a4, - __psunsigned_t a5, - __psunsigned_t a6, - __psunsigned_t a7, - __psunsigned_t a8, - __psunsigned_t a9, - __psunsigned_t a10) -{ - struct xfs_inode *ip = cur->bc_private.b.ip; - int whichfork = cur->bc_private.b.whichfork; - - ktrace_enter(xfs_bmbt_trace_buf, - (void *)((__psint_t)type | (whichfork << 8) | (line << 16)), - (void *)func, (void *)s, (void *)ip, (void *)cur, - (void *)a0, (void *)a1, (void *)a2, (void *)a3, - (void *)a4, (void *)a5, (void *)a6, (void *)a7, - (void *)a8, (void *)a9, (void *)a10); -} - -STATIC void -xfs_bmbt_trace_cursor( - struct xfs_btree_cur *cur, - __uint32_t *s0, - __uint64_t *l0, - __uint64_t *l1) -{ - struct xfs_bmbt_rec_host r; - - xfs_bmbt_set_all(&r, &cur->bc_rec.b); - - *s0 = (cur->bc_nlevels << 24) | - (cur->bc_private.b.flags << 16) | - cur->bc_private.b.allocated; - *l0 = r.l0; - *l1 = r.l1; -} - -STATIC void -xfs_bmbt_trace_key( - struct xfs_btree_cur *cur, - union xfs_btree_key *key, - __uint64_t *l0, - __uint64_t *l1) -{ - *l0 = be64_to_cpu(key->bmbt.br_startoff); - *l1 = 0; -} - -/* Endian flipping versions of the bmbt extraction functions */ -STATIC void -xfs_bmbt_disk_get_all( - xfs_bmbt_rec_t *r, - xfs_bmbt_irec_t *s) -{ - __xfs_bmbt_get_all(get_unaligned_be64(&r->l0), - get_unaligned_be64(&r->l1), s); -} - -STATIC void -xfs_bmbt_trace_record( - struct xfs_btree_cur *cur, - union xfs_btree_rec *rec, - __uint64_t *l0, - __uint64_t *l1, - __uint64_t *l2) -{ - struct xfs_bmbt_irec irec; - - xfs_bmbt_disk_get_all(&rec->bmbt, &irec); - *l0 = irec.br_startoff; - *l1 = irec.br_startblock; - *l2 = irec.br_blockcount; -} -#endif /* XFS_BTREE_TRACE */ - static const struct xfs_btree_ops xfs_bmbt_ops = { .rec_len = sizeof(xfs_bmbt_rec_t), .key_len = sizeof(xfs_bmbt_key_t), @@ -837,18 +747,10 @@ static const struct xfs_btree_ops xfs_bmbt_ops = { .init_rec_from_cur = xfs_bmbt_init_rec_from_cur, .init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur, .key_diff = xfs_bmbt_key_diff, - #ifdef DEBUG .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, #endif - -#ifdef XFS_BTREE_TRACE - .trace_enter = xfs_bmbt_trace_enter, - .trace_cursor = xfs_bmbt_trace_cursor, - .trace_key = xfs_bmbt_trace_key, - .trace_record = xfs_bmbt_trace_record, -#endif }; /* diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index 2f9e97c..cabf4b5 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -32,7 +32,6 @@ #include "xfs_inode.h" #include "xfs_inode_item.h" #include "xfs_btree.h" -#include "xfs_btree_trace.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -66,11 +65,11 @@ xfs_btree_check_lblock( be16_to_cpu(block->bb_numrecs) <= cur->bc_ops->get_maxrecs(cur, level) && block->bb_u.l.bb_leftsib && - (be64_to_cpu(block->bb_u.l.bb_leftsib) == NULLDFSBNO || + (block->bb_u.l.bb_leftsib == cpu_to_be64(NULLDFSBNO) || XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_u.l.bb_leftsib))) && block->bb_u.l.bb_rightsib && - (be64_to_cpu(block->bb_u.l.bb_rightsib) == NULLDFSBNO || + (block->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO) || XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_u.l.bb_rightsib))); if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp, @@ -105,10 +104,10 @@ xfs_btree_check_sblock( be16_to_cpu(block->bb_level) == level && be16_to_cpu(block->bb_numrecs) <= cur->bc_ops->get_maxrecs(cur, level) && - (be32_to_cpu(block->bb_u.s.bb_leftsib) == NULLAGBLOCK || + (block->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) || be32_to_cpu(block->bb_u.s.bb_leftsib) < agflen) && block->bb_u.s.bb_leftsib && - (be32_to_cpu(block->bb_u.s.bb_rightsib) == NULLAGBLOCK || + (block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK) || be32_to_cpu(block->bb_u.s.bb_rightsib) < agflen) && block->bb_u.s.bb_rightsib; if (unlikely(XFS_TEST_ERROR(!sblock_ok, cur->bc_mp, @@ -511,9 +510,9 @@ xfs_btree_islastblock( block = xfs_btree_get_block(cur, level, &bp); xfs_btree_check_block(cur, block, level, bp); if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - return be64_to_cpu(block->bb_u.l.bb_rightsib) == NULLDFSBNO; + return block->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO); else - return be32_to_cpu(block->bb_u.s.bb_rightsib) == NULLAGBLOCK; + return block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK); } /* @@ -777,14 +776,14 @@ xfs_btree_setbuf( b = XFS_BUF_TO_BLOCK(bp); if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - if (be64_to_cpu(b->bb_u.l.bb_leftsib) == NULLDFSBNO) + if (b->bb_u.l.bb_leftsib == cpu_to_be64(NULLDFSBNO)) cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA; - if (be64_to_cpu(b->bb_u.l.bb_rightsib) == NULLDFSBNO) + if (b->bb_u.l.bb_rightsib == cpu_to_be64(NULLDFSBNO)) cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA; } else { - if (be32_to_cpu(b->bb_u.s.bb_leftsib) == NULLAGBLOCK) + if (b->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK)) cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA; - if (be32_to_cpu(b->bb_u.s.bb_rightsib) == NULLAGBLOCK) + if (b->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK)) cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA; } } @@ -795,9 +794,9 @@ xfs_btree_ptr_is_null( union xfs_btree_ptr *ptr) { if (cur->bc_flags & XFS_BTREE_LONG_PTRS) - return be64_to_cpu(ptr->l) == NULLDFSBNO; + return ptr->l == cpu_to_be64(NULLDFSBNO); else - return be32_to_cpu(ptr->s) == NULLAGBLOCK; + return ptr->s == cpu_to_be32(NULLAGBLOCK); } STATIC void @@ -923,12 +922,12 @@ xfs_btree_ptr_to_daddr( union xfs_btree_ptr *ptr) { if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - ASSERT(be64_to_cpu(ptr->l) != NULLDFSBNO); + ASSERT(ptr->l != cpu_to_be64(NULLDFSBNO)); return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l)); } else { ASSERT(cur->bc_private.a.agno != NULLAGNUMBER); - ASSERT(be32_to_cpu(ptr->s) != NULLAGBLOCK); + ASSERT(ptr->s != cpu_to_be32(NULLAGBLOCK)); return XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_private.a.agno, be32_to_cpu(ptr->s)); diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h index 82fafc6..8d05a6a 100644 --- a/fs/xfs/xfs_btree.h +++ b/fs/xfs/xfs_btree.h @@ -199,25 +199,6 @@ struct xfs_btree_ops { union xfs_btree_rec *r1, union xfs_btree_rec *r2); #endif - - /* btree tracing */ -#ifdef XFS_BTREE_TRACE - void (*trace_enter)(struct xfs_btree_cur *, const char *, - char *, int, int, __psunsigned_t, - __psunsigned_t, __psunsigned_t, - __psunsigned_t, __psunsigned_t, - __psunsigned_t, __psunsigned_t, - __psunsigned_t, __psunsigned_t, - __psunsigned_t, __psunsigned_t); - void (*trace_cursor)(struct xfs_btree_cur *, __uint32_t *, - __uint64_t *, __uint64_t *); - void (*trace_key)(struct xfs_btree_cur *, - union xfs_btree_key *, __uint64_t *, - __uint64_t *); - void (*trace_record)(struct xfs_btree_cur *, - union xfs_btree_rec *, __uint64_t *, - __uint64_t *, __uint64_t *); -#endif }; /* @@ -452,4 +433,23 @@ static inline int xfs_btree_get_level(struct xfs_btree_block *block) (XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \ XFS_FSB_TO_AGBNO(mp, fsb) < mp->m_sb.sb_agblocks) +/* + * Trace hooks. Currently not implemented as they need to be ported + * over to the generic tracing functionality, which is some effort. + * + * i,j = integer (32 bit) + * b = btree block buffer (xfs_buf_t) + * p = btree ptr + * r = btree record + * k = btree key + */ +#define XFS_BTREE_TRACE_ARGBI(c, b, i) +#define XFS_BTREE_TRACE_ARGBII(c, b, i, j) +#define XFS_BTREE_TRACE_ARGI(c, i) +#define XFS_BTREE_TRACE_ARGIPK(c, i, p, s) +#define XFS_BTREE_TRACE_ARGIPR(c, i, p, r) +#define XFS_BTREE_TRACE_ARGIK(c, i, k) +#define XFS_BTREE_TRACE_ARGR(c, r) +#define XFS_BTREE_TRACE_CURSOR(c, t) + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/xfs_btree_trace.c b/fs/xfs/xfs_btree_trace.c deleted file mode 100644 index 44ff942..0000000 --- a/fs/xfs/xfs_btree_trace.c +++ /dev/null @@ -1,249 +0,0 @@ -/* - * Copyright (c) 2008 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#include "xfs.h" -#include "xfs_types.h" -#include "xfs_inum.h" -#include "xfs_bmap_btree.h" -#include "xfs_alloc_btree.h" -#include "xfs_ialloc_btree.h" -#include "xfs_inode.h" -#include "xfs_btree.h" -#include "xfs_btree_trace.h" - -STATIC void -xfs_btree_trace_ptr( - struct xfs_btree_cur *cur, - union xfs_btree_ptr ptr, - __psunsigned_t *high, - __psunsigned_t *low) -{ - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { - __u64 val = be64_to_cpu(ptr.l); - *high = val >> 32; - *low = (int)val; - } else { - *high = 0; - *low = be32_to_cpu(ptr.s); - } -} - -/* - * Add a trace buffer entry for arguments, for a buffer & 1 integer arg. - */ -void -xfs_btree_trace_argbi( - const char *func, - struct xfs_btree_cur *cur, - struct xfs_buf *b, - int i, - int line) -{ - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGBI, - line, (__psunsigned_t)b, i, 0, 0, 0, 0, 0, - 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for a buffer & 2 integer args. - */ -void -xfs_btree_trace_argbii( - const char *func, - struct xfs_btree_cur *cur, - struct xfs_buf *b, - int i0, - int i1, - int line) -{ - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGBII, - line, (__psunsigned_t)b, i0, i1, 0, 0, 0, 0, - 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for 3 block-length args - * and an integer arg. - */ -void -xfs_btree_trace_argfffi( - const char *func, - struct xfs_btree_cur *cur, - xfs_dfiloff_t o, - xfs_dfsbno_t b, - xfs_dfilblks_t i, - int j, - int line) -{ - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGFFFI, - line, - o >> 32, (int)o, - b >> 32, (int)b, - i >> 32, (int)i, - (int)j, 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for one integer arg. - */ -void -xfs_btree_trace_argi( - const char *func, - struct xfs_btree_cur *cur, - int i, - int line) -{ - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGI, - line, i, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for int, fsblock, key. - */ -void -xfs_btree_trace_argipk( - const char *func, - struct xfs_btree_cur *cur, - int i, - union xfs_btree_ptr ptr, - union xfs_btree_key *key, - int line) -{ - __psunsigned_t high, low; - __uint64_t l0, l1; - - xfs_btree_trace_ptr(cur, ptr, &high, &low); - cur->bc_ops->trace_key(cur, key, &l0, &l1); - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGIPK, - line, i, high, low, - l0 >> 32, (int)l0, - l1 >> 32, (int)l1, - 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for int, fsblock, rec. - */ -void -xfs_btree_trace_argipr( - const char *func, - struct xfs_btree_cur *cur, - int i, - union xfs_btree_ptr ptr, - union xfs_btree_rec *rec, - int line) -{ - __psunsigned_t high, low; - __uint64_t l0, l1, l2; - - xfs_btree_trace_ptr(cur, ptr, &high, &low); - cur->bc_ops->trace_record(cur, rec, &l0, &l1, &l2); - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGIPR, - line, i, - high, low, - l0 >> 32, (int)l0, - l1 >> 32, (int)l1, - l2 >> 32, (int)l2, - 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for int, key. - */ -void -xfs_btree_trace_argik( - const char *func, - struct xfs_btree_cur *cur, - int i, - union xfs_btree_key *key, - int line) -{ - __uint64_t l0, l1; - - cur->bc_ops->trace_key(cur, key, &l0, &l1); - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGIK, - line, i, - l0 >> 32, (int)l0, - l1 >> 32, (int)l1, - 0, 0, 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for arguments, for record. - */ -void -xfs_btree_trace_argr( - const char *func, - struct xfs_btree_cur *cur, - union xfs_btree_rec *rec, - int line) -{ - __uint64_t l0, l1, l2; - - cur->bc_ops->trace_record(cur, rec, &l0, &l1, &l2); - cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGR, - line, - l0 >> 32, (int)l0, - l1 >> 32, (int)l1, - l2 >> 32, (int)l2, - 0, 0, 0, 0, 0); -} - -/* - * Add a trace buffer entry for the cursor/operation. - */ -void -xfs_btree_trace_cursor( - const char *func, - struct xfs_btree_cur *cur, - int type, - int line) -{ - __uint32_t s0; - __uint64_t l0, l1; - char *s; - - switch (type) { - case XBT_ARGS: - s = "args"; - break; - case XBT_ENTRY: - s = "entry"; - break; - case XBT_ERROR: - s = "error"; - break; - case XBT_EXIT: - s = "exit"; - break; - default: - s = "unknown"; - break; - } - - cur->bc_ops->trace_cursor(cur, &s0, &l0, &l1); - cur->bc_ops->trace_enter(cur, func, s, XFS_BTREE_KTRACE_CUR, line, - s0, - l0 >> 32, (int)l0, - l1 >> 32, (int)l1, - (__psunsigned_t)cur->bc_bufs[0], - (__psunsigned_t)cur->bc_bufs[1], - (__psunsigned_t)cur->bc_bufs[2], - (__psunsigned_t)cur->bc_bufs[3], - (cur->bc_ptrs[0] << 16) | cur->bc_ptrs[1], - (cur->bc_ptrs[2] << 16) | cur->bc_ptrs[3]); -} diff --git a/fs/xfs/xfs_btree_trace.h b/fs/xfs/xfs_btree_trace.h deleted file mode 100644 index 2d8a309..0000000 --- a/fs/xfs/xfs_btree_trace.h +++ /dev/null @@ -1,99 +0,0 @@ -/* - * Copyright (c) 2008 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_BTREE_TRACE_H__ -#define __XFS_BTREE_TRACE_H__ - -struct xfs_btree_cur; -struct xfs_buf; - - -/* - * Trace hooks. - * i,j = integer (32 bit) - * b = btree block buffer (xfs_buf_t) - * p = btree ptr - * r = btree record - * k = btree key - */ - -#ifdef XFS_BTREE_TRACE - -/* - * Trace buffer entry types. - */ -#define XFS_BTREE_KTRACE_ARGBI 1 -#define XFS_BTREE_KTRACE_ARGBII 2 -#define XFS_BTREE_KTRACE_ARGFFFI 3 -#define XFS_BTREE_KTRACE_ARGI 4 -#define XFS_BTREE_KTRACE_ARGIPK 5 -#define XFS_BTREE_KTRACE_ARGIPR 6 -#define XFS_BTREE_KTRACE_ARGIK 7 -#define XFS_BTREE_KTRACE_ARGR 8 -#define XFS_BTREE_KTRACE_CUR 9 - -/* - * Sub-types for cursor traces. - */ -#define XBT_ARGS 0 -#define XBT_ENTRY 1 -#define XBT_ERROR 2 -#define XBT_EXIT 3 - -void xfs_btree_trace_argbi(const char *, struct xfs_btree_cur *, - struct xfs_buf *, int, int); -void xfs_btree_trace_argbii(const char *, struct xfs_btree_cur *, - struct xfs_buf *, int, int, int); -void xfs_btree_trace_argi(const char *, struct xfs_btree_cur *, int, int); -void xfs_btree_trace_argipk(const char *, struct xfs_btree_cur *, int, - union xfs_btree_ptr, union xfs_btree_key *, int); -void xfs_btree_trace_argipr(const char *, struct xfs_btree_cur *, int, - union xfs_btree_ptr, union xfs_btree_rec *, int); -void xfs_btree_trace_argik(const char *, struct xfs_btree_cur *, int, - union xfs_btree_key *, int); -void xfs_btree_trace_argr(const char *, struct xfs_btree_cur *, - union xfs_btree_rec *, int); -void xfs_btree_trace_cursor(const char *, struct xfs_btree_cur *, int, int); - -#define XFS_BTREE_TRACE_ARGBI(c, b, i) \ - xfs_btree_trace_argbi(__func__, c, b, i, __LINE__) -#define XFS_BTREE_TRACE_ARGBII(c, b, i, j) \ - xfs_btree_trace_argbii(__func__, c, b, i, j, __LINE__) -#define XFS_BTREE_TRACE_ARGI(c, i) \ - xfs_btree_trace_argi(__func__, c, i, __LINE__) -#define XFS_BTREE_TRACE_ARGIPK(c, i, p, k) \ - xfs_btree_trace_argipk(__func__, c, i, p, k, __LINE__) -#define XFS_BTREE_TRACE_ARGIPR(c, i, p, r) \ - xfs_btree_trace_argipr(__func__, c, i, p, r, __LINE__) -#define XFS_BTREE_TRACE_ARGIK(c, i, k) \ - xfs_btree_trace_argik(__func__, c, i, k, __LINE__) -#define XFS_BTREE_TRACE_ARGR(c, r) \ - xfs_btree_trace_argr(__func__, c, r, __LINE__) -#define XFS_BTREE_TRACE_CURSOR(c, t) \ - xfs_btree_trace_cursor(__func__, c, t, __LINE__) -#else -#define XFS_BTREE_TRACE_ARGBI(c, b, i) -#define XFS_BTREE_TRACE_ARGBII(c, b, i, j) -#define XFS_BTREE_TRACE_ARGI(c, i) -#define XFS_BTREE_TRACE_ARGIPK(c, i, p, s) -#define XFS_BTREE_TRACE_ARGIPR(c, i, p, r) -#define XFS_BTREE_TRACE_ARGIK(c, i, k) -#define XFS_BTREE_TRACE_ARGR(c, r) -#define XFS_BTREE_TRACE_CURSOR(c, t) -#endif /* XFS_BTREE_TRACE */ - -#endif /* __XFS_BTREE_TRACE_H__ */ diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 7b7e005..8849291 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -90,13 +90,11 @@ xfs_buf_item_flush_log_debug( uint first, uint last) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; uint nbytes; - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*); - if ((bip == NULL) || (bip->bli_item.li_type != XFS_LI_BUF)) { + if (bip == NULL || (bip->bli_item.li_type != XFS_LI_BUF)) return; - } ASSERT(bip->bli_logged != NULL); nbytes = last - first + 1; @@ -408,7 +406,7 @@ xfs_buf_item_unpin( int stale = bip->bli_flags & XFS_BLI_STALE; int freed; - ASSERT(XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *) == bip); + ASSERT(bp->b_fspriv == bip); ASSERT(atomic_read(&bip->bli_refcount) > 0); trace_xfs_buf_item_unpin(bip); @@ -420,7 +418,7 @@ xfs_buf_item_unpin( if (freed && stale) { ASSERT(bip->bli_flags & XFS_BLI_STALE); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); ASSERT(!(XFS_BUF_ISDELAYWRITE(bp))); ASSERT(XFS_BUF_ISSTALE(bp)); ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL); @@ -443,7 +441,7 @@ xfs_buf_item_unpin( * Since the transaction no longer refers to the buffer, * the buffer should no longer refer to the transaction. */ - XFS_BUF_SET_FSPRIVATE2(bp, NULL); + bp->b_transp = NULL; } /* @@ -454,13 +452,13 @@ xfs_buf_item_unpin( */ if (bip->bli_flags & XFS_BLI_STALE_INODE) { xfs_buf_do_callbacks(bp); - XFS_BUF_SET_FSPRIVATE(bp, NULL); - XFS_BUF_CLR_IODONE_FUNC(bp); + bp->b_fspriv = NULL; + bp->b_iodone = NULL; } else { spin_lock(&ailp->xa_lock); xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip); xfs_buf_item_relse(bp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) == NULL); + ASSERT(bp->b_fspriv == NULL); } xfs_buf_relse(bp); } @@ -483,7 +481,7 @@ xfs_buf_item_trylock( if (XFS_BUF_ISPINNED(bp)) return XFS_ITEM_PINNED; - if (!XFS_BUF_CPSEMA(bp)) + if (!xfs_buf_trylock(bp)) return XFS_ITEM_LOCKED; /* take a reference to the buffer. */ @@ -525,7 +523,7 @@ xfs_buf_item_unlock( uint hold; /* Clear the buffer's association with this transaction. */ - XFS_BUF_SET_FSPRIVATE2(bp, NULL); + bp->b_transp = NULL; /* * If this is a transaction abort, don't return early. Instead, allow @@ -684,7 +682,7 @@ xfs_buf_item_init( xfs_buf_t *bp, xfs_mount_t *mp) { - xfs_log_item_t *lip; + xfs_log_item_t *lip = bp->b_fspriv; xfs_buf_log_item_t *bip; int chunks; int map_size; @@ -696,12 +694,8 @@ xfs_buf_item_init( * nothing to do here so return. */ ASSERT(bp->b_target->bt_mount == mp); - if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) { - lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); - if (lip->li_type == XFS_LI_BUF) { - return; - } - } + if (lip != NULL && lip->li_type == XFS_LI_BUF) + return; /* * chunks is the number of XFS_BLF_CHUNK size pieces @@ -740,11 +734,9 @@ xfs_buf_item_init( * Put the buf item into the list of items attached to the * buffer at the front. */ - if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) { - bip->bli_item.li_bio_list = - XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); - } - XFS_BUF_SET_FSPRIVATE(bp, bip); + if (bp->b_fspriv) + bip->bli_item.li_bio_list = bp->b_fspriv; + bp->b_fspriv = bip; } @@ -876,12 +868,11 @@ xfs_buf_item_relse( trace_xfs_buf_item_relse(bp, _RET_IP_); - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*); - XFS_BUF_SET_FSPRIVATE(bp, bip->bli_item.li_bio_list); - if ((XFS_BUF_FSPRIVATE(bp, void *) == NULL) && - (XFS_BUF_IODONE_FUNC(bp) != NULL)) { - XFS_BUF_CLR_IODONE_FUNC(bp); - } + bip = bp->b_fspriv; + bp->b_fspriv = bip->bli_item.li_bio_list; + if (bp->b_fspriv == NULL) + bp->b_iodone = NULL; + xfs_buf_rele(bp); xfs_buf_item_free(bip); } @@ -905,20 +896,20 @@ xfs_buf_attach_iodone( xfs_log_item_t *head_lip; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); lip->li_cb = cb; - if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) { - head_lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); + head_lip = bp->b_fspriv; + if (head_lip) { lip->li_bio_list = head_lip->li_bio_list; head_lip->li_bio_list = lip; } else { - XFS_BUF_SET_FSPRIVATE(bp, lip); + bp->b_fspriv = lip; } - ASSERT((XFS_BUF_IODONE_FUNC(bp) == xfs_buf_iodone_callbacks) || - (XFS_BUF_IODONE_FUNC(bp) == NULL)); - XFS_BUF_SET_IODONE_FUNC(bp, xfs_buf_iodone_callbacks); + ASSERT(bp->b_iodone == NULL || + bp->b_iodone == xfs_buf_iodone_callbacks); + bp->b_iodone = xfs_buf_iodone_callbacks; } /* @@ -939,8 +930,8 @@ xfs_buf_do_callbacks( { struct xfs_log_item *lip; - while ((lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *)) != NULL) { - XFS_BUF_SET_FSPRIVATE(bp, lip->li_bio_list); + while ((lip = bp->b_fspriv) != NULL) { + bp->b_fspriv = lip->li_bio_list; ASSERT(lip->li_cb != NULL); /* * Clear the next pointer so we don't have any @@ -1007,7 +998,7 @@ xfs_buf_iodone_callbacks( XFS_BUF_DONE(bp); XFS_BUF_SET_START(bp); } - ASSERT(XFS_BUF_IODONE_FUNC(bp)); + ASSERT(bp->b_iodone != NULL); trace_xfs_buf_item_iodone_async(bp, _RET_IP_); xfs_buf_relse(bp); return; @@ -1026,8 +1017,8 @@ xfs_buf_iodone_callbacks( do_callbacks: xfs_buf_do_callbacks(bp); - XFS_BUF_SET_FSPRIVATE(bp, NULL); - XFS_BUF_CLR_IODONE_FUNC(bp); + bp->b_fspriv = NULL; + bp->b_iodone = NULL; xfs_buf_ioend(bp, 0); } diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 6102ac6..2925726 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -24,11 +24,12 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" -#include "xfs_dir2_sf.h" +#include "xfs_dir2.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_inode_item.h" @@ -36,10 +37,6 @@ #include "xfs_bmap.h" #include "xfs_attr.h" #include "xfs_attr_leaf.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" -#include "xfs_dir2_node.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -89,7 +86,7 @@ STATIC void xfs_da_node_unbalance(xfs_da_state_t *state, */ STATIC uint xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count); STATIC int xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp); -STATIC xfs_dabuf_t *xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra); +STATIC xfs_dabuf_t *xfs_da_buf_make(int nbuf, xfs_buf_t **bps); STATIC int xfs_da_blk_unlink(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk, xfs_da_state_blk_t *save_blk); @@ -321,11 +318,11 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, ASSERT(bp != NULL); node = bp->data; oldroot = blk1->bp->data; - if (be16_to_cpu(oldroot->hdr.info.magic) == XFS_DA_NODE_MAGIC) { + if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)) { size = (int)((char *)&oldroot->btree[be16_to_cpu(oldroot->hdr.count)] - (char *)oldroot); } else { - ASSERT(be16_to_cpu(oldroot->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); leaf = (xfs_dir2_leaf_t *)oldroot; size = (int)((char *)&leaf->ents[be16_to_cpu(leaf->hdr.count)] - (char *)leaf); @@ -352,7 +349,7 @@ xfs_da_root_split(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, node->hdr.count = cpu_to_be16(2); #ifdef DEBUG - if (be16_to_cpu(oldroot->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC) { + if (oldroot->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)) { ASSERT(blk1->blkno >= mp->m_dirleafblk && blk1->blkno < mp->m_dirfreeblk); ASSERT(blk2->blkno >= mp->m_dirleafblk && @@ -384,7 +381,7 @@ xfs_da_node_split(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk, int useextra; node = oldblk->bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); /* * With V2 dirs the extra block is data or freespace. @@ -483,8 +480,8 @@ xfs_da_node_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, node1 = node2; node2 = tmpnode; } - ASSERT(be16_to_cpu(node1->hdr.info.magic) == XFS_DA_NODE_MAGIC); - ASSERT(be16_to_cpu(node2->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node1->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); + ASSERT(node2->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); count = (be16_to_cpu(node1->hdr.count) - be16_to_cpu(node2->hdr.count)) / 2; if (count == 0) return; @@ -578,7 +575,7 @@ xfs_da_node_add(xfs_da_state_t *state, xfs_da_state_blk_t *oldblk, int tmp; node = oldblk->bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); ASSERT((oldblk->index >= 0) && (oldblk->index <= be16_to_cpu(node->hdr.count))); ASSERT(newblk->blkno != 0); if (state->args->whichfork == XFS_DATA_FORK) @@ -714,7 +711,7 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk) ASSERT(args != NULL); ASSERT(root_blk->magic == XFS_DA_NODE_MAGIC); oldroot = root_blk->bp->data; - ASSERT(be16_to_cpu(oldroot->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(oldroot->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); ASSERT(!oldroot->hdr.info.forw); ASSERT(!oldroot->hdr.info.back); @@ -737,10 +734,10 @@ xfs_da_root_join(xfs_da_state_t *state, xfs_da_state_blk_t *root_blk) ASSERT(bp != NULL); blkinfo = bp->data; if (be16_to_cpu(oldroot->hdr.level) == 1) { - ASSERT(be16_to_cpu(blkinfo->magic) == XFS_DIR2_LEAFN_MAGIC || - be16_to_cpu(blkinfo->magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(blkinfo->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) || + blkinfo->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); } else { - ASSERT(be16_to_cpu(blkinfo->magic) == XFS_DA_NODE_MAGIC); + ASSERT(blkinfo->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); } ASSERT(!blkinfo->forw); ASSERT(!blkinfo->back); @@ -776,7 +773,7 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action) */ blk = &state->path.blk[ state->path.active-1 ]; info = blk->bp->data; - ASSERT(be16_to_cpu(info->magic) == XFS_DA_NODE_MAGIC); + ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); node = (xfs_da_intnode_t *)info; count = be16_to_cpu(node->hdr.count); if (count > (state->node_ents >> 1)) { @@ -836,7 +833,7 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action) count -= state->node_ents >> 2; count -= be16_to_cpu(node->hdr.count); node = bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); count -= be16_to_cpu(node->hdr.count); xfs_da_brelse(state->args->trans, bp); if (count >= 0) @@ -911,7 +908,7 @@ xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path) } for (blk--, level--; level >= 0; blk--, level--) { node = blk->bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); btree = &node->btree[ blk->index ]; if (be32_to_cpu(btree->hashval) == lasthash) break; @@ -979,8 +976,8 @@ xfs_da_node_unbalance(xfs_da_state_t *state, xfs_da_state_blk_t *drop_blk, drop_node = drop_blk->bp->data; save_node = save_blk->bp->data; - ASSERT(be16_to_cpu(drop_node->hdr.info.magic) == XFS_DA_NODE_MAGIC); - ASSERT(be16_to_cpu(save_node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(drop_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); + ASSERT(save_node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); tp = state->args->trans; /* @@ -1278,8 +1275,8 @@ xfs_da_node_order(xfs_dabuf_t *node1_bp, xfs_dabuf_t *node2_bp) node1 = node1_bp->data; node2 = node2_bp->data; - ASSERT((be16_to_cpu(node1->hdr.info.magic) == XFS_DA_NODE_MAGIC) && - (be16_to_cpu(node2->hdr.info.magic) == XFS_DA_NODE_MAGIC)); + ASSERT(node1->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC) && + node2->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); if ((be16_to_cpu(node1->hdr.count) > 0) && (be16_to_cpu(node2->hdr.count) > 0) && ((be32_to_cpu(node2->btree[0].hashval) < be32_to_cpu(node1->btree[0].hashval)) || @@ -1299,7 +1296,7 @@ xfs_da_node_lasthash(xfs_dabuf_t *bp, int *count) xfs_da_intnode_t *node; node = bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); if (count) *count = be16_to_cpu(node->hdr.count); if (!node->hdr.count) @@ -1412,7 +1409,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path, for (blk = &path->blk[level]; level >= 0; blk--, level--) { ASSERT(blk->bp != NULL); node = blk->bp->data; - ASSERT(be16_to_cpu(node->hdr.info.magic) == XFS_DA_NODE_MAGIC); + ASSERT(node->hdr.info.magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); if (forward && (blk->index < be16_to_cpu(node->hdr.count)-1)) { blk->index++; blkno = be32_to_cpu(node->btree[blk->index].before); @@ -1451,9 +1448,9 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path, return(error); ASSERT(blk->bp != NULL); info = blk->bp->data; - ASSERT(be16_to_cpu(info->magic) == XFS_DA_NODE_MAGIC || - be16_to_cpu(info->magic) == XFS_DIR2_LEAFN_MAGIC || - be16_to_cpu(info->magic) == XFS_ATTR_LEAF_MAGIC); + ASSERT(info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC) || + info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC) || + info->magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); blk->magic = be16_to_cpu(info->magic); if (blk->magic == XFS_DA_NODE_MAGIC) { node = (xfs_da_intnode_t *)info; @@ -1546,79 +1543,62 @@ const struct xfs_nameops xfs_default_nameops = { .compname = xfs_da_compname }; -/* - * Add a block to the btree ahead of the file. - * Return the new block number to the caller. - */ int -xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno) +xfs_da_grow_inode_int( + struct xfs_da_args *args, + xfs_fileoff_t *bno, + int count) { - xfs_fileoff_t bno, b; - xfs_bmbt_irec_t map; - xfs_bmbt_irec_t *mapp; - xfs_inode_t *dp; - int nmap, error, w, count, c, got, i, mapi; - xfs_trans_t *tp; - xfs_mount_t *mp; - xfs_drfsbno_t nblks; + struct xfs_trans *tp = args->trans; + struct xfs_inode *dp = args->dp; + int w = args->whichfork; + xfs_drfsbno_t nblks = dp->i_d.di_nblocks; + struct xfs_bmbt_irec map, *mapp; + int nmap, error, got, i, mapi; - dp = args->dp; - mp = dp->i_mount; - w = args->whichfork; - tp = args->trans; - nblks = dp->i_d.di_nblocks; - - /* - * For new directories adjust the file offset and block count. - */ - if (w == XFS_DATA_FORK) { - bno = mp->m_dirleafblk; - count = mp->m_dirblkfsbs; - } else { - bno = 0; - count = 1; - } /* * Find a spot in the file space to put the new block. */ - if ((error = xfs_bmap_first_unused(tp, dp, count, &bno, w))) + error = xfs_bmap_first_unused(tp, dp, count, bno, w); + if (error) return error; - if (w == XFS_DATA_FORK) - ASSERT(bno >= mp->m_dirleafblk && bno < mp->m_dirfreeblk); + /* * Try mapping it in one filesystem block. */ nmap = 1; ASSERT(args->firstblock != NULL); - if ((error = xfs_bmapi(tp, dp, bno, count, + error = xfs_bmapi(tp, dp, *bno, count, xfs_bmapi_aflag(w)|XFS_BMAPI_WRITE|XFS_BMAPI_METADATA| XFS_BMAPI_CONTIG, args->firstblock, args->total, &map, &nmap, - args->flist))) { + args->flist); + if (error) return error; - } + ASSERT(nmap <= 1); if (nmap == 1) { mapp = ↦ mapi = 1; - } - /* - * If we didn't get it and the block might work if fragmented, - * try without the CONTIG flag. Loop until we get it all. - */ - else if (nmap == 0 && count > 1) { + } else if (nmap == 0 && count > 1) { + xfs_fileoff_t b; + int c; + + /* + * If we didn't get it and the block might work if fragmented, + * try without the CONTIG flag. Loop until we get it all. + */ mapp = kmem_alloc(sizeof(*mapp) * count, KM_SLEEP); - for (b = bno, mapi = 0; b < bno + count; ) { + for (b = *bno, mapi = 0; b < *bno + count; ) { nmap = MIN(XFS_BMAP_MAX_NMAP, count); - c = (int)(bno + count - b); - if ((error = xfs_bmapi(tp, dp, b, c, + c = (int)(*bno + count - b); + error = xfs_bmapi(tp, dp, b, c, xfs_bmapi_aflag(w)|XFS_BMAPI_WRITE| XFS_BMAPI_METADATA, args->firstblock, args->total, - &mapp[mapi], &nmap, args->flist))) { - kmem_free(mapp); - return error; - } + &mapp[mapi], &nmap, args->flist); + if (error) + goto out_free_map; if (nmap < 1) break; mapi += nmap; @@ -1629,24 +1609,53 @@ xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno) mapi = 0; mapp = NULL; } + /* * Count the blocks we got, make sure it matches the total. */ for (i = 0, got = 0; i < mapi; i++) got += mapp[i].br_blockcount; - if (got != count || mapp[0].br_startoff != bno || + if (got != count || mapp[0].br_startoff != *bno || mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount != - bno + count) { - if (mapp != &map) - kmem_free(mapp); - return XFS_ERROR(ENOSPC); + *bno + count) { + error = XFS_ERROR(ENOSPC); + goto out_free_map; } - if (mapp != &map) - kmem_free(mapp); + /* account for newly allocated blocks in reserved blocks total */ args->total -= dp->i_d.di_nblocks - nblks; - *new_blkno = (xfs_dablk_t)bno; - return 0; + +out_free_map: + if (mapp != &map) + kmem_free(mapp); + return error; +} + +/* + * Add a block to the btree ahead of the file. + * Return the new block number to the caller. + */ +int +xfs_da_grow_inode( + struct xfs_da_args *args, + xfs_dablk_t *new_blkno) +{ + xfs_fileoff_t bno; + int count; + int error; + + if (args->whichfork == XFS_DATA_FORK) { + bno = args->dp->i_mount->m_dirleafblk; + count = args->dp->i_mount->m_dirblkfsbs; + } else { + bno = 0; + count = 1; + } + + error = xfs_da_grow_inode_int(args, &bno, count); + if (!error) + *new_blkno = (xfs_dablk_t)bno; + return error; } /* @@ -1704,12 +1713,12 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop, /* * Get values from the moved block. */ - if (be16_to_cpu(dead_info->magic) == XFS_DIR2_LEAFN_MAGIC) { + if (dead_info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)) { dead_leaf2 = (xfs_dir2_leaf_t *)dead_info; dead_level = 0; dead_hash = be32_to_cpu(dead_leaf2->ents[be16_to_cpu(dead_leaf2->hdr.count) - 1].hashval); } else { - ASSERT(be16_to_cpu(dead_info->magic) == XFS_DA_NODE_MAGIC); + ASSERT(dead_info->magic == cpu_to_be16(XFS_DA_NODE_MAGIC)); dead_node = (xfs_da_intnode_t *)dead_info; dead_level = be16_to_cpu(dead_node->hdr.level); dead_hash = be32_to_cpu(dead_node->btree[be16_to_cpu(dead_node->hdr.count) - 1].hashval); @@ -1768,8 +1777,8 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop, if ((error = xfs_da_read_buf(tp, ip, par_blkno, -1, &par_buf, w))) goto done; par_node = par_buf->data; - if (unlikely( - be16_to_cpu(par_node->hdr.info.magic) != XFS_DA_NODE_MAGIC || + if (unlikely(par_node->hdr.info.magic != + cpu_to_be16(XFS_DA_NODE_MAGIC) || (level >= 0 && level != be16_to_cpu(par_node->hdr.level) + 1))) { XFS_ERROR_REPORT("xfs_da_swap_lastblock(4)", XFS_ERRLEVEL_LOW, mp); @@ -1820,7 +1829,7 @@ xfs_da_swap_lastblock(xfs_da_args_t *args, xfs_dablk_t *dead_blknop, par_node = par_buf->data; if (unlikely( be16_to_cpu(par_node->hdr.level) != level || - be16_to_cpu(par_node->hdr.info.magic) != XFS_DA_NODE_MAGIC)) { + par_node->hdr.info.magic != cpu_to_be16(XFS_DA_NODE_MAGIC))) { XFS_ERROR_REPORT("xfs_da_swap_lastblock(7)", XFS_ERRLEVEL_LOW, mp); error = XFS_ERROR(EFSCORRUPTED); @@ -1930,8 +1939,7 @@ xfs_da_do_buf( xfs_daddr_t *mappedbnop, xfs_dabuf_t **bpp, int whichfork, - int caller, - inst_t *ra) + int caller) { xfs_buf_t *bp = NULL; xfs_buf_t **bplist; @@ -2070,25 +2078,22 @@ xfs_da_do_buf( * Build a dabuf structure. */ if (bplist) { - rbp = xfs_da_buf_make(nbplist, bplist, ra); + rbp = xfs_da_buf_make(nbplist, bplist); } else if (bp) - rbp = xfs_da_buf_make(1, &bp, ra); + rbp = xfs_da_buf_make(1, &bp); else rbp = NULL; /* * For read_buf, check the magic number. */ if (caller == 1) { - xfs_dir2_data_t *data; - xfs_dir2_free_t *free; - xfs_da_blkinfo_t *info; + xfs_dir2_data_hdr_t *hdr = rbp->data; + xfs_dir2_free_t *free = rbp->data; + xfs_da_blkinfo_t *info = rbp->data; uint magic, magic1; - info = rbp->data; - data = rbp->data; - free = rbp->data; magic = be16_to_cpu(info->magic); - magic1 = be32_to_cpu(data->hdr.magic); + magic1 = be32_to_cpu(hdr->magic); if (unlikely( XFS_TEST_ERROR((magic != XFS_DA_NODE_MAGIC) && (magic != XFS_ATTR_LEAF_MAGIC) && @@ -2096,7 +2101,7 @@ xfs_da_do_buf( (magic != XFS_DIR2_LEAFN_MAGIC) && (magic1 != XFS_DIR2_BLOCK_MAGIC) && (magic1 != XFS_DIR2_DATA_MAGIC) && - (be32_to_cpu(free->hdr.magic) != XFS_DIR2_FREE_MAGIC), + (free->hdr.magic != cpu_to_be32(XFS_DIR2_FREE_MAGIC)), mp, XFS_ERRTAG_DA_READ_BUF, XFS_RANDOM_DA_READ_BUF))) { trace_xfs_da_btree_corrupt(rbp->bps[0], _RET_IP_); @@ -2143,8 +2148,7 @@ xfs_da_get_buf( xfs_dabuf_t **bpp, int whichfork) { - return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 0, - (inst_t *)__return_address); + return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 0); } /* @@ -2159,8 +2163,7 @@ xfs_da_read_buf( xfs_dabuf_t **bpp, int whichfork) { - return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 1, - (inst_t *)__return_address); + return xfs_da_do_buf(trans, dp, bno, &mappedbno, bpp, whichfork, 1); } /* @@ -2176,8 +2179,7 @@ xfs_da_reada_buf( xfs_daddr_t rval; rval = -1; - if (xfs_da_do_buf(trans, dp, bno, &rval, NULL, whichfork, 3, - (inst_t *)__return_address)) + if (xfs_da_do_buf(trans, dp, bno, &rval, NULL, whichfork, 3)) return -1; else return rval; @@ -2235,17 +2237,12 @@ xfs_da_state_free(xfs_da_state_t *state) kmem_zone_free(xfs_da_state_zone, state); } -#ifdef XFS_DABUF_DEBUG -xfs_dabuf_t *xfs_dabuf_global_list; -static DEFINE_SPINLOCK(xfs_dabuf_global_lock); -#endif - /* * Create a dabuf. */ /* ARGSUSED */ STATIC xfs_dabuf_t * -xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra) +xfs_da_buf_make(int nbuf, xfs_buf_t **bps) { xfs_buf_t *bp; xfs_dabuf_t *dabuf; @@ -2257,11 +2254,6 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra) else dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS); dabuf->dirty = 0; -#ifdef XFS_DABUF_DEBUG - dabuf->ra = ra; - dabuf->target = XFS_BUF_TARGET(bps[0]); - dabuf->blkno = XFS_BUF_ADDR(bps[0]); -#endif if (nbuf == 1) { dabuf->nbuf = 1; bp = bps[0]; @@ -2281,23 +2273,6 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra) XFS_BUF_COUNT(bp)); } } -#ifdef XFS_DABUF_DEBUG - { - xfs_dabuf_t *p; - - spin_lock(&xfs_dabuf_global_lock); - for (p = xfs_dabuf_global_list; p; p = p->next) { - ASSERT(p->blkno != dabuf->blkno || - p->target != dabuf->target); - } - dabuf->prev = NULL; - if (xfs_dabuf_global_list) - xfs_dabuf_global_list->prev = dabuf; - dabuf->next = xfs_dabuf_global_list; - xfs_dabuf_global_list = dabuf; - spin_unlock(&xfs_dabuf_global_lock); - } -#endif return dabuf; } @@ -2333,25 +2308,12 @@ xfs_da_buf_done(xfs_dabuf_t *dabuf) ASSERT(dabuf->nbuf && dabuf->data && dabuf->bbcount && dabuf->bps[0]); if (dabuf->dirty) xfs_da_buf_clean(dabuf); - if (dabuf->nbuf > 1) + if (dabuf->nbuf > 1) { kmem_free(dabuf->data); -#ifdef XFS_DABUF_DEBUG - { - spin_lock(&xfs_dabuf_global_lock); - if (dabuf->prev) - dabuf->prev->next = dabuf->next; - else - xfs_dabuf_global_list = dabuf->next; - if (dabuf->next) - dabuf->next->prev = dabuf->prev; - spin_unlock(&xfs_dabuf_global_lock); - } - memset(dabuf, 0, XFS_DA_BUF_SIZE(dabuf->nbuf)); -#endif - if (dabuf->nbuf == 1) - kmem_zone_free(xfs_dabuf_zone, dabuf); - else kmem_free(dabuf); + } else { + kmem_zone_free(xfs_dabuf_zone, dabuf); + } } /* diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h index fe9f5a8..dbf7c07 100644 --- a/fs/xfs/xfs_da_btree.h +++ b/fs/xfs/xfs_da_btree.h @@ -145,22 +145,11 @@ typedef struct xfs_dabuf { short dirty; /* data needs to be copied back */ short bbcount; /* how large is data in bbs */ void *data; /* pointer for buffers' data */ -#ifdef XFS_DABUF_DEBUG - inst_t *ra; /* return address of caller to make */ - struct xfs_dabuf *next; /* next in global chain */ - struct xfs_dabuf *prev; /* previous in global chain */ - struct xfs_buftarg *target; /* device for buffer */ - xfs_daddr_t blkno; /* daddr first in bps[0] */ -#endif struct xfs_buf *bps[1]; /* actually nbuf of these */ } xfs_dabuf_t; #define XFS_DA_BUF_SIZE(n) \ (sizeof(xfs_dabuf_t) + sizeof(struct xfs_buf *) * ((n) - 1)) -#ifdef XFS_DABUF_DEBUG -extern xfs_dabuf_t *xfs_dabuf_global_list; -#endif - /* * Storage for holding state during Btree searches and split/join ops. * @@ -248,6 +237,8 @@ int xfs_da_blk_link(xfs_da_state_t *state, xfs_da_state_blk_t *old_blk, * Utility routines. */ int xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno); +int xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno, + int count); int xfs_da_get_buf(struct xfs_trans *trans, struct xfs_inode *dp, xfs_dablk_t bno, xfs_daddr_t mappedbno, xfs_dabuf_t **bp, int whichfork); diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c index dba7a71..4580ce0 100644 --- a/fs/xfs/xfs_dir2.c +++ b/fs/xfs/xfs_dir2.c @@ -24,20 +24,17 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" #include "xfs_alloc_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_inode_item.h" #include "xfs_bmap.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" -#include "xfs_dir2_node.h" +#include "xfs_dir2.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_vnodeops.h" #include "xfs_trace.h" @@ -122,15 +119,15 @@ int xfs_dir_isempty( xfs_inode_t *dp) { - xfs_dir2_sf_t *sfp; + xfs_dir2_sf_hdr_t *sfp; ASSERT((dp->i_d.di_mode & S_IFMT) == S_IFDIR); if (dp->i_d.di_size == 0) /* might happen during shutdown. */ return 1; if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp)) return 0; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - return !sfp->hdr.count; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + return !sfp->count; } /* @@ -500,129 +497,34 @@ xfs_dir_canenter( /* * Add a block to the directory. - * This routine is for data and free blocks, not leaf/node blocks - * which are handled by xfs_da_grow_inode. + * + * This routine is for data and free blocks, not leaf/node blocks which are + * handled by xfs_da_grow_inode. */ int xfs_dir2_grow_inode( - xfs_da_args_t *args, - int space, /* v2 dir's space XFS_DIR2_xxx_SPACE */ - xfs_dir2_db_t *dbp) /* out: block number added */ + struct xfs_da_args *args, + int space, /* v2 dir's space XFS_DIR2_xxx_SPACE */ + xfs_dir2_db_t *dbp) /* out: block number added */ { - xfs_fileoff_t bno; /* directory offset of new block */ - int count; /* count of filesystem blocks */ - xfs_inode_t *dp; /* incore directory inode */ - int error; - int got; /* blocks actually mapped */ - int i; - xfs_bmbt_irec_t map; /* single structure for bmap */ - int mapi; /* mapping index */ - xfs_bmbt_irec_t *mapp; /* bmap mapping structure(s) */ - xfs_mount_t *mp; - int nmap; /* number of bmap entries */ - xfs_trans_t *tp; - xfs_drfsbno_t nblks; + struct xfs_inode *dp = args->dp; + struct xfs_mount *mp = dp->i_mount; + xfs_fileoff_t bno; /* directory offset of new block */ + int count; /* count of filesystem blocks */ + int error; trace_xfs_dir2_grow_inode(args, space); - dp = args->dp; - tp = args->trans; - mp = dp->i_mount; - nblks = dp->i_d.di_nblocks; /* * Set lowest possible block in the space requested. */ bno = XFS_B_TO_FSBT(mp, space * XFS_DIR2_SPACE_SIZE); count = mp->m_dirblkfsbs; - /* - * Find the first hole for our block. - */ - if ((error = xfs_bmap_first_unused(tp, dp, count, &bno, XFS_DATA_FORK))) - return error; - nmap = 1; - ASSERT(args->firstblock != NULL); - /* - * Try mapping the new block contiguously (one extent). - */ - if ((error = xfs_bmapi(tp, dp, bno, count, - XFS_BMAPI_WRITE|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG, - args->firstblock, args->total, &map, &nmap, - args->flist))) - return error; - ASSERT(nmap <= 1); - if (nmap == 1) { - mapp = ↦ - mapi = 1; - } - /* - * Didn't work and this is a multiple-fsb directory block. - * Try again with contiguous flag turned on. - */ - else if (nmap == 0 && count > 1) { - xfs_fileoff_t b; /* current file offset */ - /* - * Space for maximum number of mappings. - */ - mapp = kmem_alloc(sizeof(*mapp) * count, KM_SLEEP); - /* - * Iterate until we get to the end of our block. - */ - for (b = bno, mapi = 0; b < bno + count; ) { - int c; /* current fsb count */ - - /* - * Can't map more than MAX_NMAP at once. - */ - nmap = MIN(XFS_BMAP_MAX_NMAP, count); - c = (int)(bno + count - b); - if ((error = xfs_bmapi(tp, dp, b, c, - XFS_BMAPI_WRITE|XFS_BMAPI_METADATA, - args->firstblock, args->total, - &mapp[mapi], &nmap, args->flist))) { - kmem_free(mapp); - return error; - } - if (nmap < 1) - break; - /* - * Add this bunch into our table, go to the next offset. - */ - mapi += nmap; - b = mapp[mapi - 1].br_startoff + - mapp[mapi - 1].br_blockcount; - } - } - /* - * Didn't work. - */ - else { - mapi = 0; - mapp = NULL; - } - /* - * See how many fsb's we got. - */ - for (i = 0, got = 0; i < mapi; i++) - got += mapp[i].br_blockcount; - /* - * Didn't get enough fsb's, or the first/last block's are wrong. - */ - if (got != count || mapp[0].br_startoff != bno || - mapp[mapi - 1].br_startoff + mapp[mapi - 1].br_blockcount != - bno + count) { - if (mapp != &map) - kmem_free(mapp); - return XFS_ERROR(ENOSPC); - } - /* - * Done with the temporary mapping table. - */ - if (mapp != &map) - kmem_free(mapp); + error = xfs_da_grow_inode_int(args, &bno, count); + if (error) + return error; - /* account for newly allocated blocks in reserved blocks total */ - args->total -= dp->i_d.di_nblocks - nblks; *dbp = xfs_dir2_da_to_db(mp, (xfs_dablk_t)bno); /* @@ -634,7 +536,7 @@ xfs_dir2_grow_inode( size = XFS_FSB_TO_B(mp, bno + count); if (size > dp->i_d.di_size) { dp->i_d.di_size = size; - xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); + xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE); } } return 0; diff --git a/fs/xfs/xfs_dir2.h b/fs/xfs/xfs_dir2.h index 74a3b10..e937d99 100644 --- a/fs/xfs/xfs_dir2.h +++ b/fs/xfs/xfs_dir2.h @@ -16,49 +16,14 @@ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __XFS_DIR2_H__ -#define __XFS_DIR2_H__ +#define __XFS_DIR2_H__ -struct uio; -struct xfs_dabuf; -struct xfs_da_args; -struct xfs_dir2_put_args; struct xfs_bmap_free; +struct xfs_da_args; struct xfs_inode; struct xfs_mount; struct xfs_trans; -/* - * Directory version 2. - * There are 4 possible formats: - * shortform - * single block - data with embedded leaf at the end - * multiple data blocks, single leaf+freeindex block - * data blocks, node&leaf blocks (btree), freeindex blocks - * - * The shortform format is in xfs_dir2_sf.h. - * The single block format is in xfs_dir2_block.h. - * The data block format is in xfs_dir2_data.h. - * The leaf and freeindex block formats are in xfs_dir2_leaf.h. - * Node blocks are the same as the other version, in xfs_da_btree.h. - */ - -/* - * Byte offset in data block and shortform entry. - */ -typedef __uint16_t xfs_dir2_data_off_t; -#define NULLDATAOFF 0xffffU -typedef uint xfs_dir2_data_aoff_t; /* argument form */ - -/* - * Directory block number (logical dirblk in file) - */ -typedef __uint32_t xfs_dir2_db_t; - -/* - * Byte offset in a directory. - */ -typedef xfs_off_t xfs_dir2_off_t; - extern struct xfs_name xfs_name_dotdot; /* @@ -86,21 +51,10 @@ extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_bmap_free *flist, xfs_extlen_t tot); extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp, struct xfs_name *name, uint resblks); -extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino); /* - * Utility routines for v2 directories. + * Direct call from the bmap code, bypassing the generic directory layer. */ -extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space, - xfs_dir2_db_t *dbp); -extern int xfs_dir2_isblock(struct xfs_trans *tp, struct xfs_inode *dp, - int *vp); -extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, - int *vp); -extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db, - struct xfs_dabuf *bp); - -extern int xfs_dir_cilookup_result(struct xfs_da_args *args, - const unsigned char *name, int len); +extern int xfs_dir2_sf_to_block(struct xfs_da_args *args); #endif /* __XFS_DIR2_H__ */ diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c index 580d99c..9245e02 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -23,17 +23,14 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_inode_item.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -67,7 +64,7 @@ xfs_dir2_block_addname( xfs_da_args_t *args) /* directory op arguments */ { xfs_dir2_data_free_t *bf; /* bestfree table in block */ - xfs_dir2_block_t *block; /* directory block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ xfs_dabuf_t *bp; /* buffer for block */ xfs_dir2_block_tail_t *btp; /* block tail */ @@ -105,13 +102,13 @@ xfs_dir2_block_addname( return error; } ASSERT(bp != NULL); - block = bp->data; + hdr = bp->data; /* * Check the magic number, corrupted if wrong. */ - if (unlikely(be32_to_cpu(block->hdr.magic) != XFS_DIR2_BLOCK_MAGIC)) { + if (unlikely(hdr->magic != cpu_to_be32(XFS_DIR2_BLOCK_MAGIC))) { XFS_CORRUPTION_ERROR("xfs_dir2_block_addname", - XFS_ERRLEVEL_LOW, mp, block); + XFS_ERRLEVEL_LOW, mp, hdr); xfs_da_brelse(tp, bp); return XFS_ERROR(EFSCORRUPTED); } @@ -119,8 +116,8 @@ xfs_dir2_block_addname( /* * Set up pointers to parts of the block. */ - bf = block->hdr.bestfree; - btp = xfs_dir2_block_tail_p(mp, block); + bf = hdr->bestfree; + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * No stale entries? Need space for entry and new leaf. @@ -133,7 +130,7 @@ xfs_dir2_block_addname( /* * Data object just before the first leaf entry. */ - enddup = (xfs_dir2_data_unused_t *)((char *)block + be16_to_cpu(*tagp)); + enddup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); /* * If it's not free then can't do this add without cleaning up: * the space before the first leaf entry needs to be free so it @@ -146,7 +143,7 @@ xfs_dir2_block_addname( */ else { dup = (xfs_dir2_data_unused_t *) - ((char *)block + be16_to_cpu(bf[0].offset)); + ((char *)hdr + be16_to_cpu(bf[0].offset)); if (dup == enddup) { /* * It is the biggest freespace, is it too small @@ -159,7 +156,7 @@ xfs_dir2_block_addname( */ if (be16_to_cpu(bf[1].length) >= len) dup = (xfs_dir2_data_unused_t *) - ((char *)block + + ((char *)hdr + be16_to_cpu(bf[1].offset)); else dup = NULL; @@ -182,7 +179,7 @@ xfs_dir2_block_addname( */ else if (be16_to_cpu(bf[0].length) >= len) { dup = (xfs_dir2_data_unused_t *) - ((char *)block + be16_to_cpu(bf[0].offset)); + ((char *)hdr + be16_to_cpu(bf[0].offset)); compact = 0; } /* @@ -196,7 +193,7 @@ xfs_dir2_block_addname( /* * Data object just before the first leaf entry. */ - dup = (xfs_dir2_data_unused_t *)((char *)block + be16_to_cpu(*tagp)); + dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); /* * If it's not free then the data will go where the * leaf data starts now, if it works at all. @@ -255,7 +252,8 @@ xfs_dir2_block_addname( highstale = lfloghigh = -1; fromidx >= 0; fromidx--) { - if (be32_to_cpu(blp[fromidx].address) == XFS_DIR2_NULL_DATAPTR) { + if (blp[fromidx].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) { if (highstale == -1) highstale = toidx; else { @@ -272,7 +270,7 @@ xfs_dir2_block_addname( lfloghigh -= be32_to_cpu(btp->stale) - 1; be32_add_cpu(&btp->count, -(be32_to_cpu(btp->stale) - 1)); xfs_dir2_data_make_free(tp, bp, - (xfs_dir2_data_aoff_t)((char *)blp - (char *)block), + (xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr), (xfs_dir2_data_aoff_t)((be32_to_cpu(btp->stale) - 1) * sizeof(*blp)), &needlog, &needscan); blp += be32_to_cpu(btp->stale) - 1; @@ -282,7 +280,7 @@ xfs_dir2_block_addname( * This needs to happen before the next call to use_free. */ if (needscan) { - xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); needscan = 0; } } @@ -318,7 +316,7 @@ xfs_dir2_block_addname( */ xfs_dir2_data_use_free(tp, bp, enddup, (xfs_dir2_data_aoff_t) - ((char *)enddup - (char *)block + be16_to_cpu(enddup->length) - + ((char *)enddup - (char *)hdr + be16_to_cpu(enddup->length) - sizeof(*blp)), (xfs_dir2_data_aoff_t)sizeof(*blp), &needlog, &needscan); @@ -331,8 +329,7 @@ xfs_dir2_block_addname( * This needs to happen before the next call to use_free. */ if (needscan) { - xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, - &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); needscan = 0; } /* @@ -353,12 +350,14 @@ xfs_dir2_block_addname( else { for (lowstale = mid; lowstale >= 0 && - be32_to_cpu(blp[lowstale].address) != XFS_DIR2_NULL_DATAPTR; + blp[lowstale].address != + cpu_to_be32(XFS_DIR2_NULL_DATAPTR); lowstale--) continue; for (highstale = mid + 1; highstale < be32_to_cpu(btp->count) && - be32_to_cpu(blp[highstale].address) != XFS_DIR2_NULL_DATAPTR && + blp[highstale].address != + cpu_to_be32(XFS_DIR2_NULL_DATAPTR) && (lowstale < 0 || mid - lowstale > highstale - mid); highstale++) continue; @@ -397,13 +396,13 @@ xfs_dir2_block_addname( */ blp[mid].hashval = cpu_to_be32(args->hashval); blp[mid].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp, - (char *)dep - (char *)block)); + (char *)dep - (char *)hdr)); xfs_dir2_block_log_leaf(tp, bp, lfloglow, lfloghigh); /* * Mark space for the data entry used. */ xfs_dir2_data_use_free(tp, bp, dup, - (xfs_dir2_data_aoff_t)((char *)dup - (char *)block), + (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), (xfs_dir2_data_aoff_t)len, &needlog, &needscan); /* * Create the new data entry. @@ -412,12 +411,12 @@ xfs_dir2_block_addname( dep->namelen = args->namelen; memcpy(dep->name, args->name, args->namelen); tagp = xfs_dir2_data_entry_tag_p(dep); - *tagp = cpu_to_be16((char *)dep - (char *)block); + *tagp = cpu_to_be16((char *)dep - (char *)hdr); /* * Clean up the bestfree array and log the header, tail, and entry. */ if (needscan) - xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(tp, bp); xfs_dir2_block_log_tail(tp, bp); @@ -437,7 +436,7 @@ xfs_dir2_block_getdents( xfs_off_t *offset, filldir_t filldir) { - xfs_dir2_block_t *block; /* directory block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dabuf_t *bp; /* buffer for block */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_dir2_data_entry_t *dep; /* block data entry */ @@ -470,13 +469,13 @@ xfs_dir2_block_getdents( * We'll skip entries before this. */ wantoff = xfs_dir2_dataptr_to_off(mp, *offset); - block = bp->data; + hdr = bp->data; xfs_dir2_data_check(dp, bp); /* * Set up values for the loop. */ - btp = xfs_dir2_block_tail_p(mp, block); - ptr = (char *)block->u; + btp = xfs_dir2_block_tail_p(mp, hdr); + ptr = (char *)(hdr + 1); endptr = (char *)xfs_dir2_block_leaf_p(btp); /* @@ -502,11 +501,11 @@ xfs_dir2_block_getdents( /* * The entry is before the desired starting point, skip it. */ - if ((char *)dep - (char *)block < wantoff) + if ((char *)dep - (char *)hdr < wantoff) continue; cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, - (char *)dep - (char *)block); + (char *)dep - (char *)hdr); /* * If it didn't fit, set the final offset to here & return. @@ -540,17 +539,14 @@ xfs_dir2_block_log_leaf( int first, /* index of first logged leaf */ int last) /* index of last logged leaf */ { - xfs_dir2_block_t *block; /* directory block structure */ - xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ - xfs_dir2_block_tail_t *btp; /* block tail */ - xfs_mount_t *mp; /* filesystem mount point */ + xfs_dir2_data_hdr_t *hdr = bp->data; + xfs_dir2_leaf_entry_t *blp; + xfs_dir2_block_tail_t *btp; - mp = tp->t_mountp; - block = bp->data; - btp = xfs_dir2_block_tail_p(mp, block); + btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr); blp = xfs_dir2_block_leaf_p(btp); - xfs_da_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)block), - (uint)((char *)&blp[last + 1] - (char *)block - 1)); + xfs_da_log_buf(tp, bp, (uint)((char *)&blp[first] - (char *)hdr), + (uint)((char *)&blp[last + 1] - (char *)hdr - 1)); } /* @@ -561,15 +557,12 @@ xfs_dir2_block_log_tail( xfs_trans_t *tp, /* transaction structure */ xfs_dabuf_t *bp) /* block buffer */ { - xfs_dir2_block_t *block; /* directory block structure */ - xfs_dir2_block_tail_t *btp; /* block tail */ - xfs_mount_t *mp; /* filesystem mount point */ + xfs_dir2_data_hdr_t *hdr = bp->data; + xfs_dir2_block_tail_t *btp; - mp = tp->t_mountp; - block = bp->data; - btp = xfs_dir2_block_tail_p(mp, block); - xfs_da_log_buf(tp, bp, (uint)((char *)btp - (char *)block), - (uint)((char *)(btp + 1) - (char *)block - 1)); + btp = xfs_dir2_block_tail_p(tp->t_mountp, hdr); + xfs_da_log_buf(tp, bp, (uint)((char *)btp - (char *)hdr), + (uint)((char *)(btp + 1) - (char *)hdr - 1)); } /* @@ -580,7 +573,7 @@ int /* error */ xfs_dir2_block_lookup( xfs_da_args_t *args) /* dir lookup arguments */ { - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ xfs_dabuf_t *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ @@ -600,14 +593,14 @@ xfs_dir2_block_lookup( return error; dp = args->dp; mp = dp->i_mount; - block = bp->data; + hdr = bp->data; xfs_dir2_data_check(dp, bp); - btp = xfs_dir2_block_tail_p(mp, block); + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Get the offset from the leaf entry, to point to the data. */ - dep = (xfs_dir2_data_entry_t *)((char *)block + + dep = (xfs_dir2_data_entry_t *)((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); /* * Fill in inode number, CI name if appropriate, release the block. @@ -628,7 +621,7 @@ xfs_dir2_block_lookup_int( int *entno) /* returned entry number */ { xfs_dir2_dataptr_t addr; /* data entry address */ - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ xfs_dabuf_t *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ @@ -654,9 +647,9 @@ xfs_dir2_block_lookup_int( return error; } ASSERT(bp != NULL); - block = bp->data; + hdr = bp->data; xfs_dir2_data_check(dp, bp); - btp = xfs_dir2_block_tail_p(mp, block); + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Loop doing a binary search for our hash value. @@ -694,7 +687,7 @@ xfs_dir2_block_lookup_int( * Get pointer to the entry from the leaf. */ dep = (xfs_dir2_data_entry_t *) - ((char *)block + xfs_dir2_dataptr_to_off(mp, addr)); + ((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr)); /* * Compare name and if it's an exact match, return the index * and buffer. If it's the first case-insensitive match, store @@ -733,7 +726,7 @@ int /* error */ xfs_dir2_block_removename( xfs_da_args_t *args) /* directory operation args */ { - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf pointer */ xfs_dabuf_t *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ @@ -760,20 +753,20 @@ xfs_dir2_block_removename( dp = args->dp; tp = args->trans; mp = dp->i_mount; - block = bp->data; - btp = xfs_dir2_block_tail_p(mp, block); + hdr = bp->data; + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Point to the data entry using the leaf entry. */ dep = (xfs_dir2_data_entry_t *) - ((char *)block + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); + ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); /* * Mark the data entry's space free. */ needlog = needscan = 0; xfs_dir2_data_make_free(tp, bp, - (xfs_dir2_data_aoff_t)((char *)dep - (char *)block), + (xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr), xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan); /* * Fix up the block tail. @@ -789,15 +782,15 @@ xfs_dir2_block_removename( * Fix up bestfree, log the header if necessary. */ if (needscan) - xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(tp, bp); xfs_dir2_data_check(dp, bp); /* * See if the size as a shortform is good enough. */ - if ((size = xfs_dir2_block_sfsize(dp, block, &sfh)) > - XFS_IFORK_DSIZE(dp)) { + size = xfs_dir2_block_sfsize(dp, hdr, &sfh); + if (size > XFS_IFORK_DSIZE(dp)) { xfs_da_buf_done(bp); return 0; } @@ -815,7 +808,7 @@ int /* error */ xfs_dir2_block_replace( xfs_da_args_t *args) /* directory operation args */ { - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ xfs_dabuf_t *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail */ @@ -836,14 +829,14 @@ xfs_dir2_block_replace( } dp = args->dp; mp = dp->i_mount; - block = bp->data; - btp = xfs_dir2_block_tail_p(mp, block); + hdr = bp->data; + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Point to the data entry we need to change. */ dep = (xfs_dir2_data_entry_t *) - ((char *)block + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); + ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(blp[ent].address))); ASSERT(be64_to_cpu(dep->inumber) != args->inumber); /* * Change the inode number to the new value. @@ -882,7 +875,7 @@ xfs_dir2_leaf_to_block( xfs_dabuf_t *dbp) /* data buffer */ { __be16 *bestsp; /* leaf bests table */ - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_block_tail_t *btp; /* block tail */ xfs_inode_t *dp; /* incore directory inode */ xfs_dir2_data_unused_t *dup; /* unused data entry */ @@ -906,7 +899,7 @@ xfs_dir2_leaf_to_block( tp = args->trans; mp = dp->i_mount; leaf = lbp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAF1_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC)); ltp = xfs_dir2_leaf_tail_p(mp, leaf); /* * If there are data blocks other than the first one, take this @@ -917,7 +910,7 @@ xfs_dir2_leaf_to_block( while (dp->i_d.di_size > mp->m_dirblksize) { bestsp = xfs_dir2_leaf_bests_p(ltp); if (be16_to_cpu(bestsp[be32_to_cpu(ltp->bestcount) - 1]) == - mp->m_dirblksize - (uint)sizeof(block->hdr)) { + mp->m_dirblksize - (uint)sizeof(*hdr)) { if ((error = xfs_dir2_leaf_trim_data(args, lbp, (xfs_dir2_db_t)(be32_to_cpu(ltp->bestcount) - 1)))) @@ -935,18 +928,18 @@ xfs_dir2_leaf_to_block( XFS_DATA_FORK))) { goto out; } - block = dbp->data; - ASSERT(be32_to_cpu(block->hdr.magic) == XFS_DIR2_DATA_MAGIC); + hdr = dbp->data; + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC)); /* * Size of the "leaf" area in the block. */ - size = (uint)sizeof(block->tail) + + size = (uint)sizeof(xfs_dir2_block_tail_t) + (uint)sizeof(*lep) * (be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale)); /* * Look at the last data entry. */ - tagp = (__be16 *)((char *)block + mp->m_dirblksize) - 1; - dup = (xfs_dir2_data_unused_t *)((char *)block + be16_to_cpu(*tagp)); + tagp = (__be16 *)((char *)hdr + mp->m_dirblksize) - 1; + dup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); /* * If it's not free or is too short we can't do it. */ @@ -958,7 +951,7 @@ xfs_dir2_leaf_to_block( /* * Start converting it to block form. */ - block->hdr.magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC); + hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC); needlog = 1; needscan = 0; /* @@ -969,7 +962,7 @@ xfs_dir2_leaf_to_block( /* * Initialize the block tail. */ - btp = xfs_dir2_block_tail_p(mp, block); + btp = xfs_dir2_block_tail_p(mp, hdr); btp->count = cpu_to_be32(be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale)); btp->stale = 0; xfs_dir2_block_log_tail(tp, dbp); @@ -978,7 +971,8 @@ xfs_dir2_leaf_to_block( */ lep = xfs_dir2_block_leaf_p(btp); for (from = to = 0; from < be16_to_cpu(leaf->hdr.count); from++) { - if (be32_to_cpu(leaf->ents[from].address) == XFS_DIR2_NULL_DATAPTR) + if (leaf->ents[from].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) continue; lep[to++] = leaf->ents[from]; } @@ -988,7 +982,7 @@ xfs_dir2_leaf_to_block( * Scan the bestfree if we need it and log the data block header. */ if (needscan) - xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(tp, dbp); /* @@ -1002,8 +996,8 @@ xfs_dir2_leaf_to_block( /* * Now see if the resulting block can be shrunken to shortform. */ - if ((size = xfs_dir2_block_sfsize(dp, block, &sfh)) > - XFS_IFORK_DSIZE(dp)) { + size = xfs_dir2_block_sfsize(dp, hdr, &sfh); + if (size > XFS_IFORK_DSIZE(dp)) { error = 0; goto out; } @@ -1024,12 +1018,10 @@ xfs_dir2_sf_to_block( xfs_da_args_t *args) /* operation arguments */ { xfs_dir2_db_t blkno; /* dir-relative block # (0) */ - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block leaf entries */ xfs_dabuf_t *bp; /* block buffer */ xfs_dir2_block_tail_t *btp; /* block tail pointer */ - char *buf; /* sf buffer */ - int buf_len; xfs_dir2_data_entry_t *dep; /* data entry pointer */ xfs_inode_t *dp; /* incore directory inode */ int dummy; /* trash */ @@ -1043,7 +1035,8 @@ xfs_dir2_sf_to_block( int newoffset; /* offset from current entry */ int offset; /* target block offset */ xfs_dir2_sf_entry_t *sfep; /* sf entry pointer */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *oldsfp; /* old shortform header */ + xfs_dir2_sf_hdr_t *sfp; /* shortform header */ __be16 *tagp; /* end of data entry */ xfs_trans_t *tp; /* transaction pointer */ struct xfs_name name; @@ -1061,32 +1054,30 @@ xfs_dir2_sf_to_block( ASSERT(XFS_FORCED_SHUTDOWN(mp)); return XFS_ERROR(EIO); } + + oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count)); + ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count)); + /* - * Copy the directory into the stack buffer. + * Copy the directory into a temporary buffer. * Then pitch the incore inode data so we can make extents. */ + sfp = kmem_alloc(dp->i_df.if_bytes, KM_SLEEP); + memcpy(sfp, oldsfp, dp->i_df.if_bytes); - buf_len = dp->i_df.if_bytes; - buf = kmem_alloc(buf_len, KM_SLEEP); - - memcpy(buf, sfp, buf_len); - xfs_idata_realloc(dp, -buf_len, XFS_DATA_FORK); + xfs_idata_realloc(dp, -dp->i_df.if_bytes, XFS_DATA_FORK); dp->i_d.di_size = 0; xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE); - /* - * Reset pointer - old sfp is gone. - */ - sfp = (xfs_dir2_sf_t *)buf; + /* * Add block 0 to the inode. */ error = xfs_dir2_grow_inode(args, XFS_DIR2_DATA_SPACE, &blkno); if (error) { - kmem_free(buf); + kmem_free(sfp); return error; } /* @@ -1094,21 +1085,21 @@ xfs_dir2_sf_to_block( */ error = xfs_dir2_data_init(args, blkno, &bp); if (error) { - kmem_free(buf); + kmem_free(sfp); return error; } - block = bp->data; - block->hdr.magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC); + hdr = bp->data; + hdr->magic = cpu_to_be32(XFS_DIR2_BLOCK_MAGIC); /* * Compute size of block "tail" area. */ i = (uint)sizeof(*btp) + - (sfp->hdr.count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t); + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t); /* * The whole thing is initialized to free by the init routine. * Say we're using the leaf and tail area. */ - dup = (xfs_dir2_data_unused_t *)block->u; + dup = (xfs_dir2_data_unused_t *)(hdr + 1); needlog = needscan = 0; xfs_dir2_data_use_free(tp, bp, dup, mp->m_dirblksize - i, i, &needlog, &needscan); @@ -1116,50 +1107,51 @@ xfs_dir2_sf_to_block( /* * Fill in the tail. */ - btp = xfs_dir2_block_tail_p(mp, block); - btp->count = cpu_to_be32(sfp->hdr.count + 2); /* ., .. */ + btp = xfs_dir2_block_tail_p(mp, hdr); + btp->count = cpu_to_be32(sfp->count + 2); /* ., .. */ btp->stale = 0; blp = xfs_dir2_block_leaf_p(btp); - endoffset = (uint)((char *)blp - (char *)block); + endoffset = (uint)((char *)blp - (char *)hdr); /* * Remove the freespace, we'll manage it. */ xfs_dir2_data_use_free(tp, bp, dup, - (xfs_dir2_data_aoff_t)((char *)dup - (char *)block), + (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), be16_to_cpu(dup->length), &needlog, &needscan); /* * Create entry for . */ dep = (xfs_dir2_data_entry_t *) - ((char *)block + XFS_DIR2_DATA_DOT_OFFSET); + ((char *)hdr + XFS_DIR2_DATA_DOT_OFFSET); dep->inumber = cpu_to_be64(dp->i_ino); dep->namelen = 1; dep->name[0] = '.'; tagp = xfs_dir2_data_entry_tag_p(dep); - *tagp = cpu_to_be16((char *)dep - (char *)block); + *tagp = cpu_to_be16((char *)dep - (char *)hdr); xfs_dir2_data_log_entry(tp, bp, dep); blp[0].hashval = cpu_to_be32(xfs_dir_hash_dot); blp[0].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp, - (char *)dep - (char *)block)); + (char *)dep - (char *)hdr)); /* * Create entry for .. */ dep = (xfs_dir2_data_entry_t *) - ((char *)block + XFS_DIR2_DATA_DOTDOT_OFFSET); - dep->inumber = cpu_to_be64(xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent)); + ((char *)hdr + XFS_DIR2_DATA_DOTDOT_OFFSET); + dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp)); dep->namelen = 2; dep->name[0] = dep->name[1] = '.'; tagp = xfs_dir2_data_entry_tag_p(dep); - *tagp = cpu_to_be16((char *)dep - (char *)block); + *tagp = cpu_to_be16((char *)dep - (char *)hdr); xfs_dir2_data_log_entry(tp, bp, dep); blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot); blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp, - (char *)dep - (char *)block)); + (char *)dep - (char *)hdr)); offset = XFS_DIR2_DATA_FIRST_OFFSET; /* * Loop over existing entries, stuff them in. */ - if ((i = 0) == sfp->hdr.count) + i = 0; + if (!sfp->count) sfep = NULL; else sfep = xfs_dir2_sf_firstentry(sfp); @@ -1179,43 +1171,40 @@ xfs_dir2_sf_to_block( * There should be a hole here, make one. */ if (offset < newoffset) { - dup = (xfs_dir2_data_unused_t *) - ((char *)block + offset); + dup = (xfs_dir2_data_unused_t *)((char *)hdr + offset); dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); dup->length = cpu_to_be16(newoffset - offset); *xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16( - ((char *)dup - (char *)block)); + ((char *)dup - (char *)hdr)); xfs_dir2_data_log_unused(tp, bp, dup); - (void)xfs_dir2_data_freeinsert((xfs_dir2_data_t *)block, - dup, &dummy); + xfs_dir2_data_freeinsert(hdr, dup, &dummy); offset += be16_to_cpu(dup->length); continue; } /* * Copy a real entry. */ - dep = (xfs_dir2_data_entry_t *)((char *)block + newoffset); - dep->inumber = cpu_to_be64(xfs_dir2_sf_get_inumber(sfp, - xfs_dir2_sf_inumberp(sfep))); + dep = (xfs_dir2_data_entry_t *)((char *)hdr + newoffset); + dep->inumber = cpu_to_be64(xfs_dir2_sfe_get_ino(sfp, sfep)); dep->namelen = sfep->namelen; memcpy(dep->name, sfep->name, dep->namelen); tagp = xfs_dir2_data_entry_tag_p(dep); - *tagp = cpu_to_be16((char *)dep - (char *)block); + *tagp = cpu_to_be16((char *)dep - (char *)hdr); xfs_dir2_data_log_entry(tp, bp, dep); name.name = sfep->name; name.len = sfep->namelen; blp[2 + i].hashval = cpu_to_be32(mp->m_dirnameops-> hashname(&name)); blp[2 + i].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp, - (char *)dep - (char *)block)); - offset = (int)((char *)(tagp + 1) - (char *)block); - if (++i == sfp->hdr.count) + (char *)dep - (char *)hdr)); + offset = (int)((char *)(tagp + 1) - (char *)hdr); + if (++i == sfp->count) sfep = NULL; else sfep = xfs_dir2_sf_nextentry(sfp, sfep); } /* Done with the temporary buffer */ - kmem_free(buf); + kmem_free(sfp); /* * Sort the leaf entries by hash value. */ diff --git a/fs/xfs/xfs_dir2_block.h b/fs/xfs/xfs_dir2_block.h deleted file mode 100644 index 10e6896..0000000 --- a/fs/xfs/xfs_dir2_block.h +++ /dev/null @@ -1,92 +0,0 @@ -/* - * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_DIR2_BLOCK_H__ -#define __XFS_DIR2_BLOCK_H__ - -/* - * xfs_dir2_block.h - * Directory version 2, single block format structures - */ - -struct uio; -struct xfs_dabuf; -struct xfs_da_args; -struct xfs_dir2_data_hdr; -struct xfs_dir2_leaf_entry; -struct xfs_inode; -struct xfs_mount; -struct xfs_trans; - -/* - * The single block format is as follows: - * xfs_dir2_data_hdr_t structure - * xfs_dir2_data_entry_t and xfs_dir2_data_unused_t structures - * xfs_dir2_leaf_entry_t structures - * xfs_dir2_block_tail_t structure - */ - -#define XFS_DIR2_BLOCK_MAGIC 0x58443242 /* XD2B: for one block dirs */ - -typedef struct xfs_dir2_block_tail { - __be32 count; /* count of leaf entries */ - __be32 stale; /* count of stale lf entries */ -} xfs_dir2_block_tail_t; - -/* - * Generic single-block structure, for xfs_db. - */ -typedef struct xfs_dir2_block { - xfs_dir2_data_hdr_t hdr; /* magic XFS_DIR2_BLOCK_MAGIC */ - xfs_dir2_data_union_t u[1]; - xfs_dir2_leaf_entry_t leaf[1]; - xfs_dir2_block_tail_t tail; -} xfs_dir2_block_t; - -/* - * Pointer to the leaf header embedded in a data block (1-block format) - */ -static inline xfs_dir2_block_tail_t * -xfs_dir2_block_tail_p(struct xfs_mount *mp, xfs_dir2_block_t *block) -{ - return (((xfs_dir2_block_tail_t *) - ((char *)(block) + (mp)->m_dirblksize)) - 1); -} - -/* - * Pointer to the leaf entries embedded in a data block (1-block format) - */ -static inline struct xfs_dir2_leaf_entry * -xfs_dir2_block_leaf_p(xfs_dir2_block_tail_t *btp) -{ - return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count); -} - -/* - * Function declarations. - */ -extern int xfs_dir2_block_addname(struct xfs_da_args *args); -extern int xfs_dir2_block_getdents(struct xfs_inode *dp, void *dirent, - xfs_off_t *offset, filldir_t filldir); -extern int xfs_dir2_block_lookup(struct xfs_da_args *args); -extern int xfs_dir2_block_removename(struct xfs_da_args *args); -extern int xfs_dir2_block_replace(struct xfs_da_args *args); -extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args, - struct xfs_dabuf *lbp, struct xfs_dabuf *dbp); -extern int xfs_dir2_sf_to_block(struct xfs_da_args *args); - -#endif /* __XFS_DIR2_BLOCK_H__ */ diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c index 921595b..5bbe2a8 100644 --- a/fs/xfs/xfs_dir2_data.c +++ b/fs/xfs/xfs_dir2_data.c @@ -23,18 +23,18 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_error.h" +STATIC xfs_dir2_data_free_t * +xfs_dir2_data_freefind(xfs_dir2_data_hdr_t *hdr, xfs_dir2_data_unused_t *dup); + #ifdef DEBUG /* * Check the consistency of the data block. @@ -50,7 +50,7 @@ xfs_dir2_data_check( xfs_dir2_data_free_t *bf; /* bestfree table */ xfs_dir2_block_tail_t *btp=NULL; /* block tail */ int count; /* count of entries found */ - xfs_dir2_data_t *d; /* data block pointer */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_data_entry_t *dep; /* data entry */ xfs_dir2_data_free_t *dfp; /* bestfree entry */ xfs_dir2_data_unused_t *dup; /* unused entry */ @@ -66,17 +66,19 @@ xfs_dir2_data_check( struct xfs_name name; mp = dp->i_mount; - d = bp->data; - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); - bf = d->hdr.bestfree; - p = (char *)d->u; - if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC) { - btp = xfs_dir2_block_tail_p(mp, (xfs_dir2_block_t *)d); + hdr = bp->data; + bf = hdr->bestfree; + p = (char *)(hdr + 1); + + if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) { + btp = xfs_dir2_block_tail_p(mp, hdr); lep = xfs_dir2_block_leaf_p(btp); endp = (char *)lep; - } else - endp = (char *)d + mp->m_dirblksize; + } else { + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC)); + endp = (char *)hdr + mp->m_dirblksize; + } + count = lastfree = freeseen = 0; /* * Account for zero bestfree entries. @@ -108,8 +110,8 @@ xfs_dir2_data_check( if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { ASSERT(lastfree == 0); ASSERT(be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) == - (char *)dup - (char *)d); - dfp = xfs_dir2_data_freefind(d, dup); + (char *)dup - (char *)hdr); + dfp = xfs_dir2_data_freefind(hdr, dup); if (dfp) { i = (int)(dfp - bf); ASSERT((freeseen & (1 << i)) == 0); @@ -132,13 +134,13 @@ xfs_dir2_data_check( ASSERT(dep->namelen != 0); ASSERT(xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)) == 0); ASSERT(be16_to_cpu(*xfs_dir2_data_entry_tag_p(dep)) == - (char *)dep - (char *)d); + (char *)dep - (char *)hdr); count++; lastfree = 0; - if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC) { + if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) { addr = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, (xfs_dir2_data_aoff_t) - ((char *)dep - (char *)d)); + ((char *)dep - (char *)hdr)); name.name = dep->name; name.len = dep->namelen; hash = mp->m_dirnameops->hashname(&name); @@ -155,9 +157,10 @@ xfs_dir2_data_check( * Need to have seen all the entries and all the bestfree slots. */ ASSERT(freeseen == 7); - if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC) { + if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) { for (i = stale = 0; i < be32_to_cpu(btp->count); i++) { - if (be32_to_cpu(lep[i].address) == XFS_DIR2_NULL_DATAPTR) + if (lep[i].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; if (i > 0) ASSERT(be32_to_cpu(lep[i].hashval) >= be32_to_cpu(lep[i - 1].hashval)); @@ -172,9 +175,9 @@ xfs_dir2_data_check( * Given a data block and an unused entry from that block, * return the bestfree entry if any that corresponds to it. */ -xfs_dir2_data_free_t * +STATIC xfs_dir2_data_free_t * xfs_dir2_data_freefind( - xfs_dir2_data_t *d, /* data block */ + xfs_dir2_data_hdr_t *hdr, /* data block */ xfs_dir2_data_unused_t *dup) /* data unused entry */ { xfs_dir2_data_free_t *dfp; /* bestfree entry */ @@ -184,17 +187,17 @@ xfs_dir2_data_freefind( int seenzero; /* saw a 0 bestfree entry */ #endif - off = (xfs_dir2_data_aoff_t)((char *)dup - (char *)d); + off = (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr); #if defined(DEBUG) && defined(__KERNEL__) /* * Validate some consistency in the bestfree table. * Check order, non-overlapping entries, and if we find the * one we're looking for it has to be exact. */ - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); - for (dfp = &d->hdr.bestfree[0], seenzero = matched = 0; - dfp < &d->hdr.bestfree[XFS_DIR2_DATA_FD_COUNT]; + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); + for (dfp = &hdr->bestfree[0], seenzero = matched = 0; + dfp < &hdr->bestfree[XFS_DIR2_DATA_FD_COUNT]; dfp++) { if (!dfp->offset) { ASSERT(!dfp->length); @@ -210,7 +213,7 @@ xfs_dir2_data_freefind( else ASSERT(be16_to_cpu(dfp->offset) + be16_to_cpu(dfp->length) <= off); ASSERT(matched || be16_to_cpu(dfp->length) >= be16_to_cpu(dup->length)); - if (dfp > &d->hdr.bestfree[0]) + if (dfp > &hdr->bestfree[0]) ASSERT(be16_to_cpu(dfp[-1].length) >= be16_to_cpu(dfp[0].length)); } #endif @@ -219,13 +222,13 @@ xfs_dir2_data_freefind( * it can't be there since they're sorted. */ if (be16_to_cpu(dup->length) < - be16_to_cpu(d->hdr.bestfree[XFS_DIR2_DATA_FD_COUNT - 1].length)) + be16_to_cpu(hdr->bestfree[XFS_DIR2_DATA_FD_COUNT - 1].length)) return NULL; /* * Look at the three bestfree entries for our guy. */ - for (dfp = &d->hdr.bestfree[0]; - dfp < &d->hdr.bestfree[XFS_DIR2_DATA_FD_COUNT]; + for (dfp = &hdr->bestfree[0]; + dfp < &hdr->bestfree[XFS_DIR2_DATA_FD_COUNT]; dfp++) { if (!dfp->offset) return NULL; @@ -243,7 +246,7 @@ xfs_dir2_data_freefind( */ xfs_dir2_data_free_t * /* entry inserted */ xfs_dir2_data_freeinsert( - xfs_dir2_data_t *d, /* data block pointer */ + xfs_dir2_data_hdr_t *hdr, /* data block pointer */ xfs_dir2_data_unused_t *dup, /* unused space */ int *loghead) /* log the data header (out) */ { @@ -251,12 +254,13 @@ xfs_dir2_data_freeinsert( xfs_dir2_data_free_t new; /* new bestfree entry */ #ifdef __KERNEL__ - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); #endif - dfp = d->hdr.bestfree; + dfp = hdr->bestfree; new.length = dup->length; - new.offset = cpu_to_be16((char *)dup - (char *)d); + new.offset = cpu_to_be16((char *)dup - (char *)hdr); + /* * Insert at position 0, 1, or 2; or not at all. */ @@ -286,36 +290,36 @@ xfs_dir2_data_freeinsert( */ STATIC void xfs_dir2_data_freeremove( - xfs_dir2_data_t *d, /* data block pointer */ + xfs_dir2_data_hdr_t *hdr, /* data block header */ xfs_dir2_data_free_t *dfp, /* bestfree entry pointer */ int *loghead) /* out: log data header */ { #ifdef __KERNEL__ - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); #endif /* * It's the first entry, slide the next 2 up. */ - if (dfp == &d->hdr.bestfree[0]) { - d->hdr.bestfree[0] = d->hdr.bestfree[1]; - d->hdr.bestfree[1] = d->hdr.bestfree[2]; + if (dfp == &hdr->bestfree[0]) { + hdr->bestfree[0] = hdr->bestfree[1]; + hdr->bestfree[1] = hdr->bestfree[2]; } /* * It's the second entry, slide the 3rd entry up. */ - else if (dfp == &d->hdr.bestfree[1]) - d->hdr.bestfree[1] = d->hdr.bestfree[2]; + else if (dfp == &hdr->bestfree[1]) + hdr->bestfree[1] = hdr->bestfree[2]; /* * Must be the last entry. */ else - ASSERT(dfp == &d->hdr.bestfree[2]); + ASSERT(dfp == &hdr->bestfree[2]); /* * Clear the 3rd entry, must be zero now. */ - d->hdr.bestfree[2].length = 0; - d->hdr.bestfree[2].offset = 0; + hdr->bestfree[2].length = 0; + hdr->bestfree[2].offset = 0; *loghead = 1; } @@ -325,7 +329,7 @@ xfs_dir2_data_freeremove( void xfs_dir2_data_freescan( xfs_mount_t *mp, /* filesystem mount point */ - xfs_dir2_data_t *d, /* data block pointer */ + xfs_dir2_data_hdr_t *hdr, /* data block header */ int *loghead) /* out: log data header */ { xfs_dir2_block_tail_t *btp; /* block tail */ @@ -335,23 +339,23 @@ xfs_dir2_data_freescan( char *p; /* current entry pointer */ #ifdef __KERNEL__ - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); #endif /* * Start by clearing the table. */ - memset(d->hdr.bestfree, 0, sizeof(d->hdr.bestfree)); + memset(hdr->bestfree, 0, sizeof(hdr->bestfree)); *loghead = 1; /* * Set up pointers. */ - p = (char *)d->u; - if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC) { - btp = xfs_dir2_block_tail_p(mp, (xfs_dir2_block_t *)d); + p = (char *)(hdr + 1); + if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)) { + btp = xfs_dir2_block_tail_p(mp, hdr); endp = (char *)xfs_dir2_block_leaf_p(btp); } else - endp = (char *)d + mp->m_dirblksize; + endp = (char *)hdr + mp->m_dirblksize; /* * Loop over the block's entries. */ @@ -361,9 +365,9 @@ xfs_dir2_data_freescan( * If it's a free entry, insert it. */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { - ASSERT((char *)dup - (char *)d == + ASSERT((char *)dup - (char *)hdr == be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup))); - xfs_dir2_data_freeinsert(d, dup, loghead); + xfs_dir2_data_freeinsert(hdr, dup, loghead); p += be16_to_cpu(dup->length); } /* @@ -371,7 +375,7 @@ xfs_dir2_data_freescan( */ else { dep = (xfs_dir2_data_entry_t *)p; - ASSERT((char *)dep - (char *)d == + ASSERT((char *)dep - (char *)hdr == be16_to_cpu(*xfs_dir2_data_entry_tag_p(dep))); p += xfs_dir2_data_entsize(dep->namelen); } @@ -389,7 +393,7 @@ xfs_dir2_data_init( xfs_dabuf_t **bpp) /* output block buffer */ { xfs_dabuf_t *bp; /* block buffer */ - xfs_dir2_data_t *d; /* pointer to block */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_inode_t *dp; /* incore directory inode */ xfs_dir2_data_unused_t *dup; /* unused entry pointer */ int error; /* error return value */ @@ -410,26 +414,28 @@ xfs_dir2_data_init( return error; } ASSERT(bp != NULL); + /* * Initialize the header. */ - d = bp->data; - d->hdr.magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC); - d->hdr.bestfree[0].offset = cpu_to_be16(sizeof(d->hdr)); + hdr = bp->data; + hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC); + hdr->bestfree[0].offset = cpu_to_be16(sizeof(*hdr)); for (i = 1; i < XFS_DIR2_DATA_FD_COUNT; i++) { - d->hdr.bestfree[i].length = 0; - d->hdr.bestfree[i].offset = 0; + hdr->bestfree[i].length = 0; + hdr->bestfree[i].offset = 0; } + /* * Set up an unused entry for the block's body. */ - dup = &d->u[0].unused; + dup = (xfs_dir2_data_unused_t *)(hdr + 1); dup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); - t=mp->m_dirblksize - (uint)sizeof(d->hdr); - d->hdr.bestfree[0].length = cpu_to_be16(t); + t = mp->m_dirblksize - (uint)sizeof(*hdr); + hdr->bestfree[0].length = cpu_to_be16(t); dup->length = cpu_to_be16(t); - *xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)d); + *xfs_dir2_data_unused_tag_p(dup) = cpu_to_be16((char *)dup - (char *)hdr); /* * Log it and return it. */ @@ -448,14 +454,14 @@ xfs_dir2_data_log_entry( xfs_dabuf_t *bp, /* block buffer */ xfs_dir2_data_entry_t *dep) /* data entry pointer */ { - xfs_dir2_data_t *d; /* data block pointer */ + xfs_dir2_data_hdr_t *hdr = bp->data; + + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); - d = bp->data; - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); - xfs_da_log_buf(tp, bp, (uint)((char *)dep - (char *)d), + xfs_da_log_buf(tp, bp, (uint)((char *)dep - (char *)hdr), (uint)((char *)(xfs_dir2_data_entry_tag_p(dep) + 1) - - (char *)d - 1)); + (char *)hdr - 1)); } /* @@ -466,13 +472,12 @@ xfs_dir2_data_log_header( xfs_trans_t *tp, /* transaction pointer */ xfs_dabuf_t *bp) /* block buffer */ { - xfs_dir2_data_t *d; /* data block pointer */ + xfs_dir2_data_hdr_t *hdr = bp->data; - d = bp->data; - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); - xfs_da_log_buf(tp, bp, (uint)((char *)&d->hdr - (char *)d), - (uint)(sizeof(d->hdr) - 1)); + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); + + xfs_da_log_buf(tp, bp, 0, sizeof(*hdr) - 1); } /* @@ -484,23 +489,23 @@ xfs_dir2_data_log_unused( xfs_dabuf_t *bp, /* block buffer */ xfs_dir2_data_unused_t *dup) /* data unused pointer */ { - xfs_dir2_data_t *d; /* data block pointer */ + xfs_dir2_data_hdr_t *hdr = bp->data; + + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); - d = bp->data; - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); /* * Log the first part of the unused entry. */ - xfs_da_log_buf(tp, bp, (uint)((char *)dup - (char *)d), + xfs_da_log_buf(tp, bp, (uint)((char *)dup - (char *)hdr), (uint)((char *)&dup->length + sizeof(dup->length) - - 1 - (char *)d)); + 1 - (char *)hdr)); /* * Log the end (tag) of the unused entry. */ xfs_da_log_buf(tp, bp, - (uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)d), - (uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)d + + (uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr), + (uint)((char *)xfs_dir2_data_unused_tag_p(dup) - (char *)hdr + sizeof(xfs_dir2_data_off_t) - 1)); } @@ -517,7 +522,7 @@ xfs_dir2_data_make_free( int *needlogp, /* out: log header */ int *needscanp) /* out: regen bestfree */ { - xfs_dir2_data_t *d; /* data block pointer */ + xfs_dir2_data_hdr_t *hdr; /* data block pointer */ xfs_dir2_data_free_t *dfp; /* bestfree pointer */ char *endptr; /* end of data area */ xfs_mount_t *mp; /* filesystem mount point */ @@ -527,28 +532,29 @@ xfs_dir2_data_make_free( xfs_dir2_data_unused_t *prevdup; /* unused entry before us */ mp = tp->t_mountp; - d = bp->data; + hdr = bp->data; + /* * Figure out where the end of the data area is. */ - if (be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC) - endptr = (char *)d + mp->m_dirblksize; + if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC)) + endptr = (char *)hdr + mp->m_dirblksize; else { xfs_dir2_block_tail_t *btp; /* block tail */ - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); - btp = xfs_dir2_block_tail_p(mp, (xfs_dir2_block_t *)d); + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); + btp = xfs_dir2_block_tail_p(mp, hdr); endptr = (char *)xfs_dir2_block_leaf_p(btp); } /* * If this isn't the start of the block, then back up to * the previous entry and see if it's free. */ - if (offset > sizeof(d->hdr)) { + if (offset > sizeof(*hdr)) { __be16 *tagp; /* tag just before us */ - tagp = (__be16 *)((char *)d + offset) - 1; - prevdup = (xfs_dir2_data_unused_t *)((char *)d + be16_to_cpu(*tagp)); + tagp = (__be16 *)((char *)hdr + offset) - 1; + prevdup = (xfs_dir2_data_unused_t *)((char *)hdr + be16_to_cpu(*tagp)); if (be16_to_cpu(prevdup->freetag) != XFS_DIR2_DATA_FREE_TAG) prevdup = NULL; } else @@ -557,9 +563,9 @@ xfs_dir2_data_make_free( * If this isn't the end of the block, see if the entry after * us is free. */ - if ((char *)d + offset + len < endptr) { + if ((char *)hdr + offset + len < endptr) { postdup = - (xfs_dir2_data_unused_t *)((char *)d + offset + len); + (xfs_dir2_data_unused_t *)((char *)hdr + offset + len); if (be16_to_cpu(postdup->freetag) != XFS_DIR2_DATA_FREE_TAG) postdup = NULL; } else @@ -576,21 +582,21 @@ xfs_dir2_data_make_free( /* * See if prevdup and/or postdup are in bestfree table. */ - dfp = xfs_dir2_data_freefind(d, prevdup); - dfp2 = xfs_dir2_data_freefind(d, postdup); + dfp = xfs_dir2_data_freefind(hdr, prevdup); + dfp2 = xfs_dir2_data_freefind(hdr, postdup); /* * We need a rescan unless there are exactly 2 free entries * namely our two. Then we know what's happening, otherwise * since the third bestfree is there, there might be more * entries. */ - needscan = (d->hdr.bestfree[2].length != 0); + needscan = (hdr->bestfree[2].length != 0); /* * Fix up the new big freespace. */ be16_add_cpu(&prevdup->length, len + be16_to_cpu(postdup->length)); *xfs_dir2_data_unused_tag_p(prevdup) = - cpu_to_be16((char *)prevdup - (char *)d); + cpu_to_be16((char *)prevdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, prevdup); if (!needscan) { /* @@ -600,18 +606,18 @@ xfs_dir2_data_make_free( * Remove entry 1 first then entry 0. */ ASSERT(dfp && dfp2); - if (dfp == &d->hdr.bestfree[1]) { - dfp = &d->hdr.bestfree[0]; + if (dfp == &hdr->bestfree[1]) { + dfp = &hdr->bestfree[0]; ASSERT(dfp2 == dfp); - dfp2 = &d->hdr.bestfree[1]; + dfp2 = &hdr->bestfree[1]; } - xfs_dir2_data_freeremove(d, dfp2, needlogp); - xfs_dir2_data_freeremove(d, dfp, needlogp); + xfs_dir2_data_freeremove(hdr, dfp2, needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); /* * Now insert the new entry. */ - dfp = xfs_dir2_data_freeinsert(d, prevdup, needlogp); - ASSERT(dfp == &d->hdr.bestfree[0]); + dfp = xfs_dir2_data_freeinsert(hdr, prevdup, needlogp); + ASSERT(dfp == &hdr->bestfree[0]); ASSERT(dfp->length == prevdup->length); ASSERT(!dfp[1].length); ASSERT(!dfp[2].length); @@ -621,10 +627,10 @@ xfs_dir2_data_make_free( * The entry before us is free, merge with it. */ else if (prevdup) { - dfp = xfs_dir2_data_freefind(d, prevdup); + dfp = xfs_dir2_data_freefind(hdr, prevdup); be16_add_cpu(&prevdup->length, len); *xfs_dir2_data_unused_tag_p(prevdup) = - cpu_to_be16((char *)prevdup - (char *)d); + cpu_to_be16((char *)prevdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, prevdup); /* * If the previous entry was in the table, the new entry @@ -632,27 +638,27 @@ xfs_dir2_data_make_free( * the old one and add the new one. */ if (dfp) { - xfs_dir2_data_freeremove(d, dfp, needlogp); - (void)xfs_dir2_data_freeinsert(d, prevdup, needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); + xfs_dir2_data_freeinsert(hdr, prevdup, needlogp); } /* * Otherwise we need a scan if the new entry is big enough. */ else { needscan = be16_to_cpu(prevdup->length) > - be16_to_cpu(d->hdr.bestfree[2].length); + be16_to_cpu(hdr->bestfree[2].length); } } /* * The following entry is free, merge with it. */ else if (postdup) { - dfp = xfs_dir2_data_freefind(d, postdup); - newdup = (xfs_dir2_data_unused_t *)((char *)d + offset); + dfp = xfs_dir2_data_freefind(hdr, postdup); + newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset); newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); newdup->length = cpu_to_be16(len + be16_to_cpu(postdup->length)); *xfs_dir2_data_unused_tag_p(newdup) = - cpu_to_be16((char *)newdup - (char *)d); + cpu_to_be16((char *)newdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, newdup); /* * If the following entry was in the table, the new entry @@ -660,28 +666,28 @@ xfs_dir2_data_make_free( * the old one and add the new one. */ if (dfp) { - xfs_dir2_data_freeremove(d, dfp, needlogp); - (void)xfs_dir2_data_freeinsert(d, newdup, needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); + xfs_dir2_data_freeinsert(hdr, newdup, needlogp); } /* * Otherwise we need a scan if the new entry is big enough. */ else { needscan = be16_to_cpu(newdup->length) > - be16_to_cpu(d->hdr.bestfree[2].length); + be16_to_cpu(hdr->bestfree[2].length); } } /* * Neither neighbor is free. Make a new entry. */ else { - newdup = (xfs_dir2_data_unused_t *)((char *)d + offset); + newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset); newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); newdup->length = cpu_to_be16(len); *xfs_dir2_data_unused_tag_p(newdup) = - cpu_to_be16((char *)newdup - (char *)d); + cpu_to_be16((char *)newdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, newdup); - (void)xfs_dir2_data_freeinsert(d, newdup, needlogp); + xfs_dir2_data_freeinsert(hdr, newdup, needlogp); } *needscanp = needscan; } @@ -699,7 +705,7 @@ xfs_dir2_data_use_free( int *needlogp, /* out: need to log header */ int *needscanp) /* out: need regen bestfree */ { - xfs_dir2_data_t *d; /* data block */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_data_free_t *dfp; /* bestfree pointer */ int matchback; /* matches end of freespace */ int matchfront; /* matches start of freespace */ @@ -708,24 +714,24 @@ xfs_dir2_data_use_free( xfs_dir2_data_unused_t *newdup2; /* another new unused entry */ int oldlen; /* old unused entry's length */ - d = bp->data; - ASSERT(be32_to_cpu(d->hdr.magic) == XFS_DIR2_DATA_MAGIC || - be32_to_cpu(d->hdr.magic) == XFS_DIR2_BLOCK_MAGIC); + hdr = bp->data; + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) || + hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC)); ASSERT(be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG); - ASSERT(offset >= (char *)dup - (char *)d); - ASSERT(offset + len <= (char *)dup + be16_to_cpu(dup->length) - (char *)d); - ASSERT((char *)dup - (char *)d == be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup))); + ASSERT(offset >= (char *)dup - (char *)hdr); + ASSERT(offset + len <= (char *)dup + be16_to_cpu(dup->length) - (char *)hdr); + ASSERT((char *)dup - (char *)hdr == be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup))); /* * Look up the entry in the bestfree table. */ - dfp = xfs_dir2_data_freefind(d, dup); + dfp = xfs_dir2_data_freefind(hdr, dup); oldlen = be16_to_cpu(dup->length); - ASSERT(dfp || oldlen <= be16_to_cpu(d->hdr.bestfree[2].length)); + ASSERT(dfp || oldlen <= be16_to_cpu(hdr->bestfree[2].length)); /* * Check for alignment with front and back of the entry. */ - matchfront = (char *)dup - (char *)d == offset; - matchback = (char *)dup + oldlen - (char *)d == offset + len; + matchfront = (char *)dup - (char *)hdr == offset; + matchback = (char *)dup + oldlen - (char *)hdr == offset + len; ASSERT(*needscanp == 0); needscan = 0; /* @@ -734,9 +740,9 @@ xfs_dir2_data_use_free( */ if (matchfront && matchback) { if (dfp) { - needscan = (d->hdr.bestfree[2].offset != 0); + needscan = (hdr->bestfree[2].offset != 0); if (!needscan) - xfs_dir2_data_freeremove(d, dfp, needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); } } /* @@ -744,27 +750,27 @@ xfs_dir2_data_use_free( * Make a new entry with the remaining freespace. */ else if (matchfront) { - newdup = (xfs_dir2_data_unused_t *)((char *)d + offset + len); + newdup = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len); newdup->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); newdup->length = cpu_to_be16(oldlen - len); *xfs_dir2_data_unused_tag_p(newdup) = - cpu_to_be16((char *)newdup - (char *)d); + cpu_to_be16((char *)newdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, newdup); /* * If it was in the table, remove it and add the new one. */ if (dfp) { - xfs_dir2_data_freeremove(d, dfp, needlogp); - dfp = xfs_dir2_data_freeinsert(d, newdup, needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); + dfp = xfs_dir2_data_freeinsert(hdr, newdup, needlogp); ASSERT(dfp != NULL); ASSERT(dfp->length == newdup->length); - ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)d); + ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr); /* * If we got inserted at the last slot, * that means we don't know if there was a better * choice for the last slot, or not. Rescan. */ - needscan = dfp == &d->hdr.bestfree[2]; + needscan = dfp == &hdr->bestfree[2]; } } /* @@ -773,25 +779,25 @@ xfs_dir2_data_use_free( */ else if (matchback) { newdup = dup; - newdup->length = cpu_to_be16(((char *)d + offset) - (char *)newdup); + newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup); *xfs_dir2_data_unused_tag_p(newdup) = - cpu_to_be16((char *)newdup - (char *)d); + cpu_to_be16((char *)newdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, newdup); /* * If it was in the table, remove it and add the new one. */ if (dfp) { - xfs_dir2_data_freeremove(d, dfp, needlogp); - dfp = xfs_dir2_data_freeinsert(d, newdup, needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); + dfp = xfs_dir2_data_freeinsert(hdr, newdup, needlogp); ASSERT(dfp != NULL); ASSERT(dfp->length == newdup->length); - ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)d); + ASSERT(be16_to_cpu(dfp->offset) == (char *)newdup - (char *)hdr); /* * If we got inserted at the last slot, * that means we don't know if there was a better * choice for the last slot, or not. Rescan. */ - needscan = dfp == &d->hdr.bestfree[2]; + needscan = dfp == &hdr->bestfree[2]; } } /* @@ -800,15 +806,15 @@ xfs_dir2_data_use_free( */ else { newdup = dup; - newdup->length = cpu_to_be16(((char *)d + offset) - (char *)newdup); + newdup->length = cpu_to_be16(((char *)hdr + offset) - (char *)newdup); *xfs_dir2_data_unused_tag_p(newdup) = - cpu_to_be16((char *)newdup - (char *)d); + cpu_to_be16((char *)newdup - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, newdup); - newdup2 = (xfs_dir2_data_unused_t *)((char *)d + offset + len); + newdup2 = (xfs_dir2_data_unused_t *)((char *)hdr + offset + len); newdup2->freetag = cpu_to_be16(XFS_DIR2_DATA_FREE_TAG); newdup2->length = cpu_to_be16(oldlen - len - be16_to_cpu(newdup->length)); *xfs_dir2_data_unused_tag_p(newdup2) = - cpu_to_be16((char *)newdup2 - (char *)d); + cpu_to_be16((char *)newdup2 - (char *)hdr); xfs_dir2_data_log_unused(tp, bp, newdup2); /* * If the old entry was in the table, we need to scan @@ -819,13 +825,12 @@ xfs_dir2_data_use_free( * the 2 new will work. */ if (dfp) { - needscan = (d->hdr.bestfree[2].length != 0); + needscan = (hdr->bestfree[2].length != 0); if (!needscan) { - xfs_dir2_data_freeremove(d, dfp, needlogp); - (void)xfs_dir2_data_freeinsert(d, newdup, - needlogp); - (void)xfs_dir2_data_freeinsert(d, newdup2, - needlogp); + xfs_dir2_data_freeremove(hdr, dfp, needlogp); + xfs_dir2_data_freeinsert(hdr, newdup, needlogp); + xfs_dir2_data_freeinsert(hdr, newdup2, + needlogp); } } } diff --git a/fs/xfs/xfs_dir2_data.h b/fs/xfs/xfs_dir2_data.h deleted file mode 100644 index efbc290..0000000 --- a/fs/xfs/xfs_dir2_data.h +++ /dev/null @@ -1,184 +0,0 @@ -/* - * Copyright (c) 2000,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_DIR2_DATA_H__ -#define __XFS_DIR2_DATA_H__ - -/* - * Directory format 2, data block structures. - */ - -struct xfs_dabuf; -struct xfs_da_args; -struct xfs_inode; -struct xfs_trans; - -/* - * Constants. - */ -#define XFS_DIR2_DATA_MAGIC 0x58443244 /* XD2D: for multiblock dirs */ -#define XFS_DIR2_DATA_ALIGN_LOG 3 /* i.e., 8 bytes */ -#define XFS_DIR2_DATA_ALIGN (1 << XFS_DIR2_DATA_ALIGN_LOG) -#define XFS_DIR2_DATA_FREE_TAG 0xffff -#define XFS_DIR2_DATA_FD_COUNT 3 - -/* - * Directory address space divided into sections, - * spaces separated by 32GB. - */ -#define XFS_DIR2_SPACE_SIZE (1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG)) -#define XFS_DIR2_DATA_SPACE 0 -#define XFS_DIR2_DATA_OFFSET (XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE) -#define XFS_DIR2_DATA_FIRSTDB(mp) \ - xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET) - -/* - * Offsets of . and .. in data space (always block 0) - */ -#define XFS_DIR2_DATA_DOT_OFFSET \ - ((xfs_dir2_data_aoff_t)sizeof(xfs_dir2_data_hdr_t)) -#define XFS_DIR2_DATA_DOTDOT_OFFSET \ - (XFS_DIR2_DATA_DOT_OFFSET + xfs_dir2_data_entsize(1)) -#define XFS_DIR2_DATA_FIRST_OFFSET \ - (XFS_DIR2_DATA_DOTDOT_OFFSET + xfs_dir2_data_entsize(2)) - -/* - * Structures. - */ - -/* - * Describe a free area in the data block. - * The freespace will be formatted as a xfs_dir2_data_unused_t. - */ -typedef struct xfs_dir2_data_free { - __be16 offset; /* start of freespace */ - __be16 length; /* length of freespace */ -} xfs_dir2_data_free_t; - -/* - * Header for the data blocks. - * Always at the beginning of a directory-sized block. - * The code knows that XFS_DIR2_DATA_FD_COUNT is 3. - */ -typedef struct xfs_dir2_data_hdr { - __be32 magic; /* XFS_DIR2_DATA_MAGIC */ - /* or XFS_DIR2_BLOCK_MAGIC */ - xfs_dir2_data_free_t bestfree[XFS_DIR2_DATA_FD_COUNT]; -} xfs_dir2_data_hdr_t; - -/* - * Active entry in a data block. Aligned to 8 bytes. - * Tag appears as the last 2 bytes. - */ -typedef struct xfs_dir2_data_entry { - __be64 inumber; /* inode number */ - __u8 namelen; /* name length */ - __u8 name[1]; /* name bytes, no null */ - /* variable offset */ - __be16 tag; /* starting offset of us */ -} xfs_dir2_data_entry_t; - -/* - * Unused entry in a data block. Aligned to 8 bytes. - * Tag appears as the last 2 bytes. - */ -typedef struct xfs_dir2_data_unused { - __be16 freetag; /* XFS_DIR2_DATA_FREE_TAG */ - __be16 length; /* total free length */ - /* variable offset */ - __be16 tag; /* starting offset of us */ -} xfs_dir2_data_unused_t; - -typedef union { - xfs_dir2_data_entry_t entry; - xfs_dir2_data_unused_t unused; -} xfs_dir2_data_union_t; - -/* - * Generic data block structure, for xfs_db. - */ -typedef struct xfs_dir2_data { - xfs_dir2_data_hdr_t hdr; /* magic XFS_DIR2_DATA_MAGIC */ - xfs_dir2_data_union_t u[1]; -} xfs_dir2_data_t; - -/* - * Macros. - */ - -/* - * Size of a data entry. - */ -static inline int xfs_dir2_data_entsize(int n) -{ - return (int)roundup(offsetof(xfs_dir2_data_entry_t, name[0]) + (n) + \ - (uint)sizeof(xfs_dir2_data_off_t), XFS_DIR2_DATA_ALIGN); -} - -/* - * Pointer to an entry's tag word. - */ -static inline __be16 * -xfs_dir2_data_entry_tag_p(xfs_dir2_data_entry_t *dep) -{ - return (__be16 *)((char *)dep + - xfs_dir2_data_entsize(dep->namelen) - sizeof(__be16)); -} - -/* - * Pointer to a freespace's tag word. - */ -static inline __be16 * -xfs_dir2_data_unused_tag_p(xfs_dir2_data_unused_t *dup) -{ - return (__be16 *)((char *)dup + - be16_to_cpu(dup->length) - sizeof(__be16)); -} - -/* - * Function declarations. - */ -#ifdef DEBUG -extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_dabuf *bp); -#else -#define xfs_dir2_data_check(dp,bp) -#endif -extern xfs_dir2_data_free_t *xfs_dir2_data_freefind(xfs_dir2_data_t *d, - xfs_dir2_data_unused_t *dup); -extern xfs_dir2_data_free_t *xfs_dir2_data_freeinsert(xfs_dir2_data_t *d, - xfs_dir2_data_unused_t *dup, int *loghead); -extern void xfs_dir2_data_freescan(struct xfs_mount *mp, xfs_dir2_data_t *d, - int *loghead); -extern int xfs_dir2_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno, - struct xfs_dabuf **bpp); -extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_dabuf *bp, - xfs_dir2_data_entry_t *dep); -extern void xfs_dir2_data_log_header(struct xfs_trans *tp, - struct xfs_dabuf *bp); -extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_dabuf *bp, - xfs_dir2_data_unused_t *dup); -extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_dabuf *bp, - xfs_dir2_data_aoff_t offset, - xfs_dir2_data_aoff_t len, int *needlogp, - int *needscanp); -extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_dabuf *bp, - xfs_dir2_data_unused_t *dup, - xfs_dir2_data_aoff_t offset, - xfs_dir2_data_aoff_t len, int *needlogp, - int *needscanp); - -#endif /* __XFS_DIR2_DATA_H__ */ diff --git a/fs/xfs/xfs_dir2_format.h b/fs/xfs/xfs_dir2_format.h new file mode 100644 index 0000000..0727098 --- /dev/null +++ b/fs/xfs/xfs_dir2_format.h @@ -0,0 +1,597 @@ +/* + * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#ifndef __XFS_DIR2_FORMAT_H__ +#define __XFS_DIR2_FORMAT_H__ + +/* + * Directory version 2. + * + * There are 4 possible formats: + * - shortform - embedded into the inode + * - single block - data with embedded leaf at the end + * - multiple data blocks, single leaf+freeindex block + * - data blocks, node and leaf blocks (btree), freeindex blocks + * + * Note: many node blocks structures and constants are shared with the attr + * code and defined in xfs_da_btree.h. + */ + +#define XFS_DIR2_BLOCK_MAGIC 0x58443242 /* XD2B: single block dirs */ +#define XFS_DIR2_DATA_MAGIC 0x58443244 /* XD2D: multiblock dirs */ +#define XFS_DIR2_FREE_MAGIC 0x58443246 /* XD2F: free index blocks */ + +/* + * Byte offset in data block and shortform entry. + */ +typedef __uint16_t xfs_dir2_data_off_t; +#define NULLDATAOFF 0xffffU +typedef uint xfs_dir2_data_aoff_t; /* argument form */ + +/* + * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t. + * Only need 16 bits, this is the byte offset into the single block form. + */ +typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t; + +/* + * Offset in data space of a data entry. + */ +typedef __uint32_t xfs_dir2_dataptr_t; +#define XFS_DIR2_MAX_DATAPTR ((xfs_dir2_dataptr_t)0xffffffff) +#define XFS_DIR2_NULL_DATAPTR ((xfs_dir2_dataptr_t)0) + +/* + * Byte offset in a directory. + */ +typedef xfs_off_t xfs_dir2_off_t; + +/* + * Directory block number (logical dirblk in file) + */ +typedef __uint32_t xfs_dir2_db_t; + +/* + * Inode number stored as 8 8-bit values. + */ +typedef struct { __uint8_t i[8]; } xfs_dir2_ino8_t; + +/* + * Inode number stored as 4 8-bit values. + * Works a lot of the time, when all the inode numbers in a directory + * fit in 32 bits. + */ +typedef struct { __uint8_t i[4]; } xfs_dir2_ino4_t; + +typedef union { + xfs_dir2_ino8_t i8; + xfs_dir2_ino4_t i4; +} xfs_dir2_inou_t; +#define XFS_DIR2_MAX_SHORT_INUM ((xfs_ino_t)0xffffffffULL) + +/* + * Directory layout when stored internal to an inode. + * + * Small directories are packed as tightly as possible so as to fit into the + * literal area of the inode. These "shortform" directories consist of a + * single xfs_dir2_sf_hdr header followed by zero or more xfs_dir2_sf_entry + * structures. Due the different inode number storage size and the variable + * length name field in the xfs_dir2_sf_entry all these structure are + * variable length, and the accessors in this file should be used to iterate + * over them. + */ +typedef struct xfs_dir2_sf_hdr { + __uint8_t count; /* count of entries */ + __uint8_t i8count; /* count of 8-byte inode #s */ + xfs_dir2_inou_t parent; /* parent dir inode number */ +} __arch_pack xfs_dir2_sf_hdr_t; + +typedef struct xfs_dir2_sf_entry { + __u8 namelen; /* actual name length */ + xfs_dir2_sf_off_t offset; /* saved offset */ + __u8 name[]; /* name, variable size */ + /* + * A xfs_dir2_ino8_t or xfs_dir2_ino4_t follows here, at a + * variable offset after the name. + */ +} __arch_pack xfs_dir2_sf_entry_t; + +static inline int xfs_dir2_sf_hdr_size(int i8count) +{ + return sizeof(struct xfs_dir2_sf_hdr) - + (i8count == 0) * + (sizeof(xfs_dir2_ino8_t) - sizeof(xfs_dir2_ino4_t)); +} + +static inline xfs_dir2_data_aoff_t +xfs_dir2_sf_get_offset(xfs_dir2_sf_entry_t *sfep) +{ + return get_unaligned_be16(&sfep->offset.i); +} + +static inline void +xfs_dir2_sf_put_offset(xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t off) +{ + put_unaligned_be16(off, &sfep->offset.i); +} + +static inline int +xfs_dir2_sf_entsize(struct xfs_dir2_sf_hdr *hdr, int len) +{ + return sizeof(struct xfs_dir2_sf_entry) + /* namelen + offset */ + len + /* name */ + (hdr->i8count ? /* ino */ + sizeof(xfs_dir2_ino8_t) : + sizeof(xfs_dir2_ino4_t)); +} + +static inline struct xfs_dir2_sf_entry * +xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr) +{ + return (struct xfs_dir2_sf_entry *) + ((char *)hdr + xfs_dir2_sf_hdr_size(hdr->i8count)); +} + +static inline struct xfs_dir2_sf_entry * +xfs_dir2_sf_nextentry(struct xfs_dir2_sf_hdr *hdr, + struct xfs_dir2_sf_entry *sfep) +{ + return (struct xfs_dir2_sf_entry *) + ((char *)sfep + xfs_dir2_sf_entsize(hdr, sfep->namelen)); +} + + +/* + * Data block structures. + * + * A pure data block looks like the following drawing on disk: + * + * +-------------------------------------------------+ + * | xfs_dir2_data_hdr_t | + * +-------------------------------------------------+ + * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t | + * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t | + * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t | + * | ... | + * +-------------------------------------------------+ + * | unused space | + * +-------------------------------------------------+ + * + * As all the entries are variable size structures the accessors below should + * be used to iterate over them. + * + * In addition to the pure data blocks for the data and node formats, + * most structures are also used for the combined data/freespace "block" + * format below. + */ + +#define XFS_DIR2_DATA_ALIGN_LOG 3 /* i.e., 8 bytes */ +#define XFS_DIR2_DATA_ALIGN (1 << XFS_DIR2_DATA_ALIGN_LOG) +#define XFS_DIR2_DATA_FREE_TAG 0xffff +#define XFS_DIR2_DATA_FD_COUNT 3 + +/* + * Directory address space divided into sections, + * spaces separated by 32GB. + */ +#define XFS_DIR2_SPACE_SIZE (1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG)) +#define XFS_DIR2_DATA_SPACE 0 +#define XFS_DIR2_DATA_OFFSET (XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE) +#define XFS_DIR2_DATA_FIRSTDB(mp) \ + xfs_dir2_byte_to_db(mp, XFS_DIR2_DATA_OFFSET) + +/* + * Offsets of . and .. in data space (always block 0) + */ +#define XFS_DIR2_DATA_DOT_OFFSET \ + ((xfs_dir2_data_aoff_t)sizeof(struct xfs_dir2_data_hdr)) +#define XFS_DIR2_DATA_DOTDOT_OFFSET \ + (XFS_DIR2_DATA_DOT_OFFSET + xfs_dir2_data_entsize(1)) +#define XFS_DIR2_DATA_FIRST_OFFSET \ + (XFS_DIR2_DATA_DOTDOT_OFFSET + xfs_dir2_data_entsize(2)) + +/* + * Describe a free area in the data block. + * + * The freespace will be formatted as a xfs_dir2_data_unused_t. + */ +typedef struct xfs_dir2_data_free { + __be16 offset; /* start of freespace */ + __be16 length; /* length of freespace */ +} xfs_dir2_data_free_t; + +/* + * Header for the data blocks. + * + * The code knows that XFS_DIR2_DATA_FD_COUNT is 3. + */ +typedef struct xfs_dir2_data_hdr { + __be32 magic; /* XFS_DIR2_DATA_MAGIC or */ + /* XFS_DIR2_BLOCK_MAGIC */ + xfs_dir2_data_free_t bestfree[XFS_DIR2_DATA_FD_COUNT]; +} xfs_dir2_data_hdr_t; + +/* + * Active entry in a data block. + * + * Aligned to 8 bytes. After the variable length name field there is a + * 2 byte tag field, which can be accessed using xfs_dir2_data_entry_tag_p. + */ +typedef struct xfs_dir2_data_entry { + __be64 inumber; /* inode number */ + __u8 namelen; /* name length */ + __u8 name[]; /* name bytes, no null */ + /* __be16 tag; */ /* starting offset of us */ +} xfs_dir2_data_entry_t; + +/* + * Unused entry in a data block. + * + * Aligned to 8 bytes. Tag appears as the last 2 bytes and must be accessed + * using xfs_dir2_data_unused_tag_p. + */ +typedef struct xfs_dir2_data_unused { + __be16 freetag; /* XFS_DIR2_DATA_FREE_TAG */ + __be16 length; /* total free length */ + /* variable offset */ + __be16 tag; /* starting offset of us */ +} xfs_dir2_data_unused_t; + +/* + * Size of a data entry. + */ +static inline int xfs_dir2_data_entsize(int n) +{ + return (int)roundup(offsetof(struct xfs_dir2_data_entry, name[0]) + n + + (uint)sizeof(xfs_dir2_data_off_t), XFS_DIR2_DATA_ALIGN); +} + +/* + * Pointer to an entry's tag word. + */ +static inline __be16 * +xfs_dir2_data_entry_tag_p(struct xfs_dir2_data_entry *dep) +{ + return (__be16 *)((char *)dep + + xfs_dir2_data_entsize(dep->namelen) - sizeof(__be16)); +} + +/* + * Pointer to a freespace's tag word. + */ +static inline __be16 * +xfs_dir2_data_unused_tag_p(struct xfs_dir2_data_unused *dup) +{ + return (__be16 *)((char *)dup + + be16_to_cpu(dup->length) - sizeof(__be16)); +} + +/* + * Leaf block structures. + * + * A pure leaf block looks like the following drawing on disk: + * + * +---------------------------+ + * | xfs_dir2_leaf_hdr_t | + * +---------------------------+ + * | xfs_dir2_leaf_entry_t | + * | xfs_dir2_leaf_entry_t | + * | xfs_dir2_leaf_entry_t | + * | xfs_dir2_leaf_entry_t | + * | ... | + * +---------------------------+ + * | xfs_dir2_data_off_t | + * | xfs_dir2_data_off_t | + * | xfs_dir2_data_off_t | + * | ... | + * +---------------------------+ + * | xfs_dir2_leaf_tail_t | + * +---------------------------+ + * + * The xfs_dir2_data_off_t members (bests) and tail are at the end of the block + * for single-leaf (magic = XFS_DIR2_LEAF1_MAGIC) blocks only, but not present + * for directories with separate leaf nodes and free space blocks + * (magic = XFS_DIR2_LEAFN_MAGIC). + * + * As all the entries are variable size structures the accessors below should + * be used to iterate over them. + */ + +/* + * Offset of the leaf/node space. First block in this space + * is the btree root. + */ +#define XFS_DIR2_LEAF_SPACE 1 +#define XFS_DIR2_LEAF_OFFSET (XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE) +#define XFS_DIR2_LEAF_FIRSTDB(mp) \ + xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET) + +/* + * Leaf block header. + */ +typedef struct xfs_dir2_leaf_hdr { + xfs_da_blkinfo_t info; /* header for da routines */ + __be16 count; /* count of entries */ + __be16 stale; /* count of stale entries */ +} xfs_dir2_leaf_hdr_t; + +/* + * Leaf block entry. + */ +typedef struct xfs_dir2_leaf_entry { + __be32 hashval; /* hash value of name */ + __be32 address; /* address of data entry */ +} xfs_dir2_leaf_entry_t; + +/* + * Leaf block tail. + */ +typedef struct xfs_dir2_leaf_tail { + __be32 bestcount; +} xfs_dir2_leaf_tail_t; + +/* + * Leaf block. + */ +typedef struct xfs_dir2_leaf { + xfs_dir2_leaf_hdr_t hdr; /* leaf header */ + xfs_dir2_leaf_entry_t ents[]; /* entries */ +} xfs_dir2_leaf_t; + +/* + * DB blocks here are logical directory block numbers, not filesystem blocks. + */ + +static inline int xfs_dir2_max_leaf_ents(struct xfs_mount *mp) +{ + return (mp->m_dirblksize - (uint)sizeof(struct xfs_dir2_leaf_hdr)) / + (uint)sizeof(struct xfs_dir2_leaf_entry); +} + +/* + * Get address of the bestcount field in the single-leaf block. + */ +static inline struct xfs_dir2_leaf_tail * +xfs_dir2_leaf_tail_p(struct xfs_mount *mp, struct xfs_dir2_leaf *lp) +{ + return (struct xfs_dir2_leaf_tail *) + ((char *)lp + mp->m_dirblksize - + sizeof(struct xfs_dir2_leaf_tail)); +} + +/* + * Get address of the bests array in the single-leaf block. + */ +static inline __be16 * +xfs_dir2_leaf_bests_p(struct xfs_dir2_leaf_tail *ltp) +{ + return (__be16 *)ltp - be32_to_cpu(ltp->bestcount); +} + +/* + * Convert dataptr to byte in file space + */ +static inline xfs_dir2_off_t +xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp) +{ + return (xfs_dir2_off_t)dp << XFS_DIR2_DATA_ALIGN_LOG; +} + +/* + * Convert byte in file space to dataptr. It had better be aligned. + */ +static inline xfs_dir2_dataptr_t +xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by) +{ + return (xfs_dir2_dataptr_t)(by >> XFS_DIR2_DATA_ALIGN_LOG); +} + +/* + * Convert byte in space to (DB) block + */ +static inline xfs_dir2_db_t +xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by) +{ + return (xfs_dir2_db_t) + (by >> (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)); +} + +/* + * Convert dataptr to a block number + */ +static inline xfs_dir2_db_t +xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp) +{ + return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp)); +} + +/* + * Convert byte in space to offset in a block + */ +static inline xfs_dir2_data_aoff_t +xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by) +{ + return (xfs_dir2_data_aoff_t)(by & + ((1 << (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) - 1)); +} + +/* + * Convert dataptr to a byte offset in a block + */ +static inline xfs_dir2_data_aoff_t +xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp) +{ + return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp)); +} + +/* + * Convert block and offset to byte in space + */ +static inline xfs_dir2_off_t +xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db, + xfs_dir2_data_aoff_t o) +{ + return ((xfs_dir2_off_t)db << + (mp->m_sb.sb_blocklog + mp->m_sb.sb_dirblklog)) + o; +} + +/* + * Convert block (DB) to block (dablk) + */ +static inline xfs_dablk_t +xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db) +{ + return (xfs_dablk_t)(db << mp->m_sb.sb_dirblklog); +} + +/* + * Convert byte in space to (DA) block + */ +static inline xfs_dablk_t +xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by) +{ + return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by)); +} + +/* + * Convert block and offset to dataptr + */ +static inline xfs_dir2_dataptr_t +xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db, + xfs_dir2_data_aoff_t o) +{ + return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o)); +} + +/* + * Convert block (dablk) to block (DB) + */ +static inline xfs_dir2_db_t +xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da) +{ + return (xfs_dir2_db_t)(da >> mp->m_sb.sb_dirblklog); +} + +/* + * Convert block (dablk) to byte offset in space + */ +static inline xfs_dir2_off_t +xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da) +{ + return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0); +} + +/* + * Free space block defintions for the node format. + */ + +/* + * Offset of the freespace index. + */ +#define XFS_DIR2_FREE_SPACE 2 +#define XFS_DIR2_FREE_OFFSET (XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE) +#define XFS_DIR2_FREE_FIRSTDB(mp) \ + xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET) + +typedef struct xfs_dir2_free_hdr { + __be32 magic; /* XFS_DIR2_FREE_MAGIC */ + __be32 firstdb; /* db of first entry */ + __be32 nvalid; /* count of valid entries */ + __be32 nused; /* count of used entries */ +} xfs_dir2_free_hdr_t; + +typedef struct xfs_dir2_free { + xfs_dir2_free_hdr_t hdr; /* block header */ + __be16 bests[]; /* best free counts */ + /* unused entries are -1 */ +} xfs_dir2_free_t; + +static inline int xfs_dir2_free_max_bests(struct xfs_mount *mp) +{ + return (mp->m_dirblksize - sizeof(struct xfs_dir2_free_hdr)) / + sizeof(xfs_dir2_data_off_t); +} + +/* + * Convert data space db to the corresponding free db. + */ +static inline xfs_dir2_db_t +xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db) +{ + return XFS_DIR2_FREE_FIRSTDB(mp) + db / xfs_dir2_free_max_bests(mp); +} + +/* + * Convert data space db to the corresponding index in a free db. + */ +static inline int +xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db) +{ + return db % xfs_dir2_free_max_bests(mp); +} + +/* + * Single block format. + * + * The single block format looks like the following drawing on disk: + * + * +-------------------------------------------------+ + * | xfs_dir2_data_hdr_t | + * +-------------------------------------------------+ + * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t | + * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t | + * | xfs_dir2_data_entry_t OR xfs_dir2_data_unused_t : + * | ... | + * +-------------------------------------------------+ + * | unused space | + * +-------------------------------------------------+ + * | ... | + * | xfs_dir2_leaf_entry_t | + * | xfs_dir2_leaf_entry_t | + * +-------------------------------------------------+ + * | xfs_dir2_block_tail_t | + * +-------------------------------------------------+ + * + * As all the entries are variable size structures the accessors below should + * be used to iterate over them. + */ + +typedef struct xfs_dir2_block_tail { + __be32 count; /* count of leaf entries */ + __be32 stale; /* count of stale lf entries */ +} xfs_dir2_block_tail_t; + +/* + * Pointer to the leaf header embedded in a data block (1-block format) + */ +static inline struct xfs_dir2_block_tail * +xfs_dir2_block_tail_p(struct xfs_mount *mp, struct xfs_dir2_data_hdr *hdr) +{ + return ((struct xfs_dir2_block_tail *) + ((char *)hdr + mp->m_dirblksize)) - 1; +} + +/* + * Pointer to the leaf entries embedded in a data block (1-block format) + */ +static inline struct xfs_dir2_leaf_entry * +xfs_dir2_block_leaf_p(struct xfs_dir2_block_tail *btp) +{ + return ((struct xfs_dir2_leaf_entry *)btp) - be32_to_cpu(btp->count); +} + +#endif /* __XFS_DIR2_FORMAT_H__ */ diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index ae89122..ca2386d 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -24,18 +24,14 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_bmap.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" -#include "xfs_dir2_node.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -64,7 +60,7 @@ xfs_dir2_block_to_leaf( { __be16 *bestsp; /* leaf's bestsp entries */ xfs_dablk_t blkno; /* leaf block's bno */ - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_leaf_entry_t *blp; /* block's leaf entries */ xfs_dir2_block_tail_t *btp; /* block's tail */ xfs_inode_t *dp; /* incore directory inode */ @@ -101,9 +97,9 @@ xfs_dir2_block_to_leaf( } ASSERT(lbp != NULL); leaf = lbp->data; - block = dbp->data; + hdr = dbp->data; xfs_dir2_data_check(dp, dbp); - btp = xfs_dir2_block_tail_p(mp, block); + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Set the counts in the leaf header. @@ -123,23 +119,23 @@ xfs_dir2_block_to_leaf( * tail be free. */ xfs_dir2_data_make_free(tp, dbp, - (xfs_dir2_data_aoff_t)((char *)blp - (char *)block), - (xfs_dir2_data_aoff_t)((char *)block + mp->m_dirblksize - + (xfs_dir2_data_aoff_t)((char *)blp - (char *)hdr), + (xfs_dir2_data_aoff_t)((char *)hdr + mp->m_dirblksize - (char *)blp), &needlog, &needscan); /* * Fix up the block header, make it a data block. */ - block->hdr.magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC); + hdr->magic = cpu_to_be32(XFS_DIR2_DATA_MAGIC); if (needscan) - xfs_dir2_data_freescan(mp, (xfs_dir2_data_t *)block, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); /* * Set up leaf tail and bests table. */ ltp = xfs_dir2_leaf_tail_p(mp, leaf); ltp->bestcount = cpu_to_be32(1); bestsp = xfs_dir2_leaf_bests_p(ltp); - bestsp[0] = block->hdr.bestfree[0].length; + bestsp[0] = hdr->bestfree[0].length; /* * Log the data header and leaf bests table. */ @@ -152,6 +148,131 @@ xfs_dir2_block_to_leaf( return 0; } +STATIC void +xfs_dir2_leaf_find_stale( + struct xfs_dir2_leaf *leaf, + int index, + int *lowstale, + int *highstale) +{ + /* + * Find the first stale entry before our index, if any. + */ + for (*lowstale = index - 1; *lowstale >= 0; --*lowstale) { + if (leaf->ents[*lowstale].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) + break; + } + + /* + * Find the first stale entry at or after our index, if any. + * Stop if the result would require moving more entries than using + * lowstale. + */ + for (*highstale = index; + *highstale < be16_to_cpu(leaf->hdr.count); + ++*highstale) { + if (leaf->ents[*highstale].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) + break; + if (*lowstale >= 0 && index - *lowstale <= *highstale - index) + break; + } +} + +struct xfs_dir2_leaf_entry * +xfs_dir2_leaf_find_entry( + xfs_dir2_leaf_t *leaf, /* leaf structure */ + int index, /* leaf table position */ + int compact, /* need to compact leaves */ + int lowstale, /* index of prev stale leaf */ + int highstale, /* index of next stale leaf */ + int *lfloglow, /* low leaf logging index */ + int *lfloghigh) /* high leaf logging index */ +{ + if (!leaf->hdr.stale) { + xfs_dir2_leaf_entry_t *lep; /* leaf entry table pointer */ + + /* + * Now we need to make room to insert the leaf entry. + * + * If there are no stale entries, just insert a hole at index. + */ + lep = &leaf->ents[index]; + if (index < be16_to_cpu(leaf->hdr.count)) + memmove(lep + 1, lep, + (be16_to_cpu(leaf->hdr.count) - index) * + sizeof(*lep)); + + /* + * Record low and high logging indices for the leaf. + */ + *lfloglow = index; + *lfloghigh = be16_to_cpu(leaf->hdr.count); + be16_add_cpu(&leaf->hdr.count, 1); + return lep; + } + + /* + * There are stale entries. + * + * We will use one of them for the new entry. It's probably not at + * the right location, so we'll have to shift some up or down first. + * + * If we didn't compact before, we need to find the nearest stale + * entries before and after our insertion point. + */ + if (compact == 0) + xfs_dir2_leaf_find_stale(leaf, index, &lowstale, &highstale); + + /* + * If the low one is better, use it. + */ + if (lowstale >= 0 && + (highstale == be16_to_cpu(leaf->hdr.count) || + index - lowstale - 1 < highstale - index)) { + ASSERT(index - lowstale - 1 >= 0); + ASSERT(leaf->ents[lowstale].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)); + + /* + * Copy entries up to cover the stale entry and make room + * for the new entry. + */ + if (index - lowstale - 1 > 0) { + memmove(&leaf->ents[lowstale], + &leaf->ents[lowstale + 1], + (index - lowstale - 1) * + sizeof(xfs_dir2_leaf_entry_t)); + } + *lfloglow = MIN(lowstale, *lfloglow); + *lfloghigh = MAX(index - 1, *lfloghigh); + be16_add_cpu(&leaf->hdr.stale, -1); + return &leaf->ents[index - 1]; + } + + /* + * The high one is better, so use that one. + */ + ASSERT(highstale - index >= 0); + ASSERT(leaf->ents[highstale].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)); + + /* + * Copy entries down to cover the stale entry and make room for the + * new entry. + */ + if (highstale - index > 0) { + memmove(&leaf->ents[index + 1], + &leaf->ents[index], + (highstale - index) * sizeof(xfs_dir2_leaf_entry_t)); + } + *lfloglow = MIN(index, *lfloglow); + *lfloghigh = MAX(highstale, *lfloghigh); + be16_add_cpu(&leaf->hdr.stale, -1); + return &leaf->ents[index]; +} + /* * Add an entry to a leaf form directory. */ @@ -161,7 +282,7 @@ xfs_dir2_leaf_addname( { __be16 *bestsp; /* freespace table in leaf */ int compact; /* need to compact leaves */ - xfs_dir2_data_t *data; /* data block structure */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dabuf_t *dbp; /* data block buffer */ xfs_dir2_data_entry_t *dep; /* data block entry */ xfs_inode_t *dp; /* incore directory inode */ @@ -225,7 +346,7 @@ xfs_dir2_leaf_addname( continue; i = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address)); ASSERT(i < be32_to_cpu(ltp->bestcount)); - ASSERT(be16_to_cpu(bestsp[i]) != NULLDATAOFF); + ASSERT(bestsp[i] != cpu_to_be16(NULLDATAOFF)); if (be16_to_cpu(bestsp[i]) >= length) { use_block = i; break; @@ -239,7 +360,8 @@ xfs_dir2_leaf_addname( /* * Remember a block we see that's missing. */ - if (be16_to_cpu(bestsp[i]) == NULLDATAOFF && use_block == -1) + if (bestsp[i] == cpu_to_be16(NULLDATAOFF) && + use_block == -1) use_block = i; else if (be16_to_cpu(bestsp[i]) >= length) { use_block = i; @@ -250,14 +372,17 @@ xfs_dir2_leaf_addname( /* * How many bytes do we need in the leaf block? */ - needbytes = - (leaf->hdr.stale ? 0 : (uint)sizeof(leaf->ents[0])) + - (use_block != -1 ? 0 : (uint)sizeof(leaf->bests[0])); + needbytes = 0; + if (!leaf->hdr.stale) + needbytes += sizeof(xfs_dir2_leaf_entry_t); + if (use_block == -1) + needbytes += sizeof(xfs_dir2_data_off_t); + /* * Now kill use_block if it refers to a missing block, so we * can use it as an indication of allocation needed. */ - if (use_block != -1 && be16_to_cpu(bestsp[use_block]) == NULLDATAOFF) + if (use_block != -1 && bestsp[use_block] == cpu_to_be16(NULLDATAOFF)) use_block = -1; /* * If we don't have enough free bytes but we can make enough @@ -369,8 +494,8 @@ xfs_dir2_leaf_addname( */ else xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block); - data = dbp->data; - bestsp[use_block] = data->hdr.bestfree[0].length; + hdr = dbp->data; + bestsp[use_block] = hdr->bestfree[0].length; grown = 1; } /* @@ -384,7 +509,7 @@ xfs_dir2_leaf_addname( xfs_da_brelse(tp, lbp); return error; } - data = dbp->data; + hdr = dbp->data; grown = 0; } xfs_dir2_data_check(dp, dbp); @@ -392,14 +517,14 @@ xfs_dir2_leaf_addname( * Point to the biggest freespace in our data block. */ dup = (xfs_dir2_data_unused_t *) - ((char *)data + be16_to_cpu(data->hdr.bestfree[0].offset)); + ((char *)hdr + be16_to_cpu(hdr->bestfree[0].offset)); ASSERT(be16_to_cpu(dup->length) >= length); needscan = needlog = 0; /* * Mark the initial part of our freespace in use for the new entry. */ xfs_dir2_data_use_free(tp, dbp, dup, - (xfs_dir2_data_aoff_t)((char *)dup - (char *)data), length, + (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length, &needlog, &needscan); /* * Initialize our new entry (at last). @@ -409,12 +534,12 @@ xfs_dir2_leaf_addname( dep->namelen = args->namelen; memcpy(dep->name, args->name, dep->namelen); tagp = xfs_dir2_data_entry_tag_p(dep); - *tagp = cpu_to_be16((char *)dep - (char *)data); + *tagp = cpu_to_be16((char *)dep - (char *)hdr); /* * Need to scan fix up the bestfree table. */ if (needscan) - xfs_dir2_data_freescan(mp, data, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); /* * Need to log the data block's header. */ @@ -425,107 +550,15 @@ xfs_dir2_leaf_addname( * If the bests table needs to be changed, do it. * Log the change unless we've already done that. */ - if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(data->hdr.bestfree[0].length)) { - bestsp[use_block] = data->hdr.bestfree[0].length; + if (be16_to_cpu(bestsp[use_block]) != be16_to_cpu(hdr->bestfree[0].length)) { + bestsp[use_block] = hdr->bestfree[0].length; if (!grown) xfs_dir2_leaf_log_bests(tp, lbp, use_block, use_block); } - /* - * Now we need to make room to insert the leaf entry. - * If there are no stale entries, we just insert a hole at index. - */ - if (!leaf->hdr.stale) { - /* - * lep is still good as the index leaf entry. - */ - if (index < be16_to_cpu(leaf->hdr.count)) - memmove(lep + 1, lep, - (be16_to_cpu(leaf->hdr.count) - index) * sizeof(*lep)); - /* - * Record low and high logging indices for the leaf. - */ - lfloglow = index; - lfloghigh = be16_to_cpu(leaf->hdr.count); - be16_add_cpu(&leaf->hdr.count, 1); - } - /* - * There are stale entries. - * We will use one of them for the new entry. - * It's probably not at the right location, so we'll have to - * shift some up or down first. - */ - else { - /* - * If we didn't compact before, we need to find the nearest - * stale entries before and after our insertion point. - */ - if (compact == 0) { - /* - * Find the first stale entry before the insertion - * point, if any. - */ - for (lowstale = index - 1; - lowstale >= 0 && - be32_to_cpu(leaf->ents[lowstale].address) != - XFS_DIR2_NULL_DATAPTR; - lowstale--) - continue; - /* - * Find the next stale entry at or after the insertion - * point, if any. Stop if we go so far that the - * lowstale entry would be better. - */ - for (highstale = index; - highstale < be16_to_cpu(leaf->hdr.count) && - be32_to_cpu(leaf->ents[highstale].address) != - XFS_DIR2_NULL_DATAPTR && - (lowstale < 0 || - index - lowstale - 1 >= highstale - index); - highstale++) - continue; - } - /* - * If the low one is better, use it. - */ - if (lowstale >= 0 && - (highstale == be16_to_cpu(leaf->hdr.count) || - index - lowstale - 1 < highstale - index)) { - ASSERT(index - lowstale - 1 >= 0); - ASSERT(be32_to_cpu(leaf->ents[lowstale].address) == - XFS_DIR2_NULL_DATAPTR); - /* - * Copy entries up to cover the stale entry - * and make room for the new entry. - */ - if (index - lowstale - 1 > 0) - memmove(&leaf->ents[lowstale], - &leaf->ents[lowstale + 1], - (index - lowstale - 1) * sizeof(*lep)); - lep = &leaf->ents[index - 1]; - lfloglow = MIN(lowstale, lfloglow); - lfloghigh = MAX(index - 1, lfloghigh); - } - /* - * The high one is better, so use that one. - */ - else { - ASSERT(highstale - index >= 0); - ASSERT(be32_to_cpu(leaf->ents[highstale].address) == - XFS_DIR2_NULL_DATAPTR); - /* - * Copy entries down to cover the stale entry - * and make room for the new entry. - */ - if (highstale - index > 0) - memmove(&leaf->ents[index + 1], - &leaf->ents[index], - (highstale - index) * sizeof(*lep)); - lep = &leaf->ents[index]; - lfloglow = MIN(index, lfloglow); - lfloghigh = MAX(highstale, lfloghigh); - } - be16_add_cpu(&leaf->hdr.stale, -1); - } + + lep = xfs_dir2_leaf_find_entry(leaf, index, compact, lowstale, + highstale, &lfloglow, &lfloghigh); + /* * Fill in the new leaf entry. */ @@ -562,7 +595,7 @@ xfs_dir2_leaf_check( leaf = bp->data; mp = dp->i_mount; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAF1_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC)); /* * This value is not restrictive enough. * Should factor in the size of the bests table as well. @@ -582,7 +615,7 @@ xfs_dir2_leaf_check( if (i + 1 < be16_to_cpu(leaf->hdr.count)) ASSERT(be32_to_cpu(leaf->ents[i].hashval) <= be32_to_cpu(leaf->ents[i + 1].hashval)); - if (be32_to_cpu(leaf->ents[i].address) == XFS_DIR2_NULL_DATAPTR) + if (leaf->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; } ASSERT(be16_to_cpu(leaf->hdr.stale) == stale); @@ -611,7 +644,8 @@ xfs_dir2_leaf_compact( * Compress out the stale entries in place. */ for (from = to = 0, loglow = -1; from < be16_to_cpu(leaf->hdr.count); from++) { - if (be32_to_cpu(leaf->ents[from].address) == XFS_DIR2_NULL_DATAPTR) + if (leaf->ents[from].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) continue; /* * Only actually copy the entries that are different. @@ -663,24 +697,9 @@ xfs_dir2_leaf_compact_x1( leaf = bp->data; ASSERT(be16_to_cpu(leaf->hdr.stale) > 1); index = *indexp; - /* - * Find the first stale entry before our index, if any. - */ - for (lowstale = index - 1; - lowstale >= 0 && - be32_to_cpu(leaf->ents[lowstale].address) != XFS_DIR2_NULL_DATAPTR; - lowstale--) - continue; - /* - * Find the first stale entry at or after our index, if any. - * Stop if the answer would be worse than lowstale. - */ - for (highstale = index; - highstale < be16_to_cpu(leaf->hdr.count) && - be32_to_cpu(leaf->ents[highstale].address) != XFS_DIR2_NULL_DATAPTR && - (lowstale < 0 || index - lowstale > highstale - index); - highstale++) - continue; + + xfs_dir2_leaf_find_stale(leaf, index, &lowstale, &highstale); + /* * Pick the better of lowstale and highstale. */ @@ -701,7 +720,8 @@ xfs_dir2_leaf_compact_x1( if (index == from) newindex = to; if (from != keepstale && - be32_to_cpu(leaf->ents[from].address) == XFS_DIR2_NULL_DATAPTR) { + leaf->ents[from].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) { if (from == to) *lowlogp = to; continue; @@ -760,7 +780,7 @@ xfs_dir2_leaf_getdents( int byteoff; /* offset in current block */ xfs_dir2_db_t curdb; /* db for current block */ xfs_dir2_off_t curoff; /* current overall offset */ - xfs_dir2_data_t *data; /* data block structure */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_data_entry_t *dep; /* data entry */ xfs_dir2_data_unused_t *dup; /* unused entry */ int error = 0; /* error return value */ @@ -1018,23 +1038,23 @@ xfs_dir2_leaf_getdents( else if (curoff > newoff) ASSERT(xfs_dir2_byte_to_db(mp, curoff) == curdb); - data = bp->data; + hdr = bp->data; xfs_dir2_data_check(dp, bp); /* * Find our position in the block. */ - ptr = (char *)&data->u; + ptr = (char *)(hdr + 1); byteoff = xfs_dir2_byte_to_off(mp, curoff); /* * Skip past the header. */ if (byteoff == 0) - curoff += (uint)sizeof(data->hdr); + curoff += (uint)sizeof(*hdr); /* * Skip past entries until we reach our offset. */ else { - while ((char *)ptr - (char *)data < byteoff) { + while ((char *)ptr - (char *)hdr < byteoff) { dup = (xfs_dir2_data_unused_t *)ptr; if (be16_to_cpu(dup->freetag) @@ -1055,8 +1075,8 @@ xfs_dir2_leaf_getdents( curoff = xfs_dir2_db_off_to_byte(mp, xfs_dir2_byte_to_db(mp, curoff), - (char *)ptr - (char *)data); - if (ptr >= (char *)data + mp->m_dirblksize) { + (char *)ptr - (char *)hdr); + if (ptr >= (char *)hdr + mp->m_dirblksize) { continue; } } @@ -1179,7 +1199,7 @@ xfs_dir2_leaf_log_bests( xfs_dir2_leaf_tail_t *ltp; /* leaf tail structure */ leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAF1_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC)); ltp = xfs_dir2_leaf_tail_p(tp->t_mountp, leaf); firstb = xfs_dir2_leaf_bests_p(ltp) + first; lastb = xfs_dir2_leaf_bests_p(ltp) + last; @@ -1202,8 +1222,8 @@ xfs_dir2_leaf_log_ents( xfs_dir2_leaf_t *leaf; /* leaf structure */ leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAF1_MAGIC || - be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) || + leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); firstlep = &leaf->ents[first]; lastlep = &leaf->ents[last]; xfs_da_log_buf(tp, bp, (uint)((char *)firstlep - (char *)leaf), @@ -1221,8 +1241,8 @@ xfs_dir2_leaf_log_header( xfs_dir2_leaf_t *leaf; /* leaf structure */ leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAF1_MAGIC || - be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC) || + leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); xfs_da_log_buf(tp, bp, (uint)((char *)&leaf->hdr - (char *)leaf), (uint)(sizeof(leaf->hdr) - 1)); } @@ -1241,7 +1261,7 @@ xfs_dir2_leaf_log_tail( mp = tp->t_mountp; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAF1_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAF1_MAGIC)); ltp = xfs_dir2_leaf_tail_p(mp, leaf); xfs_da_log_buf(tp, bp, (uint)((char *)ltp - (char *)leaf), (uint)(mp->m_dirblksize - 1)); @@ -1437,7 +1457,7 @@ xfs_dir2_leaf_removename( xfs_da_args_t *args) /* operation arguments */ { __be16 *bestsp; /* leaf block best freespace */ - xfs_dir2_data_t *data; /* data block structure */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_db_t db; /* data block number */ xfs_dabuf_t *dbp; /* data block buffer */ xfs_dir2_data_entry_t *dep; /* data entry structure */ @@ -1467,7 +1487,7 @@ xfs_dir2_leaf_removename( tp = args->trans; mp = dp->i_mount; leaf = lbp->data; - data = dbp->data; + hdr = dbp->data; xfs_dir2_data_check(dp, dbp); /* * Point to the leaf entry, use that to point to the data entry. @@ -1475,9 +1495,9 @@ xfs_dir2_leaf_removename( lep = &leaf->ents[index]; db = xfs_dir2_dataptr_to_db(mp, be32_to_cpu(lep->address)); dep = (xfs_dir2_data_entry_t *) - ((char *)data + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address))); + ((char *)hdr + xfs_dir2_dataptr_to_off(mp, be32_to_cpu(lep->address))); needscan = needlog = 0; - oldbest = be16_to_cpu(data->hdr.bestfree[0].length); + oldbest = be16_to_cpu(hdr->bestfree[0].length); ltp = xfs_dir2_leaf_tail_p(mp, leaf); bestsp = xfs_dir2_leaf_bests_p(ltp); ASSERT(be16_to_cpu(bestsp[db]) == oldbest); @@ -1485,7 +1505,7 @@ xfs_dir2_leaf_removename( * Mark the former data entry unused. */ xfs_dir2_data_make_free(tp, dbp, - (xfs_dir2_data_aoff_t)((char *)dep - (char *)data), + (xfs_dir2_data_aoff_t)((char *)dep - (char *)hdr), xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan); /* * We just mark the leaf entry stale by putting a null in it. @@ -1499,23 +1519,23 @@ xfs_dir2_leaf_removename( * log the data block header if necessary. */ if (needscan) - xfs_dir2_data_freescan(mp, data, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(tp, dbp); /* * If the longest freespace in the data block has changed, * put the new value in the bests table and log that. */ - if (be16_to_cpu(data->hdr.bestfree[0].length) != oldbest) { - bestsp[db] = data->hdr.bestfree[0].length; + if (be16_to_cpu(hdr->bestfree[0].length) != oldbest) { + bestsp[db] = hdr->bestfree[0].length; xfs_dir2_leaf_log_bests(tp, lbp, db, db); } xfs_dir2_data_check(dp, dbp); /* * If the data block is now empty then get rid of the data block. */ - if (be16_to_cpu(data->hdr.bestfree[0].length) == - mp->m_dirblksize - (uint)sizeof(data->hdr)) { + if (be16_to_cpu(hdr->bestfree[0].length) == + mp->m_dirblksize - (uint)sizeof(*hdr)) { ASSERT(db != mp->m_dirdatablk); if ((error = xfs_dir2_shrink_inode(args, db, dbp))) { /* @@ -1542,7 +1562,7 @@ xfs_dir2_leaf_removename( * Look for the last active entry (i). */ for (i = db - 1; i > 0; i--) { - if (be16_to_cpu(bestsp[i]) != NULLDATAOFF) + if (bestsp[i] != cpu_to_be16(NULLDATAOFF)) break; } /* @@ -1686,9 +1706,6 @@ xfs_dir2_leaf_trim_data( xfs_dir2_db_t db) /* data block number */ { __be16 *bestsp; /* leaf bests table */ -#ifdef DEBUG - xfs_dir2_data_t *data; /* data block structure */ -#endif xfs_dabuf_t *dbp; /* data block buffer */ xfs_inode_t *dp; /* incore directory inode */ int error; /* error return value */ @@ -1707,20 +1724,21 @@ xfs_dir2_leaf_trim_data( XFS_DATA_FORK))) { return error; } -#ifdef DEBUG - data = dbp->data; - ASSERT(be32_to_cpu(data->hdr.magic) == XFS_DIR2_DATA_MAGIC); -#endif - /* this seems to be an error - * data is only valid if DEBUG is defined? - * RMC 09/08/1999 - */ leaf = lbp->data; ltp = xfs_dir2_leaf_tail_p(mp, leaf); - ASSERT(be16_to_cpu(data->hdr.bestfree[0].length) == - mp->m_dirblksize - (uint)sizeof(data->hdr)); + +#ifdef DEBUG +{ + struct xfs_dir2_data_hdr *hdr = dbp->data; + + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC)); + ASSERT(be16_to_cpu(hdr->bestfree[0].length) == + mp->m_dirblksize - (uint)sizeof(*hdr)); ASSERT(db == be32_to_cpu(ltp->bestcount) - 1); +} +#endif + /* * Get rid of the data block. */ @@ -1740,6 +1758,20 @@ xfs_dir2_leaf_trim_data( return 0; } +static inline size_t +xfs_dir2_leaf_size( + struct xfs_dir2_leaf_hdr *hdr, + int counts) +{ + int entries; + + entries = be16_to_cpu(hdr->count) - be16_to_cpu(hdr->stale); + return sizeof(xfs_dir2_leaf_hdr_t) + + entries * sizeof(xfs_dir2_leaf_entry_t) + + counts * sizeof(xfs_dir2_data_off_t) + + sizeof(xfs_dir2_leaf_tail_t); +} + /* * Convert node form directory to leaf form directory. * The root of the node form dir needs to already be a LEAFN block. @@ -1810,7 +1842,7 @@ xfs_dir2_node_to_leaf( return 0; lbp = state->path.blk[0].bp; leaf = lbp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); /* * Read the freespace block. */ @@ -1819,20 +1851,19 @@ xfs_dir2_node_to_leaf( return error; } free = fbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); ASSERT(!free->hdr.firstdb); + /* * Now see if the leafn and free data will fit in a leaf1. * If not, release the buffer and give up. */ - if ((uint)sizeof(leaf->hdr) + - (be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale)) * (uint)sizeof(leaf->ents[0]) + - be32_to_cpu(free->hdr.nvalid) * (uint)sizeof(leaf->bests[0]) + - (uint)sizeof(leaf->tail) > - mp->m_dirblksize) { + if (xfs_dir2_leaf_size(&leaf->hdr, be32_to_cpu(free->hdr.nvalid)) > + mp->m_dirblksize) { xfs_da_brelse(tp, fbp); return 0; } + /* * If the leaf has any stale entries in it, compress them out. * The compact routine will log the header. @@ -1851,7 +1882,7 @@ xfs_dir2_node_to_leaf( * Set up the leaf bests table. */ memcpy(xfs_dir2_leaf_bests_p(ltp), free->bests, - be32_to_cpu(ltp->bestcount) * sizeof(leaf->bests[0])); + be32_to_cpu(ltp->bestcount) * sizeof(xfs_dir2_data_off_t)); xfs_dir2_leaf_log_bests(tp, lbp, 0, be32_to_cpu(ltp->bestcount) - 1); xfs_dir2_leaf_log_tail(tp, lbp); xfs_dir2_leaf_check(dp, lbp); diff --git a/fs/xfs/xfs_dir2_leaf.h b/fs/xfs/xfs_dir2_leaf.h deleted file mode 100644 index 6c9539f..0000000 --- a/fs/xfs/xfs_dir2_leaf.h +++ /dev/null @@ -1,253 +0,0 @@ -/* - * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_DIR2_LEAF_H__ -#define __XFS_DIR2_LEAF_H__ - -struct uio; -struct xfs_dabuf; -struct xfs_da_args; -struct xfs_inode; -struct xfs_mount; -struct xfs_trans; - -/* - * Offset of the leaf/node space. First block in this space - * is the btree root. - */ -#define XFS_DIR2_LEAF_SPACE 1 -#define XFS_DIR2_LEAF_OFFSET (XFS_DIR2_LEAF_SPACE * XFS_DIR2_SPACE_SIZE) -#define XFS_DIR2_LEAF_FIRSTDB(mp) \ - xfs_dir2_byte_to_db(mp, XFS_DIR2_LEAF_OFFSET) - -/* - * Offset in data space of a data entry. - */ -typedef __uint32_t xfs_dir2_dataptr_t; -#define XFS_DIR2_MAX_DATAPTR ((xfs_dir2_dataptr_t)0xffffffff) -#define XFS_DIR2_NULL_DATAPTR ((xfs_dir2_dataptr_t)0) - -/* - * Leaf block header. - */ -typedef struct xfs_dir2_leaf_hdr { - xfs_da_blkinfo_t info; /* header for da routines */ - __be16 count; /* count of entries */ - __be16 stale; /* count of stale entries */ -} xfs_dir2_leaf_hdr_t; - -/* - * Leaf block entry. - */ -typedef struct xfs_dir2_leaf_entry { - __be32 hashval; /* hash value of name */ - __be32 address; /* address of data entry */ -} xfs_dir2_leaf_entry_t; - -/* - * Leaf block tail. - */ -typedef struct xfs_dir2_leaf_tail { - __be32 bestcount; -} xfs_dir2_leaf_tail_t; - -/* - * Leaf block. - * bests and tail are at the end of the block for single-leaf only - * (magic = XFS_DIR2_LEAF1_MAGIC not XFS_DIR2_LEAFN_MAGIC). - */ -typedef struct xfs_dir2_leaf { - xfs_dir2_leaf_hdr_t hdr; /* leaf header */ - xfs_dir2_leaf_entry_t ents[1]; /* entries */ - /* ... */ - xfs_dir2_data_off_t bests[1]; /* best free counts */ - xfs_dir2_leaf_tail_t tail; /* leaf tail */ -} xfs_dir2_leaf_t; - -/* - * DB blocks here are logical directory block numbers, not filesystem blocks. - */ - -static inline int xfs_dir2_max_leaf_ents(struct xfs_mount *mp) -{ - return (int)(((mp)->m_dirblksize - (uint)sizeof(xfs_dir2_leaf_hdr_t)) / - (uint)sizeof(xfs_dir2_leaf_entry_t)); -} - -/* - * Get address of the bestcount field in the single-leaf block. - */ -static inline xfs_dir2_leaf_tail_t * -xfs_dir2_leaf_tail_p(struct xfs_mount *mp, xfs_dir2_leaf_t *lp) -{ - return (xfs_dir2_leaf_tail_t *) - ((char *)(lp) + (mp)->m_dirblksize - - (uint)sizeof(xfs_dir2_leaf_tail_t)); -} - -/* - * Get address of the bests array in the single-leaf block. - */ -static inline __be16 * -xfs_dir2_leaf_bests_p(xfs_dir2_leaf_tail_t *ltp) -{ - return (__be16 *)ltp - be32_to_cpu(ltp->bestcount); -} - -/* - * Convert dataptr to byte in file space - */ -static inline xfs_dir2_off_t -xfs_dir2_dataptr_to_byte(struct xfs_mount *mp, xfs_dir2_dataptr_t dp) -{ - return (xfs_dir2_off_t)(dp) << XFS_DIR2_DATA_ALIGN_LOG; -} - -/* - * Convert byte in file space to dataptr. It had better be aligned. - */ -static inline xfs_dir2_dataptr_t -xfs_dir2_byte_to_dataptr(struct xfs_mount *mp, xfs_dir2_off_t by) -{ - return (xfs_dir2_dataptr_t)((by) >> XFS_DIR2_DATA_ALIGN_LOG); -} - -/* - * Convert byte in space to (DB) block - */ -static inline xfs_dir2_db_t -xfs_dir2_byte_to_db(struct xfs_mount *mp, xfs_dir2_off_t by) -{ - return (xfs_dir2_db_t)((by) >> \ - ((mp)->m_sb.sb_blocklog + (mp)->m_sb.sb_dirblklog)); -} - -/* - * Convert dataptr to a block number - */ -static inline xfs_dir2_db_t -xfs_dir2_dataptr_to_db(struct xfs_mount *mp, xfs_dir2_dataptr_t dp) -{ - return xfs_dir2_byte_to_db(mp, xfs_dir2_dataptr_to_byte(mp, dp)); -} - -/* - * Convert byte in space to offset in a block - */ -static inline xfs_dir2_data_aoff_t -xfs_dir2_byte_to_off(struct xfs_mount *mp, xfs_dir2_off_t by) -{ - return (xfs_dir2_data_aoff_t)((by) & \ - ((1 << ((mp)->m_sb.sb_blocklog + (mp)->m_sb.sb_dirblklog)) - 1)); -} - -/* - * Convert dataptr to a byte offset in a block - */ -static inline xfs_dir2_data_aoff_t -xfs_dir2_dataptr_to_off(struct xfs_mount *mp, xfs_dir2_dataptr_t dp) -{ - return xfs_dir2_byte_to_off(mp, xfs_dir2_dataptr_to_byte(mp, dp)); -} - -/* - * Convert block and offset to byte in space - */ -static inline xfs_dir2_off_t -xfs_dir2_db_off_to_byte(struct xfs_mount *mp, xfs_dir2_db_t db, - xfs_dir2_data_aoff_t o) -{ - return ((xfs_dir2_off_t)(db) << \ - ((mp)->m_sb.sb_blocklog + (mp)->m_sb.sb_dirblklog)) + (o); -} - -/* - * Convert block (DB) to block (dablk) - */ -static inline xfs_dablk_t -xfs_dir2_db_to_da(struct xfs_mount *mp, xfs_dir2_db_t db) -{ - return (xfs_dablk_t)((db) << (mp)->m_sb.sb_dirblklog); -} - -/* - * Convert byte in space to (DA) block - */ -static inline xfs_dablk_t -xfs_dir2_byte_to_da(struct xfs_mount *mp, xfs_dir2_off_t by) -{ - return xfs_dir2_db_to_da(mp, xfs_dir2_byte_to_db(mp, by)); -} - -/* - * Convert block and offset to dataptr - */ -static inline xfs_dir2_dataptr_t -xfs_dir2_db_off_to_dataptr(struct xfs_mount *mp, xfs_dir2_db_t db, - xfs_dir2_data_aoff_t o) -{ - return xfs_dir2_byte_to_dataptr(mp, xfs_dir2_db_off_to_byte(mp, db, o)); -} - -/* - * Convert block (dablk) to block (DB) - */ -static inline xfs_dir2_db_t -xfs_dir2_da_to_db(struct xfs_mount *mp, xfs_dablk_t da) -{ - return (xfs_dir2_db_t)((da) >> (mp)->m_sb.sb_dirblklog); -} - -/* - * Convert block (dablk) to byte offset in space - */ -static inline xfs_dir2_off_t -xfs_dir2_da_to_byte(struct xfs_mount *mp, xfs_dablk_t da) -{ - return xfs_dir2_db_off_to_byte(mp, xfs_dir2_da_to_db(mp, da), 0); -} - -/* - * Function declarations. - */ -extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args, - struct xfs_dabuf *dbp); -extern int xfs_dir2_leaf_addname(struct xfs_da_args *args); -extern void xfs_dir2_leaf_compact(struct xfs_da_args *args, - struct xfs_dabuf *bp); -extern void xfs_dir2_leaf_compact_x1(struct xfs_dabuf *bp, int *indexp, - int *lowstalep, int *highstalep, - int *lowlogp, int *highlogp); -extern int xfs_dir2_leaf_getdents(struct xfs_inode *dp, void *dirent, - size_t bufsize, xfs_off_t *offset, - filldir_t filldir); -extern int xfs_dir2_leaf_init(struct xfs_da_args *args, xfs_dir2_db_t bno, - struct xfs_dabuf **bpp, int magic); -extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_dabuf *bp, - int first, int last); -extern void xfs_dir2_leaf_log_header(struct xfs_trans *tp, - struct xfs_dabuf *bp); -extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args); -extern int xfs_dir2_leaf_removename(struct xfs_da_args *args); -extern int xfs_dir2_leaf_replace(struct xfs_da_args *args); -extern int xfs_dir2_leaf_search_hash(struct xfs_da_args *args, - struct xfs_dabuf *lbp); -extern int xfs_dir2_leaf_trim_data(struct xfs_da_args *args, - struct xfs_dabuf *lbp, xfs_dir2_db_t db); -extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state); - -#endif /* __XFS_DIR2_LEAF_H__ */ diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c index a0aab7d..084b324 100644 --- a/fs/xfs/xfs_dir2_node.c +++ b/fs/xfs/xfs_dir2_node.c @@ -23,18 +23,14 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_bmap.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" -#include "xfs_dir2_node.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -73,7 +69,7 @@ xfs_dir2_free_log_bests( xfs_dir2_free_t *free; /* freespace structure */ free = bp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); xfs_da_log_buf(tp, bp, (uint)((char *)&free->bests[first] - (char *)free), (uint)((char *)&free->bests[last] - (char *)free + @@ -91,7 +87,7 @@ xfs_dir2_free_log_header( xfs_dir2_free_t *free; /* freespace structure */ free = bp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); xfs_da_log_buf(tp, bp, (uint)((char *)&free->hdr - (char *)free), (uint)(sizeof(xfs_dir2_free_hdr_t) - 1)); } @@ -244,89 +240,13 @@ xfs_dir2_leafn_add( lfloglow = be16_to_cpu(leaf->hdr.count); lfloghigh = -1; } - /* - * No stale entries, just insert a space for the new entry. - */ - if (!leaf->hdr.stale) { - lep = &leaf->ents[index]; - if (index < be16_to_cpu(leaf->hdr.count)) - memmove(lep + 1, lep, - (be16_to_cpu(leaf->hdr.count) - index) * sizeof(*lep)); - lfloglow = index; - lfloghigh = be16_to_cpu(leaf->hdr.count); - be16_add_cpu(&leaf->hdr.count, 1); - } - /* - * There are stale entries. We'll use one for the new entry. - */ - else { - /* - * If we didn't do a compact then we need to figure out - * which stale entry will be used. - */ - if (compact == 0) { - /* - * Find first stale entry before our insertion point. - */ - for (lowstale = index - 1; - lowstale >= 0 && - be32_to_cpu(leaf->ents[lowstale].address) != - XFS_DIR2_NULL_DATAPTR; - lowstale--) - continue; - /* - * Find next stale entry after insertion point. - * Stop looking if the answer would be worse than - * lowstale already found. - */ - for (highstale = index; - highstale < be16_to_cpu(leaf->hdr.count) && - be32_to_cpu(leaf->ents[highstale].address) != - XFS_DIR2_NULL_DATAPTR && - (lowstale < 0 || - index - lowstale - 1 >= highstale - index); - highstale++) - continue; - } - /* - * Using the low stale entry. - * Shift entries up toward the stale slot. - */ - if (lowstale >= 0 && - (highstale == be16_to_cpu(leaf->hdr.count) || - index - lowstale - 1 < highstale - index)) { - ASSERT(be32_to_cpu(leaf->ents[lowstale].address) == - XFS_DIR2_NULL_DATAPTR); - ASSERT(index - lowstale - 1 >= 0); - if (index - lowstale - 1 > 0) - memmove(&leaf->ents[lowstale], - &leaf->ents[lowstale + 1], - (index - lowstale - 1) * sizeof(*lep)); - lep = &leaf->ents[index - 1]; - lfloglow = MIN(lowstale, lfloglow); - lfloghigh = MAX(index - 1, lfloghigh); - } - /* - * Using the high stale entry. - * Shift entries down toward the stale slot. - */ - else { - ASSERT(be32_to_cpu(leaf->ents[highstale].address) == - XFS_DIR2_NULL_DATAPTR); - ASSERT(highstale - index >= 0); - if (highstale - index > 0) - memmove(&leaf->ents[index + 1], - &leaf->ents[index], - (highstale - index) * sizeof(*lep)); - lep = &leaf->ents[index]; - lfloglow = MIN(index, lfloglow); - lfloghigh = MAX(highstale, lfloghigh); - } - be16_add_cpu(&leaf->hdr.stale, -1); - } + /* * Insert the new entry, log everything. */ + lep = xfs_dir2_leaf_find_entry(leaf, index, compact, lowstale, + highstale, &lfloglow, &lfloghigh); + lep->hashval = cpu_to_be32(args->hashval); lep->address = cpu_to_be32(xfs_dir2_db_off_to_dataptr(mp, args->blkno, args->index)); @@ -352,14 +272,14 @@ xfs_dir2_leafn_check( leaf = bp->data; mp = dp->i_mount; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); ASSERT(be16_to_cpu(leaf->hdr.count) <= xfs_dir2_max_leaf_ents(mp)); for (i = stale = 0; i < be16_to_cpu(leaf->hdr.count); i++) { if (i + 1 < be16_to_cpu(leaf->hdr.count)) { ASSERT(be32_to_cpu(leaf->ents[i].hashval) <= be32_to_cpu(leaf->ents[i + 1].hashval)); } - if (be32_to_cpu(leaf->ents[i].address) == XFS_DIR2_NULL_DATAPTR) + if (leaf->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; } ASSERT(be16_to_cpu(leaf->hdr.stale) == stale); @@ -378,7 +298,7 @@ xfs_dir2_leafn_lasthash( xfs_dir2_leaf_t *leaf; /* leaf structure */ leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); if (count) *count = be16_to_cpu(leaf->hdr.count); if (!leaf->hdr.count) @@ -417,7 +337,7 @@ xfs_dir2_leafn_lookup_for_addname( tp = args->trans; mp = dp->i_mount; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); #ifdef __KERNEL__ ASSERT(be16_to_cpu(leaf->hdr.count) > 0); #endif @@ -434,7 +354,7 @@ xfs_dir2_leafn_lookup_for_addname( curbp = state->extrablk.bp; curfdb = state->extrablk.blkno; free = curbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); } length = xfs_dir2_data_entsize(args->namelen); /* @@ -488,7 +408,7 @@ xfs_dir2_leafn_lookup_for_addname( ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); ASSERT((be32_to_cpu(free->hdr.firstdb) % - XFS_DIR2_MAX_FREE_BESTS(mp)) == 0); + xfs_dir2_free_max_bests(mp)) == 0); ASSERT(be32_to_cpu(free->hdr.firstdb) <= curdb); ASSERT(curdb < be32_to_cpu(free->hdr.firstdb) + be32_to_cpu(free->hdr.nvalid)); @@ -500,7 +420,8 @@ xfs_dir2_leafn_lookup_for_addname( /* * If it has room, return it. */ - if (unlikely(be16_to_cpu(free->bests[fi]) == NULLDATAOFF)) { + if (unlikely(free->bests[fi] == + cpu_to_be16(NULLDATAOFF))) { XFS_ERROR_REPORT("xfs_dir2_leafn_lookup_int", XFS_ERRLEVEL_LOW, mp); if (curfdb != newfdb) @@ -561,7 +482,7 @@ xfs_dir2_leafn_lookup_for_entry( tp = args->trans; mp = dp->i_mount; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); #ifdef __KERNEL__ ASSERT(be16_to_cpu(leaf->hdr.count) > 0); #endif @@ -742,7 +663,8 @@ xfs_dir2_leafn_moveents( int i; /* temp leaf index */ for (i = start_s, stale = 0; i < start_s + count; i++) { - if (be32_to_cpu(leaf_s->ents[i].address) == XFS_DIR2_NULL_DATAPTR) + if (leaf_s->ents[i].address == + cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; } } else @@ -789,8 +711,8 @@ xfs_dir2_leafn_order( leaf1 = leaf1_bp->data; leaf2 = leaf2_bp->data; - ASSERT(be16_to_cpu(leaf1->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); - ASSERT(be16_to_cpu(leaf2->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); + ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); if (be16_to_cpu(leaf1->hdr.count) > 0 && be16_to_cpu(leaf2->hdr.count) > 0 && (be32_to_cpu(leaf2->ents[0].hashval) < be32_to_cpu(leaf1->ents[0].hashval) || @@ -918,7 +840,7 @@ xfs_dir2_leafn_remove( xfs_da_state_blk_t *dblk, /* data block */ int *rval) /* resulting block needs join */ { - xfs_dir2_data_t *data; /* data block structure */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_db_t db; /* data block number */ xfs_dabuf_t *dbp; /* data block buffer */ xfs_dir2_data_entry_t *dep; /* data block entry */ @@ -938,7 +860,7 @@ xfs_dir2_leafn_remove( tp = args->trans; mp = dp->i_mount; leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); /* * Point to the entry we're removing. */ @@ -963,9 +885,9 @@ xfs_dir2_leafn_remove( * in the data block in case it changes. */ dbp = dblk->bp; - data = dbp->data; - dep = (xfs_dir2_data_entry_t *)((char *)data + off); - longest = be16_to_cpu(data->hdr.bestfree[0].length); + hdr = dbp->data; + dep = (xfs_dir2_data_entry_t *)((char *)hdr + off); + longest = be16_to_cpu(hdr->bestfree[0].length); needlog = needscan = 0; xfs_dir2_data_make_free(tp, dbp, off, xfs_dir2_data_entsize(dep->namelen), &needlog, &needscan); @@ -974,7 +896,7 @@ xfs_dir2_leafn_remove( * Log the data block header if needed. */ if (needscan) - xfs_dir2_data_freescan(mp, data, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); if (needlog) xfs_dir2_data_log_header(tp, dbp); xfs_dir2_data_check(dp, dbp); @@ -982,7 +904,7 @@ xfs_dir2_leafn_remove( * If the longest data block freespace changes, need to update * the corresponding freeblock entry. */ - if (longest < be16_to_cpu(data->hdr.bestfree[0].length)) { + if (longest < be16_to_cpu(hdr->bestfree[0].length)) { int error; /* error return value */ xfs_dabuf_t *fbp; /* freeblock buffer */ xfs_dir2_db_t fdb; /* freeblock block number */ @@ -1000,27 +922,27 @@ xfs_dir2_leafn_remove( return error; } free = fbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); ASSERT(be32_to_cpu(free->hdr.firstdb) == - XFS_DIR2_MAX_FREE_BESTS(mp) * + xfs_dir2_free_max_bests(mp) * (fdb - XFS_DIR2_FREE_FIRSTDB(mp))); /* * Calculate which entry we need to fix. */ findex = xfs_dir2_db_to_fdindex(mp, db); - longest = be16_to_cpu(data->hdr.bestfree[0].length); + longest = be16_to_cpu(hdr->bestfree[0].length); /* * If the data block is now empty we can get rid of it * (usually). */ - if (longest == mp->m_dirblksize - (uint)sizeof(data->hdr)) { + if (longest == mp->m_dirblksize - (uint)sizeof(*hdr)) { /* * Try to punch out the data block. */ error = xfs_dir2_shrink_inode(args, db, dbp); if (error == 0) { dblk->bp = NULL; - data = NULL; + hdr = NULL; } /* * We can get ENOSPC if there's no space reservation. @@ -1036,7 +958,7 @@ xfs_dir2_leafn_remove( * If we got rid of the data block, we can eliminate that entry * in the free block. */ - if (data == NULL) { + if (hdr == NULL) { /* * One less used entry in the free table. */ @@ -1052,7 +974,8 @@ xfs_dir2_leafn_remove( int i; /* free entry index */ for (i = findex - 1; - i >= 0 && be16_to_cpu(free->bests[i]) == NULLDATAOFF; + i >= 0 && + free->bests[i] == cpu_to_be16(NULLDATAOFF); i--) continue; free->hdr.nvalid = cpu_to_be32(i + 1); @@ -1209,7 +1132,7 @@ xfs_dir2_leafn_toosmall( */ blk = &state->path.blk[state->path.active - 1]; info = blk->bp->data; - ASSERT(be16_to_cpu(info->magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(info->magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); leaf = (xfs_dir2_leaf_t *)info; count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale); bytes = (uint)sizeof(leaf->hdr) + count * (uint)sizeof(leaf->ents[0]); @@ -1268,7 +1191,7 @@ xfs_dir2_leafn_toosmall( count = be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale); bytes = state->blocksize - (state->blocksize >> 2); leaf = bp->data; - ASSERT(be16_to_cpu(leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); count += be16_to_cpu(leaf->hdr.count) - be16_to_cpu(leaf->hdr.stale); bytes -= count * (uint)sizeof(leaf->ents[0]); /* @@ -1327,8 +1250,8 @@ xfs_dir2_leafn_unbalance( ASSERT(save_blk->magic == XFS_DIR2_LEAFN_MAGIC); drop_leaf = drop_blk->bp->data; save_leaf = save_blk->bp->data; - ASSERT(be16_to_cpu(drop_leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); - ASSERT(be16_to_cpu(save_leaf->hdr.info.magic) == XFS_DIR2_LEAFN_MAGIC); + ASSERT(drop_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); + ASSERT(save_leaf->hdr.info.magic == cpu_to_be16(XFS_DIR2_LEAFN_MAGIC)); /* * If there are any stale leaf entries, take this opportunity * to purge them. @@ -1432,7 +1355,7 @@ xfs_dir2_node_addname_int( xfs_da_args_t *args, /* operation arguments */ xfs_da_state_blk_t *fblk) /* optional freespace block */ { - xfs_dir2_data_t *data; /* data block structure */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_db_t dbno; /* data block number */ xfs_dabuf_t *dbp; /* data block buffer */ xfs_dir2_data_entry_t *dep; /* data entry pointer */ @@ -1469,7 +1392,7 @@ xfs_dir2_node_addname_int( */ ifbno = fblk->blkno; free = fbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); findex = fblk->index; /* * This means the free entry showed that the data block had @@ -1553,7 +1476,7 @@ xfs_dir2_node_addname_int( continue; } free = fbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); findex = 0; } /* @@ -1680,12 +1603,12 @@ xfs_dir2_node_addname_int( free->hdr.magic = cpu_to_be32(XFS_DIR2_FREE_MAGIC); free->hdr.firstdb = cpu_to_be32( (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) * - XFS_DIR2_MAX_FREE_BESTS(mp)); + xfs_dir2_free_max_bests(mp)); free->hdr.nvalid = 0; free->hdr.nused = 0; } else { free = fbp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); } /* @@ -1697,7 +1620,7 @@ xfs_dir2_node_addname_int( * freespace block, extend that table. */ if (findex >= be32_to_cpu(free->hdr.nvalid)) { - ASSERT(findex < XFS_DIR2_MAX_FREE_BESTS(mp)); + ASSERT(findex < xfs_dir2_free_max_bests(mp)); free->hdr.nvalid = cpu_to_be32(findex + 1); /* * Tag new entry so nused will go up. @@ -1708,7 +1631,7 @@ xfs_dir2_node_addname_int( * If this entry was for an empty data block * (this should always be true) then update the header. */ - if (be16_to_cpu(free->bests[findex]) == NULLDATAOFF) { + if (free->bests[findex] == cpu_to_be16(NULLDATAOFF)) { be32_add_cpu(&free->hdr.nused, 1); xfs_dir2_free_log_header(tp, fbp); } @@ -1717,8 +1640,8 @@ xfs_dir2_node_addname_int( * We haven't allocated the data entry yet so this will * change again. */ - data = dbp->data; - free->bests[findex] = data->hdr.bestfree[0].length; + hdr = dbp->data; + free->bests[findex] = hdr->bestfree[0].length; logfree = 1; } /* @@ -1743,21 +1666,21 @@ xfs_dir2_node_addname_int( xfs_da_buf_done(fbp); return error; } - data = dbp->data; + hdr = dbp->data; logfree = 0; } - ASSERT(be16_to_cpu(data->hdr.bestfree[0].length) >= length); + ASSERT(be16_to_cpu(hdr->bestfree[0].length) >= length); /* * Point to the existing unused space. */ dup = (xfs_dir2_data_unused_t *) - ((char *)data + be16_to_cpu(data->hdr.bestfree[0].offset)); + ((char *)hdr + be16_to_cpu(hdr->bestfree[0].offset)); needscan = needlog = 0; /* * Mark the first part of the unused space, inuse for us. */ xfs_dir2_data_use_free(tp, dbp, dup, - (xfs_dir2_data_aoff_t)((char *)dup - (char *)data), length, + (xfs_dir2_data_aoff_t)((char *)dup - (char *)hdr), length, &needlog, &needscan); /* * Fill in the new entry and log it. @@ -1767,13 +1690,13 @@ xfs_dir2_node_addname_int( dep->namelen = args->namelen; memcpy(dep->name, args->name, dep->namelen); tagp = xfs_dir2_data_entry_tag_p(dep); - *tagp = cpu_to_be16((char *)dep - (char *)data); + *tagp = cpu_to_be16((char *)dep - (char *)hdr); xfs_dir2_data_log_entry(tp, dbp, dep); /* * Rescan the block for bestfree if needed. */ if (needscan) - xfs_dir2_data_freescan(mp, data, &needlog); + xfs_dir2_data_freescan(mp, hdr, &needlog); /* * Log the data block header if needed. */ @@ -1782,8 +1705,8 @@ xfs_dir2_node_addname_int( /* * If the freespace entry is now wrong, update it. */ - if (be16_to_cpu(free->bests[findex]) != be16_to_cpu(data->hdr.bestfree[0].length)) { - free->bests[findex] = data->hdr.bestfree[0].length; + if (be16_to_cpu(free->bests[findex]) != be16_to_cpu(hdr->bestfree[0].length)) { + free->bests[findex] = hdr->bestfree[0].length; logfree = 1; } /* @@ -1933,7 +1856,7 @@ xfs_dir2_node_replace( xfs_da_args_t *args) /* operation arguments */ { xfs_da_state_blk_t *blk; /* leaf block */ - xfs_dir2_data_t *data; /* data block structure */ + xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_data_entry_t *dep; /* data entry changed */ int error; /* error return value */ int i; /* btree level */ @@ -1977,10 +1900,10 @@ xfs_dir2_node_replace( /* * Point to the data entry. */ - data = state->extrablk.bp->data; - ASSERT(be32_to_cpu(data->hdr.magic) == XFS_DIR2_DATA_MAGIC); + hdr = state->extrablk.bp->data; + ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC)); dep = (xfs_dir2_data_entry_t *) - ((char *)data + + ((char *)hdr + xfs_dir2_dataptr_to_off(state->mp, be32_to_cpu(lep->address))); ASSERT(inum != be64_to_cpu(dep->inumber)); /* @@ -2044,7 +1967,7 @@ xfs_dir2_node_trim_free( return 0; } free = bp->data; - ASSERT(be32_to_cpu(free->hdr.magic) == XFS_DIR2_FREE_MAGIC); + ASSERT(free->hdr.magic == cpu_to_be32(XFS_DIR2_FREE_MAGIC)); /* * If there are used entries, there's nothing to do. */ diff --git a/fs/xfs/xfs_dir2_node.h b/fs/xfs/xfs_dir2_node.h deleted file mode 100644 index 82dfe71..0000000 --- a/fs/xfs/xfs_dir2_node.h +++ /dev/null @@ -1,100 +0,0 @@ -/* - * Copyright (c) 2000,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_DIR2_NODE_H__ -#define __XFS_DIR2_NODE_H__ - -/* - * Directory version 2, btree node format structures - */ - -struct uio; -struct xfs_dabuf; -struct xfs_da_args; -struct xfs_da_state; -struct xfs_da_state_blk; -struct xfs_inode; -struct xfs_trans; - -/* - * Offset of the freespace index. - */ -#define XFS_DIR2_FREE_SPACE 2 -#define XFS_DIR2_FREE_OFFSET (XFS_DIR2_FREE_SPACE * XFS_DIR2_SPACE_SIZE) -#define XFS_DIR2_FREE_FIRSTDB(mp) \ - xfs_dir2_byte_to_db(mp, XFS_DIR2_FREE_OFFSET) - -#define XFS_DIR2_FREE_MAGIC 0x58443246 /* XD2F */ - -typedef struct xfs_dir2_free_hdr { - __be32 magic; /* XFS_DIR2_FREE_MAGIC */ - __be32 firstdb; /* db of first entry */ - __be32 nvalid; /* count of valid entries */ - __be32 nused; /* count of used entries */ -} xfs_dir2_free_hdr_t; - -typedef struct xfs_dir2_free { - xfs_dir2_free_hdr_t hdr; /* block header */ - __be16 bests[1]; /* best free counts */ - /* unused entries are -1 */ -} xfs_dir2_free_t; - -#define XFS_DIR2_MAX_FREE_BESTS(mp) \ - (((mp)->m_dirblksize - (uint)sizeof(xfs_dir2_free_hdr_t)) / \ - (uint)sizeof(xfs_dir2_data_off_t)) - -/* - * Convert data space db to the corresponding free db. - */ -static inline xfs_dir2_db_t -xfs_dir2_db_to_fdb(struct xfs_mount *mp, xfs_dir2_db_t db) -{ - return (XFS_DIR2_FREE_FIRSTDB(mp) + (db) / XFS_DIR2_MAX_FREE_BESTS(mp)); -} - -/* - * Convert data space db to the corresponding index in a free db. - */ -static inline int -xfs_dir2_db_to_fdindex(struct xfs_mount *mp, xfs_dir2_db_t db) -{ - return ((db) % XFS_DIR2_MAX_FREE_BESTS(mp)); -} - -extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args, - struct xfs_dabuf *lbp); -extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_dabuf *bp, int *count); -extern int xfs_dir2_leafn_lookup_int(struct xfs_dabuf *bp, - struct xfs_da_args *args, int *indexp, - struct xfs_da_state *state); -extern int xfs_dir2_leafn_order(struct xfs_dabuf *leaf1_bp, - struct xfs_dabuf *leaf2_bp); -extern int xfs_dir2_leafn_split(struct xfs_da_state *state, - struct xfs_da_state_blk *oldblk, - struct xfs_da_state_blk *newblk); -extern int xfs_dir2_leafn_toosmall(struct xfs_da_state *state, int *action); -extern void xfs_dir2_leafn_unbalance(struct xfs_da_state *state, - struct xfs_da_state_blk *drop_blk, - struct xfs_da_state_blk *save_blk); -extern int xfs_dir2_node_addname(struct xfs_da_args *args); -extern int xfs_dir2_node_lookup(struct xfs_da_args *args); -extern int xfs_dir2_node_removename(struct xfs_da_args *args); -extern int xfs_dir2_node_replace(struct xfs_da_args *args); -extern int xfs_dir2_node_trim_free(struct xfs_da_args *args, xfs_fileoff_t fo, - int *rvalp); - -#endif /* __XFS_DIR2_NODE_H__ */ diff --git a/fs/xfs/xfs_dir2_priv.h b/fs/xfs/xfs_dir2_priv.h new file mode 100644 index 0000000..067f403 --- /dev/null +++ b/fs/xfs/xfs_dir2_priv.h @@ -0,0 +1,135 @@ +/* + * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#ifndef __XFS_DIR2_PRIV_H__ +#define __XFS_DIR2_PRIV_H__ + +/* xfs_dir2.c */ +extern int xfs_dir_ino_validate(struct xfs_mount *mp, xfs_ino_t ino); +extern int xfs_dir2_isblock(struct xfs_trans *tp, struct xfs_inode *dp, int *r); +extern int xfs_dir2_isleaf(struct xfs_trans *tp, struct xfs_inode *dp, int *r); +extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space, + xfs_dir2_db_t *dbp); +extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db, + struct xfs_dabuf *bp); +extern int xfs_dir_cilookup_result(struct xfs_da_args *args, + const unsigned char *name, int len); + +/* xfs_dir2_block.c */ +extern int xfs_dir2_block_addname(struct xfs_da_args *args); +extern int xfs_dir2_block_getdents(struct xfs_inode *dp, void *dirent, + xfs_off_t *offset, filldir_t filldir); +extern int xfs_dir2_block_lookup(struct xfs_da_args *args); +extern int xfs_dir2_block_removename(struct xfs_da_args *args); +extern int xfs_dir2_block_replace(struct xfs_da_args *args); +extern int xfs_dir2_leaf_to_block(struct xfs_da_args *args, + struct xfs_dabuf *lbp, struct xfs_dabuf *dbp); + +/* xfs_dir2_data.c */ +#ifdef DEBUG +extern void xfs_dir2_data_check(struct xfs_inode *dp, struct xfs_dabuf *bp); +#else +#define xfs_dir2_data_check(dp,bp) +#endif +extern struct xfs_dir2_data_free * +xfs_dir2_data_freeinsert(struct xfs_dir2_data_hdr *hdr, + struct xfs_dir2_data_unused *dup, int *loghead); +extern void xfs_dir2_data_freescan(struct xfs_mount *mp, + struct xfs_dir2_data_hdr *hdr, int *loghead); +extern int xfs_dir2_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno, + struct xfs_dabuf **bpp); +extern void xfs_dir2_data_log_entry(struct xfs_trans *tp, struct xfs_dabuf *bp, + struct xfs_dir2_data_entry *dep); +extern void xfs_dir2_data_log_header(struct xfs_trans *tp, + struct xfs_dabuf *bp); +extern void xfs_dir2_data_log_unused(struct xfs_trans *tp, struct xfs_dabuf *bp, + struct xfs_dir2_data_unused *dup); +extern void xfs_dir2_data_make_free(struct xfs_trans *tp, struct xfs_dabuf *bp, + xfs_dir2_data_aoff_t offset, xfs_dir2_data_aoff_t len, + int *needlogp, int *needscanp); +extern void xfs_dir2_data_use_free(struct xfs_trans *tp, struct xfs_dabuf *bp, + struct xfs_dir2_data_unused *dup, xfs_dir2_data_aoff_t offset, + xfs_dir2_data_aoff_t len, int *needlogp, int *needscanp); + +/* xfs_dir2_leaf.c */ +extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args, + struct xfs_dabuf *dbp); +extern int xfs_dir2_leaf_addname(struct xfs_da_args *args); +extern void xfs_dir2_leaf_compact(struct xfs_da_args *args, + struct xfs_dabuf *bp); +extern void xfs_dir2_leaf_compact_x1(struct xfs_dabuf *bp, int *indexp, + int *lowstalep, int *highstalep, int *lowlogp, int *highlogp); +extern int xfs_dir2_leaf_getdents(struct xfs_inode *dp, void *dirent, + size_t bufsize, xfs_off_t *offset, filldir_t filldir); +extern int xfs_dir2_leaf_init(struct xfs_da_args *args, xfs_dir2_db_t bno, + struct xfs_dabuf **bpp, int magic); +extern void xfs_dir2_leaf_log_ents(struct xfs_trans *tp, struct xfs_dabuf *bp, + int first, int last); +extern void xfs_dir2_leaf_log_header(struct xfs_trans *tp, + struct xfs_dabuf *bp); +extern int xfs_dir2_leaf_lookup(struct xfs_da_args *args); +extern int xfs_dir2_leaf_removename(struct xfs_da_args *args); +extern int xfs_dir2_leaf_replace(struct xfs_da_args *args); +extern int xfs_dir2_leaf_search_hash(struct xfs_da_args *args, + struct xfs_dabuf *lbp); +extern int xfs_dir2_leaf_trim_data(struct xfs_da_args *args, + struct xfs_dabuf *lbp, xfs_dir2_db_t db); +extern struct xfs_dir2_leaf_entry * +xfs_dir2_leaf_find_entry(struct xfs_dir2_leaf *leaf, int index, int compact, + int lowstale, int highstale, + int *lfloglow, int *lfloghigh); +extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state); + +/* xfs_dir2_node.c */ +extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args, + struct xfs_dabuf *lbp); +extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_dabuf *bp, int *count); +extern int xfs_dir2_leafn_lookup_int(struct xfs_dabuf *bp, + struct xfs_da_args *args, int *indexp, + struct xfs_da_state *state); +extern int xfs_dir2_leafn_order(struct xfs_dabuf *leaf1_bp, + struct xfs_dabuf *leaf2_bp); +extern int xfs_dir2_leafn_split(struct xfs_da_state *state, + struct xfs_da_state_blk *oldblk, struct xfs_da_state_blk *newblk); +extern int xfs_dir2_leafn_toosmall(struct xfs_da_state *state, int *action); +extern void xfs_dir2_leafn_unbalance(struct xfs_da_state *state, + struct xfs_da_state_blk *drop_blk, + struct xfs_da_state_blk *save_blk); +extern int xfs_dir2_node_addname(struct xfs_da_args *args); +extern int xfs_dir2_node_lookup(struct xfs_da_args *args); +extern int xfs_dir2_node_removename(struct xfs_da_args *args); +extern int xfs_dir2_node_replace(struct xfs_da_args *args); +extern int xfs_dir2_node_trim_free(struct xfs_da_args *args, xfs_fileoff_t fo, + int *rvalp); + +/* xfs_dir2_sf.c */ +extern xfs_ino_t xfs_dir2_sf_get_parent_ino(struct xfs_dir2_sf_hdr *sfp); +extern xfs_ino_t xfs_dir2_sfe_get_ino(struct xfs_dir2_sf_hdr *sfp, + struct xfs_dir2_sf_entry *sfep); +extern int xfs_dir2_block_sfsize(struct xfs_inode *dp, + struct xfs_dir2_data_hdr *block, struct xfs_dir2_sf_hdr *sfhp); +extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_dabuf *bp, + int size, xfs_dir2_sf_hdr_t *sfhp); +extern int xfs_dir2_sf_addname(struct xfs_da_args *args); +extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino); +extern int xfs_dir2_sf_getdents(struct xfs_inode *dp, void *dirent, + xfs_off_t *offset, filldir_t filldir); +extern int xfs_dir2_sf_lookup(struct xfs_da_args *args); +extern int xfs_dir2_sf_removename(struct xfs_da_args *args); +extern int xfs_dir2_sf_replace(struct xfs_da_args *args); + +#endif /* __XFS_DIR2_PRIV_H__ */ diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c index b1bae6b..79d05e8 100644 --- a/fs/xfs/xfs_dir2_sf.c +++ b/fs/xfs/xfs_dir2_sf.c @@ -23,18 +23,16 @@ #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" -#include "xfs_dir2.h" #include "xfs_mount.h" #include "xfs_da_btree.h" #include "xfs_bmap_btree.h" -#include "xfs_dir2_sf.h" #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_inode_item.h" #include "xfs_error.h" -#include "xfs_dir2_data.h" -#include "xfs_dir2_leaf.h" -#include "xfs_dir2_block.h" +#include "xfs_dir2.h" +#include "xfs_dir2_format.h" +#include "xfs_dir2_priv.h" #include "xfs_trace.h" /* @@ -60,6 +58,82 @@ static void xfs_dir2_sf_toino8(xfs_da_args_t *args); #endif /* XFS_BIG_INUMS */ /* + * Inode numbers in short-form directories can come in two versions, + * either 4 bytes or 8 bytes wide. These helpers deal with the + * two forms transparently by looking at the headers i8count field. + * + * For 64-bit inode number the most significant byte must be zero. + */ +static xfs_ino_t +xfs_dir2_sf_get_ino( + struct xfs_dir2_sf_hdr *hdr, + xfs_dir2_inou_t *from) +{ + if (hdr->i8count) + return get_unaligned_be64(&from->i8.i) & 0x00ffffffffffffffULL; + else + return get_unaligned_be32(&from->i4.i); +} + +static void +xfs_dir2_sf_put_ino( + struct xfs_dir2_sf_hdr *hdr, + xfs_dir2_inou_t *to, + xfs_ino_t ino) +{ + ASSERT((ino & 0xff00000000000000ULL) == 0); + + if (hdr->i8count) + put_unaligned_be64(ino, &to->i8.i); + else + put_unaligned_be32(ino, &to->i4.i); +} + +xfs_ino_t +xfs_dir2_sf_get_parent_ino( + struct xfs_dir2_sf_hdr *hdr) +{ + return xfs_dir2_sf_get_ino(hdr, &hdr->parent); +} + +static void +xfs_dir2_sf_put_parent_ino( + struct xfs_dir2_sf_hdr *hdr, + xfs_ino_t ino) +{ + xfs_dir2_sf_put_ino(hdr, &hdr->parent, ino); +} + +/* + * In short-form directory entries the inode numbers are stored at variable + * offset behind the entry name. The inode numbers may only be accessed + * through the helpers below. + */ +static xfs_dir2_inou_t * +xfs_dir2_sfe_inop( + struct xfs_dir2_sf_entry *sfep) +{ + return (xfs_dir2_inou_t *)&sfep->name[sfep->namelen]; +} + +xfs_ino_t +xfs_dir2_sfe_get_ino( + struct xfs_dir2_sf_hdr *hdr, + struct xfs_dir2_sf_entry *sfep) +{ + return xfs_dir2_sf_get_ino(hdr, xfs_dir2_sfe_inop(sfep)); +} + +static void +xfs_dir2_sfe_put_ino( + struct xfs_dir2_sf_hdr *hdr, + struct xfs_dir2_sf_entry *sfep, + xfs_ino_t ino) +{ + xfs_dir2_sf_put_ino(hdr, xfs_dir2_sfe_inop(sfep), ino); +} + +/* * Given a block directory (dp/block), calculate its size as a shortform (sf) * directory and a header for the sf directory, if it will fit it the * space currently present in the inode. If it won't fit, the output @@ -68,7 +142,7 @@ static void xfs_dir2_sf_toino8(xfs_da_args_t *args); int /* size for sf form */ xfs_dir2_block_sfsize( xfs_inode_t *dp, /* incore inode pointer */ - xfs_dir2_block_t *block, /* block directory data */ + xfs_dir2_data_hdr_t *hdr, /* block directory data */ xfs_dir2_sf_hdr_t *sfhp) /* output: header for sf form */ { xfs_dir2_dataptr_t addr; /* data entry address */ @@ -88,7 +162,7 @@ xfs_dir2_block_sfsize( mp = dp->i_mount; count = i8count = namelen = 0; - btp = xfs_dir2_block_tail_p(mp, block); + btp = xfs_dir2_block_tail_p(mp, hdr); blp = xfs_dir2_block_leaf_p(btp); /* @@ -101,7 +175,7 @@ xfs_dir2_block_sfsize( * Calculate the pointer to the entry at hand. */ dep = (xfs_dir2_data_entry_t *) - ((char *)block + xfs_dir2_dataptr_to_off(mp, addr)); + ((char *)hdr + xfs_dir2_dataptr_to_off(mp, addr)); /* * Detect . and .., so we can special-case them. * . is not included in sf directories. @@ -138,7 +212,7 @@ xfs_dir2_block_sfsize( */ sfhp->count = count; sfhp->i8count = i8count; - xfs_dir2_sf_put_inumber((xfs_dir2_sf_t *)sfhp, &parent, &sfhp->parent); + xfs_dir2_sf_put_parent_ino(sfhp, parent); return size; } @@ -153,7 +227,7 @@ xfs_dir2_block_to_sf( int size, /* shortform directory size */ xfs_dir2_sf_hdr_t *sfhp) /* shortform directory hdr */ { - xfs_dir2_block_t *block; /* block structure */ + xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_block_tail_t *btp; /* block tail pointer */ xfs_dir2_data_entry_t *dep; /* data entry pointer */ xfs_inode_t *dp; /* incore directory inode */ @@ -164,8 +238,7 @@ xfs_dir2_block_to_sf( xfs_mount_t *mp; /* filesystem mount point */ char *ptr; /* current data pointer */ xfs_dir2_sf_entry_t *sfep; /* shortform entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ - xfs_ino_t temp; + xfs_dir2_sf_hdr_t *sfp; /* shortform directory header */ trace_xfs_dir2_block_to_sf(args); @@ -176,13 +249,14 @@ xfs_dir2_block_to_sf( * Make a copy of the block data, so we can shrink the inode * and add local data. */ - block = kmem_alloc(mp->m_dirblksize, KM_SLEEP); - memcpy(block, bp->data, mp->m_dirblksize); + hdr = kmem_alloc(mp->m_dirblksize, KM_SLEEP); + memcpy(hdr, bp->data, mp->m_dirblksize); logflags = XFS_ILOG_CORE; if ((error = xfs_dir2_shrink_inode(args, mp->m_dirdatablk, bp))) { ASSERT(error != ENOSPC); goto out; } + /* * The buffer is now unconditionally gone, whether * xfs_dir2_shrink_inode worked or not. @@ -198,14 +272,14 @@ xfs_dir2_block_to_sf( /* * Copy the header into the newly allocate local space. */ - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; memcpy(sfp, sfhp, xfs_dir2_sf_hdr_size(sfhp->i8count)); dp->i_d.di_size = size; /* * Set up to loop over the block's entries. */ - btp = xfs_dir2_block_tail_p(mp, block); - ptr = (char *)block->u; + btp = xfs_dir2_block_tail_p(mp, hdr); + ptr = (char *)(hdr + 1); endptr = (char *)xfs_dir2_block_leaf_p(btp); sfep = xfs_dir2_sf_firstentry(sfp); /* @@ -233,7 +307,7 @@ xfs_dir2_block_to_sf( else if (dep->namelen == 2 && dep->name[0] == '.' && dep->name[1] == '.') ASSERT(be64_to_cpu(dep->inumber) == - xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent)); + xfs_dir2_sf_get_parent_ino(sfp)); /* * Normal entry, copy it into shortform. */ @@ -241,11 +315,11 @@ xfs_dir2_block_to_sf( sfep->namelen = dep->namelen; xfs_dir2_sf_put_offset(sfep, (xfs_dir2_data_aoff_t) - ((char *)dep - (char *)block)); + ((char *)dep - (char *)hdr)); memcpy(sfep->name, dep->name, dep->namelen); - temp = be64_to_cpu(dep->inumber); - xfs_dir2_sf_put_inumber(sfp, &temp, - xfs_dir2_sf_inumberp(sfep)); + xfs_dir2_sfe_put_ino(sfp, sfep, + be64_to_cpu(dep->inumber)); + sfep = xfs_dir2_sf_nextentry(sfp, sfep); } ptr += xfs_dir2_data_entsize(dep->namelen); @@ -254,7 +328,7 @@ xfs_dir2_block_to_sf( xfs_dir2_sf_check(args); out: xfs_trans_log_inode(args->trans, dp, logflags); - kmem_free(block); + kmem_free(hdr); return error; } @@ -277,7 +351,7 @@ xfs_dir2_sf_addname( xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */ int old_isize; /* di_size before adding name */ int pick; /* which algorithm to use */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ xfs_dir2_sf_entry_t *sfep = NULL; /* shortform entry */ trace_xfs_dir2_sf_addname(args); @@ -294,19 +368,19 @@ xfs_dir2_sf_addname( } ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count)); + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Compute entry (and change in) size. */ - add_entsize = xfs_dir2_sf_entsize_byname(sfp, args->namelen); + add_entsize = xfs_dir2_sf_entsize(sfp, args->namelen); incr_isize = add_entsize; objchange = 0; #if XFS_BIG_INUMS /* * Do we have to change to 8 byte inodes? */ - if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->hdr.i8count == 0) { + if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { /* * Yes, adjust the entry size and the total size. */ @@ -314,7 +388,7 @@ xfs_dir2_sf_addname( (uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t); incr_isize += - (sfp->hdr.count + 2) * + (sfp->count + 2) * ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t)); objchange = 1; @@ -384,21 +458,21 @@ xfs_dir2_sf_addname_easy( { int byteoff; /* byte offset in sf dir */ xfs_inode_t *dp; /* incore directory inode */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ dp = args->dp; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; byteoff = (int)((char *)sfep - (char *)sfp); /* * Grow the in-inode space. */ - xfs_idata_realloc(dp, xfs_dir2_sf_entsize_byname(sfp, args->namelen), + xfs_idata_realloc(dp, xfs_dir2_sf_entsize(sfp, args->namelen), XFS_DATA_FORK); /* * Need to set up again due to realloc of the inode data. */ - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff); /* * Fill in the new entry. @@ -406,15 +480,14 @@ xfs_dir2_sf_addname_easy( sfep->namelen = args->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, args->name, sfep->namelen); - xfs_dir2_sf_put_inumber(sfp, &args->inumber, - xfs_dir2_sf_inumberp(sfep)); + xfs_dir2_sfe_put_ino(sfp, sfep, args->inumber); /* * Update the header and inode. */ - sfp->hdr.count++; + sfp->count++; #if XFS_BIG_INUMS if (args->inumber > XFS_DIR2_MAX_SHORT_INUM) - sfp->hdr.i8count++; + sfp->i8count++; #endif dp->i_d.di_size = new_isize; xfs_dir2_sf_check(args); @@ -444,19 +517,19 @@ xfs_dir2_sf_addname_hard( xfs_dir2_data_aoff_t offset; /* current offset value */ int old_isize; /* previous di_size */ xfs_dir2_sf_entry_t *oldsfep; /* entry in original dir */ - xfs_dir2_sf_t *oldsfp; /* original shortform dir */ + xfs_dir2_sf_hdr_t *oldsfp; /* original shortform dir */ xfs_dir2_sf_entry_t *sfep; /* entry in new dir */ - xfs_dir2_sf_t *sfp; /* new shortform dir */ + xfs_dir2_sf_hdr_t *sfp; /* new shortform dir */ /* * Copy the old directory to the stack buffer. */ dp = args->dp; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; old_isize = (int)dp->i_d.di_size; buf = kmem_alloc(old_isize, KM_SLEEP); - oldsfp = (xfs_dir2_sf_t *)buf; + oldsfp = (xfs_dir2_sf_hdr_t *)buf; memcpy(oldsfp, sfp, old_isize); /* * Loop over the old directory finding the place we're going @@ -485,7 +558,7 @@ xfs_dir2_sf_addname_hard( /* * Reset the pointer since the buffer was reallocated. */ - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Copy the first part of the directory, including the header. */ @@ -498,12 +571,11 @@ xfs_dir2_sf_addname_hard( sfep->namelen = args->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, args->name, sfep->namelen); - xfs_dir2_sf_put_inumber(sfp, &args->inumber, - xfs_dir2_sf_inumberp(sfep)); - sfp->hdr.count++; + xfs_dir2_sfe_put_ino(sfp, sfep, args->inumber); + sfp->count++; #if XFS_BIG_INUMS if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && !objchange) - sfp->hdr.i8count++; + sfp->i8count++; #endif /* * If there's more left to copy, do that. @@ -537,14 +609,14 @@ xfs_dir2_sf_addname_pick( xfs_mount_t *mp; /* filesystem mount point */ xfs_dir2_data_aoff_t offset; /* data block offset */ xfs_dir2_sf_entry_t *sfep; /* shortform entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ int size; /* entry's data size */ int used; /* data bytes used */ dp = args->dp; mp = dp->i_mount; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; size = xfs_dir2_data_entsize(args->namelen); offset = XFS_DIR2_DATA_FIRST_OFFSET; sfep = xfs_dir2_sf_firstentry(sfp); @@ -554,7 +626,7 @@ xfs_dir2_sf_addname_pick( * Keep track of data offset and whether we've seen a place * to insert the new entry. */ - for (i = 0; i < sfp->hdr.count; i++) { + for (i = 0; i < sfp->count; i++) { if (!holefit) holefit = offset + size <= xfs_dir2_sf_get_offset(sfep); offset = xfs_dir2_sf_get_offset(sfep) + @@ -566,7 +638,7 @@ xfs_dir2_sf_addname_pick( * was a data block (block form directory). */ used = offset + - (sfp->hdr.count + 3) * (uint)sizeof(xfs_dir2_leaf_entry_t) + + (sfp->count + 3) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t); /* * If it won't fit in a block form then we can't insert it, @@ -612,30 +684,30 @@ xfs_dir2_sf_check( xfs_ino_t ino; /* entry inode number */ int offset; /* data offset */ xfs_dir2_sf_entry_t *sfep; /* shortform dir entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ dp = args->dp; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; offset = XFS_DIR2_DATA_FIRST_OFFSET; - ino = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent); + ino = xfs_dir2_sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); - i < sfp->hdr.count; + i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { ASSERT(xfs_dir2_sf_get_offset(sfep) >= offset); - ino = xfs_dir2_sf_get_inumber(sfp, xfs_dir2_sf_inumberp(sfep)); + ino = xfs_dir2_sfe_get_ino(sfp, sfep); i8count += ino > XFS_DIR2_MAX_SHORT_INUM; offset = xfs_dir2_sf_get_offset(sfep) + xfs_dir2_data_entsize(sfep->namelen); } - ASSERT(i8count == sfp->hdr.i8count); + ASSERT(i8count == sfp->i8count); ASSERT(XFS_BIG_INUMS || i8count == 0); ASSERT((char *)sfep - (char *)sfp == dp->i_d.di_size); ASSERT(offset + - (sfp->hdr.count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t) <= dp->i_mount->m_dirblksize); } @@ -651,7 +723,7 @@ xfs_dir2_sf_create( { xfs_inode_t *dp; /* incore directory inode */ int i8count; /* parent inode is an 8-byte number */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ int size; /* directory size */ trace_xfs_dir2_sf_create(args); @@ -681,13 +753,13 @@ xfs_dir2_sf_create( /* * Fill in the header, */ - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - sfp->hdr.i8count = i8count; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + sfp->i8count = i8count; /* * Now can put in the inode number, since i8count is set. */ - xfs_dir2_sf_put_inumber(sfp, &pino, &sfp->hdr.parent); - sfp->hdr.count = 0; + xfs_dir2_sf_put_parent_ino(sfp, pino); + sfp->count = 0; dp->i_d.di_size = size; xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); @@ -705,7 +777,7 @@ xfs_dir2_sf_getdents( xfs_mount_t *mp; /* filesystem mount point */ xfs_dir2_dataptr_t off; /* current entry's offset */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ xfs_dir2_dataptr_t dot_offset; xfs_dir2_dataptr_t dotdot_offset; xfs_ino_t ino; @@ -724,9 +796,9 @@ xfs_dir2_sf_getdents( ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; - ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count)); + ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * If the block number in the offset is out of range, we're done. @@ -759,7 +831,7 @@ xfs_dir2_sf_getdents( * Put .. entry unless we're starting past it. */ if (*offset <= dotdot_offset) { - ino = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent); + ino = xfs_dir2_sf_get_parent_ino(sfp); if (filldir(dirent, "..", 2, dotdot_offset & 0x7fffffff, ino, DT_DIR)) { *offset = dotdot_offset & 0x7fffffff; return 0; @@ -770,7 +842,7 @@ xfs_dir2_sf_getdents( * Loop while there are more entries and put'ing works. */ sfep = xfs_dir2_sf_firstentry(sfp); - for (i = 0; i < sfp->hdr.count; i++) { + for (i = 0; i < sfp->count; i++) { off = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk, xfs_dir2_sf_get_offset(sfep)); @@ -779,7 +851,7 @@ xfs_dir2_sf_getdents( continue; } - ino = xfs_dir2_sf_get_inumber(sfp, xfs_dir2_sf_inumberp(sfep)); + ino = xfs_dir2_sfe_get_ino(sfp, sfep); if (filldir(dirent, (char *)sfep->name, sfep->namelen, off & 0x7fffffff, ino, DT_UNKNOWN)) { *offset = off & 0x7fffffff; @@ -805,7 +877,7 @@ xfs_dir2_sf_lookup( int i; /* entry index */ int error; xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ enum xfs_dacmp cmp; /* comparison result */ xfs_dir2_sf_entry_t *ci_sfep; /* case-insens. entry */ @@ -824,8 +896,8 @@ xfs_dir2_sf_lookup( } ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count)); + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Special case for . */ @@ -839,7 +911,7 @@ xfs_dir2_sf_lookup( */ if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { - args->inumber = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent); + args->inumber = xfs_dir2_sf_get_parent_ino(sfp); args->cmpresult = XFS_CMP_EXACT; return XFS_ERROR(EEXIST); } @@ -847,7 +919,7 @@ xfs_dir2_sf_lookup( * Loop over all the entries trying to match ours. */ ci_sfep = NULL; - for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->hdr.count; + for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { /* * Compare name and if it's an exact match, return the inode @@ -858,8 +930,7 @@ xfs_dir2_sf_lookup( sfep->namelen); if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { args->cmpresult = cmp; - args->inumber = xfs_dir2_sf_get_inumber(sfp, - xfs_dir2_sf_inumberp(sfep)); + args->inumber = xfs_dir2_sfe_get_ino(sfp, sfep); if (cmp == XFS_CMP_EXACT) return XFS_ERROR(EEXIST); ci_sfep = sfep; @@ -891,7 +962,7 @@ xfs_dir2_sf_removename( int newsize; /* new inode size */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ trace_xfs_dir2_sf_removename(args); @@ -908,32 +979,31 @@ xfs_dir2_sf_removename( } ASSERT(dp->i_df.if_bytes == oldsize); ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count)); + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Loop over the old directory entries. * Find the one we're deleting. */ - for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->hdr.count; + for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { if (xfs_da_compname(args, sfep->name, sfep->namelen) == XFS_CMP_EXACT) { - ASSERT(xfs_dir2_sf_get_inumber(sfp, - xfs_dir2_sf_inumberp(sfep)) == - args->inumber); + ASSERT(xfs_dir2_sfe_get_ino(sfp, sfep) == + args->inumber); break; } } /* * Didn't find it. */ - if (i == sfp->hdr.count) + if (i == sfp->count) return XFS_ERROR(ENOENT); /* * Calculate sizes. */ byteoff = (int)((char *)sfep - (char *)sfp); - entsize = xfs_dir2_sf_entsize_byname(sfp, args->namelen); + entsize = xfs_dir2_sf_entsize(sfp, args->namelen); newsize = oldsize - entsize; /* * Copy the part if any after the removed entry, sliding it down. @@ -944,22 +1014,22 @@ xfs_dir2_sf_removename( /* * Fix up the header and file size. */ - sfp->hdr.count--; + sfp->count--; dp->i_d.di_size = newsize; /* * Reallocate, making it smaller. */ xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; #if XFS_BIG_INUMS /* * Are we changing inode number size? */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM) { - if (sfp->hdr.i8count == 1) + if (sfp->i8count == 1) xfs_dir2_sf_toino4(args); else - sfp->hdr.i8count--; + sfp->i8count--; } #endif xfs_dir2_sf_check(args); @@ -983,7 +1053,7 @@ xfs_dir2_sf_replace( int i8elevated; /* sf_toino8 set i8count=1 */ #endif xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ - xfs_dir2_sf_t *sfp; /* shortform structure */ + xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ trace_xfs_dir2_sf_replace(args); @@ -999,19 +1069,19 @@ xfs_dir2_sf_replace( } ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->hdr.i8count)); + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); #if XFS_BIG_INUMS /* * New inode number is large, and need to convert to 8-byte inodes. */ - if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->hdr.i8count == 0) { + if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { int error; /* error return value */ int newsize; /* new inode size */ newsize = dp->i_df.if_bytes + - (sfp->hdr.count + 1) * + (sfp->count + 1) * ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t)); /* @@ -1029,7 +1099,7 @@ xfs_dir2_sf_replace( */ xfs_dir2_sf_toino8(args); i8elevated = 1; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; } else i8elevated = 0; #endif @@ -1040,34 +1110,32 @@ xfs_dir2_sf_replace( if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { #if XFS_BIG_INUMS || defined(DEBUG) - ino = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent); + ino = xfs_dir2_sf_get_parent_ino(sfp); ASSERT(args->inumber != ino); #endif - xfs_dir2_sf_put_inumber(sfp, &args->inumber, &sfp->hdr.parent); + xfs_dir2_sf_put_parent_ino(sfp, args->inumber); } /* * Normal entry, look for the name. */ else { for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); - i < sfp->hdr.count; + i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep)) { if (xfs_da_compname(args, sfep->name, sfep->namelen) == XFS_CMP_EXACT) { #if XFS_BIG_INUMS || defined(DEBUG) - ino = xfs_dir2_sf_get_inumber(sfp, - xfs_dir2_sf_inumberp(sfep)); + ino = xfs_dir2_sfe_get_ino(sfp, sfep); ASSERT(args->inumber != ino); #endif - xfs_dir2_sf_put_inumber(sfp, &args->inumber, - xfs_dir2_sf_inumberp(sfep)); + xfs_dir2_sfe_put_ino(sfp, sfep, args->inumber); break; } } /* * Didn't find it. */ - if (i == sfp->hdr.count) { + if (i == sfp->count) { ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); #if XFS_BIG_INUMS if (i8elevated) @@ -1085,10 +1153,10 @@ xfs_dir2_sf_replace( /* * And the old count was one, so need to convert to small. */ - if (sfp->hdr.i8count == 1) + if (sfp->i8count == 1) xfs_dir2_sf_toino4(args); else - sfp->hdr.i8count--; + sfp->i8count--; } /* * See if the old number was small, the new number is large. @@ -1099,9 +1167,9 @@ xfs_dir2_sf_replace( * add to the i8count unless we just converted to 8-byte * inodes (which does an implied i8count = 1) */ - ASSERT(sfp->hdr.i8count != 0); + ASSERT(sfp->i8count != 0); if (!i8elevated) - sfp->hdr.i8count++; + sfp->i8count++; } #endif xfs_dir2_sf_check(args); @@ -1121,13 +1189,12 @@ xfs_dir2_sf_toino4( char *buf; /* old dir's buffer */ xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ - xfs_ino_t ino; /* entry inode number */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ - xfs_dir2_sf_t *oldsfp; /* old sf directory */ + xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ - xfs_dir2_sf_t *sfp; /* new sf directory */ + xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ trace_xfs_dir2_sf_toino4(args); @@ -1140,44 +1207,42 @@ xfs_dir2_sf_toino4( */ oldsize = dp->i_df.if_bytes; buf = kmem_alloc(oldsize, KM_SLEEP); - oldsfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(oldsfp->hdr.i8count == 1); + oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(oldsfp->i8count == 1); memcpy(buf, oldsfp, oldsize); /* * Compute the new inode size. */ newsize = oldsize - - (oldsfp->hdr.count + 1) * + (oldsfp->count + 1) * ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t)); xfs_idata_realloc(dp, -oldsize, XFS_DATA_FORK); xfs_idata_realloc(dp, newsize, XFS_DATA_FORK); /* * Reset our pointers, the data has moved. */ - oldsfp = (xfs_dir2_sf_t *)buf; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + oldsfp = (xfs_dir2_sf_hdr_t *)buf; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Fill in the new header. */ - sfp->hdr.count = oldsfp->hdr.count; - sfp->hdr.i8count = 0; - ino = xfs_dir2_sf_get_inumber(oldsfp, &oldsfp->hdr.parent); - xfs_dir2_sf_put_inumber(sfp, &ino, &sfp->hdr.parent); + sfp->count = oldsfp->count; + sfp->i8count = 0; + xfs_dir2_sf_put_parent_ino(sfp, xfs_dir2_sf_get_parent_ino(oldsfp)); /* * Copy the entries field by field. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp), oldsfep = xfs_dir2_sf_firstentry(oldsfp); - i < sfp->hdr.count; + i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep), oldsfep = xfs_dir2_sf_nextentry(oldsfp, oldsfep)) { sfep->namelen = oldsfep->namelen; sfep->offset = oldsfep->offset; memcpy(sfep->name, oldsfep->name, sfep->namelen); - ino = xfs_dir2_sf_get_inumber(oldsfp, - xfs_dir2_sf_inumberp(oldsfep)); - xfs_dir2_sf_put_inumber(sfp, &ino, xfs_dir2_sf_inumberp(sfep)); + xfs_dir2_sfe_put_ino(sfp, sfep, + xfs_dir2_sfe_get_ino(oldsfp, oldsfep)); } /* * Clean up the inode. @@ -1199,13 +1264,12 @@ xfs_dir2_sf_toino8( char *buf; /* old dir's buffer */ xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ - xfs_ino_t ino; /* entry inode number */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ - xfs_dir2_sf_t *oldsfp; /* old sf directory */ + xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ - xfs_dir2_sf_t *sfp; /* new sf directory */ + xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ trace_xfs_dir2_sf_toino8(args); @@ -1218,44 +1282,42 @@ xfs_dir2_sf_toino8( */ oldsize = dp->i_df.if_bytes; buf = kmem_alloc(oldsize, KM_SLEEP); - oldsfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; - ASSERT(oldsfp->hdr.i8count == 0); + oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; + ASSERT(oldsfp->i8count == 0); memcpy(buf, oldsfp, oldsize); /* * Compute the new inode size. */ newsize = oldsize + - (oldsfp->hdr.count + 1) * + (oldsfp->count + 1) * ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t)); xfs_idata_realloc(dp, -oldsize, XFS_DATA_FORK); xfs_idata_realloc(dp, newsize, XFS_DATA_FORK); /* * Reset our pointers, the data has moved. */ - oldsfp = (xfs_dir2_sf_t *)buf; - sfp = (xfs_dir2_sf_t *)dp->i_df.if_u1.if_data; + oldsfp = (xfs_dir2_sf_hdr_t *)buf; + sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Fill in the new header. */ - sfp->hdr.count = oldsfp->hdr.count; - sfp->hdr.i8count = 1; - ino = xfs_dir2_sf_get_inumber(oldsfp, &oldsfp->hdr.parent); - xfs_dir2_sf_put_inumber(sfp, &ino, &sfp->hdr.parent); + sfp->count = oldsfp->count; + sfp->i8count = 1; + xfs_dir2_sf_put_parent_ino(sfp, xfs_dir2_sf_get_parent_ino(oldsfp)); /* * Copy the entries field by field. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp), oldsfep = xfs_dir2_sf_firstentry(oldsfp); - i < sfp->hdr.count; + i < sfp->count; i++, sfep = xfs_dir2_sf_nextentry(sfp, sfep), oldsfep = xfs_dir2_sf_nextentry(oldsfp, oldsfep)) { sfep->namelen = oldsfep->namelen; sfep->offset = oldsfep->offset; memcpy(sfep->name, oldsfep->name, sfep->namelen); - ino = xfs_dir2_sf_get_inumber(oldsfp, - xfs_dir2_sf_inumberp(oldsfep)); - xfs_dir2_sf_put_inumber(sfp, &ino, xfs_dir2_sf_inumberp(sfep)); + xfs_dir2_sfe_put_ino(sfp, sfep, + xfs_dir2_sfe_get_ino(oldsfp, oldsfep)); } /* * Clean up the inode. diff --git a/fs/xfs/xfs_dir2_sf.h b/fs/xfs/xfs_dir2_sf.h deleted file mode 100644 index 6ac44b5..0000000 --- a/fs/xfs/xfs_dir2_sf.h +++ /dev/null @@ -1,171 +0,0 @@ -/* - * Copyright (c) 2000-2001,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_DIR2_SF_H__ -#define __XFS_DIR2_SF_H__ - -/* - * Directory layout when stored internal to an inode. - * - * Small directories are packed as tightly as possible so as to - * fit into the literal area of the inode. - */ - -struct uio; -struct xfs_dabuf; -struct xfs_da_args; -struct xfs_dir2_block; -struct xfs_inode; -struct xfs_mount; -struct xfs_trans; - -/* - * Inode number stored as 8 8-bit values. - */ -typedef struct { __uint8_t i[8]; } xfs_dir2_ino8_t; - -/* - * Inode number stored as 4 8-bit values. - * Works a lot of the time, when all the inode numbers in a directory - * fit in 32 bits. - */ -typedef struct { __uint8_t i[4]; } xfs_dir2_ino4_t; - -typedef union { - xfs_dir2_ino8_t i8; - xfs_dir2_ino4_t i4; -} xfs_dir2_inou_t; -#define XFS_DIR2_MAX_SHORT_INUM ((xfs_ino_t)0xffffffffULL) - -/* - * Normalized offset (in a data block) of the entry, really xfs_dir2_data_off_t. - * Only need 16 bits, this is the byte offset into the single block form. - */ -typedef struct { __uint8_t i[2]; } __arch_pack xfs_dir2_sf_off_t; - -/* - * The parent directory has a dedicated field, and the self-pointer must - * be calculated on the fly. - * - * Entries are packed toward the top as tightly as possible. The header - * and the elements must be memcpy'd out into a work area to get correct - * alignment for the inode number fields. - */ -typedef struct xfs_dir2_sf_hdr { - __uint8_t count; /* count of entries */ - __uint8_t i8count; /* count of 8-byte inode #s */ - xfs_dir2_inou_t parent; /* parent dir inode number */ -} __arch_pack xfs_dir2_sf_hdr_t; - -typedef struct xfs_dir2_sf_entry { - __uint8_t namelen; /* actual name length */ - xfs_dir2_sf_off_t offset; /* saved offset */ - __uint8_t name[1]; /* name, variable size */ - xfs_dir2_inou_t inumber; /* inode number, var. offset */ -} __arch_pack xfs_dir2_sf_entry_t; - -typedef struct xfs_dir2_sf { - xfs_dir2_sf_hdr_t hdr; /* shortform header */ - xfs_dir2_sf_entry_t list[1]; /* shortform entries */ -} xfs_dir2_sf_t; - -static inline int xfs_dir2_sf_hdr_size(int i8count) -{ - return ((uint)sizeof(xfs_dir2_sf_hdr_t) - \ - ((i8count) == 0) * \ - ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t))); -} - -static inline xfs_dir2_inou_t *xfs_dir2_sf_inumberp(xfs_dir2_sf_entry_t *sfep) -{ - return (xfs_dir2_inou_t *)&(sfep)->name[(sfep)->namelen]; -} - -static inline xfs_intino_t -xfs_dir2_sf_get_inumber(xfs_dir2_sf_t *sfp, xfs_dir2_inou_t *from) -{ - return ((sfp)->hdr.i8count == 0 ? \ - (xfs_intino_t)XFS_GET_DIR_INO4((from)->i4) : \ - (xfs_intino_t)XFS_GET_DIR_INO8((from)->i8)); -} - -static inline void xfs_dir2_sf_put_inumber(xfs_dir2_sf_t *sfp, xfs_ino_t *from, - xfs_dir2_inou_t *to) -{ - if ((sfp)->hdr.i8count == 0) - XFS_PUT_DIR_INO4(*(from), (to)->i4); - else - XFS_PUT_DIR_INO8(*(from), (to)->i8); -} - -static inline xfs_dir2_data_aoff_t -xfs_dir2_sf_get_offset(xfs_dir2_sf_entry_t *sfep) -{ - return INT_GET_UNALIGNED_16_BE(&(sfep)->offset.i); -} - -static inline void -xfs_dir2_sf_put_offset(xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t off) -{ - INT_SET_UNALIGNED_16_BE(&(sfep)->offset.i, off); -} - -static inline int xfs_dir2_sf_entsize_byname(xfs_dir2_sf_t *sfp, int len) -{ - return ((uint)sizeof(xfs_dir2_sf_entry_t) - 1 + (len) - \ - ((sfp)->hdr.i8count == 0) * \ - ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t))); -} - -static inline int -xfs_dir2_sf_entsize_byentry(xfs_dir2_sf_t *sfp, xfs_dir2_sf_entry_t *sfep) -{ - return ((uint)sizeof(xfs_dir2_sf_entry_t) - 1 + (sfep)->namelen - \ - ((sfp)->hdr.i8count == 0) * \ - ((uint)sizeof(xfs_dir2_ino8_t) - (uint)sizeof(xfs_dir2_ino4_t))); -} - -static inline xfs_dir2_sf_entry_t *xfs_dir2_sf_firstentry(xfs_dir2_sf_t *sfp) -{ - return ((xfs_dir2_sf_entry_t *) \ - ((char *)(sfp) + xfs_dir2_sf_hdr_size(sfp->hdr.i8count))); -} - -static inline xfs_dir2_sf_entry_t * -xfs_dir2_sf_nextentry(xfs_dir2_sf_t *sfp, xfs_dir2_sf_entry_t *sfep) -{ - return ((xfs_dir2_sf_entry_t *) \ - ((char *)(sfep) + xfs_dir2_sf_entsize_byentry(sfp,sfep))); -} - -/* - * Functions. - */ -extern int xfs_dir2_block_sfsize(struct xfs_inode *dp, - struct xfs_dir2_block *block, - xfs_dir2_sf_hdr_t *sfhp); -extern int xfs_dir2_block_to_sf(struct xfs_da_args *args, struct xfs_dabuf *bp, - int size, xfs_dir2_sf_hdr_t *sfhp); -extern int xfs_dir2_sf_addname(struct xfs_da_args *args); -extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino); -extern int xfs_dir2_sf_getdents(struct xfs_inode *dp, void *dirent, - xfs_off_t *offset, filldir_t filldir); -extern int xfs_dir2_sf_lookup(struct xfs_da_args *args); -extern int xfs_dir2_sf_removename(struct xfs_da_args *args); -extern int xfs_dir2_sf_replace(struct xfs_da_args *args); - -#endif /* __XFS_DIR2_SF_H__ */ diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h index 8f6fc1a..c13fed8 100644 --- a/fs/xfs/xfs_fs.h +++ b/fs/xfs/xfs_fs.h @@ -249,6 +249,11 @@ typedef struct xfs_fsop_resblks { #define XFS_MAX_LOG_BYTES \ ((2 * 1024 * 1024 * 1024ULL) - XFS_MIN_LOG_BYTES) +/* Used for sanity checks on superblock */ +#define XFS_MAX_DBLOCKS(s) ((xfs_drfsbno_t)(s)->sb_agcount * (s)->sb_agblocks) +#define XFS_MIN_DBLOCKS(s) ((xfs_drfsbno_t)((s)->sb_agcount - 1) * \ + (s)->sb_agblocks + XFS_MIN_AG_BLOCKS) + /* * Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT */ diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 84ebeec..dd5628b 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -683,7 +683,7 @@ xfs_dialloc( return 0; } agi = XFS_BUF_TO_AGI(agbp); - ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC); + ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); } else { /* * Continue where we left off before. In this case, we @@ -691,7 +691,7 @@ xfs_dialloc( */ agbp = *IO_agbp; agi = XFS_BUF_TO_AGI(agbp); - ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC); + ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); ASSERT(be32_to_cpu(agi->agi_freecount) > 0); } mp = tp->t_mountp; @@ -775,7 +775,7 @@ nextag: if (error) goto nextag; agi = XFS_BUF_TO_AGI(agbp); - ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC); + ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); } /* * Here with an allocation group that has a free inode. @@ -944,7 +944,7 @@ nextag: * See if the most recently allocated block has any free. */ newino: - if (be32_to_cpu(agi->agi_newino) != NULLAGINO) { + if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), XFS_LOOKUP_EQ, &i); if (error) @@ -1085,7 +1085,7 @@ xfs_difree( return error; } agi = XFS_BUF_TO_AGI(agbp); - ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC); + ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); ASSERT(agbno < be32_to_cpu(agi->agi_length)); /* * Initialize the cursor. @@ -1438,7 +1438,7 @@ xfs_ialloc_log_agi( xfs_agi_t *agi; /* allocation group header */ agi = XFS_BUF_TO_AGI(bp); - ASSERT(be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC); + ASSERT(agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC)); #endif /* * Compute byte offsets for the first and last fields. @@ -1492,7 +1492,7 @@ xfs_read_agi( /* * Validate the magic number of the agi block. */ - agi_ok = be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC && + agi_ok = agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC) && XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)) && be32_to_cpu(agi->agi_seqno) == agno; if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI, diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c index 16921f5..c6a7581 100644 --- a/fs/xfs/xfs_ialloc_btree.c +++ b/fs/xfs/xfs_ialloc_btree.c @@ -31,7 +31,6 @@ #include "xfs_dinode.h" #include "xfs_inode.h" #include "xfs_btree.h" -#include "xfs_btree_trace.h" #include "xfs_ialloc.h" #include "xfs_alloc.h" #include "xfs_error.h" @@ -205,72 +204,6 @@ xfs_inobt_recs_inorder( } #endif /* DEBUG */ -#ifdef XFS_BTREE_TRACE -ktrace_t *xfs_inobt_trace_buf; - -STATIC void -xfs_inobt_trace_enter( - struct xfs_btree_cur *cur, - const char *func, - char *s, - int type, - int line, - __psunsigned_t a0, - __psunsigned_t a1, - __psunsigned_t a2, - __psunsigned_t a3, - __psunsigned_t a4, - __psunsigned_t a5, - __psunsigned_t a6, - __psunsigned_t a7, - __psunsigned_t a8, - __psunsigned_t a9, - __psunsigned_t a10) -{ - ktrace_enter(xfs_inobt_trace_buf, (void *)(__psint_t)type, - (void *)func, (void *)s, NULL, (void *)cur, - (void *)a0, (void *)a1, (void *)a2, (void *)a3, - (void *)a4, (void *)a5, (void *)a6, (void *)a7, - (void *)a8, (void *)a9, (void *)a10); -} - -STATIC void -xfs_inobt_trace_cursor( - struct xfs_btree_cur *cur, - __uint32_t *s0, - __uint64_t *l0, - __uint64_t *l1) -{ - *s0 = cur->bc_private.a.agno; - *l0 = cur->bc_rec.i.ir_startino; - *l1 = cur->bc_rec.i.ir_free; -} - -STATIC void -xfs_inobt_trace_key( - struct xfs_btree_cur *cur, - union xfs_btree_key *key, - __uint64_t *l0, - __uint64_t *l1) -{ - *l0 = be32_to_cpu(key->inobt.ir_startino); - *l1 = 0; -} - -STATIC void -xfs_inobt_trace_record( - struct xfs_btree_cur *cur, - union xfs_btree_rec *rec, - __uint64_t *l0, - __uint64_t *l1, - __uint64_t *l2) -{ - *l0 = be32_to_cpu(rec->inobt.ir_startino); - *l1 = be32_to_cpu(rec->inobt.ir_freecount); - *l2 = be64_to_cpu(rec->inobt.ir_free); -} -#endif /* XFS_BTREE_TRACE */ - static const struct xfs_btree_ops xfs_inobt_ops = { .rec_len = sizeof(xfs_inobt_rec_t), .key_len = sizeof(xfs_inobt_key_t), @@ -286,18 +219,10 @@ static const struct xfs_btree_ops xfs_inobt_ops = { .init_rec_from_cur = xfs_inobt_init_rec_from_cur, .init_ptr_from_cur = xfs_inobt_init_ptr_from_cur, .key_diff = xfs_inobt_key_diff, - #ifdef DEBUG .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, #endif - -#ifdef XFS_BTREE_TRACE - .trace_enter = xfs_inobt_trace_enter, - .trace_cursor = xfs_inobt_trace_cursor, - .trace_key = xfs_inobt_trace_key, - .trace_record = xfs_inobt_trace_record, -#endif }; /* diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index cb9b6d1..7759812 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -38,7 +38,6 @@ #include "xfs_trans_priv.h" #include "xfs_inode_item.h" #include "xfs_bmap.h" -#include "xfs_btree_trace.h" #include "xfs_trace.h" @@ -253,16 +252,21 @@ xfs_iget_cache_hit( rcu_read_lock(); spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~XFS_INEW; - ip->i_flags |= XFS_IRECLAIMABLE; - __xfs_inode_set_reclaim_tag(pag, ip); + ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); + ASSERT(ip->i_flags & XFS_IRECLAIMABLE); trace_xfs_iget_reclaim_fail(ip); goto out_error; } spin_lock(&pag->pag_ici_lock); spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM); + + /* + * Clear the per-lifetime state in the inode as we are now + * effectively a new inode and need to return to the initial + * state before reuse occurs. + */ + ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS; ip->i_flags |= XFS_INEW; __xfs_inode_clear_reclaim_tag(mp, pag, ip); inode->i_state = I_NEW; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index a098a20..3cc21dd 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -37,7 +37,6 @@ #include "xfs_buf_item.h" #include "xfs_inode_item.h" #include "xfs_btree.h" -#include "xfs_btree_trace.h" #include "xfs_alloc.h" #include "xfs_ialloc.h" #include "xfs_bmap.h" @@ -52,7 +51,7 @@ kmem_zone_t *xfs_ifork_zone; kmem_zone_t *xfs_inode_zone; /* - * Used in xfs_itruncate(). This is the maximum number of extents + * Used in xfs_itruncate_extents(). This is the maximum number of extents * freed from a file in a single transaction. */ #define XFS_ITRUNC_MAX_EXTENTS 2 @@ -167,7 +166,7 @@ xfs_imap_to_bp( dip = (xfs_dinode_t *)xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog)); - di_ok = be16_to_cpu(dip->di_magic) == XFS_DINODE_MAGIC && + di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) && XFS_DINODE_GOOD_VERSION(dip->di_version); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP, @@ -802,7 +801,7 @@ xfs_iread( * If we got something that isn't an inode it means someone * (nfs or dmi) has a stale handle. */ - if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC) { + if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC)) { #ifdef DEBUG xfs_alert(mp, "%s: dip->di_magic (0x%x) != XFS_DINODE_MAGIC (0x%x)", @@ -1179,15 +1178,15 @@ xfs_ialloc( * at least do it for regular files. */ #ifdef DEBUG -void +STATIC void xfs_isize_check( - xfs_mount_t *mp, - xfs_inode_t *ip, - xfs_fsize_t isize) + struct xfs_inode *ip, + xfs_fsize_t isize) { - xfs_fileoff_t map_first; - int nimaps; - xfs_bmbt_irec_t imaps[2]; + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t map_first; + int nimaps; + xfs_bmbt_irec_t imaps[2]; if ((ip->i_d.di_mode & S_IFMT) != S_IFREG) return; @@ -1214,168 +1213,14 @@ xfs_isize_check( ASSERT(nimaps == 1); ASSERT(imaps[0].br_startblock == HOLESTARTBLOCK); } +#else /* DEBUG */ +#define xfs_isize_check(ip, isize) #endif /* DEBUG */ /* - * Calculate the last possible buffered byte in a file. This must - * include data that was buffered beyond the EOF by the write code. - * This also needs to deal with overflowing the xfs_fsize_t type - * which can happen for sizes near the limit. - * - * We also need to take into account any blocks beyond the EOF. It - * may be the case that they were buffered by a write which failed. - * In that case the pages will still be in memory, but the inode size - * will never have been updated. - */ -STATIC xfs_fsize_t -xfs_file_last_byte( - xfs_inode_t *ip) -{ - xfs_mount_t *mp; - xfs_fsize_t last_byte; - xfs_fileoff_t last_block; - xfs_fileoff_t size_last_block; - int error; - - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)); - - mp = ip->i_mount; - /* - * Only check for blocks beyond the EOF if the extents have - * been read in. This eliminates the need for the inode lock, - * and it also saves us from looking when it really isn't - * necessary. - */ - if (ip->i_df.if_flags & XFS_IFEXTENTS) { - xfs_ilock(ip, XFS_ILOCK_SHARED); - error = xfs_bmap_last_offset(NULL, ip, &last_block, - XFS_DATA_FORK); - xfs_iunlock(ip, XFS_ILOCK_SHARED); - if (error) { - last_block = 0; - } - } else { - last_block = 0; - } - size_last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)ip->i_size); - last_block = XFS_FILEOFF_MAX(last_block, size_last_block); - - last_byte = XFS_FSB_TO_B(mp, last_block); - if (last_byte < 0) { - return XFS_MAXIOFFSET(mp); - } - last_byte += (1 << mp->m_writeio_log); - if (last_byte < 0) { - return XFS_MAXIOFFSET(mp); - } - return last_byte; -} - -/* - * Start the truncation of the file to new_size. The new size - * must be smaller than the current size. This routine will - * clear the buffer and page caches of file data in the removed - * range, and xfs_itruncate_finish() will remove the underlying - * disk blocks. - * - * The inode must have its I/O lock locked EXCLUSIVELY, and it - * must NOT have the inode lock held at all. This is because we're - * calling into the buffer/page cache code and we can't hold the - * inode lock when we do so. - * - * We need to wait for any direct I/Os in flight to complete before we - * proceed with the truncate. This is needed to prevent the extents - * being read or written by the direct I/Os from being removed while the - * I/O is in flight as there is no other method of synchronising - * direct I/O with the truncate operation. Also, because we hold - * the IOLOCK in exclusive mode, we prevent new direct I/Os from being - * started until the truncate completes and drops the lock. Essentially, - * the xfs_ioend_wait() call forms an I/O barrier that provides strict - * ordering between direct I/Os and the truncate operation. - * - * The flags parameter can have either the value XFS_ITRUNC_DEFINITE - * or XFS_ITRUNC_MAYBE. The XFS_ITRUNC_MAYBE value should be used - * in the case that the caller is locking things out of order and - * may not be able to call xfs_itruncate_finish() with the inode lock - * held without dropping the I/O lock. If the caller must drop the - * I/O lock before calling xfs_itruncate_finish(), then xfs_itruncate_start() - * must be called again with all the same restrictions as the initial - * call. - */ -int -xfs_itruncate_start( - xfs_inode_t *ip, - uint flags, - xfs_fsize_t new_size) -{ - xfs_fsize_t last_byte; - xfs_off_t toss_start; - xfs_mount_t *mp; - int error = 0; - - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); - ASSERT((new_size == 0) || (new_size <= ip->i_size)); - ASSERT((flags == XFS_ITRUNC_DEFINITE) || - (flags == XFS_ITRUNC_MAYBE)); - - mp = ip->i_mount; - - /* wait for the completion of any pending DIOs */ - if (new_size == 0 || new_size < ip->i_size) - xfs_ioend_wait(ip); - - /* - * Call toss_pages or flushinval_pages to get rid of pages - * overlapping the region being removed. We have to use - * the less efficient flushinval_pages in the case that the - * caller may not be able to finish the truncate without - * dropping the inode's I/O lock. Make sure - * to catch any pages brought in by buffers overlapping - * the EOF by searching out beyond the isize by our - * block size. We round new_size up to a block boundary - * so that we don't toss things on the same block as - * new_size but before it. - * - * Before calling toss_page or flushinval_pages, make sure to - * call remapf() over the same region if the file is mapped. - * This frees up mapped file references to the pages in the - * given range and for the flushinval_pages case it ensures - * that we get the latest mapped changes flushed out. - */ - toss_start = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size); - toss_start = XFS_FSB_TO_B(mp, toss_start); - if (toss_start < 0) { - /* - * The place to start tossing is beyond our maximum - * file size, so there is no way that the data extended - * out there. - */ - return 0; - } - last_byte = xfs_file_last_byte(ip); - trace_xfs_itruncate_start(ip, new_size, flags, toss_start, last_byte); - if (last_byte > toss_start) { - if (flags & XFS_ITRUNC_DEFINITE) { - xfs_tosspages(ip, toss_start, - -1, FI_REMAPF_LOCKED); - } else { - error = xfs_flushinval_pages(ip, toss_start, - -1, FI_REMAPF_LOCKED); - } - } - -#ifdef DEBUG - if (new_size == 0) { - ASSERT(VN_CACHED(VFS_I(ip)) == 0); - } -#endif - return error; -} - -/* - * Shrink the file to the given new_size. The new size must be smaller than - * the current size. This will free up the underlying blocks in the removed - * range after a call to xfs_itruncate_start() or xfs_atruncate_start(). + * Free up the underlying blocks past new_size. The new size must be smaller + * than the current size. This routine can be used both for the attribute and + * data fork, and does not modify the inode size, which is left to the caller. * * The transaction passed to this routine must have made a permanent log * reservation of at least XFS_ITRUNCATE_LOG_RES. This routine may commit the @@ -1387,31 +1232,6 @@ xfs_itruncate_start( * will be "held" within the returned transaction. This routine does NOT * require any disk space to be reserved for it within the transaction. * - * The fork parameter must be either xfs_attr_fork or xfs_data_fork, and it - * indicates the fork which is to be truncated. For the attribute fork we only - * support truncation to size 0. - * - * We use the sync parameter to indicate whether or not the first transaction - * we perform might have to be synchronous. For the attr fork, it needs to be - * so if the unlink of the inode is not yet known to be permanent in the log. - * This keeps us from freeing and reusing the blocks of the attribute fork - * before the unlink of the inode becomes permanent. - * - * For the data fork, we normally have to run synchronously if we're being - * called out of the inactive path or we're being called out of the create path - * where we're truncating an existing file. Either way, the truncate needs to - * be sync so blocks don't reappear in the file with altered data in case of a - * crash. wsync filesystems can run the first case async because anything that - * shrinks the inode has to run sync so by the time we're called here from - * inactive, the inode size is permanently set to 0. - * - * Calls from the truncate path always need to be sync unless we're in a wsync - * filesystem and the file has already been unlinked. - * - * The caller is responsible for correctly setting the sync parameter. It gets - * too hard for us to guess here which path we're being called out of just - * based on inode state. - * * If we get an error, we must return with the inode locked and linked into the * current transaction. This keeps things simple for the higher level code, * because it always knows that the inode is locked and held in the transaction @@ -1419,124 +1239,30 @@ xfs_itruncate_start( * dirty on error so that transactions can be easily aborted if possible. */ int -xfs_itruncate_finish( - xfs_trans_t **tp, - xfs_inode_t *ip, - xfs_fsize_t new_size, - int fork, - int sync) +xfs_itruncate_extents( + struct xfs_trans **tpp, + struct xfs_inode *ip, + int whichfork, + xfs_fsize_t new_size) { - xfs_fsblock_t first_block; - xfs_fileoff_t first_unmap_block; - xfs_fileoff_t last_block; - xfs_filblks_t unmap_len=0; - xfs_mount_t *mp; - xfs_trans_t *ntp; - int done; - int committed; - xfs_bmap_free_t free_list; - int error; + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp = *tpp; + struct xfs_trans *ntp; + xfs_bmap_free_t free_list; + xfs_fsblock_t first_block; + xfs_fileoff_t first_unmap_block; + xfs_fileoff_t last_block; + xfs_filblks_t unmap_len; + int committed; + int error = 0; + int done = 0; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); - ASSERT((new_size == 0) || (new_size <= ip->i_size)); - ASSERT(*tp != NULL); - ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES); - ASSERT(ip->i_transp == *tp); + ASSERT(new_size <= ip->i_size); + ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(ip->i_itemp != NULL); ASSERT(ip->i_itemp->ili_lock_flags == 0); - - - ntp = *tp; - mp = (ntp)->t_mountp; - ASSERT(! XFS_NOT_DQATTACHED(mp, ip)); - - /* - * We only support truncating the entire attribute fork. - */ - if (fork == XFS_ATTR_FORK) { - new_size = 0LL; - } - first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size); - trace_xfs_itruncate_finish_start(ip, new_size); - - /* - * The first thing we do is set the size to new_size permanently - * on disk. This way we don't have to worry about anyone ever - * being able to look at the data being freed even in the face - * of a crash. What we're getting around here is the case where - * we free a block, it is allocated to another file, it is written - * to, and then we crash. If the new data gets written to the - * file but the log buffers containing the free and reallocation - * don't, then we'd end up with garbage in the blocks being freed. - * As long as we make the new_size permanent before actually - * freeing any blocks it doesn't matter if they get written to. - * - * The callers must signal into us whether or not the size - * setting here must be synchronous. There are a few cases - * where it doesn't have to be synchronous. Those cases - * occur if the file is unlinked and we know the unlink is - * permanent or if the blocks being truncated are guaranteed - * to be beyond the inode eof (regardless of the link count) - * and the eof value is permanent. Both of these cases occur - * only on wsync-mounted filesystems. In those cases, we're - * guaranteed that no user will ever see the data in the blocks - * that are being truncated so the truncate can run async. - * In the free beyond eof case, the file may wind up with - * more blocks allocated to it than it needs if we crash - * and that won't get fixed until the next time the file - * is re-opened and closed but that's ok as that shouldn't - * be too many blocks. - * - * However, we can't just make all wsync xactions run async - * because there's one call out of the create path that needs - * to run sync where it's truncating an existing file to size - * 0 whose size is > 0. - * - * It's probably possible to come up with a test in this - * routine that would correctly distinguish all the above - * cases from the values of the function parameters and the - * inode state but for sanity's sake, I've decided to let the - * layers above just tell us. It's simpler to correctly figure - * out in the layer above exactly under what conditions we - * can run async and I think it's easier for others read and - * follow the logic in case something has to be changed. - * cscope is your friend -- rcc. - * - * The attribute fork is much simpler. - * - * For the attribute fork we allow the caller to tell us whether - * the unlink of the inode that led to this call is yet permanent - * in the on disk log. If it is not and we will be freeing extents - * in this inode then we make the first transaction synchronous - * to make sure that the unlink is permanent by the time we free - * the blocks. - */ - if (fork == XFS_DATA_FORK) { - if (ip->i_d.di_nextents > 0) { - /* - * If we are not changing the file size then do - * not update the on-disk file size - we may be - * called from xfs_inactive_free_eofblocks(). If we - * update the on-disk file size and then the system - * crashes before the contents of the file are - * flushed to disk then the files may be full of - * holes (ie NULL files bug). - */ - if (ip->i_size != new_size) { - ip->i_d.di_size = new_size; - ip->i_size = new_size; - xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE); - } - } - } else if (sync) { - ASSERT(!(mp->m_flags & XFS_MOUNT_WSYNC)); - if (ip->i_d.di_anextents > 0) - xfs_trans_set_sync(ntp); - } - ASSERT(fork == XFS_DATA_FORK || - (fork == XFS_ATTR_FORK && - ((sync && !(mp->m_flags & XFS_MOUNT_WSYNC)) || - (sync == 0 && (mp->m_flags & XFS_MOUNT_WSYNC))))); + ASSERT(!XFS_NOT_DQATTACHED(mp, ip)); /* * Since it is possible for space to become allocated beyond @@ -1547,128 +1273,142 @@ xfs_itruncate_finish( * beyond the maximum file size (ie it is the same as last_block), * then there is nothing to do. */ + first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size); last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp)); - ASSERT(first_unmap_block <= last_block); - done = 0; - if (last_block == first_unmap_block) { - done = 1; - } else { - unmap_len = last_block - first_unmap_block + 1; - } + if (first_unmap_block == last_block) + return 0; + + ASSERT(first_unmap_block < last_block); + unmap_len = last_block - first_unmap_block + 1; while (!done) { - /* - * Free up up to XFS_ITRUNC_MAX_EXTENTS. xfs_bunmapi() - * will tell us whether it freed the entire range or - * not. If this is a synchronous mount (wsync), - * then we can tell bunmapi to keep all the - * transactions asynchronous since the unlink - * transaction that made this inode inactive has - * already hit the disk. There's no danger of - * the freed blocks being reused, there being a - * crash, and the reused blocks suddenly reappearing - * in this file with garbage in them once recovery - * runs. - */ xfs_bmap_init(&free_list, &first_block); - error = xfs_bunmapi(ntp, ip, + error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, - xfs_bmapi_aflag(fork), + xfs_bmapi_aflag(whichfork), XFS_ITRUNC_MAX_EXTENTS, &first_block, &free_list, &done); - if (error) { - /* - * If the bunmapi call encounters an error, - * return to the caller where the transaction - * can be properly aborted. We just need to - * make sure we're not holding any resources - * that we were not when we came in. - */ - xfs_bmap_cancel(&free_list); - return error; - } + if (error) + goto out_bmap_cancel; /* * Duplicate the transaction that has the permanent * reservation and commit the old transaction. */ - error = xfs_bmap_finish(tp, &free_list, &committed); - ntp = *tp; + error = xfs_bmap_finish(&tp, &free_list, &committed); if (committed) - xfs_trans_ijoin(ntp, ip); - - if (error) { - /* - * If the bmap finish call encounters an error, return - * to the caller where the transaction can be properly - * aborted. We just need to make sure we're not - * holding any resources that we were not when we came - * in. - * - * Aborting from this point might lose some blocks in - * the file system, but oh well. - */ - xfs_bmap_cancel(&free_list); - return error; - } + xfs_trans_ijoin(tp, ip); + if (error) + goto out_bmap_cancel; if (committed) { /* * Mark the inode dirty so it will be logged and * moved forward in the log as part of every commit. */ - xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } - ntp = xfs_trans_dup(ntp); - error = xfs_trans_commit(*tp, 0); - *tp = ntp; + ntp = xfs_trans_dup(tp); + error = xfs_trans_commit(tp, 0); + tp = ntp; - xfs_trans_ijoin(ntp, ip); + xfs_trans_ijoin(tp, ip); if (error) - return error; + goto out; + /* - * transaction commit worked ok so we can drop the extra ticket + * Transaction commit worked ok so we can drop the extra ticket * reference that we gained in xfs_trans_dup() */ - xfs_log_ticket_put(ntp->t_ticket); - error = xfs_trans_reserve(ntp, 0, + xfs_log_ticket_put(tp->t_ticket); + error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, XFS_TRANS_PERM_LOG_RES, XFS_ITRUNCATE_LOG_COUNT); if (error) - return error; + goto out; } + +out: + *tpp = tp; + return error; +out_bmap_cancel: /* - * Only update the size in the case of the data fork, but - * always re-log the inode so that our permanent transaction - * can keep on rolling it forward in the log. + * If the bunmapi call encounters an error, return to the caller where + * the transaction can be properly aborted. We just need to make sure + * we're not holding any resources that we were not when we came in. */ - if (fork == XFS_DATA_FORK) { - xfs_isize_check(mp, ip, new_size); + xfs_bmap_cancel(&free_list); + goto out; +} + +int +xfs_itruncate_data( + struct xfs_trans **tpp, + struct xfs_inode *ip, + xfs_fsize_t new_size) +{ + int error; + + trace_xfs_itruncate_data_start(ip, new_size); + + /* + * The first thing we do is set the size to new_size permanently on + * disk. This way we don't have to worry about anyone ever being able + * to look at the data being freed even in the face of a crash. + * What we're getting around here is the case where we free a block, it + * is allocated to another file, it is written to, and then we crash. + * If the new data gets written to the file but the log buffers + * containing the free and reallocation don't, then we'd end up with + * garbage in the blocks being freed. As long as we make the new_size + * permanent before actually freeing any blocks it doesn't matter if + * they get written to. + */ + if (ip->i_d.di_nextents > 0) { /* - * If we are not changing the file size then do - * not update the on-disk file size - we may be - * called from xfs_inactive_free_eofblocks(). If we - * update the on-disk file size and then the system - * crashes before the contents of the file are - * flushed to disk then the files may be full of - * holes (ie NULL files bug). + * If we are not changing the file size then do not update + * the on-disk file size - we may be called from + * xfs_inactive_free_eofblocks(). If we update the on-disk + * file size and then the system crashes before the contents + * of the file are flushed to disk then the files may be + * full of holes (ie NULL files bug). */ if (ip->i_size != new_size) { ip->i_d.di_size = new_size; ip->i_size = new_size; + xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE); } } - xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE); - ASSERT((new_size != 0) || - (fork == XFS_ATTR_FORK) || - (ip->i_delayed_blks == 0)); - ASSERT((new_size != 0) || - (fork == XFS_ATTR_FORK) || - (ip->i_d.di_nextents == 0)); - trace_xfs_itruncate_finish_end(ip, new_size); + + error = xfs_itruncate_extents(tpp, ip, XFS_DATA_FORK, new_size); + if (error) + return error; + + /* + * If we are not changing the file size then do not update the on-disk + * file size - we may be called from xfs_inactive_free_eofblocks(). + * If we update the on-disk file size and then the system crashes + * before the contents of the file are flushed to disk then the files + * may be full of holes (ie NULL files bug). + */ + xfs_isize_check(ip, new_size); + if (ip->i_size != new_size) { + ip->i_d.di_size = new_size; + ip->i_size = new_size; + } + + ASSERT(new_size != 0 || ip->i_delayed_blks == 0); + ASSERT(new_size != 0 || ip->i_d.di_nextents == 0); + + /* + * Always re-log the inode so that our permanent transaction can keep + * on rolling it forward in the log. + */ + xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE); + + trace_xfs_itruncate_data_end(ip, new_size); return 0; } @@ -1694,7 +1434,6 @@ xfs_iunlink( ASSERT(ip->i_d.di_nlink == 0); ASSERT(ip->i_d.di_mode != 0); - ASSERT(ip->i_transp == tp); mp = tp->t_mountp; @@ -1717,7 +1456,7 @@ xfs_iunlink( ASSERT(agi->agi_unlinked[bucket_index]); ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != agino); - if (be32_to_cpu(agi->agi_unlinked[bucket_index]) != NULLAGINO) { + if (agi->agi_unlinked[bucket_index] != cpu_to_be32(NULLAGINO)) { /* * There is already another inode in the bucket we need * to add ourselves to. Add us at the front of the list. @@ -1728,8 +1467,7 @@ xfs_iunlink( if (error) return error; - ASSERT(be32_to_cpu(dip->di_next_unlinked) == NULLAGINO); - /* both on-disk, don't endian flip twice */ + ASSERT(dip->di_next_unlinked == cpu_to_be32(NULLAGINO)); dip->di_next_unlinked = agi->agi_unlinked[bucket_index]; offset = ip->i_imap.im_boffset + offsetof(xfs_dinode_t, di_next_unlinked); @@ -1794,7 +1532,7 @@ xfs_iunlink_remove( agino = XFS_INO_TO_AGINO(mp, ip->i_ino); ASSERT(agino != 0); bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS; - ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != NULLAGINO); + ASSERT(agi->agi_unlinked[bucket_index] != cpu_to_be32(NULLAGINO)); ASSERT(agi->agi_unlinked[bucket_index]); if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) { @@ -1959,7 +1697,7 @@ xfs_ifree_cluster( * stale first, we will not attempt to lock them in the loop * below as the XFS_ISTALE flag will be set. */ - lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); + lip = bp->b_fspriv; while (lip) { if (lip->li_type == XFS_LI_INODE) { iip = (xfs_inode_log_item_t *)lip; @@ -2086,7 +1824,6 @@ xfs_ifree( xfs_buf_t *ibp; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(ip->i_transp == tp); ASSERT(ip->i_d.di_nlink == 0); ASSERT(ip->i_d.di_nextents == 0); ASSERT(ip->i_d.di_anextents == 0); @@ -2733,7 +2470,7 @@ cluster_corrupt_out: * mark the buffer as an error and call them. Otherwise * mark it as stale and brelse. */ - if (XFS_BUF_IODONE_FUNC(bp)) { + if (bp->b_iodone) { XFS_BUF_UNDONE(bp); XFS_BUF_STALE(bp); XFS_BUF_ERROR(bp,EIO); @@ -2920,7 +2657,7 @@ xfs_iflush_int( */ xfs_synchronize_times(ip); - if (XFS_TEST_ERROR(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC, + if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC), mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad inode %Lu magic number 0x%x, ptr 0x%p", @@ -3073,8 +2810,8 @@ xfs_iflush_int( */ xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - ASSERT(XFS_BUF_IODONE_FUNC(bp) != NULL); + ASSERT(bp->b_fspriv != NULL); + ASSERT(bp->b_iodone != NULL); } else { /* * We're flushing an inode which is not in the AIL and has diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 3ae6d58..a97644a 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -241,7 +241,6 @@ typedef struct xfs_inode { xfs_ifork_t i_df; /* data fork */ /* Transaction and locking information. */ - struct xfs_trans *i_transp; /* ptr to owning transaction*/ struct xfs_inode_log_item *i_itemp; /* logging information */ mrlock_t i_lock; /* inode lock */ mrlock_t i_iolock; /* inode IO lock */ @@ -384,6 +383,16 @@ static inline void xfs_ifunlock(xfs_inode_t *ip) #define XFS_IDIRTY_RELEASE 0x0040 /* dirty release already seen */ /* + * Per-lifetime flags need to be reset when re-using a reclaimable inode during + * inode lookup. Thi prevents unintended behaviour on the new inode from + * ocurring. + */ +#define XFS_IRECLAIM_RESET_FLAGS \ + (XFS_IRECLAIMABLE | XFS_IRECLAIM | \ + XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \ + XFS_IFILESTREAM); + +/* * Flags for inode locking. * Bit ranges: 1<<1 - 1<<16-1 -- iolock/ilock modes (bitfield) * 1<<16 - 1<<32-1 -- lockdep annotation (integers) @@ -448,16 +457,6 @@ static inline void xfs_ifunlock(xfs_inode_t *ip) extern struct lock_class_key xfs_iolock_reclaimable; /* - * Flags for xfs_itruncate_start(). - */ -#define XFS_ITRUNC_DEFINITE 0x1 -#define XFS_ITRUNC_MAYBE 0x2 - -#define XFS_ITRUNC_FLAGS \ - { XFS_ITRUNC_DEFINITE, "DEFINITE" }, \ - { XFS_ITRUNC_MAYBE, "MAYBE" } - -/* * For multiple groups support: if S_ISGID bit is set in the parent * directory, group of new file is set to that of the parent, and * new subdirectory gets S_ISGID bit from parent. @@ -491,9 +490,10 @@ uint xfs_ip2xflags(struct xfs_inode *); uint xfs_dic2xflags(struct xfs_dinode *); int xfs_ifree(struct xfs_trans *, xfs_inode_t *, struct xfs_bmap_free *); -int xfs_itruncate_start(xfs_inode_t *, uint, xfs_fsize_t); -int xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *, - xfs_fsize_t, int, int); +int xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *, + int, xfs_fsize_t); +int xfs_itruncate_data(struct xfs_trans **, struct xfs_inode *, + xfs_fsize_t); int xfs_iunlink(struct xfs_trans *, xfs_inode_t *); void xfs_iext_realloc(xfs_inode_t *, int, int); @@ -569,13 +569,6 @@ void xfs_iext_irec_update_extoffs(xfs_ifork_t *, int, int); #define xfs_ipincount(ip) ((unsigned int) atomic_read(&ip->i_pincount)) -#ifdef DEBUG -void xfs_isize_check(struct xfs_mount *, struct xfs_inode *, - xfs_fsize_t); -#else /* DEBUG */ -#define xfs_isize_check(mp, ip, isize) -#endif /* DEBUG */ - #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); #else diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 09983a3..588406d 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -632,13 +632,8 @@ xfs_inode_item_unlock( struct xfs_inode *ip = iip->ili_inode; unsigned short lock_flags; - ASSERT(iip->ili_inode->i_itemp != NULL); - ASSERT(xfs_isilocked(iip->ili_inode, XFS_ILOCK_EXCL)); - - /* - * Clear the transaction pointer in the inode. - */ - ip->i_transp = NULL; + ASSERT(ip->i_itemp != NULL); + ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); /* * If the inode needed a separate buffer with which to log @@ -664,8 +659,8 @@ xfs_inode_item_unlock( lock_flags = iip->ili_lock_flags; iip->ili_lock_flags = 0; if (lock_flags) { - xfs_iunlock(iip->ili_inode, lock_flags); - IRELE(iip->ili_inode); + xfs_iunlock(ip, lock_flags); + IRELE(ip); } } @@ -681,15 +676,15 @@ xfs_inode_item_unlock( * where the cluster buffer may be unpinned before the inode is inserted into * the AIL during transaction committed processing. If the buffer is unpinned * before the inode item has been committed and inserted, then it is possible - * for the buffer to be written and IO completions before the inode is inserted + * for the buffer to be written and IO completes before the inode is inserted * into the AIL. In that case, we'd be inserting a clean, stale inode into the * AIL which will never get removed. It will, however, get reclaimed which * triggers an assert in xfs_inode_free() complaining about freein an inode * still in the AIL. * - * To avoid this, return a lower LSN than the one passed in so that the - * transaction committed code will not move the inode forward in the AIL but - * will still unpin it properly. + * To avoid this, just unpin the inode directly and return a LSN of -1 so the + * transaction committed code knows that it does not need to do any further + * processing on the item. */ STATIC xfs_lsn_t xfs_inode_item_committed( @@ -699,8 +694,10 @@ xfs_inode_item_committed( struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - if (xfs_iflags_test(ip, XFS_ISTALE)) - return lsn - 1; + if (xfs_iflags_test(ip, XFS_ISTALE)) { + xfs_inode_item_unpin(lip, 0); + return -1; + } return lsn; } @@ -877,7 +874,7 @@ xfs_iflush_done( * Scan the buffer IO completions for other inodes being completed and * attach them to the current inode log item. */ - blip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); + blip = bp->b_fspriv; prev = NULL; while (blip != NULL) { if (lip->li_cb != xfs_iflush_done) { @@ -889,7 +886,7 @@ xfs_iflush_done( /* remove from list */ next = blip->li_bio_list; if (!prev) { - XFS_BUF_SET_FSPRIVATE(bp, next); + bp->b_fspriv = next; } else { prev->li_bio_list = next; } diff --git a/fs/xfs/xfs_inum.h b/fs/xfs/xfs_inum.h index b8e4ee4..b253c0e 100644 --- a/fs/xfs/xfs_inum.h +++ b/fs/xfs/xfs_inum.h @@ -28,17 +28,6 @@ typedef __uint32_t xfs_agino_t; /* within allocation grp inode number */ -/* - * Useful inode bits for this kernel. - * Used in some places where having 64-bits in the 32-bit kernels - * costs too much. - */ -#if XFS_BIG_INUMS -typedef xfs_ino_t xfs_intino_t; -#else -typedef __uint32_t xfs_intino_t; -#endif - #define NULLFSINO ((xfs_ino_t)-1) #define NULLAGINO ((xfs_agino_t)-1) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 41d5b8f..06ff843 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -871,15 +871,9 @@ xlog_space_left( void xlog_iodone(xfs_buf_t *bp) { - xlog_in_core_t *iclog; - xlog_t *l; - int aborted; - - iclog = XFS_BUF_FSPRIVATE(bp, xlog_in_core_t *); - ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long) 2); - XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1); - aborted = 0; - l = iclog->ic_log; + xlog_in_core_t *iclog = bp->b_fspriv; + xlog_t *l = iclog->ic_log; + int aborted = 0; /* * Race to shutdown the filesystem if we see an error. @@ -1056,10 +1050,9 @@ xlog_alloc_log(xfs_mount_t *mp, bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp); if (!bp) goto out_free_log; - XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone); - XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1); + bp->b_iodone = xlog_iodone; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); log->l_xbuf = bp; spin_lock_init(&log->l_icloglock); @@ -1090,10 +1083,8 @@ xlog_alloc_log(xfs_mount_t *mp, log->l_iclog_size, 0); if (!bp) goto out_free_iclog; - if (!XFS_BUF_CPSEMA(bp)) - ASSERT(0); - XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone); - XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1); + + bp->b_iodone = xlog_iodone; iclog->ic_bp = bp; iclog->ic_data = bp->b_addr; #ifdef DEBUG @@ -1118,7 +1109,7 @@ xlog_alloc_log(xfs_mount_t *mp, iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize; ASSERT(XFS_BUF_ISBUSY(iclog->ic_bp)); - ASSERT(XFS_BUF_VALUSEMA(iclog->ic_bp) <= 0); + ASSERT(xfs_buf_islocked(iclog->ic_bp)); init_waitqueue_head(&iclog->ic_force_wait); init_waitqueue_head(&iclog->ic_write_wait); @@ -1254,9 +1245,8 @@ STATIC int xlog_bdstrat( struct xfs_buf *bp) { - struct xlog_in_core *iclog; + struct xlog_in_core *iclog = bp->b_fspriv; - iclog = XFS_BUF_FSPRIVATE(bp, xlog_in_core_t *); if (iclog->ic_state & XLOG_STATE_IOERROR) { XFS_BUF_ERROR(bp, EIO); XFS_BUF_STALE(bp); @@ -1269,7 +1259,6 @@ xlog_bdstrat( return 0; } - bp->b_flags |= _XBF_RUN_QUEUES; xfs_buf_iorequest(bp); return 0; } @@ -1351,8 +1340,6 @@ xlog_sync(xlog_t *log, } bp = iclog->ic_bp; - ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long)1); - XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)2); XFS_BUF_SET_ADDR(bp, BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn))); XFS_STATS_ADD(xs_log_blocks, BTOBB(count)); @@ -1366,22 +1353,28 @@ xlog_sync(xlog_t *log, iclog->ic_bwritecnt = 1; } XFS_BUF_SET_COUNT(bp, count); - XFS_BUF_SET_FSPRIVATE(bp, iclog); /* save for later */ + bp->b_fspriv = iclog; XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_ASYNC(bp); - bp->b_flags |= XBF_LOG_BUFFER; + bp->b_flags |= XBF_SYNCIO; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) { + bp->b_flags |= XBF_FUA; + /* - * If we have an external log device, flush the data device - * before flushing the log to make sure all meta data - * written back from the AIL actually made it to disk - * before writing out the new log tail LSN in the log buffer. + * Flush the data device before flushing the log to make + * sure all meta data written back from the AIL actually made + * it to disk before stamping the new log tail LSN into the + * log buffer. For an external log we need to issue the + * flush explicitly, and unfortunately synchronously here; + * for an internal log we can simply use the block layer + * state machine for preflushes. */ if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp) xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp); - XFS_BUF_ORDERED(bp); + else + bp->b_flags |= XBF_FLUSH; } ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); @@ -1404,19 +1397,16 @@ xlog_sync(xlog_t *log, } if (split) { bp = iclog->ic_log->l_xbuf; - ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == - (unsigned long)1); - XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)2); XFS_BUF_SET_ADDR(bp, 0); /* logical 0 */ XFS_BUF_SET_PTR(bp, (xfs_caddr_t)((__psint_t)&(iclog->ic_header)+ (__psint_t)count), split); - XFS_BUF_SET_FSPRIVATE(bp, iclog); + bp->b_fspriv = iclog; XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_ASYNC(bp); - bp->b_flags |= XBF_LOG_BUFFER; + bp->b_flags |= XBF_SYNCIO; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) - XFS_BUF_ORDERED(bp); + bp->b_flags |= XBF_FUA; dptr = XFS_BUF_PTR(bp); /* * Bump the cycle numbers at the start of each block @@ -3521,13 +3511,13 @@ xlog_verify_iclog(xlog_t *log, spin_unlock(&log->l_icloglock); /* check log magic numbers */ - if (be32_to_cpu(iclog->ic_header.h_magicno) != XLOG_HEADER_MAGIC_NUM) + if (iclog->ic_header.h_magicno != cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) xfs_emerg(log->l_mp, "%s: invalid magic num", __func__); ptr = (xfs_caddr_t) &iclog->ic_header; for (ptr += BBSIZE; ptr < ((xfs_caddr_t)&iclog->ic_header) + count; ptr += BBSIZE) { - if (be32_to_cpu(*(__be32 *)ptr) == XLOG_HEADER_MAGIC_NUM) + if (*(__be32 *)ptr == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) xfs_emerg(log->l_mp, "%s: unexpected magic num", __func__); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 04142ca..8fe4206 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -91,6 +91,8 @@ xlog_get_bp( xlog_t *log, int nbblks) { + struct xfs_buf *bp; + if (!xlog_buf_bbcount_valid(log, nbblks)) { xfs_warn(log->l_mp, "Invalid block length (0x%x) for buffer", nbblks); @@ -118,8 +120,10 @@ xlog_get_bp( nbblks += log->l_sectBBsize; nbblks = round_up(nbblks, log->l_sectBBsize); - return xfs_buf_get_uncached(log->l_mp->m_logdev_targp, - BBTOB(nbblks), 0); + bp = xfs_buf_get_uncached(log->l_mp->m_logdev_targp, BBTOB(nbblks), 0); + if (bp) + xfs_buf_unlock(bp); + return bp; } STATIC void @@ -264,7 +268,7 @@ xlog_bwrite( XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_HOLD(bp); - XFS_BUF_PSEMA(bp, PRIBIO); + xfs_buf_lock(bp); XFS_BUF_SET_COUNT(bp, BBTOB(nbblks)); XFS_BUF_SET_TARGET(bp, log->l_mp->m_logdev_targp); @@ -300,14 +304,14 @@ xlog_header_check_recover( xfs_mount_t *mp, xlog_rec_header_t *head) { - ASSERT(be32_to_cpu(head->h_magicno) == XLOG_HEADER_MAGIC_NUM); + ASSERT(head->h_magicno == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)); /* * IRIX doesn't write the h_fmt field and leaves it zeroed * (XLOG_FMT_UNKNOWN). This stops us from trying to recover * a dirty log created in IRIX. */ - if (unlikely(be32_to_cpu(head->h_fmt) != XLOG_FMT)) { + if (unlikely(head->h_fmt != cpu_to_be32(XLOG_FMT))) { xfs_warn(mp, "dirty log written in incompatible format - can't recover"); xlog_header_check_dump(mp, head); @@ -333,7 +337,7 @@ xlog_header_check_mount( xfs_mount_t *mp, xlog_rec_header_t *head) { - ASSERT(be32_to_cpu(head->h_magicno) == XLOG_HEADER_MAGIC_NUM); + ASSERT(head->h_magicno == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)); if (uuid_is_nil(&head->h_fs_uuid)) { /* @@ -367,7 +371,7 @@ xlog_recover_iodone( xfs_force_shutdown(bp->b_target->bt_mount, SHUTDOWN_META_IO_ERROR); } - XFS_BUF_CLR_IODONE_FUNC(bp); + bp->b_iodone = NULL; xfs_buf_ioend(bp, 0); } @@ -534,7 +538,7 @@ xlog_find_verify_log_record( head = (xlog_rec_header_t *)offset; - if (XLOG_HEADER_MAGIC_NUM == be32_to_cpu(head->h_magicno)) + if (head->h_magicno == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) break; if (!smallmem) @@ -916,7 +920,7 @@ xlog_find_tail( if (error) goto done; - if (XLOG_HEADER_MAGIC_NUM == be32_to_cpu(*(__be32 *)offset)) { + if (*(__be32 *)offset == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { found = 1; break; } @@ -933,8 +937,8 @@ xlog_find_tail( if (error) goto done; - if (XLOG_HEADER_MAGIC_NUM == - be32_to_cpu(*(__be32 *)offset)) { + if (*(__be32 *)offset == + cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) { found = 2; break; } @@ -1947,7 +1951,7 @@ xfs_qm_dqcheck( * This is all fine; things are still consistent, and we haven't lost * any quota information. Just don't complain about bad dquot blks. */ - if (be16_to_cpu(ddq->d_magic) != XFS_DQUOT_MAGIC) { + if (ddq->d_magic != cpu_to_be16(XFS_DQUOT_MAGIC)) { if (flags & XFS_QMOPT_DOWARN) xfs_alert(mp, "%s : XFS dquot ID 0x%x, magic 0x%x != 0x%x", @@ -2174,7 +2178,7 @@ xlog_recover_buffer_pass2( error = xfs_bwrite(mp, bp); } else { ASSERT(bp->b_target->bt_mount == mp); - XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone); + bp->b_iodone = xlog_recover_iodone; xfs_bdwrite(mp, bp); } @@ -2238,7 +2242,7 @@ xlog_recover_inode_pass2( * Make sure the place we're flushing out to really looks * like an inode! */ - if (unlikely(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)) { + if (unlikely(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))) { xfs_buf_relse(bp); xfs_alert(mp, "%s: Bad inode magic number, dip = 0x%p, dino bp = 0x%p, ino = %Ld", @@ -2434,7 +2438,7 @@ xlog_recover_inode_pass2( write_inode_buffer: ASSERT(bp->b_target->bt_mount == mp); - XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone); + bp->b_iodone = xlog_recover_iodone; xfs_bdwrite(mp, bp); error: if (need_free) @@ -2556,7 +2560,7 @@ xlog_recover_dquot_pass2( ASSERT(dq_f->qlf_size == 2); ASSERT(bp->b_target->bt_mount == mp); - XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone); + bp->b_iodone = xlog_recover_iodone; xfs_bdwrite(mp, bp); return (0); @@ -3295,7 +3299,7 @@ xlog_valid_rec_header( { int hlen; - if (unlikely(be32_to_cpu(rhead->h_magicno) != XLOG_HEADER_MAGIC_NUM)) { + if (unlikely(rhead->h_magicno != cpu_to_be32(XLOG_HEADER_MAGIC_NUM))) { XFS_ERROR_REPORT("xlog_valid_rec_header(1)", XFS_ERRLEVEL_LOW, log->l_mp); return XFS_ERROR(EFSCORRUPTED); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index b49b823..7f25245 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -348,7 +348,7 @@ xfs_mount_validate_sb( } /* - * More sanity checking. These were stolen directly from + * More sanity checking. Most of these were stolen directly from * xfs_repair. */ if (unlikely( @@ -371,23 +371,13 @@ xfs_mount_validate_sb( (sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog) || (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE) || (sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) || - (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */))) { + (sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */) || + sbp->sb_dblocks == 0 || + sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) || + sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) { if (loud) - xfs_warn(mp, "SB sanity check 1 failed"); - return XFS_ERROR(EFSCORRUPTED); - } - - /* - * Sanity check AG count, size fields against data size field - */ - if (unlikely( - sbp->sb_dblocks == 0 || - sbp->sb_dblocks > - (xfs_drfsbno_t)sbp->sb_agcount * sbp->sb_agblocks || - sbp->sb_dblocks < (xfs_drfsbno_t)(sbp->sb_agcount - 1) * - sbp->sb_agblocks + XFS_MIN_AG_BLOCKS)) { - if (loud) - xfs_warn(mp, "SB sanity check 2 failed"); + XFS_CORRUPTION_ERROR("SB sanity check failed", + XFS_ERRLEVEL_LOW, mp, sbp); return XFS_ERROR(EFSCORRUPTED); } @@ -864,7 +854,8 @@ xfs_update_alignment(xfs_mount_t *mp) if ((BBTOB(mp->m_dalign) & mp->m_blockmask) || (BBTOB(mp->m_swidth) & mp->m_blockmask)) { if (mp->m_flags & XFS_MOUNT_RETERR) { - xfs_warn(mp, "alignment check 1 failed"); + xfs_warn(mp, "alignment check failed: " + "(sunit/swidth vs. blocksize)"); return XFS_ERROR(EINVAL); } mp->m_dalign = mp->m_swidth = 0; @@ -875,6 +866,8 @@ xfs_update_alignment(xfs_mount_t *mp) mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign); if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) { if (mp->m_flags & XFS_MOUNT_RETERR) { + xfs_warn(mp, "alignment check failed: " + "(sunit/swidth vs. ag size)"); return XFS_ERROR(EINVAL); } xfs_warn(mp, @@ -889,8 +882,8 @@ xfs_update_alignment(xfs_mount_t *mp) mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth); } else { if (mp->m_flags & XFS_MOUNT_RETERR) { - xfs_warn(mp, - "stripe alignment turned off: sunit(%d) less than bsize(%d)", + xfs_warn(mp, "alignment check failed: " + "sunit(%d) less than bsize(%d)", mp->m_dalign, mp->m_blockmask +1); return XFS_ERROR(EINVAL); @@ -1096,10 +1089,6 @@ xfs_mount_reset_sbqflags( if (mp->m_flags & XFS_MOUNT_RDONLY) return 0; -#ifdef QUOTADEBUG - xfs_notice(mp, "Writing superblock quota changes"); -#endif - tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE); error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0, XFS_DEFAULT_LOG_COUNT); @@ -1532,7 +1521,7 @@ xfs_unmountfs( xfs_warn(mp, "Unable to free reserved block pool. " "Freespace may not be correct on next mount."); - error = xfs_log_sbcount(mp, 1); + error = xfs_log_sbcount(mp); if (error) xfs_warn(mp, "Unable to update superblock counters. " "Freespace may not be correct on next mount."); @@ -1568,18 +1557,14 @@ xfs_fs_writable(xfs_mount_t *mp) /* * xfs_log_sbcount * - * Called either periodically to keep the on disk superblock values - * roughly up to date or from unmount to make sure the values are - * correct on a clean unmount. + * Sync the superblock counters to disk. * * Note this code can be called during the process of freezing, so - * we may need to use the transaction allocator which does not not + * we may need to use the transaction allocator which does not * block when the transaction subsystem is in its frozen state. */ int -xfs_log_sbcount( - xfs_mount_t *mp, - uint sync) +xfs_log_sbcount(xfs_mount_t *mp) { xfs_trans_t *tp; int error; @@ -1605,8 +1590,7 @@ xfs_log_sbcount( } xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS); - if (sync) - xfs_trans_set_sync(tp); + xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, 0); return error; } @@ -1941,22 +1925,19 @@ unwind: * the superblock buffer if it can be locked without sleeping. * If it can't then we'll return NULL. */ -xfs_buf_t * +struct xfs_buf * xfs_getsb( - xfs_mount_t *mp, - int flags) + struct xfs_mount *mp, + int flags) { - xfs_buf_t *bp; + struct xfs_buf *bp = mp->m_sb_bp; - ASSERT(mp->m_sb_bp != NULL); - bp = mp->m_sb_bp; - if (flags & XBF_TRYLOCK) { - if (!XFS_BUF_CPSEMA(bp)) { + if (!xfs_buf_trylock(bp)) { + if (flags & XBF_TRYLOCK) return NULL; - } - } else { - XFS_BUF_PSEMA(bp, PRIBIO); + xfs_buf_lock(bp); } + XFS_BUF_HOLD(bp); ASSERT(XFS_BUF_ISDONE(bp)); return bp; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 3d68bb2..bb24dac 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -371,7 +371,7 @@ typedef struct xfs_mod_sb { int64_t msb_delta; /* Change to make to specified field */ } xfs_mod_sb_t; -extern int xfs_log_sbcount(xfs_mount_t *, uint); +extern int xfs_log_sbcount(xfs_mount_t *); extern __uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 7c7bc2b..efc147f 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -1361,7 +1361,7 @@ xfs_trans_item_committed( lip->li_flags |= XFS_LI_ABORTED; item_lsn = IOP_COMMITTED(lip, commit_lsn); - /* If the committed routine returns -1, item has been freed. */ + /* item_lsn of -1 means the item needs no further processing */ if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0) return; @@ -1426,6 +1426,7 @@ xfs_trans_committed( static inline void xfs_log_item_batch_insert( struct xfs_ail *ailp, + struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t commit_lsn) @@ -1434,7 +1435,7 @@ xfs_log_item_batch_insert( spin_lock(&ailp->xa_lock); /* xfs_trans_ail_update_bulk drops ailp->xa_lock */ - xfs_trans_ail_update_bulk(ailp, log_items, nr_items, commit_lsn); + xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn); for (i = 0; i < nr_items; i++) IOP_UNPIN(log_items[i], 0); @@ -1452,6 +1453,13 @@ xfs_log_item_batch_insert( * as an iclog write error even though we haven't started any IO yet. Hence in * this case all we need to do is IOP_COMMITTED processing, followed by an * IOP_UNPIN(aborted) call. + * + * The AIL cursor is used to optimise the insert process. If commit_lsn is not + * at the end of the AIL, the insert cursor avoids the need to walk + * the AIL to find the insertion point on every xfs_log_item_batch_insert() + * call. This saves a lot of needless list walking and is a net win, even + * though it slightly increases that amount of AIL lock traffic to set it up + * and tear it down. */ void xfs_trans_committed_bulk( @@ -1463,8 +1471,13 @@ xfs_trans_committed_bulk( #define LOG_ITEM_BATCH_SIZE 32 struct xfs_log_item *log_items[LOG_ITEM_BATCH_SIZE]; struct xfs_log_vec *lv; + struct xfs_ail_cursor cur; int i = 0; + spin_lock(&ailp->xa_lock); + xfs_trans_ail_cursor_last(ailp, &cur, commit_lsn); + spin_unlock(&ailp->xa_lock); + /* unpin all the log items */ for (lv = log_vector; lv; lv = lv->lv_next ) { struct xfs_log_item *lip = lv->lv_item; @@ -1474,7 +1487,7 @@ xfs_trans_committed_bulk( lip->li_flags |= XFS_LI_ABORTED; item_lsn = IOP_COMMITTED(lip, commit_lsn); - /* item_lsn of -1 means the item was freed */ + /* item_lsn of -1 means the item needs no further processing */ if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0) continue; @@ -1493,7 +1506,9 @@ xfs_trans_committed_bulk( /* * Not a bulk update option due to unusual item_lsn. * Push into AIL immediately, rechecking the lsn once - * we have the ail lock. Then unpin the item. + * we have the ail lock. Then unpin the item. This does + * not affect the AIL cursor the bulk insert path is + * using. */ spin_lock(&ailp->xa_lock); if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0) @@ -1507,7 +1522,7 @@ xfs_trans_committed_bulk( /* Item is a candidate for bulk AIL insert. */ log_items[i++] = lv->lv_item; if (i >= LOG_ITEM_BATCH_SIZE) { - xfs_log_item_batch_insert(ailp, log_items, + xfs_log_item_batch_insert(ailp, &cur, log_items, LOG_ITEM_BATCH_SIZE, commit_lsn); i = 0; } @@ -1515,7 +1530,11 @@ xfs_trans_committed_bulk( /* make sure we insert the remainder! */ if (i) - xfs_log_item_batch_insert(ailp, log_items, i, commit_lsn); + xfs_log_item_batch_insert(ailp, &cur, log_items, i, commit_lsn); + + spin_lock(&ailp->xa_lock); + xfs_trans_ail_cursor_done(ailp, &cur); + spin_unlock(&ailp->xa_lock); } /* diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 5fc2380..43233e9 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -163,17 +163,11 @@ xfs_ail_max_lsn( } /* - * AIL traversal cursor initialisation. - * - * The cursor keeps track of where our current traversal is up - * to by tracking the next Æ£tem in the list for us. However, for - * this to be safe, removing an object from the AIL needs to invalidate - * any cursor that points to it. hence the traversal cursor needs to - * be linked to the struct xfs_ail so that deletion can search all the - * active cursors for invalidation. - * - * We don't link the push cursor because it is embedded in the struct - * xfs_ail and hence easily findable. + * The cursor keeps track of where our current traversal is up to by tracking + * the next item in the list for us. However, for this to be safe, removing an + * object from the AIL needs to invalidate any cursor that points to it. hence + * the traversal cursor needs to be linked to the struct xfs_ail so that + * deletion can search all the active cursors for invalidation. */ STATIC void xfs_trans_ail_cursor_init( @@ -181,31 +175,12 @@ xfs_trans_ail_cursor_init( struct xfs_ail_cursor *cur) { cur->item = NULL; - if (cur == &ailp->xa_cursors) - return; - - cur->next = ailp->xa_cursors.next; - ailp->xa_cursors.next = cur; -} - -/* - * Set the cursor to the next item, because when we look - * up the cursor the current item may have been freed. - */ -STATIC void -xfs_trans_ail_cursor_set( - struct xfs_ail *ailp, - struct xfs_ail_cursor *cur, - struct xfs_log_item *lip) -{ - if (lip) - cur->item = xfs_ail_next(ailp, lip); + list_add_tail(&cur->list, &ailp->xa_cursors); } /* - * Get the next item in the traversal and advance the cursor. - * If the cursor was invalidated (inidicated by a lip of 1), - * restart the traversal. + * Get the next item in the traversal and advance the cursor. If the cursor + * was invalidated (indicated by a lip of 1), restart the traversal. */ struct xfs_log_item * xfs_trans_ail_cursor_next( @@ -216,45 +191,31 @@ xfs_trans_ail_cursor_next( if ((__psint_t)lip & 1) lip = xfs_ail_min(ailp); - xfs_trans_ail_cursor_set(ailp, cur, lip); + if (lip) + cur->item = xfs_ail_next(ailp, lip); return lip; } /* - * Now that the traversal is complete, we need to remove the cursor - * from the list of traversing cursors. Avoid removing the embedded - * push cursor, but use the fact it is always present to make the - * list deletion simple. + * When the traversal is complete, we need to remove the cursor from the list + * of traversing cursors. */ void xfs_trans_ail_cursor_done( struct xfs_ail *ailp, - struct xfs_ail_cursor *done) + struct xfs_ail_cursor *cur) { - struct xfs_ail_cursor *prev = NULL; - struct xfs_ail_cursor *cur; - - done->item = NULL; - if (done == &ailp->xa_cursors) - return; - prev = &ailp->xa_cursors; - for (cur = prev->next; cur; prev = cur, cur = prev->next) { - if (cur == done) { - prev->next = cur->next; - break; - } - } - ASSERT(cur); + cur->item = NULL; + list_del_init(&cur->list); } /* - * Invalidate any cursor that is pointing to this item. This is - * called when an item is removed from the AIL. Any cursor pointing - * to this object is now invalid and the traversal needs to be - * terminated so it doesn't reference a freed object. We set the - * cursor item to a value of 1 so we can distinguish between an - * invalidation and the end of the list when getting the next item - * from the cursor. + * Invalidate any cursor that is pointing to this item. This is called when an + * item is removed from the AIL. Any cursor pointing to this object is now + * invalid and the traversal needs to be terminated so it doesn't reference a + * freed object. We set the low bit of the cursor item pointer so we can + * distinguish between an invalidation and the end of the list when getting the + * next item from the cursor. */ STATIC void xfs_trans_ail_cursor_clear( @@ -263,8 +224,7 @@ xfs_trans_ail_cursor_clear( { struct xfs_ail_cursor *cur; - /* need to search all cursors */ - for (cur = &ailp->xa_cursors; cur; cur = cur->next) { + list_for_each_entry(cur, &ailp->xa_cursors, list) { if (cur->item == lip) cur->item = (struct xfs_log_item *) ((__psint_t)cur->item | 1); @@ -272,9 +232,10 @@ xfs_trans_ail_cursor_clear( } /* - * Return the item in the AIL with the current lsn. - * Return the current tree generation number for use - * in calls to xfs_trans_next_ail(). + * Find the first item in the AIL with the given @lsn by searching in ascending + * LSN order and initialise the cursor to point to the next item for a + * ascending traversal. Pass a @lsn of zero to initialise the cursor to the + * first item in the AIL. Returns NULL if the list is empty. */ xfs_log_item_t * xfs_trans_ail_cursor_first( @@ -285,46 +246,112 @@ xfs_trans_ail_cursor_first( xfs_log_item_t *lip; xfs_trans_ail_cursor_init(ailp, cur); - lip = xfs_ail_min(ailp); - if (lsn == 0) + + if (lsn == 0) { + lip = xfs_ail_min(ailp); goto out; + } list_for_each_entry(lip, &ailp->xa_ail, li_ail) { if (XFS_LSN_CMP(lip->li_lsn, lsn) >= 0) goto out; } - lip = NULL; + return NULL; + out: - xfs_trans_ail_cursor_set(ailp, cur, lip); + if (lip) + cur->item = xfs_ail_next(ailp, lip); return lip; } +static struct xfs_log_item * +__xfs_trans_ail_cursor_last( + struct xfs_ail *ailp, + xfs_lsn_t lsn) +{ + xfs_log_item_t *lip; + + list_for_each_entry_reverse(lip, &ailp->xa_ail, li_ail) { + if (XFS_LSN_CMP(lip->li_lsn, lsn) <= 0) + return lip; + } + return NULL; +} + +/* + * Find the last item in the AIL with the given @lsn by searching in descending + * LSN order and initialise the cursor to point to that item. If there is no + * item with the value of @lsn, then it sets the cursor to the last item with an + * LSN lower than @lsn. Returns NULL if the list is empty. + */ +struct xfs_log_item * +xfs_trans_ail_cursor_last( + struct xfs_ail *ailp, + struct xfs_ail_cursor *cur, + xfs_lsn_t lsn) +{ + xfs_trans_ail_cursor_init(ailp, cur); + cur->item = __xfs_trans_ail_cursor_last(ailp, lsn); + return cur->item; +} + /* - * splice the log item list into the AIL at the given LSN. + * Splice the log item list into the AIL at the given LSN. We splice to the + * tail of the given LSN to maintain insert order for push traversals. The + * cursor is optional, allowing repeated updates to the same LSN to avoid + * repeated traversals. */ static void xfs_ail_splice( - struct xfs_ail *ailp, - struct list_head *list, - xfs_lsn_t lsn) + struct xfs_ail *ailp, + struct xfs_ail_cursor *cur, + struct list_head *list, + xfs_lsn_t lsn) { - xfs_log_item_t *next_lip; + struct xfs_log_item *lip = cur ? cur->item : NULL; + struct xfs_log_item *next_lip; - /* If the list is empty, just insert the item. */ - if (list_empty(&ailp->xa_ail)) { - list_splice(list, &ailp->xa_ail); - return; + /* + * Get a new cursor if we don't have a placeholder or the existing one + * has been invalidated. + */ + if (!lip || (__psint_t)lip & 1) { + lip = __xfs_trans_ail_cursor_last(ailp, lsn); + + if (!lip) { + /* The list is empty, so just splice and return. */ + if (cur) + cur->item = NULL; + list_splice(list, &ailp->xa_ail); + return; + } } - list_for_each_entry_reverse(next_lip, &ailp->xa_ail, li_ail) { - if (XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0) - break; + /* + * Our cursor points to the item we want to insert _after_, so we have + * to update the cursor to point to the end of the list we are splicing + * in so that it points to the correct location for the next splice. + * i.e. before the splice + * + * lsn -> lsn -> lsn + x -> lsn + x ... + * ^ + * | cursor points here + * + * After the splice we have: + * + * lsn -> lsn -> lsn -> lsn -> .... -> lsn -> lsn + x -> lsn + x ... + * ^ ^ + * | cursor points here | needs to move here + * + * So we set the cursor to the last item in the list to be spliced + * before we execute the splice, resulting in the cursor pointing to + * the correct item after the splice occurs. + */ + if (cur) { + next_lip = list_entry(list->prev, struct xfs_log_item, li_ail); + cur->item = next_lip; } - - ASSERT(&next_lip->li_ail == &ailp->xa_ail || - XFS_LSN_CMP(next_lip->li_lsn, lsn) <= 0); - - list_splice_init(list, &next_lip->li_ail); + list_splice(list, &lip->li_ail); } /* @@ -351,7 +378,7 @@ xfs_ail_worker( struct xfs_ail *ailp = container_of(to_delayed_work(work), struct xfs_ail, xa_work); xfs_mount_t *mp = ailp->xa_mount; - struct xfs_ail_cursor *cur = &ailp->xa_cursors; + struct xfs_ail_cursor cur; xfs_log_item_t *lip; xfs_lsn_t lsn; xfs_lsn_t target; @@ -363,13 +390,12 @@ xfs_ail_worker( spin_lock(&ailp->xa_lock); target = ailp->xa_target; - xfs_trans_ail_cursor_init(ailp, cur); - lip = xfs_trans_ail_cursor_first(ailp, cur, ailp->xa_last_pushed_lsn); + lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn); if (!lip || XFS_FORCED_SHUTDOWN(mp)) { /* * AIL is empty or our push has reached the end. */ - xfs_trans_ail_cursor_done(ailp, cur); + xfs_trans_ail_cursor_done(ailp, &cur); spin_unlock(&ailp->xa_lock); goto out_done; } @@ -457,12 +483,12 @@ xfs_ail_worker( if (stuck > 100) break; - lip = xfs_trans_ail_cursor_next(ailp, cur); + lip = xfs_trans_ail_cursor_next(ailp, &cur); if (lip == NULL) break; lsn = lip->li_lsn; } - xfs_trans_ail_cursor_done(ailp, cur); + xfs_trans_ail_cursor_done(ailp, &cur); spin_unlock(&ailp->xa_lock); if (flush_log) { @@ -645,6 +671,7 @@ xfs_trans_unlocked_item( void xfs_trans_ail_update_bulk( struct xfs_ail *ailp, + struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t lsn) __releases(ailp->xa_lock) @@ -674,7 +701,7 @@ xfs_trans_ail_update_bulk( list_add(&lip->li_ail, &tmp); } - xfs_ail_splice(ailp, &tmp, lsn); + xfs_ail_splice(ailp, cur, &tmp, lsn); if (!mlip_changed) { spin_unlock(&ailp->xa_lock); @@ -793,6 +820,7 @@ xfs_trans_ail_init( ailp->xa_mount = mp; INIT_LIST_HEAD(&ailp->xa_ail); + INIT_LIST_HEAD(&ailp->xa_cursors); spin_lock_init(&ailp->xa_lock); INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker); mp->m_ail = ailp; diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 03b3b7f..15584fc 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -81,7 +81,7 @@ _xfs_trans_bjoin( struct xfs_buf_log_item *bip; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, void *) == NULL); + ASSERT(bp->b_transp == NULL); /* * The xfs_buf_log_item pointer is stored in b_fsprivate. If @@ -89,7 +89,7 @@ _xfs_trans_bjoin( * The checks to see if one is there are in xfs_buf_item_init(). */ xfs_buf_item_init(bp, tp->t_mountp); - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + bip = bp->b_fspriv; ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL)); ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED)); @@ -110,7 +110,7 @@ _xfs_trans_bjoin( * Initialize b_fsprivate2 so we can find it with incore_match() * in xfs_trans_get_buf() and friends above. */ - XFS_BUF_SET_FSPRIVATE2(bp, tp); + bp->b_transp = tp; } @@ -160,7 +160,7 @@ xfs_trans_get_buf(xfs_trans_t *tp, */ bp = xfs_trans_buf_item_match(tp, target_dev, blkno, len); if (bp != NULL) { - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); + ASSERT(xfs_buf_islocked(bp)); if (XFS_FORCED_SHUTDOWN(tp->t_mountp)) XFS_BUF_SUPER_STALE(bp); @@ -172,8 +172,8 @@ xfs_trans_get_buf(xfs_trans_t *tp, else if (XFS_BUF_ISSTALE(bp)) ASSERT(!XFS_BUF_ISDELAYWRITE(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + bip = bp->b_fspriv; ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_recur++; @@ -232,8 +232,8 @@ xfs_trans_getsb(xfs_trans_t *tp, * recursion count and return the buffer to the caller. */ bp = mp->m_sb_bp; - if (XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp) { - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*); + if (bp->b_transp == tp) { + bip = bp->b_fspriv; ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_recur++; @@ -327,9 +327,9 @@ xfs_trans_read_buf( */ bp = xfs_trans_buf_item_match(tp, target, blkno, len); if (bp != NULL) { - ASSERT(XFS_BUF_VALUSEMA(bp) <= 0); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); + ASSERT(xfs_buf_islocked(bp)); + ASSERT(bp->b_transp == tp); + ASSERT(bp->b_fspriv != NULL); ASSERT((XFS_BUF_ISERROR(bp)) == 0); if (!(XFS_BUF_ISDONE(bp))) { trace_xfs_trans_read_buf_io(bp, _RET_IP_); @@ -363,7 +363,7 @@ xfs_trans_read_buf( } - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t*); + bip = bp->b_fspriv; bip->bli_recur++; ASSERT(atomic_read(&bip->bli_refcount) > 0); @@ -460,32 +460,30 @@ xfs_trans_brelse(xfs_trans_t *tp, xfs_buf_t *bp) { xfs_buf_log_item_t *bip; - xfs_log_item_t *lip; /* * Default to a normal brelse() call if the tp is NULL. */ if (tp == NULL) { - ASSERT(XFS_BUF_FSPRIVATE2(bp, void *) == NULL); + struct xfs_log_item *lip = bp->b_fspriv; + + ASSERT(bp->b_transp == NULL); + /* * If there's a buf log item attached to the buffer, * then let the AIL know that the buffer is being * unlocked. */ - if (XFS_BUF_FSPRIVATE(bp, void *) != NULL) { - lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *); - if (lip->li_type == XFS_LI_BUF) { - bip = XFS_BUF_FSPRIVATE(bp,xfs_buf_log_item_t*); - xfs_trans_unlocked_item(bip->bli_item.li_ailp, - lip); - } + if (lip != NULL && lip->li_type == XFS_LI_BUF) { + bip = bp->b_fspriv; + xfs_trans_unlocked_item(bip->bli_item.li_ailp, lip); } xfs_buf_relse(bp); return; } - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + bip = bp->b_fspriv; ASSERT(bip->bli_item.li_type == XFS_LI_BUF); ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL)); @@ -556,7 +554,7 @@ xfs_trans_brelse(xfs_trans_t *tp, xfs_buf_item_relse(bp); bip = NULL; } - XFS_BUF_SET_FSPRIVATE2(bp, NULL); + bp->b_transp = NULL; /* * If we've still got a buf log item on the buffer, then @@ -581,16 +579,15 @@ void xfs_trans_bhold(xfs_trans_t *tp, xfs_buf_t *bp) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL)); ASSERT(atomic_read(&bip->bli_refcount) > 0); + bip->bli_flags |= XFS_BLI_HOLD; trace_xfs_trans_bhold(bip); } @@ -603,19 +600,17 @@ void xfs_trans_bhold_release(xfs_trans_t *tp, xfs_buf_t *bp) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_CANCEL)); ASSERT(atomic_read(&bip->bli_refcount) > 0); ASSERT(bip->bli_flags & XFS_BLI_HOLD); - bip->bli_flags &= ~XFS_BLI_HOLD; + bip->bli_flags &= ~XFS_BLI_HOLD; trace_xfs_trans_bhold_release(bip); } @@ -634,14 +629,14 @@ xfs_trans_log_buf(xfs_trans_t *tp, uint first, uint last) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT((first <= last) && (last < XFS_BUF_COUNT(bp))); - ASSERT((XFS_BUF_IODONE_FUNC(bp) == NULL) || - (XFS_BUF_IODONE_FUNC(bp) == xfs_buf_iodone_callbacks)); + ASSERT(bp->b_iodone == NULL || + bp->b_iodone == xfs_buf_iodone_callbacks); /* * Mark the buffer as needing to be written out eventually, @@ -656,9 +651,8 @@ xfs_trans_log_buf(xfs_trans_t *tp, XFS_BUF_DELAYWRITE(bp); XFS_BUF_DONE(bp); - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); ASSERT(atomic_read(&bip->bli_refcount) > 0); - XFS_BUF_SET_IODONE_FUNC(bp, xfs_buf_iodone_callbacks); + bp->b_iodone = xfs_buf_iodone_callbacks; bip->bli_item.li_cb = xfs_buf_iodone; trace_xfs_trans_log_buf(bip); @@ -706,13 +700,11 @@ xfs_trans_binval( xfs_trans_t *tp, xfs_buf_t *bp) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); trace_xfs_trans_binval(bip); @@ -780,13 +772,11 @@ xfs_trans_inode_buf( xfs_trans_t *tp, xfs_buf_t *bp) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_BUF; @@ -806,13 +796,11 @@ xfs_trans_stale_inode_buf( xfs_trans_t *tp, xfs_buf_t *bp) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_STALE_INODE; @@ -833,13 +821,11 @@ xfs_trans_inode_alloc_buf( xfs_trans_t *tp, xfs_buf_t *bp) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_flags |= XFS_BLI_INODE_ALLOC_BUF; @@ -863,16 +849,14 @@ xfs_trans_dquot_buf( xfs_buf_t *bp, uint type) { - xfs_buf_log_item_t *bip; + xfs_buf_log_item_t *bip = bp->b_fspriv; ASSERT(XFS_BUF_ISBUSY(bp)); - ASSERT(XFS_BUF_FSPRIVATE2(bp, xfs_trans_t *) == tp); - ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL); + ASSERT(bp->b_transp == tp); + ASSERT(bip != NULL); ASSERT(type == XFS_BLF_UDQUOT_BUF || type == XFS_BLF_PDQUOT_BUF || type == XFS_BLF_GDQUOT_BUF); - - bip = XFS_BUF_FSPRIVATE(bp, xfs_buf_log_item_t *); ASSERT(atomic_read(&bip->bli_refcount) > 0); bip->bli_format.blf_flags |= type; diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 048b0c6..c8dea2f 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -55,7 +55,6 @@ xfs_trans_ijoin( { xfs_inode_log_item_t *iip; - ASSERT(ip->i_transp == NULL); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); if (ip->i_itemp == NULL) xfs_inode_item_init(ip, ip->i_mount); @@ -68,12 +67,6 @@ xfs_trans_ijoin( xfs_trans_add_item(tp, &iip->ili_item); xfs_trans_inode_broot_debug(ip); - - /* - * Initialize i_transp so we can find it with xfs_inode_incore() - * in xfs_trans_iget() above. - */ - ip->i_transp = tp; } /* @@ -111,7 +104,6 @@ xfs_trans_ichgtime( ASSERT(tp); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(ip->i_transp == tp); tv = current_fs_time(inode->i_sb); @@ -140,7 +132,6 @@ xfs_trans_log_inode( xfs_inode_t *ip, uint flags) { - ASSERT(ip->i_transp == tp); ASSERT(ip->i_itemp != NULL); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 6b164e9..212946b 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -53,7 +53,7 @@ void xfs_trans_committed_bulk(struct xfs_ail *ailp, struct xfs_log_vec *lv, * of the list to trigger traversal restarts. */ struct xfs_ail_cursor { - struct xfs_ail_cursor *next; + struct list_head list; struct xfs_log_item *item; }; @@ -66,7 +66,7 @@ struct xfs_ail { struct xfs_mount *xa_mount; struct list_head xa_ail; xfs_lsn_t xa_target; - struct xfs_ail_cursor xa_cursors; + struct list_head xa_cursors; spinlock_t xa_lock; struct delayed_work xa_work; xfs_lsn_t xa_last_pushed_lsn; @@ -82,6 +82,7 @@ struct xfs_ail { extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */ void xfs_trans_ail_update_bulk(struct xfs_ail *ailp, + struct xfs_ail_cursor *cur, struct xfs_log_item **log_items, int nr_items, xfs_lsn_t lsn) __releases(ailp->xa_lock); static inline void @@ -90,7 +91,7 @@ xfs_trans_ail_update( struct xfs_log_item *lip, xfs_lsn_t lsn) __releases(ailp->xa_lock) { - xfs_trans_ail_update_bulk(ailp, &lip, 1, lsn); + xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn); } void xfs_trans_ail_delete_bulk(struct xfs_ail *ailp, @@ -111,10 +112,13 @@ xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp); void xfs_trans_unlocked_item(struct xfs_ail *, xfs_log_item_t *); -struct xfs_log_item *xfs_trans_ail_cursor_first(struct xfs_ail *ailp, +struct xfs_log_item * xfs_trans_ail_cursor_first(struct xfs_ail *ailp, struct xfs_ail_cursor *cur, xfs_lsn_t lsn); -struct xfs_log_item *xfs_trans_ail_cursor_next(struct xfs_ail *ailp, +struct xfs_log_item * xfs_trans_ail_cursor_last(struct xfs_ail *ailp, + struct xfs_ail_cursor *cur, + xfs_lsn_t lsn); +struct xfs_log_item * xfs_trans_ail_cursor_next(struct xfs_ail *ailp, struct xfs_ail_cursor *cur); void xfs_trans_ail_cursor_done(struct xfs_ail *ailp, struct xfs_ail_cursor *cur); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index b7a5fe7..88d1214 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -50,430 +50,6 @@ #include "xfs_vnodeops.h" #include "xfs_trace.h" -int -xfs_setattr( - struct xfs_inode *ip, - struct iattr *iattr, - int flags) -{ - xfs_mount_t *mp = ip->i_mount; - struct inode *inode = VFS_I(ip); - int mask = iattr->ia_valid; - xfs_trans_t *tp; - int code; - uint lock_flags; - uint commit_flags=0; - uid_t uid=0, iuid=0; - gid_t gid=0, igid=0; - struct xfs_dquot *udqp, *gdqp, *olddquot1, *olddquot2; - int need_iolock = 1; - - trace_xfs_setattr(ip); - - if (mp->m_flags & XFS_MOUNT_RDONLY) - return XFS_ERROR(EROFS); - - if (XFS_FORCED_SHUTDOWN(mp)) - return XFS_ERROR(EIO); - - code = -inode_change_ok(inode, iattr); - if (code) - return code; - - olddquot1 = olddquot2 = NULL; - udqp = gdqp = NULL; - - /* - * If disk quotas is on, we make sure that the dquots do exist on disk, - * before we start any other transactions. Trying to do this later - * is messy. We don't care to take a readlock to look at the ids - * in inode here, because we can't hold it across the trans_reserve. - * If the IDs do change before we take the ilock, we're covered - * because the i_*dquot fields will get updated anyway. - */ - if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) { - uint qflags = 0; - - if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) { - uid = iattr->ia_uid; - qflags |= XFS_QMOPT_UQUOTA; - } else { - uid = ip->i_d.di_uid; - } - if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) { - gid = iattr->ia_gid; - qflags |= XFS_QMOPT_GQUOTA; - } else { - gid = ip->i_d.di_gid; - } - - /* - * We take a reference when we initialize udqp and gdqp, - * so it is important that we never blindly double trip on - * the same variable. See xfs_create() for an example. - */ - ASSERT(udqp == NULL); - ASSERT(gdqp == NULL); - code = xfs_qm_vop_dqalloc(ip, uid, gid, xfs_get_projid(ip), - qflags, &udqp, &gdqp); - if (code) - return code; - } - - /* - * For the other attributes, we acquire the inode lock and - * first do an error checking pass. - */ - tp = NULL; - lock_flags = XFS_ILOCK_EXCL; - if (flags & XFS_ATTR_NOLOCK) - need_iolock = 0; - if (!(mask & ATTR_SIZE)) { - tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); - commit_flags = 0; - code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), - 0, 0, 0); - if (code) { - lock_flags = 0; - goto error_return; - } - } else { - if (need_iolock) - lock_flags |= XFS_IOLOCK_EXCL; - } - - xfs_ilock(ip, lock_flags); - - /* - * Change file ownership. Must be the owner or privileged. - */ - if (mask & (ATTR_UID|ATTR_GID)) { - /* - * These IDs could have changed since we last looked at them. - * But, we're assured that if the ownership did change - * while we didn't have the inode locked, inode's dquot(s) - * would have changed also. - */ - iuid = ip->i_d.di_uid; - igid = ip->i_d.di_gid; - gid = (mask & ATTR_GID) ? iattr->ia_gid : igid; - uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid; - - /* - * Do a quota reservation only if uid/gid is actually - * going to change. - */ - if (XFS_IS_QUOTA_RUNNING(mp) && - ((XFS_IS_UQUOTA_ON(mp) && iuid != uid) || - (XFS_IS_GQUOTA_ON(mp) && igid != gid))) { - ASSERT(tp); - code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, - capable(CAP_FOWNER) ? - XFS_QMOPT_FORCE_RES : 0); - if (code) /* out of quota */ - goto error_return; - } - } - - /* - * Truncate file. Must have write permission and not be a directory. - */ - if (mask & ATTR_SIZE) { - /* Short circuit the truncate case for zero length files */ - if (iattr->ia_size == 0 && - ip->i_size == 0 && ip->i_d.di_nextents == 0) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - lock_flags &= ~XFS_ILOCK_EXCL; - if (mask & ATTR_CTIME) { - inode->i_mtime = inode->i_ctime = - current_fs_time(inode->i_sb); - xfs_mark_inode_dirty_sync(ip); - } - code = 0; - goto error_return; - } - - if (S_ISDIR(ip->i_d.di_mode)) { - code = XFS_ERROR(EISDIR); - goto error_return; - } else if (!S_ISREG(ip->i_d.di_mode)) { - code = XFS_ERROR(EINVAL); - goto error_return; - } - - /* - * Make sure that the dquots are attached to the inode. - */ - code = xfs_qm_dqattach_locked(ip, 0); - if (code) - goto error_return; - - /* - * Now we can make the changes. Before we join the inode - * to the transaction, if ATTR_SIZE is set then take care of - * the part of the truncation that must be done without the - * inode lock. This needs to be done before joining the inode - * to the transaction, because the inode cannot be unlocked - * once it is a part of the transaction. - */ - if (iattr->ia_size > ip->i_size) { - /* - * Do the first part of growing a file: zero any data - * in the last block that is beyond the old EOF. We - * need to do this before the inode is joined to the - * transaction to modify the i_size. - */ - code = xfs_zero_eof(ip, iattr->ia_size, ip->i_size); - if (code) - goto error_return; - } - xfs_iunlock(ip, XFS_ILOCK_EXCL); - lock_flags &= ~XFS_ILOCK_EXCL; - - /* - * We are going to log the inode size change in this - * transaction so any previous writes that are beyond the on - * disk EOF and the new EOF that have not been written out need - * to be written here. If we do not write the data out, we - * expose ourselves to the null files problem. - * - * Only flush from the on disk size to the smaller of the in - * memory file size or the new size as that's the range we - * really care about here and prevents waiting for other data - * not within the range we care about here. - */ - if (ip->i_size != ip->i_d.di_size && - iattr->ia_size > ip->i_d.di_size) { - code = xfs_flush_pages(ip, - ip->i_d.di_size, iattr->ia_size, - XBF_ASYNC, FI_NONE); - if (code) - goto error_return; - } - - /* wait for all I/O to complete */ - xfs_ioend_wait(ip); - - code = -block_truncate_page(inode->i_mapping, iattr->ia_size, - xfs_get_blocks); - if (code) - goto error_return; - - tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE); - code = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0, - XFS_TRANS_PERM_LOG_RES, - XFS_ITRUNCATE_LOG_COUNT); - if (code) - goto error_return; - - truncate_setsize(inode, iattr->ia_size); - - commit_flags = XFS_TRANS_RELEASE_LOG_RES; - lock_flags |= XFS_ILOCK_EXCL; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - - xfs_trans_ijoin(tp, ip); - - /* - * Only change the c/mtime if we are changing the size - * or we are explicitly asked to change it. This handles - * the semantic difference between truncate() and ftruncate() - * as implemented in the VFS. - * - * The regular truncate() case without ATTR_CTIME and ATTR_MTIME - * is a special case where we need to update the times despite - * not having these flags set. For all other operations the - * VFS set these flags explicitly if it wants a timestamp - * update. - */ - if (iattr->ia_size != ip->i_size && - (!(mask & (ATTR_CTIME | ATTR_MTIME)))) { - iattr->ia_ctime = iattr->ia_mtime = - current_fs_time(inode->i_sb); - mask |= ATTR_CTIME | ATTR_MTIME; - } - - if (iattr->ia_size > ip->i_size) { - ip->i_d.di_size = iattr->ia_size; - ip->i_size = iattr->ia_size; - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - } else if (iattr->ia_size <= ip->i_size || - (iattr->ia_size == 0 && ip->i_d.di_nextents)) { - /* - * signal a sync transaction unless - * we're truncating an already unlinked - * file on a wsync filesystem - */ - code = xfs_itruncate_finish(&tp, ip, iattr->ia_size, - XFS_DATA_FORK, - ((ip->i_d.di_nlink != 0 || - !(mp->m_flags & XFS_MOUNT_WSYNC)) - ? 1 : 0)); - if (code) - goto abort_return; - /* - * Truncated "down", so we're removing references - * to old data here - if we now delay flushing for - * a long time, we expose ourselves unduly to the - * notorious NULL files problem. So, we mark this - * vnode and flush it when the file is closed, and - * do not wait the usual (long) time for writeout. - */ - xfs_iflags_set(ip, XFS_ITRUNCATED); - } - } else if (tp) { - xfs_trans_ijoin(tp, ip); - } - - /* - * Change file ownership. Must be the owner or privileged. - */ - if (mask & (ATTR_UID|ATTR_GID)) { - /* - * CAP_FSETID overrides the following restrictions: - * - * The set-user-ID and set-group-ID bits of a file will be - * cleared upon successful return from chown() - */ - if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && - !capable(CAP_FSETID)) { - ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); - } - - /* - * Change the ownerships and register quota modifications - * in the transaction. - */ - if (iuid != uid) { - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) { - ASSERT(mask & ATTR_UID); - ASSERT(udqp); - olddquot1 = xfs_qm_vop_chown(tp, ip, - &ip->i_udquot, udqp); - } - ip->i_d.di_uid = uid; - inode->i_uid = uid; - } - if (igid != gid) { - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) { - ASSERT(!XFS_IS_PQUOTA_ON(mp)); - ASSERT(mask & ATTR_GID); - ASSERT(gdqp); - olddquot2 = xfs_qm_vop_chown(tp, ip, - &ip->i_gdquot, gdqp); - } - ip->i_d.di_gid = gid; - inode->i_gid = gid; - } - } - - /* - * Change file access modes. - */ - if (mask & ATTR_MODE) { - umode_t mode = iattr->ia_mode; - - if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID)) - mode &= ~S_ISGID; - - ip->i_d.di_mode &= S_IFMT; - ip->i_d.di_mode |= mode & ~S_IFMT; - - inode->i_mode &= S_IFMT; - inode->i_mode |= mode & ~S_IFMT; - } - - /* - * Change file access or modified times. - */ - if (mask & ATTR_ATIME) { - inode->i_atime = iattr->ia_atime; - ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec; - ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec; - ip->i_update_core = 1; - } - if (mask & ATTR_CTIME) { - inode->i_ctime = iattr->ia_ctime; - ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; - ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec; - ip->i_update_core = 1; - } - if (mask & ATTR_MTIME) { - inode->i_mtime = iattr->ia_mtime; - ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; - ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; - ip->i_update_core = 1; - } - - /* - * And finally, log the inode core if any attribute in it - * has been changed. - */ - if (mask & (ATTR_UID|ATTR_GID|ATTR_MODE| - ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - - XFS_STATS_INC(xs_ig_attrchg); - - /* - * If this is a synchronous mount, make sure that the - * transaction goes to disk before returning to the user. - * This is slightly sub-optimal in that truncates require - * two sync transactions instead of one for wsync filesystems. - * One for the truncate and one for the timestamps since we - * don't want to change the timestamps unless we're sure the - * truncate worked. Truncates are less than 1% of the laddis - * mix so this probably isn't worth the trouble to optimize. - */ - code = 0; - if (mp->m_flags & XFS_MOUNT_WSYNC) - xfs_trans_set_sync(tp); - - code = xfs_trans_commit(tp, commit_flags); - - xfs_iunlock(ip, lock_flags); - - /* - * Release any dquot(s) the inode had kept before chown. - */ - xfs_qm_dqrele(olddquot1); - xfs_qm_dqrele(olddquot2); - xfs_qm_dqrele(udqp); - xfs_qm_dqrele(gdqp); - - if (code) - return code; - - /* - * XXX(hch): Updating the ACL entries is not atomic vs the i_mode - * update. We could avoid this with linked transactions - * and passing down the transaction pointer all the way - * to attr_set. No previous user of the generic - * Posix ACL code seems to care about this issue either. - */ - if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) { - code = -xfs_acl_chmod(inode); - if (code) - return XFS_ERROR(code); - } - - return 0; - - abort_return: - commit_flags |= XFS_TRANS_ABORT; - error_return: - xfs_qm_dqrele(udqp); - xfs_qm_dqrele(gdqp); - if (tp) { - xfs_trans_cancel(tp, commit_flags); - } - if (lock_flags != 0) { - xfs_iunlock(ip, lock_flags); - } - return code; -} - /* * The maximum pathlen is 1024 bytes. Since the minimum file system * blocksize is 512 bytes, we can get a max of 2 extents back from @@ -621,13 +197,6 @@ xfs_free_eofblocks( */ tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE); - /* - * Do the xfs_itruncate_start() call before - * reserving any log space because - * itruncate_start will call into the buffer - * cache and we can't - * do that within a transaction. - */ if (flags & XFS_FREE_EOF_TRYLOCK) { if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) { xfs_trans_cancel(tp, 0); @@ -636,13 +205,6 @@ xfs_free_eofblocks( } else { xfs_ilock(ip, XFS_IOLOCK_EXCL); } - error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, - ip->i_size); - if (error) { - xfs_trans_cancel(tp, 0); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - return error; - } error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), @@ -658,15 +220,12 @@ xfs_free_eofblocks( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip); - error = xfs_itruncate_finish(&tp, ip, - ip->i_size, - XFS_DATA_FORK, - 0); - /* - * If we get an error at this point we - * simply don't bother truncating the file. - */ + error = xfs_itruncate_data(&tp, ip, ip->i_size); if (error) { + /* + * If we get an error at this point we simply don't + * bother truncating the file. + */ xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT)); @@ -960,8 +519,11 @@ xfs_release( * be exposed to that problem. */ truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED); - if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) - xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE); + if (truncated) { + xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE); + if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) + xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE); + } } if (ip->i_d.di_nlink == 0) @@ -1081,20 +643,9 @@ xfs_inactive( tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE); if (truncate) { - /* - * Do the xfs_itruncate_start() call before - * reserving any log space because itruncate_start - * will call into the buffer cache and we can't - * do that within a transaction. - */ xfs_ilock(ip, XFS_IOLOCK_EXCL); - error = xfs_itruncate_start(ip, XFS_ITRUNC_DEFINITE, 0); - if (error) { - xfs_trans_cancel(tp, 0); - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - return VN_INACTIVE_CACHE; - } + xfs_ioend_wait(ip); error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), @@ -1111,16 +662,7 @@ xfs_inactive( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip); - /* - * normally, we have to run xfs_itruncate_finish sync. - * But if filesystem is wsync and we're in the inactive - * path, then we know that nlink == 0, and that the - * xaction that made nlink == 0 is permanently committed - * since xfs_remove runs as a synchronous transaction. - */ - error = xfs_itruncate_finish(&tp, ip, 0, XFS_DATA_FORK, - (!(mp->m_flags & XFS_MOUNT_WSYNC) ? 1 : 0)); - + error = xfs_itruncate_data(&tp, ip, 0); if (error) { xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); @@ -2427,6 +1969,8 @@ xfs_zero_remaining_bytes( if (!bp) return XFS_ERROR(ENOMEM); + xfs_buf_unlock(bp); + for (offset = startoff; offset <= endoff; offset = lastoffset + 1) { offset_fsb = XFS_B_TO_FSBT(mp, offset); nimap = 1; @@ -2781,7 +2325,7 @@ xfs_change_file_space( iattr.ia_valid = ATTR_SIZE; iattr.ia_size = startoffset; - error = xfs_setattr(ip, &iattr, attr_flags); + error = xfs_setattr_size(ip, &iattr, attr_flags); if (error) return error; diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h index 3bcd233..35d3d51 100644 --- a/fs/xfs/xfs_vnodeops.h +++ b/fs/xfs/xfs_vnodeops.h @@ -13,7 +13,8 @@ struct xfs_inode; struct xfs_iomap; -int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags); +int xfs_setattr_nonsize(struct xfs_inode *ip, struct iattr *vap, int flags); +int xfs_setattr_size(struct xfs_inode *ip, struct iattr *vap, int flags); #define XFS_ATTR_DMI 0x01 /* invocation from a DMI function */ #define XFS_ATTR_NONBLOCK 0x02 /* return EAGAIN if operation would block */ #define XFS_ATTR_NOLOCK 0x04 /* Don't grab any conflicting locks */ diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3a10ef5..6cd5b64 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -210,7 +210,7 @@ struct acpi_device_power_state { struct acpi_device_power { int state; /* Current state */ struct acpi_device_power_flags flags; - struct acpi_device_power_state states[4]; /* Power states (D0-D3) */ + struct acpi_device_power_state states[ACPI_D_STATE_COUNT]; /* Power states (D0-D3Cold) */ }; /* Performance Management */ diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index a756bc8..4543b6f 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -98,8 +98,11 @@ acpi_os_table_override(struct acpi_table_header *existing_table, /* * Spinlock primitives */ + +#ifndef acpi_os_create_lock acpi_status acpi_os_create_lock(acpi_spinlock *out_handle); +#endif void acpi_os_delete_lock(acpi_spinlock handle); diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h index 5d2a5e9..2ce1be9 100644 --- a/include/acpi/platform/aclinux.h +++ b/include/acpi/platform/aclinux.h @@ -159,6 +159,24 @@ static inline void *acpi_os_acquire_object(acpi_cache_t * cache) } while (0) #endif +/* + * When lockdep is enabled, the spin_lock_init() macro stringifies it's + * argument and uses that as a name for the lock in debugging. + * By executing spin_lock_init() in a macro the key changes from "lock" for + * all locks to the name of the argument of acpi_os_create_lock(), which + * prevents lockdep from reporting false positives for ACPICA locks. + */ +#define acpi_os_create_lock(__handle) \ +({ \ + spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \ + \ + if (lock) { \ + *(__handle) = lock; \ + spin_lock_init(*(__handle)); \ + } \ + lock ? AE_OK : AE_NO_MEMORY; \ +}) + #endif /* __KERNEL__ */ #endif /* __ACLINUX_H__ */ diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index e08f344..3d53efd 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -182,6 +182,7 @@ {0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6759, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x675F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6760, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6761, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6762, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ @@ -192,6 +193,7 @@ {0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6880, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6888, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \ diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 5479fdc..514ed45 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -201,6 +201,9 @@ struct amba_pl011_data { bool (*dma_filter)(struct dma_chan *chan, void *filter_param); void *dma_rx_param; void *dma_tx_param; + void (*init) (void); + void (*exit) (void); + void (*reset) (void); }; #endif diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 2a7cea5..6395692 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -167,7 +167,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ - REQ_NOIDLE | REQ_FLUSH | REQ_FUA) + REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_RAHEAD (1 << __REQ_RAHEAD) diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index b22fb0d..8c7c2de 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -169,7 +169,8 @@ extern void blk_trace_shutdown(struct request_queue *); extern int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, struct block_device *bdev, struct blk_user_trace_setup *buts); -extern void __trace_note_message(struct blk_trace *, const char *fmt, ...); +extern __attribute__((format(printf, 2, 3))) +void __trace_note_message(struct blk_trace *, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream diff --git a/include/linux/compat.h b/include/linux/compat.h index ddcb7db..846bb17 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -467,6 +467,8 @@ asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, unsigned int optlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); +asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, + unsigned vlen, unsigned int flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags); asmlinkage long compat_sys_recv(int fd, void __user *buf, size_t len, diff --git a/include/linux/connector.h b/include/linux/connector.h index 7c60d09..f696bcc 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -44,7 +44,7 @@ #define CN_VAL_DRBD 0x1 #define CN_KVP_IDX 0x9 /* HyperV KVP */ -#define CN_NETLINK_USERS 9 +#define CN_NETLINK_USERS 10 /* Highest index + 1 */ /* * Maximum connector's message size. diff --git a/include/linux/device.h b/include/linux/device.h index c66111a..e4f62d8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -530,7 +530,6 @@ struct device_dma_parameters { * @dma_mem: Internal for coherent mem override. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. - * @of_match: Matching of_device_id from driver. * @devt: For creating the sysfs "dev". * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. @@ -654,13 +653,13 @@ static inline int device_is_registered(struct device *dev) static inline void device_enable_async_suspend(struct device *dev) { - if (!dev->power.in_suspend) + if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { - if (!dev->power.in_suspend) + if (!dev->power.is_prepared) dev->power.async_suspend = false; } diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 246f576..447c367 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -117,10 +117,10 @@ /* drbdsetup XY resize -d Z * you are free to reduce the device size to nothing, if you want to. * the upper limit with 64bit kernel, enough ram and flexible meta data - * is 16 TB, currently. */ + * is 1 PiB, currently. */ /* DRBD_MAX_SECTORS */ #define DRBD_DISK_SIZE_SECT_MIN 0 -#define DRBD_DISK_SIZE_SECT_MAX (16 * (2LLU << 30)) +#define DRBD_DISK_SIZE_SECT_MAX (1 * (2LLU << 40)) #define DRBD_DISK_SIZE_SECT_DEF 0 /* = disabled = no user size... */ #define DRBD_ON_IO_ERROR_DEF EP_PASS_ON diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e73e2e..b5b9792 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -639,6 +639,7 @@ struct address_space { struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct mutex i_mmap_mutex; /* protect tree, count, list */ + /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7c4d72f..9ec20de 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -204,6 +204,8 @@ extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, gfp_t); +extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, + struct inode *); /** * fscache_register_netfs - Register a filesystem as desiring caching services @@ -643,4 +645,23 @@ bool fscache_maybe_release_page(struct fscache_cookie *cookie, return false; } +/** + * fscache_uncache_all_inode_pages - Uncache all an inode's pages + * @cookie: The cookie representing the inode's cache object. + * @inode: The inode to uncache pages from. + * + * Uncache all the pages in an inode that are marked PG_fscache, assuming them + * to be associated with the given cookie. + * + * This function may sleep. It will wait for pages that are being written out + * and will wait whilst the PG_fscache mark is removed by the cache. + */ +static inline +void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, + struct inode *inode) +{ + if (fscache_cookie_valid(cookie)) + __fscache_uncache_all_inode_pages(cookie, inode); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/fsl-diu-fb.h b/include/linux/fsl-diu-fb.h index 781d467..daa9952 100644 --- a/include/linux/fsl-diu-fb.h +++ b/include/linux/fsl-diu-fb.h @@ -24,12 +24,6 @@ * See mpc8610fb_set_par(), map_video_memory(), and unmap_video_memory() */ #define MEM_ALLOC_THRESHOLD (1024*768*4+32) -/* Minimum value that the pixel clock can be set to in pico seconds - * This is determined by platform clock/3 where the minimum platform - * clock is 533MHz. This gives 5629 pico seconds. - */ -#define MIN_PIX_CLK 5629 -#define MAX_PIX_CLK 96096 #include <linux/types.h> diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 51932e5..fd0dc30 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -135,6 +135,7 @@ struct hrtimer_sleeper { * @cpu_base: per cpu clock base * @index: clock type index for per_cpu support when moving a * timer to a base on another cpu. + * @clockid: clock id for per_cpu support * @active: red black tree root node for the active timers * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock diff --git a/include/linux/irq.h b/include/linux/irq.h index 8b45384..baa397e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -676,7 +676,8 @@ void irq_gc_mask_disable_reg(struct irq_data *d); void irq_gc_mask_set_bit(struct irq_data *d); void irq_gc_mask_clr_bit(struct irq_data *d); void irq_gc_unmask_enable_reg(struct irq_data *d); -void irq_gc_ack(struct irq_data *d); +void irq_gc_ack_set_bit(struct irq_data *d); +void irq_gc_ack_clr_bit(struct irq_data *d); void irq_gc_mask_disable_reg_and_ack(struct irq_data *d); void irq_gc_eoi(struct irq_data *d); int irq_gc_set_wake(struct irq_data *d, unsigned int on); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4ecb7b1..d087c2e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1024,7 +1024,6 @@ struct journal_s /* Filing buffers */ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __jbd2_journal_unfile_buffer(struct journal_head *); extern void __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); @@ -1165,7 +1164,6 @@ extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_in */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh); struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh); -void jbd2_journal_remove_journal_head(struct buffer_head *bh); void jbd2_journal_put_journal_head(struct journal_head *jh); /* diff --git a/include/linux/memory.h b/include/linux/memory.h index e1e3b2b..935699b 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -20,6 +20,8 @@ #include <linux/compiler.h> #include <linux/mutex.h> +#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) + struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h index be469a3..38a372a 100644 --- a/include/linux/mfd/ds1wm.h +++ b/include/linux/mfd/ds1wm.h @@ -3,4 +3,11 @@ struct ds1wm_driver_data { int active_high; int clock_rate; + /* in milliseconds, the amount of time to */ + /* sleep following a reset pulse. Zero */ + /* should work if your bus devices recover*/ + /* time respects the 1-wire spec since the*/ + /* ds1wm implements the precise timings of*/ + /* a reset pulse/presence detect sequence.*/ + unsigned int reset_recover_delay; }; diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 5a90266..0dc9804 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -68,6 +68,11 @@ * controller and report the event to the driver. */ #define TMIO_MMC_HAS_COLD_CD (1 << 3) +/* + * Some controllers require waiting for the SD bus to become + * idle before writing to some registers. + */ +#define TMIO_MMC_HAS_IDLE_WAIT (1 << 4) int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); @@ -80,6 +85,8 @@ struct tmio_mmc_dma { int alignment_shift; }; +struct tmio_mmc_host; + /* * data for the MMC controller */ @@ -94,6 +101,7 @@ struct tmio_mmc_data { void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); int (*get_cd)(struct platform_device *host); + int (*write16_hook)(struct tmio_mmc_host *host, int addr); }; static inline void tmio_mmc_cd_wakeup(struct tmio_mmc_data *pdata) diff --git a/include/linux/mmc/boot.h b/include/linux/mmc/boot.h index 39d787c..23acc3b 100644 --- a/include/linux/mmc/boot.h +++ b/include/linux/mmc/boot.h @@ -1,7 +1,7 @@ -#ifndef MMC_BOOT_H -#define MMC_BOOT_H +#ifndef LINUX_MMC_BOOT_H +#define LINUX_MMC_BOOT_H enum { MMC_PROGRESS_ENTER, MMC_PROGRESS_INIT, MMC_PROGRESS_LOAD, MMC_PROGRESS_DONE }; -#endif +#endif /* LINUX_MMC_BOOT_H */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index c6927a4..b460fc2 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -64,6 +64,19 @@ struct mmc_ext_csd { unsigned long long enhanced_area_offset; /* Units: Byte */ unsigned int enhanced_area_size; /* Units: KB */ unsigned int boot_size; /* in bytes */ + u8 raw_partition_support; /* 160 */ + u8 raw_erased_mem_count; /* 181 */ + u8 raw_ext_csd_structure; /* 194 */ + u8 raw_card_type; /* 196 */ + u8 raw_s_a_timeout; /* 217 */ + u8 raw_hc_erase_gap_size; /* 221 */ + u8 raw_erase_timeout_mult; /* 223 */ + u8 raw_hc_erase_grp_size; /* 224 */ + u8 raw_sec_trim_mult; /* 229 */ + u8 raw_sec_erase_mult; /* 230 */ + u8 raw_sec_feature_support;/* 231 */ + u8 raw_trim_mult; /* 232 */ + u8 raw_sectors[4]; /* 212 - 4 bytes */ }; struct sd_scr { @@ -390,4 +403,4 @@ extern void mmc_unregister_driver(struct mmc_driver *); extern void mmc_fixup_device(struct mmc_card *card, const struct mmc_fixup *table); -#endif +#endif /* LINUX_MMC_CARD_H */ diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index b6718e5..b8b1b7a 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -117,6 +117,7 @@ struct mmc_data { unsigned int sg_len; /* size of scatter list */ struct scatterlist *sg; /* I/O scatter list */ + s32 host_cookie; /* host private data */ }; struct mmc_request { @@ -125,13 +126,16 @@ struct mmc_request { struct mmc_data *data; struct mmc_command *stop; - void *done_data; /* completion data */ + struct completion completion; void (*done)(struct mmc_request *);/* completion function */ }; struct mmc_host; struct mmc_card; +struct mmc_async_req; +extern struct mmc_async_req *mmc_start_req(struct mmc_host *, + struct mmc_async_req *, int *); extern void mmc_wait_for_req(struct mmc_host *, struct mmc_request *); extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int); extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *); @@ -155,6 +159,7 @@ extern int mmc_can_trim(struct mmc_card *card); extern int mmc_can_secure_erase_trim(struct mmc_card *card); extern int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from, unsigned int nr); +extern unsigned int mmc_calc_max_discard(struct mmc_card *card); extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen); @@ -179,4 +184,4 @@ static inline void mmc_claim_host(struct mmc_host *host) extern u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max); -#endif +#endif /* LINUX_MMC_CORE_H */ diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index bdd7cee..6b46819 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -11,8 +11,8 @@ * (at your option) any later version. */ -#ifndef _LINUX_MMC_DW_MMC_H_ -#define _LINUX_MMC_DW_MMC_H_ +#ifndef LINUX_MMC_DW_MMC_H +#define LINUX_MMC_DW_MMC_H #define MAX_MCI_SLOTS 2 @@ -48,6 +48,7 @@ struct mmc_data; * @data: The data currently being transferred, or NULL if no data * transfer is in progress. * @use_dma: Whether DMA channel is initialized or not. + * @using_dma: Whether DMA is in use for the current transfer. * @sg_dma: Bus address of DMA buffer. * @sg_cpu: Virtual address of DMA buffer. * @dma_ops: Pointer to platform-specific DMA callbacks. @@ -74,7 +75,11 @@ struct mmc_data; * @pdev: Platform device associated with the MMC controller. * @pdata: Platform data associated with the MMC controller. * @slot: Slots sharing this MMC controller. + * @fifo_depth: depth of FIFO. * @data_shift: log2 of FIFO item size. + * @part_buf_start: Start index in part_buf. + * @part_buf_count: Bytes of partial data in part_buf. + * @part_buf: Simple buffer for partial fifo reads/writes. * @push_data: Pointer to FIFO push function. * @pull_data: Pointer to FIFO pull function. * @quirks: Set of quirks that apply to specific versions of the IP. @@ -117,6 +122,7 @@ struct dw_mci { /* DMA interface members*/ int use_dma; + int using_dma; dma_addr_t sg_dma; void *sg_cpu; @@ -131,7 +137,7 @@ struct dw_mci { u32 stop_cmdr; u32 dir_status; struct tasklet_struct tasklet; - struct tasklet_struct card_tasklet; + struct work_struct card_work; unsigned long pending_events; unsigned long completed_events; enum dw_mci_state state; @@ -146,7 +152,15 @@ struct dw_mci { struct dw_mci_slot *slot[MAX_MCI_SLOTS]; /* FIFO push and pull */ + int fifo_depth; int data_shift; + u8 part_buf_start; + u8 part_buf_count; + union { + u16 part_buf16; + u32 part_buf32; + u64 part_buf; + }; void (*push_data)(struct dw_mci *host, void *buf, int cnt); void (*pull_data)(struct dw_mci *host, void *buf, int cnt); @@ -196,6 +210,12 @@ struct dw_mci_board { unsigned int bus_hz; /* Bus speed */ unsigned int caps; /* Capabilities */ + /* + * Override fifo depth. If 0, autodetect it from the FIFOTH register, + * but note that this may not be reliable after a bootloader has used + * it. + */ + unsigned int fifo_depth; /* delay in mS before detecting cards after interrupt */ u32 detect_delay_ms; @@ -219,4 +239,4 @@ struct dw_mci_board { struct block_settings *blk_settings; }; -#endif /* _LINUX_MMC_DW_MMC_H_ */ +#endif /* LINUX_MMC_DW_MMC_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 1ee4424..0f83858 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -106,6 +106,15 @@ struct mmc_host_ops { */ int (*enable)(struct mmc_host *host); int (*disable)(struct mmc_host *host, int lazy); + /* + * It is optional for the host to implement pre_req and post_req in + * order to support double buffering of requests (prepare one + * request while another request is active). + */ + void (*post_req)(struct mmc_host *host, struct mmc_request *req, + int err); + void (*pre_req)(struct mmc_host *host, struct mmc_request *req, + bool is_first_req); void (*request)(struct mmc_host *host, struct mmc_request *req); /* * Avoid calling these three functions too often or in a "fast path", @@ -139,11 +148,22 @@ struct mmc_host_ops { int (*start_signal_voltage_switch)(struct mmc_host *host, struct mmc_ios *ios); int (*execute_tuning)(struct mmc_host *host); void (*enable_preset_value)(struct mmc_host *host, bool enable); + int (*select_drive_strength)(unsigned int max_dtr, int host_drv, int card_drv); }; struct mmc_card; struct device; +struct mmc_async_req { + /* active mmc request */ + struct mmc_request *mrq; + /* + * Check error status of completed mmc request. + * Returns 0 if success otherwise non zero. + */ + int (*err_check) (struct mmc_card *, struct mmc_async_req *); +}; + struct mmc_host { struct device *parent; struct device class_dev; @@ -231,6 +251,7 @@ struct mmc_host { unsigned int max_req_size; /* maximum number of bytes in one req */ unsigned int max_blk_size; /* maximum size of one mmc block */ unsigned int max_blk_count; /* maximum number of blocks in one req */ + unsigned int max_discard_to; /* max. discard timeout in ms */ /* private data */ spinlock_t lock; /* lock for claim and bus ops */ @@ -281,6 +302,8 @@ struct mmc_host { struct dentry *debugfs_root; + struct mmc_async_req *areq; /* active async req */ + unsigned long private[0] ____cacheline_aligned; }; @@ -373,5 +396,4 @@ static inline int mmc_host_cmd23(struct mmc_host *host) { return host->caps & MMC_CAP_CMD23; } -#endif - +#endif /* LINUX_MMC_HOST_H */ diff --git a/include/linux/mmc/ioctl.h b/include/linux/mmc/ioctl.h index 5baf298..8fa5bc5 100644 --- a/include/linux/mmc/ioctl.h +++ b/include/linux/mmc/ioctl.h @@ -51,4 +51,4 @@ struct mmc_ioc_cmd { * block device operations. */ #define MMC_IOC_MAX_BYTES (512L * 256) -#endif /* LINUX_MMC_IOCTL_H */ +#endif /* LINUX_MMC_IOCTL_H */ diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h index ac26a68..5a794cb 100644 --- a/include/linux/mmc/mmc.h +++ b/include/linux/mmc/mmc.h @@ -21,8 +21,8 @@ * 15 May 2002 */ -#ifndef MMC_MMC_H -#define MMC_MMC_H +#ifndef LINUX_MMC_MMC_H +#define LINUX_MMC_MMC_H /* Standard MMC commands (4.1) type argument response */ /* class 1 */ @@ -140,6 +140,16 @@ static inline bool mmc_op_multi(u32 opcode) #define R1_SWITCH_ERROR (1 << 7) /* sx, c */ #define R1_APP_CMD (1 << 5) /* sr, c */ +#define R1_STATE_IDLE 0 +#define R1_STATE_READY 1 +#define R1_STATE_IDENT 2 +#define R1_STATE_STBY 3 +#define R1_STATE_TRAN 4 +#define R1_STATE_DATA 5 +#define R1_STATE_RCV 6 +#define R1_STATE_PRG 7 +#define R1_STATE_DIS 8 + /* * MMC/SD in SPI mode reports R1 status always, and R2 for SEND_STATUS * R1 is the low order byte; R2 is the next highest byte, when present. @@ -327,5 +337,4 @@ struct _mmc_csd { #define MMC_SWITCH_MODE_CLEAR_BITS 0x02 /* Clear bits which are 1 in value */ #define MMC_SWITCH_MODE_WRITE_BYTE 0x03 /* Set target to value */ -#endif /* MMC_MMC_PROTOCOL_H */ - +#endif /* LINUX_MMC_MMC_H */ diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h index d37aac4..4a13920 100644 --- a/include/linux/mmc/pm.h +++ b/include/linux/mmc/pm.h @@ -27,4 +27,4 @@ typedef unsigned int mmc_pm_flag_t; #define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */ #define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */ -#endif +#endif /* LINUX_MMC_PM_H */ diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h index 7d35d52..1ebcf9b 100644 --- a/include/linux/mmc/sd.h +++ b/include/linux/mmc/sd.h @@ -9,8 +9,8 @@ * your option) any later version. */ -#ifndef MMC_SD_H -#define MMC_SD_H +#ifndef LINUX_MMC_SD_H +#define LINUX_MMC_SD_H /* SD commands type argument response */ /* class 0 */ @@ -91,5 +91,4 @@ #define SD_SWITCH_ACCESS_DEF 0 #define SD_SWITCH_ACCESS_HS 1 -#endif - +#endif /* LINUX_MMC_SD_H */ diff --git a/include/linux/mmc/sdhci-pltfm.h b/include/linux/mmc/sdhci-pltfm.h deleted file mode 100644 index 548d59d..0000000 --- a/include/linux/mmc/sdhci-pltfm.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Platform data declarations for the sdhci-pltfm driver. - * - * Copyright (c) 2010 MontaVista Software, LLC. - * - * Author: Anton Vorontsov <avorontsov@ru.mvista.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or (at - * your option) any later version. - */ - -#ifndef _SDHCI_PLTFM_H -#define _SDHCI_PLTFM_H - -struct sdhci_ops; -struct sdhci_host; - -/** - * struct sdhci_pltfm_data - SDHCI platform-specific information & hooks - * @ops: optional pointer to the platform-provided SDHCI ops - * @quirks: optional SDHCI quirks - * @init: optional hook that is called during device probe, before the - * driver tries to access any SDHCI registers - * @exit: optional hook that is called during device removal - */ -struct sdhci_pltfm_data { - struct sdhci_ops *ops; - unsigned int quirks; - int (*init)(struct sdhci_host *host, struct sdhci_pltfm_data *pdata); - void (*exit)(struct sdhci_host *host); -}; - -#endif /* _SDHCI_PLTFM_H */ diff --git a/include/linux/mmc/sdhci-spear.h b/include/linux/mmc/sdhci-spear.h index 9188c97..5cdc96d 100644 --- a/include/linux/mmc/sdhci-spear.h +++ b/include/linux/mmc/sdhci-spear.h @@ -11,8 +11,8 @@ * warranty of any kind, whether express or implied. */ -#ifndef MMC_SDHCI_SPEAR_H -#define MMC_SDHCI_SPEAR_H +#ifndef LINUX_MMC_SDHCI_SPEAR_H +#define LINUX_MMC_SDHCI_SPEAR_H #include <linux/platform_device.h> /* @@ -39,4 +39,4 @@ sdhci_set_plat_data(struct platform_device *pdev, struct sdhci_plat_data *data) pdev->dev.platform_data = data; } -#endif /* MMC_SDHCI_SPEAR_H */ +#endif /* LINUX_MMC_SDHCI_SPEAR_H */ diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h index 6a68c4e..5666f3a 100644 --- a/include/linux/mmc/sdhci.h +++ b/include/linux/mmc/sdhci.h @@ -8,8 +8,8 @@ * the Free Software Foundation; either version 2 of the License, or (at * your option) any later version. */ -#ifndef __SDHCI_H -#define __SDHCI_H +#ifndef LINUX_MMC_SDHCI_H +#define LINUX_MMC_SDHCI_H #include <linux/scatterlist.h> #include <linux/compiler.h> @@ -162,4 +162,4 @@ struct sdhci_host { unsigned long private[0] ____cacheline_aligned; }; -#endif /* __SDHCI_H */ +#endif /* LINUX_MMC_SDHCI_H */ diff --git a/include/linux/mmc/sdio.h b/include/linux/mmc/sdio.h index 245cdac..2a2e990 100644 --- a/include/linux/mmc/sdio.h +++ b/include/linux/mmc/sdio.h @@ -9,8 +9,8 @@ * your option) any later version. */ -#ifndef MMC_SDIO_H -#define MMC_SDIO_H +#ifndef LINUX_MMC_SDIO_H +#define LINUX_MMC_SDIO_H /* SDIO commands type argument response */ #define SD_IO_SEND_OP_COND 5 /* bcr [23:0] OCR R4 */ @@ -161,5 +161,4 @@ #define SDIO_FBR_BLKSIZE 0x10 /* block size (2 bytes) */ -#endif - +#endif /* LINUX_MMC_SDIO_H */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 31baaf8..50f0bc9 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -9,8 +9,8 @@ * your option) any later version. */ -#ifndef MMC_SDIO_FUNC_H -#define MMC_SDIO_FUNC_H +#ifndef LINUX_MMC_SDIO_FUNC_H +#define LINUX_MMC_SDIO_FUNC_H #include <linux/device.h> #include <linux/mod_devicetable.h> @@ -161,5 +161,4 @@ extern void sdio_f0_writeb(struct sdio_func *func, unsigned char b, extern mmc_pm_flag_t sdio_get_host_pm_caps(struct sdio_func *func); extern int sdio_set_host_pm_flags(struct sdio_func *func, mmc_pm_flag_t flags); -#endif - +#endif /* LINUX_MMC_SDIO_FUNC_H */ diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index a36ab3b..9f03fee 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -2,8 +2,8 @@ * SDIO Classes, Interface Types, Manufacturer IDs, etc. */ -#ifndef MMC_SDIO_IDS_H -#define MMC_SDIO_IDS_H +#ifndef LINUX_MMC_SDIO_IDS_H +#define LINUX_MMC_SDIO_IDS_H /* * Standard SDIO Function Interfaces @@ -44,4 +44,4 @@ #define SDIO_DEVICE_ID_SIANO_NOVA_A0 0x1100 #define SDIO_DEVICE_ID_SIANO_STELLAR 0x5347 -#endif +#endif /* LINUX_MMC_SDIO_IDS_H */ diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h index 9eb9b4b..0222cd8 100644 --- a/include/linux/mmc/sh_mmcif.h +++ b/include/linux/mmc/sh_mmcif.h @@ -11,8 +11,8 @@ * */ -#ifndef __SH_MMCIF_H__ -#define __SH_MMCIF_H__ +#ifndef LINUX_MMC_SH_MMCIF_H +#define LINUX_MMC_SH_MMCIF_H #include <linux/io.h> #include <linux/platform_device.h> @@ -220,4 +220,4 @@ static inline void sh_mmcif_boot_init(void __iomem *base) sh_mmcif_boot_cmd(base, 0x03400040, 0x00010000); } -#endif /* __SH_MMCIF_H__ */ +#endif /* LINUX_MMC_SH_MMCIF_H */ diff --git a/include/linux/mmc/sh_mobile_sdhi.h b/include/linux/mmc/sh_mobile_sdhi.h index faf32b6..bd50b36 100644 --- a/include/linux/mmc/sh_mobile_sdhi.h +++ b/include/linux/mmc/sh_mobile_sdhi.h @@ -1,5 +1,5 @@ -#ifndef __SH_MOBILE_SDHI_H__ -#define __SH_MOBILE_SDHI_H__ +#ifndef LINUX_MMC_SH_MOBILE_SDHI_H +#define LINUX_MMC_SH_MOBILE_SDHI_H #include <linux/types.h> @@ -17,4 +17,4 @@ struct sh_mobile_sdhi_info { int (*get_cd)(struct platform_device *pdev); }; -#endif /* __SH_MOBILE_SDHI_H__ */ +#endif /* LINUX_MMC_SH_MOBILE_SDHI_H */ diff --git a/include/linux/mmc/tmio.h b/include/linux/mmc/tmio.h index 19490b9..a1c1f32 100644 --- a/include/linux/mmc/tmio.h +++ b/include/linux/mmc/tmio.h @@ -12,8 +12,8 @@ * * TC6393XB TC6391XB TC6387XB T7L66XB ASIC3 */ -#ifndef _LINUX_MMC_TMIO_H_ -#define _LINUX_MMC_TMIO_H_ +#ifndef LINUX_MMC_TMIO_H +#define LINUX_MMC_TMIO_H #define CTL_SD_CMD 0x00 #define CTL_ARG_REG 0x04 @@ -21,6 +21,7 @@ #define CTL_XFER_BLK_COUNT 0xa #define CTL_RESPONSE 0x0c #define CTL_STATUS 0x1c +#define CTL_STATUS2 0x1e #define CTL_IRQ_MASK 0x20 #define CTL_SD_CARD_CLK_CTL 0x24 #define CTL_SD_XFER_LEN 0x26 @@ -30,6 +31,7 @@ #define CTL_TRANSACTION_CTL 0x34 #define CTL_SDIO_STATUS 0x36 #define CTL_SDIO_IRQ_MASK 0x38 +#define CTL_DMA_ENABLE 0xd8 #define CTL_RESET_SD 0xe0 #define CTL_SDIO_REGS 0x100 #define CTL_CLK_AND_WAIT_CTL 0x138 @@ -60,4 +62,4 @@ #define TMIO_BBS 512 /* Boot block size */ -#endif /* _LINUX_MMC_TMIO_H_ */ +#endif /* LINUX_MMC_TMIO_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c928dac..9f7c3eb 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -647,6 +647,13 @@ typedef struct pglist_data { #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) +#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) + +#define node_end_pfn(nid) ({\ + pg_data_t *__pgdat = NODE_DATA(nid);\ + __pgdat->node_start_pfn + __pgdat->node_spanned_pages;\ +}) + #include <linux/memory_hotplug.h> extern struct mutex zonelists_mutex; diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h index 15da0e9..db4836b 100644 --- a/include/linux/mtd/ubi.h +++ b/include/linux/mtd/ubi.h @@ -155,12 +155,14 @@ struct ubi_device_info { }; /* - * enum - volume notification types. - * @UBI_VOLUME_ADDED: volume has been added - * @UBI_VOLUME_REMOVED: start volume volume - * @UBI_VOLUME_RESIZED: volume size has been re-sized - * @UBI_VOLUME_RENAMED: volume name has been re-named - * @UBI_VOLUME_UPDATED: volume name has been updated + * Volume notification types. + * @UBI_VOLUME_ADDED: a volume has been added (an UBI device was attached or a + * volume was created) + * @UBI_VOLUME_REMOVED: a volume has been removed (an UBI device was detached + * or a volume was removed) + * @UBI_VOLUME_RESIZED: a volume has been re-sized + * @UBI_VOLUME_RENAMED: a volume has been re-named + * @UBI_VOLUME_UPDATED: data has been written to a volume * * These constants define which type of event has happened when a volume * notification function is invoked. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 54b8b4d..9e19477 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1097,12 +1097,6 @@ struct net_device { #define NETIF_F_ALL_FCOE (NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \ NETIF_F_FSO) -#define NETIF_F_ALL_TX_OFFLOADS (NETIF_F_ALL_CSUM | NETIF_F_SG | \ - NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ - NETIF_F_HIGHDMA | \ - NETIF_F_SCTP_CSUM | \ - NETIF_F_ALL_FCOE) - /* * If one device supports one of these features, then enable them * for all in netdev_increment_features. diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 3a34e80..25311b3 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -92,6 +92,9 @@ extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, struct nfs_page *); extern void nfs_pageio_complete(struct nfs_pageio_descriptor *desc); extern void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t); +extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, + struct nfs_page *prev, + struct nfs_page *req); extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern int nfs_set_page_tag_locked(struct nfs_page *req); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5e8444a..00848d8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -158,7 +158,6 @@ struct nfs_seqid; /* nfs41 sessions channel attributes */ struct nfs4_channel_attrs { - u32 headerpadsz; u32 max_rqst_sz; u32 max_resp_sz; u32 max_resp_sz_cached; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a311008..f8910e1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1537,6 +1537,7 @@ #define PCI_DEVICE_ID_RICOH_RL5C476 0x0476 #define PCI_DEVICE_ID_RICOH_RL5C478 0x0478 #define PCI_DEVICE_ID_RICOH_R5C822 0x0822 +#define PCI_DEVICE_ID_RICOH_R5CE823 0xe823 #define PCI_DEVICE_ID_RICOH_R5C832 0x0832 #define PCI_DEVICE_ID_RICOH_R5C843 0x0843 diff --git a/include/linux/platform_data/pxa_sdhci.h b/include/linux/platform_data/pxa_sdhci.h new file mode 100644 index 0000000..51ad099 --- /dev/null +++ b/include/linux/platform_data/pxa_sdhci.h @@ -0,0 +1,60 @@ +/* + * include/linux/platform_data/pxa_sdhci.h + * + * Copyright 2010 Marvell + * Zhangfei Gao <zhangfei.gao@marvell.com> + * + * PXA Platform - SDHCI platform data definitions + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _PXA_SDHCI_H_ +#define _PXA_SDHCI_H_ + +/* pxa specific flag */ +/* Require clock free running */ +#define PXA_FLAG_ENABLE_CLOCK_GATING (1<<0) +/* card always wired to host, like on-chip emmc */ +#define PXA_FLAG_CARD_PERMANENT (1<<1) +/* Board design supports 8-bit data on SD/SDIO BUS */ +#define PXA_FLAG_SD_8_BIT_CAPABLE_SLOT (1<<2) + +/* + * struct pxa_sdhci_platdata() - Platform device data for PXA SDHCI + * @flags: flags for platform requirement + * @clk_delay_cycles: + * mmp2: each step is roughly 100ps, 5bits width + * pxa910: each step is 1ns, 4bits width + * @clk_delay_sel: select clk_delay, used on pxa910 + * 0: choose feedback clk + * 1: choose feedback clk + delay value + * 2: choose internal clk + * @clk_delay_enable: enable clk_delay or not, used on pxa910 + * @ext_cd_gpio: gpio pin used for external CD line + * @ext_cd_gpio_invert: invert values for external CD gpio line + * @max_speed: the maximum speed supported + * @host_caps: Standard MMC host capabilities bit field. + * @quirks: quirks of platfrom + * @pm_caps: pm_caps of platfrom + */ +struct sdhci_pxa_platdata { + unsigned int flags; + unsigned int clk_delay_cycles; + unsigned int clk_delay_sel; + bool clk_delay_enable; + unsigned int ext_cd_gpio; + bool ext_cd_gpio_invert; + unsigned int max_speed; + unsigned int host_caps; + unsigned int quirks; + unsigned int pm_caps; +}; + +struct sdhci_pxa { + u8 clk_enable; + u8 power_mode; +}; +#endif /* _PXA_SDHCI_H_ */ diff --git a/include/linux/pm.h b/include/linux/pm.h index 3160648..411e4f4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -425,7 +425,8 @@ struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; unsigned int async_suspend:1; - unsigned int in_suspend:1; /* Owned by the PM core */ + bool is_prepared:1; /* Owned by the PM core */ + bool is_suspended:1; /* Ditto */ spinlock_t lock; #ifdef CONFIG_PM_SLEEP struct list_head entry; diff --git a/include/linux/sched.h b/include/linux/sched.h index a837b20..14a6c7b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -808,7 +808,7 @@ enum cpu_idle_type { * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the * increased costs. */ -#if BITS_PER_LONG > 32 +#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ # define SCHED_LOAD_RESOLUTION 10 # define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) # define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) @@ -844,6 +844,7 @@ enum cpu_idle_type { #define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */ #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ +#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ enum powersavings_balance_level { POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */ @@ -893,16 +894,21 @@ static inline int sd_power_saving_flags(void) return 0; } -struct sched_group { - struct sched_group *next; /* Must be a circular list */ +struct sched_group_power { atomic_t ref; - /* * CPU power of this group, SCHED_LOAD_SCALE being max power for a * single CPU. */ - unsigned int cpu_power, cpu_power_orig; + unsigned int power, power_orig; +}; + +struct sched_group { + struct sched_group *next; /* Must be a circular list */ + atomic_t ref; + unsigned int group_weight; + struct sched_group_power *sgp; /* * The CPUs this group covers. @@ -1254,6 +1260,9 @@ struct task_struct { #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; char rcu_read_unlock_special; +#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) + int rcu_boosted; +#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */ struct list_head rcu_node_entry; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TREE_PREEMPT_RCU diff --git a/include/linux/sdla.h b/include/linux/sdla.h index 564acd3..9995c7f 100644 --- a/include/linux/sdla.h +++ b/include/linux/sdla.h @@ -112,11 +112,7 @@ struct sdla_dlci_conf { short Tb_max; }; -#ifndef __KERNEL__ - -void sdla(void *cfg_info, char *dev, struct frad_conf *conf, int quiet); - -#else +#ifdef __KERNEL__ /* important Z80 window addresses */ #define SDLA_CONTROL_WND 0xE000 diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 2b7fec8..aa08fa8 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -3,6 +3,7 @@ #include <linux/swap.h> #include <linux/mempolicy.h> +#include <linux/pagemap.h> #include <linux/percpu_counter.h> /* inode in-kernel data */ @@ -45,7 +46,27 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) return container_of(inode, struct shmem_inode_info, vfs_inode); } +/* + * Functions in mm/shmem.c called directly from elsewhere: + */ extern int init_tmpfs(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); +extern struct file *shmem_file_setup(const char *name, + loff_t size, unsigned long flags); +extern int shmem_zero_setup(struct vm_area_struct *); +extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); +extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); +extern int shmem_unuse(swp_entry_t entry, struct page *page); +extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, + struct page **pagep, swp_entry_t *ent); + +static inline struct page *shmem_read_mapping_page( + struct address_space *mapping, pgoff_t index) +{ + return shmem_read_mapping_page_gfp(mapping, index, + mapping_gfp_mask(mapping)); +} #endif diff --git a/include/linux/slab.h b/include/linux/slab.h index ad4dd1c..573c809 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -134,6 +134,26 @@ unsigned int kmem_cache_size(struct kmem_cache *); #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_HIGH - PAGE_SHIFT) /* + * Some archs want to perform DMA into kmalloc caches and need a guaranteed + * alignment larger than the alignment of a 64-bit integer. + * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. + */ +#ifdef ARCH_DMA_MINALIGN +#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN +#else +#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) +#endif + +/* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + +/* * Common kmalloc functions provided by all allocators */ void * __must_check __krealloc(const void *, size_t, gfp_t); diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 83203ae..d00e0ba 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -18,53 +18,25 @@ #include <trace/events/kmem.h> /* - * Enforce a minimum alignment for the kmalloc caches. - * Usually, the kmalloc caches are cache_line_size() aligned, except when - * DEBUG and FORCED_DEBUG are enabled, then they are BYTES_PER_WORD aligned. - * Some archs want to perform DMA into kmalloc caches and need a guaranteed - * alignment larger than the alignment of a 64-bit integer. - * ARCH_KMALLOC_MINALIGN allows that. - * Note that increasing this value may disable some debug features. - */ -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -/* - * Enforce a minimum alignment for all caches. - * Intended for archs that get misalignment faults even for BYTES_PER_WORD - * aligned buffers. Includes ARCH_KMALLOC_MINALIGN. - * If possible: Do not enable this flag for CONFIG_DEBUG_SLAB, it disables - * some debug features. - */ -#define ARCH_SLAB_MINALIGN 0 -#endif - -/* * struct kmem_cache * * manages a cache. */ struct kmem_cache { -/* 1) per-cpu data, touched during every alloc/free */ - struct array_cache *array[NR_CPUS]; -/* 2) Cache tunables. Protected by cache_chain_mutex */ +/* 1) Cache tunables. Protected by cache_chain_mutex */ unsigned int batchcount; unsigned int limit; unsigned int shared; unsigned int buffer_size; u32 reciprocal_buffer_size; -/* 3) touched by every alloc & free from the backend */ +/* 2) touched by every alloc & free from the backend */ unsigned int flags; /* constant flags */ unsigned int num; /* # of objs per slab */ -/* 4) cache_grow/shrink */ +/* 3) cache_grow/shrink */ /* order of pgs per slab (2^n) */ unsigned int gfporder; @@ -80,11 +52,11 @@ struct kmem_cache { /* constructor func */ void (*ctor)(void *obj); -/* 5) cache creation/removal */ +/* 4) cache creation/removal */ const char *name; struct list_head next; -/* 6) statistics */ +/* 5) statistics */ #ifdef CONFIG_DEBUG_SLAB unsigned long num_active; unsigned long num_allocations; @@ -111,16 +83,18 @@ struct kmem_cache { int obj_size; #endif /* CONFIG_DEBUG_SLAB */ +/* 6) per-cpu/per-node data, touched during every alloc/free */ /* - * We put nodelists[] at the end of kmem_cache, because we want to size - * this array to nr_node_ids slots instead of MAX_NUMNODES + * We put array[] at the end of kmem_cache, because we want to size + * this array to nr_cpu_ids slots instead of NR_CPUS * (see kmem_cache_init()) - * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache - * is statically defined, so we reserve the max number of nodes. + * We still use [NR_CPUS] and not [1] or [0] because cache_cache + * is statically defined, so we reserve the max number of cpus. */ - struct kmem_list3 *nodelists[MAX_NUMNODES]; + struct kmem_list3 **nodelists; + struct array_cache *array[NR_CPUS]; /* - * Do not add fields after nodelists[] + * Do not add fields after array[] */ }; diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h index 4382db0..0ec00b3 100644 --- a/include/linux/slob_def.h +++ b/include/linux/slob_def.h @@ -1,16 +1,6 @@ #ifndef __LINUX_SLOB_DEF_H #define __LINUX_SLOB_DEF_H -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long) -#endif - void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); static __always_inline void *kmem_cache_alloc(struct kmem_cache *cachep, diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index c8668d1..4b35c06 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -113,16 +113,6 @@ struct kmem_cache { #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) -#ifdef ARCH_DMA_MINALIGN -#define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN -#else -#define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) -#endif - -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - /* * Maximum kmalloc object size handled by SLUB. Larger object allocations * are passed through to the page allocator. The page allocator "fastpath" @@ -228,6 +218,19 @@ kmalloc_order(size_t size, gfp_t flags, unsigned int order) return ret; } +/** + * Calling this on allocated memory will check that the memory + * is expected to be in use, and print warnings if not. + */ +#ifdef CONFIG_SLUB_DEBUG +extern bool verify_mem_not_deleted(const void *x); +#else +static inline bool verify_mem_not_deleted(const void *x) +{ + return true; +} +#endif + #ifdef CONFIG_TRACING extern void * kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size); diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index f73c482..fe2d8e6 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -84,7 +84,8 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2; + tk_cred_retry : 2, + tk_rebind_retry : 2; }; #define tk_xprt tk_client->cl_xprt diff --git a/include/linux/swap.h b/include/linux/swap.h index e705646..a273468 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -300,16 +300,6 @@ static inline void scan_unevictable_unregister_node(struct node *node) extern int kswapd_run(int nid); extern void kswapd_stop(int nid); -#ifdef CONFIG_MMU -/* linux/mm/shmem.c */ -extern int shmem_unuse(swp_entry_t entry, struct page *page); -#endif /* CONFIG_MMU */ - -#ifdef CONFIG_CGROUP_MEM_RES_CTLR -extern void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff, - struct page **pagep, swp_entry_t *ent); -#endif - #ifdef CONFIG_SWAP /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); diff --git a/include/media/lirc_dev.h b/include/media/lirc_dev.h index 630e702..168dd0b 100644 --- a/include/media/lirc_dev.h +++ b/include/media/lirc_dev.h @@ -9,7 +9,7 @@ #ifndef _LINUX_LIRC_DEV_H #define _LINUX_LIRC_DEV_H -#define MAX_IRCTL_DEVICES 4 +#define MAX_IRCTL_DEVICES 8 #define BUFLEN 16 #define mod(n, div) ((n) % (div)) diff --git a/include/media/m5mols.h b/include/media/m5mols.h index 2d7e7ca..aac2c0e 100644 --- a/include/media/m5mols.h +++ b/include/media/m5mols.h @@ -2,10 +2,10 @@ * Driver header for M-5MOLS 8M Pixel camera sensor with ISP * * Copyright (C) 2011 Samsung Electronics Co., Ltd. - * Author: HeungJun Kim, riverful.kim@samsung.com + * Author: HeungJun Kim <riverful.kim@samsung.com> * * Copyright (C) 2009 Samsung Electronics Co., Ltd. - * Author: Dongsoo Nathaniel Kim, dongsoo45.kim@samsung.com + * Author: Dongsoo Nathaniel Kim <dongsoo45.kim@samsung.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/include/media/v4l2-subdev.h b/include/media/v4l2-subdev.h index 1562c4f..2884e3e 100644 --- a/include/media/v4l2-subdev.h +++ b/include/media/v4l2-subdev.h @@ -173,16 +173,20 @@ struct v4l2_subdev_core_ops { struct v4l2_event_subscription *sub); }; -/* s_mode: switch the tuner to a specific tuner mode. Replacement of s_radio. +/* s_radio: v4l device was opened in radio mode. - s_radio: v4l device was opened in Radio mode, to be replaced by s_mode. + g_frequency: freq->type must be filled in. Normally done by video_ioctl2 + or the bridge driver. + + g_tuner: + s_tuner: vt->type must be filled in. Normally done by video_ioctl2 or the + bridge driver. s_type_addr: sets tuner type and its I2C addr. s_config: sets tda9887 specific stuff, like port1, port2 and qss */ struct v4l2_subdev_tuner_ops { - int (*s_mode)(struct v4l2_subdev *sd, enum v4l2_tuner_type); int (*s_radio)(struct v4l2_subdev *sd); int (*s_frequency)(struct v4l2_subdev *sd, struct v4l2_frequency *freq); int (*g_frequency)(struct v4l2_subdev *sd, struct v4l2_frequency *freq); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 0589f55..396e8fc 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2688,7 +2688,7 @@ void cfg80211_send_unprot_disassoc(struct net_device *dev, const u8 *buf, * @dev: network device * @addr: The source MAC address of the frame * @key_type: The key type that the received frame used - * @key_id: Key identifier (0..3) + * @key_id: Key identifier (0..3). Can be -1 if missing. * @tsc: The TSC value of the frame that generated the MIC failure (6 octets) * @gfp: allocation flags * diff --git a/include/net/dst.h b/include/net/dst.h index 7d15d23..e12ddfb 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -77,6 +77,7 @@ struct dst_entry { #define DST_NOPOLICY 0x0004 #define DST_NOHASH 0x0008 #define DST_NOCACHE 0x0010 +#define DST_NOCOUNT 0x0020 union { struct dst_entry *next; struct rtable __rcu *rt_next; diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index dd6847e..6506458 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -63,6 +63,7 @@ typedef enum { SCTP_CMD_ECN_ECNE, /* Do delayed ECNE processing. */ SCTP_CMD_ECN_CWR, /* Do delayed CWR processing. */ SCTP_CMD_TIMER_START, /* Start a timer. */ + SCTP_CMD_TIMER_START_ONCE, /* Start a timer once */ SCTP_CMD_TIMER_RESTART, /* Restart a timer. */ SCTP_CMD_TIMER_STOP, /* Stop a timer. */ SCTP_CMD_INIT_CHOOSE_TRANSPORT, /* Choose transport for an INIT. */ diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 99b027b..ca4693b 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -80,7 +80,7 @@ static inline struct sctp_ulpevent *sctp_skb2event(struct sk_buff *skb) void sctp_ulpevent_free(struct sctp_ulpevent *); int sctp_ulpevent_is_notification(const struct sctp_ulpevent *); -void sctp_queue_purge_ulpevents(struct sk_buff_head *list); +unsigned int sctp_queue_purge_ulpevents(struct sk_buff_head *list); struct sctp_ulpevent *sctp_ulpevent_make_assoc_change( const struct sctp_association *asoc, diff --git a/include/net/sock.h b/include/net/sock.h index f2046e4..c0b938c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -178,7 +178,6 @@ struct sock_common { * @sk_dst_cache: destination cache * @sk_dst_lock: destination cache lock * @sk_policy: flow policy - * @sk_rmem_alloc: receive queue bytes committed * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_write_queue: Packet sending queue diff --git a/include/sound/sb16_csp.h b/include/sound/sb16_csp.h index 736eac7..af1b49e 100644 --- a/include/sound/sb16_csp.h +++ b/include/sound/sb16_csp.h @@ -99,7 +99,14 @@ struct snd_sb_csp_info { /* get CSP information */ #define SNDRV_SB_CSP_IOCTL_INFO _IOR('H', 0x10, struct snd_sb_csp_info) /* load microcode to CSP */ -#define SNDRV_SB_CSP_IOCTL_LOAD_CODE _IOW('H', 0x11, struct snd_sb_csp_microcode) +/* NOTE: struct snd_sb_csp_microcode overflows the max size (13 bits) + * defined for some architectures like MIPS, and it leads to build errors. + * (x86 and co have 14-bit size, thus it's valid, though.) + * As a workaround for skipping the size-limit check, here we don't use the + * normal _IOW() macro but _IOC() with the manual argument. + */ +#define SNDRV_SB_CSP_IOCTL_LOAD_CODE \ + _IOC(_IOC_WRITE, 'H', 0x11, sizeof(struct snd_sb_csp_microcode)) /* unload microcode from CSP */ #define SNDRV_SB_CSP_IOCTL_UNLOAD_CODE _IO('H', 0x12) /* start CSP */ diff --git a/include/sound/soc.h b/include/sound/soc.h index f1de3e0..3a4bd3a 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -248,8 +248,7 @@ typedef int (*hw_write_t)(void *,const char* ,int); extern struct snd_ac97_bus_ops soc_ac97_ops; enum snd_soc_control_type { - SND_SOC_CUSTOM = 1, - SND_SOC_I2C, + SND_SOC_I2C = 1, SND_SOC_SPI, }; diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index e09592d..5ce2b2f 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -26,7 +26,7 @@ TRACE_EVENT(ext4_free_inode, __field( umode_t, mode ) __field( uid_t, uid ) __field( gid_t, gid ) - __field( blkcnt_t, blocks ) + __field( __u64, blocks ) ), TP_fast_assign( @@ -40,9 +40,8 @@ TRACE_EVENT(ext4_free_inode, TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->mode, __entry->uid, __entry->gid, - (unsigned long long) __entry->blocks) + (unsigned long) __entry->ino, __entry->mode, + __entry->uid, __entry->gid, __entry->blocks) ); TRACE_EVENT(ext4_request_inode, @@ -178,7 +177,7 @@ TRACE_EVENT(ext4_begin_ordered_truncate, TP_printk("dev %d,%d ino %lu new_size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (long long) __entry->new_size) + __entry->new_size) ); DECLARE_EVENT_CLASS(ext4__write_begin, @@ -204,7 +203,7 @@ DECLARE_EVENT_CLASS(ext4__write_begin, __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu pos %llu len %u flags %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->flags) @@ -248,7 +247,7 @@ DECLARE_EVENT_CLASS(ext4__write_end, __entry->copied = copied; ), - TP_printk("dev %d,%d ino %lu pos %llu len %u copied %u", + TP_printk("dev %d,%d ino %lu pos %lld len %u copied %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->pos, __entry->len, __entry->copied) @@ -286,29 +285,6 @@ DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_ARGS(inode, pos, len, copied) ); -TRACE_EVENT(ext4_writepage, - TP_PROTO(struct inode *inode, struct page *page), - - TP_ARGS(inode, page), - - TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) - __field( pgoff_t, index ) - - ), - - TP_fast_assign( - __entry->dev = inode->i_sb->s_dev; - __entry->ino = inode->i_ino; - __entry->index = page->index; - ), - - TP_printk("dev %d,%d ino %lu page_index %lu", - MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, __entry->index) -); - TRACE_EVENT(ext4_da_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), @@ -341,7 +317,7 @@ TRACE_EVENT(ext4_da_writepages, ), TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld " - "range_start %llu range_end %llu sync_mode %d" + "range_start %lld range_end %lld sync_mode %d" "for_kupdate %d range_cyclic %d writeback_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->nr_to_write, @@ -449,7 +425,14 @@ DECLARE_EVENT_CLASS(ext4__page_op, TP_printk("dev %d,%d ino %lu page_index %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->index) + (unsigned long) __entry->index) +); + +DEFINE_EVENT(ext4__page_op, ext4_writepage, + + TP_PROTO(struct page *page), + + TP_ARGS(page) ); DEFINE_EVENT(ext4__page_op, ext4_readpage, @@ -489,7 +472,7 @@ TRACE_EVENT(ext4_invalidatepage, TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->index, __entry->offset) + (unsigned long) __entry->index, __entry->offset) ); TRACE_EVENT(ext4_discard_blocks, @@ -562,12 +545,10 @@ DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa, ); TRACE_EVENT(ext4_mb_release_inode_pa, - TP_PROTO(struct super_block *sb, - struct inode *inode, - struct ext4_prealloc_space *pa, + TP_PROTO(struct ext4_prealloc_space *pa, unsigned long long block, unsigned int count), - TP_ARGS(sb, inode, pa, block, count), + TP_ARGS(pa, block, count), TP_STRUCT__entry( __field( dev_t, dev ) @@ -578,8 +559,8 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ), TP_fast_assign( - __entry->dev = sb->s_dev; - __entry->ino = inode->i_ino; + __entry->dev = pa->pa_inode->i_sb->s_dev; + __entry->ino = pa->pa_inode->i_ino; __entry->block = block; __entry->count = count; ), @@ -591,10 +572,9 @@ TRACE_EVENT(ext4_mb_release_inode_pa, ); TRACE_EVENT(ext4_mb_release_group_pa, - TP_PROTO(struct super_block *sb, - struct ext4_prealloc_space *pa), + TP_PROTO(struct ext4_prealloc_space *pa), - TP_ARGS(sb, pa), + TP_ARGS(pa), TP_STRUCT__entry( __field( dev_t, dev ) @@ -604,7 +584,7 @@ TRACE_EVENT(ext4_mb_release_group_pa, ), TP_fast_assign( - __entry->dev = sb->s_dev; + __entry->dev = pa->pa_inode->i_sb->s_dev; __entry->pa_pstart = pa->pa_pstart; __entry->pa_len = pa->pa_len; ), @@ -666,10 +646,10 @@ TRACE_EVENT(ext4_request_blocks, __field( ino_t, ino ) __field( unsigned int, flags ) __field( unsigned int, len ) - __field( __u64, logical ) + __field( __u32, logical ) + __field( __u32, lleft ) + __field( __u32, lright ) __field( __u64, goal ) - __field( __u64, lleft ) - __field( __u64, lright ) __field( __u64, pleft ) __field( __u64, pright ) ), @@ -687,17 +667,13 @@ TRACE_EVENT(ext4_request_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu " - "lleft %llu lright %llu pleft %llu pright %llu ", + TP_printk("dev %d,%d ino %lu flags %u len %u lblk %u goal %llu " + "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->flags, __entry->len, - (unsigned long long) __entry->logical, - (unsigned long long) __entry->goal, - (unsigned long long) __entry->lleft, - (unsigned long long) __entry->lright, - (unsigned long long) __entry->pleft, - (unsigned long long) __entry->pright) + (unsigned long) __entry->ino, __entry->flags, + __entry->len, __entry->logical, __entry->goal, + __entry->lleft, __entry->lright, __entry->pleft, + __entry->pright) ); TRACE_EVENT(ext4_allocate_blocks, @@ -711,10 +687,10 @@ TRACE_EVENT(ext4_allocate_blocks, __field( __u64, block ) __field( unsigned int, flags ) __field( unsigned int, len ) - __field( __u64, logical ) + __field( __u32, logical ) + __field( __u32, lleft ) + __field( __u32, lright ) __field( __u64, goal ) - __field( __u64, lleft ) - __field( __u64, lright ) __field( __u64, pleft ) __field( __u64, pright ) ), @@ -733,17 +709,13 @@ TRACE_EVENT(ext4_allocate_blocks, __entry->pright = ar->pright; ), - TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu " - "goal %llu lleft %llu lright %llu pleft %llu pright %llu", + TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %u " + "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->flags, __entry->len, __entry->block, - (unsigned long long) __entry->logical, - (unsigned long long) __entry->goal, - (unsigned long long) __entry->lleft, - (unsigned long long) __entry->lright, - (unsigned long long) __entry->pleft, - (unsigned long long) __entry->pright) + (unsigned long) __entry->ino, __entry->flags, + __entry->len, __entry->block, __entry->logical, + __entry->goal, __entry->lleft, __entry->lright, + __entry->pleft, __entry->pright) ); TRACE_EVENT(ext4_free_blocks, @@ -755,10 +727,10 @@ TRACE_EVENT(ext4_free_blocks, TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) - __field( umode_t, mode ) + __field( umode_t, mode ) __field( __u64, block ) __field( unsigned long, count ) - __field( int, flags ) + __field( int, flags ) ), TP_fast_assign( @@ -798,7 +770,7 @@ TRACE_EVENT(ext4_sync_file_enter, __entry->parent = dentry->d_parent->d_inode->i_ino; ), - TP_printk("dev %d,%d ino %ld parent %ld datasync %d ", + TP_printk("dev %d,%d ino %lu parent %lu datasync %d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->parent, __entry->datasync) @@ -821,7 +793,7 @@ TRACE_EVENT(ext4_sync_file_exit, __entry->dev = inode->i_sb->s_dev; ), - TP_printk("dev %d,%d ino %ld ret %d", + TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) @@ -1005,7 +977,7 @@ DECLARE_EVENT_CLASS(ext4__mballoc, __entry->result_len = len; ), - TP_printk("dev %d,%d inode %lu extent %u/%d/%u ", + TP_printk("dev %d,%d inode %lu extent %u/%d/%d ", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->result_group, __entry->result_start, @@ -1093,7 +1065,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, "allocated_meta_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->mode, (unsigned long long) __entry->i_blocks, + __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) ); @@ -1127,7 +1099,7 @@ TRACE_EVENT(ext4_da_reserve_space, "reserved_data_blocks %d reserved_meta_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->mode, (unsigned long long) __entry->i_blocks, + __entry->mode, __entry->i_blocks, __entry->md_needed, __entry->reserved_data_blocks, __entry->reserved_meta_blocks) ); @@ -1164,7 +1136,7 @@ TRACE_EVENT(ext4_da_release_space, "allocated_meta_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->mode, (unsigned long long) __entry->i_blocks, + __entry->mode, __entry->i_blocks, __entry->freed_blocks, __entry->reserved_data_blocks, __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) ); @@ -1239,14 +1211,15 @@ TRACE_EVENT(ext4_direct_IO_enter, __entry->rw = rw; ), - TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lu rw %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, __entry->len, __entry->rw) + __entry->pos, __entry->len, __entry->rw) ); TRACE_EVENT(ext4_direct_IO_exit, - TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw, int ret), + TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, + int rw, int ret), TP_ARGS(inode, offset, len, rw, ret), @@ -1268,10 +1241,10 @@ TRACE_EVENT(ext4_direct_IO_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d ino %lu pos %llu len %lu rw %d ret %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lu rw %d ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, __entry->len, + __entry->pos, __entry->len, __entry->rw, __entry->ret) ); @@ -1296,15 +1269,15 @@ TRACE_EVENT(ext4_fallocate_enter, __entry->mode = mode; ), - TP_printk("dev %d,%d ino %ld pos %llu len %llu mode %d", + TP_printk("dev %d,%d ino %lu pos %lld len %lld mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, - (unsigned long long) __entry->len, __entry->mode) + (unsigned long) __entry->ino, __entry->pos, + __entry->len, __entry->mode) ); TRACE_EVENT(ext4_fallocate_exit, - TP_PROTO(struct inode *inode, loff_t offset, unsigned int max_blocks, int ret), + TP_PROTO(struct inode *inode, loff_t offset, + unsigned int max_blocks, int ret), TP_ARGS(inode, offset, max_blocks, ret), @@ -1312,7 +1285,7 @@ TRACE_EVENT(ext4_fallocate_exit, __field( ino_t, ino ) __field( dev_t, dev ) __field( loff_t, pos ) - __field( unsigned, blocks ) + __field( unsigned int, blocks ) __field( int, ret ) ), @@ -1324,10 +1297,10 @@ TRACE_EVENT(ext4_fallocate_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d ino %ld pos %llu blocks %d ret %d", + TP_printk("dev %d,%d ino %lu pos %lld blocks %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long long) __entry->pos, __entry->blocks, + __entry->pos, __entry->blocks, __entry->ret) ); @@ -1350,7 +1323,7 @@ TRACE_EVENT(ext4_unlink_enter, __entry->dev = dentry->d_inode->i_sb->s_dev; ), - TP_printk("dev %d,%d ino %ld size %lld parent %ld", + TP_printk("dev %d,%d ino %lu size %lld parent %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->size, (unsigned long) __entry->parent) @@ -1373,7 +1346,7 @@ TRACE_EVENT(ext4_unlink_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d ino %ld ret %d", + TP_printk("dev %d,%d ino %lu ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->ret) @@ -1387,7 +1360,7 @@ DECLARE_EVENT_CLASS(ext4__truncate, TP_STRUCT__entry( __field( ino_t, ino ) __field( dev_t, dev ) - __field( blkcnt_t, blocks ) + __field( __u64, blocks ) ), TP_fast_assign( @@ -1396,9 +1369,9 @@ DECLARE_EVENT_CLASS(ext4__truncate, __entry->blocks = inode->i_blocks; ), - TP_printk("dev %d,%d ino %lu blocks %lu", + TP_printk("dev %d,%d ino %lu blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, (unsigned long) __entry->blocks) + (unsigned long) __entry->ino, __entry->blocks) ); DEFINE_EVENT(ext4__truncate, ext4_truncate_enter, @@ -1417,7 +1390,7 @@ DEFINE_EVENT(ext4__truncate, ext4_truncate_exit, DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - unsigned len, unsigned flags), + unsigned int len, unsigned int flags), TP_ARGS(inode, lblk, len, flags), @@ -1425,8 +1398,8 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter, __field( ino_t, ino ) __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) - __field( unsigned, len ) - __field( unsigned, flags ) + __field( unsigned int, len ) + __field( unsigned int, flags ) ), TP_fast_assign( @@ -1440,7 +1413,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter, TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned) __entry->lblk, __entry->len, __entry->flags) + __entry->lblk, __entry->len, __entry->flags) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, @@ -1459,7 +1432,7 @@ DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_PROTO(struct inode *inode, ext4_lblk_t lblk, - ext4_fsblk_t pblk, unsigned len, int ret), + ext4_fsblk_t pblk, unsigned int len, int ret), TP_ARGS(inode, lblk, pblk, len, ret), @@ -1468,7 +1441,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit, __field( dev_t, dev ) __field( ext4_lblk_t, lblk ) __field( ext4_fsblk_t, pblk ) - __field( unsigned, len ) + __field( unsigned int, len ) __field( int, ret ) ), @@ -1484,7 +1457,7 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_exit, TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, + __entry->lblk, __entry->pblk, __entry->len, __entry->ret) ); @@ -1524,7 +1497,7 @@ TRACE_EVENT(ext4_ext_load_extent, TP_printk("dev %d,%d ino %lu lblk %u pblk %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned) __entry->lblk, (unsigned long long) __entry->pblk) + __entry->lblk, __entry->pblk) ); TRACE_EVENT(ext4_load_inode, diff --git a/include/xen/events.h b/include/xen/events.h index 9af21e1..d287997 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -74,8 +74,6 @@ int xen_set_callback_via(uint64_t via); void xen_evtchn_do_upcall(struct pt_regs *regs); void xen_hvm_evtchn_do_upcall(void); -/* Allocate a pirq for a physical interrupt, given a gsi. */ -int xen_allocate_pirq_gsi(unsigned gsi); /* Bind a pirq for a physical interrupt to an irq. */ int xen_bind_pirq_gsi_to_irq(unsigned gsi, unsigned pirq, int shareable, char *name); diff --git a/init/calibrate.c b/init/calibrate.c index 2568d22..aae2f40 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -245,30 +245,32 @@ recalibrate: void __cpuinit calibrate_delay(void) { + unsigned long lpj; static bool printed; if (preset_lpj) { - loops_per_jiffy = preset_lpj; + lpj = preset_lpj; if (!printed) pr_info("Calibrating delay loop (skipped) " "preset value.. "); } else if ((!printed) && lpj_fine) { - loops_per_jiffy = lpj_fine; + lpj = lpj_fine; pr_info("Calibrating delay loop (skipped), " "value calculated using timer frequency.. "); - } else if ((loops_per_jiffy = calibrate_delay_direct()) != 0) { + } else if ((lpj = calibrate_delay_direct()) != 0) { if (!printed) pr_info("Calibrating delay using timer " "specific routine.. "); } else { if (!printed) pr_info("Calibrating delay loop... "); - loops_per_jiffy = calibrate_delay_converge(); + lpj = calibrate_delay_converge(); } if (!printed) pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n", - loops_per_jiffy/(500000/HZ), - (loops_per_jiffy/(5000/HZ)) % 100, loops_per_jiffy); + lpj/(500000/HZ), + (lpj/(5000/HZ)) % 100, lpj); + loops_per_jiffy = lpj; printed = true; } diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 31a9db7..3a2cab4 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -101,10 +101,10 @@ void irq_gc_unmask_enable_reg(struct irq_data *d) } /** - * irq_gc_ack - Ack pending interrupt + * irq_gc_ack_set_bit - Ack pending interrupt via setting bit * @d: irq_data */ -void irq_gc_ack(struct irq_data *d) +void irq_gc_ack_set_bit(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); u32 mask = 1 << (d->irq - gc->irq_base); @@ -115,6 +115,20 @@ void irq_gc_ack(struct irq_data *d) } /** + * irq_gc_ack_clr_bit - Ack pending interrupt via clearing bit + * @d: irq_data + */ +void irq_gc_ack_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = ~(1 << (d->irq - gc->irq_base)); + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack); + irq_gc_unlock(gc); +} + +/** * irq_gc_mask_disable_reg_and_ack- Mask and ack pending interrupt * @d: irq_data */ diff --git a/kernel/jump_label.c b/kernel/jump_label.c index fa27e75..a8ce450 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -375,15 +375,19 @@ int jump_label_text_reserved(void *start, void *end) static void jump_label_update(struct jump_label_key *key, int enable) { - struct jump_entry *entry = key->entries; - - /* if there are no users, entry can be NULL */ - if (entry) - __jump_label_update(key, entry, __stop___jump_table, enable); + struct jump_entry *entry = key->entries, *stop = __stop___jump_table; #ifdef CONFIG_MODULES + struct module *mod = __module_address((jump_label_t)key); + __jump_label_mod_update(key, enable); + + if (mod) + stop = mod->jump_entries + mod->num_jump_entries; #endif + /* if there are no users, entry can be NULL */ + if (entry) + __jump_label_update(key, entry, stop, enable); } #endif diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index ace5588..06efa54 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1211,7 +1211,11 @@ static void free_unnecessary_pages(void) to_free_highmem = alloc_highmem - save; } else { to_free_highmem = 0; - to_free_normal -= save - alloc_highmem; + save -= alloc_highmem; + if (to_free_normal > save) + to_free_normal -= save; + else + to_free_normal = 0; } memory_bm_position_reset(©_bm); diff --git a/kernel/power/user.c b/kernel/power/user.c index 7d02d33..42ddbc6 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -113,8 +113,10 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) pm_notifier_call_chain(PM_POST_RESTORE); } - if (error) + if (error) { + free_basic_memory_bitmaps(); atomic_inc(&snapshot_device_available); + } data->frozen = 0; data->ready = 0; data->platform_support = 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 7e59ffb..ba06207 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -84,9 +84,32 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data); static struct rcu_state *rcu_state; +/* + * The rcu_scheduler_active variable transitions from zero to one just + * before the first task is spawned. So when this variable is zero, RCU + * can assume that there is but one task, allowing RCU to (for example) + * optimized synchronize_sched() to a simple barrier(). When this variable + * is one, RCU must actually do all the hard work required to detect real + * grace periods. This variable is also used to suppress boot-time false + * positives from lockdep-RCU error checking. + */ int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); +/* + * The rcu_scheduler_fully_active variable transitions from zero to one + * during the early_initcall() processing, which is after the scheduler + * is capable of creating new tasks. So RCU processing (for example, + * creating tasks for RCU priority boosting) must be delayed until after + * rcu_scheduler_fully_active transitions from zero to one. We also + * currently delay invocation of any RCU callbacks until after this point. + * + * It might later prove better for people registering RCU callbacks during + * early boot to take responsibility for these callbacks, but one step at + * a time. + */ +static int rcu_scheduler_fully_active __read_mostly; + #ifdef CONFIG_RCU_BOOST /* @@ -98,7 +121,6 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); -static char rcu_kthreads_spawnable; #endif /* #ifdef CONFIG_RCU_BOOST */ @@ -1467,6 +1489,8 @@ static void rcu_process_callbacks(struct softirq_action *unused) */ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { + if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) + return; if (likely(!rsp->boost)) { rcu_do_batch(rsp, rdp); return; diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 14dc7dd..8aafbb8 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -68,6 +68,7 @@ struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state); DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; +static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -147,7 +148,7 @@ static void rcu_preempt_note_context_switch(int cpu) struct rcu_data *rdp; struct rcu_node *rnp; - if (t->rcu_read_lock_nesting && + if (t->rcu_read_lock_nesting > 0 && (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ @@ -190,6 +191,14 @@ static void rcu_preempt_note_context_switch(int cpu) rnp->gp_tasks = &t->rcu_node_entry; } raw_spin_unlock_irqrestore(&rnp->lock, flags); + } else if (t->rcu_read_lock_nesting < 0 && + t->rcu_read_unlock_special) { + + /* + * Complete exit from RCU read-side critical section on + * behalf of preempted instance of __rcu_read_unlock(). + */ + rcu_read_unlock_special(t); } /* @@ -284,7 +293,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static void rcu_read_unlock_special(struct task_struct *t) +static noinline void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -309,7 +318,7 @@ static void rcu_read_unlock_special(struct task_struct *t) } /* Hardware IRQ handlers cannot block. */ - if (in_irq()) { + if (in_irq() || in_serving_softirq()) { local_irq_restore(flags); return; } @@ -342,6 +351,11 @@ static void rcu_read_unlock_special(struct task_struct *t) #ifdef CONFIG_RCU_BOOST if (&t->rcu_node_entry == rnp->boost_tasks) rnp->boost_tasks = np; + /* Snapshot and clear ->rcu_boosted with rcu_node lock held. */ + if (t->rcu_boosted) { + special |= RCU_READ_UNLOCK_BOOSTED; + t->rcu_boosted = 0; + } #endif /* #ifdef CONFIG_RCU_BOOST */ t->rcu_blocked_node = NULL; @@ -358,7 +372,6 @@ static void rcu_read_unlock_special(struct task_struct *t) #ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ if (special & RCU_READ_UNLOCK_BOOSTED) { - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED; rt_mutex_unlock(t->rcu_boost_mutex); t->rcu_boost_mutex = NULL; } @@ -387,13 +400,22 @@ void __rcu_read_unlock(void) struct task_struct *t = current; barrier(); /* needed if we ever invoke rcu_read_unlock in rcutree.c */ - --t->rcu_read_lock_nesting; - barrier(); /* decrement before load of ->rcu_read_unlock_special */ - if (t->rcu_read_lock_nesting == 0 && - unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); + if (t->rcu_read_lock_nesting != 1) + --t->rcu_read_lock_nesting; + else { + t->rcu_read_lock_nesting = INT_MIN; + barrier(); /* assign before ->rcu_read_unlock_special load */ + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0); + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } #endif /* #ifdef CONFIG_PROVE_LOCKING */ } EXPORT_SYMBOL_GPL(__rcu_read_unlock); @@ -589,7 +611,8 @@ static void rcu_preempt_check_callbacks(int cpu) rcu_preempt_qs(cpu); return; } - if (per_cpu(rcu_preempt_data, cpu).qs_pending) + if (t->rcu_read_lock_nesting > 0 && + per_cpu(rcu_preempt_data, cpu).qs_pending) t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; } @@ -695,9 +718,12 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) raw_spin_lock_irqsave(&rnp->lock, flags); for (;;) { - if (!sync_rcu_preempt_exp_done(rnp)) + if (!sync_rcu_preempt_exp_done(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); break; + } if (rnp->parent == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); wake_up(&sync_rcu_preempt_exp_wq); break; } @@ -707,7 +733,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) raw_spin_lock(&rnp->lock); /* irqs already disabled */ rnp->expmask &= ~mask; } - raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* @@ -1174,7 +1199,7 @@ static int rcu_boost(struct rcu_node *rnp) t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED; + t->rcu_boosted = 1; raw_spin_unlock_irqrestore(&rnp->lock, flags); rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */ rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ @@ -1532,7 +1557,7 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) struct sched_param sp; struct task_struct *t; - if (!rcu_kthreads_spawnable || + if (!rcu_scheduler_fully_active || per_cpu(rcu_cpu_kthread_task, cpu) != NULL) return 0; t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu); @@ -1639,7 +1664,7 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, struct sched_param sp; struct task_struct *t; - if (!rcu_kthreads_spawnable || + if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0) return 0; if (rnp->node_kthread_task == NULL) { @@ -1665,7 +1690,7 @@ static int __init rcu_spawn_kthreads(void) int cpu; struct rcu_node *rnp; - rcu_kthreads_spawnable = 1; + rcu_scheduler_fully_active = 1; for_each_possible_cpu(cpu) { per_cpu(rcu_cpu_has_work, cpu) = 0; if (cpu_online(cpu)) @@ -1687,7 +1712,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu) struct rcu_node *rnp = rdp->mynode; /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ - if (rcu_kthreads_spawnable) { + if (rcu_scheduler_fully_active) { (void)rcu_spawn_one_cpu_kthread(cpu); if (rnp->node_kthread_task == NULL) (void)rcu_spawn_one_node_kthread(rcu_state, rnp); @@ -1726,6 +1751,13 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt) { } +static int __init rcu_scheduler_really_started(void) +{ + rcu_scheduler_fully_active = 1; + return 0; +} +early_initcall(rcu_scheduler_really_started); + static void __cpuinit rcu_prepare_kthreads(int cpu) { } diff --git a/kernel/resource.c b/kernel/resource.c index 798e2fa..3ff4017 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -38,6 +38,14 @@ struct resource iomem_resource = { }; EXPORT_SYMBOL(iomem_resource); +/* constraints to be met while allocating resources */ +struct resource_constraint { + resource_size_t min, max, align; + resource_size_t (*alignf)(void *, const struct resource *, + resource_size_t, resource_size_t); + void *alignf_data; +}; + static DEFINE_RWLOCK(resource_lock); static void *r_next(struct seq_file *m, void *v, loff_t *pos) @@ -384,16 +392,13 @@ static bool resource_contains(struct resource *res1, struct resource *res2) } /* - * Find empty slot in the resource tree given range and alignment. + * Find empty slot in the resource tree with the given range and + * alignment constraints */ -static int find_resource(struct resource *root, struct resource *new, - resource_size_t size, resource_size_t min, - resource_size_t max, resource_size_t align, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), - void *alignf_data) +static int __find_resource(struct resource *root, struct resource *old, + struct resource *new, + resource_size_t size, + struct resource_constraint *constraint) { struct resource *this = root->child; struct resource tmp = *new, avail, alloc; @@ -404,25 +409,26 @@ static int find_resource(struct resource *root, struct resource *new, * Skip past an allocated resource that starts at 0, since the assignment * of this->start - 1 to tmp->end below would cause an underflow. */ - if (this && this->start == 0) { - tmp.start = this->end + 1; + if (this && this->start == root->start) { + tmp.start = (this == old) ? old->start : this->end + 1; this = this->sibling; } for(;;) { if (this) - tmp.end = this->start - 1; + tmp.end = (this == old) ? this->end : this->start - 1; else tmp.end = root->end; - resource_clip(&tmp, min, max); + resource_clip(&tmp, constraint->min, constraint->max); arch_remove_reservations(&tmp); /* Check for overflow after ALIGN() */ avail = *new; - avail.start = ALIGN(tmp.start, align); + avail.start = ALIGN(tmp.start, constraint->align); avail.end = tmp.end; if (avail.start >= tmp.start) { - alloc.start = alignf(alignf_data, &avail, size, align); + alloc.start = constraint->alignf(constraint->alignf_data, &avail, + size, constraint->align); alloc.end = alloc.start + size - 1; if (resource_contains(&avail, &alloc)) { new->start = alloc.start; @@ -432,14 +438,75 @@ static int find_resource(struct resource *root, struct resource *new, } if (!this) break; - tmp.start = this->end + 1; + if (this != old) + tmp.start = this->end + 1; this = this->sibling; } return -EBUSY; } +/* + * Find empty slot in the resource tree given range and alignment. + */ +static int find_resource(struct resource *root, struct resource *new, + resource_size_t size, + struct resource_constraint *constraint) +{ + return __find_resource(root, NULL, new, size, constraint); +} + /** - * allocate_resource - allocate empty slot in the resource tree given range & alignment + * reallocate_resource - allocate a slot in the resource tree given range & alignment. + * The resource will be relocated if the new size cannot be reallocated in the + * current location. + * + * @root: root resource descriptor + * @old: resource descriptor desired by caller + * @newsize: new size of the resource descriptor + * @constraint: the size and alignment constraints to be met. + */ +int reallocate_resource(struct resource *root, struct resource *old, + resource_size_t newsize, + struct resource_constraint *constraint) +{ + int err=0; + struct resource new = *old; + struct resource *conflict; + + write_lock(&resource_lock); + + if ((err = __find_resource(root, old, &new, newsize, constraint))) + goto out; + + if (resource_contains(&new, old)) { + old->start = new.start; + old->end = new.end; + goto out; + } + + if (old->child) { + err = -EBUSY; + goto out; + } + + if (resource_contains(old, &new)) { + old->start = new.start; + old->end = new.end; + } else { + __release_resource(old); + *old = new; + conflict = __request_resource(root, old); + BUG_ON(conflict); + } +out: + write_unlock(&resource_lock); + return err; +} + + +/** + * allocate_resource - allocate empty slot in the resource tree given range & alignment. + * The resource will be reallocated with a new size if it was already allocated * @root: root resource descriptor * @new: resource descriptor desired by caller * @size: requested resource region size @@ -459,12 +526,25 @@ int allocate_resource(struct resource *root, struct resource *new, void *alignf_data) { int err; + struct resource_constraint constraint; if (!alignf) alignf = simple_align_resource; + constraint.min = min; + constraint.max = max; + constraint.align = align; + constraint.alignf = alignf; + constraint.alignf_data = alignf_data; + + if ( new->parent ) { + /* resource is already allocated, try reallocating with + the new constraints */ + return reallocate_resource(root, new, size, &constraint); + } + write_lock(&resource_lock); - err = find_resource(root, new, size, min, max, align, alignf, alignf_data); + err = find_resource(root, new, size, &constraint); if (err >= 0 && __request_resource(root, new)) err = -EBUSY; write_unlock(&resource_lock); diff --git a/kernel/sched.c b/kernel/sched.c index 3f2e502..fde6ff9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -292,8 +292,8 @@ static DEFINE_SPINLOCK(task_group_lock); * (The default weight is 1024 - so there's no practical * limitation from this.) */ -#define MIN_SHARES 2 -#define MAX_SHARES (1UL << (18 + SCHED_LOAD_RESOLUTION)) +#define MIN_SHARES (1UL << 1) +#define MAX_SHARES (1UL << 18) static int root_task_group_load = ROOT_TASK_GROUP_LOAD; #endif @@ -2544,13 +2544,9 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) } #ifdef CONFIG_SMP -static void sched_ttwu_pending(void) +static void sched_ttwu_do_pending(struct task_struct *list) { struct rq *rq = this_rq(); - struct task_struct *list = xchg(&rq->wake_list, NULL); - - if (!list) - return; raw_spin_lock(&rq->lock); @@ -2563,9 +2559,45 @@ static void sched_ttwu_pending(void) raw_spin_unlock(&rq->lock); } +#ifdef CONFIG_HOTPLUG_CPU + +static void sched_ttwu_pending(void) +{ + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + sched_ttwu_do_pending(list); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + void scheduler_ipi(void) { - sched_ttwu_pending(); + struct rq *rq = this_rq(); + struct task_struct *list = xchg(&rq->wake_list, NULL); + + if (!list) + return; + + /* + * Not all reschedule IPI handlers call irq_enter/irq_exit, since + * traditionally all their work was done from the interrupt return + * path. Now that we actually do some work, we need to make sure + * we do call them. + * + * Some archs already do call them, luckily irq_enter/exit nest + * properly. + * + * Arguably we should visit all archs and update all handlers, + * however a fair share of IPIs are still resched only so this would + * somewhat pessimize the simple resched case. + */ + irq_enter(); + sched_ttwu_do_pending(list); + irq_exit(); } static void ttwu_queue_remote(struct task_struct *p, int cpu) @@ -6557,7 +6589,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!group->cpu_power) { + if (!group->sgp->power) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: domain->cpu_power not " "set\n"); @@ -6581,9 +6613,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->cpu_power != SCHED_POWER_SCALE) { + if (group->sgp->power != SCHED_POWER_SCALE) { printk(KERN_CONT " (cpu_power = %d)", - group->cpu_power); + group->sgp->power); } group = group->next; @@ -6774,11 +6806,39 @@ static struct root_domain *alloc_rootdomain(void) return rd; } +static void free_sched_groups(struct sched_group *sg, int free_sgp) +{ + struct sched_group *tmp, *first; + + if (!sg) + return; + + first = sg; + do { + tmp = sg->next; + + if (free_sgp && atomic_dec_and_test(&sg->sgp->ref)) + kfree(sg->sgp); + + kfree(sg); + sg = tmp; + } while (sg != first); +} + static void free_sched_domain(struct rcu_head *rcu) { struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); - if (atomic_dec_and_test(&sd->groups->ref)) + + /* + * If its an overlapping domain it has private groups, iterate and + * nuke them all. + */ + if (sd->flags & SD_OVERLAP) { + free_sched_groups(sd->groups, 1); + } else if (atomic_dec_and_test(&sd->groups->ref)) { + kfree(sd->groups->sgp); kfree(sd->groups); + } kfree(sd); } @@ -6945,6 +7005,7 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0; struct sd_data { struct sched_domain **__percpu sd; struct sched_group **__percpu sg; + struct sched_group_power **__percpu sgp; }; struct s_data { @@ -6964,15 +7025,73 @@ struct sched_domain_topology_level; typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +#define SDTL_OVERLAP 0x01 + struct sched_domain_topology_level { sched_domain_init_f init; sched_domain_mask_f mask; + int flags; struct sd_data data; }; -/* - * Assumes the sched_domain tree is fully constructed - */ +static int +build_overlap_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered = sched_domains_tmpmask; + struct sd_data *sdd = sd->private; + struct sched_domain *child; + int i; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct cpumask *sg_span; + + if (cpumask_test_cpu(i, covered)) + continue; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(i)); + + if (!sg) + goto fail; + + sg_span = sched_group_cpus(sg); + + child = *per_cpu_ptr(sdd->sd, i); + if (child->child) { + child = child->child; + cpumask_copy(sg_span, sched_domain_span(child)); + } else + cpumask_set_cpu(i, sg_span); + + cpumask_or(covered, covered, sg_span); + + sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span)); + atomic_inc(&sg->sgp->ref); + + if (cpumask_test_cpu(cpu, sg_span)) + groups = sg; + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + last->next = first; + } + sd->groups = groups; + + return 0; + +fail: + free_sched_groups(first, 0); + + return -ENOMEM; +} + static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) { struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); @@ -6981,24 +7100,24 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) if (child) cpu = cpumask_first(sched_domain_span(child)); - if (sg) + if (sg) { *sg = *per_cpu_ptr(sdd->sg, cpu); + (*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu); + atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */ + } return cpu; } /* - * build_sched_groups takes the cpumask we wish to span, and a pointer - * to a function which identifies what group(along with sched group) a CPU - * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids - * (due to the fact that we keep track of groups covered with a struct cpumask). - * * build_sched_groups will build a circular linked list of the groups * covered by the given span, and will set each group's ->cpumask correctly, * and ->cpu_power to 0. + * + * Assumes the sched_domain tree is fully constructed */ -static void -build_sched_groups(struct sched_domain *sd) +static int +build_sched_groups(struct sched_domain *sd, int cpu) { struct sched_group *first = NULL, *last = NULL; struct sd_data *sdd = sd->private; @@ -7006,6 +7125,12 @@ build_sched_groups(struct sched_domain *sd) struct cpumask *covered; int i; + get_group(cpu, sdd, &sd->groups); + atomic_inc(&sd->groups->ref); + + if (cpu != cpumask_first(sched_domain_span(sd))) + return 0; + lockdep_assert_held(&sched_domains_mutex); covered = sched_domains_tmpmask; @@ -7020,7 +7145,7 @@ build_sched_groups(struct sched_domain *sd) continue; cpumask_clear(sched_group_cpus(sg)); - sg->cpu_power = 0; + sg->sgp->power = 0; for_each_cpu(j, span) { if (get_group(j, sdd, NULL) != group) @@ -7037,6 +7162,8 @@ build_sched_groups(struct sched_domain *sd) last = sg; } last->next = first; + + return 0; } /* @@ -7051,12 +7178,17 @@ build_sched_groups(struct sched_domain *sd) */ static void init_sched_groups_power(int cpu, struct sched_domain *sd) { - WARN_ON(!sd || !sd->groups); + struct sched_group *sg = sd->groups; - if (cpu != group_first_cpu(sd->groups)) - return; + WARN_ON(!sd || !sg); + + do { + sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + sg = sg->next; + } while (sg != sd->groups); - sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); + if (cpu != group_first_cpu(sg)) + return; update_group_power(sd, cpu); } @@ -7177,15 +7309,15 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, static void claim_allocations(int cpu, struct sched_domain *sd) { struct sd_data *sdd = sd->private; - struct sched_group *sg = sd->groups; WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); *per_cpu_ptr(sdd->sd, cpu) = NULL; - if (cpu == cpumask_first(sched_group_cpus(sg))) { - WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg); + if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) *per_cpu_ptr(sdd->sg, cpu) = NULL; - } + + if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref)) + *per_cpu_ptr(sdd->sgp, cpu) = NULL; } #ifdef CONFIG_SCHED_SMT @@ -7210,7 +7342,7 @@ static struct sched_domain_topology_level default_topology[] = { #endif { sd_init_CPU, cpu_cpu_mask, }, #ifdef CONFIG_NUMA - { sd_init_NODE, cpu_node_mask, }, + { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, }, { sd_init_ALLNODES, cpu_allnodes_mask, }, #endif { NULL, }, @@ -7234,9 +7366,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sdd->sg) return -ENOMEM; + sdd->sgp = alloc_percpu(struct sched_group_power *); + if (!sdd->sgp) + return -ENOMEM; + for_each_cpu(j, cpu_map) { struct sched_domain *sd; struct sched_group *sg; + struct sched_group_power *sgp; sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); @@ -7251,6 +7388,13 @@ static int __sdt_alloc(const struct cpumask *cpu_map) return -ENOMEM; *per_cpu_ptr(sdd->sg, j) = sg; + + sgp = kzalloc_node(sizeof(struct sched_group_power), + GFP_KERNEL, cpu_to_node(j)); + if (!sgp) + return -ENOMEM; + + *per_cpu_ptr(sdd->sgp, j) = sgp; } } @@ -7266,11 +7410,15 @@ static void __sdt_free(const struct cpumask *cpu_map) struct sd_data *sdd = &tl->data; for_each_cpu(j, cpu_map) { - kfree(*per_cpu_ptr(sdd->sd, j)); + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); kfree(*per_cpu_ptr(sdd->sg, j)); + kfree(*per_cpu_ptr(sdd->sgp, j)); } free_percpu(sdd->sd); free_percpu(sdd->sg); + free_percpu(sdd->sgp); } } @@ -7316,8 +7464,13 @@ static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_topology_level *tl; sd = NULL; - for (tl = sched_domain_topology; tl->init; tl++) + for (tl = sched_domain_topology; tl->init; tl++) { sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i); + if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } while (sd->child) sd = sd->child; @@ -7329,13 +7482,13 @@ static int build_sched_domains(const struct cpumask *cpu_map, for_each_cpu(i, cpu_map) { for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { sd->span_weight = cpumask_weight(sched_domain_span(sd)); - get_group(i, sd->private, &sd->groups); - atomic_inc(&sd->groups->ref); - - if (i != cpumask_first(sched_domain_span(sd))) - continue; - - build_sched_groups(sd); + if (sd->flags & SD_OVERLAP) { + if (build_overlap_sched_groups(sd, i)) + goto error; + } else { + if (build_sched_groups(sd, i)) + goto error; + } } } @@ -7757,6 +7910,9 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) #endif #endif cfs_rq->min_vruntime = (u64)(-(1LL << 20)); +#ifndef CONFIG_64BIT + cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; +#endif } static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) @@ -8450,10 +8606,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) if (!tg->se[0]) return -EINVAL; - if (shares < MIN_SHARES) - shares = MIN_SHARES; - else if (shares > MAX_SHARES) - shares = MAX_SHARES; + shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); mutex_lock(&shares_mutex); if (tg->shares == shares) diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 433491c..c768588 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1585,7 +1585,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, } /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_POWER_SCALE) / group->cpu_power; + avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power; if (local_group) { this_load = avg_load; @@ -2631,7 +2631,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) power >>= SCHED_POWER_SHIFT; } - sdg->cpu_power_orig = power; + sdg->sgp->power_orig = power; if (sched_feat(ARCH_POWER)) power *= arch_scale_freq_power(sd, cpu); @@ -2647,7 +2647,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu) power = 1; cpu_rq(cpu)->cpu_power = power; - sdg->cpu_power = power; + sdg->sgp->power = power; } static void update_group_power(struct sched_domain *sd, int cpu) @@ -2665,11 +2665,11 @@ static void update_group_power(struct sched_domain *sd, int cpu) group = child->groups; do { - power += group->cpu_power; + power += group->sgp->power; group = group->next; } while (group != child->groups); - sdg->cpu_power = power; + sdg->sgp->power = power; } /* @@ -2691,7 +2691,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) /* * If ~90% of the cpu_power is still there, we're good. */ - if (group->cpu_power * 32 > group->cpu_power_orig * 29) + if (group->sgp->power * 32 > group->sgp->power_orig * 29) return 1; return 0; @@ -2771,7 +2771,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, } /* Adjust by relative CPU power of the group */ - sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->cpu_power; + sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power; /* * Consider the group unbalanced when the imbalance is larger @@ -2788,7 +2788,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd, if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1) sgs->group_imb = 1; - sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, + sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power, SCHED_POWER_SCALE); if (!sgs->group_capacity) sgs->group_capacity = fix_small_capacity(sd, group); @@ -2877,7 +2877,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, return; sds->total_load += sgs.group_load; - sds->total_pwr += sg->cpu_power; + sds->total_pwr += sg->sgp->power; /* * In case the child domain prefers tasks go to siblings @@ -2962,7 +2962,7 @@ static int check_asym_packing(struct sched_domain *sd, if (this_cpu > busiest_cpu) return 0; - *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power, + *imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power, SCHED_POWER_SCALE); return 1; } @@ -2993,7 +2993,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, scaled_busy_load_per_task = sds->busiest_load_per_task * SCHED_POWER_SCALE; - scaled_busy_load_per_task /= sds->busiest->cpu_power; + scaled_busy_load_per_task /= sds->busiest->sgp->power; if (sds->max_load - sds->this_load + scaled_busy_load_per_task >= (scaled_busy_load_per_task * imbn)) { @@ -3007,28 +3007,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds, * moving them. */ - pwr_now += sds->busiest->cpu_power * + pwr_now += sds->busiest->sgp->power * min(sds->busiest_load_per_task, sds->max_load); - pwr_now += sds->this->cpu_power * + pwr_now += sds->this->sgp->power * min(sds->this_load_per_task, sds->this_load); pwr_now /= SCHED_POWER_SCALE; /* Amount of load we'd subtract */ tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / - sds->busiest->cpu_power; + sds->busiest->sgp->power; if (sds->max_load > tmp) - pwr_move += sds->busiest->cpu_power * + pwr_move += sds->busiest->sgp->power * min(sds->busiest_load_per_task, sds->max_load - tmp); /* Amount of load we'd add */ - if (sds->max_load * sds->busiest->cpu_power < + if (sds->max_load * sds->busiest->sgp->power < sds->busiest_load_per_task * SCHED_POWER_SCALE) - tmp = (sds->max_load * sds->busiest->cpu_power) / - sds->this->cpu_power; + tmp = (sds->max_load * sds->busiest->sgp->power) / + sds->this->sgp->power; else tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) / - sds->this->cpu_power; - pwr_move += sds->this->cpu_power * + sds->this->sgp->power; + pwr_move += sds->this->sgp->power * min(sds->this_load_per_task, sds->this_load + tmp); pwr_move /= SCHED_POWER_SCALE; @@ -3074,7 +3074,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); - load_above_capacity /= sds->busiest->cpu_power; + load_above_capacity /= sds->busiest->sgp->power; } /* @@ -3090,8 +3090,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, max_pull = min(sds->max_load - sds->avg_load, load_above_capacity); /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * sds->busiest->cpu_power, - (sds->avg_load - sds->this_load) * sds->this->cpu_power) + *imbalance = min(max_pull * sds->busiest->sgp->power, + (sds->avg_load - sds->this_load) * sds->this->sgp->power) / SCHED_POWER_SCALE; /* diff --git a/kernel/sched_features.h b/kernel/sched_features.h index be40f73..1e7066d 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -70,3 +70,5 @@ SCHED_FEAT(NONIRQ_POWER, 1) * using the scheduler IPI. Reduces rq->lock contention/bounces. */ SCHED_FEAT(TTWU_QUEUE, 1) + +SCHED_FEAT(FORCE_SD_OVERLAP, 0) diff --git a/kernel/signal.c b/kernel/signal.c index ff76786..415d85d 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1178,18 +1178,25 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, { struct sighand_struct *sighand; - rcu_read_lock(); for (;;) { + local_irq_save(*flags); + rcu_read_lock(); sighand = rcu_dereference(tsk->sighand); - if (unlikely(sighand == NULL)) + if (unlikely(sighand == NULL)) { + rcu_read_unlock(); + local_irq_restore(*flags); break; + } - spin_lock_irqsave(&sighand->siglock, *flags); - if (likely(sighand == tsk->sighand)) + spin_lock(&sighand->siglock); + if (likely(sighand == tsk->sighand)) { + rcu_read_unlock(); break; - spin_unlock_irqrestore(&sighand->siglock, *flags); + } + spin_unlock(&sighand->siglock); + rcu_read_unlock(); + local_irq_restore(*flags); } - rcu_read_unlock(); return sighand; } diff --git a/kernel/softirq.c b/kernel/softirq.c index 40cf63d..fca82c3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -315,16 +315,24 @@ static inline void invoke_softirq(void) { if (!force_irqthreads) __do_softirq(); - else + else { + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_OFFSET); wakeup_softirqd(); + __local_bh_enable(SOFTIRQ_OFFSET); + } } #else static inline void invoke_softirq(void) { if (!force_irqthreads) do_softirq(); - else + else { + __local_bh_disable((unsigned long)__builtin_return_address(0), + SOFTIRQ_OFFSET); wakeup_softirqd(); + __local_bh_enable(SOFTIRQ_OFFSET); + } } #endif diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 9ffea36..fc0f220 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -285,16 +285,18 @@ ret: static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; - struct listener *s, *tmp; + struct listener *s, *tmp, *s2; unsigned int cpu; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; + s = NULL; if (isadd == REGISTER) { for_each_cpu(cpu, mask) { - s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, - cpu_to_node(cpu)); + if (!s) + s = kmalloc_node(sizeof(struct listener), + GFP_KERNEL, cpu_to_node(cpu)); if (!s) goto cleanup; s->pid = pid; @@ -303,9 +305,16 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); + list_for_each_entry_safe(s2, tmp, &listeners->list, list) { + if (s2->pid == pid) + goto next_cpu; + } list_add(&s->list, &listeners->list); + s = NULL; +next_cpu: up_write(&listeners->sem); } + kfree(s); return 0; } diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 2d96624..59f369f 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -42,15 +42,75 @@ static struct alarm_base { clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; +/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */ +static ktime_t freezer_delta; +static DEFINE_SPINLOCK(freezer_delta_lock); + #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; -#endif +static DEFINE_SPINLOCK(rtcdev_lock); -/* freezer delta & lock used to handle clock_nanosleep triggered wakeups */ -static ktime_t freezer_delta; -static DEFINE_SPINLOCK(freezer_delta_lock); +/** + * has_wakealarm - check rtc device has wakealarm ability + * @dev: current device + * @name_ptr: name to be returned + * + * This helper function checks to see if the rtc device can wake + * from suspend. + */ +static int has_wakealarm(struct device *dev, void *name_ptr) +{ + struct rtc_device *candidate = to_rtc_device(dev); + + if (!candidate->ops->set_alarm) + return 0; + if (!device_may_wakeup(candidate->dev.parent)) + return 0; + + *(const char **)name_ptr = dev_name(dev); + return 1; +} + +/** + * alarmtimer_get_rtcdev - Return selected rtcdevice + * + * This function returns the rtc device to use for wakealarms. + * If one has not already been chosen, it checks to see if a + * functional rtc device is available. + */ +static struct rtc_device *alarmtimer_get_rtcdev(void) +{ + struct device *dev; + char *str; + unsigned long flags; + struct rtc_device *ret; + + spin_lock_irqsave(&rtcdev_lock, flags); + if (!rtcdev) { + /* Find an rtc device and init the rtc_timer */ + dev = class_find_device(rtc_class, NULL, &str, has_wakealarm); + /* If we have a device then str is valid. See has_wakealarm() */ + if (dev) { + rtcdev = rtc_class_open(str); + /* + * Drop the reference we got in class_find_device, + * rtc_open takes its own. + */ + put_device(dev); + rtc_timer_init(&rtctimer, NULL, NULL); + } + } + ret = rtcdev; + spin_unlock_irqrestore(&rtcdev_lock, flags); + + return ret; +} +#else +#define alarmtimer_get_rtcdev() (0) +#define rtcdev (0) +#endif /** @@ -166,6 +226,7 @@ static int alarmtimer_suspend(struct device *dev) struct rtc_time tm; ktime_t min, now; unsigned long flags; + struct rtc_device *rtc; int i; spin_lock_irqsave(&freezer_delta_lock, flags); @@ -173,8 +234,9 @@ static int alarmtimer_suspend(struct device *dev) freezer_delta = ktime_set(0, 0); spin_unlock_irqrestore(&freezer_delta_lock, flags); + rtc = rtcdev; /* If we have no rtcdev, just return */ - if (!rtcdev) + if (!rtc) return 0; /* Find the soonest timer to expire*/ @@ -199,12 +261,12 @@ static int alarmtimer_suspend(struct device *dev) WARN_ON(min.tv64 < NSEC_PER_SEC); /* Setup an rtc timer to fire that far in the future */ - rtc_timer_cancel(rtcdev, &rtctimer); - rtc_read_time(rtcdev, &tm); + rtc_timer_cancel(rtc, &rtctimer); + rtc_read_time(rtc, &tm); now = rtc_tm_to_ktime(tm); now = ktime_add(now, min); - rtc_timer_start(rtcdev, &rtctimer, now, ktime_set(0, 0)); + rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0)); return 0; } @@ -322,6 +384,9 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp) { clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + return hrtimer_get_res(baseid, tp); } @@ -336,6 +401,9 @@ static int alarm_clock_get(clockid_t which_clock, struct timespec *tp) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + *tp = ktime_to_timespec(base->gettime()); return 0; } @@ -351,6 +419,9 @@ static int alarm_timer_create(struct k_itimer *new_timer) enum alarmtimer_type type; struct alarm_base *base; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; @@ -385,6 +456,9 @@ static void alarm_timer_get(struct k_itimer *timr, */ static int alarm_timer_del(struct k_itimer *timr) { + if (!rtcdev) + return -ENOTSUPP; + alarm_cancel(&timr->it.alarmtimer); return 0; } @@ -402,6 +476,9 @@ static int alarm_timer_set(struct k_itimer *timr, int flags, struct itimerspec *new_setting, struct itimerspec *old_setting) { + if (!rtcdev) + return -ENOTSUPP; + /* Save old values */ old_setting->it_interval = ktime_to_timespec(timr->it.alarmtimer.period); @@ -541,6 +618,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, int ret = 0; struct restart_block *restart; + if (!alarmtimer_get_rtcdev()) + return -ENOTSUPP; + if (!capable(CAP_WAKE_ALARM)) return -EPERM; @@ -638,65 +718,3 @@ static int __init alarmtimer_init(void) } device_initcall(alarmtimer_init); -#ifdef CONFIG_RTC_CLASS -/** - * has_wakealarm - check rtc device has wakealarm ability - * @dev: current device - * @name_ptr: name to be returned - * - * This helper function checks to see if the rtc device can wake - * from suspend. - */ -static int __init has_wakealarm(struct device *dev, void *name_ptr) -{ - struct rtc_device *candidate = to_rtc_device(dev); - - if (!candidate->ops->set_alarm) - return 0; - if (!device_may_wakeup(candidate->dev.parent)) - return 0; - - *(const char **)name_ptr = dev_name(dev); - return 1; -} - -/** - * alarmtimer_init_late - Late initializing of alarmtimer code - * - * This function locates a rtc device to use for wakealarms. - * Run as late_initcall to make sure rtc devices have been - * registered. - */ -static int __init alarmtimer_init_late(void) -{ - struct device *dev; - char *str; - - /* Find an rtc device and init the rtc_timer */ - dev = class_find_device(rtc_class, NULL, &str, has_wakealarm); - /* If we have a device then str is valid. See has_wakealarm() */ - if (dev) { - rtcdev = rtc_class_open(str); - /* - * Drop the reference we got in class_find_device, - * rtc_open takes its own. - */ - put_device(dev); - } - if (!rtcdev) { - printk(KERN_WARNING "No RTC device found, ALARM timers will" - " not wake from suspend"); - } - rtc_timer_init(&rtctimer, NULL, NULL); - - return 0; -} -#else -static int __init alarmtimer_init_late(void) -{ - printk(KERN_WARNING "Kernel not built with RTC support, ALARM timers" - " will not wake from suspend"); - return 0; -} -#endif -late_initcall(alarmtimer_init_late); diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 9d86e45..a78b7c6 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -198,7 +198,7 @@ static void free_object(struct debug_obj *obj) * initialized: */ if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache) - sched = !work_pending(&debug_obj_work); + sched = keventd_up() && !work_pending(&debug_obj_work); hlist_add_head(&obj->node, &obj_pool); obj_pool_free++; obj_pool_used--; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cf7d027..e013b8e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -35,6 +35,7 @@ #include <linux/limits.h> #include <linux/mutex.h> #include <linux/rbtree.h> +#include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -107,10 +108,12 @@ enum mem_cgroup_events_index { enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, + MEM_CGROUP_TARGET_NUMAINFO, MEM_CGROUP_NTARGETS, }; #define THRESHOLDS_EVENTS_TARGET (128) #define SOFTLIMIT_EVENTS_TARGET (1024) +#define NUMAINFO_EVENTS_TARGET (1024) struct mem_cgroup_stat_cpu { long count[MEM_CGROUP_STAT_NSTATS]; @@ -236,7 +239,8 @@ struct mem_cgroup { int last_scanned_node; #if MAX_NUMNODES > 1 nodemask_t scan_nodes; - unsigned long next_scan_node_update; + atomic_t numainfo_events; + atomic_t numainfo_updating; #endif /* * Should the accounting and control be hierarchical, per subtree? @@ -576,15 +580,6 @@ static long mem_cgroup_read_stat(struct mem_cgroup *mem, return val; } -static long mem_cgroup_local_usage(struct mem_cgroup *mem) -{ - long ret; - - ret = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS); - ret += mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE); - return ret; -} - static void mem_cgroup_swap_statistics(struct mem_cgroup *mem, bool charge) { @@ -688,6 +683,9 @@ static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target) case MEM_CGROUP_TARGET_SOFTLIMIT: next = val + SOFTLIMIT_EVENTS_TARGET; break; + case MEM_CGROUP_TARGET_NUMAINFO: + next = val + NUMAINFO_EVENTS_TARGET; + break; default: return; } @@ -706,11 +704,19 @@ static void memcg_check_events(struct mem_cgroup *mem, struct page *page) mem_cgroup_threshold(mem); __mem_cgroup_target_update(mem, MEM_CGROUP_TARGET_THRESH); if (unlikely(__memcg_event_check(mem, - MEM_CGROUP_TARGET_SOFTLIMIT))){ + MEM_CGROUP_TARGET_SOFTLIMIT))) { mem_cgroup_update_tree(mem, page); __mem_cgroup_target_update(mem, - MEM_CGROUP_TARGET_SOFTLIMIT); + MEM_CGROUP_TARGET_SOFTLIMIT); + } +#if MAX_NUMNODES > 1 + if (unlikely(__memcg_event_check(mem, + MEM_CGROUP_TARGET_NUMAINFO))) { + atomic_inc(&mem->numainfo_events); + __mem_cgroup_target_update(mem, + MEM_CGROUP_TARGET_NUMAINFO); } +#endif } } @@ -1128,7 +1134,6 @@ unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, return MEM_CGROUP_ZSTAT(mz, lru); } -#ifdef CONFIG_NUMA static unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *memcg, int nid) { @@ -1140,6 +1145,17 @@ static unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *memcg, return ret; } +static unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup *memcg, + int nid) +{ + unsigned long ret; + + ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_ANON) + + mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_ANON); + return ret; +} + +#if MAX_NUMNODES > 1 static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg) { u64 total = 0; @@ -1151,17 +1167,6 @@ static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg) return total; } -static unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup *memcg, - int nid) -{ - unsigned long ret; - - ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_ANON) + - mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_ANON); - - return ret; -} - static unsigned long mem_cgroup_nr_anon_lru_pages(struct mem_cgroup *memcg) { u64 total = 0; @@ -1558,6 +1563,28 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem) return ret; } +/** + * test_mem_cgroup_node_reclaimable + * @mem: the target memcg + * @nid: the node ID to be checked. + * @noswap : specify true here if the user wants flle only information. + * + * This function returns whether the specified memcg contains any + * reclaimable pages on a node. Returns true if there are any reclaimable + * pages in the node. + */ +static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem, + int nid, bool noswap) +{ + if (mem_cgroup_node_nr_file_lru_pages(mem, nid)) + return true; + if (noswap || !total_swap_pages) + return false; + if (mem_cgroup_node_nr_anon_lru_pages(mem, nid)) + return true; + return false; + +} #if MAX_NUMNODES > 1 /* @@ -1569,26 +1596,26 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem) static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem) { int nid; - - if (time_after(mem->next_scan_node_update, jiffies)) + /* + * numainfo_events > 0 means there was at least NUMAINFO_EVENTS_TARGET + * pagein/pageout changes since the last update. + */ + if (!atomic_read(&mem->numainfo_events)) + return; + if (atomic_inc_return(&mem->numainfo_updating) > 1) return; - mem->next_scan_node_update = jiffies + 10*HZ; /* make a nodemask where this memcg uses memory from */ mem->scan_nodes = node_states[N_HIGH_MEMORY]; for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) { - if (mem_cgroup_get_zonestat_node(mem, nid, LRU_INACTIVE_FILE) || - mem_cgroup_get_zonestat_node(mem, nid, LRU_ACTIVE_FILE)) - continue; - - if (total_swap_pages && - (mem_cgroup_get_zonestat_node(mem, nid, LRU_INACTIVE_ANON) || - mem_cgroup_get_zonestat_node(mem, nid, LRU_ACTIVE_ANON))) - continue; - node_clear(nid, mem->scan_nodes); + if (!test_mem_cgroup_node_reclaimable(mem, nid, false)) + node_clear(nid, mem->scan_nodes); } + + atomic_set(&mem->numainfo_events, 0); + atomic_set(&mem->numainfo_updating, 0); } /* @@ -1626,11 +1653,51 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *mem) return node; } +/* + * Check all nodes whether it contains reclaimable pages or not. + * For quick scan, we make use of scan_nodes. This will allow us to skip + * unused nodes. But scan_nodes is lazily updated and may not cotain + * enough new information. We need to do double check. + */ +bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) +{ + int nid; + + /* + * quick check...making use of scan_node. + * We can skip unused nodes. + */ + if (!nodes_empty(mem->scan_nodes)) { + for (nid = first_node(mem->scan_nodes); + nid < MAX_NUMNODES; + nid = next_node(nid, mem->scan_nodes)) { + + if (test_mem_cgroup_node_reclaimable(mem, nid, noswap)) + return true; + } + } + /* + * Check rest of nodes. + */ + for_each_node_state(nid, N_HIGH_MEMORY) { + if (node_isset(nid, mem->scan_nodes)) + continue; + if (test_mem_cgroup_node_reclaimable(mem, nid, noswap)) + return true; + } + return false; +} + #else int mem_cgroup_select_victim_node(struct mem_cgroup *mem) { return 0; } + +bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap) +{ + return test_mem_cgroup_node_reclaimable(mem, 0, noswap); +} #endif /* @@ -1701,7 +1768,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, } } } - if (!mem_cgroup_local_usage(victim)) { + if (!mem_cgroup_reclaimable(victim, noswap)) { /* this cgroup's local usage == 0 */ css_put(&victim->css); continue; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index eac0ba5..740c4f5 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -391,10 +391,11 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, struct task_struct *tsk; struct anon_vma *av; - read_lock(&tasklist_lock); av = page_lock_anon_vma(page); if (av == NULL) /* Not actually mapped anymore */ - goto out; + return; + + read_lock(&tasklist_lock); for_each_process (tsk) { struct anon_vma_chain *vmac; @@ -408,9 +409,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, add_to_kill(tsk, page, vma, to_kill, tkc); } } - page_unlock_anon_vma(av); -out: read_unlock(&tasklist_lock); + page_unlock_anon_vma(av); } /* @@ -424,17 +424,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, struct prio_tree_iter iter; struct address_space *mapping = page->mapping; - /* - * A note on the locking order between the two locks. - * We don't rely on this particular order. - * If you have some other code that needs a different order - * feel free to switch them around. Or add a reverse link - * from mm_struct to task_struct, then this could be all - * done without taking tasklist_lock and looping over all tasks. - */ - - read_lock(&tasklist_lock); mutex_lock(&mapping->i_mmap_mutex); + read_lock(&tasklist_lock); for_each_process(tsk) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); @@ -454,8 +445,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, add_to_kill(tsk, page, vma, to_kill, tkc); } } - mutex_unlock(&mapping->i_mmap_mutex); read_unlock(&tasklist_lock); + mutex_unlock(&mapping->i_mmap_mutex); } /* diff --git a/mm/memory.c b/mm/memory.c index 87d9353..9b8a01d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -305,6 +305,7 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) if (batch->nr == batch->max) { if (!tlb_next_batch(tlb)) return 0; + batch = tlb->active; } VM_BUG_ON(batch->nr > batch->max); @@ -2798,30 +2799,6 @@ void unmap_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL(unmap_mapping_range); -int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) -{ - struct address_space *mapping = inode->i_mapping; - - /* - * If the underlying filesystem is not going to provide - * a way to truncate a range of blocks (punch a hole) - - * we should return failure right now. - */ - if (!inode->i_op->truncate_range) - return -ENOSYS; - - mutex_lock(&inode->i_mutex); - down_write(&inode->i_alloc_sem); - unmap_mapping_range(mapping, offset, (end - offset), 1); - truncate_inode_pages_range(mapping, offset, end); - unmap_mapping_range(mapping, offset, (end - offset), 1); - inode->i_op->truncate_range(inode, offset, end); - up_write(&inode->i_alloc_sem); - mutex_unlock(&inode->i_mutex); - - return 0; -} - /* * We enter with non-exclusive mmap_sem (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 02159c7..c46887b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -498,7 +498,9 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ + mutex_lock(&zonelists_mutex); build_all_zonelists(NULL); + mutex_unlock(&zonelists_mutex); return pgdat; } @@ -521,7 +523,7 @@ int mem_online_node(int nid) lock_memory_hotplug(); pgdat = hotadd_new_pgdat(nid, 0); - if (pgdat) { + if (!pgdat) { ret = -ENOMEM; goto out; } @@ -1813,10 +1813,13 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, return NULL; } -int remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long to, unsigned long size, pgprot_t prot) +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) { - vma->vm_start = vma->vm_pgoff << PAGE_SHIFT; + if (addr != (pfn << PAGE_SHIFT)) + return -EINVAL; + + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; return 0; } EXPORT_SYMBOL(remap_pfn_range); @@ -38,9 +38,8 @@ * in arch-dependent flush_dcache_mmap_lock, * within inode_wb_list_lock in __sync_single_inode) * - * (code doesn't rely on that order so it could be switched around) - * ->tasklist_lock - * anon_vma->mutex (memory_failure, collect_procs_anon) + * anon_vma->mutex,mapping->i_mutex (memory_failure, collect_procs_anon) + * ->tasklist_lock * pte map lock */ @@ -539,7 +539,7 @@ static void shmem_free_pages(struct list_head *next) } while (next); } -static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) +void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long idx; @@ -562,6 +562,8 @@ static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) spinlock_t *punch_lock; unsigned long upper_limit; + truncate_inode_pages_range(inode->i_mapping, start, end); + inode->i_ctime = inode->i_mtime = CURRENT_TIME; idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; if (idx >= info->next_index) @@ -738,16 +740,8 @@ done2: * lowered next_index. Also, though shmem_getpage checks * i_size before adding to cache, no recheck after: so fix the * narrow window there too. - * - * Recalling truncate_inode_pages_range and unmap_mapping_range - * every time for punch_hole (which never got a chance to clear - * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive, - * yet hardly ever necessary: try to optimize them out later. */ truncate_inode_pages_range(inode->i_mapping, start, end); - if (punch_hole) - unmap_mapping_range(inode->i_mapping, start, - end - start, 1); } spin_lock(&info->lock); @@ -766,22 +760,23 @@ done2: shmem_free_pages(pages_to_free.next); } } +EXPORT_SYMBOL_GPL(shmem_truncate_range); -static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) +static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; - loff_t newsize = attr->ia_size; int error; error = inode_change_ok(inode, attr); if (error) return error; - if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE) - && newsize != inode->i_size) { + if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { + loff_t oldsize = inode->i_size; + loff_t newsize = attr->ia_size; struct page *page = NULL; - if (newsize < inode->i_size) { + if (newsize < oldsize) { /* * If truncating down to a partial page, then * if that page is already allocated, hold it @@ -810,12 +805,19 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) spin_unlock(&info->lock); } } - - /* XXX(truncate): truncate_setsize should be called last */ - truncate_setsize(inode, newsize); + if (newsize != oldsize) { + i_size_write(inode, newsize); + inode->i_ctime = inode->i_mtime = CURRENT_TIME; + } + if (newsize < oldsize) { + loff_t holebegin = round_up(newsize, PAGE_SIZE); + unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); + shmem_truncate_range(inode, newsize, (loff_t)-1); + /* unmap again to remove racily COWed private pages */ + unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); + } if (page) page_cache_release(page); - shmem_truncate_range(inode, newsize, (loff_t)-1); } setattr_copy(inode, attr); @@ -832,7 +834,6 @@ static void shmem_evict_inode(struct inode *inode) struct shmem_xattr *xattr, *nxattr; if (inode->i_mapping->a_ops == &shmem_aops) { - truncate_inode_pages(inode->i_mapping, 0); shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; shmem_truncate_range(inode, 0, (loff_t)-1); @@ -2706,7 +2707,7 @@ static const struct file_operations shmem_file_operations = { }; static const struct inode_operations shmem_inode_operations = { - .setattr = shmem_notify_change, + .setattr = shmem_setattr, .truncate_range = shmem_truncate_range, #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, @@ -2739,7 +2740,7 @@ static const struct inode_operations shmem_dir_inode_operations = { .removexattr = shmem_removexattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL - .setattr = shmem_notify_change, + .setattr = shmem_setattr, .check_acl = generic_check_acl, #endif }; @@ -2752,7 +2753,7 @@ static const struct inode_operations shmem_special_inode_operations = { .removexattr = shmem_removexattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL - .setattr = shmem_notify_change, + .setattr = shmem_setattr, .check_acl = generic_check_acl, #endif }; @@ -2908,6 +2909,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) return 0; } +void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end) +{ + truncate_inode_pages_range(inode->i_mapping, start, end); +} +EXPORT_SYMBOL_GPL(shmem_truncate_range); + #ifdef CONFIG_CGROUP_MEM_RES_CTLR /** * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file @@ -3028,3 +3035,26 @@ int shmem_zero_setup(struct vm_area_struct *vma) vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } + +/** + * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. + * @mapping: the page's address_space + * @index: the page index + * @gfp: the page allocator flags to use if allocating + * + * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", + * with any new page allocations done using the specified allocation flags. + * But read_cache_page_gfp() uses the ->readpage() method: which does not + * suit tmpfs, since it may have pages in swapcache, and needs to find those + * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. + * + * Provide a stub for those callers to start using now, then later + * flesh it out to call shmem_getpage() with additional gfp mask, when + * shmem_file_splice_read() is added and shmem_readpage() is removed. + */ +struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ + return read_cache_page_gfp(mapping, index, gfp); +} +EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); @@ -574,7 +574,9 @@ static struct arraycache_init initarray_generic = { {0, BOOT_CPUCACHE_ENTRIES, 1, 0} }; /* internal cache of cache description objs */ +static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES]; static struct kmem_cache cache_cache = { + .nodelists = cache_cache_nodelists, .batchcount = 1, .limit = BOOT_CPUCACHE_ENTRIES, .shared = 1, @@ -1492,11 +1494,10 @@ void __init kmem_cache_init(void) cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node]; /* - * struct kmem_cache size depends on nr_node_ids, which - * can be less than MAX_NUMNODES. + * struct kmem_cache size depends on nr_node_ids & nr_cpu_ids */ - cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) + - nr_node_ids * sizeof(struct kmem_list3 *); + cache_cache.buffer_size = offsetof(struct kmem_cache, array[nr_cpu_ids]) + + nr_node_ids * sizeof(struct kmem_list3 *); #if DEBUG cache_cache.obj_size = cache_cache.buffer_size; #endif @@ -2308,6 +2309,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (!cachep) goto oops; + cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids]; #if DEBUG cachep->obj_size = size; @@ -3153,12 +3155,11 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); -#if ARCH_SLAB_MINALIGN - if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) { + if (ARCH_SLAB_MINALIGN && + ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", - objp, ARCH_SLAB_MINALIGN); + objp, (int)ARCH_SLAB_MINALIGN); } -#endif return objp; } #else @@ -482,6 +482,8 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node) int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); void *ret; + gfp &= gfp_allowed_mask; + lockdep_trace_alloc(gfp); if (size < PAGE_SIZE - align) { @@ -608,6 +610,10 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node) { void *b; + flags &= gfp_allowed_mask; + + lockdep_trace_alloc(flags); + if (c->size < PAGE_SIZE) { b = slob_alloc(c->size, flags, c->align, node); trace_kmem_cache_alloc_node(_RET_IP_, b, c->size, @@ -27,6 +27,7 @@ #include <linux/memory.h> #include <linux/math64.h> #include <linux/fault-inject.h> +#include <linux/stacktrace.h> #include <trace/events/kmem.h> @@ -191,8 +192,12 @@ static LIST_HEAD(slab_caches); /* * Tracking user of a slab. */ +#define TRACK_ADDRS_COUNT 16 struct track { unsigned long addr; /* Called from address */ +#ifdef CONFIG_STACKTRACE + unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */ +#endif int cpu; /* Was running on cpu */ int pid; /* Pid context */ unsigned long when; /* When did the operation occur */ @@ -420,6 +425,24 @@ static void set_track(struct kmem_cache *s, void *object, struct track *p = get_track(s, object, alloc); if (addr) { +#ifdef CONFIG_STACKTRACE + struct stack_trace trace; + int i; + + trace.nr_entries = 0; + trace.max_entries = TRACK_ADDRS_COUNT; + trace.entries = p->addrs; + trace.skip = 3; + save_stack_trace(&trace); + + /* See rant in lockdep.c */ + if (trace.nr_entries != 0 && + trace.entries[trace.nr_entries - 1] == ULONG_MAX) + trace.nr_entries--; + + for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++) + p->addrs[i] = 0; +#endif p->addr = addr; p->cpu = smp_processor_id(); p->pid = current->pid; @@ -444,6 +467,16 @@ static void print_track(const char *s, struct track *t) printk(KERN_ERR "INFO: %s in %pS age=%lu cpu=%u pid=%d\n", s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid); +#ifdef CONFIG_STACKTRACE + { + int i; + for (i = 0; i < TRACK_ADDRS_COUNT; i++) + if (t->addrs[i]) + printk(KERN_ERR "\t%pS\n", (void *)t->addrs[i]); + else + break; + } +#endif } static void print_tracking(struct kmem_cache *s, void *object) @@ -557,10 +590,10 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) memset(p + s->objsize, val, s->inuse - s->objsize); } -static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes) +static u8 *check_bytes8(u8 *start, u8 value, unsigned int bytes) { while (bytes) { - if (*start != (u8)value) + if (*start != value) return start; start++; bytes--; @@ -568,6 +601,38 @@ static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes) return NULL; } +static u8 *check_bytes(u8 *start, u8 value, unsigned int bytes) +{ + u64 value64; + unsigned int words, prefix; + + if (bytes <= 16) + return check_bytes8(start, value, bytes); + + value64 = value | value << 8 | value << 16 | value << 24; + value64 = value64 | value64 << 32; + prefix = 8 - ((unsigned long)start) % 8; + + if (prefix) { + u8 *r = check_bytes8(start, value, prefix); + if (r) + return r; + start += prefix; + bytes -= prefix; + } + + words = bytes / 8; + + while (words) { + if (*(u64 *)start != value64) + return check_bytes8(start, value, 8); + start += 8; + words--; + } + + return check_bytes8(start, value, bytes % 8); +} + static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { @@ -2928,6 +2993,42 @@ size_t ksize(const void *object) } EXPORT_SYMBOL(ksize); +#ifdef CONFIG_SLUB_DEBUG +bool verify_mem_not_deleted(const void *x) +{ + struct page *page; + void *object = (void *)x; + unsigned long flags; + bool rv; + + if (unlikely(ZERO_OR_NULL_PTR(x))) + return false; + + local_irq_save(flags); + + page = virt_to_head_page(x); + if (unlikely(!PageSlab(page))) { + /* maybe it was from stack? */ + rv = true; + goto out_unlock; + } + + slab_lock(page); + if (on_freelist(page->slab, page, object)) { + object_err(page->slab, page, object, "Object is on free-list"); + rv = false; + } else { + rv = true; + } + slab_unlock(page); + +out_unlock: + local_irq_restore(flags); + return rv; +} +EXPORT_SYMBOL(verify_mem_not_deleted); +#endif + void kfree(const void *x) { struct page *page; diff --git a/mm/swapfile.c b/mm/swapfile.c index d537d29..ff8dc1a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -14,7 +14,7 @@ #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> -#include <linux/shm.h> +#include <linux/shmem_fs.h> #include <linux/blkdev.h> #include <linux/random.h> #include <linux/writeback.h> diff --git a/mm/truncate.c b/mm/truncate.c index 3a29a61..e13f22e 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -304,6 +304,11 @@ EXPORT_SYMBOL(truncate_inode_pages_range); * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_mutex. + * + * Note: When this function returns, there can be a page in the process of + * deletion (inside __delete_from_page_cache()) in the specified range. Thus + * mapping->nrpages can be non-zero when this function returns even after + * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { @@ -603,3 +608,27 @@ int vmtruncate(struct inode *inode, loff_t offset) return 0; } EXPORT_SYMBOL(vmtruncate); + +int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) +{ + struct address_space *mapping = inode->i_mapping; + + /* + * If the underlying filesystem is not going to provide + * a way to truncate a range of blocks (punch a hole) - + * we should return failure right now. + */ + if (!inode->i_op->truncate_range) + return -ENOSYS; + + mutex_lock(&inode->i_mutex); + down_write(&inode->i_alloc_sem); + unmap_mapping_range(mapping, offset, (end - offset), 1); + inode->i_op->truncate_range(inode, offset, end); + /* unmap again to remove racily COWed private pages */ + unmap_mapping_range(mapping, offset, (end - offset), 1); + up_write(&inode->i_alloc_sem); + mutex_unlock(&inode->i_mutex); + + return 0; +} diff --git a/mm/vmscan.c b/mm/vmscan.c index 8ff834e..d036e59 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1995,14 +1995,13 @@ restart: * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. */ -static unsigned long shrink_zones(int priority, struct zonelist *zonelist, +static void shrink_zones(int priority, struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; - unsigned long total_scanned = 0; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -2017,19 +2016,23 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist, continue; if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; /* Let kswapd poll it */ + /* + * This steals pages from memory cgroups over softlimit + * and returns the number of reclaimed pages and + * scanned pages. This works for global memory pressure + * and balancing, not for a memcg's limit. + */ + nr_soft_scanned = 0; + nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, + sc->order, sc->gfp_mask, + &nr_soft_scanned); + sc->nr_reclaimed += nr_soft_reclaimed; + sc->nr_scanned += nr_soft_scanned; + /* need some check for avoid more shrink_zone() */ } - nr_soft_scanned = 0; - nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone, - sc->order, sc->gfp_mask, - &nr_soft_scanned); - sc->nr_reclaimed += nr_soft_reclaimed; - total_scanned += nr_soft_scanned; - shrink_zone(priority, zone, sc); } - - return total_scanned; } static bool zone_reclaimable(struct zone *zone) @@ -2094,7 +2097,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, sc->nr_scanned = 0; if (!priority) disable_swap_token(sc->mem_cgroup); - total_scanned += shrink_zones(priority, zonelist, sc); + shrink_zones(priority, zonelist, sc); /* * Don't shrink slabs when reclaiming memory from * over limit cgroups @@ -2307,7 +2310,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages, for (i = 0; i <= classzone_idx; i++) present_pages += pgdat->node_zones[i].present_pages; - return balanced_pages > (present_pages >> 2); + /* A special case here: if zone has no page, we think it's balanced */ + return balanced_pages >= (present_pages >> 2); } /* is kswapd sleeping prematurely? */ @@ -2323,7 +2327,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, return true; /* Check the watermark levels */ - for (i = 0; i < pgdat->nr_zones; i++) { + for (i = 0; i <= classzone_idx; i++) { struct zone *zone = pgdat->node_zones + i; if (!populated_zone(zone)) @@ -2341,7 +2345,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining, } if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), - classzone_idx, 0)) + i, 0)) all_zones_ok = false; else balanced += zone->present_pages; @@ -2448,7 +2452,6 @@ loop_again: if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), 0, 0)) { end_zone = i; - *classzone_idx = i; break; } } @@ -2507,18 +2510,18 @@ loop_again: KSWAPD_ZONE_BALANCE_GAP_RATIO); if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone) + balance_gap, - end_zone, 0)) + end_zone, 0)) { shrink_zone(priority, zone, &sc); - reclaim_state->reclaimed_slab = 0; - nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages); - sc.nr_reclaimed += reclaim_state->reclaimed_slab; - total_scanned += sc.nr_scanned; - if (zone->all_unreclaimable) - continue; - if (nr_slab == 0 && - !zone_reclaimable(zone)) - zone->all_unreclaimable = 1; + reclaim_state->reclaimed_slab = 0; + nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages); + sc.nr_reclaimed += reclaim_state->reclaimed_slab; + total_scanned += sc.nr_scanned; + + if (nr_slab == 0 && !zone_reclaimable(zone)) + zone->all_unreclaimable = 1; + } + /* * If we've done a decent amount of scanning and * the reclaim ratio is low, start doing writepage @@ -2528,6 +2531,12 @@ loop_again: total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) sc.may_writepage = 1; + if (zone->all_unreclaimable) { + if (end_zone && end_zone == i) + end_zone--; + continue; + } + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { all_zones_ok = 0; @@ -2706,8 +2715,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx) */ static int kswapd(void *p) { - unsigned long order; - int classzone_idx; + unsigned long order, new_order; + int classzone_idx, new_classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -2737,17 +2746,23 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - order = 0; - classzone_idx = MAX_NR_ZONES - 1; + order = new_order = 0; + classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; for ( ; ; ) { - unsigned long new_order; - int new_classzone_idx; int ret; - new_order = pgdat->kswapd_max_order; - new_classzone_idx = pgdat->classzone_idx; - pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = MAX_NR_ZONES - 1; + /* + * If the last balance_pgdat was unsuccessful it's unlikely a + * new request of a similar or harder type will succeed soon + * so consider going to sleep on the basis we reclaimed at + */ + if (classzone_idx >= new_classzone_idx && order == new_order) { + new_order = pgdat->kswapd_max_order; + new_classzone_idx = pgdat->classzone_idx; + pgdat->kswapd_max_order = 0; + pgdat->classzone_idx = pgdat->nr_zones - 1; + } + if (order < new_order || classzone_idx > new_classzone_idx) { /* * Don't sleep if someone wants a larger 'order' @@ -2760,7 +2775,7 @@ static int kswapd(void *p) order = pgdat->kswapd_max_order; classzone_idx = pgdat->classzone_idx; pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = MAX_NR_ZONES - 1; + pgdat->classzone_idx = pgdat->nr_zones - 1; } ret = try_to_freeze(); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 7ea5cf9..6e82148 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -528,7 +528,11 @@ static int vlan_dev_init(struct net_device *dev) (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); - dev->hw_features = NETIF_F_ALL_TX_OFFLOADS; + dev->hw_features = NETIF_F_ALL_CSUM | NETIF_F_SG | + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | + NETIF_F_HIGHDMA | NETIF_F_SCTP_CSUM | + NETIF_F_ALL_FCOE; + dev->features |= real_dev->vlan_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; @@ -586,9 +590,14 @@ static void vlan_dev_uninit(struct net_device *dev) static u32 vlan_dev_fix_features(struct net_device *dev, u32 features) { struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + u32 old_features = features; features &= real_dev->features; features &= real_dev->vlan_features; + + if (old_features & NETIF_F_SOFT_FEATURES) + features |= old_features & NETIF_F_SOFT_FEATURES; + if (dev_ethtool_get_rx_csum(real_dev)) features |= NETIF_F_RXCSUM; features |= NETIF_F_LLTX; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3163330..bcd158f 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -393,6 +393,9 @@ int hci_conn_del(struct hci_conn *conn) hci_dev_put(hdev); + if (conn->handle == 0) + kfree(conn); + return 0; } @@ -608,11 +611,11 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) goto encrypt; auth: - if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) return 0; - hci_conn_auth(conn, sec_level, auth_type); - return 0; + if (!hci_conn_auth(conn, sec_level, auth_type)) + return 0; encrypt: if (conn->link_mode & HCI_LM_ENCRYPT) diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index c405a95..43b4c2d 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -464,7 +464,8 @@ static void hidp_idle_timeout(unsigned long arg) { struct hidp_session *session = (struct hidp_session *) arg; - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); } static void hidp_set_timer(struct hidp_session *session) @@ -535,7 +536,8 @@ static void hidp_process_hid_control(struct hidp_session *session, skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(current); } } @@ -706,9 +708,8 @@ static int hidp_session(void *arg) add_wait_queue(sk_sleep(intr_sk), &intr_wait); session->waiting_for_startup = 0; wake_up_interruptible(&session->startup_queue); - while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - + set_current_state(TASK_INTERRUPTIBLE); + while (!atomic_read(&session->terminate)) { if (ctrl_sk->sk_state != BT_CONNECTED || intr_sk->sk_state != BT_CONNECTED) break; @@ -726,6 +727,7 @@ static int hidp_session(void *arg) hidp_process_transmit(session); schedule(); + set_current_state(TASK_INTERRUPTIBLE); } set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(intr_sk), &intr_wait); @@ -1060,7 +1062,8 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, err_add_device: hid_destroy_device(session->hid); session->hid = NULL; - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); unlink: hidp_del_timer(session); @@ -1111,7 +1114,8 @@ int hidp_del_connection(struct hidp_conndel_req *req) skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); } } else err = -ENOENT; diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index 19e9500..af1bcc8 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -142,6 +142,7 @@ struct hidp_session { uint ctrl_mtu; uint intr_mtu; + atomic_t terminate; struct task_struct *task; unsigned char keys[8]; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index e64a1c2..7705e26 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -620,7 +620,8 @@ static void l2cap_conn_start(struct l2cap_conn *conn) struct sock *parent = bt_sk(sk)->parent; rsp.result = cpu_to_le16(L2CAP_CR_PEND); rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND); - parent->sk_data_ready(parent, 0); + if (parent) + parent->sk_data_ready(parent, 0); } else { sk->sk_state = BT_CONFIG; @@ -2323,7 +2324,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr sk = chan->sk; - if (sk->sk_state != BT_CONFIG) { + if (sk->sk_state != BT_CONFIG && sk->sk_state != BT_CONNECT2) { struct l2cap_cmd_rej rej; rej.reason = cpu_to_le16(0x0002); @@ -2334,7 +2335,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr /* Reject if config buffer is too small. */ len = cmd_len - sizeof(*req); - if (chan->conf_len + len > sizeof(chan->conf_req)) { + if (len < 0 || chan->conf_len + len > sizeof(chan->conf_req)) { l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, l2cap_build_conf_rsp(chan, rsp, L2CAP_CONF_REJECT, flags), rsp); @@ -4002,21 +4003,31 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } } else if (sk->sk_state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; - __u16 result; + __u16 res, stat; if (!status) { - sk->sk_state = BT_CONFIG; - result = L2CAP_CR_SUCCESS; + if (bt_sk(sk)->defer_setup) { + struct sock *parent = bt_sk(sk)->parent; + res = L2CAP_CR_PEND; + stat = L2CAP_CS_AUTHOR_PEND; + if (parent) + parent->sk_data_ready(parent, 0); + } else { + sk->sk_state = BT_CONFIG; + res = L2CAP_CR_SUCCESS; + stat = L2CAP_CS_NO_INFO; + } } else { sk->sk_state = BT_DISCONN; l2cap_sock_set_timer(sk, HZ / 10); - result = L2CAP_CR_SEC_BLOCK; + res = L2CAP_CR_SEC_BLOCK; + stat = L2CAP_CS_NO_INFO; } rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); - rsp.result = cpu_to_le16(result); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(res); + rsp.status = cpu_to_le16(stat); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index c188c80..32b8f9f 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -49,7 +49,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_pull(skb, ETH_HLEN); rcu_read_lock(); - if (is_multicast_ether_addr(dest)) { + if (is_broadcast_ether_addr(dest)) + br_flood_deliver(br, skb); + else if (is_multicast_ether_addr(dest)) { if (unlikely(netpoll_tx_running(dev))) { br_flood_deliver(br, skb); goto out; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f3ac1e8..f06ee39 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -60,7 +60,7 @@ int br_handle_frame_finish(struct sk_buff *skb) br = p->br; br_fdb_update(br, p, eth_hdr(skb)->h_source); - if (is_multicast_ether_addr(dest) && + if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && br_multicast_rcv(br, p, skb)) goto drop; @@ -77,7 +77,9 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; - if (is_multicast_ether_addr(dest)) { + if (is_broadcast_ether_addr(dest)) + skb2 = skb; + else if (is_multicast_ether_addr(dest)) { mdst = br_mdb_get(br, skb); if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) { if ((mdst && mdst->mglist) || diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 29b9812..2d85ca7 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1379,8 +1379,11 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; - if (iph->protocol != IPPROTO_IGMP) + if (iph->protocol != IPPROTO_IGMP) { + if ((iph->daddr & IGMP_LOCAL_GROUP_MASK) != IGMP_LOCAL_GROUP) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; + } len = ntohs(iph->tot_len); if (skb->len < len || len < ip_hdrlen(skb)) diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c index a3a3a31..41466cc 100644 --- a/net/ceph/ceph_fs.c +++ b/net/ceph/ceph_fs.c @@ -36,16 +36,19 @@ int ceph_flags_to_mode(int flags) if ((flags & O_DIRECTORY) == O_DIRECTORY) return CEPH_FILE_MODE_PIN; #endif - if ((flags & O_APPEND) == O_APPEND) - flags |= O_WRONLY; - if ((flags & O_ACCMODE) == O_RDWR) - mode = CEPH_FILE_MODE_RDWR; - else if ((flags & O_ACCMODE) == O_WRONLY) + switch (flags & O_ACCMODE) { + case O_WRONLY: mode = CEPH_FILE_MODE_WR; - else + break; + case O_RDONLY: mode = CEPH_FILE_MODE_RD; - + break; + case O_RDWR: + case O_ACCMODE: /* this is what the VFS does */ + mode = CEPH_FILE_MODE_RDWR; + break; + } #ifdef O_LAZY if (flags & O_LAZY) mode |= CEPH_FILE_MODE_LAZY; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 9cb627a..7330c27 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -477,8 +477,9 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, calc_layout(osdc, vino, layout, off, plen, req, ops); req->r_file_layout = *layout; /* keep a copy */ - /* in case it differs from natural alignment that calc_layout - filled in for us */ + /* in case it differs from natural (file) alignment that + calc_layout filled in for us */ + req->r_num_pages = calc_pages_for(page_align, *plen); req->r_page_alignment = page_align; ceph_osdc_build_request(req, off, plen, ops, @@ -2027,8 +2028,9 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, int want = calc_pages_for(req->r_page_alignment, data_len); if (unlikely(req->r_num_pages < want)) { - pr_warning("tid %lld reply %d > expected %d pages\n", - tid, want, m->nr_pages); + pr_warning("tid %lld reply has %d bytes %d pages, we" + " had only %d pages ready\n", tid, data_len, + want, req->r_num_pages); *skip = 1; ceph_msg_put(m); m = NULL; diff --git a/net/core/dst.c b/net/core/dst.c index 9ccca03..6135f36 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -190,7 +190,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->lastuse = jiffies; dst->flags = flags; dst->next = NULL; - dst_entries_add(ops, 1); + if (!(flags & DST_NOCOUNT)) + dst_entries_add(ops, 1); return dst; } EXPORT_SYMBOL(dst_alloc); @@ -243,7 +244,8 @@ again: neigh_release(neigh); } - dst_entries_add(dst->ops, -1); + if (!(dst->flags & DST_NOCOUNT)) + dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index eae1f67..ef1528a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -465,8 +465,10 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) goto out; - if (addr->sin_family != AF_INET) + if (addr->sin_family != AF_INET) { + err = -EAFNOSUPPORT; goto out; + } chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a8024ea..84f26e8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -802,8 +802,6 @@ static int __ip_append_data(struct sock *sk, skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; - length += exthdrlen; - transhdrlen += exthdrlen; mtu = cork->fragsize; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -830,7 +828,7 @@ static int __ip_append_data(struct sock *sk, cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags); @@ -883,17 +881,16 @@ alloc_new_skb: else alloclen = fraglen; + alloclen += exthdrlen; + /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ - if (datalen == length + fraggap) { + if (datalen == length + fraggap) alloclen += rt->dst.trailer_len; - /* make sure mtu is not reached */ - if (datalen > mtu - fragheaderlen - rt->dst.trailer_len) - datalen -= ALIGN(rt->dst.trailer_len, 8); - } + if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len + 15, @@ -926,11 +923,11 @@ alloc_new_skb: /* * Find where to start putting bytes. */ - data = skb_put(skb, fraglen); + data = skb_put(skb, fraglen + exthdrlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); - data += fragheaderlen; + data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( @@ -1064,7 +1061,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, */ *rtp = NULL; cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + rt->dst.dev->mtu : dst_mtu(&rt->dst); cork->dst = &rt->dst; cork->length = 0; cork->tx_flags = ipc->tx_flags; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 4614bab..2e97e3e 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,51 +17,35 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; - unsigned long orefdst; + __be32 saddr = iph->saddr; + __u8 flags = 0; unsigned int hh_len; - unsigned int type; - type = inet_addr_type(net, iph->saddr); - if (skb->sk && inet_sk(skb->sk)->transparent) - type = RTN_LOCAL; - if (addr_type == RTN_UNSPEC) - addr_type = type; + if (!skb->sk && addr_type != RTN_LOCAL) { + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(net, saddr); + if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) + flags |= FLOWI_FLAG_ANYSRC; + else + saddr = 0; + } /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. */ - if (addr_type == RTN_LOCAL) { - fl4.daddr = iph->daddr; - if (type == RTN_LOCAL) - fl4.saddr = iph->saddr; - fl4.flowi4_tos = RT_TOS(iph->tos); - fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; - fl4.flowi4_mark = skb->mark; - fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return -1; - - /* Drop old route. */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - } else { - /* non-local src, find valid iif to satisfy - * rp-filter when calling ip_route_input. */ - fl4.daddr = iph->saddr; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return -1; + fl4.daddr = iph->daddr; + fl4.saddr = saddr; + fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + fl4.flowi4_mark = skb->mark; + fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags; + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return -1; - orefdst = skb->_skb_refdst; - if (ip_route_input(skb, iph->daddr, iph->saddr, - RT_TOS(iph->tos), rt->dst.dev) != 0) { - dst_release(&rt->dst); - return -1; - } - dst_release(&rt->dst); - refdst_drop(orefdst); - } + /* Drop old route. */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); if (skb_dst(skb)->error) return -1; diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 1ff79e5..51f13f8 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -40,7 +40,6 @@ static void send_reset(struct sk_buff *oldskb, int hook) struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _otcph, *tcph; - unsigned int addr_type; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) @@ -55,6 +54,9 @@ static void send_reset(struct sk_buff *oldskb, int hook) if (oth->rst) return; + if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + return; + /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return; @@ -101,19 +103,11 @@ static void send_reset(struct sk_buff *oldskb, int hook) nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); - addr_type = RTN_UNSPEC; - if (hook != NF_INET_FORWARD -#ifdef CONFIG_BRIDGE_NETFILTER - || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED) -#endif - ) - addr_type = RTN_LOCAL; - /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(nskb, addr_type)) + if (ip_route_me_harder(nskb, RTN_UNSPEC)) goto free_nskb; niph->ttl = ip4_dst_hoplimit(skb_dst(nskb)); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 054a59d..46febca 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3220,7 +3220,7 @@ __setup("thash_entries=", set_thash_entries); void __init tcp_init(void) { struct sk_buff *skb = NULL; - unsigned long nr_pages, limit; + unsigned long limit; int i, max_share, cnt; unsigned long jiffy = jiffies; @@ -3277,13 +3277,7 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; sysctl_tcp_mem[1] = limit; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index abca870..198f75b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1249,6 +1249,9 @@ csum_copy_err: if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -2206,16 +2209,10 @@ void __init udp_table_init(struct udp_table *table, const char *name) void __init udp_init(void) { - unsigned long nr_pages, limit; + unsigned long limit; udp_table_init(&udp_table, "UDP"); - /* Set the pressure threshold up by the same strategy of TCP. It is a - * fraction of global memory that is up to 1/2 at 256 MB, decreasing - * toward zero with the amount of memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2d51840..327a617 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -32,7 +32,12 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) dst = skb_dst(skb); mtu = dst_mtu(dst); if (skb->len > mtu) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + if (skb->sk) + ip_local_error(skb->sk, EMSGSIZE, ip_hdr(skb)->daddr, + inet_sk(skb->sk)->inet_dport, mtu); + else + icmp_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); ret = -EMSGSIZE; } out: diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d450a2f..3b5669a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -274,7 +274,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return -EINVAL; if (addr->sin6_family != AF_INET6) - return -EINVAL; + return -EAFNOSUPPORT; addr_type = ipv6_addr_type(&addr->sin6_addr); if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index de2b1de..0ef1f08 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -228,9 +228,10 @@ static struct rt6_info ip6_blk_hole_entry_template = { /* allocate dst with ip6_dst_ops */ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, - struct net_device *dev) + struct net_device *dev, + int flags) { - struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, 0); + struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags); memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); @@ -1042,7 +1043,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(idev == NULL)) return NULL; - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); if (unlikely(rt == NULL)) { in6_dev_put(idev); goto out; @@ -1062,14 +1063,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); rt->dst.output = ip6_output; -#if 0 /* there's no chance to use these for ndisc */ - rt->dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST - ? DST_HOST - : 0; - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); - rt->rt6i_dst.plen = 128; -#endif - spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; icmp6_dst_gc_list = &rt->dst; @@ -1214,7 +1207,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT); if (rt == NULL) { err = -ENOMEM; @@ -1244,7 +1237,7 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) - rt->dst.flags = DST_HOST; + rt->dst.flags |= DST_HOST; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); @@ -1734,7 +1727,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { struct net *net = dev_net(ort->rt6i_dev); struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - ort->dst.dev); + ort->dst.dev, 0); if (rt) { rt->dst.input = ort->dst.input; @@ -2013,7 +2006,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, { struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - net->loopback_dev); + net->loopback_dev, 0); struct neighbour *neigh; if (rt == NULL) { @@ -2025,7 +2018,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, in6_dev_hold(idev); - rt->dst.flags = DST_HOST; + rt->dst.flags |= DST_HOST; rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_idev = idev; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 41f8c9c..328985c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -453,8 +453,11 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (flags & MSG_DONTWAIT) + if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 58ffa7d..669d2e3 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -877,7 +877,8 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, for (i = 0; i < IEEE80211_NUM_BANDS; i++) { local->sched_scan_ies.ie[i] = kzalloc(2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len, + local->scan_ies_len + + req->ie_len, GFP_KERNEL); if (!local->sched_scan_ies.ie[i]) { ret = -ENOMEM; diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 9dc3b5f..8f6a302 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -86,6 +86,11 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + int queue = rx->queue; + + /* otherwise, TKIP is vulnerable to TID 0 vs. non-QoS replays */ + if (rx->queue == NUM_RX_DATA_QUEUES - 1) + queue = 0; /* * it makes no sense to check for MIC errors on anything other @@ -148,13 +153,19 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) update_iv: /* update IV in key information to be able to detect replays */ - rx->key->u.tkip.rx[rx->queue].iv32 = rx->tkip_iv32; - rx->key->u.tkip.rx[rx->queue].iv16 = rx->tkip_iv16; + rx->key->u.tkip.rx[queue].iv32 = rx->tkip_iv32; + rx->key->u.tkip.rx[queue].iv16 = rx->tkip_iv16; return RX_CONTINUE; mic_fail: - mac80211_ev_michael_mic_failure(rx->sdata, rx->key->conf.keyidx, + /* + * In some cases the key can be unset - e.g. a multicast packet, in + * a driver that supports HW encryption. Send up the key idx only if + * the key is set. + */ + mac80211_ev_michael_mic_failure(rx->sdata, + rx->key ? rx->key->conf.keyidx : -1, (void *) skb->data, NULL, GFP_ATOMIC); return RX_DROP_UNUSABLE; } @@ -235,6 +246,11 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) struct ieee80211_key *key = rx->key; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + int queue = rx->queue; + + /* otherwise, TKIP is vulnerable to TID 0 vs. non-QoS replays */ + if (rx->queue == NUM_RX_DATA_QUEUES - 1) + queue = 0; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -255,7 +271,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) res = ieee80211_tkip_decrypt_data(rx->local->wep_rx_tfm, key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, - hdr->addr1, hwaccel, rx->queue, + hdr->addr1, hwaccel, queue, &rx->tkip_iv32, &rx->tkip_iv16); if (res != TKIP_DECRYPT_OK) diff --git a/net/sctp/output.c b/net/sctp/output.c index b4f3cf0..08b3cea 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -500,23 +500,20 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: Adler-32 is no longer applicable, as has been replaced * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ - if (!sctp_checksum_disable && - !(dst->dev->features & (NETIF_F_NO_CSUM | NETIF_F_SCTP_CSUM))) { - __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); + if (!sctp_checksum_disable) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); - /* 3) Put the resultant value into the checksum field in the - * common header, and leave the rest of the bits unchanged. - */ - sh->checksum = sctp_end_cksum(crc32); - } else { - if (dst->dev->features & NETIF_F_SCTP_CSUM) { + /* 3) Put the resultant value into the checksum field in the + * common header, and leave the rest of the bits unchanged. + */ + sh->checksum = sctp_end_cksum(crc32); + } else { /* no need to seed pseudo checksum for SCTP */ nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (skb_transport_header(nskb) - nskb->head); nskb->csum_offset = offsetof(struct sctphdr, checksum); - } else { - nskb->ip_summed = CHECKSUM_UNNECESSARY; } } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 1c88c89..d036821 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1582,6 +1582,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, #endif /* SCTP_DEBUG */ if (transport) { if (bytes_acked) { + struct sctp_association *asoc = transport->asoc; + /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never @@ -1600,6 +1602,17 @@ static void sctp_check_transmitted(struct sctp_outq *q, transport->error_count = 0; transport->asoc->overall_error_count = 0; + /* + * While in SHUTDOWN PENDING, we may have started + * the T5 shutdown guard timer after reaching the + * retransmission limit. Stop that timer as soon + * as the receiver acknowledged any data. + */ + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && + del_timer(&asoc->timers + [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) + sctp_association_put(asoc); + /* Mark the destination transport address as * active if it is not so marked. */ @@ -1629,10 +1642,15 @@ static void sctp_check_transmitted(struct sctp_outq *q, * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. + * + * Allow the association to timeout while in SHUTDOWN + * PENDING or SHUTDOWN RECEIVED in case the receiver + * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && - (sack_ctsn+2 == q->asoc->next_tsn)) { + (sack_ctsn+2 == q->asoc->next_tsn) && + q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { SCTP_DEBUG_PRINTK("%s: SACK received for zero " "window probe: %u\n", __func__, sack_ctsn); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 67380a2..207175b 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1058,7 +1058,6 @@ SCTP_STATIC __init int sctp_init(void) int status = -EINVAL; unsigned long goal; unsigned long limit; - unsigned long nr_pages; int max_share; int order; @@ -1148,15 +1147,7 @@ SCTP_STATIC __init int sctp_init(void) /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - * Note this initializes the data in sctpv6_prot too - * Unabashedly stolen from tcp_init - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_sctp_mem[0] = limit / 4 * 3; sysctl_sctp_mem[1] = limit; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 534c2e5..6e0f882 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -670,10 +670,19 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the * HEARTBEAT should clear the error counter of the destination * transport address to which the HEARTBEAT was sent. - * The association's overall error count is also cleared. */ t->error_count = 0; - t->asoc->overall_error_count = 0; + + /* + * Although RFC4960 specifies that the overall error count must + * be cleared when a HEARTBEAT ACK is received, we make an + * exception while in SHUTDOWN PENDING. If the peer keeps its + * window shut forever, we may never be able to transmit our + * outstanding data and rely on the retransmission limit be reached + * to shutdown the association. + */ + if (t->asoc->state != SCTP_STATE_SHUTDOWN_PENDING) + t->asoc->overall_error_count = 0; /* Clear the hb_sent flag to signal that we had a good * acknowledgement. @@ -1437,6 +1446,13 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_cmd_setup_t2(commands, asoc, cmd->obj.ptr); break; + case SCTP_CMD_TIMER_START_ONCE: + timer = &asoc->timers[cmd->obj.to]; + + if (timer_pending(timer)) + break; + /* fall through */ + case SCTP_CMD_TIMER_START: timer = &asoc->timers[cmd->obj.to]; timeout = asoc->timeouts[cmd->obj.to]; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a297283..2461171 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -5154,7 +5154,7 @@ sctp_disposition_t sctp_sf_do_9_2_start_shutdown( * The sender of the SHUTDOWN MAY also start an overall guard timer * 'T5-shutdown-guard' to bound the overall time for shutdown sequence. */ - sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); if (asoc->autoclose) @@ -5299,14 +5299,28 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(const struct sctp_endpoint *ep, SCTP_INC_STATS(SCTP_MIB_T3_RTX_EXPIREDS); if (asoc->overall_error_count >= asoc->max_retrans) { - sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, - SCTP_ERROR(ETIMEDOUT)); - /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, - SCTP_PERR(SCTP_ERROR_NO_ERROR)); - SCTP_INC_STATS(SCTP_MIB_ABORTEDS); - SCTP_DEC_STATS(SCTP_MIB_CURRESTAB); - return SCTP_DISPOSITION_DELETE_TCB; + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { + /* + * We are here likely because the receiver had its rwnd + * closed for a while and we have not been able to + * transmit the locally queued data within the maximum + * retransmission attempts limit. Start the T5 + * shutdown guard timer to give the receiver one last + * chance and some additional time to recover before + * aborting. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START_ONCE, + SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, + SCTP_ERROR(ETIMEDOUT)); + /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_NO_ERROR)); + SCTP_INC_STATS(SCTP_MIB_ABORTEDS); + SCTP_DEC_STATS(SCTP_MIB_CURRESTAB); + return SCTP_DISPOSITION_DELETE_TCB; + } } /* E1) For the destination address for which the timer diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 0338dc6..7c211a7 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -827,7 +827,7 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ - TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6766913..d3ccf79 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1384,6 +1384,7 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) struct sctp_endpoint *ep; struct sctp_association *asoc; struct list_head *pos, *temp; + unsigned int data_was_unread; SCTP_DEBUG_PRINTK("sctp_close(sk: 0x%p, timeout:%ld)\n", sk, timeout); @@ -1393,6 +1394,10 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) ep = sctp_sk(sk)->ep; + /* Clean up any skbs sitting on the receive queue. */ + data_was_unread = sctp_queue_purge_ulpevents(&sk->sk_receive_queue); + data_was_unread += sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); + /* Walk all associations on an endpoint. */ list_for_each_safe(pos, temp, &ep->asocs) { asoc = list_entry(pos, struct sctp_association, asocs); @@ -1410,7 +1415,9 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) } } - if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { + if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) || + !skb_queue_empty(&asoc->ulpq.reasm) || + (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); @@ -1420,10 +1427,6 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) sctp_primitive_SHUTDOWN(asoc, NULL); } - /* Clean up any skbs sitting on the receive queue. */ - sctp_queue_purge_ulpevents(&sk->sk_receive_queue); - sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); - /* On a TCP-style socket, block for at most linger_time if set. */ if (sctp_style(sk, TCP) && timeout) sctp_wait_for_close(sk, timeout); @@ -2073,10 +2076,33 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk, static int sctp_setsockopt_events(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_association *asoc; + struct sctp_ulpevent *event; + if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; + + /* + * At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, + * if there is no data to be sent or retransmit, the stack will + * immediately send up this notification. + */ + if (sctp_ulpevent_type_enabled(SCTP_SENDER_DRY_EVENT, + &sctp_sk(sk)->subscribe)) { + asoc = sctp_id2assoc(sk, 0); + + if (asoc && sctp_outq_is_empty(&asoc->outqueue)) { + event = sctp_ulpevent_make_sender_dry_event(asoc, + GFP_ATOMIC); + if (!event) + return -ENOMEM; + + sctp_ulpq_tail_event(&asoc->ulpq, event); + } + } + return 0; } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index e70e5fc..8a84017 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -1081,9 +1081,19 @@ void sctp_ulpevent_free(struct sctp_ulpevent *event) } /* Purge the skb lists holding ulpevents. */ -void sctp_queue_purge_ulpevents(struct sk_buff_head *list) +unsigned int sctp_queue_purge_ulpevents(struct sk_buff_head *list) { struct sk_buff *skb; - while ((skb = skb_dequeue(list)) != NULL) - sctp_ulpevent_free(sctp_skb2event(skb)); + unsigned int data_unread = 0; + + while ((skb = skb_dequeue(list)) != NULL) { + struct sctp_ulpevent *event = sctp_skb2event(skb); + + if (!sctp_ulpevent_is_notification(event)) + data_unread += skb->len; + + sctp_ulpevent_free(event); + } + + return data_unread; } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 339ba64..5daf6cc 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -577,13 +577,13 @@ retry: } inode = &gss_msg->inode->vfs_inode; for (;;) { - prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_KILLABLE); spin_lock(&inode->i_lock); if (gss_msg->ctx != NULL || gss_msg->msg.errno < 0) { break; } spin_unlock(&inode->i_lock); - if (signalled()) { + if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto out_intr; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b84d739..8c91415 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1061,7 +1061,7 @@ call_allocate(struct rpc_task *task) dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid); - if (RPC_IS_ASYNC(task) || !signalled()) { + if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) { task->tk_action = call_allocate; rpc_delay(task, HZ>>4); return; @@ -1175,6 +1175,9 @@ call_bind_status(struct rpc_task *task) status = -EOPNOTSUPP; break; } + if (task->tk_rebind_retry == 0) + break; + task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; case -ETIMEDOUT: diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 9a80a92..e45d2fb 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -597,7 +597,7 @@ void rpcb_getport_async(struct rpc_task *task) u32 bind_version; struct rpc_xprt *xprt; struct rpc_clnt *rpcb_clnt; - static struct rpcbind_args *map; + struct rpcbind_args *map; struct rpc_task *child; struct sockaddr_storage addr; struct sockaddr *sap = (struct sockaddr *)&addr; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6b43ee7..4814e24 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -616,30 +616,25 @@ static void __rpc_execute(struct rpc_task *task) BUG_ON(RPC_IS_QUEUED(task)); for (;;) { + void (*do_action)(struct rpc_task *); /* - * Execute any pending callback. + * Execute any pending callback first. */ - if (task->tk_callback) { - void (*save_callback)(struct rpc_task *); - - /* - * We set tk_callback to NULL before calling it, - * in case it sets the tk_callback field itself: - */ - save_callback = task->tk_callback; - task->tk_callback = NULL; - save_callback(task); - } else { + do_action = task->tk_callback; + task->tk_callback = NULL; + if (do_action == NULL) { /* * Perform the next FSM step. - * tk_action may be NULL when the task has been killed - * by someone else. + * tk_action may be NULL if the task has been killed. + * In particular, note that rpc_killall_tasks may + * do this at any time, so beware when dereferencing. */ - if (task->tk_action == NULL) + do_action = task->tk_action; + if (do_action == NULL) break; - task->tk_action(task); } + do_action(task); /* * Lockless check for whether task is sleeping or not. @@ -792,6 +787,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; + task->tk_rebind_retry = 2; task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; diff --git a/net/wireless/core.c b/net/wireless/core.c index c22ef34..880dbe2 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -366,6 +366,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) mutex_init(&rdev->mtx); mutex_init(&rdev->devlist_mtx); + mutex_init(&rdev->sched_scan_mtx); INIT_LIST_HEAD(&rdev->netdev_list); spin_lock_init(&rdev->bss_lock); INIT_LIST_HEAD(&rdev->bss_list); @@ -701,6 +702,7 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) rfkill_destroy(rdev->rfkill); mutex_destroy(&rdev->mtx); mutex_destroy(&rdev->devlist_mtx); + mutex_destroy(&rdev->sched_scan_mtx); list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&scan->pub); cfg80211_rdev_free_wowlan(rdev); @@ -737,12 +739,16 @@ static void wdev_cleanup_work(struct work_struct *work) ___cfg80211_scan_done(rdev, true); } + cfg80211_unlock_rdev(rdev); + + mutex_lock(&rdev->sched_scan_mtx); + if (WARN_ON(rdev->sched_scan_req && rdev->sched_scan_req->dev == wdev->netdev)) { __cfg80211_stop_sched_scan(rdev, false); } - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); mutex_lock(&rdev->devlist_mtx); rdev->opencount--; @@ -830,9 +836,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); __cfg80211_stop_sched_scan(rdev, false); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); wdev_lock(wdev); #ifdef CONFIG_CFG80211_WEXT diff --git a/net/wireless/core.h b/net/wireless/core.h index 3dce1f1..a570ff9 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -65,6 +65,8 @@ struct cfg80211_registered_device { struct work_struct scan_done_wk; struct work_struct sched_scan_results_wk; + struct mutex sched_scan_mtx; + #ifdef CONFIG_NL80211_TESTMODE struct genl_info *testmode_info; #endif diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 98fa8eb..cea3381 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3461,9 +3461,6 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; - if (rdev->sched_scan_req) - return -EINPROGRESS; - if (!info->attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) return -EINVAL; @@ -3502,12 +3499,21 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (ie_len > wiphy->max_scan_ie_len) return -EINVAL; + mutex_lock(&rdev->sched_scan_mtx); + + if (rdev->sched_scan_req) { + err = -EINPROGRESS; + goto out; + } + request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); - if (!request) - return -ENOMEM; + if (!request) { + err = -ENOMEM; + goto out; + } if (n_ssids) request->ssids = (void *)&request->channels[n_channels]; @@ -3605,6 +3611,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, out_free: kfree(request); out: + mutex_unlock(&rdev->sched_scan_mtx); return err; } @@ -3612,12 +3619,17 @@ static int nl80211_stop_sched_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + int err; if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) || !rdev->ops->sched_scan_stop) return -EOPNOTSUPP; - return __cfg80211_stop_sched_scan(rdev, false); + mutex_lock(&rdev->sched_scan_mtx); + err = __cfg80211_stop_sched_scan(rdev, false); + mutex_unlock(&rdev->sched_scan_mtx); + + return err; } static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, @@ -6463,7 +6475,8 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, if (addr) NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); NLA_PUT_U32(msg, NL80211_ATTR_KEY_TYPE, key_type); - NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_id); + if (key_id != -1) + NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_id); if (tsc) NLA_PUT(msg, NL80211_ATTR_KEY_SEQ, 6, tsc); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7a6c676..ae0c225 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -100,14 +100,14 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, sched_scan_results_wk); - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); /* we don't have sched_scan_req anymore if the scan is stopping */ if (rdev->sched_scan_req) nl80211_send_sched_scan_results(rdev, rdev->sched_scan_req->dev); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); } void cfg80211_sched_scan_results(struct wiphy *wiphy) @@ -123,9 +123,9 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); __cfg80211_stop_sched_scan(rdev, true); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); @@ -135,7 +135,7 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, int err; struct net_device *dev; - ASSERT_RDEV_LOCK(rdev); + lockdep_assert_held(&rdev->sched_scan_mtx); if (!rdev->sched_scan_req) return 0; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9bec2e8..5ce74a3 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -50,7 +50,7 @@ static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); -static int xfrm_bundle_ok(struct xfrm_dst *xdst, int family); +static int xfrm_bundle_ok(struct xfrm_dst *xdst); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, @@ -2241,7 +2241,7 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) static int stale_bundle(struct dst_entry *dst) { - return !xfrm_bundle_ok((struct xfrm_dst *)dst, AF_UNSPEC); + return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) @@ -2313,7 +2313,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) * still valid. */ -static int xfrm_bundle_ok(struct xfrm_dst *first, int family) +static int xfrm_bundle_ok(struct xfrm_dst *first) { struct dst_entry *dst = &first->u.dst; struct xfrm_dst *last; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d70f85e..9414b9c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1345,6 +1345,8 @@ out: xfrm_state_check_expire(x1); err = 0; + x->km.state = XFRM_STATE_DEAD; + __xfrm_state_put(x); } spin_unlock_bh(&x1->lock); diff --git a/scripts/depmod.sh b/scripts/depmod.sh index 3b029cb..a272356 100755 --- a/scripts/depmod.sh +++ b/scripts/depmod.sh @@ -21,13 +21,15 @@ fi # older versions of depmod require the version string to start with three # numbers, so we cheat with a symlink here depmod_hack_needed=true -mkdir -p .tmp_depmod/lib/modules/$KERNELRELEASE -if "$DEPMOD" -b .tmp_depmod $KERNELRELEASE 2>/dev/null; then - if test -e .tmp_depmod/lib/modules/$KERNELRELEASE/modules.dep -o \ - -e .tmp_depmod/lib/modules/$KERNELRELEASE/modules.dep.bin; then +tmp_dir=$(mktemp -d ${TMPDIR:-/tmp}/depmod.XXXXXX) +mkdir -p "$tmp_dir/lib/modules/$KERNELRELEASE" +if "$DEPMOD" -b "$tmp_dir" $KERNELRELEASE 2>/dev/null; then + if test -e "$tmp_dir/lib/modules/$KERNELRELEASE/modules.dep" -o \ + -e "$tmp_dir/lib/modules/$KERNELRELEASE/modules.dep.bin"; then depmod_hack_needed=false fi fi +rm -rf "$tmp_dir" if $depmod_hack_needed; then symlink="$INSTALL_MOD_PATH/lib/modules/99.98.$KERNELRELEASE" ln -s "$KERNELRELEASE" "$symlink" diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 8e319a4..8246532 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -469,7 +469,7 @@ static struct key *construct_key_and_link(struct key_type *type, } else if (ret == -EINPROGRESS) { ret = 0; } else { - key = ERR_PTR(ret); + goto couldnt_alloc_key; } key_put(dest_keyring); @@ -479,6 +479,7 @@ static struct key *construct_key_and_link(struct key_type *type, construction_failed: key_negate_and_link(key, key_negative_timeout, NULL, NULL); key_put(key); +couldnt_alloc_key: key_put(dest_keyring); kleave(" = %d", ret); return ERR_PTR(ret); diff --git a/sound/atmel/abdac.c b/sound/atmel/abdac.c index 6e24091..bfee60c 100644 --- a/sound/atmel/abdac.c +++ b/sound/atmel/abdac.c @@ -599,4 +599,4 @@ module_exit(atmel_abdac_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Driver for Atmel Audio Bitstream DAC (ABDAC)"); -MODULE_AUTHOR("Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>"); +MODULE_AUTHOR("Hans-Christian Egtvedt <egtvedt@samfundet.no>"); diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c index b310702..ac35222 100644 --- a/sound/atmel/ac97c.c +++ b/sound/atmel/ac97c.c @@ -1199,4 +1199,4 @@ module_exit(atmel_ac97c_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Driver for Atmel AC97 controller"); -MODULE_AUTHOR("Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>"); +MODULE_AUTHOR("Hans-Christian Egtvedt <egtvedt@samfundet.no>"); diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c index 2ca6f4f..e3569bd 100644 --- a/sound/pci/asihpi/asihpi.c +++ b/sound/pci/asihpi/asihpi.c @@ -27,7 +27,6 @@ #include "hpioctl.h" #include <linux/pci.h> -#include <linux/version.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/slab.h> diff --git a/sound/pci/cs5535audio/cs5535audio_pcm.c b/sound/pci/cs5535audio/cs5535audio_pcm.c index f16bc8a..e083122 100644 --- a/sound/pci/cs5535audio/cs5535audio_pcm.c +++ b/sound/pci/cs5535audio/cs5535audio_pcm.c @@ -149,7 +149,7 @@ static int cs5535audio_build_dma_packets(struct cs5535audio *cs5535au, &((struct cs5535audio_dma_desc *) dma->desc_buf.area)[i]; desc->addr = cpu_to_le32(addr); desc->size = cpu_to_le32(period_bytes); - desc->ctlreserved = cpu_to_le32(PRD_EOP); + desc->ctlreserved = cpu_to_le16(PRD_EOP); desc_addr += sizeof(struct cs5535audio_dma_desc); addr += period_bytes; } @@ -157,7 +157,7 @@ static int cs5535audio_build_dma_packets(struct cs5535audio *cs5535au, lastdesc = &((struct cs5535audio_dma_desc *) dma->desc_buf.area)[periods]; lastdesc->addr = cpu_to_le32((u32) dma->desc_buf.addr); lastdesc->size = 0; - lastdesc->ctlreserved = cpu_to_le32(PRD_JMP); + lastdesc->ctlreserved = cpu_to_le16(PRD_JMP); jmpprd_addr = cpu_to_le32(lastdesc->addr + (sizeof(struct cs5535audio_dma_desc)*periods)); diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c index b05f7be..e3e8531 100644 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -294,7 +294,7 @@ static int hdmi_update_eld(struct hdmi_eld *e, snd_printd(KERN_INFO "HDMI: out of range MNL %d\n", mnl); goto out_fail; } else - strlcpy(e->monitor_name, buf + ELD_FIXED_BYTES, mnl); + strlcpy(e->monitor_name, buf + ELD_FIXED_BYTES, mnl + 1); for (i = 0; i < e->sad_count; i++) { if (ELD_FIXED_BYTES + mnl + 3 * (i + 1) > size) { diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 694b9daf..7bbc5f2 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -3074,6 +3074,7 @@ static const char * const cxt5066_models[CXT5066_MODELS] = { }; static const struct snd_pci_quirk cxt5066_cfg_tbl[] = { + SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT5066_AUTO), SND_PCI_QUIRK_MASK(0x1025, 0xff00, 0x0400, "Acer", CXT5066_IDEAPAD), SND_PCI_QUIRK(0x1028, 0x02d8, "Dell Vostro", CXT5066_DELL_VOSTRO), SND_PCI_QUIRK(0x1028, 0x02f5, "Dell Vostro 320", CXT5066_IDEAPAD), @@ -4389,6 +4390,8 @@ static const struct hda_codec_preset snd_hda_preset_conexant[] = { .patch = patch_cxt5066 }, { .id = 0x14f15069, .name = "CX20585", .patch = patch_cxt5066 }, + { .id = 0x14f1506c, .name = "CX20588", + .patch = patch_cxt5066 }, { .id = 0x14f1506e, .name = "CX20590", .patch = patch_cxt5066 }, { .id = 0x14f15097, .name = "CX20631", @@ -4417,6 +4420,7 @@ MODULE_ALIAS("snd-hda-codec-id:14f15066"); MODULE_ALIAS("snd-hda-codec-id:14f15067"); MODULE_ALIAS("snd-hda-codec-id:14f15068"); MODULE_ALIAS("snd-hda-codec-id:14f15069"); +MODULE_ALIAS("snd-hda-codec-id:14f1506c"); MODULE_ALIAS("snd-hda-codec-id:14f1506e"); MODULE_ALIAS("snd-hda-codec-id:14f15097"); MODULE_ALIAS("snd-hda-codec-id:14f15098"); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 61a774b..b48fb43 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2715,17 +2715,30 @@ typedef int (*getput_call_t)(struct snd_kcontrol *kcontrol, static int alc_cap_getput_caller(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol, - getput_call_t func) + getput_call_t func, bool check_adc_switch) { struct hda_codec *codec = snd_kcontrol_chip(kcontrol); struct alc_spec *spec = codec->spec; - unsigned int adc_idx = snd_ctl_get_ioffidx(kcontrol, &ucontrol->id); - int err; + int i, err = 0; mutex_lock(&codec->control_mutex); - kcontrol->private_value = HDA_COMPOSE_AMP_VAL(spec->adc_nids[adc_idx], - 3, 0, HDA_INPUT); - err = func(kcontrol, ucontrol); + if (check_adc_switch && spec->dual_adc_switch) { + for (i = 0; i < spec->num_adc_nids; i++) { + kcontrol->private_value = + HDA_COMPOSE_AMP_VAL(spec->adc_nids[i], + 3, 0, HDA_INPUT); + err = func(kcontrol, ucontrol); + if (err < 0) + goto error; + } + } else { + i = snd_ctl_get_ioffidx(kcontrol, &ucontrol->id); + kcontrol->private_value = + HDA_COMPOSE_AMP_VAL(spec->adc_nids[i], + 3, 0, HDA_INPUT); + err = func(kcontrol, ucontrol); + } + error: mutex_unlock(&codec->control_mutex); return err; } @@ -2734,14 +2747,14 @@ static int alc_cap_vol_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { return alc_cap_getput_caller(kcontrol, ucontrol, - snd_hda_mixer_amp_volume_get); + snd_hda_mixer_amp_volume_get, false); } static int alc_cap_vol_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { return alc_cap_getput_caller(kcontrol, ucontrol, - snd_hda_mixer_amp_volume_put); + snd_hda_mixer_amp_volume_put, true); } /* capture mixer elements */ @@ -2751,14 +2764,14 @@ static int alc_cap_sw_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { return alc_cap_getput_caller(kcontrol, ucontrol, - snd_hda_mixer_amp_switch_get); + snd_hda_mixer_amp_switch_get, false); } static int alc_cap_sw_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { return alc_cap_getput_caller(kcontrol, ucontrol, - snd_hda_mixer_amp_switch_put); + snd_hda_mixer_amp_switch_put, true); } #define _DEFINE_CAPMIX(num) \ @@ -4883,7 +4896,6 @@ static const struct snd_pci_quirk alc880_cfg_tbl[] = { SND_PCI_QUIRK(0x1025, 0xe309, "ULI", ALC880_3ST_DIG), SND_PCI_QUIRK(0x1025, 0xe310, "ULI", ALC880_3ST), SND_PCI_QUIRK(0x1039, 0x1234, NULL, ALC880_6ST_DIG), - SND_PCI_QUIRK(0x103c, 0x2a09, "HP", ALC880_5ST), SND_PCI_QUIRK(0x1043, 0x10b3, "ASUS W1V", ALC880_ASUS_W1V), SND_PCI_QUIRK(0x1043, 0x10c2, "ASUS W6A", ALC880_ASUS_DIG), SND_PCI_QUIRK(0x1043, 0x10c3, "ASUS Wxx", ALC880_ASUS_DIG), @@ -12600,6 +12612,7 @@ static const struct hda_verb alc262_toshiba_rx1_unsol_verbs[] = { */ enum { PINFIX_FSC_H270, + PINFIX_HP_Z200, }; static const struct alc_fixup alc262_fixups[] = { @@ -12612,9 +12625,17 @@ static const struct alc_fixup alc262_fixups[] = { { } } }, + [PINFIX_HP_Z200] = { + .type = ALC_FIXUP_PINS, + .v.pins = (const struct alc_pincfg[]) { + { 0x16, 0x99130120 }, /* internal speaker */ + { } + } + }, }; static const struct snd_pci_quirk alc262_fixup_tbl[] = { + SND_PCI_QUIRK(0x103c, 0x170b, "HP Z200", PINFIX_HP_Z200), SND_PCI_QUIRK(0x1734, 0x1147, "FSC Celsius H270", PINFIX_FSC_H270), {} }; @@ -12731,6 +12752,8 @@ static const struct snd_pci_quirk alc262_cfg_tbl[] = { ALC262_HP_BPC), SND_PCI_QUIRK_MASK(0x103c, 0xff00, 0x1500, "HP z series", ALC262_HP_BPC), + SND_PCI_QUIRK(0x103c, 0x170b, "HP Z200", + ALC262_AUTO), SND_PCI_QUIRK_MASK(0x103c, 0xff00, 0x1700, "HP xw series", ALC262_HP_BPC), SND_PCI_QUIRK(0x103c, 0x2800, "HP D7000", ALC262_HP_BPC_D7000_WL), @@ -13872,7 +13895,6 @@ static const struct snd_pci_quirk alc268_cfg_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1205, "ASUS W7J", ALC268_3ST), SND_PCI_QUIRK(0x1170, 0x0040, "ZEPTO", ALC268_ZEPTO), SND_PCI_QUIRK(0x14c0, 0x0025, "COMPAL IFL90/JFL-92", ALC268_TOSHIBA), - SND_PCI_QUIRK(0x152d, 0x0763, "Diverse (CPR2000)", ALC268_ACER), SND_PCI_QUIRK(0x152d, 0x0771, "Quanta IL1", ALC267_QUANTA_IL1), {} }; diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index c952582..f43bb0e 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -745,12 +745,23 @@ static int via_independent_hp_put(struct snd_kcontrol *kcontrol, struct via_spec *spec = codec->spec; hda_nid_t nid = kcontrol->private_value; unsigned int pinsel = ucontrol->value.enumerated.item[0]; + unsigned int parm0, parm1; /* Get Independent Mode index of headphone pin widget */ spec->hp_independent_mode = spec->hp_independent_mode_index == pinsel ? 1 : 0; - if (spec->codec_type == VT1718S) + if (spec->codec_type == VT1718S) { snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CONNECT_SEL, pinsel ? 2 : 0); + /* Set correct mute switch for MW3 */ + parm0 = spec->hp_independent_mode ? + AMP_IN_UNMUTE(0) : AMP_IN_MUTE(0); + parm1 = spec->hp_independent_mode ? + AMP_IN_MUTE(1) : AMP_IN_UNMUTE(1); + snd_hda_codec_write(codec, 0x1b, 0, + AC_VERB_SET_AMP_GAIN_MUTE, parm0); + snd_hda_codec_write(codec, 0x1b, 0, + AC_VERB_SET_AMP_GAIN_MUTE, parm1); + } else snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CONNECT_SEL, pinsel); @@ -4283,9 +4294,6 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = { {0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(2)}, {0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(3)}, {0x21, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(5)}, - - /* Setup default input of Front HP to MW9 */ - {0x28, AC_VERB_SET_CONNECT_SEL, 0x1}, /* PW9 PW10 Output enable */ {0x2d, AC_VERB_SET_PIN_WIDGET_CONTROL, AC_PINCTL_OUT_EN}, {0x2e, AC_VERB_SET_PIN_WIDGET_CONTROL, AC_PINCTL_OUT_EN}, @@ -4294,10 +4302,10 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = { /* Enable Boost Volume backdoor */ {0x1, 0xf88, 0x8}, /* MW0/1/2/3/4: un-mute index 0 (AOWx), mute index 1 (MW9) */ - {0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, + {0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)}, {0x19, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, {0x1a, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, - {0x1b, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, + {0x1b, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(0)}, {0x1c, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, {0x18, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(1)}, {0x19, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_MUTE(1)}, @@ -4307,8 +4315,6 @@ static const struct hda_verb vt1718S_volume_init_verbs[] = { /* set MUX1 = 2 (AOW4), MUX2 = 1 (AOW3) */ {0x34, AC_VERB_SET_CONNECT_SEL, 0x2}, {0x35, AC_VERB_SET_CONNECT_SEL, 0x1}, - /* Unmute MW4's index 0 */ - {0x1c, AC_VERB_SET_AMP_GAIN_MUTE, AMP_IN_UNMUTE(0)}, { } }; @@ -4456,6 +4462,19 @@ static int vt1718S_auto_create_multi_out_ctls(struct via_spec *spec, if (err < 0) return err; } else if (i == AUTO_SEQ_FRONT) { + /* add control to mixer index 0 */ + err = via_add_control(spec, VIA_CTL_WIDGET_VOL, + "Master Front Playback Volume", + HDA_COMPOSE_AMP_VAL(0x21, 3, 5, + HDA_INPUT)); + if (err < 0) + return err; + err = via_add_control(spec, VIA_CTL_WIDGET_MUTE, + "Master Front Playback Switch", + HDA_COMPOSE_AMP_VAL(0x21, 3, 5, + HDA_INPUT)); + if (err < 0) + return err; /* Front */ sprintf(name, "%s Playback Volume", chname[i]); err = via_add_control( diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c index 3f08afc..c8e402f 100644 --- a/sound/pci/rme9652/hdspm.c +++ b/sound/pci/rme9652/hdspm.c @@ -896,11 +896,11 @@ struct hdspm { unsigned char max_channels_in; unsigned char max_channels_out; - char *channel_map_in; - char *channel_map_out; + signed char *channel_map_in; + signed char *channel_map_out; - char *channel_map_in_ss, *channel_map_in_ds, *channel_map_in_qs; - char *channel_map_out_ss, *channel_map_out_ds, *channel_map_out_qs; + signed char *channel_map_in_ss, *channel_map_in_ds, *channel_map_in_qs; + signed char *channel_map_out_ss, *channel_map_out_ds, *channel_map_out_qs; char **port_names_in; char **port_names_out; diff --git a/sound/soc/blackfin/bf5xx-i2s-pcm.c b/sound/soc/blackfin/bf5xx-i2s-pcm.c index b5101ef..f1fd95b 100644 --- a/sound/soc/blackfin/bf5xx-i2s-pcm.c +++ b/sound/soc/blackfin/bf5xx-i2s-pcm.c @@ -138,11 +138,20 @@ static snd_pcm_uframes_t bf5xx_pcm_pointer(struct snd_pcm_substream *substream) pr_debug("%s enter\n", __func__); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { diff = sport_curr_offset_tx(sport); - frames = bytes_to_frames(substream->runtime, diff); } else { diff = sport_curr_offset_rx(sport); - frames = bytes_to_frames(substream->runtime, diff); } + + /* + * TX at least can report one frame beyond the end of the + * buffer if we hit the wraparound case - clamp to within the + * buffer as the ALSA APIs require. + */ + if (diff == snd_pcm_lib_buffer_bytes(substream)) + diff = 0; + + frames = bytes_to_frames(substream->runtime, diff); + return frames; } diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c index 4be0570..65f4604 100644 --- a/sound/soc/codecs/ak4642.c +++ b/sound/soc/codecs/ak4642.c @@ -357,7 +357,7 @@ static int ak4642_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) default: return -EINVAL; } - snd_soc_update_bits(codec, PW_MGMT2, MS, data); + snd_soc_update_bits(codec, PW_MGMT2, MS | MCKO | PMPLL, data); snd_soc_update_bits(codec, MD_CTL1, BCKO_MASK, bcko); /* format type */ diff --git a/sound/soc/codecs/tlv320aic26.c b/sound/soc/codecs/tlv320aic26.c index e2a7608..7859bdc 100644 --- a/sound/soc/codecs/tlv320aic26.c +++ b/sound/soc/codecs/tlv320aic26.c @@ -161,10 +161,18 @@ static int aic26_hw_params(struct snd_pcm_substream *substream, dev_dbg(&aic26->spi->dev, "bad format\n"); return -EINVAL; } - /* Configure PLL */ + /** + * Configure PLL + * fsref = (mclk * PLLM) / 2048 + * where PLLM = J.DDDD (DDDD register ranges from 0 to 9999, decimal) + */ pval = 1; - jval = (fsref == 44100) ? 7 : 8; - dval = (fsref == 44100) ? 5264 : 1920; + /* compute J portion of multiplier */ + jval = fsref / (aic26->mclk / 2048); + /* compute fractional DDDD component of multiplier */ + dval = fsref - (jval * (aic26->mclk / 2048)); + dval = (10000 * dval) / (aic26->mclk / 2048); + dev_dbg(&aic26->spi->dev, "Setting PLLM to %d.%04d\n", jval, dval); qval = 0; reg = 0x8000 | qval << 11 | pval << 8 | jval << 2; aic26_reg_write(codec, AIC26_REG_PLL_PROG1, reg); diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index c3d96fc..789453d 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1114,12 +1114,19 @@ static int aic3x_set_power(struct snd_soc_codec *codec, int power) /* Sync reg_cache with the hardware */ codec->cache_only = 0; - for (i = 0; i < ARRAY_SIZE(aic3x_reg); i++) + for (i = AIC3X_SAMPLE_RATE_SEL_REG; i < ARRAY_SIZE(aic3x_reg); i++) snd_soc_write(codec, i, cache[i]); if (aic3x->model == AIC3X_MODEL_3007) aic3x_init_3007(codec); codec->cache_sync = 0; } else { + /* + * Do soft reset to this codec instance in order to clear + * possible VDD leakage currents in case the supply regulators + * remain on + */ + snd_soc_write(codec, AIC3X_RESET, SOFT_RESET); + codec->cache_sync = 1; aic3x->power = 0; /* HW writes are needless when bias is off */ codec->cache_only = 1; diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c index 2dc964b..76b4361 100644 --- a/sound/soc/codecs/wm8731.c +++ b/sound/soc/codecs/wm8731.c @@ -175,6 +175,7 @@ static const struct snd_kcontrol_new wm8731_input_mux_controls = SOC_DAPM_ENUM("Input Select", wm8731_insel_enum); static const struct snd_soc_dapm_widget wm8731_dapm_widgets[] = { +SND_SOC_DAPM_SUPPLY("ACTIVE",WM8731_ACTIVE, 0, 0, NULL, 0), SND_SOC_DAPM_SUPPLY("OSC", WM8731_PWR, 5, 1, NULL, 0), SND_SOC_DAPM_MIXER("Output Mixer", WM8731_PWR, 4, 1, &wm8731_output_mixer_controls[0], @@ -204,6 +205,8 @@ static int wm8731_check_osc(struct snd_soc_dapm_widget *source, static const struct snd_soc_dapm_route wm8731_intercon[] = { {"DAC", NULL, "OSC", wm8731_check_osc}, {"ADC", NULL, "OSC", wm8731_check_osc}, + {"DAC", NULL, "ACTIVE"}, + {"ADC", NULL, "ACTIVE"}, /* output mixer */ {"Output Mixer", "Line Bypass Switch", "Line Input"}, @@ -315,29 +318,6 @@ static int wm8731_hw_params(struct snd_pcm_substream *substream, return 0; } -static int wm8731_pcm_prepare(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct snd_soc_codec *codec = dai->codec; - - /* set active */ - snd_soc_write(codec, WM8731_ACTIVE, 0x0001); - - return 0; -} - -static void wm8731_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) -{ - struct snd_soc_codec *codec = dai->codec; - - /* deactivate */ - if (!codec->active) { - udelay(50); - snd_soc_write(codec, WM8731_ACTIVE, 0x0); - } -} - static int wm8731_mute(struct snd_soc_dai *dai, int mute) { struct snd_soc_codec *codec = dai->codec; @@ -480,7 +460,6 @@ static int wm8731_set_bias_level(struct snd_soc_codec *codec, snd_soc_write(codec, WM8731_PWR, reg | 0x0040); break; case SND_SOC_BIAS_OFF: - snd_soc_write(codec, WM8731_ACTIVE, 0x0); snd_soc_write(codec, WM8731_PWR, 0xffff); regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies), wm8731->supplies); @@ -496,9 +475,7 @@ static int wm8731_set_bias_level(struct snd_soc_codec *codec, SNDRV_PCM_FMTBIT_S24_LE) static struct snd_soc_dai_ops wm8731_dai_ops = { - .prepare = wm8731_pcm_prepare, .hw_params = wm8731_hw_params, - .shutdown = wm8731_shutdown, .digital_mute = wm8731_mute, .set_sysclk = wm8731_set_dai_sysclk, .set_fmt = wm8731_set_dai_fmt, diff --git a/sound/soc/codecs/wm8991.c b/sound/soc/codecs/wm8991.c index 3c2ee1b..6af23d0 100644 --- a/sound/soc/codecs/wm8991.c +++ b/sound/soc/codecs/wm8991.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/moduleparam.h> -#include <linux/version.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/delay.h> diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index 970a95c..83014a7 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -1190,7 +1190,6 @@ SND_SOC_DAPM_INPUT("DMIC1DAT"), SND_SOC_DAPM_INPUT("DMIC2DAT"), SND_SOC_DAPM_INPUT("Clock"), -SND_SOC_DAPM_MICBIAS("MICBIAS", WM8994_MICBIAS, 2, 0), SND_SOC_DAPM_SUPPLY_S("MICBIAS Supply", 1, SND_SOC_NOPM, 0, 0, micbias_ev, SND_SOC_DAPM_PRE_PMU), @@ -1509,8 +1508,10 @@ static const struct snd_soc_dapm_route wm8994_revd_intercon[] = { { "AIF2DACDAT", NULL, "AIF1DACDAT" }, { "AIF1ADCDAT", NULL, "AIF2ADCDAT" }, { "AIF2ADCDAT", NULL, "AIF1ADCDAT" }, - { "MICBIAS", NULL, "CLK_SYS" }, - { "MICBIAS", NULL, "MICBIAS Supply" }, + { "MICBIAS1", NULL, "CLK_SYS" }, + { "MICBIAS1", NULL, "MICBIAS Supply" }, + { "MICBIAS2", NULL, "CLK_SYS" }, + { "MICBIAS2", NULL, "MICBIAS Supply" }, }; static const struct snd_soc_dapm_route wm8994_intercon[] = { @@ -1713,6 +1714,8 @@ static int _wm8994_set_fll(struct snd_soc_codec *codec, int id, int src, snd_soc_update_bits(codec, WM8994_FLL1_CONTROL_1 + reg_offset, WM8994_FLL1_ENA | WM8994_FLL1_FRAC, reg); + + msleep(5); } wm8994->fll[id].in = freq_in; @@ -2761,7 +2764,7 @@ static void wm8958_default_micdet(u16 status, void *data) report = SND_JACK_MICROPHONE; /* Everything else is buttons; just assign slots */ - if (status & 0x1c0) + if (status & 0x1c) report |= SND_JACK_BTN_0; done: diff --git a/sound/soc/imx/Kconfig b/sound/soc/imx/Kconfig index d8f130d..bb699bb 100644 --- a/sound/soc/imx/Kconfig +++ b/sound/soc/imx/Kconfig @@ -11,9 +11,6 @@ menuconfig SND_IMX_SOC if SND_IMX_SOC -config SND_MXC_SOC_SSI - tristate - config SND_MXC_SOC_FIQ tristate @@ -24,7 +21,6 @@ config SND_MXC_SOC_WM1133_EV1 tristate "Audio on the the i.MX31ADS with WM1133-EV1 fitted" depends on MACH_MX31ADS_WM1133_EV1 && EXPERIMENTAL select SND_SOC_WM8350 - select SND_MXC_SOC_SSI select SND_MXC_SOC_FIQ help Enable support for audio on the i.MX31ADS with the WM1133-EV1 @@ -34,7 +30,6 @@ config SND_SOC_MX27VIS_AIC32X4 tristate "SoC audio support for Visstrim M10 boards" depends on MACH_IMX27_VISSTRIM_M10 select SND_SOC_TVL320AIC32X4 - select SND_MXC_SOC_SSI select SND_MXC_SOC_MX2 help Say Y if you want to add support for SoC audio on Visstrim SM10 @@ -44,7 +39,6 @@ config SND_SOC_PHYCORE_AC97 tristate "SoC Audio support for Phytec phyCORE (and phyCARD) boards" depends on MACH_PCM043 || MACH_PCA100 select SND_SOC_WM9712 - select SND_MXC_SOC_SSI select SND_MXC_SOC_FIQ help Say Y if you want to add support for SoC audio on Phytec phyCORE @@ -57,7 +51,6 @@ config SND_SOC_EUKREA_TLV320 || MACH_EUKREA_MBIMXSD35_BASEBOARD \ || MACH_EUKREA_MBIMXSD51_BASEBOARD select SND_SOC_TLV320AIC23 - select SND_MXC_SOC_SSI select SND_MXC_SOC_FIQ help Enable I2S based access to the TLV320AIC23B codec attached diff --git a/sound/soc/imx/imx-pcm-dma-mx2.c b/sound/soc/imx/imx-pcm-dma-mx2.c index aab7765..4173b3d 100644 --- a/sound/soc/imx/imx-pcm-dma-mx2.c +++ b/sound/soc/imx/imx-pcm-dma-mx2.c @@ -337,3 +337,5 @@ static void __exit snd_imx_pcm_exit(void) platform_driver_unregister(&imx_pcm_driver); } module_exit(snd_imx_pcm_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:imx-pcm-audio"); diff --git a/sound/soc/imx/imx-ssi.c b/sound/soc/imx/imx-ssi.c index 5b13fec..61fceb0 100644 --- a/sound/soc/imx/imx-ssi.c +++ b/sound/soc/imx/imx-ssi.c @@ -774,4 +774,4 @@ module_exit(imx_ssi_exit); MODULE_AUTHOR("Sascha Hauer, <s.hauer@pengutronix.de>"); MODULE_DESCRIPTION("i.MX I2S/ac97 SoC Interface"); MODULE_LICENSE("GPL"); - +MODULE_ALIAS("platform:imx-ssi"); diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c index 2ce0b2d..fab20a5 100644 --- a/sound/soc/pxa/pxa2xx-pcm.c +++ b/sound/soc/pxa/pxa2xx-pcm.c @@ -95,14 +95,14 @@ static int pxa2xx_soc_pcm_new(struct snd_card *card, struct snd_soc_dai *dai, if (!card->dev->coherent_dma_mask) card->dev->coherent_dma_mask = DMA_BIT_MASK(32); - if (dai->driver->playback.channels_min) { + if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) { ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, SNDRV_PCM_STREAM_PLAYBACK); if (ret) goto out; } - if (dai->driver->capture.channels_min) { + if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) { ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, SNDRV_PCM_STREAM_CAPTURE); if (ret) diff --git a/sound/soc/sh/fsi-ak4642.c b/sound/soc/sh/fsi-ak4642.c index d6f4703..770a71a 100644 --- a/sound/soc/sh/fsi-ak4642.c +++ b/sound/soc/sh/fsi-ak4642.c @@ -97,7 +97,7 @@ static int fsi_ak4642_remove(struct platform_device *pdev) static struct fsi_ak4642_data fsi_a_ak4642 = { .name = "AK4642", - .card = "FSIA (AK4642)", + .card = "FSIA-AK4642", .cpu_dai = "fsia-dai", .codec = "ak4642-codec.0-0012", .platform = "sh_fsi.0", @@ -106,7 +106,7 @@ static struct fsi_ak4642_data fsi_a_ak4642 = { static struct fsi_ak4642_data fsi_b_ak4642 = { .name = "AK4642", - .card = "FSIB (AK4642)", + .card = "FSIB-AK4642", .cpu_dai = "fsib-dai", .codec = "ak4642-codec.0-0012", .platform = "sh_fsi.0", @@ -115,7 +115,7 @@ static struct fsi_ak4642_data fsi_b_ak4642 = { static struct fsi_ak4642_data fsi_a_ak4643 = { .name = "AK4643", - .card = "FSIA (AK4643)", + .card = "FSIA-AK4643", .cpu_dai = "fsia-dai", .codec = "ak4642-codec.0-0013", .platform = "sh_fsi.0", @@ -124,7 +124,7 @@ static struct fsi_ak4642_data fsi_a_ak4643 = { static struct fsi_ak4642_data fsi_b_ak4643 = { .name = "AK4643", - .card = "FSIB (AK4643)", + .card = "FSIB-AK4643", .cpu_dai = "fsib-dai", .codec = "ak4642-codec.0-0013", .platform = "sh_fsi.0", @@ -133,7 +133,7 @@ static struct fsi_ak4642_data fsi_b_ak4643 = { static struct fsi_ak4642_data fsi2_a_ak4642 = { .name = "AK4642", - .card = "FSI2A (AK4642)", + .card = "FSI2A-AK4642", .cpu_dai = "fsia-dai", .codec = "ak4642-codec.0-0012", .platform = "sh_fsi2", @@ -142,7 +142,7 @@ static struct fsi_ak4642_data fsi2_a_ak4642 = { static struct fsi_ak4642_data fsi2_b_ak4642 = { .name = "AK4642", - .card = "FSI2B (AK4642)", + .card = "FSI2B-AK4642", .cpu_dai = "fsib-dai", .codec = "ak4642-codec.0-0012", .platform = "sh_fsi2", @@ -151,7 +151,7 @@ static struct fsi_ak4642_data fsi2_b_ak4642 = { static struct fsi_ak4642_data fsi2_a_ak4643 = { .name = "AK4643", - .card = "FSI2A (AK4643)", + .card = "FSI2A-AK4643", .cpu_dai = "fsia-dai", .codec = "ak4642-codec.0-0013", .platform = "sh_fsi2", @@ -160,7 +160,7 @@ static struct fsi_ak4642_data fsi2_a_ak4643 = { static struct fsi_ak4642_data fsi2_b_ak4643 = { .name = "AK4643", - .card = "FSI2B (AK4643)", + .card = "FSI2B-AK4643", .cpu_dai = "fsib-dai", .codec = "ak4642-codec.0-0013", .platform = "sh_fsi2", diff --git a/sound/soc/sh/fsi-da7210.c b/sound/soc/sh/fsi-da7210.c index dbafd7a..59553fd 100644 --- a/sound/soc/sh/fsi-da7210.c +++ b/sound/soc/sh/fsi-da7210.c @@ -42,7 +42,7 @@ static struct snd_soc_dai_link fsi_da7210_dai = { }; static struct snd_soc_card fsi_soc_card = { - .name = "FSI (DA7210)", + .name = "FSI-DA7210", .dai_link = &fsi_da7210_dai, .num_links = 1, }; diff --git a/sound/soc/sh/fsi-hdmi.c b/sound/soc/sh/fsi-hdmi.c index 9719985..d3d9fd8 100644 --- a/sound/soc/sh/fsi-hdmi.c +++ b/sound/soc/sh/fsi-hdmi.c @@ -83,13 +83,13 @@ static int fsi_hdmi_remove(struct platform_device *pdev) static struct fsi_hdmi_data fsi2_a_hdmi = { .cpu_dai = "fsia-dai", - .card = "FSI2A (SH MOBILE HDMI)", + .card = "FSI2A-HDMI", .id = FSI_PORT_A, }; static struct fsi_hdmi_data fsi2_b_hdmi = { .cpu_dai = "fsib-dai", - .card = "FSI2B (SH MOBILE HDMI)", + .card = "FSI2B-HDMI", .id = FSI_PORT_B, }; diff --git a/sound/soc/soc-cache.c b/sound/soc/soc-cache.c index c005ceb..039b953 100644 --- a/sound/soc/soc-cache.c +++ b/sound/soc/soc-cache.c @@ -409,9 +409,6 @@ int snd_soc_codec_set_cache_io(struct snd_soc_codec *codec, codec->bulk_write_raw = snd_soc_hw_bulk_write_raw; switch (control) { - case SND_SOC_CUSTOM: - break; - case SND_SOC_I2C: #if defined(CONFIG_I2C) || (defined(CONFIG_I2C_MODULE) && defined(MODULE)) codec->hw_write = (hw_write_t)i2c_master_send; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index d75043e..b194be0 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1929,8 +1929,9 @@ static void snd_soc_instantiate_card(struct snd_soc_card *card) "%s", card->name); snprintf(card->snd_card->longname, sizeof(card->snd_card->longname), "%s", card->long_name ? card->long_name : card->name); - snprintf(card->snd_card->driver, sizeof(card->snd_card->driver), - "%s", card->driver_name ? card->driver_name : card->name); + if (card->driver_name) + strlcpy(card->snd_card->driver, card->driver_name, + sizeof(card->snd_card->driver)); if (card->late_probe) { ret = card->late_probe(card); diff --git a/sound/soc/tegra/tegra_i2s.c b/sound/soc/tegra/tegra_i2s.c index 6b817e2..95f03c1 100644 --- a/sound/soc/tegra/tegra_i2s.c +++ b/sound/soc/tegra/tegra_i2s.c @@ -222,12 +222,18 @@ static int tegra_i2s_hw_params(struct snd_pcm_substream *substream, if (i2sclock % (2 * srate)) reg |= TEGRA_I2S_TIMING_NON_SYM_ENABLE; + if (!i2s->clk_refs) + clk_enable(i2s->clk_i2s); + tegra_i2s_write(i2s, TEGRA_I2S_TIMING, reg); tegra_i2s_write(i2s, TEGRA_I2S_FIFO_SCR, TEGRA_I2S_FIFO_SCR_FIFO2_ATN_LVL_FOUR_SLOTS | TEGRA_I2S_FIFO_SCR_FIFO1_ATN_LVL_FOUR_SLOTS); + if (!i2s->clk_refs) + clk_disable(i2s->clk_i2s); + return 0; } diff --git a/sound/spi/at73c213.c b/sound/spi/at73c213.c index 337a002..4dd051b 100644 --- a/sound/spi/at73c213.c +++ b/sound/spi/at73c213.c @@ -1124,6 +1124,6 @@ static void __exit at73c213_exit(void) } module_exit(at73c213_exit); -MODULE_AUTHOR("Hans-Christian Egtvedt <hcegtvedt@atmel.com>"); +MODULE_AUTHOR("Hans-Christian Egtvedt <egtvedt@samfundet.no>"); MODULE_DESCRIPTION("Sound driver for AT73C213 with Atmel SSC"); MODULE_LICENSE("GPL"); |