diff options
548 files changed, 8156 insertions, 4572 deletions
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index cbbd3e0..5f3beda 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -94,28 +94,37 @@ What: /sys/block/<disk>/queue/physical_block_size Date: May 2009 Contact: Martin K. Petersen <martin.petersen@oracle.com> Description: - This is the smallest unit the storage device can write - without resorting to read-modify-write operation. It is - usually the same as the logical block size but may be - bigger. One example is SATA drives with 4KB sectors - that expose a 512-byte logical block size to the - operating system. + This is the smallest unit a physical storage device can + write atomically. It is usually the same as the logical + block size but may be bigger. One example is SATA + drives with 4KB sectors that expose a 512-byte logical + block size to the operating system. For stacked block + devices the physical_block_size variable contains the + maximum physical_block_size of the component devices. What: /sys/block/<disk>/queue/minimum_io_size Date: April 2009 Contact: Martin K. Petersen <martin.petersen@oracle.com> Description: - Storage devices may report a preferred minimum I/O size, - which is the smallest request the device can perform - without incurring a read-modify-write penalty. For disk - drives this is often the physical block size. For RAID - arrays it is often the stripe chunk size. + Storage devices may report a granularity or preferred + minimum I/O size which is the smallest request the + device can perform without incurring a performance + penalty. For disk drives this is often the physical + block size. For RAID arrays it is often the stripe + chunk size. A properly aligned multiple of + minimum_io_size is the preferred request size for + workloads where a high number of I/O operations is + desired. What: /sys/block/<disk>/queue/optimal_io_size Date: April 2009 Contact: Martin K. Petersen <martin.petersen@oracle.com> Description: Storage devices may report an optimal I/O size, which is - the device's preferred unit of receiving I/O. This is - rarely reported for disk drives. For RAID devices it is - usually the stripe width or the internal block size. + the device's preferred unit for sustained I/O. This is + rarely reported for disk drives. For RAID arrays it is + usually the stripe width or the internal track size. A + properly aligned multiple of optimal_io_size is the + preferred request size for workloads where sustained + throughput is desired. If no optimal I/O size is + reported this file contains 0. diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl index a50d6cd..992e67e 100644 --- a/Documentation/DocBook/kernel-hacking.tmpl +++ b/Documentation/DocBook/kernel-hacking.tmpl @@ -449,8 +449,8 @@ printk(KERN_INFO "i = %u\n", i); </para> <programlisting> -__u32 ipaddress; -printk(KERN_INFO "my ip: %d.%d.%d.%d\n", NIPQUAD(ipaddress)); +__be32 ipaddress; +printk(KERN_INFO "my ip: %pI4\n", &ipaddress); </programlisting> <para> diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt index 43cb100..9d58c7c5 100644 --- a/Documentation/arm/memory.txt +++ b/Documentation/arm/memory.txt @@ -21,6 +21,8 @@ ffff8000 ffffffff copy_user_page / clear_user_page use. For SA11xx and Xscale, this is used to setup a minicache mapping. +ffff4000 ffffffff cache aliasing on ARMv6 and later CPUs. + ffff1000 ffff7fff Reserved. Platforms must not use this address range. diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 7bb0d93..dbea4f9 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -139,6 +139,7 @@ Code Seq# Include File Comments 'm' all linux/synclink.h conflict! 'm' 00-1F net/irda/irmod.h conflict! 'n' 00-7F linux/ncp_fs.h +'n' 80-8F linux/nilfs2_fs.h NILFS2 'n' E0-FF video/matrox.h matroxfb 'o' 00-1F fs/ocfs2/ocfs2_fs.h OCFS2 'o' 00-03 include/mtd/ubi-user.h conflict! (OCFS2 and UBI overlaps) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index dd1a6d4..7936b80 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1115,6 +1115,10 @@ and is between 256 and 4096 characters. It is defined in the file libata.dma=4 Compact Flash DMA only Combinations also work, so libata.dma=3 enables DMA for disks and CDROMs, but not CFs. + + libata.ignore_hpa= [LIBATA] Ignore HPA limit + libata.ignore_hpa=0 keep BIOS limits (default) + libata.ignore_hpa=1 ignore limits, using full disk libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume when set. diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt index f2296ec..e2ddcde 100644 --- a/Documentation/laptops/thinkpad-acpi.txt +++ b/Documentation/laptops/thinkpad-acpi.txt @@ -36,8 +36,6 @@ detailed description): - Bluetooth enable and disable - video output switching, expansion control - ThinkLight on and off - - limited docking and undocking - - UltraBay eject - CMOS/UCMS control - LED control - ACPI sounds @@ -729,131 +727,6 @@ cannot be read or if it is unknown, thinkpad-acpi will report it as "off". It is impossible to know if the status returned through sysfs is valid. -Docking / undocking -- /proc/acpi/ibm/dock ------------------------------------------- - -Docking and undocking (e.g. with the X4 UltraBase) requires some -actions to be taken by the operating system to safely make or break -the electrical connections with the dock. - -The docking feature of this driver generates the following ACPI events: - - ibm/dock GDCK 00000003 00000001 -- eject request - ibm/dock GDCK 00000003 00000002 -- undocked - ibm/dock GDCK 00000000 00000003 -- docked - -NOTE: These events will only be generated if the laptop was docked -when originally booted. This is due to the current lack of support for -hot plugging of devices in the Linux ACPI framework. If the laptop was -booted while not in the dock, the following message is shown in the -logs: - - Mar 17 01:42:34 aero kernel: thinkpad_acpi: dock device not present - -In this case, no dock-related events are generated but the dock and -undock commands described below still work. They can be executed -manually or triggered by Fn key combinations (see the example acpid -configuration files included in the driver tarball package available -on the web site). - -When the eject request button on the dock is pressed, the first event -above is generated. The handler for this event should issue the -following command: - - echo undock > /proc/acpi/ibm/dock - -After the LED on the dock goes off, it is safe to eject the laptop. -Note: if you pressed this key by mistake, go ahead and eject the -laptop, then dock it back in. Otherwise, the dock may not function as -expected. - -When the laptop is docked, the third event above is generated. The -handler for this event should issue the following command to fully -enable the dock: - - echo dock > /proc/acpi/ibm/dock - -The contents of the /proc/acpi/ibm/dock file shows the current status -of the dock, as provided by the ACPI framework. - -The docking support in this driver does not take care of enabling or -disabling any other devices you may have attached to the dock. For -example, a CD drive plugged into the UltraBase needs to be disabled or -enabled separately. See the provided example acpid configuration files -for how this can be accomplished. - -There is no support yet for PCI devices that may be attached to a -docking station, e.g. in the ThinkPad Dock II. The driver currently -does not recognize, enable or disable such devices. This means that -the only docking stations currently supported are the X-series -UltraBase docks and "dumb" port replicators like the Mini Dock (the -latter don't need any ACPI support, actually). - - -UltraBay eject -- /proc/acpi/ibm/bay ------------------------------------- - -Inserting or ejecting an UltraBay device requires some actions to be -taken by the operating system to safely make or break the electrical -connections with the device. - -This feature generates the following ACPI events: - - ibm/bay MSTR 00000003 00000000 -- eject request - ibm/bay MSTR 00000001 00000000 -- eject lever inserted - -NOTE: These events will only be generated if the UltraBay was present -when the laptop was originally booted (on the X series, the UltraBay -is in the dock, so it may not be present if the laptop was undocked). -This is due to the current lack of support for hot plugging of devices -in the Linux ACPI framework. If the laptop was booted without the -UltraBay, the following message is shown in the logs: - - Mar 17 01:42:34 aero kernel: thinkpad_acpi: bay device not present - -In this case, no bay-related events are generated but the eject -command described below still works. It can be executed manually or -triggered by a hot key combination. - -Sliding the eject lever generates the first event shown above. The -handler for this event should take whatever actions are necessary to -shut down the device in the UltraBay (e.g. call idectl), then issue -the following command: - - echo eject > /proc/acpi/ibm/bay - -After the LED on the UltraBay goes off, it is safe to pull out the -device. - -When the eject lever is inserted, the second event above is -generated. The handler for this event should take whatever actions are -necessary to enable the UltraBay device (e.g. call idectl). - -The contents of the /proc/acpi/ibm/bay file shows the current status -of the UltraBay, as provided by the ACPI framework. - -EXPERIMENTAL warm eject support on the 600e/x, A22p and A3x (To use -this feature, you need to supply the experimental=1 parameter when -loading the module): - -These models do not have a button near the UltraBay device to request -a hot eject but rather require the laptop to be put to sleep -(suspend-to-ram) before the bay device is ejected or inserted). -The sequence of steps to eject the device is as follows: - - echo eject > /proc/acpi/ibm/bay - put the ThinkPad to sleep - remove the drive - resume from sleep - cat /proc/acpi/ibm/bay should show that the drive was removed - -On the A3x, both the UltraBay 2000 and UltraBay Plus devices are -supported. Use "eject2" instead of "eject" for the second bay. - -Note: the UltraBay eject support on the 600e/x, A22p and A3x is -EXPERIMENTAL and may not work as expected. USE WITH CAUTION! - - CMOS/UCMS control ----------------- diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt index e20d913..abf768c 100644 --- a/Documentation/lockdep-design.txt +++ b/Documentation/lockdep-design.txt @@ -30,9 +30,9 @@ State The validator tracks lock-class usage history into 4n + 1 separate state bits: - 'ever held in STATE context' -- 'ever head as readlock in STATE context' -- 'ever head with STATE enabled' -- 'ever head as readlock with STATE enabled' +- 'ever held as readlock in STATE context' +- 'ever held with STATE enabled' +- 'ever held as readlock with STATE enabled' Where STATE can be either one of (kernel/lockdep_states.h) - hardirq diff --git a/MAINTAINERS b/MAINTAINERS index d6befb2..b1114cf 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4995,7 +4995,9 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial.git S: Maintained TTY LAYER -S: Orphan +M: Greg Kroah-Hartman <gregkh@suse.de> +S: Maintained +T: quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/ F: drivers/char/tty_* F: drivers/serial/serial_core.c F: include/linux/serial_core.h @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 31 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Man-Eating Seals of Antiquity # *DOCUMENTATION* diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c index 9e6e512..17153b5 100644 --- a/arch/arm/boot/compressed/misc.c +++ b/arch/arm/boot/compressed/misc.c @@ -29,7 +29,6 @@ unsigned int __machine_arch_type; static void putstr(const char *ptr); -#include <linux/compiler.h> #include <mach/uncompress.h> #ifdef CONFIG_DEBUG_ICEDCC diff --git a/arch/arm/common/clkdev.c b/arch/arm/common/clkdev.c index f37afd9..aae5bc0 100644 --- a/arch/arm/common/clkdev.c +++ b/arch/arm/common/clkdev.c @@ -17,6 +17,7 @@ #include <linux/err.h> #include <linux/string.h> #include <linux/mutex.h> +#include <linux/clk.h> #include <asm/clkdev.h> #include <mach/clkdev.h> diff --git a/arch/arm/configs/mx27_defconfig b/arch/arm/configs/mx27_defconfig index 083516c..75263a8 100644 --- a/arch/arm/configs/mx27_defconfig +++ b/arch/arm/configs/mx27_defconfig @@ -1,15 +1,15 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.30-rc1 -# Wed Apr 8 10:18:06 2009 +# Linux kernel version: 2.6.31-rc4 +# Fri Jul 24 16:08:06 2009 # CONFIG_ARM=y +CONFIG_HAVE_PWM=y CONFIG_SYS_SUPPORTS_APM_EMULATION=y CONFIG_GENERIC_GPIO=y CONFIG_GENERIC_TIME=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_MMU=y -# CONFIG_NO_IOPORT is not set CONFIG_GENERIC_HARDIRQS=y CONFIG_STACKTRACE_SUPPORT=y CONFIG_HAVE_LATENCYTOP_SUPPORT=y @@ -18,14 +18,13 @@ CONFIG_TRACE_IRQFLAGS_SUPPORT=y CONFIG_HARDIRQS_SW_RESEND=y CONFIG_GENERIC_IRQ_PROBE=y CONFIG_RWSEM_GENERIC_SPINLOCK=y -# CONFIG_ARCH_HAS_ILOG2_U32 is not set -# CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_ARCH_MTD_XIP=y CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y CONFIG_VECTORS_BASE=0xffff0000 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +CONFIG_CONSTRUCTORS=y # # General setup @@ -85,7 +84,12 @@ CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_AIO=y + +# +# Performance Counters +# CONFIG_VM_EVENT_COUNTERS=y +# CONFIG_STRIP_ASM_SYMS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SLAB=y # CONFIG_SLUB is not set @@ -99,6 +103,12 @@ CONFIG_KPROBES=y CONFIG_KRETPROBES=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y +CONFIG_HAVE_CLK=y + +# +# GCOV-based kernel profiling +# +# CONFIG_GCOV_KERNEL is not set # CONFIG_SLOW_WORK is not set CONFIG_HAVE_GENERIC_DMA_COHERENT=y CONFIG_SLABINFO=y @@ -111,7 +121,7 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_BLOCK=y -# CONFIG_LBD is not set +CONFIG_LBDAF=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_BLK_DEV_INTEGRITY is not set @@ -138,13 +148,14 @@ CONFIG_FREEZER=y # CONFIG_ARCH_VERSATILE is not set # CONFIG_ARCH_AT91 is not set # CONFIG_ARCH_CLPS711X is not set +# CONFIG_ARCH_GEMINI is not set # CONFIG_ARCH_EBSA110 is not set # CONFIG_ARCH_EP93XX is not set -# CONFIG_ARCH_GEMINI is not set # CONFIG_ARCH_FOOTBRIDGE is not set +CONFIG_ARCH_MXC=y +# CONFIG_ARCH_STMP3XXX is not set # CONFIG_ARCH_NETX is not set # CONFIG_ARCH_H720X is not set -# CONFIG_ARCH_IMX is not set # CONFIG_ARCH_IOP13XX is not set # CONFIG_ARCH_IOP32X is not set # CONFIG_ARCH_IOP33X is not set @@ -153,25 +164,25 @@ CONFIG_FREEZER=y # CONFIG_ARCH_IXP4XX is not set # CONFIG_ARCH_L7200 is not set # CONFIG_ARCH_KIRKWOOD is not set -# CONFIG_ARCH_KS8695 is not set -# CONFIG_ARCH_NS9XXX is not set # CONFIG_ARCH_LOKI is not set # CONFIG_ARCH_MV78XX0 is not set -CONFIG_ARCH_MXC=y # CONFIG_ARCH_ORION5X is not set +# CONFIG_ARCH_MMP is not set +# CONFIG_ARCH_KS8695 is not set +# CONFIG_ARCH_NS9XXX is not set +# CONFIG_ARCH_W90X900 is not set # CONFIG_ARCH_PNX4008 is not set # CONFIG_ARCH_PXA is not set -# CONFIG_ARCH_MMP is not set +# CONFIG_ARCH_MSM is not set # CONFIG_ARCH_RPC is not set # CONFIG_ARCH_SA1100 is not set # CONFIG_ARCH_S3C2410 is not set # CONFIG_ARCH_S3C64XX is not set # CONFIG_ARCH_SHARK is not set # CONFIG_ARCH_LH7A40X is not set +# CONFIG_ARCH_U300 is not set # CONFIG_ARCH_DAVINCI is not set # CONFIG_ARCH_OMAP is not set -# CONFIG_ARCH_MSM is not set -# CONFIG_ARCH_W90X900 is not set # # Freescale MXC Implementations @@ -188,6 +199,8 @@ CONFIG_MACH_MX27=y CONFIG_MACH_MX27ADS=y CONFIG_MACH_PCM038=y CONFIG_MACH_PCM970_BASEBOARD=y +CONFIG_MACH_MX27_3DS=y +CONFIG_MACH_MX27LITE=y CONFIG_MXC_IRQ_PRIOR=y CONFIG_MXC_PWM=y @@ -213,7 +226,6 @@ CONFIG_ARM_THUMB=y # CONFIG_CPU_DCACHE_DISABLE is not set # CONFIG_CPU_DCACHE_WRITETHROUGH is not set # CONFIG_CPU_CACHE_ROUND_ROBIN is not set -# CONFIG_OUTER_CACHE is not set CONFIG_COMMON_CLKDEV=y # @@ -238,7 +250,6 @@ CONFIG_PREEMPT=y CONFIG_HZ=100 CONFIG_AEABI=y CONFIG_OABI_COMPAT=y -CONFIG_ARCH_FLATMEM_HAS_HOLES=y # CONFIG_ARCH_SPARSEMEM_DEFAULT is not set # CONFIG_ARCH_SELECT_MEMORY_MODEL is not set # CONFIG_HIGHMEM is not set @@ -253,10 +264,11 @@ CONFIG_SPLIT_PTLOCK_CPUS=4096 # CONFIG_PHYS_ADDR_T_64BIT is not set CONFIG_ZONE_DMA_FLAG=0 CONFIG_VIRT_TO_BUS=y -CONFIG_UNEVICTABLE_LRU=y CONFIG_HAVE_MLOCK=y CONFIG_HAVE_MLOCKED_PAGE_BIT=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 CONFIG_ALIGNMENT_TRAP=y +# CONFIG_UACCESS_WITH_MEMCPY is not set # # Boot options @@ -361,6 +373,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set # CONFIG_PHONET is not set +# CONFIG_IEEE802154 is not set # CONFIG_NET_SCHED is not set # CONFIG_DCB is not set @@ -474,7 +487,16 @@ CONFIG_MTD_PHYSMAP=y # CONFIG_MTD_DOC2000 is not set # CONFIG_MTD_DOC2001 is not set # CONFIG_MTD_DOC2001PLUS is not set -# CONFIG_MTD_NAND is not set +CONFIG_MTD_NAND=y +# CONFIG_MTD_NAND_VERIFY_WRITE is not set +# CONFIG_MTD_NAND_ECC_SMC is not set +# CONFIG_MTD_NAND_MUSEUM_IDS is not set +# CONFIG_MTD_NAND_GPIO is not set +CONFIG_MTD_NAND_IDS=y +# CONFIG_MTD_NAND_DISKONCHIP is not set +# CONFIG_MTD_NAND_NANDSIM is not set +# CONFIG_MTD_NAND_PLATFORM is not set +CONFIG_MTD_NAND_MXC=y # CONFIG_MTD_ONENAND is not set # @@ -485,7 +507,15 @@ CONFIG_MTD_PHYSMAP=y # # UBI - Unsorted block images # -# CONFIG_MTD_UBI is not set +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_WL_THRESHOLD=4096 +CONFIG_MTD_UBI_BEB_RESERVE=1 +# CONFIG_MTD_UBI_GLUEBI is not set + +# +# UBI debugging options +# +# CONFIG_MTD_UBI_DEBUG is not set # CONFIG_PARPORT is not set CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_COW_COMMON is not set @@ -494,7 +524,21 @@ CONFIG_BLK_DEV=y # CONFIG_BLK_DEV_RAM is not set # CONFIG_CDROM_PKTCDVD is not set # CONFIG_ATA_OVER_ETH is not set -# CONFIG_MISC_DEVICES is not set +# CONFIG_MG_DISK is not set +CONFIG_MISC_DEVICES=y +# CONFIG_ICS932S401 is not set +# CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_ISL29003 is not set +# CONFIG_C2PORT is not set + +# +# EEPROM support +# +CONFIG_EEPROM_AT24=y +# CONFIG_EEPROM_AT25 is not set +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_MAX6875 is not set +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -508,7 +552,6 @@ CONFIG_HAVE_IDE=y # CONFIG_ATA is not set # CONFIG_MD is not set CONFIG_NETDEVICES=y -CONFIG_COMPAT_NET_DEV_OPS=y # CONFIG_DUMMY is not set # CONFIG_BONDING is not set # CONFIG_MACVLAN is not set @@ -534,6 +577,8 @@ CONFIG_NET_ETHERNET=y # CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set # CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set # CONFIG_B44 is not set +# CONFIG_KS8842 is not set +# CONFIG_KS8851 is not set CONFIG_FEC=y # CONFIG_FEC2 is not set # CONFIG_NETDEV_1000 is not set @@ -580,6 +625,11 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_TABLET is not set CONFIG_INPUT_TOUCHSCREEN=y # CONFIG_TOUCHSCREEN_ADS7846 is not set +# CONFIG_TOUCHSCREEN_AD7877 is not set +# CONFIG_TOUCHSCREEN_AD7879_I2C is not set +# CONFIG_TOUCHSCREEN_AD7879_SPI is not set +# CONFIG_TOUCHSCREEN_AD7879 is not set +# CONFIG_TOUCHSCREEN_EETI is not set # CONFIG_TOUCHSCREEN_FUJITSU is not set # CONFIG_TOUCHSCREEN_GUNZE is not set # CONFIG_TOUCHSCREEN_ELO is not set @@ -592,6 +642,7 @@ CONFIG_INPUT_TOUCHSCREEN=y # CONFIG_TOUCHSCREEN_TOUCHWIN is not set # CONFIG_TOUCHSCREEN_TOUCHIT213 is not set # CONFIG_TOUCHSCREEN_TSC2007 is not set +# CONFIG_TOUCHSCREEN_W90X900 is not set # CONFIG_INPUT_MISC is not set # @@ -644,6 +695,7 @@ CONFIG_I2C_HELPER_AUTO=y # # I2C system bus drivers (mostly embedded / system-on-chip) # +# CONFIG_I2C_DESIGNWARE is not set # CONFIG_I2C_GPIO is not set CONFIG_I2C_IMX=y # CONFIG_I2C_OCORES is not set @@ -668,7 +720,6 @@ CONFIG_I2C_IMX=y # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set -# CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set # CONFIG_I2C_DEBUG_ALGO is not set @@ -719,6 +770,7 @@ CONFIG_W1=y # # CONFIG_W1_MASTER_DS2482 is not set CONFIG_W1_MASTER_MXC=y +# CONFIG_W1_MASTER_DS1WM is not set # CONFIG_W1_MASTER_GPIO is not set # @@ -753,54 +805,16 @@ CONFIG_SSB_POSSIBLE=y # CONFIG_TPS65010 is not set # CONFIG_TWL4030_CORE is not set # CONFIG_MFD_TMIO is not set +# CONFIG_MFD_T7L66XB is not set +# CONFIG_MFD_TC6387XB is not set # CONFIG_MFD_TC6393XB is not set # CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set # CONFIG_MFD_PCF50633 is not set - -# -# Multimedia devices -# - -# -# Multimedia core support -# -CONFIG_VIDEO_DEV=y -CONFIG_VIDEO_V4L2_COMMON=y -CONFIG_VIDEO_ALLOW_V4L1=y -CONFIG_VIDEO_V4L1_COMPAT=y -# CONFIG_DVB_CORE is not set -CONFIG_VIDEO_MEDIA=y - -# -# Multimedia drivers -# -# CONFIG_MEDIA_ATTACH is not set -CONFIG_MEDIA_TUNER=y -# CONFIG_MEDIA_TUNER_CUSTOMISE is not set -CONFIG_MEDIA_TUNER_SIMPLE=y -CONFIG_MEDIA_TUNER_TDA8290=y -CONFIG_MEDIA_TUNER_TDA9887=y -CONFIG_MEDIA_TUNER_TEA5761=y -CONFIG_MEDIA_TUNER_TEA5767=y -CONFIG_MEDIA_TUNER_MT20XX=y -CONFIG_MEDIA_TUNER_XC2028=y -CONFIG_MEDIA_TUNER_XC5000=y -CONFIG_MEDIA_TUNER_MC44S803=y -CONFIG_VIDEO_V4L2=y -CONFIG_VIDEO_V4L1=y -CONFIG_VIDEO_CAPTURE_DRIVERS=y -# CONFIG_VIDEO_ADV_DEBUG is not set -# CONFIG_VIDEO_FIXED_MINOR_RANGES is not set -CONFIG_VIDEO_HELPER_CHIPS_AUTO=y -# CONFIG_VIDEO_VIVI is not set -# CONFIG_VIDEO_CPIA is not set -# CONFIG_VIDEO_SAA5246A is not set -# CONFIG_VIDEO_SAA5249 is not set -# CONFIG_SOC_CAMERA is not set -# CONFIG_RADIO_ADAPTERS is not set -# CONFIG_DAB is not set +# CONFIG_AB3100_CORE is not set +# CONFIG_EZX_PCAP is not set +# CONFIG_MEDIA_SUPPORT is not set # # Graphics support @@ -917,6 +931,7 @@ CONFIG_RTC_DRV_PCF8563=y # CONFIG_RTC_DRV_S35390A is not set # CONFIG_RTC_DRV_FM3130 is not set # CONFIG_RTC_DRV_RX8581 is not set +# CONFIG_RTC_DRV_RX8025 is not set # # SPI RTC drivers @@ -962,12 +977,15 @@ CONFIG_RTC_DRV_PCF8563=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set # CONFIG_FS_POSIX_ACL is not set -CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set +# CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_BTRFS_FS is not set +CONFIG_FILE_LOCKING=y +CONFIG_FSNOTIFY=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY is not set +CONFIG_INOTIFY_USER=y # CONFIG_QUOTA is not set # CONFIG_AUTOFS_FS is not set # CONFIG_AUTOFS4_FS is not set @@ -1021,6 +1039,12 @@ CONFIG_JFFS2_ZLIB=y # CONFIG_JFFS2_LZO is not set CONFIG_JFFS2_RTIME=y # CONFIG_JFFS2_RUBIN is not set +CONFIG_UBIFS_FS=y +# CONFIG_UBIFS_FS_XATTR is not set +# CONFIG_UBIFS_FS_ADVANCED_COMPR is not set +CONFIG_UBIFS_FS_LZO=y +CONFIG_UBIFS_FS_ZLIB=y +# CONFIG_UBIFS_FS_DEBUG is not set # CONFIG_CRAMFS is not set # CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set @@ -1119,25 +1143,11 @@ CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_NOP_TRACER=y CONFIG_HAVE_FUNCTION_TRACER=y CONFIG_RING_BUFFER=y +CONFIG_EVENT_TRACING=y +CONFIG_CONTEXT_SWITCH_TRACER=y CONFIG_TRACING=y CONFIG_TRACING_SUPPORT=y - -# -# Tracers -# -# CONFIG_FUNCTION_TRACER is not set -# CONFIG_IRQSOFF_TRACER is not set -# CONFIG_PREEMPT_TRACER is not set -# CONFIG_SCHED_TRACER is not set -# CONFIG_CONTEXT_SWITCH_TRACER is not set -# CONFIG_EVENT_TRACER is not set -# CONFIG_BOOT_TRACER is not set -# CONFIG_TRACE_BRANCH_PROFILING is not set -# CONFIG_STACK_TRACER is not set -# CONFIG_KMEMTRACE is not set -# CONFIG_WORKQUEUE_TRACER is not set -# CONFIG_BLK_DEV_IO_TRACE is not set -# CONFIG_FTRACE_STARTUP_TEST is not set +# CONFIG_FTRACE is not set # CONFIG_DYNAMIC_DEBUG is not set # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y @@ -1151,16 +1161,104 @@ CONFIG_ARM_UNWIND=y # CONFIG_SECURITY is not set # CONFIG_SECURITYFS is not set # CONFIG_SECURITY_FILE_CAPABILITIES is not set -# CONFIG_CRYPTO is not set +CONFIG_CRYPTO=y + +# +# Crypto core or helper +# +# CONFIG_CRYPTO_FIPS is not set +CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_ALGAPI2=y +# CONFIG_CRYPTO_MANAGER is not set +# CONFIG_CRYPTO_MANAGER2 is not set +# CONFIG_CRYPTO_GF128MUL is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_CRYPTD is not set +# CONFIG_CRYPTO_AUTHENC is not set +# CONFIG_CRYPTO_TEST is not set + +# +# Authenticated Encryption with Associated Data +# +# CONFIG_CRYPTO_CCM is not set +# CONFIG_CRYPTO_GCM is not set +# CONFIG_CRYPTO_SEQIV is not set + +# +# Block modes +# +# CONFIG_CRYPTO_CBC is not set +# CONFIG_CRYPTO_CTR is not set +# CONFIG_CRYPTO_CTS is not set +# CONFIG_CRYPTO_ECB is not set +# CONFIG_CRYPTO_LRW is not set +# CONFIG_CRYPTO_PCBC is not set +# CONFIG_CRYPTO_XTS is not set + +# +# Hash modes +# +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_XCBC is not set + +# +# Digest +# +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_MD4 is not set +# CONFIG_CRYPTO_MD5 is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +# CONFIG_CRYPTO_RMD128 is not set +# CONFIG_CRYPTO_RMD160 is not set +# CONFIG_CRYPTO_RMD256 is not set +# CONFIG_CRYPTO_RMD320 is not set +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_WP512 is not set + +# +# Ciphers +# +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_CAMELLIA is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_DES is not set +# CONFIG_CRYPTO_FCRYPT is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_SALSA20 is not set +# CONFIG_CRYPTO_SEED is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_TWOFISH is not set + +# +# Compression +# +CONFIG_CRYPTO_DEFLATE=y +# CONFIG_CRYPTO_ZLIB is not set +CONFIG_CRYPTO_LZO=y + +# +# Random Number Generation +# +# CONFIG_CRYPTO_ANSI_CPRNG is not set +CONFIG_CRYPTO_HW=y CONFIG_BINARY_PRINTF=y # # Library routines # CONFIG_BITREVERSE=y +CONFIG_RATIONAL=y CONFIG_GENERIC_FIND_LAST_BIT=y # CONFIG_CRC_CCITT is not set -# CONFIG_CRC16 is not set +CONFIG_CRC16=y # CONFIG_CRC_T10DIF is not set # CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y @@ -1168,6 +1266,8 @@ CONFIG_CRC32=y # CONFIG_LIBCRC32C is not set CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y +CONFIG_LZO_COMPRESS=y +CONFIG_LZO_DECOMPRESS=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y diff --git a/arch/arm/configs/mx3_defconfig b/arch/arm/configs/mx3_defconfig index 20ada52..a4f9a2a 100644 --- a/arch/arm/configs/mx3_defconfig +++ b/arch/arm/configs/mx3_defconfig @@ -1,15 +1,15 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.30-rc1 -# Wed Apr 8 11:06:37 2009 +# Linux kernel version: 2.6.31-rc4 +# Tue Jul 28 14:11:34 2009 # CONFIG_ARM=y +CONFIG_HAVE_PWM=y CONFIG_SYS_SUPPORTS_APM_EMULATION=y CONFIG_GENERIC_GPIO=y CONFIG_GENERIC_TIME=y CONFIG_GENERIC_CLOCKEVENTS=y CONFIG_MMU=y -# CONFIG_NO_IOPORT is not set CONFIG_GENERIC_HARDIRQS=y CONFIG_STACKTRACE_SUPPORT=y CONFIG_HAVE_LATENCYTOP_SUPPORT=y @@ -18,14 +18,13 @@ CONFIG_TRACE_IRQFLAGS_SUPPORT=y CONFIG_HARDIRQS_SW_RESEND=y CONFIG_GENERIC_IRQ_PROBE=y CONFIG_RWSEM_GENERIC_SPINLOCK=y -# CONFIG_ARCH_HAS_ILOG2_U32 is not set -# CONFIG_ARCH_HAS_ILOG2_U64 is not set CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_ARCH_MTD_XIP=y CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y CONFIG_VECTORS_BASE=0xffff0000 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" +CONFIG_CONSTRUCTORS=y # # General setup @@ -86,7 +85,12 @@ CONFIG_TIMERFD=y CONFIG_EVENTFD=y CONFIG_SHMEM=y CONFIG_AIO=y + +# +# Performance Counters +# CONFIG_VM_EVENT_COUNTERS=y +# CONFIG_STRIP_ASM_SYMS is not set CONFIG_COMPAT_BRK=y CONFIG_SLAB=y # CONFIG_SLUB is not set @@ -97,6 +101,11 @@ CONFIG_HAVE_OPROFILE=y # CONFIG_KPROBES is not set CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y +CONFIG_HAVE_CLK=y + +# +# GCOV-based kernel profiling +# # CONFIG_SLOW_WORK is not set CONFIG_HAVE_GENERIC_DMA_COHERENT=y CONFIG_SLABINFO=y @@ -109,7 +118,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_BLOCK=y -# CONFIG_LBD is not set +CONFIG_LBDAF=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_BLK_DEV_INTEGRITY is not set @@ -136,13 +145,14 @@ CONFIG_FREEZER=y # CONFIG_ARCH_VERSATILE is not set # CONFIG_ARCH_AT91 is not set # CONFIG_ARCH_CLPS711X is not set +# CONFIG_ARCH_GEMINI is not set # CONFIG_ARCH_EBSA110 is not set # CONFIG_ARCH_EP93XX is not set -# CONFIG_ARCH_GEMINI is not set # CONFIG_ARCH_FOOTBRIDGE is not set +CONFIG_ARCH_MXC=y +# CONFIG_ARCH_STMP3XXX is not set # CONFIG_ARCH_NETX is not set # CONFIG_ARCH_H720X is not set -# CONFIG_ARCH_IMX is not set # CONFIG_ARCH_IOP13XX is not set # CONFIG_ARCH_IOP32X is not set # CONFIG_ARCH_IOP33X is not set @@ -151,25 +161,25 @@ CONFIG_FREEZER=y # CONFIG_ARCH_IXP4XX is not set # CONFIG_ARCH_L7200 is not set # CONFIG_ARCH_KIRKWOOD is not set -# CONFIG_ARCH_KS8695 is not set -# CONFIG_ARCH_NS9XXX is not set # CONFIG_ARCH_LOKI is not set # CONFIG_ARCH_MV78XX0 is not set -CONFIG_ARCH_MXC=y # CONFIG_ARCH_ORION5X is not set +# CONFIG_ARCH_MMP is not set +# CONFIG_ARCH_KS8695 is not set +# CONFIG_ARCH_NS9XXX is not set +# CONFIG_ARCH_W90X900 is not set # CONFIG_ARCH_PNX4008 is not set # CONFIG_ARCH_PXA is not set -# CONFIG_ARCH_MMP is not set +# CONFIG_ARCH_MSM is not set # CONFIG_ARCH_RPC is not set # CONFIG_ARCH_SA1100 is not set # CONFIG_ARCH_S3C2410 is not set # CONFIG_ARCH_S3C64XX is not set # CONFIG_ARCH_SHARK is not set # CONFIG_ARCH_LH7A40X is not set +# CONFIG_ARCH_U300 is not set # CONFIG_ARCH_DAVINCI is not set # CONFIG_ARCH_OMAP is not set -# CONFIG_ARCH_MSM is not set -# CONFIG_ARCH_W90X900 is not set # # Freescale MXC Implementations @@ -178,6 +188,7 @@ CONFIG_ARCH_MXC=y # CONFIG_ARCH_MX2 is not set CONFIG_ARCH_MX3=y CONFIG_ARCH_MX31=y +CONFIG_ARCH_MX35=y # # MX3 platforms: @@ -185,12 +196,19 @@ CONFIG_ARCH_MX31=y CONFIG_MACH_MX31ADS=y CONFIG_MACH_MX31ADS_WM1133_EV1=y CONFIG_MACH_PCM037=y +CONFIG_MACH_PCM037_EET=y CONFIG_MACH_MX31LITE=y CONFIG_MACH_MX31_3DS=y CONFIG_MACH_MX31MOBOARD=y +CONFIG_MACH_MX31LILLY=y CONFIG_MACH_QONG=y +CONFIG_MACH_PCM043=y +CONFIG_MACH_ARMADILLO5X0=y +CONFIG_MACH_MX35_3DS=y CONFIG_MXC_IRQ_PRIOR=y CONFIG_MXC_PWM=y +CONFIG_ARCH_HAS_RNGA=y +CONFIG_ARCH_MXC_IOMUX_V3=y # # Processor Type @@ -218,6 +236,7 @@ CONFIG_ARM_THUMB=y # CONFIG_CPU_BPREDICT_DISABLE is not set CONFIG_OUTER_CACHE=y CONFIG_CACHE_L2X0=y +# CONFIG_ARM_ERRATA_411920 is not set CONFIG_COMMON_CLKDEV=y # @@ -242,7 +261,6 @@ CONFIG_PREEMPT=y CONFIG_HZ=100 CONFIG_AEABI=y CONFIG_OABI_COMPAT=y -CONFIG_ARCH_FLATMEM_HAS_HOLES=y # CONFIG_ARCH_SPARSEMEM_DEFAULT is not set # CONFIG_ARCH_SELECT_MEMORY_MODEL is not set # CONFIG_HIGHMEM is not set @@ -257,10 +275,11 @@ CONFIG_SPLIT_PTLOCK_CPUS=4 # CONFIG_PHYS_ADDR_T_64BIT is not set CONFIG_ZONE_DMA_FLAG=0 CONFIG_VIRT_TO_BUS=y -CONFIG_UNEVICTABLE_LRU=y CONFIG_HAVE_MLOCK=y CONFIG_HAVE_MLOCKED_PAGE_BIT=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=4096 CONFIG_ALIGNMENT_TRAP=y +# CONFIG_UACCESS_WITH_MEMCPY is not set # # Boot options @@ -362,6 +381,7 @@ CONFIG_DEFAULT_TCP_CONG="cubic" # CONFIG_ECONET is not set # CONFIG_WAN_ROUTER is not set # CONFIG_PHONET is not set +# CONFIG_IEEE802154 is not set # CONFIG_NET_SCHED is not set # CONFIG_DCB is not set @@ -465,7 +485,16 @@ CONFIG_MTD_PHYSMAP=y # CONFIG_MTD_DOC2000 is not set # CONFIG_MTD_DOC2001 is not set # CONFIG_MTD_DOC2001PLUS is not set -# CONFIG_MTD_NAND is not set +CONFIG_MTD_NAND=y +# CONFIG_MTD_NAND_VERIFY_WRITE is not set +# CONFIG_MTD_NAND_ECC_SMC is not set +# CONFIG_MTD_NAND_MUSEUM_IDS is not set +# CONFIG_MTD_NAND_GPIO is not set +CONFIG_MTD_NAND_IDS=y +# CONFIG_MTD_NAND_DISKONCHIP is not set +# CONFIG_MTD_NAND_NANDSIM is not set +# CONFIG_MTD_NAND_PLATFORM is not set +CONFIG_MTD_NAND_MXC=y # CONFIG_MTD_ONENAND is not set # @@ -476,10 +505,30 @@ CONFIG_MTD_PHYSMAP=y # # UBI - Unsorted block images # -# CONFIG_MTD_UBI is not set +CONFIG_MTD_UBI=y +CONFIG_MTD_UBI_WL_THRESHOLD=4096 +CONFIG_MTD_UBI_BEB_RESERVE=1 +# CONFIG_MTD_UBI_GLUEBI is not set + +# +# UBI debugging options +# +# CONFIG_MTD_UBI_DEBUG is not set # CONFIG_PARPORT is not set # CONFIG_BLK_DEV is not set -# CONFIG_MISC_DEVICES is not set +CONFIG_MISC_DEVICES=y +# CONFIG_ICS932S401 is not set +# CONFIG_ENCLOSURE_SERVICES is not set +# CONFIG_ISL29003 is not set +# CONFIG_C2PORT is not set + +# +# EEPROM support +# +CONFIG_EEPROM_AT24=y +# CONFIG_EEPROM_LEGACY is not set +# CONFIG_EEPROM_MAX6875 is not set +# CONFIG_EEPROM_93CX6 is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -493,7 +542,6 @@ CONFIG_HAVE_IDE=y # CONFIG_ATA is not set # CONFIG_MD is not set CONFIG_NETDEVICES=y -CONFIG_COMPAT_NET_DEV_OPS=y # CONFIG_DUMMY is not set # CONFIG_BONDING is not set # CONFIG_MACVLAN is not set @@ -528,7 +576,7 @@ CONFIG_MII=y # CONFIG_ETHOC is not set # CONFIG_SMC911X is not set CONFIG_SMSC911X=y -# CONFIG_DNET is not set +CONFIG_DNET=y # CONFIG_IBM_NEW_EMAC_ZMII is not set # CONFIG_IBM_NEW_EMAC_RGMII is not set # CONFIG_IBM_NEW_EMAC_TAH is not set @@ -537,8 +585,10 @@ CONFIG_SMSC911X=y # CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set # CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set # CONFIG_B44 is not set -CONFIG_CS89x0=y -CONFIG_CS89x0_NONISA_IRQ=y +# CONFIG_CS89x0 is not set +# CONFIG_KS8842 is not set +CONFIG_FEC=y +# CONFIG_FEC2 is not set # CONFIG_NETDEV_1000 is not set # CONFIG_NETDEV_10000 is not set @@ -609,6 +659,7 @@ CONFIG_I2C_HELPER_AUTO=y # # I2C system bus drivers (mostly embedded / system-on-chip) # +# CONFIG_I2C_DESIGNWARE is not set # CONFIG_I2C_GPIO is not set CONFIG_I2C_IMX=y # CONFIG_I2C_OCORES is not set @@ -633,7 +684,6 @@ CONFIG_I2C_IMX=y # CONFIG_SENSORS_PCF8574 is not set # CONFIG_PCF8575 is not set # CONFIG_SENSORS_PCA9539 is not set -# CONFIG_SENSORS_MAX6875 is not set # CONFIG_SENSORS_TSL2550 is not set # CONFIG_I2C_DEBUG_CORE is not set # CONFIG_I2C_DEBUG_ALGO is not set @@ -669,6 +719,7 @@ CONFIG_W1=y # # CONFIG_W1_MASTER_DS2482 is not set CONFIG_W1_MASTER_MXC=y +# CONFIG_W1_MASTER_DS1WM is not set # CONFIG_W1_MASTER_GPIO is not set # @@ -703,6 +754,8 @@ CONFIG_SSB_POSSIBLE=y # CONFIG_TPS65010 is not set # CONFIG_TWL4030_CORE is not set # CONFIG_MFD_TMIO is not set +# CONFIG_MFD_T7L66XB is not set +# CONFIG_MFD_TC6387XB is not set # CONFIG_MFD_TC6393XB is not set # CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set @@ -711,10 +764,8 @@ CONFIG_MFD_WM8350_CONFIG_MODE_0=y CONFIG_MFD_WM8352_CONFIG_MODE_0=y CONFIG_MFD_WM8350_I2C=y # CONFIG_MFD_PCF50633 is not set - -# -# Multimedia devices -# +# CONFIG_AB3100_CORE is not set +CONFIG_MEDIA_SUPPORT=y # # Multimedia core support @@ -758,8 +809,10 @@ CONFIG_SOC_CAMERA_MT9T031=y CONFIG_SOC_CAMERA_MT9V022=y CONFIG_SOC_CAMERA_TW9910=y # CONFIG_SOC_CAMERA_PLATFORM is not set -# CONFIG_SOC_CAMERA_OV772X is not set +CONFIG_SOC_CAMERA_OV772X=y +CONFIG_MX3_VIDEO=y CONFIG_VIDEO_MX3=y +# CONFIG_VIDEO_SH_MOBILE_CEU is not set # CONFIG_RADIO_ADAPTERS is not set # CONFIG_DAB is not set @@ -847,8 +900,11 @@ CONFIG_REGULATOR=y # CONFIG_REGULATOR_DEBUG is not set # CONFIG_REGULATOR_FIXED_VOLTAGE is not set # CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set +# CONFIG_REGULATOR_USERSPACE_CONSUMER is not set # CONFIG_REGULATOR_BQ24022 is not set +# CONFIG_REGULATOR_MAX1586 is not set CONFIG_REGULATOR_WM8350=y +# CONFIG_REGULATOR_LP3971 is not set # CONFIG_UIO is not set # CONFIG_STAGING is not set @@ -861,10 +917,12 @@ CONFIG_REGULATOR_WM8350=y # CONFIG_REISERFS_FS is not set # CONFIG_JFS_FS is not set # CONFIG_FS_POSIX_ACL is not set -CONFIG_FILE_LOCKING=y # CONFIG_XFS_FS is not set +# CONFIG_GFS2_FS is not set # CONFIG_OCFS2_FS is not set # CONFIG_BTRFS_FS is not set +CONFIG_FILE_LOCKING=y +CONFIG_FSNOTIFY=y # CONFIG_DNOTIFY is not set CONFIG_INOTIFY=y CONFIG_INOTIFY_USER=y @@ -921,6 +979,12 @@ CONFIG_JFFS2_ZLIB=y # CONFIG_JFFS2_LZO is not set CONFIG_JFFS2_RTIME=y # CONFIG_JFFS2_RUBIN is not set +CONFIG_UBIFS_FS=y +# CONFIG_UBIFS_FS_XATTR is not set +# CONFIG_UBIFS_FS_ADVANCED_COMPR is not set +CONFIG_UBIFS_FS_LZO=y +CONFIG_UBIFS_FS_ZLIB=y +# CONFIG_UBIFS_FS_DEBUG is not set # CONFIG_CRAMFS is not set # CONFIG_SQUASHFS is not set # CONFIG_VXFS_FS is not set @@ -937,6 +1001,7 @@ CONFIG_NFS_FS=y CONFIG_NFS_V3=y # CONFIG_NFS_V3_ACL is not set CONFIG_NFS_V4=y +# CONFIG_NFS_V4_1 is not set CONFIG_ROOT_NFS=y # CONFIG_NFSD is not set CONFIG_LOCKD=y @@ -979,22 +1044,7 @@ CONFIG_FRAME_WARN=1024 CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_HAVE_FUNCTION_TRACER=y CONFIG_TRACING_SUPPORT=y - -# -# Tracers -# -# CONFIG_FUNCTION_TRACER is not set -# CONFIG_IRQSOFF_TRACER is not set -# CONFIG_PREEMPT_TRACER is not set -# CONFIG_SCHED_TRACER is not set -# CONFIG_CONTEXT_SWITCH_TRACER is not set -# CONFIG_EVENT_TRACER is not set -# CONFIG_BOOT_TRACER is not set -# CONFIG_TRACE_BRANCH_PROFILING is not set -# CONFIG_STACK_TRACER is not set -# CONFIG_KMEMTRACE is not set -# CONFIG_WORKQUEUE_TRACER is not set -# CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_FTRACE is not set # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y CONFIG_ARM_UNWIND=y @@ -1094,9 +1144,9 @@ CONFIG_CRYPTO_DES=y # # Compression # -# CONFIG_CRYPTO_DEFLATE is not set +CONFIG_CRYPTO_DEFLATE=y # CONFIG_CRYPTO_ZLIB is not set -# CONFIG_CRYPTO_LZO is not set +CONFIG_CRYPTO_LZO=y # # Random Number Generation @@ -1109,9 +1159,10 @@ CONFIG_CRYPTO_HW=y # Library routines # CONFIG_BITREVERSE=y +CONFIG_RATIONAL=y CONFIG_GENERIC_FIND_LAST_BIT=y # CONFIG_CRC_CCITT is not set -# CONFIG_CRC16 is not set +CONFIG_CRC16=y # CONFIG_CRC_T10DIF is not set # CONFIG_CRC_ITU_T is not set CONFIG_CRC32=y @@ -1119,6 +1170,8 @@ CONFIG_CRC32=y # CONFIG_LIBCRC32C is not set CONFIG_ZLIB_INFLATE=y CONFIG_ZLIB_DEFLATE=y +CONFIG_LZO_COMPRESS=y +CONFIG_LZO_DECOMPRESS=y CONFIG_HAS_IOMEM=y CONFIG_HAS_IOPORT=y CONFIG_HAS_DMA=y diff --git a/arch/arm/configs/omap3_evm_defconfig b/arch/arm/configs/omap3_evm_defconfig index 28be17f..d5ff477 100644 --- a/arch/arm/configs/omap3_evm_defconfig +++ b/arch/arm/configs/omap3_evm_defconfig @@ -1107,7 +1107,7 @@ CONFIG_USB_ZERO=m CONFIG_USB_OTG_UTILS=y # CONFIG_USB_GPIO_VBUS is not set # CONFIG_ISP1301_OMAP is not set -CONFIG_TWL4030_USB=y +# CONFIG_TWL4030_USB is not set # CONFIG_NOP_USB_XCEIV is not set CONFIG_MMC=y # CONFIG_MMC_DEBUG is not set diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h index 9e07fe5..9ed2377 100644 --- a/arch/arm/include/asm/atomic.h +++ b/arch/arm/include/asm/atomic.h @@ -159,8 +159,6 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr) #else /* ARM_ARCH_6 */ -#include <asm/system.h> - #ifdef CONFIG_SMP #error SMP not supported on pre-ARMv6 CPUs #endif diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 366e509..8c3de1a 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -148,7 +148,7 @@ trace: sub r0, r0, #MCOUNT_INSN_SIZE mov lr, pc mov pc, r2 - mov lr, r1 @ restore lr + ldr lr, [fp, #-4] @ restore lr ldmia sp!, {r0-r3, pc} #endif /* CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 93bb424..f6bc5d4 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -133,7 +133,7 @@ sys_sigaction(int sig, const struct old_sigaction __user *act, } #ifdef CONFIG_CRUNCH -static int preserve_crunch_context(struct crunch_sigframe *frame) +static int preserve_crunch_context(struct crunch_sigframe __user *frame) { char kbuf[sizeof(*frame) + 8]; struct crunch_sigframe *kframe; @@ -146,7 +146,7 @@ static int preserve_crunch_context(struct crunch_sigframe *frame) return __copy_to_user(frame, kframe, sizeof(*frame)); } -static int restore_crunch_context(struct crunch_sigframe *frame) +static int restore_crunch_context(struct crunch_sigframe __user *frame) { char kbuf[sizeof(*frame) + 8]; struct crunch_sigframe *kframe; diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c index 5ac2f56..d6ab64c 100644 --- a/arch/arm/mach-davinci/board-dm355-evm.c +++ b/arch/arm/mach-davinci/board-dm355-evm.c @@ -37,7 +37,6 @@ #include <mach/serial.h> #include <mach/nand.h> #include <mach/mmc.h> -#include <mach/common.h> #define DAVINCI_ASYNC_EMIF_CONTROL_BASE 0x01e10000 #define DAVINCI_ASYNC_EMIF_DATA_CE0_BASE 0x02000000 diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index 28c9008..84ad5d1 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -36,7 +36,6 @@ #include <mach/serial.h> #include <mach/nand.h> #include <mach/mmc.h> -#include <mach/common.h> #define DAVINCI_ASYNC_EMIF_CONTROL_BASE 0x01e10000 #define DAVINCI_ASYNC_EMIF_DATA_CE0_BASE 0x02000000 diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index d9d4045..56c8cd0 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -45,7 +45,6 @@ #include <mach/nand.h> #include <mach/mmc.h> #include <mach/emac.h> -#include <mach/common.h> #define DM644X_EVM_PHY_MASK (0x2) #define DM644X_EVM_MDIO_FREQUENCY (2200000) /* PHY bus frequency */ diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index e17de63..8657e72 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -47,7 +47,6 @@ #include <mach/i2c.h> #include <mach/mmc.h> #include <mach/emac.h> -#include <mach/common.h> #define DM646X_EVM_PHY_MASK (0x2) #define DM646X_EVM_MDIO_FREQUENCY (2200000) /* PHY bus frequency */ diff --git a/arch/arm/mach-davinci/board-sffsdr.c b/arch/arm/mach-davinci/board-sffsdr.c index 748a8e4..7acdfd8 100644 --- a/arch/arm/mach-davinci/board-sffsdr.c +++ b/arch/arm/mach-davinci/board-sffsdr.c @@ -52,7 +52,6 @@ #include <mach/serial.h> #include <mach/psc.h> #include <mach/mux.h> -#include <mach/common.h> #define SFFSDR_PHY_MASK (0x2) #define SFFSDR_MDIO_FREQUENCY (2200000) /* PHY bus frequency */ diff --git a/arch/arm/mach-ep93xx/include/mach/ts72xx.h b/arch/arm/mach-ep93xx/include/mach/ts72xx.h index 34ddec0..4117344 100644 --- a/arch/arm/mach-ep93xx/include/mach/ts72xx.h +++ b/arch/arm/mach-ep93xx/include/mach/ts72xx.h @@ -41,9 +41,6 @@ #define TS72XX_OPTIONS2_TS9420_BOOT 0x02 -#define TS72XX_NOR_PHYS_BASE 0x60000000 -#define TS72XX_NOR2_PHYS_BASE 0x62000000 - #define TS72XX_NAND1_DATA_PHYS_BASE 0x60000000 #define TS72XX_NAND2_DATA_PHYS_BASE 0x70000000 #define TS72XX_NAND_DATA_VIRT_BASE 0xfebfc000 diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c index 7ee024d..aaf1371 100644 --- a/arch/arm/mach-ep93xx/ts72xx.c +++ b/arch/arm/mach-ep93xx/ts72xx.c @@ -112,13 +112,16 @@ static void __init ts72xx_map_io(void) } } +/************************************************************************* + * NOR flash (TS-7200 only) + *************************************************************************/ static struct physmap_flash_data ts72xx_flash_data = { - .width = 1, + .width = 2, }; static struct resource ts72xx_flash_resource = { - .start = TS72XX_NOR_PHYS_BASE, - .end = TS72XX_NOR_PHYS_BASE + SZ_16M - 1, + .start = EP93XX_CS6_PHYS_BASE, + .end = EP93XX_CS6_PHYS_BASE + SZ_16M - 1, .flags = IORESOURCE_MEM, }; @@ -132,6 +135,12 @@ static struct platform_device ts72xx_flash = { .resource = &ts72xx_flash_resource, }; +static void __init ts72xx_register_flash(void) +{ + if (board_is_ts7200()) + platform_device_register(&ts72xx_flash); +} + static unsigned char ts72xx_rtc_readbyte(unsigned long addr) { __raw_writeb(addr, TS72XX_RTC_INDEX_VIRT_BASE); @@ -165,8 +174,7 @@ static struct ep93xx_eth_data ts72xx_eth_data = { static void __init ts72xx_init_machine(void) { ep93xx_init_devices(); - if (board_is_ts7200()) - platform_device_register(&ts72xx_flash); + ts72xx_register_flash(); platform_device_register(&ts72xx_rtc_device); ep93xx_register_eth(&ts72xx_eth_data, 1); diff --git a/arch/arm/mach-ks8695/include/mach/hardware.h b/arch/arm/mach-ks8695/include/mach/hardware.h index 1d640d0..e0f911d 100644 --- a/arch/arm/mach-ks8695/include/mach/hardware.h +++ b/arch/arm/mach-ks8695/include/mach/hardware.h @@ -17,6 +17,11 @@ #include <asm/sizes.h> /* + * Clocks are derived from MCLK, which is 25Mhz + */ +#define KS8695_CLOCK_RATE 25000000 + +/* * Physical RAM address. */ #define KS8695_SDRAM_PA 0x00000000 diff --git a/arch/arm/mach-ks8695/include/mach/timex.h b/arch/arm/mach-ks8695/include/mach/timex.h index 4682e35..10f7163 100644 --- a/arch/arm/mach-ks8695/include/mach/timex.h +++ b/arch/arm/mach-ks8695/include/mach/timex.h @@ -14,7 +14,8 @@ #ifndef __ASM_ARCH_TIMEX_H #define __ASM_ARCH_TIMEX_H -/* timers are derived from MCLK, which is 25MHz */ -#define CLOCK_TICK_RATE 25000000 +#include <mach/hardware.h> + +#define CLOCK_TICK_RATE KS8695_CLOCK_RATE #endif diff --git a/arch/arm/mach-ks8695/pci.c b/arch/arm/mach-ks8695/pci.c index f5ebcc0..7849966 100644 --- a/arch/arm/mach-ks8695/pci.c +++ b/arch/arm/mach-ks8695/pci.c @@ -245,6 +245,9 @@ static int ks8695_pci_fault(unsigned long addr, unsigned int fsr, struct pt_regs static void __init ks8695_pci_preinit(void) { + /* make software reset to avoid freeze if PCI bus was messed up */ + __raw_writel(0x80000000, KS8695_PCI_VA + KS8695_PBCS); + /* stage 1 initialization, subid, subdevice = 0x0001 */ __raw_writel(0x00010001, KS8695_PCI_VA + KS8695_CRCSID); diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c index a2d7814..505d98c 100644 --- a/arch/arm/mach-omap1/mcbsp.c +++ b/arch/arm/mach-omap1/mcbsp.c @@ -19,7 +19,6 @@ #include <mach/irqs.h> #include <mach/dma.h> -#include <mach/irqs.h> #include <mach/mux.h> #include <mach/cpu.h> #include <mach/mcbsp.h> diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c index d3cc145..cf3dd77 100644 --- a/arch/arm/mach-omap2/board-omap3evm.c +++ b/arch/arm/mach-omap2/board-omap3evm.c @@ -25,6 +25,7 @@ #include <linux/spi/spi.h> #include <linux/spi/ads7846.h> #include <linux/i2c/twl4030.h> +#include <linux/usb/otg.h> #include <mach/hardware.h> #include <asm/mach-types.h> @@ -307,6 +308,10 @@ static void __init omap3_evm_init(void) ARRAY_SIZE(omap3evm_spi_board_info)); omap_serial_init(); +#ifdef CONFIG_NOP_USB_XCEIV + /* OMAP3EVM uses ISP1504 phy and so register nop transceiver */ + usb_nop_xceiv_register(); +#endif usb_musb_init(); ads7846_dev_init(); } diff --git a/arch/arm/mach-omap2/mcbsp.c b/arch/arm/mach-omap2/mcbsp.c index a5c0f04..99b6e15 100644 --- a/arch/arm/mach-omap2/mcbsp.c +++ b/arch/arm/mach-omap2/mcbsp.c @@ -19,7 +19,6 @@ #include <mach/irqs.h> #include <mach/dma.h> -#include <mach/irqs.h> #include <mach/mux.h> #include <mach/cpu.h> #include <mach/mcbsp.h> diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c index d85296d..739e59e 100644 --- a/arch/arm/mach-omap2/usb-musb.c +++ b/arch/arm/mach-omap2/usb-musb.c @@ -155,20 +155,6 @@ static struct platform_device musb_device = { .resource = musb_resources, }; -#ifdef CONFIG_NOP_USB_XCEIV -static u64 nop_xceiv_dmamask = DMA_BIT_MASK(32); - -static struct platform_device nop_xceiv_device = { - .name = "nop_usb_xceiv", - .id = -1, - .dev = { - .dma_mask = &nop_xceiv_dmamask, - .coherent_dma_mask = DMA_BIT_MASK(32), - .platform_data = NULL, - }, -}; -#endif - void __init usb_musb_init(void) { if (cpu_is_omap243x()) @@ -183,13 +169,6 @@ void __init usb_musb_init(void) */ musb_plat.clock = "ick"; -#ifdef CONFIG_NOP_USB_XCEIV - if (platform_device_register(&nop_xceiv_device) < 0) { - printk(KERN_ERR "Unable to register NOP-XCEIV device\n"); - return; - } -#endif - if (platform_device_register(&musb_device) < 0) { printk(KERN_ERR "Unable to register HS-USB (MUSB) device\n"); return; diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 63b10d9..9cd0946 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -1141,12 +1141,16 @@ struct power_supply_info em_x270_psy_info = { static void em_x270_battery_low(void) { +#if defined(CONFIG_APM_EMULATION) apm_queue_event(APM_LOW_BATTERY); +#endif } static void em_x270_battery_critical(void) { +#if defined(CONFIG_APM_EMULATION) apm_queue_event(APM_CRITICAL_SUSPEND); +#endif } struct da9030_battery_info em_x270_batterty_info = { diff --git a/arch/arm/mach-pxa/palmld.c b/arch/arm/mach-pxa/palmld.c index ed70f28..169fcc1 100644 --- a/arch/arm/mach-pxa/palmld.c +++ b/arch/arm/mach-pxa/palmld.c @@ -128,6 +128,10 @@ static unsigned long palmld_pin_config[] __initdata = { GPIO38_GPIO, /* wifi ready */ GPIO81_GPIO, /* wifi reset */ + /* FFUART */ + GPIO34_FFUART_RXD, + GPIO39_FFUART_TXD, + /* HDD */ GPIO98_GPIO, /* HDD reset */ GPIO115_GPIO, /* HDD power */ diff --git a/arch/arm/mach-pxa/palmt5.c b/arch/arm/mach-pxa/palmt5.c index aae64a1..33f726f 100644 --- a/arch/arm/mach-pxa/palmt5.c +++ b/arch/arm/mach-pxa/palmt5.c @@ -111,6 +111,10 @@ static unsigned long palmt5_pin_config[] __initdata = { /* PWM */ GPIO16_PWM0_OUT, + /* FFUART */ + GPIO34_FFUART_RXD, + GPIO39_FFUART_TXD, + /* MISC */ GPIO10_GPIO, /* hotsync button */ GPIO90_GPIO, /* power detect */ diff --git a/arch/arm/mach-pxa/palmtx.c b/arch/arm/mach-pxa/palmtx.c index 6c15d84..83d0208 100644 --- a/arch/arm/mach-pxa/palmtx.c +++ b/arch/arm/mach-pxa/palmtx.c @@ -127,6 +127,10 @@ static unsigned long palmtx_pin_config[] __initdata = { GPIO76_LCD_PCLK, GPIO77_LCD_BIAS, + /* FFUART */ + GPIO34_FFUART_RXD, + GPIO39_FFUART_TXD, + /* MISC. */ GPIO10_GPIO, /* hotsync button */ GPIO12_GPIO, /* power detect */ diff --git a/arch/arm/mach-pxa/treo680.c b/arch/arm/mach-pxa/treo680.c index a06f19e..753ec4d 100644 --- a/arch/arm/mach-pxa/treo680.c +++ b/arch/arm/mach-pxa/treo680.c @@ -409,7 +409,7 @@ err1: static void treo680_irda_shutdown(struct device *dev) { - gpio_free(GPIO_NR_TREO680_AMP_EN); + gpio_free(GPIO_NR_TREO680_IR_EN); } static struct pxaficp_platform_data treo680_ficp_info = { diff --git a/arch/arm/mach-pxa/zylonite_pxa300.c b/arch/arm/mach-pxa/zylonite_pxa300.c index cefd1c0..8409544 100644 --- a/arch/arm/mach-pxa/zylonite_pxa300.c +++ b/arch/arm/mach-pxa/zylonite_pxa300.c @@ -197,10 +197,12 @@ static void __init zylonite_detect_lcd_panel(void) for (i = 0; i < NUM_LCD_DETECT_PINS; i++) { id = id << 1; gpio = mfp_to_gpio(lcd_detect_pins[i]); + gpio_request(gpio, "LCD_ID_PINS"); gpio_direction_input(gpio); if (gpio_get_value(gpio)) id = id | 0x1; + gpio_free(gpio); } /* lcd id, flush out bit 1 */ diff --git a/arch/arm/mach-pxa/zylonite_pxa320.c b/arch/arm/mach-pxa/zylonite_pxa320.c index cc5a228..60d08f2 100644 --- a/arch/arm/mach-pxa/zylonite_pxa320.c +++ b/arch/arm/mach-pxa/zylonite_pxa320.c @@ -176,10 +176,12 @@ static void __init zylonite_detect_lcd_panel(void) for (i = 0; i < NUM_LCD_DETECT_PINS; i++) { id = id << 1; gpio = mfp_to_gpio(lcd_detect_pins[i]); + gpio_request(gpio, "LCD_ID_PINS"); gpio_direction_input(gpio); if (gpio_get_value(gpio)) id = id | 0x1; + gpio_free(gpio); } /* lcd id, flush out bit 1 */ diff --git a/arch/arm/mach-s3c2410/include/mach/gpio-core.h b/arch/arm/mach-s3c2410/include/mach/gpio-core.h index 8fe1920..f8b879a 100644 --- a/arch/arm/mach-s3c2410/include/mach/gpio-core.h +++ b/arch/arm/mach-s3c2410/include/mach/gpio-core.h @@ -28,7 +28,7 @@ static inline struct s3c_gpio_chip *s3c_gpiolib_getchip(unsigned int pin) return NULL; chip = &s3c24xx_gpios[pin/32]; - return (S3C2410_GPIO_OFFSET(pin) > chip->chip.ngpio) ? chip : NULL; + return (S3C2410_GPIO_OFFSET(pin) < chip->chip.ngpio) ? chip : NULL; } #endif /* __ASM_ARCH_GPIO_CORE_H */ diff --git a/arch/arm/plat-omap/common.c b/arch/arm/plat-omap/common.c index ebcf006..95587b6 100644 --- a/arch/arm/plat-omap/common.c +++ b/arch/arm/plat-omap/common.c @@ -253,11 +253,8 @@ static struct clocksource clocksource_32k = { */ unsigned long long sched_clock(void) { - unsigned long long ret; - - ret = (unsigned long long)clocksource_32k.read(&clocksource_32k); - ret = (ret * clocksource_32k.mult_orig) >> clocksource_32k.shift; - return ret; + return clocksource_cyc2ns(clocksource_32k.read(&clocksource_32k), + clocksource_32k.mult, clocksource_32k.shift); } static int __init omap_init_clocksource_32k(void) diff --git a/arch/arm/plat-s3c24xx/pwm.c b/arch/arm/plat-s3c24xx/pwm.c index 0120b76..82a6d4d 100644 --- a/arch/arm/plat-s3c24xx/pwm.c +++ b/arch/arm/plat-s3c24xx/pwm.c @@ -246,6 +246,10 @@ int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns) tcmp = duty_ns / tin_ns; tcmp = tcnt - tcmp; + /* the pwm hw only checks the compare register after a decrement, + so the pin never toggles if tcmp = tcnt */ + if (tcmp == tcnt) + tcmp--; pwm_dbg(pwm, "tin_ns=%lu, tcmp=%ld/%lu\n", tin_ns, tcmp, tcnt); diff --git a/arch/arm/plat-s3c64xx/pm.c b/arch/arm/plat-s3c64xx/pm.c index 07a6516..47632fc 100644 --- a/arch/arm/plat-s3c64xx/pm.c +++ b/arch/arm/plat-s3c64xx/pm.c @@ -117,8 +117,6 @@ void s3c_pm_save_core(void) * this. */ -#include <plat/regs-gpio.h> - static void s3c64xx_cpu_suspend(void) { unsigned long tmp; diff --git a/arch/arm/plat-s3c64xx/s3c6400-clock.c b/arch/arm/plat-s3c64xx/s3c6400-clock.c index 1debc1f..febac19 100644 --- a/arch/arm/plat-s3c64xx/s3c6400-clock.c +++ b/arch/arm/plat-s3c64xx/s3c6400-clock.c @@ -153,7 +153,7 @@ static unsigned long s3c64xx_clk_arm_round_rate(struct clk *clk, u32 div; if (parent < rate) - return rate; + return parent; div = (parent / rate) - 1; if (div > armclk_mask) @@ -175,7 +175,7 @@ static int s3c64xx_clk_arm_set_rate(struct clk *clk, unsigned long rate) div = clk_get_rate(clk->parent) / rate; val = __raw_readl(S3C_CLK_DIV0); - val &= armclk_mask; + val &= ~armclk_mask; val |= (div - 1); __raw_writel(val, S3C_CLK_DIV0); diff --git a/arch/arm/plat-stmp3xxx/pinmux.c b/arch/arm/plat-stmp3xxx/pinmux.c index d412003..6d6b1a4 100644 --- a/arch/arm/plat-stmp3xxx/pinmux.c +++ b/arch/arm/plat-stmp3xxx/pinmux.c @@ -22,7 +22,6 @@ #include <linux/sysdev.h> #include <linux/string.h> #include <linux/bitops.h> -#include <linux/sysdev.h> #include <linux/irq.h> #include <mach/hardware.h> diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 58a7e46a..e7cbaa0 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -41,11 +41,6 @@ $(error Sorry, you need a newer version of the assember, one that is built from ftp://ftp.hpl.hp.com/pub/linux-ia64/gas-030124.tar.gz) endif -ifeq ($(call cc-version),0304) - cflags-$(CONFIG_ITANIUM) += -mtune=merced - cflags-$(CONFIG_MCKINLEY) += -mtune=mckinley -endif - KBUILD_CFLAGS += $(cflags-y) head-y := arch/ia64/kernel/head.o arch/ia64/kernel/init_task.o diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h index e2ca800..57a2787 100644 --- a/arch/ia64/include/asm/bitops.h +++ b/arch/ia64/include/asm/bitops.h @@ -286,7 +286,7 @@ __test_and_clear_bit(int nr, volatile void * addr) { __u32 *p = (__u32 *) addr + (nr >> 5); __u32 m = 1 << (nr & 31); - int oldbitset = *p & m; + int oldbitset = (*p & m) != 0; *p &= ~m; return oldbitset; diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 0a9cc73..8840a69 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -155,7 +155,6 @@ #include <linux/bitops.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> -#include <asm/processor.h> /* * Next come the mappings that determine how mmap() protection bits diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 2d31186..8ebccb5 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -21,6 +21,7 @@ EXPORT_SYMBOL(csum_ipv6_magic); #include <asm/page.h> EXPORT_SYMBOL(clear_page); +EXPORT_SYMBOL(copy_page); #ifdef CONFIG_VIRTUAL_MEM_MAP #include <linux/bootmem.h> @@ -60,9 +61,6 @@ EXPORT_SYMBOL(__udivdi3); EXPORT_SYMBOL(__moddi3); EXPORT_SYMBOL(__umoddi3); -#include <asm/page.h> -EXPORT_SYMBOL(copy_page); - #if defined(CONFIG_MD_RAID456) || defined(CONFIG_MD_RAID456_MODULE) extern void xor_ia64_2(void); extern void xor_ia64_3(void); diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index c48b03f..dab4d39 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -1072,6 +1072,10 @@ iosapic_init (unsigned long phys_addr, unsigned int gsi_base) } addr = ioremap(phys_addr, 0); + if (addr == NULL) { + spin_unlock_irqrestore(&iosapic_lock, flags); + return -ENOMEM; + } ver = iosapic_version(addr); if ((err = iosapic_check_gsi_range(gsi_base, ver))) { iounmap(addr); diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c index 0569596..f6b1ff0 100644 --- a/arch/ia64/kernel/pci-dma.c +++ b/arch/ia64/kernel/pci-dma.c @@ -69,11 +69,6 @@ iommu_dma_init(void) int iommu_dma_supported(struct device *dev, u64 mask) { - struct dma_map_ops *ops = platform_dma_get_ops(dev); - - if (ops->dma_supported) - return ops->dma_supported(dev, mask); - /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. The caller just has to use GFP_DMA in this case. */ diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index bc80dff..8f06035 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -372,6 +372,10 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) retval = kobject_init_and_add(&all_cpu_cache_info[cpu].kobj, &cache_ktype_percpu_entry, &sys_dev->kobj, "%s", "cache"); + if (unlikely(retval < 0)) { + cpu_cache_sysfs_exit(cpu); + return retval; + } for (i = 0; i < all_cpu_cache_info[cpu].num_cache_leaves; i++) { this_object = LEAF_KOBJECT_PTR(cpu,i); @@ -385,7 +389,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) } kobject_put(&all_cpu_cache_info[cpu].kobj); cpu_cache_sysfs_exit(cpu); - break; + return retval; } kobject_uevent(&(this_object->kobj), KOBJ_ADD); } diff --git a/arch/ia64/kvm/mmio.c b/arch/ia64/kvm/mmio.c index 21f63ff..9bf55af 100644 --- a/arch/ia64/kvm/mmio.c +++ b/arch/ia64/kvm/mmio.c @@ -247,7 +247,8 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma) vcpu_get_fpreg(vcpu, inst.M9.f2, &v); /* Write high word. FIXME: this is a kludge! */ v.u.bits[1] &= 0x3ffff; - mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE); + mmio_access(vcpu, padr + 8, (u64 *)&v.u.bits[1], 8, + ma, IOREQ_WRITE); data = v.u.bits[0]; size = 3; } else if (inst.M10.major == 7 && inst.M10.x6 == 0x3B) { @@ -265,7 +266,8 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma) /* Write high word.FIXME: this is a kludge! */ v.u.bits[1] &= 0x3ffff; - mmio_access(vcpu, padr + 8, &v.u.bits[1], 8, ma, IOREQ_WRITE); + mmio_access(vcpu, padr + 8, (u64 *)&v.u.bits[1], + 8, ma, IOREQ_WRITE); data = v.u.bits[0]; size = 3; } else if (inst.M10.major == 7 && inst.M10.x6 == 0x31) { diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c index 46b02cb..cc406d0 100644 --- a/arch/ia64/kvm/vcpu.c +++ b/arch/ia64/kvm/vcpu.c @@ -461,7 +461,7 @@ void setreg(unsigned long regnum, unsigned long val, u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg) { struct kvm_pt_regs *regs = vcpu_regs(vcpu); - u64 val; + unsigned long val; if (!reg) return 0; @@ -469,7 +469,7 @@ u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg) return val; } -void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 value, int nat) +void vcpu_set_gr(struct kvm_vcpu *vcpu, unsigned long reg, u64 value, int nat) { struct kvm_pt_regs *regs = vcpu_regs(vcpu); long sof = (regs->cr_ifs) & 0x7f; @@ -1072,7 +1072,7 @@ void kvm_ttag(struct kvm_vcpu *vcpu, INST64 inst) vcpu_set_gr(vcpu, inst.M46.r1, tag, 0); } -int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, u64 *padr) +int vcpu_tpa(struct kvm_vcpu *vcpu, u64 vadr, unsigned long *padr) { struct thash_data *data; union ia64_isr visr, pt_isr; diff --git a/arch/ia64/kvm/vcpu.h b/arch/ia64/kvm/vcpu.h index 042af92..360724d 100644 --- a/arch/ia64/kvm/vcpu.h +++ b/arch/ia64/kvm/vcpu.h @@ -686,14 +686,15 @@ static inline int highest_inservice_irq(struct kvm_vcpu *vcpu) return highest_bits((int *)&(VMX(vcpu, insvc[0]))); } -extern void vcpu_get_fpreg(struct kvm_vcpu *vcpu, u64 reg, +extern void vcpu_get_fpreg(struct kvm_vcpu *vcpu, unsigned long reg, struct ia64_fpreg *val); -extern void vcpu_set_fpreg(struct kvm_vcpu *vcpu, u64 reg, +extern void vcpu_set_fpreg(struct kvm_vcpu *vcpu, unsigned long reg, struct ia64_fpreg *val); -extern u64 vcpu_get_gr(struct kvm_vcpu *vcpu, u64 reg); -extern void vcpu_set_gr(struct kvm_vcpu *vcpu, u64 reg, u64 val, int nat); -extern u64 vcpu_get_psr(struct kvm_vcpu *vcpu); -extern void vcpu_set_psr(struct kvm_vcpu *vcpu, u64 val); +extern u64 vcpu_get_gr(struct kvm_vcpu *vcpu, unsigned long reg); +extern void vcpu_set_gr(struct kvm_vcpu *vcpu, unsigned long reg, + u64 val, int nat); +extern unsigned long vcpu_get_psr(struct kvm_vcpu *vcpu); +extern void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val); extern u64 vcpu_thash(struct kvm_vcpu *vcpu, u64 vadr); extern void vcpu_bsw0(struct kvm_vcpu *vcpu); extern void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte, diff --git a/arch/m68knommu/kernel/time.c b/arch/m68knommu/kernel/time.c index d182b2f..6843224 100644 --- a/arch/m68knommu/kernel/time.c +++ b/arch/m68knommu/kernel/time.c @@ -72,9 +72,10 @@ static unsigned long read_rtc_mmss(void) return mktime(year, mon, day, hour, min, sec);; } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return read_rtc_mmss(); + ts->tv_sec = read_rtc_mmss(); + ts->tv_nsec = 0; } int update_persistent_clock(struct timespec now) diff --git a/arch/mips/alchemy/mtx-1/platform.c b/arch/mips/alchemy/mtx-1/platform.c index 8b5914d..e30e42a 100644 --- a/arch/mips/alchemy/mtx-1/platform.c +++ b/arch/mips/alchemy/mtx-1/platform.c @@ -1,7 +1,7 @@ /* * MTX-1 platform devices registration * - * Copyright (C) 2007, Florian Fainelli <florian@openwrt.org> + * Copyright (C) 2007-2009, Florian Fainelli <florian@openwrt.org> * * 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 @@ -142,7 +142,17 @@ static struct __initdata platform_device * mtx1_devs[] = { static int __init mtx1_register_devices(void) { - gpio_direction_input(207); + int rc; + + rc = gpio_request(mtx1_gpio_button[0].gpio, + mtx1_gpio_button[0].desc); + if (rc < 0) { + printk(KERN_INFO "mtx1: failed to request %d\n", + mtx1_gpio_button[0].gpio); + goto out; + } + gpio_direction_input(mtx1_gpio_button[0].gpio); +out: return platform_add_devices(mtx1_devs, ARRAY_SIZE(mtx1_devs)); } diff --git a/arch/mips/ar7/Makefile b/arch/mips/ar7/Makefile index 7435e44..26bc5da 100644 --- a/arch/mips/ar7/Makefile +++ b/arch/mips/ar7/Makefile @@ -8,3 +8,4 @@ obj-y := \ platform.o \ gpio.o \ clock.o +EXTRA_CFLAGS += -Werror diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c index 27dc666..cc65c8e 100644 --- a/arch/mips/ar7/clock.c +++ b/arch/mips/ar7/clock.c @@ -264,19 +264,6 @@ static void __init tnetd7300_init_clocks(void) iounmap(bootcr); } -static int tnetd7200_get_clock(int base, struct tnetd7200_clock *clock, - u32 *bootcr, u32 bus_clock) -{ - int divisor = ((readl(&clock->prediv) & 0x1f) + 1) * - ((readl(&clock->postdiv) & 0x1f) + 1); - - if (*bootcr & BOOT_PLL_BYPASS) - return base / divisor; - - return base * ((readl(&clock->mul) & 0xf) + 1) / divisor; -} - - static void tnetd7200_set_clock(int base, struct tnetd7200_clock *clock, int prediv, int postdiv, int postdiv2, int mul, u32 frequency) { diff --git a/arch/mips/ar7/memory.c b/arch/mips/ar7/memory.c index 46fed44..696c723 100644 --- a/arch/mips/ar7/memory.c +++ b/arch/mips/ar7/memory.c @@ -52,7 +52,7 @@ static int __init memsize(void) size <<= 1; } while (size < (64 << 20)); - writel(tmpaddr, &addr); + writel((u32)tmpaddr, &addr); return size; } diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 5422449..2ecab61 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -28,7 +28,6 @@ #include <linux/serial_8250.h> #include <linux/ioport.h> #include <linux/io.h> -#include <linux/version.h> #include <linux/vlynq.h> #include <linux/leds.h> #include <linux/string.h> @@ -243,13 +242,13 @@ static struct platform_device physmap_flash = { .num_resources = 1, }; -static u64 cpmac_dma_mask = DMA_32BIT_MASK; +static u64 cpmac_dma_mask = DMA_BIT_MASK(32); static struct platform_device cpmac_low = { .id = 0, .name = "cpmac", .dev = { .dma_mask = &cpmac_dma_mask, - .coherent_dma_mask = DMA_32BIT_MASK, + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &cpmac_low_data, }, .resource = cpmac_low_res, @@ -261,7 +260,7 @@ static struct platform_device cpmac_high = { .name = "cpmac", .dev = { .dma_mask = &cpmac_dma_mask, - .coherent_dma_mask = DMA_32BIT_MASK, + .coherent_dma_mask = DMA_BIT_MASK(32), .platform_data = &cpmac_high_data, }, .resource = cpmac_high_res, @@ -481,6 +480,7 @@ static void __init detect_leds(void) static int __init ar7_register_devices(void) { int res; +#ifdef CONFIG_SERIAL_8250 static struct uart_port uart_port[2]; memset(uart_port, 0, sizeof(struct uart_port) * 2); @@ -512,7 +512,7 @@ static int __init ar7_register_devices(void) if (res) return res; } - +#endif /* CONFIG_SERIAL_8250 */ res = platform_device_register(&physmap_flash); if (res) return res; diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c index a320bce..5ad6f1d 100644 --- a/arch/mips/ar7/prom.c +++ b/arch/mips/ar7/prom.c @@ -144,7 +144,7 @@ static char * __init lookup_psp_var_map(u8 num) { int i; - for (i = 0; i < sizeof(psp_var_map); i++) + for (i = 0; i < ARRAY_SIZE(psp_var_map); i++) if (psp_var_map[i].num == num) return psp_var_map[i].value; diff --git a/arch/mips/ar7/setup.c b/arch/mips/ar7/setup.c index 6ebb5f1..39f6b5b 100644 --- a/arch/mips/ar7/setup.c +++ b/arch/mips/ar7/setup.c @@ -15,7 +15,6 @@ * with this program; if not, write to the Free Software Foundation, Inc., * 59 Temple Place - Suite 330, Boston MA 02111-1307, USA. */ -#include <linux/version.h> #include <linux/init.h> #include <linux/ioport.h> #include <linux/pm.h> diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c index 0b891a9..32d51a3 100644 --- a/arch/mips/cavium-octeon/smp.c +++ b/arch/mips/cavium-octeon/smp.c @@ -194,11 +194,11 @@ static void octeon_init_secondary(void) void octeon_prepare_cpus(unsigned int max_cpus) { cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffffffff); - if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_SHARED, + if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_DISABLED, "mailbox0", mailbox_interrupt)) { panic("Cannot request_irq(OCTEON_IRQ_MBOX0)\n"); } - if (request_irq(OCTEON_IRQ_MBOX1, mailbox_interrupt, IRQF_SHARED, + if (request_irq(OCTEON_IRQ_MBOX1, mailbox_interrupt, IRQF_DISABLED, "mailbox1", mailbox_interrupt)) { panic("Cannot request_irq(OCTEON_IRQ_MBOX1)\n"); } diff --git a/arch/mips/dec/ecc-berr.c b/arch/mips/dec/ecc-berr.c index 6a17c9b..7abce66 100644 --- a/arch/mips/dec/ecc-berr.c +++ b/arch/mips/dec/ecc-berr.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/dec/ecc-berr.c - * * Bus error event handling code for systems equipped with ECC * handling logic, i.e. DECstation/DECsystem 5000/200 (KN02), * 5000/240 (KN03), 5000/260 (KN05) and DECsystem 5900 (KN03), diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S index 00cecdc..82c8528 100644 --- a/arch/mips/dec/int-handler.S +++ b/arch/mips/dec/int-handler.S @@ -1,6 +1,4 @@ /* - * arch/mips/dec/int-handler.S - * * Copyright (C) 1995, 1996, 1997 Paul M. Antoine and Harald Koerfgen * Copyright (C) 2000, 2001, 2002, 2003, 2005 Maciej W. Rozycki * diff --git a/arch/mips/dec/ioasic-irq.c b/arch/mips/dec/ioasic-irq.c index 3acb133..cb41954 100644 --- a/arch/mips/dec/ioasic-irq.c +++ b/arch/mips/dec/ioasic-irq.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/dec/ioasic-irq.c - * * DEC I/O ASIC interrupts. * * Copyright (c) 2002, 2003 Maciej W. Rozycki diff --git a/arch/mips/dec/kn01-berr.c b/arch/mips/dec/kn01-berr.c index d3b8002..b0dc6d5 100644 --- a/arch/mips/dec/kn01-berr.c +++ b/arch/mips/dec/kn01-berr.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/dec/kn01-berr.c - * * Bus error event handling code for DECstation/DECsystem 3100 * and 2100 (KN01) systems equipped with parity error detection * logic. diff --git a/arch/mips/dec/kn02-irq.c b/arch/mips/dec/kn02-irq.c index 02439dc..ed90a8d 100644 --- a/arch/mips/dec/kn02-irq.c +++ b/arch/mips/dec/kn02-irq.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/dec/kn02-irq.c - * * DECstation 5000/200 (KN02) Control and Status Register * interrupts. * diff --git a/arch/mips/dec/kn02xa-berr.c b/arch/mips/dec/kn02xa-berr.c index 5f04545..07ca540 100644 --- a/arch/mips/dec/kn02xa-berr.c +++ b/arch/mips/dec/kn02xa-berr.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/dec/kn02xa-berr.c - * * Bus error event handling code for 5000-series systems equipped * with parity error detection logic, i.e. DECstation/DECsystem * 5000/120, /125, /133 (KN02-BA), 5000/150 (KN04-BA) and Personal diff --git a/arch/mips/dec/prom/call_o32.S b/arch/mips/dec/prom/call_o32.S index e523454..8c84981 100644 --- a/arch/mips/dec/prom/call_o32.S +++ b/arch/mips/dec/prom/call_o32.S @@ -1,6 +1,4 @@ /* - * arch/mips/dec/prom/call_o32.S - * * O32 interface for the 64 (or N32) ABI. * * Copyright (C) 2002 Maciej W. Rozycki diff --git a/arch/mips/dec/prom/console.c b/arch/mips/dec/prom/console.c index 078e1a1..caa6e04 100644 --- a/arch/mips/dec/prom/console.c +++ b/arch/mips/dec/prom/console.c @@ -1,6 +1,4 @@ /* - * arch/mips/dec/prom/console.c - * * DECstation PROM-based early console support. * * Copyright (C) 2004, 2007 Maciej W. Rozycki diff --git a/arch/mips/dec/time.c b/arch/mips/dec/time.c index 1359c03..02f505f 100644 --- a/arch/mips/dec/time.c +++ b/arch/mips/dec/time.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/dec/time.c - * * Copyright (C) 1991, 1992, 1995 Linus Torvalds * Copyright (C) 2000, 2003 Maciej W. Rozycki * @@ -20,7 +18,7 @@ #include <asm/dec/ioasic.h> #include <asm/dec/machtype.h> -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned int year, mon, day, hour, min, sec, real_year; unsigned long flags; @@ -55,7 +53,8 @@ unsigned long read_persistent_clock(void) year += real_year - 72 + 2000; - return mktime(year, mon, day, hour, min, sec); + ts->tv_sec = mktime(year, mon, day, hour, min, sec); + ts->tv_nsec = 0; } /* diff --git a/arch/mips/emma/common/Makefile b/arch/mips/emma/common/Makefile index c392d28..f27d84d 100644 --- a/arch/mips/emma/common/Makefile +++ b/arch/mips/emma/common/Makefile @@ -1,7 +1,4 @@ # -# arch/mips/emma2rh/common/Makefile -# Makefile for the common code of NEC EMMA2RH based board. -# # Copyright (C) NEC Electronics Corporation 2005-2006 # # This program is free software; you can redistribute it and/or modify diff --git a/arch/mips/emma/common/prom.c b/arch/mips/emma/common/prom.c index 120f53f..708f087 100644 --- a/arch/mips/emma/common/prom.c +++ b/arch/mips/emma/common/prom.c @@ -1,7 +1,4 @@ /* - * arch/mips/emma2rh/common/prom.c - * This file is prom file. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This file is based on the arch/mips/ddb5xxx/common/prom.c diff --git a/arch/mips/emma/markeins/Makefile b/arch/mips/emma/markeins/Makefile index 16e0017..f8ba250 100644 --- a/arch/mips/emma/markeins/Makefile +++ b/arch/mips/emma/markeins/Makefile @@ -1,7 +1,4 @@ # -# arch/mips/emma2rh/markeins/Makefile -# Makefile for the common code of NEC EMMA2RH based board. -# # Copyright (C) NEC Electronics Corporation 2005-2006 # # This program is free software; you can redistribute it and/or modify diff --git a/arch/mips/emma/markeins/irq.c b/arch/mips/emma/markeins/irq.c index 43828ae..9504b7e 100644 --- a/arch/mips/emma/markeins/irq.c +++ b/arch/mips/emma/markeins/irq.c @@ -1,7 +1,4 @@ /* - * arch/mips/emma2rh/markeins/irq.c - * This file defines the irq handler for EMMA2RH. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This file is based on the arch/mips/ddb5xxx/ddb5477/irq.c diff --git a/arch/mips/emma/markeins/led.c b/arch/mips/emma/markeins/led.c index 377a181..4975589 100644 --- a/arch/mips/emma/markeins/led.c +++ b/arch/mips/emma/markeins/led.c @@ -1,7 +1,4 @@ /* - * arch/mips/emma2rh/markeins/led.c - * This file defines the led display for Mark-eins. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This program is free software; you can redistribute it and/or modify diff --git a/arch/mips/emma/markeins/platform.c b/arch/mips/emma/markeins/platform.c index 80ae12e..b05b08b 100644 --- a/arch/mips/emma/markeins/platform.c +++ b/arch/mips/emma/markeins/platform.c @@ -1,7 +1,4 @@ /* - * arch/mips/emma2rh/markeins/platofrm.c - * This file sets up platform devices for EMMA2RH Mark-eins. - * * Copyright(C) MontaVista Software Inc, 2006 * * Author: dmitry pervushin <dpervushin@ru.mvista.com> diff --git a/arch/mips/emma/markeins/setup.c b/arch/mips/emma/markeins/setup.c index 67f4565..335dc8c 100644 --- a/arch/mips/emma/markeins/setup.c +++ b/arch/mips/emma/markeins/setup.c @@ -1,7 +1,4 @@ /* - * arch/mips/emma2rh/markeins/setup.c - * This file is setup for EMMA2RH Mark-eins. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This file is based on the arch/mips/ddb5xxx/ddb5477/setup.c. diff --git a/arch/mips/fw/lib/call_o32.S b/arch/mips/fw/lib/call_o32.S index bdf7d1d..e0a68713 100644 --- a/arch/mips/fw/lib/call_o32.S +++ b/arch/mips/fw/lib/call_o32.S @@ -1,6 +1,4 @@ /* - * arch/mips/dec/prom/call_o32.S - * * O32 interface for the 64 (or N32) ABI. * * Copyright (C) 2002 Maciej W. Rozycki diff --git a/arch/mips/include/asm/emma/emma2rh.h b/arch/mips/include/asm/emma/emma2rh.h index 30aea91..2afb2fe 100644 --- a/arch/mips/include/asm/emma/emma2rh.h +++ b/arch/mips/include/asm/emma/emma2rh.h @@ -1,7 +1,4 @@ /* - * arch/mips/include/asm/emma/emma2rh.h - * This file is EMMA2RH common header. - * * Copyright (C) NEC Electronics Corporation 2005-2006 * * This file based on include/asm-mips/ddb5xxx/ddb5xxx.h diff --git a/arch/mips/include/asm/emma/markeins.h b/arch/mips/include/asm/emma/markeins.h index 973b062..2618bf2 100644 --- a/arch/mips/include/asm/emma/markeins.h +++ b/arch/mips/include/asm/emma/markeins.h @@ -1,7 +1,4 @@ /* - * include/asm-mips/emma2rh/markeins.h - * This file is EMMA2RH board depended header. - * * Copyright (C) NEC Electronics Corporation 2005-2006 * * This file based on include/asm-mips/ddb5xxx/ddb5xxx.h diff --git a/arch/mips/include/asm/gic.h b/arch/mips/include/asm/gic.h index 10292e3..a8f5734 100644 --- a/arch/mips/include/asm/gic.h +++ b/arch/mips/include/asm/gic.h @@ -20,7 +20,7 @@ #define GIC_TRIG_EDGE 1 #define GIC_TRIG_LEVEL 0 -#if CONFIG_SMP +#ifdef CONFIG_SMP #define GIC_NUM_INTRS (24 + NR_CPUS * 2) #else #define GIC_NUM_INTRS 32 diff --git a/arch/mips/include/asm/pmc-sierra/msp71xx/war.h b/arch/mips/include/asm/pmc-sierra/msp71xx/war.h index 0bf48fc..9e2ee42 100644 --- a/arch/mips/include/asm/pmc-sierra/msp71xx/war.h +++ b/arch/mips/include/asm/pmc-sierra/msp71xx/war.h @@ -23,6 +23,8 @@ #if defined(CONFIG_PMC_MSP7120_EVAL) || defined(CONFIG_PMC_MSP7120_GW) || \ defined(CONFIG_PMC_MSP7120_FPGA) #define MIPS34K_MISSED_ITLB_WAR 1 +#else +#define MIPS34K_MISSED_ITLB_WAR 0 #endif #endif /* __ASM_MIPS_PMC_SIERRA_WAR_H */ diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 0f926aa..087a888 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -311,8 +311,9 @@ extern void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long unsigned long get_wchan(struct task_struct *p); -#define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + THREAD_SIZE - 32) -#define task_pt_regs(tsk) ((struct pt_regs *)__KSTK_TOS(tsk) - 1) +#define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \ + THREAD_SIZE - 32 - sizeof(struct pt_regs)) +#define task_pt_regs(tsk) ((struct pt_regs *)__KSTK_TOS(tsk)) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->cp0_epc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29]) #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status) diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h index b70c49f..e753a77 100644 --- a/arch/mips/include/asm/unistd.h +++ b/arch/mips/include/asm/unistd.h @@ -354,16 +354,17 @@ #define __NR_pwritev (__NR_Linux + 331) #define __NR_rt_tgsigqueueinfo (__NR_Linux + 332) #define __NR_perf_counter_open (__NR_Linux + 333) +#define __NR_accept4 (__NR_Linux + 334) /* * Offset of the last Linux o32 flavoured syscall */ -#define __NR_Linux_syscalls 333 +#define __NR_Linux_syscalls 334 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */ #define __NR_O32_Linux 4000 -#define __NR_O32_Linux_syscalls 333 +#define __NR_O32_Linux_syscalls 334 #if _MIPS_SIM == _MIPS_SIM_ABI64 @@ -664,16 +665,17 @@ #define __NR_pwritev (__NR_Linux + 290) #define __NR_rt_tgsigqueueinfo (__NR_Linux + 291) #define __NR_perf_counter_open (__NR_Linux + 292) +#define __NR_accept4 (__NR_Linux + 293) /* * Offset of the last Linux 64-bit flavoured syscall */ -#define __NR_Linux_syscalls 292 +#define __NR_Linux_syscalls 293 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */ #define __NR_64_Linux 5000 -#define __NR_64_Linux_syscalls 292 +#define __NR_64_Linux_syscalls 293 #if _MIPS_SIM == _MIPS_SIM_NABI32 @@ -978,16 +980,17 @@ #define __NR_pwritev (__NR_Linux + 294) #define __NR_rt_tgsigqueueinfo (__NR_Linux + 295) #define __NR_perf_counter_open (__NR_Linux + 296) +#define __NR_accept4 (__NR_Linux + 297) /* * Offset of the last N32 flavoured syscall */ -#define __NR_Linux_syscalls 296 +#define __NR_Linux_syscalls 297 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */ #define __NR_N32_Linux 6000 -#define __NR_N32_Linux_syscalls 296 +#define __NR_N32_Linux_syscalls 297 #ifdef __KERNEL__ diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index f0fd636..0d64d0f 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -190,7 +190,7 @@ int vdma_free(unsigned long laddr) return -1; } - while (pgtbl[i].owner == laddr && i < VDMA_PGTBL_ENTRIES) { + while (i < VDMA_PGTBL_ENTRIES && pgtbl[i].owner == laddr) { pgtbl[i].owner = VDMA_PAGE_EMPTY; i++; } diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index 492a0a8..531ce7b 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -188,7 +188,8 @@ NESTED(kernel_entry, 16, sp) # kernel entry point MTC0 zero, CP0_CONTEXT # clear context register PTR_LA $28, init_thread_union - PTR_LI sp, _THREAD_SIZE - 32 + /* Set the SP after an empty pt_regs. */ + PTR_LI sp, _THREAD_SIZE - 32 - PT_SIZE PTR_ADDU sp, $28 set_saved_sp sp, t0, t1 PTR_SUBU sp, 4 * SZREG # init stack pointer diff --git a/arch/mips/kernel/irq_txx9.c b/arch/mips/kernel/irq_txx9.c index a4d1462..9b78029 100644 --- a/arch/mips/kernel/irq_txx9.c +++ b/arch/mips/kernel/irq_txx9.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/kernel/irq_txx9.c - * * Based on linux/arch/mips/jmr3927/rbhma3100/irq.c, * linux/arch/mips/tx4927/common/tx4927_irq.c, * linux/arch/mips/tx4938/common/irq.c diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index 3e9100d..6f51dda 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -98,7 +98,8 @@ static int apply_r_mips_32_rela(struct module *me, u32 *location, Elf_Addr v) static int apply_r_mips_26_rel(struct module *me, u32 *location, Elf_Addr v) { if (v % 4) { - printk(KERN_ERR "module %s: dangerous relocation\n", me->name); + pr_err("module %s: dangerous R_MIPS_26 REL relocation\n", + me->name); return -ENOEXEC; } @@ -118,7 +119,8 @@ static int apply_r_mips_26_rel(struct module *me, u32 *location, Elf_Addr v) static int apply_r_mips_26_rela(struct module *me, u32 *location, Elf_Addr v) { if (v % 4) { - printk(KERN_ERR "module %s: dangerous relocation\n", me->name); + pr_err("module %s: dangerous R_MIPS_26 RELArelocation\n", + me->name); return -ENOEXEC; } @@ -222,7 +224,7 @@ static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) return 0; out_danger: - printk(KERN_ERR "module %s: dangerous " "relocation\n", me->name); + pr_err("module %s: dangerous R_MIPS_LO16 REL relocation\n", me->name); return -ENOEXEC; } @@ -301,7 +303,7 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, /* This is the symbol it is referring to */ sym = (Elf_Sym *)sechdrs[symindex].sh_addr + ELF_MIPS_R_SYM(rel[i]); - if (!sym->st_value) { + if (IS_ERR_VALUE(sym->st_value)) { /* Ignore unresolved weak symbol */ if (ELF_ST_BIND(sym->st_info) == STB_WEAK) continue; @@ -341,7 +343,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, /* This is the symbol it is referring to */ sym = (Elf_Sym *)sechdrs[symindex].sh_addr + ELF_MIPS_R_SYM(rel[i]); - if (!sym->st_value) { + if (IS_ERR_VALUE(sym->st_value)) { /* Ignore unresolved weak symbol */ if (ELF_ST_BIND(sym->st_info) == STB_WEAK) continue; diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index e0a4ac1..26109c4 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/kernel/proc.c - * * Copyright (C) 1995, 1996, 2001 Ralf Baechle * Copyright (C) 2001, 2004 MIPS Technologies, Inc. * Copyright (C) 2004 Maciej W. Rozycki diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index c09d681..f3d73e1 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -115,7 +115,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, { struct thread_info *ti = task_thread_info(p); struct pt_regs *childregs; - long childksp; + unsigned long childksp; p->set_child_tid = p->clear_child_tid = NULL; childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32; @@ -132,6 +132,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, /* set up new TSS. */ childregs = (struct pt_regs *) childksp - 1; + /* Put the stack after the struct pt_regs. */ + childksp = (unsigned long) childregs; *childregs = *regs; childregs->regs[7] = 0; /* Clear error flag */ diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 20a86e0..b570821 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -654,6 +654,7 @@ einval: li v0, -ENOSYS sys sys_pwritev 6 sys sys_rt_tgsigqueueinfo 4 sys sys_perf_counter_open 5 + sys sys_accept4 4 .endm /* We pre-compute the number of _instruction_ bytes needed to diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index b046130..3d866f2 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -491,4 +491,5 @@ sys_call_table: PTR sys_pwritev /* 5390 */ PTR sys_rt_tgsigqueueinfo PTR sys_perf_counter_open + PTR sys_accept4 .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 15874f9..e855b11 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -417,4 +417,5 @@ EXPORT(sysn32_call_table) PTR sys_pwritev PTR compat_sys_rt_tgsigqueueinfo /* 5295 */ PTR sys_perf_counter_open + PTR sys_accept4 .size sysn32_call_table,.-sysn32_call_table diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 781e0f1..0c49f1a 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -537,4 +537,5 @@ sys_call_table: PTR compat_sys_pwritev PTR compat_sys_rt_tgsigqueueinfo PTR sys_perf_counter_open + PTR sys_accept4 .size sys_call_table,.-sys_call_table diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c index 8a0626c..c16bb6d 100644 --- a/arch/mips/kernel/smtc.c +++ b/arch/mips/kernel/smtc.c @@ -465,11 +465,8 @@ void smtc_prepare_cpus(int cpus) smtc_configure_tlb(); for (tc = 0, vpe = 0 ; (vpe < nvpe) && (tc < ntc) ; vpe++) { - /* - * Set the MVP bits. - */ - settc(tc); - write_vpe_c0_vpeconf0(read_vpe_c0_vpeconf0() | VPECONF0_MVP); + if (tcpervpe[vpe] == 0) + continue; if (vpe != 0) printk(", "); printk("VPE %d: TC", vpe); @@ -488,6 +485,12 @@ void smtc_prepare_cpus(int cpus) } if (vpe != 0) { /* + * Allow this VPE to control others. + */ + write_vpe_c0_vpeconf0(read_vpe_c0_vpeconf0() | + VPECONF0_MVP); + + /* * Clear any stale software interrupts from VPE's Cause */ write_vpe_c0_cause(0); diff --git a/arch/mips/kernel/stacktrace.c b/arch/mips/kernel/stacktrace.c index 58f5cd7..d52ff77 100644 --- a/arch/mips/kernel/stacktrace.c +++ b/arch/mips/kernel/stacktrace.c @@ -1,6 +1,4 @@ /* - * arch/mips/kernel/stacktrace.c - * * Stack trace management functions * * Copyright (C) 2006 Atsushi Nemoto <anemo@mba.ocn.ne.jp> diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 07b9ec2..9a1ab7e 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -73,7 +73,7 @@ static int major; static const int minor = 1; /* fixed for now */ #ifdef CONFIG_MIPS_APSP_KSPD - static struct kspd_notifications kspd_events; +static struct kspd_notifications kspd_events; static int kspd_events_reqd = 0; #endif @@ -155,10 +155,9 @@ struct { }; static void release_progmem(void *ptr); -extern void save_gp_address(unsigned int secbase, unsigned int rel); /* get the vpe associated with this minor */ -struct vpe *get_vpe(int minor) +static struct vpe *get_vpe(int minor) { struct vpe *v; @@ -174,7 +173,7 @@ struct vpe *get_vpe(int minor) } /* get the vpe associated with this minor */ -struct tc *get_tc(int index) +static struct tc *get_tc(int index) { struct tc *t; @@ -186,20 +185,8 @@ struct tc *get_tc(int index) return NULL; } -struct tc *get_tc_unused(void) -{ - struct tc *t; - - list_for_each_entry(t, &vpecontrol.tc_list, list) { - if (t->state == TC_STATE_UNUSED) - return t; - } - - return NULL; -} - /* allocate a vpe and associate it with this minor (or index) */ -struct vpe *alloc_vpe(int minor) +static struct vpe *alloc_vpe(int minor) { struct vpe *v; @@ -216,7 +203,7 @@ struct vpe *alloc_vpe(int minor) } /* allocate a tc. At startup only tc0 is running, all other can be halted. */ -struct tc *alloc_tc(int index) +static struct tc *alloc_tc(int index) { struct tc *tc; @@ -232,7 +219,7 @@ out: } /* clean up and free everything */ -void release_vpe(struct vpe *v) +static void release_vpe(struct vpe *v) { list_del(&v->list); if (v->load_addr) @@ -240,7 +227,7 @@ void release_vpe(struct vpe *v) kfree(v); } -void dump_mtregs(void) +static void dump_mtregs(void) { unsigned long val; @@ -327,7 +314,8 @@ static void layout_sections(struct module *mod, const Elf_Ehdr * hdr, || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL) continue; - s->sh_entsize = get_offset(&mod->core_size, s); + s->sh_entsize = + get_offset((unsigned long *)&mod->core_size, s); } if (m == 0) @@ -461,16 +449,15 @@ static int apply_r_mips_lo16(struct module *me, uint32_t *location, { unsigned long insnlo = *location; Elf32_Addr val, vallo; + struct mips_hi16 *l, *next; /* Sign extend the addend we extract from the lo insn. */ vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000; if (mips_hi16_list != NULL) { - struct mips_hi16 *l; l = mips_hi16_list; while (l != NULL) { - struct mips_hi16 *next; unsigned long insn; /* @@ -480,7 +467,7 @@ static int apply_r_mips_lo16(struct module *me, uint32_t *location, printk(KERN_DEBUG "VPE loader: " "apply_r_mips_lo16/hi16: \t" "inconsistent value information\n"); - return -ENOEXEC; + goto out_free; } /* @@ -518,6 +505,16 @@ static int apply_r_mips_lo16(struct module *me, uint32_t *location, *location = insnlo; return 0; + +out_free: + while (l != NULL) { + next = l->next; + kfree(l); + l = next; + } + mips_hi16_list = NULL; + + return -ENOEXEC; } static int (*reloc_handlers[]) (struct module *me, uint32_t *location, @@ -541,7 +538,7 @@ static char *rstrs[] = { [R_MIPS_PC16] = "MIPS_PC16" }; -int apply_relocations(Elf32_Shdr *sechdrs, +static int apply_relocations(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, unsigned int relsec, @@ -586,7 +583,7 @@ int apply_relocations(Elf32_Shdr *sechdrs, return 0; } -void save_gp_address(unsigned int secbase, unsigned int rel) +static inline void save_gp_address(unsigned int secbase, unsigned int rel) { gp_addr = secbase + rel; gp_offs = gp_addr - (secbase & 0xffff0000); diff --git a/arch/mips/lasat/ds1603.c b/arch/mips/lasat/ds1603.c index 52cb143..c6fd96f 100644 --- a/arch/mips/lasat/ds1603.c +++ b/arch/mips/lasat/ds1603.c @@ -135,7 +135,7 @@ static void rtc_end_op(void) lasat_ndelay(1000); } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned long word; unsigned long flags; @@ -147,7 +147,8 @@ unsigned long read_persistent_clock(void) rtc_end_op(); spin_unlock_irqrestore(&rtc_lock, flags); - return word; + ts->tv_sec = word; + ts->tv_nsec = 0; } int rtc_mips_set_mmss(unsigned long time) diff --git a/arch/mips/lasat/sysctl.c b/arch/mips/lasat/sysctl.c index 8f88886..3f04d4c 100644 --- a/arch/mips/lasat/sysctl.c +++ b/arch/mips/lasat/sysctl.c @@ -92,10 +92,12 @@ static int rtctmp; int proc_dolasatrtc(ctl_table *table, int write, struct file *filp, void *buffer, size_t *lenp, loff_t *ppos) { + struct timespec ts; int r; if (!write) { - rtctmp = read_persistent_clock(); + read_persistent_clock(&ts); + rtctmp = ts.tv_sec; /* check for time < 0 and set to 0 */ if (rtctmp < 0) rtctmp = 0; @@ -134,9 +136,11 @@ int sysctl_lasat_rtc(ctl_table *table, void *oldval, size_t *oldlenp, void *newval, size_t newlen) { + struct timespec ts; int r; - rtctmp = read_persistent_clock(); + read_persistent_clock(&ts); + rtctmp = ts.tv_sec; if (rtctmp < 0) rtctmp = 0; r = sysctl_intvec(table, oldval, oldlenp, newval, newlen); diff --git a/arch/mips/lemote/lm2e/setup.c b/arch/mips/lemote/lm2e/setup.c index ebd6cea..24b355d 100644 --- a/arch/mips/lemote/lm2e/setup.c +++ b/arch/mips/lemote/lm2e/setup.c @@ -54,9 +54,10 @@ void __init plat_time_init(void) mips_hpt_frequency = cpu_clock_freq / 2; } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return mc146818_get_cmos_time(); + ts->tv_sec = mc146818_get_cmos_time(); + ts->tv_nsec = 0; } void (*__wbflush)(void); diff --git a/arch/mips/mipssim/sim_time.c b/arch/mips/mipssim/sim_time.c index 0cea932..5492c42 100644 --- a/arch/mips/mipssim/sim_time.c +++ b/arch/mips/mipssim/sim_time.c @@ -89,13 +89,13 @@ unsigned __cpuinit get_c0_compare_int(void) if (cpu_has_veic) { set_vi_handler(MSC01E_INT_CPUCTR, mips_timer_dispatch); mips_cpu_timer_irq = MSC01E_INT_BASE + MSC01E_INT_CPUCTR; - } else { -#endif - { - if (cpu_has_vint) - set_vi_handler(cp0_compare_irq, mips_timer_dispatch); - mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; + + return mips_cpu_timer_irq; } +#endif + if (cpu_has_vint) + set_vi_handler(cp0_compare_irq, mips_timer_dispatch); + mips_cpu_timer_irq = MIPS_CPU_IRQ_BASE + cp0_compare_irq; return mips_cpu_timer_irq; } diff --git a/arch/mips/mm/c-octeon.c b/arch/mips/mm/c-octeon.c index b165cdc..10ab69f 100644 --- a/arch/mips/mm/c-octeon.c +++ b/arch/mips/mm/c-octeon.c @@ -289,7 +289,7 @@ static void cache_parity_error_octeon(int non_recoverable) } /** - * Called when the the exception is not recoverable + * Called when the the exception is recoverable */ asmlinkage void cache_parity_error_octeon_recoverable(void) @@ -298,7 +298,7 @@ asmlinkage void cache_parity_error_octeon_recoverable(void) } /** - * Called when the the exception is recoverable + * Called when the the exception is not recoverable */ asmlinkage void cache_parity_error_octeon_non_recoverable(void) diff --git a/arch/mips/mm/extable.c b/arch/mips/mm/extable.c index 297fb9f..9d25d2b 100644 --- a/arch/mips/mm/extable.c +++ b/arch/mips/mm/extable.c @@ -1,5 +1,9 @@ /* - * linux/arch/mips/mm/extable.c + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1997, 99, 2001 - 2004 Ralf Baechle <ralf@linux-mips.org> */ #include <linux/module.h> #include <linux/spinlock.h> diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 6751ce9..f956ecb 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -171,6 +171,7 @@ out_of_memory: * We ran out of memory, call the OOM killer, and return the userspace * (which will retry the fault, or kill us if we got oom-killed). */ + up_read(&mm->mmap_sem); pagefault_out_of_memory(); return; diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c index a8756f8..3e0a9b3 100644 --- a/arch/mips/mti-malta/malta-int.c +++ b/arch/mips/mti-malta/malta-int.c @@ -331,6 +331,7 @@ static struct irqaction irq_call = { .flags = IRQF_DISABLED|IRQF_PERCPU, .name = "IPI_call" }; +#endif /* CONFIG_MIPS_MT_SMP */ static int gic_resched_int_base; static int gic_call_int_base; @@ -346,7 +347,6 @@ unsigned int plat_ipi_resched_int_xlate(unsigned int cpu) { return GIC_RESCHED_INT(cpu); } -#endif /* CONFIG_MIPS_MT_SMP */ static struct irqaction i8259irq = { .handler = no_action, diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c index 0b97d47..3c6f190 100644 --- a/arch/mips/mti-malta/malta-time.c +++ b/arch/mips/mti-malta/malta-time.c @@ -100,9 +100,10 @@ static unsigned int __init estimate_cpu_frequency(void) return count; } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return mc146818_get_cmos_time(); + ts->tv_sec = mc146818_get_cmos_time(); + ts->tv_nsec = 0; } static void __init plat_perf_setup(void) diff --git a/arch/mips/nxp/pnx8550/common/time.c b/arch/mips/nxp/pnx8550/common/time.c index 8df43e9..18b1927 100644 --- a/arch/mips/nxp/pnx8550/common/time.c +++ b/arch/mips/nxp/pnx8550/common/time.c @@ -138,7 +138,7 @@ __init void plat_time_init(void) * HZ timer interrupts per second. */ mips_hpt_frequency = 27UL * ((1000000UL * n)/(m * pow2p)); - cpj = (mips_hpt_frequency + HZ / 2) / HZ; + cpj = DIV_ROUND_CLOSEST(mips_hpt_frequency, HZ); write_c0_count(0); timer_ack(); diff --git a/arch/mips/pci/fixup-emma2rh.c b/arch/mips/pci/fixup-emma2rh.c index fba5aad..0d9ccf4 100644 --- a/arch/mips/pci/fixup-emma2rh.c +++ b/arch/mips/pci/fixup-emma2rh.c @@ -1,7 +1,4 @@ /* - * arch/mips/pci/fixup-emma2rh.c - * This file defines the PCI configration. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This file is based on the arch/mips/ddb5xxx/ddb5477/pci.c diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c index 0ad39e5..f0bb914 100644 --- a/arch/mips/pci/fixup-sb1250.c +++ b/arch/mips/pci/fixup-sb1250.c @@ -1,6 +1,4 @@ /* - * arch/mips/pci/fixup-sb1250.c - * * Copyright (C) 2004, 2006 MIPS Technologies, Inc. All rights reserved. * Author: Maciej W. Rozycki <macro@mips.com> * diff --git a/arch/mips/pci/ops-emma2rh.c b/arch/mips/pci/ops-emma2rh.c index 5947a70..710aef5 100644 --- a/arch/mips/pci/ops-emma2rh.c +++ b/arch/mips/pci/ops-emma2rh.c @@ -1,7 +1,4 @@ /* - * arch/mips/pci/ops-emma2rh.c - * This file defines the PCI operation for EMMA2RH. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This file is based on the arch/mips/pci/ops-vr41xx.c diff --git a/arch/mips/pci/pci-emma2rh.c b/arch/mips/pci/pci-emma2rh.c index 2df4190..773e34f 100644 --- a/arch/mips/pci/pci-emma2rh.c +++ b/arch/mips/pci/pci-emma2rh.c @@ -1,7 +1,4 @@ /* - * arch/mips/pci/pci-emma2rh.c - * This file defines the PCI configration. - * * Copyright (C) NEC Electronics Corporation 2004-2006 * * This file is based on the arch/mips/ddb5xxx/ddb5477/pci.c diff --git a/arch/mips/pci/pci-tx4927.c b/arch/mips/pci/pci-tx4927.c index aaa9005..a580740 100644 --- a/arch/mips/pci/pci-tx4927.c +++ b/arch/mips/pci/pci-tx4927.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/pci/pci-tx4927.c - * * Based on linux/arch/mips/txx9/rbtx4938/setup.c, * and RBTX49xx patch from CELF patch archive. * diff --git a/arch/mips/pci/pci-tx4938.c b/arch/mips/pci/pci-tx4938.c index 1ea257b..20e45f3 100644 --- a/arch/mips/pci/pci-tx4938.c +++ b/arch/mips/pci/pci-tx4938.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/pci/pci-tx4938.c - * * Based on linux/arch/mips/txx9/rbtx4938/setup.c, * and RBTX49xx patch from CELF patch archive. * diff --git a/arch/mips/pci/pci-tx4939.c b/arch/mips/pci/pci-tx4939.c index 5fecf1c..9ef8406 100644 --- a/arch/mips/pci/pci-tx4939.c +++ b/arch/mips/pci/pci-tx4939.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/pci/pci-tx4939.c - * * Based on linux/arch/mips/txx9/rbtx4939/setup.c, * and RBTX49xx patch from CELF patch archive. * diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c index 7526224..6aa5c54 100644 --- a/arch/mips/pci/pcie-octeon.c +++ b/arch/mips/pci/pcie-octeon.c @@ -1040,19 +1040,29 @@ static inline int octeon_pcie_read_config(int pcie_port, struct pci_bus *bus, int bus_number = bus->number; /* - * We need to force the bus number to be zero on the root - * bus. Linux numbers the 2nd root bus to start after all - * buses on root 0. + * For the top level bus make sure our hardware bus number + * matches the software one. */ - if (bus->parent == NULL) - bus_number = 0; + if (bus->parent == NULL) { + union cvmx_pciercx_cfg006 pciercx_cfg006; + pciercx_cfg006.u32 = cvmx_pcie_cfgx_read(pcie_port, + CVMX_PCIERCX_CFG006(pcie_port)); + if (pciercx_cfg006.s.pbnum != bus_number) { + pciercx_cfg006.s.pbnum = bus_number; + pciercx_cfg006.s.sbnum = bus_number; + pciercx_cfg006.s.subbnum = bus_number; + cvmx_pcie_cfgx_write(pcie_port, + CVMX_PCIERCX_CFG006(pcie_port), + pciercx_cfg006.u32); + } + } /* * PCIe only has a single device connected to Octeon. It is * always device ID 0. Don't bother doing reads for other * device IDs on the first segment. */ - if ((bus_number == 0) && (devfn >> 3 != 0)) + if ((bus->parent == NULL) && (devfn >> 3 != 0)) return PCIBIOS_FUNC_NOT_SUPPORTED; /* @@ -1070,7 +1080,7 @@ static inline int octeon_pcie_read_config(int pcie_port, struct pci_bus *bus, * bridge only respondes to device ID 0, function * 0-1 */ - if ((bus_number == 0) && (devfn >= 2)) + if ((bus->parent == NULL) && (devfn >= 2)) return PCIBIOS_FUNC_NOT_SUPPORTED; /* * The PCI-X slots are device ID 2,3. Choose one of @@ -1167,13 +1177,6 @@ static inline int octeon_pcie_write_config(int pcie_port, struct pci_bus *bus, int size, u32 val) { int bus_number = bus->number; - /* - * We need to force the bus number to be zero on the root - * bus. Linux numbers the 2nd root bus to start after all - * busses on root 0. - */ - if (bus->parent == NULL) - bus_number = 0; switch (size) { case 4: diff --git a/arch/mips/pmc-sierra/msp71xx/gpio.c b/arch/mips/pmc-sierra/msp71xx/gpio.c index 69848c5..aaccbe5 100644 --- a/arch/mips/pmc-sierra/msp71xx/gpio.c +++ b/arch/mips/pmc-sierra/msp71xx/gpio.c @@ -1,6 +1,4 @@ /* - * @file /arch/mips/pmc-sierra/msp71xx/gpio.c - * * Generic PMC MSP71xx GPIO handling. These base gpio are controlled by two * types of registers. The data register sets the output level when in output * mode and when in input mode will contain the value at the input. The config diff --git a/arch/mips/pmc-sierra/msp71xx/gpio_extended.c b/arch/mips/pmc-sierra/msp71xx/gpio_extended.c index fc6dbc6..2a99f36 100644 --- a/arch/mips/pmc-sierra/msp71xx/gpio_extended.c +++ b/arch/mips/pmc-sierra/msp71xx/gpio_extended.c @@ -1,6 +1,4 @@ /* - * @file /arch/mips/pmc-sierra/msp71xx/gpio_extended.c - * * Generic PMC MSP71xx EXTENDED (EXD) GPIO handling. The extended gpio is * a set of hardware registers that have no need for explicit locking as * it is handled by unique method of writing individual set/clr bits. diff --git a/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c b/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c index f5f1b8d..61f3902 100644 --- a/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c +++ b/arch/mips/pmc-sierra/msp71xx/msp_irq_slp.c @@ -45,13 +45,6 @@ static inline void mask_msp_slp_irq(unsigned int irq) */ static inline void ack_msp_slp_irq(unsigned int irq) { - mask_slp_irq(irq); - - /* - * only really necessary for 18, 16-14 and sometimes 3:0 (since - * these can be edge sensitive) but it doesn't hurt for the others. - */ - /* check for PER interrupt range */ if (irq < MSP_PER_INTBASE) *SLP_INT_STS_REG = (1 << (irq - MSP_SLP_INTBASE)); @@ -62,8 +55,7 @@ static inline void ack_msp_slp_irq(unsigned int irq) static struct irq_chip msp_slp_irq_controller = { .name = "MSP_SLP", .ack = ack_msp_slp_irq, - .mask = ack_msp_slp_irq, - .mask_ack = ack_msp_slp_irq, + .mask = mask_msp_slp_irq, .unmask = unmask_msp_slp_irq, }; @@ -79,7 +71,7 @@ void __init msp_slp_irq_init(void) /* initialize all the IRQ descriptors */ for (i = MSP_SLP_INTBASE; i < MSP_PER_INTBASE + 32; i++) - set_irq_chip_and_handler(i, &msp_slp_irq_controller + set_irq_chip_and_handler(i, &msp_slp_irq_controller, handle_level_irq); } diff --git a/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c b/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c index caf5e9a..fc990cb 100644 --- a/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c +++ b/arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c @@ -1,6 +1,4 @@ /* - * arch/mips/pmc-sierra/yosemite/atmel_read_eeprom.c - * * Copyright (C) 2003 PMC-Sierra Inc. * Author: Manish Lachwani (lachwani@pmc-sierra.com) * diff --git a/arch/mips/pmc-sierra/yosemite/setup.c b/arch/mips/pmc-sierra/yosemite/setup.c index 2d3c0dc..3498ac9 100644 --- a/arch/mips/pmc-sierra/yosemite/setup.c +++ b/arch/mips/pmc-sierra/yosemite/setup.c @@ -70,7 +70,7 @@ void __init bus_error_init(void) } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned int year, month, day, hour, min, sec; unsigned long flags; @@ -92,7 +92,8 @@ unsigned long read_persistent_clock(void) m48t37_base->control = 0x00; spin_unlock_irqrestore(&rtc_lock, flags); - return mktime(year, month, day, hour, min, sec); + ts->tv_sec = mktime(year, month, day, hour, min, sec); + ts->tv_nsec = 0; } int rtc_mips_set_time(unsigned long tim) diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 672e45d..623ffc9 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -87,19 +87,26 @@ enum swarm_rtc_type { enum swarm_rtc_type swarm_rtc_type; -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { + unsigned long sec; + switch (swarm_rtc_type) { case RTC_XICOR: - return xicor_get_time(); + sec = xicor_get_time(); + break; case RTC_M4LT81: - return m41t81_get_time(); + sec = m41t81_get_time(); + break; case RTC_NONE: default: - return mktime(2000, 1, 1, 0, 0, 0); + sec = mktime(2000, 1, 1, 0, 0, 0); + break; } + ts->tv_sec = sec; + tv->tv_nsec = 0; } int rtc_mips_set_time(unsigned long sec) diff --git a/arch/mips/sibyte/swarm/swarm-i2c.c b/arch/mips/sibyte/swarm/swarm-i2c.c index 4282ac9..0625050 100644 --- a/arch/mips/sibyte/swarm/swarm-i2c.c +++ b/arch/mips/sibyte/swarm/swarm-i2c.c @@ -1,6 +1,4 @@ /* - * arch/mips/sibyte/swarm/swarm-i2c.c - * * Broadcom BCM91250A (SWARM), etc. I2C platform setup. * * Copyright (c) 2008 Maciej W. Rozycki diff --git a/arch/mips/sni/time.c b/arch/mips/sni/time.c index 0d9ec1a..62df6a5 100644 --- a/arch/mips/sni/time.c +++ b/arch/mips/sni/time.c @@ -182,7 +182,8 @@ void __init plat_time_init(void) setup_pit_timer(); } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - return -1; + ts->tv_sec = -1; + ts->tv_nsec = 0; } diff --git a/arch/mips/txx9/generic/mem_tx4927.c b/arch/mips/txx9/generic/mem_tx4927.c index ef6ea6e..70f9626 100644 --- a/arch/mips/txx9/generic/mem_tx4927.c +++ b/arch/mips/txx9/generic/mem_tx4927.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/txx9/generic/mem_tx4927.c - * * common tx4927 memory interface * * Author: MontaVista Software, Inc. diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c index 3b7d77d..a205e2b 100644 --- a/arch/mips/txx9/generic/setup.c +++ b/arch/mips/txx9/generic/setup.c @@ -1,6 +1,4 @@ /* - * linux/arch/mips/txx9/generic/setup.c - * * Based on linux/arch/mips/txx9/rbtx4938/setup.c, * and RBTX49xx patch from CELF patch archive. * diff --git a/arch/mips/txx9/rbtx4939/setup.c b/arch/mips/txx9/rbtx4939/setup.c index c033ffe..b0c241e 100644 --- a/arch/mips/txx9/rbtx4939/setup.c +++ b/arch/mips/txx9/rbtx4939/setup.c @@ -512,10 +512,10 @@ static void __init rbtx4939_setup(void) rbtx4939_ebusc_setup(); /* always enable ATA0 */ txx9_set64(&tx4939_ccfgptr->pcfg, TX4939_PCFG_ATA0MODE); - rbtx4939_update_ioc_pen(); if (txx9_master_clock == 0) txx9_master_clock = 20000000; tx4939_setup(); + rbtx4939_update_ioc_pen(); #ifdef HAVE_RBTX4939_IOSWAB ioswabw = rbtx4939_ioswabw; __mem_ioswabw = rbtx4939_mem_ioswabw; diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h index 35d2ed6..19aecc9 100644 --- a/arch/mn10300/include/asm/pci.h +++ b/arch/mn10300/include/asm/pci.h @@ -59,7 +59,6 @@ void pcibios_penalize_isa_irq(int irq); #include <linux/slab.h> #include <asm/scatterlist.h> #include <linux/string.h> -#include <linux/mm.h> #include <asm/io.h> struct pci_dev; diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index ae3e70c..e552e54 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -553,7 +553,7 @@ * on most of those machines only handles cache transactions. */ extrd,u,*= \pte,_PAGE_NO_CACHE_BIT+32,1,%r0 - depi 1,12,1,\prot + depdi 1,12,1,\prot /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ convert_for_tlb_insert20 \pte diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index ef5caf2..61ee0ee 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -86,8 +86,12 @@ * the bottom of the table, which has a maximum signed displacement of * 0x3fff; however, since we're only going forward, this becomes * 0x1fff, and thus, since each GOT entry is 8 bytes long we can have - * at most 1023 entries */ -#define MAX_GOTS 1023 + * at most 1023 entries. + * To overcome this 14bit displacement with some kernel modules, we'll + * use instead the unusal 16bit displacement method (see reassemble_16a) + * which gives us a maximum positive displacement of 0x7fff, and as such + * allows us to allocate up to 4095 GOT entries. */ +#define MAX_GOTS 4095 /* three functions to determine where in the module core * or init pieces the location is */ @@ -145,12 +149,40 @@ struct stub_entry { /* The reassemble_* functions prepare an immediate value for insertion into an opcode. pa-risc uses all sorts of weird bitfields in the instruction to hold the value. */ +static inline int sign_unext(int x, int len) +{ + int len_ones; + + len_ones = (1 << len) - 1; + return x & len_ones; +} + +static inline int low_sign_unext(int x, int len) +{ + int sign, temp; + + sign = (x >> (len-1)) & 1; + temp = sign_unext(x, len-1); + return (temp << 1) | sign; +} + static inline int reassemble_14(int as14) { return (((as14 & 0x1fff) << 1) | ((as14 & 0x2000) >> 13)); } +static inline int reassemble_16a(int as16) +{ + int s, t; + + /* Unusual 16-bit encoding, for wide mode only. */ + t = (as16 << 1) & 0xffff; + s = (as16 & 0x8000); + return (t ^ s ^ (s >> 1)) | (s >> 15); +} + + static inline int reassemble_17(int as17) { return (((as17 & 0x10000) >> 16) | @@ -407,6 +439,7 @@ static Elf_Addr get_stub(struct module *me, unsigned long value, long addend, enum elf_stub_type stub_type, Elf_Addr loc0, unsigned int targetsec) { struct stub_entry *stub; + int __maybe_unused d; /* initialize stub_offset to point in front of the section */ if (!me->arch.section[targetsec].stub_offset) { @@ -460,12 +493,19 @@ static Elf_Addr get_stub(struct module *me, unsigned long value, long addend, */ switch (stub_type) { case ELF_STUB_GOT: - stub->insns[0] = 0x537b0000; /* ldd 0(%dp),%dp */ + d = get_got(me, value, addend); + if (d <= 15) { + /* Format 5 */ + stub->insns[0] = 0x0f6010db; /* ldd 0(%dp),%dp */ + stub->insns[0] |= low_sign_unext(d, 5) << 16; + } else { + /* Format 3 */ + stub->insns[0] = 0x537b0000; /* ldd 0(%dp),%dp */ + stub->insns[0] |= reassemble_16a(d); + } stub->insns[1] = 0x53610020; /* ldd 10(%dp),%r1 */ stub->insns[2] = 0xe820d000; /* bve (%r1) */ stub->insns[3] = 0x537b0030; /* ldd 18(%dp),%dp */ - - stub->insns[0] |= reassemble_14(get_got(me, value, addend) & 0x3fff); break; case ELF_STUB_MILLI: stub->insns[0] = 0x20200000; /* ldil 0,%r1 */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index dfdf13c..fddc3ed 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -34,7 +34,7 @@ #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 /* We don't currently support large pages. */ -#define KVM_PAGES_PER_HPAGE (1<<31) +#define KVM_PAGES_PER_HPAGE (1UL << 31) struct kvm; struct kvm_run; diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 20a60d6..ccf129d 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -7,6 +7,7 @@ #include <linux/device.h> #include <linux/dma-mapping.h> +#include <linux/lmb.h> #include <asm/bug.h> #include <asm/abs_addr.h> @@ -90,11 +91,10 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg, static int dma_direct_dma_supported(struct device *dev, u64 mask) { #ifdef CONFIG_PPC64 - /* Could be improved to check for memory though it better be - * done via some global so platforms can set the limit in case + /* Could be improved so platforms can set the limit in case * they have limited DMA windows */ - return mask >= DMA_BIT_MASK(32); + return mask >= (lmb_end_of_DRAM() - 1); #else return 1; #endif diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c index c244133..cc466d0 100644 --- a/arch/powerpc/kernel/mpc7450-pmu.c +++ b/arch/powerpc/kernel/mpc7450-pmu.c @@ -407,7 +407,8 @@ struct power_pmu mpc7450_pmu = { static int init_mpc7450_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450")) + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450")) return -ENODEV; return register_power_pmu(&mpc7450_pmu); diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c index 809fdf9..70e1f57 100644 --- a/arch/powerpc/kernel/perf_counter.c +++ b/arch/powerpc/kernel/perf_counter.c @@ -518,6 +518,8 @@ void hw_perf_disable(void) struct cpu_hw_counters *cpuhw; unsigned long flags; + if (!ppmu) + return; local_irq_save(flags); cpuhw = &__get_cpu_var(cpu_hw_counters); @@ -572,6 +574,8 @@ void hw_perf_enable(void) int n_lim; int idx; + if (!ppmu) + return; local_irq_save(flags); cpuhw = &__get_cpu_var(cpu_hw_counters); if (!cpuhw->disabled) { @@ -737,6 +741,8 @@ int hw_perf_group_sched_in(struct perf_counter *group_leader, long i, n, n0; struct perf_counter *sub; + if (!ppmu) + return 0; cpuhw = &__get_cpu_var(cpu_hw_counters); n0 = cpuhw->n_counters; n = collect_events(group_leader, ppmu->n_counter - n0, @@ -1281,6 +1287,8 @@ void hw_perf_counter_setup(int cpu) { struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu); + if (!ppmu) + return; memset(cpuhw, 0, sizeof(*cpuhw)); cpuhw->mmcr[0] = MMCR0_FC; } diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c index db90b0c..3c90a3d 100644 --- a/arch/powerpc/kernel/power4-pmu.c +++ b/arch/powerpc/kernel/power4-pmu.c @@ -606,7 +606,8 @@ static struct power_pmu power4_pmu = { static int init_power4_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4")) + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4")) return -ENODEV; return register_power_pmu(&power4_pmu); diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c index f4adca8..31918af 100644 --- a/arch/powerpc/kernel/power5+-pmu.c +++ b/arch/powerpc/kernel/power5+-pmu.c @@ -678,8 +678,9 @@ static struct power_pmu power5p_pmu = { static int init_power5p_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+") - && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++")) + if (!cur_cpu_spec->oprofile_cpu_type || + (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+") + && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++"))) return -ENODEV; return register_power_pmu(&power5p_pmu); diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c index 29b2c6c..867f6f6 100644 --- a/arch/powerpc/kernel/power5-pmu.c +++ b/arch/powerpc/kernel/power5-pmu.c @@ -618,7 +618,8 @@ static struct power_pmu power5_pmu = { static int init_power5_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5")) + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5")) return -ENODEV; return register_power_pmu(&power5_pmu); diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c index 09ae5bf..fa21890 100644 --- a/arch/powerpc/kernel/power6-pmu.c +++ b/arch/powerpc/kernel/power6-pmu.c @@ -537,7 +537,8 @@ static struct power_pmu power6_pmu = { static int init_power6_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6")) + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6")) return -ENODEV; return register_power_pmu(&power6_pmu); diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c index 5a9f5cb..388cf57 100644 --- a/arch/powerpc/kernel/power7-pmu.c +++ b/arch/powerpc/kernel/power7-pmu.c @@ -366,7 +366,8 @@ static struct power_pmu power7_pmu = { static int init_power7_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7")) + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7")) return -ENODEV; return register_power_pmu(&power7_pmu); diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c index 833097a..75dccb7 100644 --- a/arch/powerpc/kernel/ppc970-pmu.c +++ b/arch/powerpc/kernel/ppc970-pmu.c @@ -488,8 +488,9 @@ static struct power_pmu ppc970_pmu = { static int init_ppc970_pmu(void) { - if (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970") - && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP")) + if (!cur_cpu_spec->oprofile_cpu_type || + (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970") + && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP"))) return -ENODEV; return register_power_pmu(&ppc970_pmu); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 211d7b0..5b16575 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -772,11 +772,12 @@ int update_persistent_clock(struct timespec now) return ppc_md.set_rtc_time(&tm); } -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { struct rtc_time tm; static int first = 1; + ts->tv_nsec = 0; /* XXX this is a litle fragile but will work okay in the short term */ if (first) { first = 0; @@ -784,14 +785,18 @@ unsigned long read_persistent_clock(void) timezone_offset = ppc_md.time_init(); /* get_boot_time() isn't guaranteed to be safe to call late */ - if (ppc_md.get_boot_time) - return ppc_md.get_boot_time() -timezone_offset; + if (ppc_md.get_boot_time) { + ts->tv_sec = ppc_md.get_boot_time() - timezone_offset; + return; + } + } + if (!ppc_md.get_rtc_time) { + ts->tv_sec = 0; + return; } - if (!ppc_md.get_rtc_time) - return 0; ppc_md.get_rtc_time(&tm); - return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec); + ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec); } /* clocksource code */ diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 8d15314..cae14c4 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -208,6 +208,9 @@ static noinline __init void detect_machine_type(void) machine_flags |= MACHINE_FLAG_KVM; else machine_flags |= MACHINE_FLAG_VM; + + /* Store machine flags for setting up lowcore early */ + S390_lowcore.machine_flags = machine_flags; } static __init void early_pgm_check_handler(void) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index d4c8e9c..6bff1a1 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -182,12 +182,14 @@ static void timing_alert_interrupt(__u16 code) static void etr_reset(void); static void stp_reset(void); -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - struct timespec ts; + tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, ts); +} - tod_to_timeval(get_clock() - TOD_UNIX_EPOCH, &ts); - return ts.tv_sec; +void read_boot_clock(struct timespec *ts) +{ + tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, ts); } static cycle_t read_tod_clock(struct clocksource *cs) @@ -205,6 +207,10 @@ static struct clocksource clocksource_tod = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; +struct clocksource * __init clocksource_default_clock(void) +{ + return &clocksource_tod; +} void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) { @@ -242,10 +248,6 @@ void update_vsyscall_tz(void) */ void __init time_init(void) { - struct timespec ts; - unsigned long flags; - cycle_t now; - /* Reset time synchronization interfaces. */ etr_reset(); stp_reset(); @@ -261,26 +263,6 @@ void __init time_init(void) if (clocksource_register(&clocksource_tod) != 0) panic("Could not register TOD clock source"); - /* - * The TOD clock is an accurate clock. The xtime should be - * initialized in a way that the difference between TOD and - * xtime is reasonably small. Too bad that timekeeping_init - * sets xtime.tv_nsec to zero. In addition the clock source - * change from the jiffies clock source to the TOD clock - * source add another error of up to 1/HZ second. The same - * function sets wall_to_monotonic to a value that is too - * small for /proc/uptime to be accurate. - * Reset xtime and wall_to_monotonic to sane values. - */ - write_seqlock_irqsave(&xtime_lock, flags); - now = get_clock(); - tod_to_timeval(now - TOD_UNIX_EPOCH, &xtime); - clocksource_tod.cycle_last = now; - clocksource_tod.raw_time = xtime; - tod_to_timeval(sched_clock_base_cc - TOD_UNIX_EPOCH, &ts); - set_normalized_timespec(&wall_to_monotonic, -ts.tv_sec, -ts.tv_nsec); - write_sequnlock_irqrestore(&xtime_lock, flags); - /* Enable TOD clock interrupts on the boot cpu. */ init_cpu_timer(); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index f04f530..4d61341 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -386,7 +386,7 @@ no_timer: } __unset_cpu_idle(vcpu); __set_current_state(TASK_RUNNING); - remove_wait_queue(&vcpu->wq, &wait); + remove_wait_queue(&vcpu->arch.local_int.wq, &wait); spin_unlock_bh(&vcpu->arch.local_int.lock); spin_unlock(&vcpu->arch.local_int.float_int->lock); hrtimer_try_to_cancel(&vcpu->arch.ckc_timer); diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index 3667883..0ef81d6 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -169,7 +169,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, unsigned long *reg) { struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int; - struct kvm_s390_local_interrupt *li; + struct kvm_s390_local_interrupt *li = NULL; struct kvm_s390_interrupt_info *inti; int rc; u8 tmp; @@ -189,9 +189,10 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address, return 2; /* busy */ spin_lock(&fi->lock); - li = fi->local_int[cpu_addr]; + if (cpu_addr < KVM_MAX_VCPUS) + li = fi->local_int[cpu_addr]; - if ((cpu_addr >= KVM_MAX_VCPUS) || (li == NULL)) { + if (li == NULL) { rc = 1; /* incorrect state */ *reg &= SIGP_STAT_INCORRECT_STATE; kfree(inti); diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c index 7ffd1b43..b9c88cc 100644 --- a/arch/sh/boards/board-ap325rxa.c +++ b/arch/sh/boards/board-ap325rxa.c @@ -547,7 +547,7 @@ static int __init ap325rxa_devices_setup(void) return platform_add_devices(ap325rxa_devices, ARRAY_SIZE(ap325rxa_devices)); } -device_initcall(ap325rxa_devices_setup); +arch_initcall(ap325rxa_devices_setup); /* Return the board specific boot mode pin configuration */ static int ap325rxa_mode_pins(void) diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index f70f464..f9b2e4d 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -608,7 +608,7 @@ static int __init migor_devices_setup(void) return platform_add_devices(migor_devices, ARRAY_SIZE(migor_devices)); } -__initcall(migor_devices_setup); +arch_initcall(migor_devices_setup); /* Return the board specific boot mode pin configuration */ static int migor_mode_pins(void) diff --git a/arch/sh/kernel/cpu/sh2/setup-sh7619.c b/arch/sh/kernel/cpu/sh2/setup-sh7619.c index 1379873..8555c05 100644 --- a/arch/sh/kernel/cpu/sh2/setup-sh7619.c +++ b/arch/sh/kernel/cpu/sh2/setup-sh7619.c @@ -187,7 +187,7 @@ static int __init sh7619_devices_setup(void) return platform_add_devices(sh7619_devices, ARRAY_SIZE(sh7619_devices)); } -__initcall(sh7619_devices_setup); +arch_initcall(sh7619_devices_setup); void __init plat_irq_setup(void) { diff --git a/arch/sh/kernel/cpu/sh2a/setup-mxg.c b/arch/sh/kernel/cpu/sh2a/setup-mxg.c index 869c2da..b673764 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-mxg.c +++ b/arch/sh/kernel/cpu/sh2a/setup-mxg.c @@ -238,7 +238,7 @@ static int __init mxg_devices_setup(void) return platform_add_devices(mxg_devices, ARRAY_SIZE(mxg_devices)); } -__initcall(mxg_devices_setup); +arch_initcall(mxg_devices_setup); void __init plat_irq_setup(void) { diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c index d8febe1..fbde5b7 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c @@ -357,7 +357,7 @@ static int __init sh7201_devices_setup(void) return platform_add_devices(sh7201_devices, ARRAY_SIZE(sh7201_devices)); } -__initcall(sh7201_devices_setup); +arch_initcall(sh7201_devices_setup); void __init plat_irq_setup(void) { diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c index 62e3039..d3fd536 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7203.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7203.c @@ -367,7 +367,7 @@ static int __init sh7203_devices_setup(void) return platform_add_devices(sh7203_devices, ARRAY_SIZE(sh7203_devices)); } -__initcall(sh7203_devices_setup); +arch_initcall(sh7203_devices_setup); void __init plat_irq_setup(void) { diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c index 3e6f3d7..a9ccc5e 100644 --- a/arch/sh/kernel/cpu/sh2a/setup-sh7206.c +++ b/arch/sh/kernel/cpu/sh2a/setup-sh7206.c @@ -338,7 +338,7 @@ static int __init sh7206_devices_setup(void) return platform_add_devices(sh7206_devices, ARRAY_SIZE(sh7206_devices)); } -__initcall(sh7206_devices_setup); +arch_initcall(sh7206_devices_setup); void __init plat_irq_setup(void) { diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7705.c b/arch/sh/kernel/cpu/sh3/setup-sh7705.c index 88f742f..c231059 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7705.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7705.c @@ -222,7 +222,7 @@ static int __init sh7705_devices_setup(void) return platform_add_devices(sh7705_devices, ARRAY_SIZE(sh7705_devices)); } -__initcall(sh7705_devices_setup); +arch_initcall(sh7705_devices_setup); static struct platform_device *sh7705_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c index c563067..347ab35 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c @@ -250,7 +250,7 @@ static int __init sh770x_devices_setup(void) return platform_add_devices(sh770x_devices, ARRAY_SIZE(sh770x_devices)); } -__initcall(sh770x_devices_setup); +arch_initcall(sh770x_devices_setup); static struct platform_device *sh770x_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7710.c b/arch/sh/kernel/cpu/sh3/setup-sh7710.c index efa76c8..717e90a 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7710.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7710.c @@ -226,7 +226,7 @@ static int __init sh7710_devices_setup(void) return platform_add_devices(sh7710_devices, ARRAY_SIZE(sh7710_devices)); } -__initcall(sh7710_devices_setup); +arch_initcall(sh7710_devices_setup); static struct platform_device *sh7710_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh3/setup-sh7720.c b/arch/sh/kernel/cpu/sh3/setup-sh7720.c index 5b21077..74d8baa 100644 --- a/arch/sh/kernel/cpu/sh3/setup-sh7720.c +++ b/arch/sh/kernel/cpu/sh3/setup-sh7720.c @@ -388,7 +388,7 @@ static int __init sh7720_devices_setup(void) return platform_add_devices(sh7720_devices, ARRAY_SIZE(sh7720_devices)); } -__initcall(sh7720_devices_setup); +arch_initcall(sh7720_devices_setup); static struct platform_device *sh7720_early_devices[] __initdata = { &cmt0_device, diff --git a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c index 6d088d1..de4827d 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh4-202.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh4-202.c @@ -138,7 +138,7 @@ static int __init sh4202_devices_setup(void) return platform_add_devices(sh4202_devices, ARRAY_SIZE(sh4202_devices)); } -__initcall(sh4202_devices_setup); +arch_initcall(sh4202_devices_setup); static struct platform_device *sh4202_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c index 851672d..1b8b122 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c @@ -239,7 +239,7 @@ static int __init sh7750_devices_setup(void) return platform_add_devices(sh7750_devices, ARRAY_SIZE(sh7750_devices)); } -__initcall(sh7750_devices_setup); +arch_initcall(sh7750_devices_setup); static struct platform_device *sh7750_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7760.c b/arch/sh/kernel/cpu/sh4/setup-sh7760.c index 5b82251..7fbb7be 100644 --- a/arch/sh/kernel/cpu/sh4/setup-sh7760.c +++ b/arch/sh/kernel/cpu/sh4/setup-sh7760.c @@ -265,7 +265,7 @@ static int __init sh7760_devices_setup(void) return platform_add_devices(sh7760_devices, ARRAY_SIZE(sh7760_devices)); } -__initcall(sh7760_devices_setup); +arch_initcall(sh7760_devices_setup); static struct platform_device *sh7760_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c index 6307e08..ac4d567 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c @@ -325,7 +325,7 @@ static int __init sh7343_devices_setup(void) return platform_add_devices(sh7343_devices, ARRAY_SIZE(sh7343_devices)); } -__initcall(sh7343_devices_setup); +arch_initcall(sh7343_devices_setup); static struct platform_device *sh7343_early_devices[] __initdata = { &cmt_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c index c18f7d0..1a956b1 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c @@ -318,7 +318,7 @@ static int __init sh7366_devices_setup(void) return platform_add_devices(sh7366_devices, ARRAY_SIZE(sh7366_devices)); } -__initcall(sh7366_devices_setup); +arch_initcall(sh7366_devices_setup); static struct platform_device *sh7366_early_devices[] __initdata = { &cmt_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c index ea524a2..cda76eb 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c @@ -359,7 +359,7 @@ static int __init sh7722_devices_setup(void) return platform_add_devices(sh7722_devices, ARRAY_SIZE(sh7722_devices)); } -__initcall(sh7722_devices_setup); +arch_initcall(sh7722_devices_setup); static struct platform_device *sh7722_early_devices[] __initdata = { &cmt_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c index e1bb80b..b45dace 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c @@ -473,7 +473,7 @@ static int __init sh7723_devices_setup(void) return platform_add_devices(sh7723_devices, ARRAY_SIZE(sh7723_devices)); } -__initcall(sh7723_devices_setup); +arch_initcall(sh7723_devices_setup); static struct platform_device *sh7723_early_devices[] __initdata = { &cmt_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c index e5ac9eb..a04edaa 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7724.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7724.c @@ -508,7 +508,7 @@ static int __init sh7724_devices_setup(void) return platform_add_devices(sh7724_devices, ARRAY_SIZE(sh7724_devices)); } -device_initcall(sh7724_devices_setup); +arch_initcall(sh7724_devices_setup); static struct platform_device *sh7724_early_devices[] __initdata = { &cmt_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c index f1e0c0d..4659fff 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7763.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7763.c @@ -314,7 +314,7 @@ static int __init sh7763_devices_setup(void) return platform_add_devices(sh7763_devices, ARRAY_SIZE(sh7763_devices)); } -__initcall(sh7763_devices_setup); +arch_initcall(sh7763_devices_setup); static struct platform_device *sh7763_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c index 1e86209..eead08d 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7770.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7770.c @@ -368,7 +368,7 @@ static int __init sh7770_devices_setup(void) return platform_add_devices(sh7770_devices, ARRAY_SIZE(sh7770_devices)); } -__initcall(sh7770_devices_setup); +arch_initcall(sh7770_devices_setup); static struct platform_device *sh7770_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c index 715e05b..2c901f4 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7780.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7780.c @@ -256,7 +256,7 @@ static int __init sh7780_devices_setup(void) return platform_add_devices(sh7780_devices, ARRAY_SIZE(sh7780_devices)); } -__initcall(sh7780_devices_setup); +arch_initcall(sh7780_devices_setup); static struct platform_device *sh7780_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c index af56140..7f6c718 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7785.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7785.c @@ -263,7 +263,7 @@ static int __init sh7785_devices_setup(void) return platform_add_devices(sh7785_devices, ARRAY_SIZE(sh7785_devices)); } -__initcall(sh7785_devices_setup); +arch_initcall(sh7785_devices_setup); static struct platform_device *sh7785_early_devices[] __initdata = { &tmu0_device, diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c index b700494..0104a8e 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-sh7786.c +++ b/arch/sh/kernel/cpu/sh4a/setup-sh7786.c @@ -547,7 +547,7 @@ static int __init sh7786_devices_setup(void) return platform_add_devices(sh7786_devices, ARRAY_SIZE(sh7786_devices)); } -device_initcall(sh7786_devices_setup); +arch_initcall(sh7786_devices_setup); void __init plat_early_device_setup(void) { diff --git a/arch/sh/kernel/cpu/sh4a/setup-shx3.c b/arch/sh/kernel/cpu/sh4a/setup-shx3.c index 53c65fd..07f0789 100644 --- a/arch/sh/kernel/cpu/sh4a/setup-shx3.c +++ b/arch/sh/kernel/cpu/sh4a/setup-shx3.c @@ -256,7 +256,7 @@ static int __init shx3_devices_setup(void) return platform_add_devices(shx3_devices, ARRAY_SIZE(shx3_devices)); } -__initcall(shx3_devices_setup); +arch_initcall(shx3_devices_setup); void __init plat_early_device_setup(void) { diff --git a/arch/sh/kernel/cpu/sh5/setup-sh5.c b/arch/sh/kernel/cpu/sh5/setup-sh5.c index f5ff1ac..6a0f82f 100644 --- a/arch/sh/kernel/cpu/sh5/setup-sh5.c +++ b/arch/sh/kernel/cpu/sh5/setup-sh5.c @@ -186,7 +186,7 @@ static int __init sh5_devices_setup(void) return platform_add_devices(sh5_devices, ARRAY_SIZE(sh5_devices)); } -__initcall(sh5_devices_setup); +arch_initcall(sh5_devices_setup); void __init plat_early_device_setup(void) { diff --git a/arch/sh/kernel/time.c b/arch/sh/kernel/time.c index 9b352a1..0e0e858 100644 --- a/arch/sh/kernel/time.c +++ b/arch/sh/kernel/time.c @@ -39,11 +39,9 @@ void (*rtc_sh_get_time)(struct timespec *) = null_rtc_get_time; int (*rtc_sh_set_time)(const time_t) = null_rtc_set_time; #ifdef CONFIG_GENERIC_CMOS_UPDATE -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { - struct timespec tv; - rtc_sh_get_time(&tv); - return tv.tv_sec; + rtc_sh_get_time(ts); } int update_persistent_clock(struct timespec now) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 738bdc6..13ffa5d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,6 +24,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE + select HAVE_PERF_COUNTERS if (!M386 && !M486) select HAVE_IOREMAP_PROT select HAVE_KPROBES select ARCH_WANT_OPTIONAL_GPIOLIB @@ -742,7 +743,6 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC - select HAVE_PERF_COUNTERS if (!M386 && !M486) config X86_IO_APIC def_bool y diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index edc90f2..8406ed7 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -33,7 +33,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ efi_call_virt(f, a1, a2, a3, a4, a5, a6) -#define efi_ioremap(addr, size) ioremap_cache(addr, size) +#define efi_ioremap(addr, size, type) ioremap_cache(addr, size) #else /* !CONFIG_X86_32 */ @@ -84,7 +84,8 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) -extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size); +extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, + u32 type); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 2bdab21..c6ccbe7 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -12,9 +12,15 @@ static inline unsigned long native_save_fl(void) { unsigned long flags; + /* + * Note: this needs to be "=r" not "=rm", because we have the + * stack offset from what gcc expects at the time the "pop" is + * executed, and so a memory reference with respect to the stack + * would end up using the wrong address. + */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" - : "=g" (flags) + : "=r" (flags) : /* no input */ : "memory"); diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 341070f..77a6850 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -175,7 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info); #define UV_GLOBAL_MMR32_PNODE_BITS(p) ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT)) #define UV_GLOBAL_MMR64_PNODE_BITS(p) \ - ((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT) + (((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT) #define UV_APIC_PNODE_SHIFT 6 @@ -327,6 +327,7 @@ struct uv_blade_info { unsigned short nr_possible_cpus; unsigned short nr_online_cpus; unsigned short pnode; + short memory_nid; }; extern struct uv_blade_info *uv_blade_info; extern short *uv_node_to_blade; @@ -363,6 +364,12 @@ static inline int uv_blade_to_pnode(int bid) return uv_blade_info[bid].pnode; } +/* Nid of memory node on blade. -1 if no blade-local memory */ +static inline int uv_blade_to_memory_nid(int bid) +{ + return uv_blade_info[bid].memory_nid; +} + /* Determine the number of possible cpus on a blade */ static inline int uv_blade_nr_possible_cpus(int bid) { diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index dc27a69..3d61e20 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -21,6 +21,7 @@ struct vsyscall_gtod_data { u32 shift; } clock; struct timespec wall_to_monotonic; + struct timespec wall_time_coarse; }; extern struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 2284a48..d2ed6c5 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3793,6 +3793,9 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, mmr_pnode = uv_blade_to_pnode(mmr_blade); uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); + if (cfg->move_in_progress) + send_cleanup_vector(cfg); + return irq; } diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 8e4cbb2..a5371ec 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -17,11 +17,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return x2apic_enabled(); } -/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */ - +/* + * need to use more than cpu 0, because we need more vectors when + * MSI-X are used. + */ static const struct cpumask *x2apic_target_cpus(void) { - return cpumask_of(0); + return cpu_online_mask; } /* @@ -170,7 +172,7 @@ static unsigned long set_apic_id(unsigned int id) static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb) { - return current_cpu_data.initial_apicid >> index_msb; + return initial_apicid >> index_msb; } static void x2apic_send_IPI_self(int vector) diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index a284359..a8989aa 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -27,11 +27,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -/* Start with all IRQs pointing to boot CPU. IRQ balancing will shift them. */ - +/* + * need to use more than cpu 0, because we need more vectors when + * MSI-X are used. + */ static const struct cpumask *x2apic_target_cpus(void) { - return cpumask_of(0); + return cpu_online_mask; } static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask) @@ -162,7 +164,7 @@ static unsigned long set_apic_id(unsigned int id) static int x2apic_phys_pkg_id(int initial_apicid, int index_msb) { - return current_cpu_data.initial_apicid >> index_msb; + return initial_apicid >> index_msb; } static void x2apic_send_IPI_self(int vector) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 096d19a..832e908 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -261,7 +261,7 @@ struct apic apic_x2apic_uv_x = { .apic_id_registered = uv_apic_id_registered, .irq_delivery_mode = dest_Fixed, - .irq_dest_mode = 1, /* logical */ + .irq_dest_mode = 0, /* physical */ .target_cpus = uv_target_cpus, .disable_esr = 0, @@ -362,12 +362,6 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) BUG(); } -static __init void map_low_mmrs(void) -{ - init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE); - init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE); -} - enum map_type {map_wb, map_uc}; static __init void map_high(char *id, unsigned long base, int shift, @@ -395,26 +389,6 @@ static __init void map_gru_high(int max_pnode) map_high("GRU", gru.s.base, shift, max_pnode, map_wb); } -static __init void map_config_high(int max_pnode) -{ - union uvh_rh_gam_cfg_overlay_config_mmr_u cfg; - int shift = UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT; - - cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR); - if (cfg.s.enable) - map_high("CONFIG", cfg.s.base, shift, max_pnode, map_uc); -} - -static __init void map_mmr_high(int max_pnode) -{ - union uvh_rh_gam_mmr_overlay_config_mmr_u mmr; - int shift = UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT; - - mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR); - if (mmr.s.enable) - map_high("MMR", mmr.s.base, shift, max_pnode, map_uc); -} - static __init void map_mmioh_high(int max_pnode) { union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh; @@ -566,8 +540,6 @@ void __init uv_system_init(void) unsigned long mmr_base, present, paddr; unsigned short pnode_mask; - map_low_mmrs(); - m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG); m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; @@ -591,6 +563,8 @@ void __init uv_system_init(void) bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades(); uv_blade_info = kmalloc(bytes, GFP_KERNEL); BUG_ON(!uv_blade_info); + for (blade = 0; blade < uv_num_possible_blades(); blade++) + uv_blade_info[blade].memory_nid = -1; get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size); @@ -629,6 +603,9 @@ void __init uv_system_init(void) lcpu = uv_blade_info[blade].nr_possible_cpus; uv_blade_info[blade].nr_possible_cpus++; + /* Any node on the blade, else will contain -1. */ + uv_blade_info[blade].memory_nid = nid; + uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base; uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size; uv_cpu_hub_info(cpu)->m_val = m_val; @@ -662,11 +639,10 @@ void __init uv_system_init(void) pnode = (paddr >> m_val) & pnode_mask; blade = boot_pnode_to_blade(pnode); uv_node_to_blade[nid] = blade; + max_pnode = max(pnode, max_pnode); } map_gru_high(max_pnode); - map_mmr_high(max_pnode); - map_config_high(max_pnode); map_mmioh_high(max_pnode); uv_cpu_init(); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 79302e9..442b550 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -811,7 +811,7 @@ static int apm_do_idle(void) u8 ret = 0; int idled = 0; int polling; - int err; + int err = 0; polling = !!(current_thread_info()->status & TS_POLLING); if (polling) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e2485b0..63fddcd 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -400,6 +400,13 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) level = cpuid_eax(1); if((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* + * Some BIOSes incorrectly force this feature, but only K8 + * revision D (model = 0x14) and later actually support it. + */ + if (c->x86_model < 0x14) + clear_cpu_cap(c, X86_FEATURE_LAHF_LM); } if (c->x86 == 0x10 || c->x86 == 0x11) set_cpu_cap(c, X86_FEATURE_REP_GOOD); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f1961c0..5ce60a8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -59,7 +59,30 @@ void __init setup_cpu_local_masks(void) alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); } -static const struct cpu_dev *this_cpu __cpuinitdata; +static void __cpuinit default_init(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_X86_64 + display_cacheinfo(c); +#else + /* Not much we can do here... */ + /* Check if at least it has cpuid */ + if (c->cpuid_level == -1) { + /* No cpuid. It must be an ancient CPU */ + if (c->x86 == 4) + strcpy(c->x86_model_id, "486"); + else if (c->x86 == 3) + strcpy(c->x86_model_id, "386"); + } +#endif +} + +static const struct cpu_dev __cpuinitconst default_cpu = { + .c_init = default_init, + .c_vendor = "Unknown", + .c_x86_vendor = X86_VENDOR_UNKNOWN, +}; + +static const struct cpu_dev *this_cpu __cpuinitdata = &default_cpu; DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { #ifdef CONFIG_X86_64 @@ -332,29 +355,6 @@ void switch_to_new_gdt(int cpu) static const struct cpu_dev *__cpuinitdata cpu_devs[X86_VENDOR_NUM] = {}; -static void __cpuinit default_init(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_X86_64 - display_cacheinfo(c); -#else - /* Not much we can do here... */ - /* Check if at least it has cpuid */ - if (c->cpuid_level == -1) { - /* No cpuid. It must be an ancient CPU */ - if (c->x86 == 4) - strcpy(c->x86_model_id, "486"); - else if (c->x86 == 3) - strcpy(c->x86_model_id, "386"); - } -#endif -} - -static const struct cpu_dev __cpuinitconst default_cpu = { - .c_init = default_init, - .c_vendor = "Unknown", - .c_x86_vendor = X86_VENDOR_UNKNOWN, -}; - static void __cpuinit get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index bff8dd1..8bc64cf 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -36,6 +36,7 @@ static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, thermal_throttle_count); +static DEFINE_PER_CPU(bool, thermal_throttle_active); static atomic_t therm_throt_en = ATOMIC_INIT(0); @@ -96,24 +97,27 @@ static int therm_throt_process(int curr) { unsigned int cpu = smp_processor_id(); __u64 tmp_jiffs = get_jiffies_64(); + bool was_throttled = __get_cpu_var(thermal_throttle_active); + bool is_throttled = __get_cpu_var(thermal_throttle_active) = curr; - if (curr) + if (is_throttled) __get_cpu_var(thermal_throttle_count)++; - if (time_before64(tmp_jiffs, __get_cpu_var(next_check))) + if (!(was_throttled ^ is_throttled) && + time_before64(tmp_jiffs, __get_cpu_var(next_check))) return 0; __get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL; /* if we just entered the thermal event */ - if (curr) { + if (is_throttled) { printk(KERN_CRIT "CPU%d: Temperature above threshold, " - "cpu clock throttled (total events = %lu)\n", cpu, - __get_cpu_var(thermal_throttle_count)); + "cpu clock throttled (total events = %lu)\n", + cpu, __get_cpu_var(thermal_throttle_count)); add_taint(TAINT_MACHINE_CHECK); - } else { - printk(KERN_CRIT "CPU%d: Temperature/speed normal\n", cpu); + } else if (was_throttled) { + printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu); } return 1; diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c index a7aa8f9..900332b 100644 --- a/arch/x86/kernel/cpu/perf_counter.c +++ b/arch/x86/kernel/cpu/perf_counter.c @@ -55,6 +55,7 @@ struct x86_pmu { int num_counters_fixed; int counter_bits; u64 counter_mask; + int apic; u64 max_period; u64 intel_ctrl; }; @@ -72,8 +73,8 @@ static const u64 p6_perfmon_event_map[] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0079, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, - [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0000, - [PERF_COUNT_HW_CACHE_MISSES] = 0x0000, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0f2e, + [PERF_COUNT_HW_CACHE_MISSES] = 0x012e, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4, [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5, [PERF_COUNT_HW_BUS_CYCLES] = 0x0062, @@ -613,6 +614,7 @@ static DEFINE_MUTEX(pmc_reserve_mutex); static bool reserve_pmc_hardware(void) { +#ifdef CONFIG_X86_LOCAL_APIC int i; if (nmi_watchdog == NMI_LOCAL_APIC) @@ -627,9 +629,11 @@ static bool reserve_pmc_hardware(void) if (!reserve_evntsel_nmi(x86_pmu.eventsel + i)) goto eventsel_fail; } +#endif return true; +#ifdef CONFIG_X86_LOCAL_APIC eventsel_fail: for (i--; i >= 0; i--) release_evntsel_nmi(x86_pmu.eventsel + i); @@ -644,10 +648,12 @@ perfctr_fail: enable_lapic_nmi_watchdog(); return false; +#endif } static void release_pmc_hardware(void) { +#ifdef CONFIG_X86_LOCAL_APIC int i; for (i = 0; i < x86_pmu.num_counters; i++) { @@ -657,6 +663,7 @@ static void release_pmc_hardware(void) if (nmi_watchdog == NMI_LOCAL_APIC) enable_lapic_nmi_watchdog(); +#endif } static void hw_perf_counter_destroy(struct perf_counter *counter) @@ -748,6 +755,15 @@ static int __hw_perf_counter_init(struct perf_counter *counter) hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; atomic64_set(&hwc->period_left, hwc->sample_period); + } else { + /* + * If we have a PMU initialized but no APIC + * interrupts, we cannot sample hardware + * counters (user-space has to fall back and + * sample via a hrtimer based software counter): + */ + if (!x86_pmu.apic) + return -EOPNOTSUPP; } counter->destroy = hw_perf_counter_destroy; @@ -1449,18 +1465,22 @@ void smp_perf_pending_interrupt(struct pt_regs *regs) void set_perf_counter_pending(void) { +#ifdef CONFIG_X86_LOCAL_APIC apic->send_IPI_self(LOCAL_PENDING_VECTOR); +#endif } void perf_counters_lapic_init(void) { - if (!x86_pmu_initialized()) +#ifdef CONFIG_X86_LOCAL_APIC + if (!x86_pmu.apic || !x86_pmu_initialized()) return; /* * Always use NMI for PMU */ apic_write(APIC_LVTPC, APIC_DM_NMI); +#endif } static int __kprobes @@ -1484,7 +1504,9 @@ perf_counter_nmi_handler(struct notifier_block *self, regs = args->regs; +#ifdef CONFIG_X86_LOCAL_APIC apic_write(APIC_LVTPC, APIC_DM_NMI); +#endif /* * Can't rely on the handled return value to say it was our NMI, two * counters could trigger 'simultaneously' raising two back-to-back NMIs. @@ -1515,6 +1537,7 @@ static struct x86_pmu p6_pmu = { .event_map = p6_pmu_event_map, .raw_event = p6_pmu_raw_event, .max_events = ARRAY_SIZE(p6_perfmon_event_map), + .apic = 1, .max_period = (1ULL << 31) - 1, .version = 0, .num_counters = 2, @@ -1541,6 +1564,7 @@ static struct x86_pmu intel_pmu = { .event_map = intel_pmu_event_map, .raw_event = intel_pmu_raw_event, .max_events = ARRAY_SIZE(intel_perfmon_event_map), + .apic = 1, /* * Intel PMCs cannot be accessed sanely above 32 bit width, * so we install an artificial 1<<31 period regardless of @@ -1564,6 +1588,7 @@ static struct x86_pmu amd_pmu = { .num_counters = 4, .counter_bits = 48, .counter_mask = (1ULL << 48) - 1, + .apic = 1, /* use highest bit to detect overflow */ .max_period = (1ULL << 47) - 1, }; @@ -1589,13 +1614,14 @@ static int p6_pmu_init(void) return -ENODEV; } + x86_pmu = p6_pmu; + if (!cpu_has_apic) { - pr_info("no Local APIC, try rebooting with lapic"); - return -ENODEV; + pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); + pr_info("no hardware sampling interrupt available.\n"); + x86_pmu.apic = 0; } - x86_pmu = p6_pmu; - return 0; } diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index 96f7ac0..fe26ba3 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -354,7 +354,7 @@ void __init efi_init(void) */ c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2); if (c16) { - for (i = 0; i < sizeof(vendor) && *c16; ++i) + for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i) vendor[i] = *c16++; vendor[i] = '\0'; } else @@ -512,7 +512,7 @@ void __init efi_enter_virtual_mode(void) && end_pfn <= max_pfn_mapped)) va = __va(md->phys_addr); else - va = efi_ioremap(md->phys_addr, size); + va = efi_ioremap(md->phys_addr, size, md->type); md->virt_addr = (u64) (unsigned long) va; diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c index 22c3b78..ac0621a 100644 --- a/arch/x86/kernel/efi_64.c +++ b/arch/x86/kernel/efi_64.c @@ -98,10 +98,14 @@ void __init efi_call_phys_epilog(void) early_runtime_code_mapping_set_exec(0); } -void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size) +void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size, + u32 type) { unsigned long last_map_pfn; + if (type == EFI_MEMORY_MAPPED_IO) + return ioremap(phys_addr, size); + last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size); if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) return NULL; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 8663afb..0d98a01 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -602,7 +602,11 @@ ignore_int: #endif iret -.section .cpuinit.data,"wa" +#ifndef CONFIG_HOTPLUG_CPU + __CPUINITDATA +#else + __REFDATA +#endif .align 4 ENTRY(initial_code) .long i386_start_kernel diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 5cf36c0..23c1679 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -19,12 +19,6 @@ DEFINE_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); -#ifdef CONFIG_X86_32 -static void pit_disable_clocksource(void); -#else -static inline void pit_disable_clocksource(void) { } -#endif - /* * HPET replaces the PIT, when enabled. So we need to know, which of * the two timers is used @@ -57,12 +51,10 @@ static void init_pit_timer(enum clock_event_mode mode, outb_pit(0, PIT_CH0); outb_pit(0, PIT_CH0); } - pit_disable_clocksource(); break; case CLOCK_EVT_MODE_ONESHOT: /* One shot setup */ - pit_disable_clocksource(); outb_pit(0x38, PIT_MODE); break; @@ -200,17 +192,6 @@ static struct clocksource pit_cs = { .shift = 20, }; -static void pit_disable_clocksource(void) -{ - /* - * Use mult to check whether it is registered or not - */ - if (pit_cs.mult) { - clocksource_unregister(&pit_cs); - pit_cs.mult = 0; - } -} - static int __init init_pit_clocksource(void) { /* diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 508e982..a06e8d1 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -3,6 +3,7 @@ #include <linux/init.h> #include <linux/pm.h> #include <linux/efi.h> +#include <linux/dmi.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -17,7 +18,6 @@ #include <asm/cpu.h> #ifdef CONFIG_X86_32 -# include <linux/dmi.h> # include <linux/ctype.h> # include <linux/mc146818rtc.h> #else @@ -404,6 +404,46 @@ EXPORT_SYMBOL(machine_real_restart); #endif /* CONFIG_X86_32 */ +/* + * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot + */ +static int __init set_pci_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_CF9) { + reboot_type = BOOT_CF9; + printk(KERN_INFO "%s series board detected. " + "Selecting PCI-method for reboots.\n", d->ident); + } + return 0; +} + +static struct dmi_system_id __initdata pci_reboot_dmi_table[] = { + { /* Handle problems with rebooting on Apple MacBook5 */ + .callback = set_pci_reboot, + .ident = "Apple MacBook5", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), + }, + }, + { /* Handle problems with rebooting on Apple MacBookPro5 */ + .callback = set_pci_reboot, + .ident = "Apple MacBookPro5", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"), + }, + }, + { } +}; + +static int __init pci_reboot_init(void) +{ + dmi_check_system(pci_reboot_dmi_table); + return 0; +} +core_initcall(pci_reboot_init); + static inline void kb_wait(void) { int i; diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 5d465b2..bf67dcb 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -178,7 +178,7 @@ static int set_rtc_mmss(unsigned long nowtime) } /* not static: needed by APM */ -unsigned long read_persistent_clock(void) +void read_persistent_clock(struct timespec *ts) { unsigned long retval, flags; @@ -186,7 +186,8 @@ unsigned long read_persistent_clock(void) retval = get_wallclock(); spin_unlock_irqrestore(&rtc_lock, flags); - return retval; + ts->tv_sec = retval; + ts->tv_nsec = 0; } int update_persistent_clock(struct timespec now) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6e1a368..fc3672a 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -275,15 +275,20 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) * use the TSC value at the transitions to calculate a pretty * good value for the TSC frequencty. */ +static inline int pit_verify_msb(unsigned char val) +{ + /* Ignore LSB */ + inb(0x42); + return inb(0x42) == val; +} + static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; u64 tsc = 0; for (count = 0; count < 50000; count++) { - /* Ignore LSB */ - inb(0x42); - if (inb(0x42) != val) + if (!pit_verify_msb(val)) break; tsc = get_cycles(); } @@ -336,8 +341,7 @@ static unsigned long quick_pit_calibrate(void) * to do that is to just read back the 16-bit counter * once from the PIT. */ - inb(0x42); - inb(0x42); + pit_verify_msb(0); if (pit_expect_msb(0xff, &tsc, &d1)) { for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) { @@ -348,8 +352,19 @@ static unsigned long quick_pit_calibrate(void) * Iterate until the error is less than 500 ppm */ delta -= tsc; - if (d1+d2 < delta >> 11) - goto success; + if (d1+d2 >= delta >> 11) + continue; + + /* + * Check the PIT one more time to verify that + * all TSC reads were stable wrt the PIT. + * + * This also guarantees serialization of the + * last cycle read ('d2') in pit_expect_msb. + */ + if (!pit_verify_msb(0xfe - i)) + break; + goto success; } } printk("Fast TSC calibration failed\n"); @@ -729,10 +744,16 @@ static cycle_t __vsyscall_fn vread_tsc(void) } #endif +static void resume_tsc(void) +{ + clocksource_tsc.cycle_last = 0; +} + static struct clocksource clocksource_tsc = { .name = "tsc", .rating = 300, .read = read_tsc, + .resume = resume_tsc, .mask = CLOCKSOURCE_MASK(64), .shift = 22, .flags = CLOCK_SOURCE_IS_CONTINUOUS | @@ -746,12 +767,14 @@ void mark_tsc_unstable(char *reason) { if (!tsc_unstable) { tsc_unstable = 1; - printk("Marking TSC unstable due to %s\n", reason); + printk(KERN_INFO "Marking TSC unstable due to %s\n", reason); /* Change only the rating, when not registered */ if (clocksource_tsc.mult) - clocksource_change_rating(&clocksource_tsc, 0); - else + clocksource_mark_unstable(&clocksource_tsc); + else { + clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE; clocksource_tsc.rating = 0; + } } } diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index b263423..95a7289 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -441,7 +441,7 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip, ap.ds = __USER_DS; ap.es = __USER_DS; ap.fs = __KERNEL_PERCPU; - ap.gs = 0; + ap.gs = __KERNEL_STACK_CANARY; ap.eflags = 0; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 59f31d2..78d185d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -393,8 +393,8 @@ SECTIONS #ifdef CONFIG_X86_32 -ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), - "kernel image bigger than KERNEL_IMAGE_SIZE") +. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), + "kernel image bigger than KERNEL_IMAGE_SIZE"); #else /* * Per-cpu symbols which need to be offset from __per_cpu_load @@ -407,12 +407,12 @@ INIT_PER_CPU(irq_stack_union); /* * Build-time check on the image size: */ -ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), - "kernel image bigger than KERNEL_IMAGE_SIZE") +. = ASSERT((_end - _text <= KERNEL_IMAGE_SIZE), + "kernel image bigger than KERNEL_IMAGE_SIZE"); #ifdef CONFIG_SMP -ASSERT((per_cpu__irq_stack_union == 0), - "irq_stack_union is not at start of per-cpu area"); +. = ASSERT((per_cpu__irq_stack_union == 0), + "irq_stack_union is not at start of per-cpu area"); #endif #endif /* CONFIG_X86_32 */ @@ -420,7 +420,7 @@ ASSERT((per_cpu__irq_stack_union == 0), #ifdef CONFIG_KEXEC #include <asm/kexec.h> -ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, - "kexec control code size is too big") +. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, + "kexec control code size is too big"); #endif diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 25ee06a..cf53a78 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -87,6 +87,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic; + vsyscall_gtod_data.wall_time_coarse = __current_kernel_time(); write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 4d6f0d2..21f68e0 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -104,6 +104,9 @@ static s64 __kpit_elapsed(struct kvm *kvm) ktime_t remaining; struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; + if (!ps->pit_timer.period) + return 0; + /* * The Counter does not stop when it reaches zero. In * Modes 0, 1, 4, and 5 the Counter ``wraps around'' to diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 7030b5f..0ef5bb2 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -489,16 +489,20 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage) * * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc * containing more mappings. + * + * Returns the number of rmap entries before the spte was added or zero if + * the spte was not added. + * */ -static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) +static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) { struct kvm_mmu_page *sp; struct kvm_rmap_desc *desc; unsigned long *rmapp; - int i; + int i, count = 0; if (!is_rmap_pte(*spte)) - return; + return count; gfn = unalias_gfn(vcpu->kvm, gfn); sp = page_header(__pa(spte)); sp->gfns[spte - sp->spt] = gfn; @@ -515,8 +519,10 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) } else { rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte); desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul); - while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) + while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) { desc = desc->more; + count += RMAP_EXT; + } if (desc->shadow_ptes[RMAP_EXT-1]) { desc->more = mmu_alloc_rmap_desc(vcpu); desc = desc->more; @@ -525,6 +531,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage) ; desc->shadow_ptes[i] = spte; } + return count; } static void rmap_desc_remove_entry(unsigned long *rmapp, @@ -754,6 +761,19 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp) return young; } +#define RMAP_RECYCLE_THRESHOLD 1000 + +static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage) +{ + unsigned long *rmapp; + + gfn = unalias_gfn(vcpu->kvm, gfn); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage); + + kvm_unmap_rmapp(vcpu->kvm, rmapp); + kvm_flush_remote_tlbs(vcpu->kvm); +} + int kvm_age_hva(struct kvm *kvm, unsigned long hva) { return kvm_handle_hva(kvm, hva, kvm_age_rmapp); @@ -1407,24 +1427,25 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) */ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages) { + int used_pages; + + used_pages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages; + used_pages = max(0, used_pages); + /* * If we set the number of mmu pages to be smaller be than the * number of actived pages , we must to free some mmu pages before we * change the value */ - if ((kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages) > - kvm_nr_mmu_pages) { - int n_used_mmu_pages = kvm->arch.n_alloc_mmu_pages - - kvm->arch.n_free_mmu_pages; - - while (n_used_mmu_pages > kvm_nr_mmu_pages) { + if (used_pages > kvm_nr_mmu_pages) { + while (used_pages > kvm_nr_mmu_pages) { struct kvm_mmu_page *page; page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); kvm_mmu_zap_page(kvm, page); - n_used_mmu_pages--; + used_pages--; } kvm->arch.n_free_mmu_pages = 0; } @@ -1740,6 +1761,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, { int was_rmapped = 0; int was_writeble = is_writeble_pte(*shadow_pte); + int rmap_count; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", @@ -1781,9 +1803,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, page_header_update_slot(vcpu->kvm, shadow_pte, gfn); if (!was_rmapped) { - rmap_add(vcpu, shadow_pte, gfn, largepage); + rmap_count = rmap_add(vcpu, shadow_pte, gfn, largepage); if (!is_rmap_pte(*shadow_pte)) kvm_release_pfn_clean(pfn); + if (rmap_count > RMAP_RECYCLE_THRESHOLD) + rmap_recycle(vcpu, gfn, largepage); } else { if (was_writeble) kvm_release_pfn_dirty(pfn); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 71510e0..b1f658a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -711,6 +711,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) svm->vmcb->control.tsc_offset += delta; vcpu->cpu = cpu; kvm_migrate_timers(vcpu); + svm->asid_generation = 0; } for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) @@ -1031,7 +1032,6 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; } - svm->vcpu.cpu = svm_data->cpu; svm->asid_generation = svm_data->asid_generation; svm->vmcb->control.asid = svm_data->next_asid++; } @@ -2300,8 +2300,8 @@ static void pre_svm_run(struct vcpu_svm *svm) struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu); svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; - if (svm->vcpu.cpu != cpu || - svm->asid_generation != svm_data->asid_generation) + /* FIXME: handle wraparound of asid_generation */ + if (svm->asid_generation != svm_data->asid_generation) new_asid(svm, svm_data); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 356a0ce..29f9129 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3157,8 +3157,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); enum emulation_result err = EMULATE_DONE; - preempt_enable(); local_irq_enable(); + preempt_enable(); while (!guest_state_valid(vcpu)) { err = emulate_instruction(vcpu, kvm_run, 0, 0, 0); @@ -3168,7 +3168,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, if (err != EMULATE_DONE) { kvm_report_emulation_failure(vcpu, "emulation failure"); - return; + break; } if (signal_pending(current)) @@ -3177,8 +3177,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, schedule(); } - local_irq_disable(); preempt_disable(); + local_irq_disable(); vmx->invalid_state_emulation_result = err; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fe5474a..3d45290 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -704,11 +704,48 @@ static bool msr_mtrr_valid(unsigned msr) return false; } +static bool valid_pat_type(unsigned t) +{ + return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ +} + +static bool valid_mtrr_type(unsigned t) +{ + return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ +} + +static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int i; + + if (!msr_mtrr_valid(msr)) + return false; + + if (msr == MSR_IA32_CR_PAT) { + for (i = 0; i < 8; i++) + if (!valid_pat_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } else if (msr == MSR_MTRRdefType) { + if (data & ~0xcff) + return false; + return valid_mtrr_type(data & 0xff); + } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { + for (i = 0; i < 8 ; i++) + if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } + + /* variable MTRRs */ + return valid_mtrr_type(data & 0xff); +} + static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) { u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - if (!msr_mtrr_valid(msr)) + if (!mtrr_valid(vcpu, msr, data)) return 1; if (msr == MSR_MTRRdefType) { @@ -1079,14 +1116,13 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) goto out; r = -E2BIG; - if (n < num_msrs_to_save) + if (n < msr_list.nmsrs) goto out; r = -EFAULT; if (copy_to_user(user_msr_list->indices, &msrs_to_save, num_msrs_to_save * sizeof(u32))) goto out; - if (copy_to_user(user_msr_list->indices - + num_msrs_to_save * sizeof(u32), + if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, ARRAY_SIZE(emulated_msrs) * sizeof(u32))) goto out; diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 1440b9c..caa24ac 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -89,16 +89,13 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) rv.msrs = msrs; rv.msr_no = msr_no; - preempt_disable(); - /* - * FIXME: handle the CPU we're executing on separately for now until - * smp_call_function_many has been fixed to not skip it. - */ - this_cpu = raw_smp_processor_id(); - smp_call_function_single(this_cpu, __rdmsr_on_cpu, &rv, 1); + this_cpu = get_cpu(); + + if (cpumask_test_cpu(this_cpu, mask)) + __rdmsr_on_cpu(&rv); smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1); - preempt_enable(); + put_cpu(); } EXPORT_SYMBOL(rdmsr_on_cpus); @@ -121,16 +118,13 @@ void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs) rv.msrs = msrs; rv.msr_no = msr_no; - preempt_disable(); - /* - * FIXME: handle the CPU we're executing on separately for now until - * smp_call_function_many has been fixed to not skip it. - */ - this_cpu = raw_smp_processor_id(); - smp_call_function_single(this_cpu, __wrmsr_on_cpu, &rv, 1); + this_cpu = get_cpu(); + + if (cpumask_test_cpu(this_cpu, mask)) + __wrmsr_on_cpu(&rv); smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1); - preempt_enable(); + put_cpu(); } EXPORT_SYMBOL(wrmsr_on_cpus); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 1b734d7..7e600c1 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -591,9 +591,12 @@ static int __change_page_attr(struct cpa_data *cpa, int primary) unsigned int level; pte_t *kpte, old_pte; - if (cpa->flags & CPA_PAGES_ARRAY) - address = (unsigned long)page_address(cpa->pages[cpa->curpage]); - else if (cpa->flags & CPA_ARRAY) + if (cpa->flags & CPA_PAGES_ARRAY) { + struct page *page = cpa->pages[cpa->curpage]; + if (unlikely(PageHighMem(page))) + return 0; + address = (unsigned long)page_address(page); + } else if (cpa->flags & CPA_ARRAY) address = cpa->vaddr[cpa->curpage]; else address = *cpa->vaddr; @@ -697,9 +700,12 @@ static int cpa_process_alias(struct cpa_data *cpa) * No need to redo, when the primary call touched the direct * mapping already: */ - if (cpa->flags & CPA_PAGES_ARRAY) - vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]); - else if (cpa->flags & CPA_ARRAY) + if (cpa->flags & CPA_PAGES_ARRAY) { + struct page *page = cpa->pages[cpa->curpage]; + if (unlikely(PageHighMem(page))) + return 0; + vaddr = (unsigned long)page_address(page); + } else if (cpa->flags & CPA_ARRAY) vaddr = cpa->vaddr[cpa->curpage]; else vaddr = *cpa->vaddr; @@ -997,12 +1003,15 @@ EXPORT_SYMBOL(set_memory_array_uc); int _set_memory_wc(unsigned long addr, int numpages) { int ret; + unsigned long addr_copy = addr; + ret = change_page_attr_set(&addr, numpages, __pgprot(_PAGE_CACHE_UC_MINUS), 0); - if (!ret) { - ret = change_page_attr_set(&addr, numpages, - __pgprot(_PAGE_CACHE_WC), 0); + ret = change_page_attr_set_clr(&addr_copy, numpages, + __pgprot(_PAGE_CACHE_WC), + __pgprot(_PAGE_CACHE_MASK), + 0, 0, NULL); } return ret; } @@ -1119,7 +1128,9 @@ int set_pages_array_uc(struct page **pages, int addrinarray) int free_idx; for (i = 0; i < addrinarray; i++) { - start = (unsigned long)page_address(pages[i]); + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) goto err_out; @@ -1132,7 +1143,9 @@ int set_pages_array_uc(struct page **pages, int addrinarray) err_out: free_idx = i; for (i = 0; i < free_idx; i++) { - start = (unsigned long)page_address(pages[i]); + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; free_memtype(start, end); } @@ -1161,7 +1174,9 @@ int set_pages_array_wb(struct page **pages, int addrinarray) return retval; for (i = 0; i < addrinarray; i++) { - start = (unsigned long)page_address(pages[i]); + if (PageHighMem(pages[i])) + continue; + start = page_to_pfn(pages[i]) << PAGE_SHIFT; end = start + PAGE_SIZE; free_memtype(start, end); } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index af8f965..ed34f5e 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -329,7 +329,6 @@ void __init reserve_top_address(unsigned long reserve) printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", (int)-reserve); __FIXADDR_TOP = -reserve - PAGE_SIZE; - __VMALLOC_RESERVE += reserve; #endif } diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 6a40b78b..ee55754 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -86,14 +86,47 @@ notrace static noinline int do_monotonic(struct timespec *ts) return 0; } +notrace static noinline int do_realtime_coarse(struct timespec *ts) +{ + unsigned long seq; + do { + seq = read_seqbegin(>od->lock); + ts->tv_sec = gtod->wall_time_coarse.tv_sec; + ts->tv_nsec = gtod->wall_time_coarse.tv_nsec; + } while (unlikely(read_seqretry(>od->lock, seq))); + return 0; +} + +notrace static noinline int do_monotonic_coarse(struct timespec *ts) +{ + unsigned long seq, ns, secs; + do { + seq = read_seqbegin(>od->lock); + secs = gtod->wall_time_coarse.tv_sec; + ns = gtod->wall_time_coarse.tv_nsec; + secs += gtod->wall_to_monotonic.tv_sec; + ns += gtod->wall_to_monotonic.tv_nsec; + } while (unlikely(read_seqretry(>od->lock, seq))); + vset_normalized_timespec(ts, secs, ns); + return 0; +} + notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts) { - if (likely(gtod->sysctl_enabled && gtod->clock.vread)) + if (likely(gtod->sysctl_enabled)) switch (clock) { case CLOCK_REALTIME: - return do_realtime(ts); + if (likely(gtod->clock.vread)) + return do_realtime(ts); + break; case CLOCK_MONOTONIC: - return do_monotonic(ts); + if (likely(gtod->clock.vread)) + return do_monotonic(ts); + break; + case CLOCK_REALTIME_COARSE: + return do_realtime_coarse(ts); + case CLOCK_MONOTONIC_COARSE: + return do_monotonic_coarse(ts); } return vdso_fallback_gettime(clock, ts); } diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 8848120..19085ff 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -59,9 +59,8 @@ static struct irqaction timer_irqaction = { void __init time_init(void) { - xtime.tv_nsec = 0; - xtime.tv_sec = read_persistent_clock(); - + /* FIXME: xtime&wall_to_monotonic are set in timekeeping_init. */ + read_persistent_clock(&xtime); set_normalized_timespec(&wall_to_monotonic, -xtime.tv_sec, -xtime.tv_nsec); diff --git a/block/Kconfig b/block/Kconfig index 95a86ad..9be0b56 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -48,9 +48,9 @@ config LBDAF If unsure, say Y. config BLK_DEV_BSG - bool "Block layer SG support v4 (EXPERIMENTAL)" - depends on EXPERIMENTAL - ---help--- + bool "Block layer SG support v4" + default y + help Saying Y here will enable generic SG (SCSI generic) v4 support for any block device. @@ -60,7 +60,10 @@ config BLK_DEV_BSG protocols (e.g. Task Management Functions and SMP in Serial Attached SCSI). - If unsure, say N. + This option is required by recent UDEV versions to properly + access device serial numbers, etc. + + If unsure, say Y. config BLK_DEV_INTEGRITY bool "Block layer data integrity support" diff --git a/block/blk-settings.c b/block/blk-settings.c index 8a3ea3b..476d870 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -7,6 +7,7 @@ #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/bootmem.h> /* for max_pfn/max_low_pfn */ +#include <linux/gcd.h> #include "blk.h" @@ -384,8 +385,8 @@ void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset) EXPORT_SYMBOL(blk_queue_alignment_offset); /** - * blk_queue_io_min - set minimum request size for the queue - * @q: the request queue for the device + * blk_limits_io_min - set minimum request size for a device + * @limits: the queue limits * @min: smallest I/O size in bytes * * Description: @@ -394,15 +395,35 @@ EXPORT_SYMBOL(blk_queue_alignment_offset); * smallest I/O the device can perform without incurring a performance * penalty. */ -void blk_queue_io_min(struct request_queue *q, unsigned int min) +void blk_limits_io_min(struct queue_limits *limits, unsigned int min) { - q->limits.io_min = min; + limits->io_min = min; - if (q->limits.io_min < q->limits.logical_block_size) - q->limits.io_min = q->limits.logical_block_size; + if (limits->io_min < limits->logical_block_size) + limits->io_min = limits->logical_block_size; - if (q->limits.io_min < q->limits.physical_block_size) - q->limits.io_min = q->limits.physical_block_size; + if (limits->io_min < limits->physical_block_size) + limits->io_min = limits->physical_block_size; +} +EXPORT_SYMBOL(blk_limits_io_min); + +/** + * blk_queue_io_min - set minimum request size for the queue + * @q: the request queue for the device + * @min: smallest I/O size in bytes + * + * Description: + * Storage devices may report a granularity or preferred minimum I/O + * size which is the smallest request the device can perform without + * incurring a performance penalty. For disk drives this is often the + * physical block size. For RAID arrays it is often the stripe chunk + * size. A properly aligned multiple of minimum_io_size is the + * preferred request size for workloads where a high number of I/O + * operations is desired. + */ +void blk_queue_io_min(struct request_queue *q, unsigned int min) +{ + blk_limits_io_min(&q->limits, min); } EXPORT_SYMBOL(blk_queue_io_min); @@ -412,8 +433,12 @@ EXPORT_SYMBOL(blk_queue_io_min); * @opt: optimal request size in bytes * * Description: - * Drivers can call this function to set the preferred I/O request - * size for devices that report such a value. + * Storage devices may report an optimal I/O size, which is the + * device's preferred unit for sustained I/O. This is rarely reported + * for disk drives. For RAID arrays it is usually the stripe width or + * the internal track size. A properly aligned multiple of + * optimal_io_size is the preferred request size for workloads where + * sustained throughput is desired. */ void blk_queue_io_opt(struct request_queue *q, unsigned int opt) { @@ -433,27 +458,7 @@ EXPORT_SYMBOL(blk_queue_io_opt); **/ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b) { - /* zero is "infinity" */ - t->limits.max_sectors = min_not_zero(queue_max_sectors(t), - queue_max_sectors(b)); - - t->limits.max_hw_sectors = min_not_zero(queue_max_hw_sectors(t), - queue_max_hw_sectors(b)); - - t->limits.seg_boundary_mask = min_not_zero(queue_segment_boundary(t), - queue_segment_boundary(b)); - - t->limits.max_phys_segments = min_not_zero(queue_max_phys_segments(t), - queue_max_phys_segments(b)); - - t->limits.max_hw_segments = min_not_zero(queue_max_hw_segments(t), - queue_max_hw_segments(b)); - - t->limits.max_segment_size = min_not_zero(queue_max_segment_size(t), - queue_max_segment_size(b)); - - t->limits.logical_block_size = max(queue_logical_block_size(t), - queue_logical_block_size(b)); + blk_stack_limits(&t->limits, &b->limits, 0); if (!t->queue_lock) WARN_ON_ONCE(1); @@ -523,6 +528,16 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, return -1; } + /* Find lcm() of optimal I/O size */ + if (t->io_opt && b->io_opt) + t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt); + else if (b->io_opt) + t->io_opt = b->io_opt; + + /* Verify that optimal I/O size is a multiple of io_min */ + if (t->io_min && t->io_opt % t->io_min) + return -1; + return 0; } EXPORT_SYMBOL(blk_stack_limits); diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 7a0f4aa..9a62224 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -38,6 +38,9 @@ #define _COMPONENT ACPI_MEMORY_DEVICE_COMPONENT +#undef PREFIX +#define PREFIX "ACPI:memory_hp:" + ACPI_MODULE_NAME("acpi_memhotplug"); MODULE_AUTHOR("Naveen B S <naveen.b.s@intel.com>"); MODULE_DESCRIPTION("Hotplug Mem Driver"); @@ -153,6 +156,7 @@ acpi_memory_get_device(acpi_handle handle, acpi_handle phandle; struct acpi_device *device = NULL; struct acpi_device *pdevice = NULL; + int result; if (!acpi_bus_get_device(handle, &device) && device) @@ -165,9 +169,9 @@ acpi_memory_get_device(acpi_handle handle, } /* Get the parent device */ - status = acpi_bus_get_device(phandle, &pdevice); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Cannot get acpi bus device")); + result = acpi_bus_get_device(phandle, &pdevice); + if (result) { + printk(KERN_WARNING PREFIX "Cannot get acpi bus device"); return -EINVAL; } @@ -175,9 +179,9 @@ acpi_memory_get_device(acpi_handle handle, * Now add the notified device. This creates the acpi_device * and invokes .add function */ - status = acpi_bus_add(&device, pdevice, handle, ACPI_BUS_TYPE_DEVICE); - if (ACPI_FAILURE(status)) { - ACPI_EXCEPTION((AE_INFO, status, "Cannot add acpi bus")); + result = acpi_bus_add(&device, pdevice, handle, ACPI_BUS_TYPE_DEVICE); + if (result) { + printk(KERN_WARNING PREFIX "Cannot add acpi bus"); return -EINVAL; } @@ -238,7 +242,12 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) num_enabled++; continue; } - + /* + * If the memory block size is zero, please ignore it. + * Don't try to do the following memory hotplug flowchart. + */ + if (!info->length) + continue; if (node < 0) node = memory_add_physaddr_to_nid(info->start_addr); @@ -253,8 +262,15 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) mem_device->state = MEMORY_INVALID_STATE; return -EINVAL; } - - return result; + /* + * Sometimes the memory device will contain several memory blocks. + * When one memory block is hot-added to the system memory, it will + * be regarded as a success. + * Otherwise if the last memory block can't be hot-added to the system + * memory, it will be failure and the memory device can't be bound with + * driver. + */ + return 0; } static int acpi_memory_powerdown_device(struct acpi_memory_device *mem_device) diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h index 544dcf8..eb6f038 100644 --- a/drivers/acpi/acpica/acobject.h +++ b/drivers/acpi/acpica/acobject.h @@ -97,6 +97,7 @@ #define AOPOBJ_OBJECT_INITIALIZED 0x08 #define AOPOBJ_SETUP_COMPLETE 0x10 #define AOPOBJ_SINGLE_DATUM 0x20 +#define AOPOBJ_INVALID 0x40 /* Used if host OS won't allow an op_region address */ /****************************************************************************** * diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c index 584d766..b79978f 100644 --- a/drivers/acpi/acpica/dsopcode.c +++ b/drivers/acpi/acpica/dsopcode.c @@ -397,6 +397,30 @@ acpi_status acpi_ds_get_region_arguments(union acpi_operand_object *obj_desc) status = acpi_ds_execute_arguments(node, acpi_ns_get_parent_node(node), extra_desc->extra.aml_length, extra_desc->extra.aml_start); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + + /* Validate the region address/length via the host OS */ + + status = acpi_os_validate_address(obj_desc->region.space_id, + obj_desc->region.address, + (acpi_size) obj_desc->region.length, + acpi_ut_get_node_name(node)); + + if (ACPI_FAILURE(status)) { + /* + * Invalid address/length. We will emit an error message and mark + * the region as invalid, so that it will cause an additional error if + * it is ever used. Then return AE_OK. + */ + ACPI_EXCEPTION((AE_INFO, status, + "During address validation of OpRegion [%4.4s]", + node->name.ascii)); + obj_desc->common.flags |= AOPOBJ_INVALID; + status = AE_OK; + } + return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c index d4075b8..6687be1 100644 --- a/drivers/acpi/acpica/exfldio.c +++ b/drivers/acpi/acpica/exfldio.c @@ -113,6 +113,12 @@ acpi_ex_setup_region(union acpi_operand_object *obj_desc, } } + /* Exit if Address/Length have been disallowed by the host OS */ + + if (rgn_desc->common.flags & AOPOBJ_INVALID) { + return_ACPI_STATUS(AE_AML_ILLEGAL_ADDRESS); + } + /* * Exit now for SMBus address space, it has a non-linear address space * and the request cannot be directly validated diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 7167071..5691f16 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -189,11 +189,36 @@ acpi_status __init acpi_os_initialize(void) return AE_OK; } +static void bind_to_cpu0(struct work_struct *work) +{ + set_cpus_allowed(current, cpumask_of_cpu(0)); + kfree(work); +} + +static void bind_workqueue(struct workqueue_struct *wq) +{ + struct work_struct *work; + + work = kzalloc(sizeof(struct work_struct), GFP_KERNEL); + INIT_WORK(work, bind_to_cpu0); + queue_work(wq, work); +} + acpi_status acpi_os_initialize1(void) { + /* + * On some machines, a software-initiated SMI causes corruption unless + * the SMI runs on CPU 0. An SMI can be initiated by any AML, but + * typically it's done in GPE-related methods that are run via + * workqueues, so we can avoid the known corruption cases by binding + * the workqueues to CPU 0. + */ kacpid_wq = create_singlethread_workqueue("kacpid"); + bind_workqueue(kacpid_wq); kacpi_notify_wq = create_singlethread_workqueue("kacpi_notify"); + bind_workqueue(kacpi_notify_wq); kacpi_hotplug_wq = create_singlethread_workqueue("kacpi_hotplug"); + bind_workqueue(kacpi_hotplug_wq); BUG_ON(!kacpid_wq); BUG_ON(!kacpi_notify_wq); BUG_ON(!kacpi_hotplug_wq); diff --git a/drivers/acpi/system.c b/drivers/acpi/system.c index 0944dae..9c61ab2 100644 --- a/drivers/acpi/system.c +++ b/drivers/acpi/system.c @@ -121,7 +121,7 @@ static void acpi_table_attr_init(struct acpi_table_attr *table_attr, table_attr->attr.size = 0; table_attr->attr.read = acpi_table_show; table_attr->attr.attr.name = table_attr->name; - table_attr->attr.attr.mode = 0444; + table_attr->attr.attr.mode = 0400; return; } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 958c1fa..fe3eba5 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -219,6 +219,8 @@ enum { AHCI_HFLAG_SECT255 = (1 << 8), /* max 255 sectors */ AHCI_HFLAG_YES_NCQ = (1 << 9), /* force NCQ cap on */ AHCI_HFLAG_NO_SUSPEND = (1 << 10), /* don't suspend */ + AHCI_HFLAG_SRST_TOUT_IS_OFFLINE = (1 << 11), /* treat SRST timeout as + link offline */ /* ap->flags bits */ @@ -1663,6 +1665,7 @@ static int ahci_do_softreset(struct ata_link *link, unsigned int *class, int (*check_ready)(struct ata_link *link)) { struct ata_port *ap = link->ap; + struct ahci_host_priv *hpriv = ap->host->private_data; const char *reason = NULL; unsigned long now, msecs; struct ata_taskfile tf; @@ -1701,12 +1704,21 @@ static int ahci_do_softreset(struct ata_link *link, unsigned int *class, /* wait for link to become ready */ rc = ata_wait_after_reset(link, deadline, check_ready); - /* link occupied, -ENODEV too is an error */ - if (rc) { + if (rc == -EBUSY && hpriv->flags & AHCI_HFLAG_SRST_TOUT_IS_OFFLINE) { + /* + * Workaround for cases where link online status can't + * be trusted. Treat device readiness timeout as link + * offline. + */ + ata_link_printk(link, KERN_INFO, + "device not ready, treating as offline\n"); + *class = ATA_DEV_NONE; + } else if (rc) { + /* link occupied, -ENODEV too is an error */ reason = "device not ready"; goto fail; - } - *class = ahci_dev_classify(ap); + } else + *class = ahci_dev_classify(ap); DPRINTK("EXIT, class=%u\n", *class); return 0; @@ -1773,7 +1785,8 @@ static int ahci_sb600_softreset(struct ata_link *link, unsigned int *class, irq_sts = readl(port_mmio + PORT_IRQ_STAT); if (irq_sts & PORT_IRQ_BAD_PMP) { ata_link_printk(link, KERN_WARNING, - "failed due to HW bug, retry pmp=0\n"); + "applying SB600 PMP SRST workaround " + "and retrying\n"); rc = ahci_do_softreset(link, class, 0, deadline, ahci_check_ready); } @@ -2726,6 +2739,56 @@ static bool ahci_broken_suspend(struct pci_dev *pdev) return !ver || strcmp(ver, dmi->driver_data) < 0; } +static bool ahci_broken_online(struct pci_dev *pdev) +{ +#define ENCODE_BUSDEVFN(bus, slot, func) \ + (void *)(unsigned long)(((bus) << 8) | PCI_DEVFN((slot), (func))) + static const struct dmi_system_id sysids[] = { + /* + * There are several gigabyte boards which use + * SIMG5723s configured as hardware RAID. Certain + * 5723 firmware revisions shipped there keep the link + * online but fail to answer properly to SRST or + * IDENTIFY when no device is attached downstream + * causing libata to retry quite a few times leading + * to excessive detection delay. + * + * As these firmwares respond to the second reset try + * with invalid device signature, considering unknown + * sig as offline works around the problem acceptably. + */ + { + .ident = "EP45-DQ6", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, + "Gigabyte Technology Co., Ltd."), + DMI_MATCH(DMI_BOARD_NAME, "EP45-DQ6"), + }, + .driver_data = ENCODE_BUSDEVFN(0x0a, 0x00, 0), + }, + { + .ident = "EP45-DS5", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, + "Gigabyte Technology Co., Ltd."), + DMI_MATCH(DMI_BOARD_NAME, "EP45-DS5"), + }, + .driver_data = ENCODE_BUSDEVFN(0x03, 0x00, 0), + }, + { } /* terminate list */ + }; +#undef ENCODE_BUSDEVFN + const struct dmi_system_id *dmi = dmi_first_match(sysids); + unsigned int val; + + if (!dmi) + return false; + + val = (unsigned long)dmi->driver_data; + + return pdev->bus->number == (val >> 8) && pdev->devfn == (val & 0xff); +} + static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { static int printed_version; @@ -2841,6 +2904,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) "BIOS update required for suspend/resume\n"); } + if (ahci_broken_online(pdev)) { + hpriv->flags |= AHCI_HFLAG_SRST_TOUT_IS_OFFLINE; + dev_info(&pdev->dev, + "online status unreliable, applying workaround\n"); + } + /* CAP.NP sometimes indicate the index of the last enabled * port, at other times, that of the last possible port, so * determining the maximum port number requires looking at diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8ac98ff..072ba5e 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4302,6 +4302,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_HORKAGE_BROKEN_HPA }, { "MAXTOR 6L080L4", "A93.0500", ATA_HORKAGE_BROKEN_HPA }, + /* this one allows HPA unlocking but fails IOs on the area */ + { "OCZ-VERTEX", "1.30", ATA_HORKAGE_BROKEN_HPA }, + /* Devices which report 1 sector over size HPA */ { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE, }, { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE, }, diff --git a/drivers/ata/pata_at91.c b/drivers/ata/pata_at91.c index 5702aff..41c94b1 100644 --- a/drivers/ata/pata_at91.c +++ b/drivers/ata/pata_at91.c @@ -250,7 +250,7 @@ static int __devinit pata_at91_probe(struct platform_device *pdev) ata_port_desc(ap, "no IRQ, using PIO polling"); } - info = kzalloc(sizeof(*info), GFP_KERNEL); + info = devm_kzalloc(dev, sizeof(*info), GFP_KERNEL); if (!info) { dev_err(dev, "failed to allocate memory for private data\n"); @@ -275,7 +275,7 @@ static int __devinit pata_at91_probe(struct platform_device *pdev) if (!info->ide_addr) { dev_err(dev, "failed to map IO base\n"); ret = -ENOMEM; - goto err_ide_ioremap; + goto err_put; } info->alt_addr = devm_ioremap(dev, @@ -284,7 +284,7 @@ static int __devinit pata_at91_probe(struct platform_device *pdev) if (!info->alt_addr) { dev_err(dev, "failed to map CTL base\n"); ret = -ENOMEM; - goto err_alt_ioremap; + goto err_put; } ap->ioaddr.cmd_addr = info->ide_addr; @@ -303,13 +303,8 @@ static int __devinit pata_at91_probe(struct platform_device *pdev) irq ? ata_sff_interrupt : NULL, irq_flags, &pata_at91_sht); -err_alt_ioremap: - devm_iounmap(dev, info->ide_addr); - -err_ide_ioremap: +err_put: clk_put(info->mck); - kfree(info); - return ret; } @@ -317,7 +312,6 @@ static int __devexit pata_at91_remove(struct platform_device *pdev) { struct ata_host *host = dev_get_drvdata(&pdev->dev); struct at91_ide_info *info; - struct device *dev = &pdev->dev; if (!host) return 0; @@ -328,11 +322,8 @@ static int __devexit pata_at91_remove(struct platform_device *pdev) if (!info) return 0; - devm_iounmap(dev, info->ide_addr); - devm_iounmap(dev, info->alt_addr); clk_put(info->mck); - kfree(info); return 0; } diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c index bec0b8a..4591556 100644 --- a/drivers/ata/pata_atiixp.c +++ b/drivers/ata/pata_atiixp.c @@ -1,6 +1,7 @@ /* * pata_atiixp.c - ATI PATA for new ATA layer * (C) 2005 Red Hat Inc + * (C) 2009 Bartlomiej Zolnierkiewicz * * Based on * @@ -61,20 +62,19 @@ static void atiixp_set_pio_timing(struct ata_port *ap, struct ata_device *adev, struct pci_dev *pdev = to_pci_dev(ap->host->dev); int dn = 2 * ap->port_no + adev->devno; - - /* Check this is correct - the order is odd in both drivers */ int timing_shift = (16 * ap->port_no) + 8 * (adev->devno ^ 1); - u16 pio_mode_data, pio_timing_data; + u32 pio_timing_data; + u16 pio_mode_data; pci_read_config_word(pdev, ATIIXP_IDE_PIO_MODE, &pio_mode_data); pio_mode_data &= ~(0x7 << (4 * dn)); pio_mode_data |= pio << (4 * dn); pci_write_config_word(pdev, ATIIXP_IDE_PIO_MODE, pio_mode_data); - pci_read_config_word(pdev, ATIIXP_IDE_PIO_TIMING, &pio_timing_data); + pci_read_config_dword(pdev, ATIIXP_IDE_PIO_TIMING, &pio_timing_data); pio_timing_data &= ~(0xFF << timing_shift); pio_timing_data |= (pio_timings[pio] << timing_shift); - pci_write_config_word(pdev, ATIIXP_IDE_PIO_TIMING, pio_timing_data); + pci_write_config_dword(pdev, ATIIXP_IDE_PIO_TIMING, pio_timing_data); } /** @@ -119,16 +119,17 @@ static void atiixp_set_dmamode(struct ata_port *ap, struct ata_device *adev) udma_mode_data |= dma << (4 * dn); pci_write_config_word(pdev, ATIIXP_IDE_UDMA_MODE, udma_mode_data); } else { - u16 mwdma_timing_data; - /* Check this is correct - the order is odd in both drivers */ int timing_shift = (16 * ap->port_no) + 8 * (adev->devno ^ 1); + u32 mwdma_timing_data; dma -= XFER_MW_DMA_0; - pci_read_config_word(pdev, ATIIXP_IDE_MWDMA_TIMING, &mwdma_timing_data); + pci_read_config_dword(pdev, ATIIXP_IDE_MWDMA_TIMING, + &mwdma_timing_data); mwdma_timing_data &= ~(0xFF << timing_shift); mwdma_timing_data |= (mwdma_timings[dma] << timing_shift); - pci_write_config_word(pdev, ATIIXP_IDE_MWDMA_TIMING, mwdma_timing_data); + pci_write_config_dword(pdev, ATIIXP_IDE_MWDMA_TIMING, + mwdma_timing_data); } /* * We must now look at the PIO mode situation. We may need to diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index b2d11f3..86a4058 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -602,6 +602,7 @@ MODULE_VERSION(DRV_VERSION); static int adma_enabled; static int swncq_enabled = 1; +static int msi_enabled; static void nv_adma_register_mode(struct ata_port *ap) { @@ -2459,6 +2460,11 @@ static int nv_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } else if (type == SWNCQ) nv_swncq_host_init(host); + if (msi_enabled) { + dev_printk(KERN_NOTICE, &pdev->dev, "Using MSI\n"); + pci_enable_msi(pdev); + } + pci_set_master(pdev); return ata_host_activate(host, pdev->irq, ipriv->irq_handler, IRQF_SHARED, ipriv->sht); @@ -2558,4 +2564,6 @@ module_param_named(adma, adma_enabled, bool, 0444); MODULE_PARM_DESC(adma, "Enable use of ADMA (Default: false)"); module_param_named(swncq, swncq_enabled, bool, 0444); MODULE_PARM_DESC(swncq, "Enable use of SWNCQ (Default: true)"); +module_param_named(msi, msi_enabled, bool, 0444); +MODULE_PARM_DESC(msi, "Enable use of MSI (Default: false)"); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 81cb01b..456594b 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -483,9 +483,6 @@ int platform_driver_register(struct platform_driver *drv) drv->driver.remove = platform_drv_remove; if (drv->shutdown) drv->driver.shutdown = platform_drv_shutdown; - if (drv->suspend || drv->resume) - pr_warning("Platform driver '%s' needs updating - please use " - "dev_pm_ops\n", drv->driver.name); return driver_register(&drv->driver); } diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index f4bb43f..e077701 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -225,7 +225,7 @@ static const struct agp_bridge_driver parisc_agp_driver = { .configure = parisc_agp_configure, .fetch_size = parisc_agp_fetch_size, .tlb_flush = parisc_agp_tlbflush, - .mask_memory = parisc_agp_mask_memory, + .mask_memory = parisc_agp_page_mask_memory, .masks = parisc_agp_masks, .agp_enable = parisc_agp_enable, .cache_flush = global_cache_flush, diff --git a/drivers/char/pty.c b/drivers/char/pty.c index 6e6942c..d083c73 100644 --- a/drivers/char/pty.c +++ b/drivers/char/pty.c @@ -144,6 +144,8 @@ static int pty_write(struct tty_struct *tty, const unsigned char *buf, static int pty_write_room(struct tty_struct *tty) { + if (tty->stopped) + return 0; return pty_space(tty->link); } diff --git a/drivers/char/tty_ldisc.c b/drivers/char/tty_ldisc.c index acd76b7..1733d34 100644 --- a/drivers/char/tty_ldisc.c +++ b/drivers/char/tty_ldisc.c @@ -48,6 +48,41 @@ static DECLARE_WAIT_QUEUE_HEAD(tty_ldisc_wait); /* Line disc dispatch table */ static struct tty_ldisc_ops *tty_ldiscs[NR_LDISCS]; +static inline struct tty_ldisc *get_ldisc(struct tty_ldisc *ld) +{ + if (ld) + atomic_inc(&ld->users); + return ld; +} + +static void put_ldisc(struct tty_ldisc *ld) +{ + unsigned long flags; + + if (WARN_ON_ONCE(!ld)) + return; + + /* + * If this is the last user, free the ldisc, and + * release the ldisc ops. + * + * We really want an "atomic_dec_and_lock_irqsave()", + * but we don't have it, so this does it by hand. + */ + local_irq_save(flags); + if (atomic_dec_and_lock(&ld->users, &tty_ldisc_lock)) { + struct tty_ldisc_ops *ldo = ld->ops; + + ldo->refcount--; + module_put(ldo->owner); + spin_unlock_irqrestore(&tty_ldisc_lock, flags); + + kfree(ld); + return; + } + local_irq_restore(flags); +} + /** * tty_register_ldisc - install a line discipline * @disc: ldisc number @@ -142,7 +177,7 @@ static struct tty_ldisc *tty_ldisc_try_get(int disc) /* lock it */ ldops->refcount++; ld->ops = ldops; - ld->refcount = 0; + atomic_set(&ld->users, 1); err = 0; } } @@ -181,35 +216,6 @@ static struct tty_ldisc *tty_ldisc_get(int disc) return ld; } -/** - * tty_ldisc_put - drop ldisc reference - * @ld: ldisc - * - * Drop a reference to a line discipline. Manage refcounts and - * module usage counts. Free the ldisc once the recount hits zero. - * - * Locking: - * takes tty_ldisc_lock to guard against ldisc races - */ - -static void tty_ldisc_put(struct tty_ldisc *ld) -{ - unsigned long flags; - int disc = ld->ops->num; - struct tty_ldisc_ops *ldo; - - BUG_ON(disc < N_TTY || disc >= NR_LDISCS); - - spin_lock_irqsave(&tty_ldisc_lock, flags); - ldo = tty_ldiscs[disc]; - BUG_ON(ldo->refcount == 0); - ldo->refcount--; - module_put(ldo->owner); - spin_unlock_irqrestore(&tty_ldisc_lock, flags); - WARN_ON(ld->refcount); - kfree(ld); -} - static void *tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos) { return (*pos < NR_LDISCS) ? pos : NULL; @@ -234,7 +240,7 @@ static int tty_ldiscs_seq_show(struct seq_file *m, void *v) if (IS_ERR(ld)) return 0; seq_printf(m, "%-10s %2d\n", ld->ops->name ? ld->ops->name : "???", i); - tty_ldisc_put(ld); + put_ldisc(ld); return 0; } @@ -288,20 +294,17 @@ static void tty_ldisc_assign(struct tty_struct *tty, struct tty_ldisc *ld) * Locking: takes tty_ldisc_lock */ -static int tty_ldisc_try(struct tty_struct *tty) +static struct tty_ldisc *tty_ldisc_try(struct tty_struct *tty) { unsigned long flags; struct tty_ldisc *ld; - int ret = 0; spin_lock_irqsave(&tty_ldisc_lock, flags); - ld = tty->ldisc; - if (test_bit(TTY_LDISC, &tty->flags)) { - ld->refcount++; - ret = 1; - } + ld = NULL; + if (test_bit(TTY_LDISC, &tty->flags)) + ld = get_ldisc(tty->ldisc); spin_unlock_irqrestore(&tty_ldisc_lock, flags); - return ret; + return ld; } /** @@ -322,10 +325,11 @@ static int tty_ldisc_try(struct tty_struct *tty) struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *tty) { + struct tty_ldisc *ld; + /* wait_event is a macro */ - wait_event(tty_ldisc_wait, tty_ldisc_try(tty)); - WARN_ON(tty->ldisc->refcount == 0); - return tty->ldisc; + wait_event(tty_ldisc_wait, (ld = tty_ldisc_try(tty)) != NULL); + return ld; } EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait); @@ -342,9 +346,7 @@ EXPORT_SYMBOL_GPL(tty_ldisc_ref_wait); struct tty_ldisc *tty_ldisc_ref(struct tty_struct *tty) { - if (tty_ldisc_try(tty)) - return tty->ldisc; - return NULL; + return tty_ldisc_try(tty); } EXPORT_SYMBOL_GPL(tty_ldisc_ref); @@ -360,21 +362,15 @@ EXPORT_SYMBOL_GPL(tty_ldisc_ref); void tty_ldisc_deref(struct tty_ldisc *ld) { - unsigned long flags; - - BUG_ON(ld == NULL); - - spin_lock_irqsave(&tty_ldisc_lock, flags); - if (ld->refcount == 0) - printk(KERN_ERR "tty_ldisc_deref: no references.\n"); - else - ld->refcount--; - if (ld->refcount == 0) - wake_up(&tty_ldisc_wait); - spin_unlock_irqrestore(&tty_ldisc_lock, flags); + put_ldisc(ld); } EXPORT_SYMBOL_GPL(tty_ldisc_deref); +static inline void tty_ldisc_put(struct tty_ldisc *ld) +{ + put_ldisc(ld); +} + /** * tty_ldisc_enable - allow ldisc use * @tty: terminal to activate ldisc on @@ -523,31 +519,6 @@ static int tty_ldisc_halt(struct tty_struct *tty) } /** - * tty_ldisc_wait_idle - wait for the ldisc to become idle - * @tty: tty to wait for - * - * Wait for the line discipline to become idle. The discipline must - * have been halted for this to guarantee it remains idle. - * - * tty_ldisc_lock protects the ref counts currently. - */ - -static int tty_ldisc_wait_idle(struct tty_struct *tty) -{ - unsigned long flags; - spin_lock_irqsave(&tty_ldisc_lock, flags); - while (tty->ldisc->refcount) { - spin_unlock_irqrestore(&tty_ldisc_lock, flags); - if (wait_event_timeout(tty_ldisc_wait, - tty->ldisc->refcount == 0, 5 * HZ) == 0) - return -EBUSY; - spin_lock_irqsave(&tty_ldisc_lock, flags); - } - spin_unlock_irqrestore(&tty_ldisc_lock, flags); - return 0; -} - -/** * tty_set_ldisc - set line discipline * @tty: the terminal to set * @ldisc: the line discipline @@ -642,14 +613,6 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc) flush_scheduled_work(); - /* Let any existing reference holders finish */ - retval = tty_ldisc_wait_idle(tty); - if (retval < 0) { - clear_bit(TTY_LDISC_CHANGING, &tty->flags); - tty_ldisc_put(new_ldisc); - return retval; - } - mutex_lock(&tty->ldisc_mutex); if (test_bit(TTY_HUPPED, &tty->flags)) { /* We were raced by the hangup method. It will have stomped @@ -795,7 +758,6 @@ void tty_ldisc_hangup(struct tty_struct *tty) if (tty->ldisc) { /* Not yet closed */ /* Switch back to N_TTY */ tty_ldisc_halt(tty); - tty_ldisc_wait_idle(tty); tty_ldisc_reinit(tty); /* At this point we have a closed ldisc and we want to reopen it. We could defer this to the next open but @@ -860,14 +822,6 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty) tty_ldisc_halt(tty); flush_scheduled_work(); - /* - * Wait for any short term users (we know they are just driver - * side waiters as the file is closing so user count on the file - * side is zero. - */ - - tty_ldisc_wait_idle(tty); - mutex_lock(&tty->ldisc_mutex); /* * Now kill off the ldisc diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b90eda8..fd69086 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -858,6 +858,8 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) /* Check for existing affected CPUs. * They may not be aware of it due to CPU Hotplug. + * cpufreq_cpu_put is called when the device is removed + * in __cpufreq_remove_dev() */ managed_policy = cpufreq_cpu_get(j); if (unlikely(managed_policy)) { @@ -884,7 +886,7 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) ret = sysfs_create_link(&sys_dev->kobj, &managed_policy->kobj, "cpufreq"); - if (!ret) + if (ret) cpufreq_cpu_put(managed_policy); /* * Success. We only needed to be added to the mask. @@ -924,6 +926,8 @@ static int cpufreq_add_dev(struct sys_device *sys_dev) spin_lock_irqsave(&cpufreq_driver_lock, flags); for_each_cpu(j, policy->cpus) { + if (!cpu_online(j)) + continue; per_cpu(cpufreq_cpu_data, j) = policy; per_cpu(policy_cpu, j) = policy->cpu; } @@ -1244,13 +1248,22 @@ EXPORT_SYMBOL(cpufreq_get); static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg) { - int cpu = sysdev->id; int ret = 0; + +#ifdef __powerpc__ + int cpu = sysdev->id; unsigned int cur_freq = 0; struct cpufreq_policy *cpu_policy; dprintk("suspending cpu %u\n", cpu); + /* + * This whole bogosity is here because Powerbooks are made of fail. + * No sane platform should need any of the code below to be run. + * (it's entirely the wrong thing to do, as driver->get may + * reenable interrupts on some architectures). + */ + if (!cpu_online(cpu)) return 0; @@ -1309,6 +1322,7 @@ static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg) out: cpufreq_cpu_put(cpu_policy); +#endif /* __powerpc__ */ return ret; } @@ -1322,12 +1336,18 @@ out: */ static int cpufreq_resume(struct sys_device *sysdev) { - int cpu = sysdev->id; int ret = 0; + +#ifdef __powerpc__ + int cpu = sysdev->id; struct cpufreq_policy *cpu_policy; dprintk("resuming cpu %u\n", cpu); + /* As with the ->suspend method, all the code below is + * only necessary because Powerbooks suck. + * See commit 42d4dc3f4e1e for jokes. */ + if (!cpu_online(cpu)) return 0; @@ -1391,6 +1411,7 @@ out: schedule_work(&cpu_policy->update); fail: cpufreq_cpu_put(cpu_policy); +#endif /* __powerpc__ */ return ret; } diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index 5749050..bdea7e2 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -63,6 +63,7 @@ struct cpu_dbs_info_s { unsigned int down_skip; unsigned int requested_freq; int cpu; + unsigned int enable:1; /* * percpu mutex that serializes governor limit change with * do_dbs_timer invocation. We do not want do_dbs_timer to run @@ -141,6 +142,9 @@ dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val, struct cpufreq_policy *policy; + if (!this_dbs_info->enable) + return 0; + policy = this_dbs_info->cur_policy; /* @@ -497,6 +501,7 @@ static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info) int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate); delay -= jiffies % delay; + dbs_info->enable = 1; INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer); queue_delayed_work_on(dbs_info->cpu, kconservative_wq, &dbs_info->work, delay); @@ -504,6 +509,7 @@ static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info) static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info) { + dbs_info->enable = 0; cancel_delayed_work_sync(&dbs_info->work); } diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 24964c1..e2a10bc 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -868,6 +868,8 @@ static void amd64_read_dbam_reg(struct amd64_pvt *pvt) goto err_reg; } + return; + err_reg: debugf0("Error reading F2x%03x.\n", reg); } @@ -2634,6 +2636,8 @@ static void amd64_read_mc_registers(struct amd64_pvt *pvt) amd64_dump_misc_regs(pvt); + return; + err_reg: debugf0("Reading an MC register failed\n"); @@ -2977,6 +2981,9 @@ static int amd64_check_ecc_enabled(struct amd64_pvt *pvt) "ECC is enabled by BIOS, Proceeding " "with EDAC module initialization\n"); + /* Signal good ECC status */ + ret = 0; + /* CLEAR the override, since BIOS controlled it */ ecc_enable_override = 0; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 8fab789..33be210 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -1461,7 +1461,7 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, goto out; } - if (crtc_req->count_connectors > 0 && !mode && !fb) { + if (crtc_req->count_connectors > 0 && (!mode || !fb)) { DRM_DEBUG("Count connectors is %d but no mode or fb set\n", crtc_req->count_connectors); ret = -EINVAL; diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index 3da9cfa..6aaa2cb 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -706,8 +706,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) struct drm_encoder **save_encoders, *new_encoder; struct drm_framebuffer *old_fb = NULL; bool save_enabled; - bool mode_changed = false; - bool fb_changed = false; + bool mode_changed = false; /* if true do a full mode set */ + bool fb_changed = false; /* if true and !mode_changed just do a flip */ struct drm_connector *connector; int count = 0, ro, fail = 0; struct drm_crtc_helper_funcs *crtc_funcs; @@ -758,6 +758,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) if (set->crtc->fb == NULL) { DRM_DEBUG("crtc has no fb, full mode set\n"); mode_changed = true; + } else if (set->fb == NULL) { + mode_changed = true; } else if ((set->fb->bits_per_pixel != set->crtc->fb->bits_per_pixel) || set->fb->depth != set->crtc->fb->depth) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index b4a3dbc..f85aaf2 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -566,7 +566,7 @@ int drm_wait_vblank(struct drm_device *dev, void *data, ret = drm_vblank_get(dev, crtc); if (ret) { - DRM_ERROR("failed to acquire vblank counter, %d\n", ret); + DRM_DEBUG("failed to acquire vblank counter, %d\n", ret); return ret; } seq = drm_vblank_count(dev, crtc); diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 54f492a..7914097 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -566,6 +566,8 @@ void drm_mode_connector_list_update(struct drm_connector *connector) found_it = 1; /* if equal delete the probed mode */ mode->status = pmode->status; + /* Merge type bits together */ + mode->type |= pmode->type; list_del(&pmode->head); drm_mode_destroy(connector->dev, pmode); break; diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index 8c47831..50d1f78 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -1186,6 +1186,13 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (ret) goto out_iomapfree; + dev_priv->wq = create_workqueue("i915"); + if (dev_priv->wq == NULL) { + DRM_ERROR("Failed to create our workqueue.\n"); + ret = -ENOMEM; + goto out_iomapfree; + } + /* enable GEM by default */ dev_priv->has_gem = 1; @@ -1211,7 +1218,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) if (!I915_NEED_GFX_HWS(dev)) { ret = i915_init_phys_hws(dev); if (ret != 0) - goto out_iomapfree; + goto out_workqueue_free; } i915_get_mem_freq(dev); @@ -1245,7 +1252,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) ret = i915_load_modeset_init(dev, prealloc_size, agp_size); if (ret < 0) { DRM_ERROR("failed to init modeset\n"); - goto out_rmmap; + goto out_workqueue_free; } } @@ -1256,6 +1263,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) return 0; +out_workqueue_free: + destroy_workqueue(dev_priv->wq); out_iomapfree: io_mapping_free(dev_priv->mm.gtt_mapping); out_rmmap: @@ -1269,6 +1278,8 @@ int i915_driver_unload(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; + destroy_workqueue(dev_priv->wq); + io_mapping_free(dev_priv->mm.gtt_mapping); if (dev_priv->mm.gtt_mtrr >= 0) { mtrr_del(dev_priv->mm.gtt_mtrr, dev->agp->base, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d087528..7537f57 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -219,6 +219,7 @@ typedef struct drm_i915_private { unsigned int lvds_vbt:1; unsigned int int_crt_support:1; unsigned int lvds_use_ssc:1; + unsigned int edp_support:1; int lvds_ssc_freq; struct drm_i915_fence_reg fence_regs[16]; /* assume 965 */ @@ -229,6 +230,8 @@ typedef struct drm_i915_private { spinlock_t error_lock; struct drm_i915_error_state *first_error; + struct work_struct error_work; + struct workqueue_struct *wq; /* Register state */ u8 saveLBB; @@ -888,6 +891,7 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller); IS_I915GM(dev))) #define SUPPORTS_INTEGRATED_HDMI(dev) (IS_G4X(dev) || IS_IGDNG(dev)) #define SUPPORTS_INTEGRATED_DP(dev) (IS_G4X(dev) || IS_IGDNG(dev)) +#define SUPPORTS_EDP(dev) (IS_IGDNG_M(dev)) #define I915_HAS_HOTPLUG(dev) (IS_I945G(dev) || IS_I945GM(dev) || IS_I965G(dev)) /* dsparb controlled by hw only */ #define DSPARB_HWCONTROL(dev) (IS_G4X(dev) || IS_IGDNG(dev)) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 5bf4203..140bee1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1570,7 +1570,7 @@ i915_add_request(struct drm_device *dev, struct drm_file *file_priv, } if (was_empty && !dev_priv->mm.suspended) - schedule_delayed_work(&dev_priv->mm.retire_work, HZ); + queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, HZ); return seqno; } @@ -1719,7 +1719,7 @@ i915_gem_retire_work_handler(struct work_struct *work) i915_gem_retire_requests(dev); if (!dev_priv->mm.suspended && !list_empty(&dev_priv->mm.request_list)) - schedule_delayed_work(&dev_priv->mm.retire_work, HZ); + queue_delayed_work(dev_priv->wq, &dev_priv->mm.retire_work, HZ); mutex_unlock(&dev->struct_mutex); } diff --git a/drivers/gpu/drm/i915/i915_gem_debugfs.c b/drivers/gpu/drm/i915/i915_gem_debugfs.c index 9a44bfc..cb3b974 100644 --- a/drivers/gpu/drm/i915/i915_gem_debugfs.c +++ b/drivers/gpu/drm/i915/i915_gem_debugfs.c @@ -343,6 +343,8 @@ static int i915_error_state(struct seq_file *m, void *unused) error = dev_priv->first_error; + seq_printf(m, "Time: %ld s %ld us\n", error->time.tv_sec, + error->time.tv_usec); seq_printf(m, "EIR: 0x%08x\n", error->eir); seq_printf(m, " PGTBL_ER: 0x%08x\n", error->pgtbl_er); seq_printf(m, " INSTPM: 0x%08x\n", error->instpm); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 7ba23a6..7ebc84c 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -190,7 +190,7 @@ u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) low_frame = pipe ? PIPEBFRAMEPIXEL : PIPEAFRAMEPIXEL; if (!i915_pipe_enabled(dev, pipe)) { - DRM_ERROR("trying to get vblank count for disabled pipe %d\n", pipe); + DRM_DEBUG("trying to get vblank count for disabled pipe %d\n", pipe); return 0; } @@ -219,7 +219,7 @@ u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe) int reg = pipe ? PIPEB_FRMCOUNT_GM45 : PIPEA_FRMCOUNT_GM45; if (!i915_pipe_enabled(dev, pipe)) { - DRM_ERROR("trying to get vblank count for disabled pipe %d\n", pipe); + DRM_DEBUG("trying to get vblank count for disabled pipe %d\n", pipe); return 0; } @@ -290,6 +290,35 @@ irqreturn_t igdng_irq_handler(struct drm_device *dev) return ret; } +/** + * i915_error_work_func - do process context error handling work + * @work: work struct + * + * Fire an error uevent so userspace can see that a hang or error + * was detected. + */ +static void i915_error_work_func(struct work_struct *work) +{ + drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t, + error_work); + struct drm_device *dev = dev_priv->dev; + char *event_string = "ERROR=1"; + char *envp[] = { event_string, NULL }; + + DRM_DEBUG("generating error event\n"); + + kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, envp); +} + +/** + * i915_capture_error_state - capture an error record for later analysis + * @dev: drm device + * + * Should be called when an error is detected (either a hang or an error + * interrupt) to capture error state from the time of the error. Fills + * out a structure which becomes available in debugfs for user level tools + * to pick up. + */ static void i915_capture_error_state(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; @@ -325,12 +354,137 @@ static void i915_capture_error_state(struct drm_device *dev) error->acthd = I915_READ(ACTHD_I965); } + do_gettimeofday(&error->time); + dev_priv->first_error = error; out: spin_unlock_irqrestore(&dev_priv->error_lock, flags); } +/** + * i915_handle_error - handle an error interrupt + * @dev: drm device + * + * Do some basic checking of regsiter state at error interrupt time and + * dump it to the syslog. Also call i915_capture_error_state() to make + * sure we get a record and make it available in debugfs. Fire a uevent + * so userspace knows something bad happened (should trigger collection + * of a ring dump etc.). + */ +static void i915_handle_error(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 eir = I915_READ(EIR); + u32 pipea_stats = I915_READ(PIPEASTAT); + u32 pipeb_stats = I915_READ(PIPEBSTAT); + + i915_capture_error_state(dev); + + printk(KERN_ERR "render error detected, EIR: 0x%08x\n", + eir); + + if (IS_G4X(dev)) { + if (eir & (GM45_ERROR_MEM_PRIV | GM45_ERROR_CP_PRIV)) { + u32 ipeir = I915_READ(IPEIR_I965); + + printk(KERN_ERR " IPEIR: 0x%08x\n", + I915_READ(IPEIR_I965)); + printk(KERN_ERR " IPEHR: 0x%08x\n", + I915_READ(IPEHR_I965)); + printk(KERN_ERR " INSTDONE: 0x%08x\n", + I915_READ(INSTDONE_I965)); + printk(KERN_ERR " INSTPS: 0x%08x\n", + I915_READ(INSTPS)); + printk(KERN_ERR " INSTDONE1: 0x%08x\n", + I915_READ(INSTDONE1)); + printk(KERN_ERR " ACTHD: 0x%08x\n", + I915_READ(ACTHD_I965)); + I915_WRITE(IPEIR_I965, ipeir); + (void)I915_READ(IPEIR_I965); + } + if (eir & GM45_ERROR_PAGE_TABLE) { + u32 pgtbl_err = I915_READ(PGTBL_ER); + printk(KERN_ERR "page table error\n"); + printk(KERN_ERR " PGTBL_ER: 0x%08x\n", + pgtbl_err); + I915_WRITE(PGTBL_ER, pgtbl_err); + (void)I915_READ(PGTBL_ER); + } + } + + if (IS_I9XX(dev)) { + if (eir & I915_ERROR_PAGE_TABLE) { + u32 pgtbl_err = I915_READ(PGTBL_ER); + printk(KERN_ERR "page table error\n"); + printk(KERN_ERR " PGTBL_ER: 0x%08x\n", + pgtbl_err); + I915_WRITE(PGTBL_ER, pgtbl_err); + (void)I915_READ(PGTBL_ER); + } + } + + if (eir & I915_ERROR_MEMORY_REFRESH) { + printk(KERN_ERR "memory refresh error\n"); + printk(KERN_ERR "PIPEASTAT: 0x%08x\n", + pipea_stats); + printk(KERN_ERR "PIPEBSTAT: 0x%08x\n", + pipeb_stats); + /* pipestat has already been acked */ + } + if (eir & I915_ERROR_INSTRUCTION) { + printk(KERN_ERR "instruction error\n"); + printk(KERN_ERR " INSTPM: 0x%08x\n", + I915_READ(INSTPM)); + if (!IS_I965G(dev)) { + u32 ipeir = I915_READ(IPEIR); + + printk(KERN_ERR " IPEIR: 0x%08x\n", + I915_READ(IPEIR)); + printk(KERN_ERR " IPEHR: 0x%08x\n", + I915_READ(IPEHR)); + printk(KERN_ERR " INSTDONE: 0x%08x\n", + I915_READ(INSTDONE)); + printk(KERN_ERR " ACTHD: 0x%08x\n", + I915_READ(ACTHD)); + I915_WRITE(IPEIR, ipeir); + (void)I915_READ(IPEIR); + } else { + u32 ipeir = I915_READ(IPEIR_I965); + + printk(KERN_ERR " IPEIR: 0x%08x\n", + I915_READ(IPEIR_I965)); + printk(KERN_ERR " IPEHR: 0x%08x\n", + I915_READ(IPEHR_I965)); + printk(KERN_ERR " INSTDONE: 0x%08x\n", + I915_READ(INSTDONE_I965)); + printk(KERN_ERR " INSTPS: 0x%08x\n", + I915_READ(INSTPS)); + printk(KERN_ERR " INSTDONE1: 0x%08x\n", + I915_READ(INSTDONE1)); + printk(KERN_ERR " ACTHD: 0x%08x\n", + I915_READ(ACTHD_I965)); + I915_WRITE(IPEIR_I965, ipeir); + (void)I915_READ(IPEIR_I965); + } + } + + I915_WRITE(EIR, eir); + (void)I915_READ(EIR); + eir = I915_READ(EIR); + if (eir) { + /* + * some errors might have become stuck, + * mask them. + */ + DRM_ERROR("EIR stuck: 0x%08x, masking\n", eir); + I915_WRITE(EMR, I915_READ(EMR) | eir); + I915_WRITE(IIR, I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT); + } + + queue_work(dev_priv->wq, &dev_priv->error_work); +} + irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) { struct drm_device *dev = (struct drm_device *) arg; @@ -372,6 +526,9 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) pipea_stats = I915_READ(PIPEASTAT); pipeb_stats = I915_READ(PIPEBSTAT); + if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT) + i915_handle_error(dev); + /* * Clear the PIPE(A|B)STAT regs before the IIR */ @@ -403,86 +560,13 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS) DRM_DEBUG("hotplug event received, stat 0x%08x\n", hotplug_status); if (hotplug_status & dev_priv->hotplug_supported_mask) - schedule_work(&dev_priv->hotplug_work); + queue_work(dev_priv->wq, + &dev_priv->hotplug_work); I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status); I915_READ(PORT_HOTPLUG_STAT); } - if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT) { - u32 eir = I915_READ(EIR); - - i915_capture_error_state(dev); - - printk(KERN_ERR "render error detected, EIR: 0x%08x\n", - eir); - if (eir & I915_ERROR_PAGE_TABLE) { - u32 pgtbl_err = I915_READ(PGTBL_ER); - printk(KERN_ERR "page table error\n"); - printk(KERN_ERR " PGTBL_ER: 0x%08x\n", - pgtbl_err); - I915_WRITE(PGTBL_ER, pgtbl_err); - (void)I915_READ(PGTBL_ER); - } - if (eir & I915_ERROR_MEMORY_REFRESH) { - printk(KERN_ERR "memory refresh error\n"); - printk(KERN_ERR "PIPEASTAT: 0x%08x\n", - pipea_stats); - printk(KERN_ERR "PIPEBSTAT: 0x%08x\n", - pipeb_stats); - /* pipestat has already been acked */ - } - if (eir & I915_ERROR_INSTRUCTION) { - printk(KERN_ERR "instruction error\n"); - printk(KERN_ERR " INSTPM: 0x%08x\n", - I915_READ(INSTPM)); - if (!IS_I965G(dev)) { - u32 ipeir = I915_READ(IPEIR); - - printk(KERN_ERR " IPEIR: 0x%08x\n", - I915_READ(IPEIR)); - printk(KERN_ERR " IPEHR: 0x%08x\n", - I915_READ(IPEHR)); - printk(KERN_ERR " INSTDONE: 0x%08x\n", - I915_READ(INSTDONE)); - printk(KERN_ERR " ACTHD: 0x%08x\n", - I915_READ(ACTHD)); - I915_WRITE(IPEIR, ipeir); - (void)I915_READ(IPEIR); - } else { - u32 ipeir = I915_READ(IPEIR_I965); - - printk(KERN_ERR " IPEIR: 0x%08x\n", - I915_READ(IPEIR_I965)); - printk(KERN_ERR " IPEHR: 0x%08x\n", - I915_READ(IPEHR_I965)); - printk(KERN_ERR " INSTDONE: 0x%08x\n", - I915_READ(INSTDONE_I965)); - printk(KERN_ERR " INSTPS: 0x%08x\n", - I915_READ(INSTPS)); - printk(KERN_ERR " INSTDONE1: 0x%08x\n", - I915_READ(INSTDONE1)); - printk(KERN_ERR " ACTHD: 0x%08x\n", - I915_READ(ACTHD_I965)); - I915_WRITE(IPEIR_I965, ipeir); - (void)I915_READ(IPEIR_I965); - } - } - - I915_WRITE(EIR, eir); - (void)I915_READ(EIR); - eir = I915_READ(EIR); - if (eir) { - /* - * some errors might have become stuck, - * mask them. - */ - DRM_ERROR("EIR stuck: 0x%08x, masking\n", eir); - I915_WRITE(EMR, I915_READ(EMR) | eir); - I915_WRITE(IIR, I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT); - } - } - I915_WRITE(IIR, iir); new_iir = I915_READ(IIR); /* Flush posted writes */ @@ -830,6 +914,7 @@ void i915_driver_irq_preinstall(struct drm_device * dev) atomic_set(&dev_priv->irq_received, 0); INIT_WORK(&dev_priv->hotplug_work, i915_hotplug_work_func); + INIT_WORK(&dev_priv->error_work, i915_error_work_func); if (IS_IGDNG(dev)) { igdng_irq_preinstall(dev); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 6c08584..2955083 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1395,6 +1395,7 @@ #define TV_V_CHROMA_42 0x684a8 /* Display Port */ +#define DP_A 0x64000 /* eDP */ #define DP_B 0x64100 #define DP_C 0x64200 #define DP_D 0x64300 @@ -1437,13 +1438,22 @@ /* Mystic DPCD version 1.1 special mode */ #define DP_ENHANCED_FRAMING (1 << 18) +/* eDP */ +#define DP_PLL_FREQ_270MHZ (0 << 16) +#define DP_PLL_FREQ_160MHZ (1 << 16) +#define DP_PLL_FREQ_MASK (3 << 16) + /** locked once port is enabled */ #define DP_PORT_REVERSAL (1 << 15) +/* eDP */ +#define DP_PLL_ENABLE (1 << 14) + /** sends the clock on lane 15 of the PEG for debug */ #define DP_CLOCK_OUTPUT_ENABLE (1 << 13) #define DP_SCRAMBLING_DISABLE (1 << 12) +#define DP_SCRAMBLING_DISABLE_IGDNG (1 << 7) /** limit RGB values to avoid confusing TVs */ #define DP_COLOR_RANGE_16_235 (1 << 8) @@ -1463,6 +1473,13 @@ * is 20 bytes in each direction, hence the 5 fixed * data registers */ +#define DPA_AUX_CH_CTL 0x64010 +#define DPA_AUX_CH_DATA1 0x64014 +#define DPA_AUX_CH_DATA2 0x64018 +#define DPA_AUX_CH_DATA3 0x6401c +#define DPA_AUX_CH_DATA4 0x64020 +#define DPA_AUX_CH_DATA5 0x64024 + #define DPB_AUX_CH_CTL 0x64110 #define DPB_AUX_CH_DATA1 0x64114 #define DPB_AUX_CH_DATA2 0x64118 @@ -1618,7 +1635,7 @@ #define I830_FIFO_LINE_SIZE 32 #define I945_FIFO_SIZE 127 /* 945 & 965 */ #define I915_FIFO_SIZE 95 -#define I855GM_FIFO_SIZE 255 +#define I855GM_FIFO_SIZE 127 /* In cachelines */ #define I830_FIFO_SIZE 95 #define I915_MAX_WM 0x3f @@ -1848,6 +1865,8 @@ #define PFA_CTL_1 0x68080 #define PFB_CTL_1 0x68880 #define PF_ENABLE (1<<31) +#define PFA_WIN_SZ 0x68074 +#define PFB_WIN_SZ 0x68874 /* legacy palette */ #define LGC_PALETTE_A 0x4a000 @@ -2208,4 +2227,28 @@ #define PCH_PP_OFF_DELAYS 0xc720c #define PCH_PP_DIVISOR 0xc7210 +#define PCH_DP_B 0xe4100 +#define PCH_DPB_AUX_CH_CTL 0xe4110 +#define PCH_DPB_AUX_CH_DATA1 0xe4114 +#define PCH_DPB_AUX_CH_DATA2 0xe4118 +#define PCH_DPB_AUX_CH_DATA3 0xe411c +#define PCH_DPB_AUX_CH_DATA4 0xe4120 +#define PCH_DPB_AUX_CH_DATA5 0xe4124 + +#define PCH_DP_C 0xe4200 +#define PCH_DPC_AUX_CH_CTL 0xe4210 +#define PCH_DPC_AUX_CH_DATA1 0xe4214 +#define PCH_DPC_AUX_CH_DATA2 0xe4218 +#define PCH_DPC_AUX_CH_DATA3 0xe421c +#define PCH_DPC_AUX_CH_DATA4 0xe4220 +#define PCH_DPC_AUX_CH_DATA5 0xe4224 + +#define PCH_DP_D 0xe4300 +#define PCH_DPD_AUX_CH_CTL 0xe4310 +#define PCH_DPD_AUX_CH_DATA1 0xe4314 +#define PCH_DPD_AUX_CH_DATA2 0xe4318 +#define PCH_DPD_AUX_CH_DATA3 0xe431c +#define PCH_DPD_AUX_CH_DATA4 0xe4320 +#define PCH_DPD_AUX_CH_DATA5 0xe4324 + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 9e1d16e..1d04e19 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -598,7 +598,7 @@ int i915_restore_state(struct drm_device *dev) for (i = 0; i < 16; i++) { I915_WRITE(SWF00 + (i << 2), dev_priv->saveSWF0[i]); - I915_WRITE(SWF10 + (i << 2), dev_priv->saveSWF1[i+7]); + I915_WRITE(SWF10 + (i << 2), dev_priv->saveSWF1[i]); } for (i = 0; i < 3; i++) I915_WRITE(SWF30 + (i << 2), dev_priv->saveSWF2[i]); diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 7cc4471..300aee3 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -97,14 +97,13 @@ static void parse_lfp_panel_data(struct drm_i915_private *dev_priv, struct bdb_header *bdb) { - struct drm_device *dev = dev_priv->dev; struct bdb_lvds_options *lvds_options; struct bdb_lvds_lfp_data *lvds_lfp_data; struct bdb_lvds_lfp_data_ptrs *lvds_lfp_data_ptrs; struct bdb_lvds_lfp_data_entry *entry; struct lvds_dvo_timing *dvo_timing; struct drm_display_mode *panel_fixed_mode; - int lfp_data_size; + int lfp_data_size, dvo_timing_offset; /* Defaults if we can't find VBT info */ dev_priv->lvds_dither = 0; @@ -133,14 +132,16 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv, entry = (struct bdb_lvds_lfp_data_entry *) ((uint8_t *)lvds_lfp_data->data + (lfp_data_size * lvds_options->panel_type)); + dvo_timing_offset = lvds_lfp_data_ptrs->ptr[0].dvo_timing_offset - + lvds_lfp_data_ptrs->ptr[0].fp_timing_offset; - /* On IGDNG mobile, LVDS data block removes panel fitting registers. - So dec 2 dword from dvo_timing offset */ - if (IS_IGDNG(dev)) - dvo_timing = (struct lvds_dvo_timing *) - ((u8 *)&entry->dvo_timing - 8); - else - dvo_timing = &entry->dvo_timing; + /* + * the size of fp_timing varies on the different platform. + * So calculate the DVO timing relative offset in LVDS data + * entry to get the DVO timing entry + */ + dvo_timing = (struct lvds_dvo_timing *) + ((unsigned char *)entry + dvo_timing_offset); panel_fixed_mode = kzalloc(sizeof(*panel_fixed_mode), GFP_KERNEL); @@ -295,6 +296,25 @@ parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, } return; } + +static void +parse_driver_features(struct drm_i915_private *dev_priv, + struct bdb_header *bdb) +{ + struct drm_device *dev = dev_priv->dev; + struct bdb_driver_features *driver; + + /* set default for chips without eDP */ + if (!SUPPORTS_EDP(dev)) { + dev_priv->edp_support = 0; + return; + } + + driver = find_section(bdb, BDB_DRIVER_FEATURES); + if (driver && driver->lvds_config == BDB_DRIVER_FEATURE_EDP) + dev_priv->edp_support = 1; +} + /** * intel_init_bios - initialize VBIOS settings & find VBT * @dev: DRM device @@ -345,6 +365,8 @@ intel_init_bios(struct drm_device *dev) parse_lfp_panel_data(dev_priv, bdb); parse_sdvo_panel_data(dev_priv, bdb); parse_sdvo_device_mapping(dev_priv, bdb); + parse_driver_features(dev_priv, bdb); + pci_unmap_rom(pdev, bios); return 0; diff --git a/drivers/gpu/drm/i915/intel_bios.h b/drivers/gpu/drm/i915/intel_bios.h index fe72e1c..0f8e5f6 100644 --- a/drivers/gpu/drm/i915/intel_bios.h +++ b/drivers/gpu/drm/i915/intel_bios.h @@ -381,6 +381,51 @@ struct bdb_sdvo_lvds_options { } __attribute__((packed)); +#define BDB_DRIVER_FEATURE_NO_LVDS 0 +#define BDB_DRIVER_FEATURE_INT_LVDS 1 +#define BDB_DRIVER_FEATURE_SDVO_LVDS 2 +#define BDB_DRIVER_FEATURE_EDP 3 + +struct bdb_driver_features { + u8 boot_dev_algorithm:1; + u8 block_display_switch:1; + u8 allow_display_switch:1; + u8 hotplug_dvo:1; + u8 dual_view_zoom:1; + u8 int15h_hook:1; + u8 sprite_in_clone:1; + u8 primary_lfp_id:1; + + u16 boot_mode_x; + u16 boot_mode_y; + u8 boot_mode_bpp; + u8 boot_mode_refresh; + + u16 enable_lfp_primary:1; + u16 selective_mode_pruning:1; + u16 dual_frequency:1; + u16 render_clock_freq:1; /* 0: high freq; 1: low freq */ + u16 nt_clone_support:1; + u16 power_scheme_ui:1; /* 0: CUI; 1: 3rd party */ + u16 sprite_display_assign:1; /* 0: secondary; 1: primary */ + u16 cui_aspect_scaling:1; + u16 preserve_aspect_ratio:1; + u16 sdvo_device_power_down:1; + u16 crt_hotplug:1; + u16 lvds_config:2; + u16 tv_hotplug:1; + u16 hdmi_config:2; + + u8 static_display:1; + u8 reserved2:7; + u16 legacy_crt_max_x; + u16 legacy_crt_max_y; + u8 legacy_crt_max_refresh; + + u8 hdmi_termination; + u8 custom_vbt_version; +} __attribute__((packed)); + bool intel_init_bios(struct drm_device *dev); /* diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index d6a1a6e..4cf8e2e 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -156,6 +156,9 @@ static bool intel_igdng_crt_detect_hotplug(struct drm_connector *connector) temp = adpa = I915_READ(PCH_ADPA); + adpa &= ~ADPA_DAC_ENABLE; + I915_WRITE(PCH_ADPA, adpa); + adpa &= ~ADPA_CRT_HOTPLUG_MASK; adpa |= (ADPA_CRT_HOTPLUG_PERIOD_128 | @@ -169,13 +172,14 @@ static bool intel_igdng_crt_detect_hotplug(struct drm_connector *connector) DRM_DEBUG("pch crt adpa 0x%x", adpa); I915_WRITE(PCH_ADPA, adpa); - /* This might not be needed as not specified in spec...*/ - udelay(1000); + while ((I915_READ(PCH_ADPA) & ADPA_CRT_HOTPLUG_FORCE_TRIGGER) != 0) + ; /* Check the status to see if both blue and green are on now */ adpa = I915_READ(PCH_ADPA); - if ((adpa & ADPA_CRT_HOTPLUG_MONITOR_MASK) == - ADPA_CRT_HOTPLUG_MONITOR_COLOR) + adpa &= ADPA_CRT_HOTPLUG_MONITOR_MASK; + if ((adpa == ADPA_CRT_HOTPLUG_MONITOR_COLOR) || + (adpa == ADPA_CRT_HOTPLUG_MONITOR_MONO)) ret = true; else ret = false; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 508838e..d6fce21 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -34,6 +34,8 @@ #include "drm_crtc_helper.h" +#define HAS_eDP (intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP)) + bool intel_pipe_has_type (struct drm_crtc *crtc, int type); static void intel_update_watermarks(struct drm_device *dev); @@ -88,7 +90,7 @@ struct intel_limit { #define I8XX_P2_SLOW 4 #define I8XX_P2_FAST 2 #define I8XX_P2_LVDS_SLOW 14 -#define I8XX_P2_LVDS_FAST 14 /* No fast option */ +#define I8XX_P2_LVDS_FAST 7 #define I8XX_P2_SLOW_LIMIT 165000 #define I9XX_DOT_MIN 20000 @@ -268,6 +270,9 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, static bool intel_find_pll_g4x_dp(const intel_limit_t *, struct drm_crtc *crtc, int target, int refclk, intel_clock_t *best_clock); +static bool +intel_find_pll_igdng_dp(const intel_limit_t *, struct drm_crtc *crtc, + int target, int refclk, intel_clock_t *best_clock); static const intel_limit_t intel_limits_i8xx_dvo = { .dot = { .min = I8XX_DOT_MIN, .max = I8XX_DOT_MAX }, @@ -598,6 +603,23 @@ bool intel_pipe_has_type (struct drm_crtc *crtc, int type) return false; } +struct drm_connector * +intel_pipe_get_output (struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector *l_entry, *ret = NULL; + + list_for_each_entry(l_entry, &mode_config->connector_list, head) { + if (l_entry->encoder && + l_entry->encoder->crtc == crtc) { + ret = l_entry; + break; + } + } + return ret; +} + #define INTELPllInvalid(s) do { /* DRM_DEBUG(s); */ return false; } while (0) /** * Returns whether the given set of divisors are valid for a given refclk with @@ -645,7 +667,7 @@ intel_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, int err = target; if (IS_I9XX(dev) && intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS) && - (I915_READ(LVDS) & LVDS_PORT_EN) != 0) { + (I915_READ(LVDS)) != 0) { /* * For LVDS, if the panel is on, just rely on its current * settings for dual-channel. We haven't figured out how to @@ -752,6 +774,30 @@ intel_g4x_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, } static bool +intel_find_pll_igdng_dp(const intel_limit_t *limit, struct drm_crtc *crtc, + int target, int refclk, intel_clock_t *best_clock) +{ + struct drm_device *dev = crtc->dev; + intel_clock_t clock; + if (target < 200000) { + clock.n = 1; + clock.p1 = 2; + clock.p2 = 10; + clock.m1 = 12; + clock.m2 = 9; + } else { + clock.n = 2; + clock.p1 = 1; + clock.p2 = 10; + clock.m1 = 14; + clock.m2 = 8; + } + intel_clock(dev, refclk, &clock); + memcpy(best_clock, &clock, sizeof(intel_clock_t)); + return true; +} + +static bool intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, int target, int refclk, intel_clock_t *best_clock) { @@ -763,6 +809,14 @@ intel_igdng_find_best_PLL(const intel_limit_t *limit, struct drm_crtc *crtc, int err_most = 47; found = false; + /* eDP has only 2 clock choice, no n/m/p setting */ + if (HAS_eDP) + return true; + + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) + return intel_find_pll_igdng_dp(limit, crtc, target, + refclk, best_clock); + if (intel_pipe_has_type(crtc, INTEL_OUTPUT_LVDS)) { if ((I915_READ(LVDS) & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP) @@ -998,6 +1052,90 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y, return 0; } +/* Disable the VGA plane that we never use */ +static void i915_disable_vga (struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u8 sr1; + u32 vga_reg; + + if (IS_IGDNG(dev)) + vga_reg = CPU_VGACNTRL; + else + vga_reg = VGACNTRL; + + if (I915_READ(vga_reg) & VGA_DISP_DISABLE) + return; + + I915_WRITE8(VGA_SR_INDEX, 1); + sr1 = I915_READ8(VGA_SR_DATA); + I915_WRITE8(VGA_SR_DATA, sr1 | (1 << 5)); + udelay(100); + + I915_WRITE(vga_reg, VGA_DISP_DISABLE); +} + +static void igdng_disable_pll_edp (struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 dpa_ctl; + + DRM_DEBUG("\n"); + dpa_ctl = I915_READ(DP_A); + dpa_ctl &= ~DP_PLL_ENABLE; + I915_WRITE(DP_A, dpa_ctl); +} + +static void igdng_enable_pll_edp (struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 dpa_ctl; + + dpa_ctl = I915_READ(DP_A); + dpa_ctl |= DP_PLL_ENABLE; + I915_WRITE(DP_A, dpa_ctl); + udelay(200); +} + + +static void igdng_set_pll_edp (struct drm_crtc *crtc, int clock) +{ + struct drm_device *dev = crtc->dev; + struct drm_i915_private *dev_priv = dev->dev_private; + u32 dpa_ctl; + + DRM_DEBUG("eDP PLL enable for clock %d\n", clock); + dpa_ctl = I915_READ(DP_A); + dpa_ctl &= ~DP_PLL_FREQ_MASK; + + if (clock < 200000) { + u32 temp; + dpa_ctl |= DP_PLL_FREQ_160MHZ; + /* workaround for 160Mhz: + 1) program 0x4600c bits 15:0 = 0x8124 + 2) program 0x46010 bit 0 = 1 + 3) program 0x46034 bit 24 = 1 + 4) program 0x64000 bit 14 = 1 + */ + temp = I915_READ(0x4600c); + temp &= 0xffff0000; + I915_WRITE(0x4600c, temp | 0x8124); + + temp = I915_READ(0x46010); + I915_WRITE(0x46010, temp | 1); + + temp = I915_READ(0x46034); + I915_WRITE(0x46034, temp | (1 << 24)); + } else { + dpa_ctl |= DP_PLL_FREQ_270MHZ; + } + I915_WRITE(DP_A, dpa_ctl); + + udelay(500); +} + static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) { struct drm_device *dev = crtc->dev; @@ -1015,6 +1153,7 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) int fdi_rx_imr_reg = (pipe == 0) ? FDI_RXA_IMR : FDI_RXB_IMR; int transconf_reg = (pipe == 0) ? TRANSACONF : TRANSBCONF; int pf_ctl_reg = (pipe == 0) ? PFA_CTL_1 : PFB_CTL_1; + int pf_win_size = (pipe == 0) ? PFA_WIN_SZ : PFB_WIN_SZ; int cpu_htot_reg = (pipe == 0) ? HTOTAL_A : HTOTAL_B; int cpu_hblank_reg = (pipe == 0) ? HBLANK_A : HBLANK_B; int cpu_hsync_reg = (pipe == 0) ? HSYNC_A : HSYNC_B; @@ -1028,7 +1167,7 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) int trans_vblank_reg = (pipe == 0) ? TRANS_VBLANK_A : TRANS_VBLANK_B; int trans_vsync_reg = (pipe == 0) ? TRANS_VSYNC_A : TRANS_VSYNC_B; u32 temp; - int tries = 5, j; + int tries = 5, j, n; /* XXX: When our outputs are all unaware of DPMS modes other than off * and on, we should map those modes to DRM_MODE_DPMS_OFF in the CRTC. @@ -1038,27 +1177,32 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) case DRM_MODE_DPMS_STANDBY: case DRM_MODE_DPMS_SUSPEND: DRM_DEBUG("crtc %d dpms on\n", pipe); - /* enable PCH DPLL */ - temp = I915_READ(pch_dpll_reg); - if ((temp & DPLL_VCO_ENABLE) == 0) { - I915_WRITE(pch_dpll_reg, temp | DPLL_VCO_ENABLE); - I915_READ(pch_dpll_reg); - } - - /* enable PCH FDI RX PLL, wait warmup plus DMI latency */ - temp = I915_READ(fdi_rx_reg); - I915_WRITE(fdi_rx_reg, temp | FDI_RX_PLL_ENABLE | - FDI_SEL_PCDCLK | - FDI_DP_PORT_WIDTH_X4); /* default 4 lanes */ - I915_READ(fdi_rx_reg); - udelay(200); + if (HAS_eDP) { + /* enable eDP PLL */ + igdng_enable_pll_edp(crtc); + } else { + /* enable PCH DPLL */ + temp = I915_READ(pch_dpll_reg); + if ((temp & DPLL_VCO_ENABLE) == 0) { + I915_WRITE(pch_dpll_reg, temp | DPLL_VCO_ENABLE); + I915_READ(pch_dpll_reg); + } - /* Enable CPU FDI TX PLL, always on for IGDNG */ - temp = I915_READ(fdi_tx_reg); - if ((temp & FDI_TX_PLL_ENABLE) == 0) { - I915_WRITE(fdi_tx_reg, temp | FDI_TX_PLL_ENABLE); - I915_READ(fdi_tx_reg); - udelay(100); + /* enable PCH FDI RX PLL, wait warmup plus DMI latency */ + temp = I915_READ(fdi_rx_reg); + I915_WRITE(fdi_rx_reg, temp | FDI_RX_PLL_ENABLE | + FDI_SEL_PCDCLK | + FDI_DP_PORT_WIDTH_X4); /* default 4 lanes */ + I915_READ(fdi_rx_reg); + udelay(200); + + /* Enable CPU FDI TX PLL, always on for IGDNG */ + temp = I915_READ(fdi_tx_reg); + if ((temp & FDI_TX_PLL_ENABLE) == 0) { + I915_WRITE(fdi_tx_reg, temp | FDI_TX_PLL_ENABLE); + I915_READ(fdi_tx_reg); + udelay(100); + } } /* Enable CPU pipe */ @@ -1077,122 +1221,126 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) I915_WRITE(dspbase_reg, I915_READ(dspbase_reg)); } - /* enable CPU FDI TX and PCH FDI RX */ - temp = I915_READ(fdi_tx_reg); - temp |= FDI_TX_ENABLE; - temp |= FDI_DP_PORT_WIDTH_X4; /* default */ - temp &= ~FDI_LINK_TRAIN_NONE; - temp |= FDI_LINK_TRAIN_PATTERN_1; - I915_WRITE(fdi_tx_reg, temp); - I915_READ(fdi_tx_reg); + if (!HAS_eDP) { + /* enable CPU FDI TX and PCH FDI RX */ + temp = I915_READ(fdi_tx_reg); + temp |= FDI_TX_ENABLE; + temp |= FDI_DP_PORT_WIDTH_X4; /* default */ + temp &= ~FDI_LINK_TRAIN_NONE; + temp |= FDI_LINK_TRAIN_PATTERN_1; + I915_WRITE(fdi_tx_reg, temp); + I915_READ(fdi_tx_reg); - temp = I915_READ(fdi_rx_reg); - temp &= ~FDI_LINK_TRAIN_NONE; - temp |= FDI_LINK_TRAIN_PATTERN_1; - I915_WRITE(fdi_rx_reg, temp | FDI_RX_ENABLE); - I915_READ(fdi_rx_reg); + temp = I915_READ(fdi_rx_reg); + temp &= ~FDI_LINK_TRAIN_NONE; + temp |= FDI_LINK_TRAIN_PATTERN_1; + I915_WRITE(fdi_rx_reg, temp | FDI_RX_ENABLE); + I915_READ(fdi_rx_reg); - udelay(150); + udelay(150); - /* Train FDI. */ - /* umask FDI RX Interrupt symbol_lock and bit_lock bit - for train result */ - temp = I915_READ(fdi_rx_imr_reg); - temp &= ~FDI_RX_SYMBOL_LOCK; - temp &= ~FDI_RX_BIT_LOCK; - I915_WRITE(fdi_rx_imr_reg, temp); - I915_READ(fdi_rx_imr_reg); - udelay(150); + /* Train FDI. */ + /* umask FDI RX Interrupt symbol_lock and bit_lock bit + for train result */ + temp = I915_READ(fdi_rx_imr_reg); + temp &= ~FDI_RX_SYMBOL_LOCK; + temp &= ~FDI_RX_BIT_LOCK; + I915_WRITE(fdi_rx_imr_reg, temp); + I915_READ(fdi_rx_imr_reg); + udelay(150); - temp = I915_READ(fdi_rx_iir_reg); - DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); + temp = I915_READ(fdi_rx_iir_reg); + DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); - if ((temp & FDI_RX_BIT_LOCK) == 0) { - for (j = 0; j < tries; j++) { - temp = I915_READ(fdi_rx_iir_reg); - DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); - if (temp & FDI_RX_BIT_LOCK) - break; - udelay(200); - } - if (j != tries) + if ((temp & FDI_RX_BIT_LOCK) == 0) { + for (j = 0; j < tries; j++) { + temp = I915_READ(fdi_rx_iir_reg); + DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); + if (temp & FDI_RX_BIT_LOCK) + break; + udelay(200); + } + if (j != tries) + I915_WRITE(fdi_rx_iir_reg, + temp | FDI_RX_BIT_LOCK); + else + DRM_DEBUG("train 1 fail\n"); + } else { I915_WRITE(fdi_rx_iir_reg, temp | FDI_RX_BIT_LOCK); - else - DRM_DEBUG("train 1 fail\n"); - } else { - I915_WRITE(fdi_rx_iir_reg, - temp | FDI_RX_BIT_LOCK); - DRM_DEBUG("train 1 ok 2!\n"); - } - temp = I915_READ(fdi_tx_reg); - temp &= ~FDI_LINK_TRAIN_NONE; - temp |= FDI_LINK_TRAIN_PATTERN_2; - I915_WRITE(fdi_tx_reg, temp); - - temp = I915_READ(fdi_rx_reg); - temp &= ~FDI_LINK_TRAIN_NONE; - temp |= FDI_LINK_TRAIN_PATTERN_2; - I915_WRITE(fdi_rx_reg, temp); + DRM_DEBUG("train 1 ok 2!\n"); + } + temp = I915_READ(fdi_tx_reg); + temp &= ~FDI_LINK_TRAIN_NONE; + temp |= FDI_LINK_TRAIN_PATTERN_2; + I915_WRITE(fdi_tx_reg, temp); + + temp = I915_READ(fdi_rx_reg); + temp &= ~FDI_LINK_TRAIN_NONE; + temp |= FDI_LINK_TRAIN_PATTERN_2; + I915_WRITE(fdi_rx_reg, temp); - udelay(150); + udelay(150); - temp = I915_READ(fdi_rx_iir_reg); - DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); + temp = I915_READ(fdi_rx_iir_reg); + DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); - if ((temp & FDI_RX_SYMBOL_LOCK) == 0) { - for (j = 0; j < tries; j++) { - temp = I915_READ(fdi_rx_iir_reg); - DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); - if (temp & FDI_RX_SYMBOL_LOCK) - break; - udelay(200); - } - if (j != tries) { + if ((temp & FDI_RX_SYMBOL_LOCK) == 0) { + for (j = 0; j < tries; j++) { + temp = I915_READ(fdi_rx_iir_reg); + DRM_DEBUG("FDI_RX_IIR 0x%x\n", temp); + if (temp & FDI_RX_SYMBOL_LOCK) + break; + udelay(200); + } + if (j != tries) { + I915_WRITE(fdi_rx_iir_reg, + temp | FDI_RX_SYMBOL_LOCK); + DRM_DEBUG("train 2 ok 1!\n"); + } else + DRM_DEBUG("train 2 fail\n"); + } else { I915_WRITE(fdi_rx_iir_reg, temp | FDI_RX_SYMBOL_LOCK); - DRM_DEBUG("train 2 ok 1!\n"); - } else - DRM_DEBUG("train 2 fail\n"); - } else { - I915_WRITE(fdi_rx_iir_reg, temp | FDI_RX_SYMBOL_LOCK); - DRM_DEBUG("train 2 ok 2!\n"); - } - DRM_DEBUG("train done\n"); + DRM_DEBUG("train 2 ok 2!\n"); + } + DRM_DEBUG("train done\n"); - /* set transcoder timing */ - I915_WRITE(trans_htot_reg, I915_READ(cpu_htot_reg)); - I915_WRITE(trans_hblank_reg, I915_READ(cpu_hblank_reg)); - I915_WRITE(trans_hsync_reg, I915_READ(cpu_hsync_reg)); + /* set transcoder timing */ + I915_WRITE(trans_htot_reg, I915_READ(cpu_htot_reg)); + I915_WRITE(trans_hblank_reg, I915_READ(cpu_hblank_reg)); + I915_WRITE(trans_hsync_reg, I915_READ(cpu_hsync_reg)); - I915_WRITE(trans_vtot_reg, I915_READ(cpu_vtot_reg)); - I915_WRITE(trans_vblank_reg, I915_READ(cpu_vblank_reg)); - I915_WRITE(trans_vsync_reg, I915_READ(cpu_vsync_reg)); + I915_WRITE(trans_vtot_reg, I915_READ(cpu_vtot_reg)); + I915_WRITE(trans_vblank_reg, I915_READ(cpu_vblank_reg)); + I915_WRITE(trans_vsync_reg, I915_READ(cpu_vsync_reg)); - /* enable PCH transcoder */ - temp = I915_READ(transconf_reg); - I915_WRITE(transconf_reg, temp | TRANS_ENABLE); - I915_READ(transconf_reg); + /* enable PCH transcoder */ + temp = I915_READ(transconf_reg); + I915_WRITE(transconf_reg, temp | TRANS_ENABLE); + I915_READ(transconf_reg); - while ((I915_READ(transconf_reg) & TRANS_STATE_ENABLE) == 0) - ; + while ((I915_READ(transconf_reg) & TRANS_STATE_ENABLE) == 0) + ; - /* enable normal */ + /* enable normal */ - temp = I915_READ(fdi_tx_reg); - temp &= ~FDI_LINK_TRAIN_NONE; - I915_WRITE(fdi_tx_reg, temp | FDI_LINK_TRAIN_NONE | - FDI_TX_ENHANCE_FRAME_ENABLE); - I915_READ(fdi_tx_reg); + temp = I915_READ(fdi_tx_reg); + temp &= ~FDI_LINK_TRAIN_NONE; + I915_WRITE(fdi_tx_reg, temp | FDI_LINK_TRAIN_NONE | + FDI_TX_ENHANCE_FRAME_ENABLE); + I915_READ(fdi_tx_reg); - temp = I915_READ(fdi_rx_reg); - temp &= ~FDI_LINK_TRAIN_NONE; - I915_WRITE(fdi_rx_reg, temp | FDI_LINK_TRAIN_NONE | - FDI_RX_ENHANCE_FRAME_ENABLE); - I915_READ(fdi_rx_reg); + temp = I915_READ(fdi_rx_reg); + temp &= ~FDI_LINK_TRAIN_NONE; + I915_WRITE(fdi_rx_reg, temp | FDI_LINK_TRAIN_NONE | + FDI_RX_ENHANCE_FRAME_ENABLE); + I915_READ(fdi_rx_reg); - /* wait one idle pattern time */ - udelay(100); + /* wait one idle pattern time */ + udelay(100); + + } intel_crtc_load_lut(crtc); @@ -1200,8 +1348,7 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) case DRM_MODE_DPMS_OFF: DRM_DEBUG("crtc %d dpms off\n", pipe); - /* Disable the VGA plane that we never use */ - I915_WRITE(CPU_VGACNTRL, VGA_DISP_DISABLE); + i915_disable_vga(dev); /* Disable display plane */ temp = I915_READ(dspcntr_reg); @@ -1217,17 +1364,23 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) if ((temp & PIPEACONF_ENABLE) != 0) { I915_WRITE(pipeconf_reg, temp & ~PIPEACONF_ENABLE); I915_READ(pipeconf_reg); + n = 0; /* wait for cpu pipe off, pipe state */ - while ((I915_READ(pipeconf_reg) & I965_PIPECONF_ACTIVE) != 0) - ; + while ((I915_READ(pipeconf_reg) & I965_PIPECONF_ACTIVE) != 0) { + n++; + if (n < 60) { + udelay(500); + continue; + } else { + DRM_DEBUG("pipe %d off delay\n", pipe); + break; + } + } } else DRM_DEBUG("crtc %d is disabled\n", pipe); - /* IGDNG-A : disable cpu panel fitter ? */ - temp = I915_READ(pf_ctl_reg); - if ((temp & PF_ENABLE) != 0) { - I915_WRITE(pf_ctl_reg, temp & ~PF_ENABLE); - I915_READ(pf_ctl_reg); + if (HAS_eDP) { + igdng_disable_pll_edp(crtc); } /* disable CPU FDI tx and PCH FDI rx */ @@ -1239,6 +1392,8 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) I915_WRITE(fdi_rx_reg, temp & ~FDI_RX_ENABLE); I915_READ(fdi_rx_reg); + udelay(100); + /* still set train pattern 1 */ temp = I915_READ(fdi_tx_reg); temp &= ~FDI_LINK_TRAIN_NONE; @@ -1250,14 +1405,25 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) temp |= FDI_LINK_TRAIN_PATTERN_1; I915_WRITE(fdi_rx_reg, temp); + udelay(100); + /* disable PCH transcoder */ temp = I915_READ(transconf_reg); if ((temp & TRANS_ENABLE) != 0) { I915_WRITE(transconf_reg, temp & ~TRANS_ENABLE); I915_READ(transconf_reg); + n = 0; /* wait for PCH transcoder off, transcoder state */ - while ((I915_READ(transconf_reg) & TRANS_STATE_ENABLE) != 0) - ; + while ((I915_READ(transconf_reg) & TRANS_STATE_ENABLE) != 0) { + n++; + if (n < 60) { + udelay(500); + continue; + } else { + DRM_DEBUG("transcoder %d off delay\n", pipe); + break; + } + } } /* disable PCH DPLL */ @@ -1275,6 +1441,22 @@ static void igdng_crtc_dpms(struct drm_crtc *crtc, int mode) I915_READ(fdi_rx_reg); } + /* Disable CPU FDI TX PLL */ + temp = I915_READ(fdi_tx_reg); + if ((temp & FDI_TX_PLL_ENABLE) != 0) { + I915_WRITE(fdi_tx_reg, temp & ~FDI_TX_PLL_ENABLE); + I915_READ(fdi_tx_reg); + udelay(100); + } + + /* Disable PF */ + temp = I915_READ(pf_ctl_reg); + if ((temp & PF_ENABLE) != 0) { + I915_WRITE(pf_ctl_reg, temp & ~PF_ENABLE); + I915_READ(pf_ctl_reg); + } + I915_WRITE(pf_win_size, 0); + /* Wait for the clocks to turn off. */ udelay(150); break; @@ -1342,7 +1524,7 @@ static void i9xx_crtc_dpms(struct drm_crtc *crtc, int mode) //intel_crtc_dpms_video(crtc, FALSE); TODO /* Disable the VGA plane that we never use */ - I915_WRITE(VGACNTRL, VGA_DISP_DISABLE); + i915_disable_vga(dev); /* Disable display plane */ temp = I915_READ(dspcntr_reg); @@ -1623,48 +1805,72 @@ static struct intel_watermark_params igd_cursor_hplloff_wm = { IGD_FIFO_LINE_SIZE }; static struct intel_watermark_params i945_wm_info = { - I915_FIFO_LINE_SIZE, + I945_FIFO_SIZE, I915_MAX_WM, 1, - 0, - IGD_FIFO_LINE_SIZE + 2, + I915_FIFO_LINE_SIZE }; static struct intel_watermark_params i915_wm_info = { - I945_FIFO_SIZE, + I915_FIFO_SIZE, I915_MAX_WM, 1, - 0, + 2, I915_FIFO_LINE_SIZE }; static struct intel_watermark_params i855_wm_info = { I855GM_FIFO_SIZE, I915_MAX_WM, 1, - 0, + 2, I830_FIFO_LINE_SIZE }; static struct intel_watermark_params i830_wm_info = { I830_FIFO_SIZE, I915_MAX_WM, 1, - 0, + 2, I830_FIFO_LINE_SIZE }; +/** + * intel_calculate_wm - calculate watermark level + * @clock_in_khz: pixel clock + * @wm: chip FIFO params + * @pixel_size: display pixel size + * @latency_ns: memory latency for the platform + * + * Calculate the watermark level (the level at which the display plane will + * start fetching from memory again). Each chip has a different display + * FIFO size and allocation, so the caller needs to figure that out and pass + * in the correct intel_watermark_params structure. + * + * As the pixel clock runs, the FIFO will be drained at a rate that depends + * on the pixel size. When it reaches the watermark level, it'll start + * fetching FIFO line sized based chunks from memory until the FIFO fills + * past the watermark point. If the FIFO drains completely, a FIFO underrun + * will occur, and a display engine hang could result. + */ static unsigned long intel_calculate_wm(unsigned long clock_in_khz, struct intel_watermark_params *wm, int pixel_size, unsigned long latency_ns) { - unsigned long bytes_required, wm_size; + long entries_required, wm_size; + + entries_required = (clock_in_khz * pixel_size * latency_ns) / 1000000; + entries_required /= wm->cacheline_size; - bytes_required = (clock_in_khz * pixel_size * latency_ns) / 1000000; - bytes_required /= wm->cacheline_size; - wm_size = wm->fifo_size - bytes_required - wm->guard_size; + DRM_DEBUG("FIFO entries required for mode: %d\n", entries_required); - if (wm_size > wm->max_wm) + wm_size = wm->fifo_size - (entries_required + wm->guard_size); + + DRM_DEBUG("FIFO watermark level: %d\n", wm_size); + + /* Don't promote wm_size to unsigned... */ + if (wm_size > (long)wm->max_wm) wm_size = wm->max_wm; - if (wm_size == 0) + if (wm_size <= 0) wm_size = wm->default_wm; return wm_size; } @@ -1799,8 +2005,40 @@ static void igd_enable_cxsr(struct drm_device *dev, unsigned long clock, return; } -const static int latency_ns = 5000; /* default for non-igd platforms */ +const static int latency_ns = 3000; /* default for non-igd platforms */ +static int intel_get_fifo_size(struct drm_device *dev, int plane) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + uint32_t dsparb = I915_READ(DSPARB); + int size; + + if (IS_I9XX(dev)) { + if (plane == 0) + size = dsparb & 0x7f; + else + size = ((dsparb >> DSPARB_CSTART_SHIFT) & 0x7f) - + (dsparb & 0x7f); + } else if (IS_I85X(dev)) { + if (plane == 0) + size = dsparb & 0x1ff; + else + size = ((dsparb >> DSPARB_BEND_SHIFT) & 0x1ff) - + (dsparb & 0x1ff); + size >>= 1; /* Convert to cachelines */ + } else if (IS_845G(dev)) { + size = dsparb & 0x7f; + size >>= 2; /* Convert to cachelines */ + } else { + size = dsparb & 0x7f; + size >>= 1; /* Convert to cachelines */ + } + + DRM_DEBUG("FIFO size - (0x%08x) %s: %d\n", dsparb, plane ? "B" : "A", + size); + + return size; +} static void i965_update_wm(struct drm_device *dev) { @@ -1817,101 +2055,89 @@ static void i9xx_update_wm(struct drm_device *dev, int planea_clock, int planeb_clock, int sr_hdisplay, int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t fwater_lo = I915_READ(FW_BLC) & MM_FIFO_WATERMARK; - uint32_t fwater_hi = I915_READ(FW_BLC2) & LM_FIFO_WATERMARK; - int bsize, asize, cwm, bwm = 1, awm = 1, srwm = 1; - uint32_t dsparb = I915_READ(DSPARB); - int planea_entries, planeb_entries; - struct intel_watermark_params *wm_params; + uint32_t fwater_lo; + uint32_t fwater_hi; + int total_size, cacheline_size, cwm, srwm = 1; + int planea_wm, planeb_wm; + struct intel_watermark_params planea_params, planeb_params; unsigned long line_time_us; int sr_clock, sr_entries = 0; + /* Create copies of the base settings for each pipe */ if (IS_I965GM(dev) || IS_I945GM(dev)) - wm_params = &i945_wm_info; + planea_params = planeb_params = i945_wm_info; else if (IS_I9XX(dev)) - wm_params = &i915_wm_info; + planea_params = planeb_params = i915_wm_info; else - wm_params = &i855_wm_info; - - planea_entries = intel_calculate_wm(planea_clock, wm_params, - pixel_size, latency_ns); - planeb_entries = intel_calculate_wm(planeb_clock, wm_params, - pixel_size, latency_ns); - - DRM_DEBUG("FIFO entries - A: %d, B: %d\n", planea_entries, - planeb_entries); + planea_params = planeb_params = i855_wm_info; - if (IS_I9XX(dev)) { - asize = dsparb & 0x7f; - bsize = (dsparb >> DSPARB_CSTART_SHIFT) & 0x7f; - } else { - asize = dsparb & 0x1ff; - bsize = (dsparb >> DSPARB_BEND_SHIFT) & 0x1ff; - } - DRM_DEBUG("FIFO size - A: %d, B: %d\n", asize, bsize); + /* Grab a couple of global values before we overwrite them */ + total_size = planea_params.fifo_size; + cacheline_size = planea_params.cacheline_size; - /* Two extra entries for padding */ - awm = asize - (planea_entries + 2); - bwm = bsize - (planeb_entries + 2); + /* Update per-plane FIFO sizes */ + planea_params.fifo_size = intel_get_fifo_size(dev, 0); + planeb_params.fifo_size = intel_get_fifo_size(dev, 1); - /* Sanity check against potentially bad FIFO allocations */ - if (awm <= 0) { - /* pipe is on but has too few FIFO entries */ - if (planea_entries != 0) - DRM_DEBUG("plane A needs more FIFO entries\n"); - awm = 1; - } - if (bwm <= 0) { - if (planeb_entries != 0) - DRM_DEBUG("plane B needs more FIFO entries\n"); - bwm = 1; - } + planea_wm = intel_calculate_wm(planea_clock, &planea_params, + pixel_size, latency_ns); + planeb_wm = intel_calculate_wm(planeb_clock, &planeb_params, + pixel_size, latency_ns); + DRM_DEBUG("FIFO watermarks - A: %d, B: %d\n", planea_wm, planeb_wm); /* * Overlay gets an aggressive default since video jitter is bad. */ cwm = 2; - /* Calc sr entries for one pipe configs */ - if (!planea_clock || !planeb_clock) { + /* Calc sr entries for one plane configs */ + if (sr_hdisplay && (!planea_clock || !planeb_clock)) { + /* self-refresh has much higher latency */ + const static int sr_latency_ns = 6000; + sr_clock = planea_clock ? planea_clock : planeb_clock; - line_time_us = (sr_hdisplay * 1000) / sr_clock; - sr_entries = (((latency_ns / line_time_us) + 1) * pixel_size * - sr_hdisplay) / 1000; - sr_entries = roundup(sr_entries / wm_params->cacheline_size, 1); - if (sr_entries < wm_params->fifo_size) - srwm = wm_params->fifo_size - sr_entries; + line_time_us = ((sr_hdisplay * 1000) / sr_clock); + + /* Use ns/us then divide to preserve precision */ + sr_entries = (((sr_latency_ns / line_time_us) + 1) * + pixel_size * sr_hdisplay) / 1000; + sr_entries = roundup(sr_entries / cacheline_size, 1); + DRM_DEBUG("self-refresh entries: %d\n", sr_entries); + srwm = total_size - sr_entries; + if (srwm < 0) + srwm = 1; + if (IS_I9XX(dev)) + I915_WRITE(FW_BLC_SELF, (srwm & 0x3f)); } DRM_DEBUG("Setting FIFO watermarks - A: %d, B: %d, C: %d, SR %d\n", - awm, bwm, cwm, srwm); + planea_wm, planeb_wm, cwm, srwm); - fwater_lo = fwater_lo | ((bwm & 0x3f) << 16) | (awm & 0x3f); - fwater_hi = fwater_hi | (cwm & 0x1f); + fwater_lo = ((planeb_wm & 0x3f) << 16) | (planea_wm & 0x3f); + fwater_hi = (cwm & 0x1f); + + /* Set request length to 8 cachelines per fetch */ + fwater_lo = fwater_lo | (1 << 24) | (1 << 8); + fwater_hi = fwater_hi | (1 << 8); I915_WRITE(FW_BLC, fwater_lo); I915_WRITE(FW_BLC2, fwater_hi); - if (IS_I9XX(dev)) - I915_WRITE(FW_BLC_SELF, FW_BLC_SELF_EN | (srwm & 0x3f)); } static void i830_update_wm(struct drm_device *dev, int planea_clock, int pixel_size) { struct drm_i915_private *dev_priv = dev->dev_private; - uint32_t dsparb = I915_READ(DSPARB); - uint32_t fwater_lo = I915_READ(FW_BLC) & MM_FIFO_WATERMARK; - unsigned int asize, awm; - int planea_entries; - - planea_entries = intel_calculate_wm(planea_clock, &i830_wm_info, - pixel_size, latency_ns); + uint32_t fwater_lo = I915_READ(FW_BLC) & ~0xfff; + int planea_wm; - asize = dsparb & 0x7f; + i830_wm_info.fifo_size = intel_get_fifo_size(dev, 0); - awm = asize - planea_entries; + planea_wm = intel_calculate_wm(planea_clock, &i830_wm_info, + pixel_size, latency_ns); + fwater_lo |= (3<<8) | planea_wm; - fwater_lo = fwater_lo | awm; + DRM_DEBUG("Setting FIFO watermarks - A: %d\n", planea_wm); I915_WRITE(FW_BLC, fwater_lo); } @@ -1984,7 +2210,7 @@ static void intel_update_watermarks(struct drm_device *dev) if (enabled <= 0) return; - /* Single pipe configs can enable self refresh */ + /* Single plane configs can enable self refresh */ if (enabled == 1 && IS_IGD(dev)) igd_enable_cxsr(dev, sr_clock, pixel_size); else if (IS_IGD(dev)) @@ -2028,6 +2254,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, u32 dpll = 0, fp = 0, dspcntr, pipeconf; bool ok, is_sdvo = false, is_dvo = false; bool is_crt = false, is_lvds = false, is_tv = false, is_dp = false; + bool is_edp = false; struct drm_mode_config *mode_config = &dev->mode_config; struct drm_connector *connector; const intel_limit_t *limit; @@ -2043,6 +2270,7 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, int lvds_reg = LVDS; u32 temp; int sdvo_pixel_multiply; + int target_clock; drm_vblank_pre_modeset(dev, pipe); @@ -2074,6 +2302,9 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, case INTEL_OUTPUT_DISPLAYPORT: is_dp = true; break; + case INTEL_OUTPUT_EDP: + is_edp = true; + break; } num_outputs++; @@ -2125,11 +2356,29 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, } /* FDI link */ - if (IS_IGDNG(dev)) - igdng_compute_m_n(3, 4, /* lane num 4 */ - adjusted_mode->clock, - 270000, /* lane clock */ - &m_n); + if (IS_IGDNG(dev)) { + int lane, link_bw; + /* eDP doesn't require FDI link, so just set DP M/N + according to current link config */ + if (is_edp) { + struct drm_connector *edp; + target_clock = mode->clock; + edp = intel_pipe_get_output(crtc); + intel_edp_link_config(to_intel_output(edp), + &lane, &link_bw); + } else { + /* DP over FDI requires target mode clock + instead of link clock */ + if (is_dp) + target_clock = mode->clock; + else + target_clock = adjusted_mode->clock; + lane = 4; + link_bw = 270000; + } + igdng_compute_m_n(3, lane, target_clock, + link_bw, &m_n); + } if (IS_IGD(dev)) fp = (1 << clock.n) << 16 | clock.m1 << 8 | clock.m2; @@ -2250,29 +2499,15 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, dpll_reg = pch_dpll_reg; } - if (dpll & DPLL_VCO_ENABLE) { + if (is_edp) { + igdng_disable_pll_edp(crtc); + } else if ((dpll & DPLL_VCO_ENABLE)) { I915_WRITE(fp_reg, fp); I915_WRITE(dpll_reg, dpll & ~DPLL_VCO_ENABLE); I915_READ(dpll_reg); udelay(150); } - if (IS_IGDNG(dev)) { - /* enable PCH clock reference source */ - /* XXX need to change the setting for other outputs */ - u32 temp; - temp = I915_READ(PCH_DREF_CONTROL); - temp &= ~DREF_NONSPREAD_SOURCE_MASK; - temp |= DREF_NONSPREAD_CK505_ENABLE; - temp &= ~DREF_SSC_SOURCE_MASK; - temp |= DREF_SSC_SOURCE_ENABLE; - temp &= ~DREF_SSC1_ENABLE; - /* if no eDP, disable source output to CPU */ - temp &= ~DREF_CPU_SOURCE_OUTPUT_MASK; - temp |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - I915_WRITE(PCH_DREF_CONTROL, temp); - } - /* The LVDS pin pair needs to be on before the DPLLs are enabled. * This is an exception to the general rule that mode_set doesn't turn * things on. @@ -2304,23 +2539,25 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, if (is_dp) intel_dp_set_m_n(crtc, mode, adjusted_mode); - I915_WRITE(fp_reg, fp); - I915_WRITE(dpll_reg, dpll); - I915_READ(dpll_reg); - /* Wait for the clocks to stabilize. */ - udelay(150); - - if (IS_I965G(dev) && !IS_IGDNG(dev)) { - sdvo_pixel_multiply = adjusted_mode->clock / mode->clock; - I915_WRITE(dpll_md_reg, (0 << DPLL_MD_UDI_DIVIDER_SHIFT) | - ((sdvo_pixel_multiply - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT)); - } else { - /* write it again -- the BIOS does, after all */ + if (!is_edp) { + I915_WRITE(fp_reg, fp); I915_WRITE(dpll_reg, dpll); + I915_READ(dpll_reg); + /* Wait for the clocks to stabilize. */ + udelay(150); + + if (IS_I965G(dev) && !IS_IGDNG(dev)) { + sdvo_pixel_multiply = adjusted_mode->clock / mode->clock; + I915_WRITE(dpll_md_reg, (0 << DPLL_MD_UDI_DIVIDER_SHIFT) | + ((sdvo_pixel_multiply - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT)); + } else { + /* write it again -- the BIOS does, after all */ + I915_WRITE(dpll_reg, dpll); + } + I915_READ(dpll_reg); + /* Wait for the clocks to stabilize. */ + udelay(150); } - I915_READ(dpll_reg); - /* Wait for the clocks to stabilize. */ - udelay(150); I915_WRITE(htot_reg, (adjusted_mode->crtc_hdisplay - 1) | ((adjusted_mode->crtc_htotal - 1) << 16)); @@ -2350,10 +2587,14 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc, I915_WRITE(link_m1_reg, m_n.link_m); I915_WRITE(link_n1_reg, m_n.link_n); - /* enable FDI RX PLL too */ - temp = I915_READ(fdi_rx_reg); - I915_WRITE(fdi_rx_reg, temp | FDI_RX_PLL_ENABLE); - udelay(200); + if (is_edp) { + igdng_set_pll_edp(crtc, adjusted_mode->clock); + } else { + /* enable FDI RX PLL too */ + temp = I915_READ(fdi_rx_reg); + I915_WRITE(fdi_rx_reg, temp | FDI_RX_PLL_ENABLE); + udelay(200); + } } I915_WRITE(pipeconf_reg, pipeconf); @@ -2951,12 +3192,17 @@ static void intel_setup_outputs(struct drm_device *dev) if (IS_IGDNG(dev)) { int found; + if (IS_MOBILE(dev) && (I915_READ(DP_A) & DP_DETECTED)) + intel_dp_init(dev, DP_A); + if (I915_READ(HDMIB) & PORT_DETECTED) { /* check SDVOB */ /* found = intel_sdvo_init(dev, HDMIB); */ found = 0; if (!found) intel_hdmi_init(dev, HDMIB); + if (!found && (I915_READ(PCH_DP_B) & DP_DETECTED)) + intel_dp_init(dev, PCH_DP_B); } if (I915_READ(HDMIC) & PORT_DETECTED) @@ -2965,6 +3211,12 @@ static void intel_setup_outputs(struct drm_device *dev) if (I915_READ(HDMID) & PORT_DETECTED) intel_hdmi_init(dev, HDMID); + if (I915_READ(PCH_DP_C) & DP_DETECTED) + intel_dp_init(dev, PCH_DP_C); + + if (I915_READ(PCH_DP_D) & DP_DETECTED) + intel_dp_init(dev, PCH_DP_D); + } else if (IS_I9XX(dev)) { int found; u32 reg; @@ -3039,6 +3291,10 @@ static void intel_setup_outputs(struct drm_device *dev) (1 << 1)); clone_mask = (1 << INTEL_OUTPUT_DISPLAYPORT); break; + case INTEL_OUTPUT_EDP: + crtc_mask = (1 << 1); + clone_mask = (1 << INTEL_OUTPUT_EDP); + break; } encoder->possible_crtcs = crtc_mask; encoder->possible_clones = intel_connector_clones(dev, clone_mask); @@ -3148,6 +3404,9 @@ void intel_modeset_init(struct drm_device *dev) if (IS_I965G(dev)) { dev->mode_config.max_width = 8192; dev->mode_config.max_height = 8192; + } else if (IS_I9XX(dev)) { + dev->mode_config.max_width = 4096; + dev->mode_config.max_height = 4096; } else { dev->mode_config.max_width = 2048; dev->mode_config.max_height = 2048; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 6770ae8..a6ff15a 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -40,6 +40,8 @@ #define DP_LINK_CONFIGURATION_SIZE 9 +#define IS_eDP(i) ((i)->type == INTEL_OUTPUT_EDP) + struct intel_dp_priv { uint32_t output_reg; uint32_t DP; @@ -63,6 +65,19 @@ intel_dp_link_train(struct intel_output *intel_output, uint32_t DP, static void intel_dp_link_down(struct intel_output *intel_output, uint32_t DP); +void +intel_edp_link_config (struct intel_output *intel_output, + int *lane_num, int *link_bw) +{ + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + + *lane_num = dp_priv->lane_count; + if (dp_priv->link_bw == DP_LINK_BW_1_62) + *link_bw = 162000; + else if (dp_priv->link_bw == DP_LINK_BW_2_7) + *link_bw = 270000; +} + static int intel_dp_max_lane_count(struct intel_output *intel_output) { @@ -206,7 +221,13 @@ intel_dp_aux_ch(struct intel_output *intel_output, * and would like to run at 2MHz. So, take the * hrawclk value and divide by 2 and use that */ - aux_clock_divider = intel_hrawclk(dev) / 2; + if (IS_eDP(intel_output)) + aux_clock_divider = 225; /* eDP input clock at 450Mhz */ + else if (IS_IGDNG(dev)) + aux_clock_divider = 62; /* IGDNG: input clock fixed at 125Mhz */ + else + aux_clock_divider = intel_hrawclk(dev) / 2; + /* Must try at least 3 times according to DP spec */ for (try = 0; try < 5; try++) { /* Load the send data into the aux channel data registers */ @@ -236,7 +257,7 @@ intel_dp_aux_ch(struct intel_output *intel_output, } /* Clear done status and any errors */ - I915_WRITE(ch_ctl, (ctl | + I915_WRITE(ch_ctl, (status | DP_AUX_CH_CTL_DONE | DP_AUX_CH_CTL_TIME_OUT_ERROR | DP_AUX_CH_CTL_RECEIVE_ERROR)); @@ -295,7 +316,7 @@ intel_dp_aux_native_write(struct intel_output *intel_output, return -1; msg[0] = AUX_NATIVE_WRITE << 4; msg[1] = address >> 8; - msg[2] = address; + msg[2] = address & 0xff; msg[3] = send_bytes - 1; memcpy(&msg[4], send, send_bytes); msg_bytes = send_bytes + 4; @@ -387,8 +408,8 @@ intel_dp_i2c_init(struct intel_output *intel_output, const char *name) memset(&dp_priv->adapter, '\0', sizeof (dp_priv->adapter)); dp_priv->adapter.owner = THIS_MODULE; dp_priv->adapter.class = I2C_CLASS_DDC; - strncpy (dp_priv->adapter.name, name, sizeof dp_priv->adapter.name - 1); - dp_priv->adapter.name[sizeof dp_priv->adapter.name - 1] = '\0'; + strncpy (dp_priv->adapter.name, name, sizeof(dp_priv->adapter.name) - 1); + dp_priv->adapter.name[sizeof(dp_priv->adapter.name) - 1] = '\0'; dp_priv->adapter.algo_data = &dp_priv->algo; dp_priv->adapter.dev.parent = &intel_output->base.kdev; @@ -493,22 +514,40 @@ intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, intel_dp_compute_m_n(3, lane_count, mode->clock, adjusted_mode->clock, &m_n); - if (intel_crtc->pipe == 0) { - I915_WRITE(PIPEA_GMCH_DATA_M, - ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | - m_n.gmch_m); - I915_WRITE(PIPEA_GMCH_DATA_N, - m_n.gmch_n); - I915_WRITE(PIPEA_DP_LINK_M, m_n.link_m); - I915_WRITE(PIPEA_DP_LINK_N, m_n.link_n); + if (IS_IGDNG(dev)) { + if (intel_crtc->pipe == 0) { + I915_WRITE(TRANSA_DATA_M1, + ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | + m_n.gmch_m); + I915_WRITE(TRANSA_DATA_N1, m_n.gmch_n); + I915_WRITE(TRANSA_DP_LINK_M1, m_n.link_m); + I915_WRITE(TRANSA_DP_LINK_N1, m_n.link_n); + } else { + I915_WRITE(TRANSB_DATA_M1, + ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | + m_n.gmch_m); + I915_WRITE(TRANSB_DATA_N1, m_n.gmch_n); + I915_WRITE(TRANSB_DP_LINK_M1, m_n.link_m); + I915_WRITE(TRANSB_DP_LINK_N1, m_n.link_n); + } } else { - I915_WRITE(PIPEB_GMCH_DATA_M, - ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | - m_n.gmch_m); - I915_WRITE(PIPEB_GMCH_DATA_N, - m_n.gmch_n); - I915_WRITE(PIPEB_DP_LINK_M, m_n.link_m); - I915_WRITE(PIPEB_DP_LINK_N, m_n.link_n); + if (intel_crtc->pipe == 0) { + I915_WRITE(PIPEA_GMCH_DATA_M, + ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | + m_n.gmch_m); + I915_WRITE(PIPEA_GMCH_DATA_N, + m_n.gmch_n); + I915_WRITE(PIPEA_DP_LINK_M, m_n.link_m); + I915_WRITE(PIPEA_DP_LINK_N, m_n.link_n); + } else { + I915_WRITE(PIPEB_GMCH_DATA_M, + ((m_n.tu - 1) << PIPE_GMCH_DATA_M_TU_SIZE_SHIFT) | + m_n.gmch_m); + I915_WRITE(PIPEB_GMCH_DATA_N, + m_n.gmch_n); + I915_WRITE(PIPEB_DP_LINK_M, m_n.link_m); + I915_WRITE(PIPEB_DP_LINK_N, m_n.link_n); + } } } @@ -556,8 +595,38 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode, if (intel_crtc->pipe == 1) dp_priv->DP |= DP_PIPEB_SELECT; + + if (IS_eDP(intel_output)) { + /* don't miss out required setting for eDP */ + dp_priv->DP |= DP_PLL_ENABLE; + if (adjusted_mode->clock < 200000) + dp_priv->DP |= DP_PLL_FREQ_160MHZ; + else + dp_priv->DP |= DP_PLL_FREQ_270MHZ; + } } +static void igdng_edp_backlight_on (struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 pp; + + DRM_DEBUG("\n"); + pp = I915_READ(PCH_PP_CONTROL); + pp |= EDP_BLC_ENABLE; + I915_WRITE(PCH_PP_CONTROL, pp); +} + +static void igdng_edp_backlight_off (struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = dev->dev_private; + u32 pp; + + DRM_DEBUG("\n"); + pp = I915_READ(PCH_PP_CONTROL); + pp &= ~EDP_BLC_ENABLE; + I915_WRITE(PCH_PP_CONTROL, pp); +} static void intel_dp_dpms(struct drm_encoder *encoder, int mode) @@ -569,11 +638,17 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode) uint32_t dp_reg = I915_READ(dp_priv->output_reg); if (mode != DRM_MODE_DPMS_ON) { - if (dp_reg & DP_PORT_EN) + if (dp_reg & DP_PORT_EN) { intel_dp_link_down(intel_output, dp_priv->DP); + if (IS_eDP(intel_output)) + igdng_edp_backlight_off(dev); + } } else { - if (!(dp_reg & DP_PORT_EN)) + if (!(dp_reg & DP_PORT_EN)) { intel_dp_link_train(intel_output, dp_priv->DP, dp_priv->link_configuration); + if (IS_eDP(intel_output)) + igdng_edp_backlight_on(dev); + } } dp_priv->dpms_mode = mode; } @@ -935,6 +1010,23 @@ intel_dp_link_down(struct intel_output *intel_output, uint32_t DP) struct drm_i915_private *dev_priv = dev->dev_private; struct intel_dp_priv *dp_priv = intel_output->dev_priv; + DRM_DEBUG("\n"); + + if (IS_eDP(intel_output)) { + DP &= ~DP_PLL_ENABLE; + I915_WRITE(dp_priv->output_reg, DP); + POSTING_READ(dp_priv->output_reg); + udelay(100); + } + + DP &= ~DP_LINK_TRAIN_MASK; + I915_WRITE(dp_priv->output_reg, DP | DP_LINK_TRAIN_PAT_IDLE); + POSTING_READ(dp_priv->output_reg); + + udelay(17000); + + if (IS_eDP(intel_output)) + DP |= DP_LINK_TRAIN_OFF; I915_WRITE(dp_priv->output_reg, DP & ~DP_PORT_EN); POSTING_READ(dp_priv->output_reg); } @@ -978,6 +1070,24 @@ intel_dp_check_link_status(struct intel_output *intel_output) intel_dp_link_train(intel_output, dp_priv->DP, dp_priv->link_configuration); } +static enum drm_connector_status +igdng_dp_detect(struct drm_connector *connector) +{ + struct intel_output *intel_output = to_intel_output(connector); + struct intel_dp_priv *dp_priv = intel_output->dev_priv; + enum drm_connector_status status; + + status = connector_status_disconnected; + if (intel_dp_aux_native_read(intel_output, + 0x000, dp_priv->dpcd, + sizeof (dp_priv->dpcd)) == sizeof (dp_priv->dpcd)) + { + if (dp_priv->dpcd[0] != 0) + status = connector_status_connected; + } + return status; +} + /** * Uses CRT_HOTPLUG_EN and CRT_HOTPLUG_STAT to detect DP connection. * @@ -996,6 +1106,9 @@ intel_dp_detect(struct drm_connector *connector) dp_priv->has_audio = false; + if (IS_IGDNG(dev)) + return igdng_dp_detect(connector); + temp = I915_READ(PORT_HOTPLUG_EN); I915_WRITE(PORT_HOTPLUG_EN, @@ -1039,11 +1152,27 @@ intel_dp_detect(struct drm_connector *connector) static int intel_dp_get_modes(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); + struct drm_device *dev = intel_output->base.dev; + struct drm_i915_private *dev_priv = dev->dev_private; + int ret; /* We should parse the EDID data and find out if it has an audio sink */ - return intel_ddc_get_modes(intel_output); + ret = intel_ddc_get_modes(intel_output); + if (ret) + return ret; + + /* if eDP has no EDID, try to use fixed panel mode from VBT */ + if (IS_eDP(intel_output)) { + if (dev_priv->panel_fixed_mode != NULL) { + struct drm_display_mode *mode; + mode = drm_mode_duplicate(dev, dev_priv->panel_fixed_mode); + drm_mode_probed_add(connector, mode); + return 1; + } + } + return 0; } static void @@ -1106,6 +1235,7 @@ intel_dp_init(struct drm_device *dev, int output_reg) struct drm_connector *connector; struct intel_output *intel_output; struct intel_dp_priv *dp_priv; + const char *name = NULL; intel_output = kcalloc(sizeof(struct intel_output) + sizeof(struct intel_dp_priv), 1, GFP_KERNEL); @@ -1119,7 +1249,10 @@ intel_dp_init(struct drm_device *dev, int output_reg) DRM_MODE_CONNECTOR_DisplayPort); drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs); - intel_output->type = INTEL_OUTPUT_DISPLAYPORT; + if (output_reg == DP_A) + intel_output->type = INTEL_OUTPUT_EDP; + else + intel_output->type = INTEL_OUTPUT_DISPLAYPORT; connector->interlace_allowed = true; connector->doublescan_allowed = 0; @@ -1139,12 +1272,41 @@ intel_dp_init(struct drm_device *dev, int output_reg) drm_sysfs_connector_add(connector); /* Set up the DDC bus. */ - intel_dp_i2c_init(intel_output, - (output_reg == DP_B) ? "DPDDC-B" : - (output_reg == DP_C) ? "DPDDC-C" : "DPDDC-D"); + switch (output_reg) { + case DP_A: + name = "DPDDC-A"; + break; + case DP_B: + case PCH_DP_B: + name = "DPDDC-B"; + break; + case DP_C: + case PCH_DP_C: + name = "DPDDC-C"; + break; + case DP_D: + case PCH_DP_D: + name = "DPDDC-D"; + break; + } + + intel_dp_i2c_init(intel_output, name); + intel_output->ddc_bus = &dp_priv->adapter; intel_output->hot_plug = intel_dp_hot_plug; + if (output_reg == DP_A) { + /* initialize panel mode from VBT if available for eDP */ + if (dev_priv->lfp_lvds_vbt_mode) { + dev_priv->panel_fixed_mode = + drm_mode_duplicate(dev, dev_priv->lfp_lvds_vbt_mode); + if (dev_priv->panel_fixed_mode) { + dev_priv->panel_fixed_mode->type |= + DRM_MODE_TYPE_PREFERRED; + } + } + } + /* For G4X desktop chip, PEG_BAND_GAP_DATA 3:0 must first be written * 0xd. Failure to do so will result in spurious interrupts being * generated on the port when a cable is not attached. diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 004541c..d6f92ea 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -55,6 +55,7 @@ #define INTEL_OUTPUT_TVOUT 5 #define INTEL_OUTPUT_HDMI 6 #define INTEL_OUTPUT_DISPLAYPORT 7 +#define INTEL_OUTPUT_EDP 8 #define INTEL_DVO_CHIP_NONE 0 #define INTEL_DVO_CHIP_LVDS 1 @@ -121,6 +122,8 @@ extern void intel_dp_init(struct drm_device *dev, int dp_reg); void intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode, struct drm_display_mode *adjusted_mode); +extern void intel_edp_link_config (struct intel_output *, int *, int *); + extern void intel_crtc_load_lut(struct drm_crtc *crtc); extern void intel_encoder_prepare (struct drm_encoder *encoder); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 9e30daa..1842290 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -130,16 +130,17 @@ static bool intel_hdmi_mode_fixup(struct drm_encoder *encoder, } static enum drm_connector_status -intel_hdmi_edid_detect(struct drm_connector *connector) +intel_hdmi_detect(struct drm_connector *connector) { struct intel_output *intel_output = to_intel_output(connector); struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; struct edid *edid = NULL; enum drm_connector_status status = connector_status_disconnected; + hdmi_priv->has_hdmi_sink = false; edid = drm_get_edid(&intel_output->base, intel_output->ddc_bus); - hdmi_priv->has_hdmi_sink = false; + if (edid) { if (edid->input & DRM_EDID_INPUT_DIGITAL) { status = connector_status_connected; @@ -148,65 +149,8 @@ intel_hdmi_edid_detect(struct drm_connector *connector) intel_output->base.display_info.raw_edid = NULL; kfree(edid); } - return status; -} - -static enum drm_connector_status -igdng_hdmi_detect(struct drm_connector *connector) -{ - struct intel_output *intel_output = to_intel_output(connector); - struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; - - /* FIXME hotplug detect */ - - hdmi_priv->has_hdmi_sink = false; - return intel_hdmi_edid_detect(connector); -} -static enum drm_connector_status -intel_hdmi_detect(struct drm_connector *connector) -{ - struct drm_device *dev = connector->dev; - struct drm_i915_private *dev_priv = dev->dev_private; - struct intel_output *intel_output = to_intel_output(connector); - struct intel_hdmi_priv *hdmi_priv = intel_output->dev_priv; - u32 temp, bit; - - if (IS_IGDNG(dev)) - return igdng_hdmi_detect(connector); - - temp = I915_READ(PORT_HOTPLUG_EN); - - switch (hdmi_priv->sdvox_reg) { - case SDVOB: - temp |= HDMIB_HOTPLUG_INT_EN; - break; - case SDVOC: - temp |= HDMIC_HOTPLUG_INT_EN; - break; - default: - return connector_status_unknown; - } - - I915_WRITE(PORT_HOTPLUG_EN, temp); - - POSTING_READ(PORT_HOTPLUG_EN); - - switch (hdmi_priv->sdvox_reg) { - case SDVOB: - bit = HDMIB_HOTPLUG_INT_STATUS; - break; - case SDVOC: - bit = HDMIC_HOTPLUG_INT_STATUS; - break; - default: - return connector_status_unknown; - } - - if ((I915_READ(PORT_HOTPLUG_STAT) & bit) != 0) - return intel_hdmi_edid_detect(connector); - else - return connector_status_disconnected; + return status; } static int intel_hdmi_get_modes(struct drm_connector *connector) diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 9ab38ef..3f445a8 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -780,6 +780,14 @@ static const struct dmi_system_id intel_no_lvds[] = { }, { .callback = intel_no_lvds_dmi_callback, + .ident = "AOpen Mini PC MP915", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AOpen"), + DMI_MATCH(DMI_BOARD_NAME, "i915GMx-F"), + }, + }, + { + .callback = intel_no_lvds_dmi_callback, .ident = "Aopen i945GTt-VFA", .matches = { DMI_MATCH(DMI_PRODUCT_VERSION, "AO00001JW"), @@ -884,6 +892,10 @@ void intel_lvds_init(struct drm_device *dev) if (IS_IGDNG(dev)) { if ((I915_READ(PCH_LVDS) & LVDS_DETECTED) == 0) return; + if (dev_priv->edp_support) { + DRM_DEBUG("disable LVDS for eDP support\n"); + return; + } gpio = PCH_GPIOC; } diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c index 4f0c309..5371d93 100644 --- a/drivers/gpu/drm/i915/intel_sdvo.c +++ b/drivers/gpu/drm/i915/intel_sdvo.c @@ -31,6 +31,7 @@ #include "drm.h" #include "drm_crtc.h" #include "intel_drv.h" +#include "drm_edid.h" #include "i915_drm.h" #include "i915_drv.h" #include "intel_sdvo_regs.h" @@ -55,6 +56,12 @@ struct intel_sdvo_priv { /* Pixel clock limitations reported by the SDVO device, in kHz */ int pixel_clock_min, pixel_clock_max; + /* + * For multiple function SDVO device, + * this is for current attached outputs. + */ + uint16_t attached_output; + /** * This is set if we're going to treat the device as TV-out. * @@ -114,6 +121,9 @@ struct intel_sdvo_priv { u32 save_SDVOX; }; +static bool +intel_sdvo_output_setup(struct intel_output *intel_output, uint16_t flags); + /** * Writes the SDVOB or SDVOC with the given value, but always writes both * SDVOB and SDVOC to work around apparent hardware issues (according to @@ -1435,41 +1445,96 @@ void intel_sdvo_set_hotplug(struct drm_connector *connector, int on) intel_sdvo_read_response(intel_output, &response, 2); } -static void -intel_sdvo_hdmi_sink_detect(struct drm_connector *connector) +static bool +intel_sdvo_multifunc_encoder(struct intel_output *intel_output) +{ + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; + int caps = 0; + + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_TMDS1)) + caps++; + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_RGB0 | SDVO_OUTPUT_RGB1)) + caps++; + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_SVID0 | SDVO_OUTPUT_SVID0)) + caps++; + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_CVBS0 | SDVO_OUTPUT_CVBS1)) + caps++; + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_YPRPB0 | SDVO_OUTPUT_YPRPB1)) + caps++; + + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_SCART0 | SDVO_OUTPUT_SCART1)) + caps++; + + if (sdvo_priv->caps.output_flags & + (SDVO_OUTPUT_LVDS0 | SDVO_OUTPUT_LVDS1)) + caps++; + + return (caps > 1); +} + +enum drm_connector_status +intel_sdvo_hdmi_sink_detect(struct drm_connector *connector, u16 response) { struct intel_output *intel_output = to_intel_output(connector); struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; + enum drm_connector_status status = connector_status_connected; struct edid *edid = NULL; edid = drm_get_edid(&intel_output->base, intel_output->ddc_bus); if (edid != NULL) { - sdvo_priv->is_hdmi = drm_detect_hdmi_monitor(edid); + /* Don't report the output as connected if it's a DVI-I + * connector with a non-digital EDID coming out. + */ + if (response & (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_TMDS1)) { + if (edid->input & DRM_EDID_INPUT_DIGITAL) + sdvo_priv->is_hdmi = + drm_detect_hdmi_monitor(edid); + else + status = connector_status_disconnected; + } + kfree(edid); intel_output->base.display_info.raw_edid = NULL; - } + + } else if (response & (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_TMDS1)) + status = connector_status_disconnected; + + return status; } static enum drm_connector_status intel_sdvo_detect(struct drm_connector *connector) { - u8 response[2]; + uint16_t response; u8 status; struct intel_output *intel_output = to_intel_output(connector); + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; intel_sdvo_write_cmd(intel_output, SDVO_CMD_GET_ATTACHED_DISPLAYS, NULL, 0); status = intel_sdvo_read_response(intel_output, &response, 2); - DRM_DEBUG("SDVO response %d %d\n", response[0], response[1]); + DRM_DEBUG("SDVO response %d %d\n", response & 0xff, response >> 8); if (status != SDVO_CMD_STATUS_SUCCESS) return connector_status_unknown; - if ((response[0] != 0) || (response[1] != 0)) { - intel_sdvo_hdmi_sink_detect(connector); - return connector_status_connected; - } else + if (response == 0) return connector_status_disconnected; + + if (intel_sdvo_multifunc_encoder(intel_output) && + sdvo_priv->attached_output != response) { + if (sdvo_priv->controlled_output != response && + intel_sdvo_output_setup(intel_output, response) != true) + return connector_status_unknown; + sdvo_priv->attached_output = response; + } + return intel_sdvo_hdmi_sink_detect(connector, response); } static void intel_sdvo_get_ddc_modes(struct drm_connector *connector) @@ -1866,16 +1931,101 @@ intel_sdvo_get_slave_addr(struct drm_device *dev, int output_device) return 0x72; } +static bool +intel_sdvo_output_setup(struct intel_output *intel_output, uint16_t flags) +{ + struct drm_connector *connector = &intel_output->base; + struct drm_encoder *encoder = &intel_output->enc; + struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv; + bool ret = true, registered = false; + + sdvo_priv->is_tv = false; + intel_output->needs_tv_clock = false; + sdvo_priv->is_lvds = false; + + if (device_is_registered(&connector->kdev)) { + drm_sysfs_connector_remove(connector); + registered = true; + } + + if (flags & + (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_TMDS1)) { + if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_TMDS0) + sdvo_priv->controlled_output = SDVO_OUTPUT_TMDS0; + else + sdvo_priv->controlled_output = SDVO_OUTPUT_TMDS1; + + encoder->encoder_type = DRM_MODE_ENCODER_TMDS; + connector->connector_type = DRM_MODE_CONNECTOR_DVID; + + if (intel_sdvo_get_supp_encode(intel_output, + &sdvo_priv->encode) && + intel_sdvo_get_digital_encoding_mode(intel_output) && + sdvo_priv->is_hdmi) { + /* enable hdmi encoding mode if supported */ + intel_sdvo_set_encode(intel_output, SDVO_ENCODE_HDMI); + intel_sdvo_set_colorimetry(intel_output, + SDVO_COLORIMETRY_RGB256); + connector->connector_type = DRM_MODE_CONNECTOR_HDMIA; + } + } else if (flags & SDVO_OUTPUT_SVID0) { + + sdvo_priv->controlled_output = SDVO_OUTPUT_SVID0; + encoder->encoder_type = DRM_MODE_ENCODER_TVDAC; + connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO; + sdvo_priv->is_tv = true; + intel_output->needs_tv_clock = true; + } else if (flags & SDVO_OUTPUT_RGB0) { + + sdvo_priv->controlled_output = SDVO_OUTPUT_RGB0; + encoder->encoder_type = DRM_MODE_ENCODER_DAC; + connector->connector_type = DRM_MODE_CONNECTOR_VGA; + } else if (flags & SDVO_OUTPUT_RGB1) { + + sdvo_priv->controlled_output = SDVO_OUTPUT_RGB1; + encoder->encoder_type = DRM_MODE_ENCODER_DAC; + connector->connector_type = DRM_MODE_CONNECTOR_VGA; + } else if (flags & SDVO_OUTPUT_LVDS0) { + + sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS0; + encoder->encoder_type = DRM_MODE_ENCODER_LVDS; + connector->connector_type = DRM_MODE_CONNECTOR_LVDS; + sdvo_priv->is_lvds = true; + } else if (flags & SDVO_OUTPUT_LVDS1) { + + sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS1; + encoder->encoder_type = DRM_MODE_ENCODER_LVDS; + connector->connector_type = DRM_MODE_CONNECTOR_LVDS; + sdvo_priv->is_lvds = true; + } else { + + unsigned char bytes[2]; + + sdvo_priv->controlled_output = 0; + memcpy(bytes, &sdvo_priv->caps.output_flags, 2); + DRM_DEBUG_KMS(I915_SDVO, + "%s: Unknown SDVO output type (0x%02x%02x)\n", + SDVO_NAME(sdvo_priv), + bytes[0], bytes[1]); + ret = false; + } + + if (ret && registered) + ret = drm_sysfs_connector_add(connector) == 0 ? true : false; + + + return ret; + +} + bool intel_sdvo_init(struct drm_device *dev, int output_device) { struct drm_connector *connector; struct intel_output *intel_output; struct intel_sdvo_priv *sdvo_priv; - int connector_type; u8 ch[0x40]; int i; - int encoder_type; intel_output = kcalloc(sizeof(struct intel_output)+sizeof(struct intel_sdvo_priv), 1, GFP_KERNEL); if (!intel_output) { @@ -1925,88 +2075,28 @@ bool intel_sdvo_init(struct drm_device *dev, int output_device) intel_output->ddc_bus->algo = &intel_sdvo_i2c_bit_algo; /* In defaut case sdvo lvds is false */ - sdvo_priv->is_lvds = false; intel_sdvo_get_capabilities(intel_output, &sdvo_priv->caps); - if (sdvo_priv->caps.output_flags & - (SDVO_OUTPUT_TMDS0 | SDVO_OUTPUT_TMDS1)) { - if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_TMDS0) - sdvo_priv->controlled_output = SDVO_OUTPUT_TMDS0; - else - sdvo_priv->controlled_output = SDVO_OUTPUT_TMDS1; - - encoder_type = DRM_MODE_ENCODER_TMDS; - connector_type = DRM_MODE_CONNECTOR_DVID; - - if (intel_sdvo_get_supp_encode(intel_output, - &sdvo_priv->encode) && - intel_sdvo_get_digital_encoding_mode(intel_output) && - sdvo_priv->is_hdmi) { - /* enable hdmi encoding mode if supported */ - intel_sdvo_set_encode(intel_output, SDVO_ENCODE_HDMI); - intel_sdvo_set_colorimetry(intel_output, - SDVO_COLORIMETRY_RGB256); - connector_type = DRM_MODE_CONNECTOR_HDMIA; - } - } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_SVID0) - { - sdvo_priv->controlled_output = SDVO_OUTPUT_SVID0; - encoder_type = DRM_MODE_ENCODER_TVDAC; - connector_type = DRM_MODE_CONNECTOR_SVIDEO; - sdvo_priv->is_tv = true; - intel_output->needs_tv_clock = true; - } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_RGB0) - { - sdvo_priv->controlled_output = SDVO_OUTPUT_RGB0; - encoder_type = DRM_MODE_ENCODER_DAC; - connector_type = DRM_MODE_CONNECTOR_VGA; - } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_RGB1) - { - sdvo_priv->controlled_output = SDVO_OUTPUT_RGB1; - encoder_type = DRM_MODE_ENCODER_DAC; - connector_type = DRM_MODE_CONNECTOR_VGA; - } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_LVDS0) - { - sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS0; - encoder_type = DRM_MODE_ENCODER_LVDS; - connector_type = DRM_MODE_CONNECTOR_LVDS; - sdvo_priv->is_lvds = true; - } - else if (sdvo_priv->caps.output_flags & SDVO_OUTPUT_LVDS1) - { - sdvo_priv->controlled_output = SDVO_OUTPUT_LVDS1; - encoder_type = DRM_MODE_ENCODER_LVDS; - connector_type = DRM_MODE_CONNECTOR_LVDS; - sdvo_priv->is_lvds = true; - } - else - { - unsigned char bytes[2]; - - sdvo_priv->controlled_output = 0; - memcpy (bytes, &sdvo_priv->caps.output_flags, 2); - DRM_DEBUG_KMS(I915_SDVO, - "%s: Unknown SDVO output type (0x%02x%02x)\n", - SDVO_NAME(sdvo_priv), - bytes[0], bytes[1]); - encoder_type = DRM_MODE_ENCODER_NONE; - connector_type = DRM_MODE_CONNECTOR_Unknown; + if (intel_sdvo_output_setup(intel_output, + sdvo_priv->caps.output_flags) != true) { + DRM_DEBUG("SDVO output failed to setup on SDVO%c\n", + output_device == SDVOB ? 'B' : 'C'); goto err_i2c; } + connector = &intel_output->base; drm_connector_init(dev, connector, &intel_sdvo_connector_funcs, - connector_type); + connector->connector_type); + drm_connector_helper_add(connector, &intel_sdvo_connector_helper_funcs); connector->interlace_allowed = 0; connector->doublescan_allowed = 0; connector->display_info.subpixel_order = SubPixelHorizontalRGB; - drm_encoder_init(dev, &intel_output->enc, &intel_sdvo_enc_funcs, encoder_type); + drm_encoder_init(dev, &intel_output->enc, + &intel_sdvo_enc_funcs, intel_output->enc.encoder_type); + drm_encoder_helper_add(&intel_output->enc, &intel_sdvo_helper_funcs); drm_mode_connector_attach_encoder(&intel_output->base, &intel_output->enc); diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c index a43c98e..da4ab4d 100644 --- a/drivers/gpu/drm/i915/intel_tv.c +++ b/drivers/gpu/drm/i915/intel_tv.c @@ -1490,6 +1490,27 @@ static struct input_res { {"1920x1080", 1920, 1080}, }; +/* + * Chose preferred mode according to line number of TV format + */ +static void +intel_tv_chose_preferred_modes(struct drm_connector *connector, + struct drm_display_mode *mode_ptr) +{ + struct intel_output *intel_output = to_intel_output(connector); + const struct tv_mode *tv_mode = intel_tv_mode_find(intel_output); + + if (tv_mode->nbr_end < 480 && mode_ptr->vdisplay == 480) + mode_ptr->type |= DRM_MODE_TYPE_PREFERRED; + else if (tv_mode->nbr_end > 480) { + if (tv_mode->progressive == true && tv_mode->nbr_end < 720) { + if (mode_ptr->vdisplay == 720) + mode_ptr->type |= DRM_MODE_TYPE_PREFERRED; + } else if (mode_ptr->vdisplay == 1080) + mode_ptr->type |= DRM_MODE_TYPE_PREFERRED; + } +} + /** * Stub get_modes function. * @@ -1544,6 +1565,7 @@ intel_tv_get_modes(struct drm_connector *connector) mode_ptr->clock = (int) tmp; mode_ptr->type = DRM_MODE_TYPE_DRIVER; + intel_tv_chose_preferred_modes(connector, mode_ptr); drm_mode_probed_add(connector, mode_ptr); count++; } diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 05a4489..f1ba8ff 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -722,13 +722,14 @@ int r100_cs_packet_parse(struct radeon_cs_parser *p, unsigned idx) { struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx]; - uint32_t header = ib_chunk->kdata[idx]; + uint32_t header; if (idx >= ib_chunk->length_dw) { DRM_ERROR("Can not parse packet at %d after CS end %d !\n", idx, ib_chunk->length_dw); return -EINVAL; } + header = ib_chunk->kdata[idx]; pkt->idx = idx; pkt->type = CP_PACKET_GET_TYPE(header); pkt->count = CP_PACKET_GET_COUNT(header); diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c index 146f357..20f1790 100644 --- a/drivers/gpu/drm/radeon/r600_cp.c +++ b/drivers/gpu/drm/radeon/r600_cp.c @@ -384,8 +384,9 @@ static void r600_cp_load_microcode(drm_radeon_private_t *dev_priv) DRM_INFO("Loading RV670 PFP Microcode\n"); for (i = 0; i < PFP_UCODE_SIZE; i++) RADEON_WRITE(R600_CP_PFP_UCODE_DATA, RV670_pfp_microcode[i]); - } else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780)) { - DRM_INFO("Loading RS780 CP Microcode\n"); + } else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780) || + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS880)) { + DRM_INFO("Loading RS780/RS880 CP Microcode\n"); for (i = 0; i < PM4_UCODE_SIZE; i++) { RADEON_WRITE(R600_CP_ME_RAM_DATA, RS780_cp_microcode[i][0]); @@ -396,7 +397,7 @@ static void r600_cp_load_microcode(drm_radeon_private_t *dev_priv) } RADEON_WRITE(R600_CP_PFP_UCODE_ADDR, 0); - DRM_INFO("Loading RS780 PFP Microcode\n"); + DRM_INFO("Loading RS780/RS880 PFP Microcode\n"); for (i = 0; i < PFP_UCODE_SIZE; i++) RADEON_WRITE(R600_CP_PFP_UCODE_DATA, RS780_pfp_microcode[i]); } @@ -783,6 +784,7 @@ static void r600_gfx_init(struct drm_device *dev, break; case CHIP_RV610: case CHIP_RS780: + case CHIP_RS880: case CHIP_RV620: dev_priv->r600_max_pipes = 1; dev_priv->r600_max_tile_pipes = 1; @@ -917,7 +919,8 @@ static void r600_gfx_init(struct drm_device *dev, ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV630) || ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV610) || ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV620) || - ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780)) + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780) || + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS880)) RADEON_WRITE(R600_DB_DEBUG, R600_PREZ_MUST_WAIT_FOR_POSTZ_DONE); else RADEON_WRITE(R600_DB_DEBUG, 0); @@ -935,7 +938,8 @@ static void r600_gfx_init(struct drm_device *dev, sq_ms_fifo_sizes = RADEON_READ(R600_SQ_MS_FIFO_SIZES); if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV610) || ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV620) || - ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780)) { + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780) || + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS880)) { sq_ms_fifo_sizes = (R600_CACHE_FIFO_SIZE(0xa) | R600_FETCH_FIFO_HIWATER(0xa) | R600_DONE_FIFO_HIWATER(0xe0) | @@ -978,7 +982,8 @@ static void r600_gfx_init(struct drm_device *dev, R600_NUM_ES_STACK_ENTRIES(0)); } else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV610) || ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV620) || - ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780)) { + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780) || + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS880)) { /* no vertex cache */ sq_config &= ~R600_VC_ENABLE; @@ -1035,7 +1040,8 @@ static void r600_gfx_init(struct drm_device *dev, if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV610) || ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV620) || - ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780)) + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS780) || + ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS880)) RADEON_WRITE(R600_VGT_CACHE_INVALIDATION, R600_CACHE_INVALIDATION(R600_TC_ONLY)); else RADEON_WRITE(R600_VGT_CACHE_INVALIDATION, R600_CACHE_INVALIDATION(R600_VC_AND_TC)); @@ -1078,6 +1084,7 @@ static void r600_gfx_init(struct drm_device *dev, break; case CHIP_RV610: case CHIP_RS780: + case CHIP_RS880: case CHIP_RV620: gs_prim_buffer_depth = 32; break; @@ -1123,6 +1130,7 @@ static void r600_gfx_init(struct drm_device *dev, switch (dev_priv->flags & RADEON_FAMILY_MASK) { case CHIP_RV610: case CHIP_RS780: + case CHIP_RS880: case CHIP_RV620: tc_cntl = R600_TC_L2_SIZE(8); break; diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index a162ade..9ff6dcb 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -152,7 +152,9 @@ int radeon_mc_setup(struct radeon_device *rdev) } } else { rdev->mc.vram_location = 0; - rdev->mc.gtt_location = rdev->mc.mc_vram_size; + tmp = rdev->mc.mc_vram_size; + tmp = (tmp + rdev->mc.gtt_size - 1) & ~(rdev->mc.gtt_size - 1); + rdev->mc.gtt_location = tmp; } DRM_INFO("radeon: VRAM %uM\n", rdev->mc.real_vram_size >> 20); DRM_INFO("radeon: VRAM from 0x%08X to 0x%08X\n", diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 3cfcee1..0bd5879 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -318,6 +318,14 @@ static int __init radeon_init(void) driver = &driver_old; driver->num_ioctls = radeon_max_ioctl; #if defined(CONFIG_DRM_RADEON_KMS) +#ifdef CONFIG_VGA_CONSOLE + if (vgacon_text_force() && radeon_modeset == -1) { + DRM_INFO("VGACON disable radeon kernel modesetting.\n"); + driver = &driver_old; + driver->driver_features &= ~DRIVER_MODESET; + radeon_modeset = 0; + } +#endif /* if enabled by default */ if (radeon_modeset == -1) { DRM_INFO("radeon default to kernel modesetting.\n"); @@ -329,17 +337,8 @@ static int __init radeon_init(void) driver->driver_features |= DRIVER_MODESET; driver->num_ioctls = radeon_max_kms_ioctl; } - /* if the vga console setting is enabled still * let modprobe override it */ -#ifdef CONFIG_VGA_CONSOLE - if (vgacon_text_force() && radeon_modeset == -1) { - DRM_INFO("VGACON disable radeon kernel modesetting.\n"); - driver = &driver_old; - driver->driver_features &= ~DRIVER_MODESET; - radeon_modeset = 0; - } -#endif #endif return drm_init(driver); } diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h index 127d045..3933f82 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.h +++ b/drivers/gpu/drm/radeon/radeon_drv.h @@ -143,6 +143,7 @@ enum radeon_family { CHIP_RV635, CHIP_RV670, CHIP_RS780, + CHIP_RS880, CHIP_RV770, CHIP_RV730, CHIP_RV710, diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 937a2f1..3357110 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -58,6 +58,8 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) if (r) { DRM_ERROR("Failed to initialize radeon, disabling IOCTL\n"); radeon_device_fini(rdev); + kfree(rdev); + dev->dev_private = NULL; return r; } return 0; diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index dd9ac2f..e98cae3 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -106,7 +106,7 @@ static inline uint32_t radeon_object_flags_from_domain(uint32_t domain) flags |= TTM_PL_FLAG_VRAM | TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED; } if (domain & RADEON_GEM_DOMAIN_GTT) { - flags |= TTM_PL_FLAG_TT | TTM_PL_FLAG_WC | TTM_PL_FLAG_UNCACHED; + flags |= TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING; } if (domain & RADEON_GEM_DOMAIN_CPU) { flags |= TTM_PL_FLAG_SYSTEM | TTM_PL_MASK_CACHING; diff --git a/drivers/gpu/drm/radeon/rv515.c b/drivers/gpu/drm/radeon/rv515.c index 551e608..fd8f3ca 100644 --- a/drivers/gpu/drm/radeon/rv515.c +++ b/drivers/gpu/drm/radeon/rv515.c @@ -370,6 +370,7 @@ void rv515_vram_info(struct radeon_device *rdev) rv515_vram_get_type(rdev); + r100_vram_init_sizes(rdev); /* FIXME: we should enforce default clock in case GPU is not in * default setup */ diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 6538d42..c2b0d71 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1182,13 +1182,14 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev, int ttm_bo_clean_mm(struct ttm_bo_device *bdev, unsigned mem_type) { - struct ttm_mem_type_manager *man = &bdev->man[mem_type]; + struct ttm_mem_type_manager *man; int ret = -EINVAL; if (mem_type >= TTM_NUM_MEM_TYPES) { printk(KERN_ERR TTM_PFX "Illegal memory type %d\n", mem_type); return ret; } + man = &bdev->man[mem_type]; if (!man->has_type) { printk(KERN_ERR TTM_PFX "Trying to take down uninitialized " @@ -1575,6 +1576,10 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, driver->sync_obj_unref(&sync_obj); driver->sync_obj_unref(&tmp_obj); spin_lock(&bo->lock); + } else { + spin_unlock(&bo->lock); + driver->sync_obj_unref(&sync_obj); + spin_lock(&bo->lock); } } return 0; diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index ce2e6f3..ad4ada0 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -150,7 +150,7 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, #ifdef CONFIG_X86 dst = kmap_atomic_prot(d, KM_USER0, prot); #else - if (prot != PAGE_KERNEL) + if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) dst = vmap(&d, 1, 0, prot); else dst = kmap(d); @@ -163,7 +163,7 @@ static int ttm_copy_io_ttm_page(struct ttm_tt *ttm, void *src, #ifdef CONFIG_X86 kunmap_atomic(dst, KM_USER0); #else - if (prot != PAGE_KERNEL) + if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) vunmap(dst); else kunmap(d); @@ -186,7 +186,7 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, #ifdef CONFIG_X86 src = kmap_atomic_prot(s, KM_USER0, prot); #else - if (prot != PAGE_KERNEL) + if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) src = vmap(&s, 1, 0, prot); else src = kmap(s); @@ -199,7 +199,7 @@ static int ttm_copy_ttm_io_page(struct ttm_tt *ttm, void *dst, #ifdef CONFIG_X86 kunmap_atomic(src, KM_USER0); #else - if (prot != PAGE_KERNEL) + if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) vunmap(src); else kunmap(s); diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index e9b2e7cb..541b981 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -27,6 +27,7 @@ struct matrix_keypad { const struct matrix_keypad_platform_data *pdata; struct input_dev *input_dev; unsigned short *keycodes; + unsigned int row_shift; uint32_t last_key_state[MATRIX_MAX_COLS]; struct delayed_work work; @@ -136,7 +137,7 @@ static void matrix_keypad_scan(struct work_struct *work) if ((bits_changed & (1 << row)) == 0) continue; - code = (row << 4) + col; + code = MATRIX_SCAN_CODE(row, col, keypad->row_shift); input_event(input_dev, EV_MSC, MSC_SCAN, code); input_report_key(input_dev, keypad->keycodes[code], @@ -317,6 +318,7 @@ static int __devinit matrix_keypad_probe(struct platform_device *pdev) struct matrix_keypad *keypad; struct input_dev *input_dev; unsigned short *keycodes; + unsigned int row_shift; int i; int err; @@ -332,14 +334,11 @@ static int __devinit matrix_keypad_probe(struct platform_device *pdev) return -EINVAL; } - if (!keymap_data->max_keymap_size) { - dev_err(&pdev->dev, "invalid keymap data supplied\n"); - return -EINVAL; - } + row_shift = get_count_order(pdata->num_col_gpios); keypad = kzalloc(sizeof(struct matrix_keypad), GFP_KERNEL); - keycodes = kzalloc(keymap_data->max_keymap_size * - sizeof(keypad->keycodes), + keycodes = kzalloc((pdata->num_row_gpios << row_shift) * + sizeof(*keycodes), GFP_KERNEL); input_dev = input_allocate_device(); if (!keypad || !keycodes || !input_dev) { @@ -350,6 +349,7 @@ static int __devinit matrix_keypad_probe(struct platform_device *pdev) keypad->input_dev = input_dev; keypad->pdata = pdata; keypad->keycodes = keycodes; + keypad->row_shift = row_shift; keypad->stopped = true; INIT_DELAYED_WORK(&keypad->work, matrix_keypad_scan); spin_lock_init(&keypad->lock); @@ -363,7 +363,7 @@ static int __devinit matrix_keypad_probe(struct platform_device *pdev) input_dev->keycode = keycodes; input_dev->keycodesize = sizeof(*keycodes); - input_dev->keycodemax = keymap_data->max_keymap_size; + input_dev->keycodemax = pdata->num_row_gpios << keypad->row_shift; for (i = 0; i < keymap_data->keymap_size; i++) { unsigned int key = keymap_data->keymap[i]; @@ -371,7 +371,7 @@ static int __devinit matrix_keypad_probe(struct platform_device *pdev) unsigned int col = KEY_COL(key); unsigned short code = KEY_VAL(key); - keycodes[(row << 4) + col] = code; + keycodes[MATRIX_SCAN_CODE(row, col, row_shift)] = code; __set_bit(code, input_dev->keybit); } __clear_bit(KEY_RESERVED, input_dev->keybit); diff --git a/drivers/input/misc/wistron_btns.c b/drivers/input/misc/wistron_btns.c index 26e17a9..27ee976 100644 --- a/drivers/input/misc/wistron_btns.c +++ b/drivers/input/misc/wistron_btns.c @@ -611,6 +611,20 @@ static struct key_entry keymap_wistron_generic[] __initdata = { { KE_END, 0 } }; +static struct key_entry keymap_prestigio[] __initdata = { + { KE_KEY, 0x11, {KEY_PROG1} }, + { KE_KEY, 0x12, {KEY_PROG2} }, + { KE_WIFI, 0x30 }, + { KE_KEY, 0x22, {KEY_REWIND} }, + { KE_KEY, 0x23, {KEY_FORWARD} }, + { KE_KEY, 0x24, {KEY_PLAYPAUSE} }, + { KE_KEY, 0x25, {KEY_STOPCD} }, + { KE_KEY, 0x31, {KEY_MAIL} }, + { KE_KEY, 0x36, {KEY_WWW} }, + { KE_END, 0 } +}; + + /* * If your machine is not here (which is currently rather likely), please send * a list of buttons and their key codes (reported when loading this module @@ -971,6 +985,8 @@ static int __init select_keymap(void) if (keymap_name != NULL) { if (strcmp (keymap_name, "1557/MS2141") == 0) keymap = keymap_wistron_ms2141; + else if (strcmp (keymap_name, "prestigio") == 0) + keymap = keymap_prestigio; else if (strcmp (keymap_name, "generic") == 0) keymap = keymap_wistron_generic; else { diff --git a/drivers/input/serio/hp_sdc_mlc.c b/drivers/input/serio/hp_sdc_mlc.c index b587e2d..820e516 100644 --- a/drivers/input/serio/hp_sdc_mlc.c +++ b/drivers/input/serio/hp_sdc_mlc.c @@ -296,7 +296,7 @@ static void hp_sdc_mlc_out(hil_mlc *mlc) priv->tseq[3] = 0; if (mlc->opacket & HIL_CTRL_APE) { priv->tseq[3] |= HP_SDC_LPC_APE_IPF; - down_trylock(&mlc->csem); + BUG_ON(down_trylock(&mlc->csem)); } enqueue: hp_sdc_enqueue_transaction(&priv->trans); diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 924e8ed..ae04d8a 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -78,6 +78,14 @@ static struct dmi_system_id __initdata i8042_dmi_noloop_table[] = { }, }, { + .ident = "ASUS G1S", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_BOARD_NAME, "G1S"), + DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + }, + }, + { /* AUX LOOP command does not raise AUX IRQ */ .ident = "ASUS P65UP5", .matches = { diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index c3b661a..7e5f30d 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -1480,7 +1480,7 @@ l1oip_init(void) return -ENOMEM; l1oip_cnt = 0; - while (type[l1oip_cnt] && l1oip_cnt < MAX_CARDS) { + while (l1oip_cnt < MAX_CARDS && type[l1oip_cnt]) { switch (type[l1oip_cnt] & 0xff) { case 1: pri = 0; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 5810fa9..5fe39c2 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -220,6 +220,7 @@ static int linear_run (mddev_t *mddev) mddev->queue->unplug_fn = linear_unplug; mddev->queue->backing_dev_info.congested_fn = linear_congested; mddev->queue->backing_dev_info.congested_data = mddev; + md_integrity_register(mddev); return 0; } @@ -256,6 +257,7 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev) rcu_assign_pointer(mddev->private, newconf); md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); call_rcu(&oldconf->rcu, free_conf); return 0; } diff --git a/drivers/md/md.c b/drivers/md/md.c index d4351ff..103f2d3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -359,6 +359,7 @@ static mddev_t * mddev_find(dev_t unit) else new->md_minor = MINOR(unit) >> MdpMinorShift; + mutex_init(&new->open_mutex); mutex_init(&new->reconfig_mutex); INIT_LIST_HEAD(&new->disks); INIT_LIST_HEAD(&new->all_mddevs); @@ -1308,7 +1309,12 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) } if (mddev->level != LEVEL_MULTIPATH) { int role; - role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); + if (rdev->desc_nr < 0 || + rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { + role = 0xffff; + rdev->desc_nr = -1; + } else + role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); switch(role) { case 0xffff: /* spare */ break; @@ -1394,8 +1400,14 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) if (rdev2->desc_nr+1 > max_dev) max_dev = rdev2->desc_nr+1; - if (max_dev > le32_to_cpu(sb->max_dev)) + if (max_dev > le32_to_cpu(sb->max_dev)) { + int bmask; sb->max_dev = cpu_to_le32(max_dev); + rdev->sb_size = max_dev * 2 + 256; + bmask = queue_logical_block_size(rdev->bdev->bd_disk->queue)-1; + if (rdev->sb_size & bmask) + rdev->sb_size = (rdev->sb_size | bmask) + 1; + } for (i=0; i<max_dev;i++) sb->dev_roles[i] = cpu_to_le16(0xfffe); @@ -1487,37 +1499,76 @@ static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2) static LIST_HEAD(pending_raid_disks); -static void md_integrity_check(mdk_rdev_t *rdev, mddev_t *mddev) +/* + * Try to register data integrity profile for an mddev + * + * This is called when an array is started and after a disk has been kicked + * from the array. It only succeeds if all working and active component devices + * are integrity capable with matching profiles. + */ +int md_integrity_register(mddev_t *mddev) +{ + mdk_rdev_t *rdev, *reference = NULL; + + if (list_empty(&mddev->disks)) + return 0; /* nothing to do */ + if (blk_get_integrity(mddev->gendisk)) + return 0; /* already registered */ + list_for_each_entry(rdev, &mddev->disks, same_set) { + /* skip spares and non-functional disks */ + if (test_bit(Faulty, &rdev->flags)) + continue; + if (rdev->raid_disk < 0) + continue; + /* + * If at least one rdev is not integrity capable, we can not + * enable data integrity for the md device. + */ + if (!bdev_get_integrity(rdev->bdev)) + return -EINVAL; + if (!reference) { + /* Use the first rdev as the reference */ + reference = rdev; + continue; + } + /* does this rdev's profile match the reference profile? */ + if (blk_integrity_compare(reference->bdev->bd_disk, + rdev->bdev->bd_disk) < 0) + return -EINVAL; + } + /* + * All component devices are integrity capable and have matching + * profiles, register the common profile for the md device. + */ + if (blk_integrity_register(mddev->gendisk, + bdev_get_integrity(reference->bdev)) != 0) { + printk(KERN_ERR "md: failed to register integrity for %s\n", + mdname(mddev)); + return -EINVAL; + } + printk(KERN_NOTICE "md: data integrity on %s enabled\n", + mdname(mddev)); + return 0; +} +EXPORT_SYMBOL(md_integrity_register); + +/* Disable data integrity if non-capable/non-matching disk is being added */ +void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev) { - struct mdk_personality *pers = mddev->pers; - struct gendisk *disk = mddev->gendisk; struct blk_integrity *bi_rdev = bdev_get_integrity(rdev->bdev); - struct blk_integrity *bi_mddev = blk_get_integrity(disk); + struct blk_integrity *bi_mddev = blk_get_integrity(mddev->gendisk); - /* Data integrity passthrough not supported on RAID 4, 5 and 6 */ - if (pers && pers->level >= 4 && pers->level <= 6) + if (!bi_mddev) /* nothing to do */ return; - - /* If rdev is integrity capable, register profile for mddev */ - if (!bi_mddev && bi_rdev) { - if (blk_integrity_register(disk, bi_rdev)) - printk(KERN_ERR "%s: %s Could not register integrity!\n", - __func__, disk->disk_name); - else - printk(KERN_NOTICE "Enabling data integrity on %s\n", - disk->disk_name); + if (rdev->raid_disk < 0) /* skip spares */ return; - } - - /* Check that mddev and rdev have matching profiles */ - if (blk_integrity_compare(disk, rdev->bdev->bd_disk) < 0) { - printk(KERN_ERR "%s: %s/%s integrity mismatch!\n", __func__, - disk->disk_name, rdev->bdev->bd_disk->disk_name); - printk(KERN_NOTICE "Disabling data integrity on %s\n", - disk->disk_name); - blk_integrity_unregister(disk); - } + if (bi_rdev && blk_integrity_compare(mddev->gendisk, + rdev->bdev->bd_disk) >= 0) + return; + printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev)); + blk_integrity_unregister(mddev->gendisk); } +EXPORT_SYMBOL(md_integrity_add_rdev); static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) { @@ -1591,7 +1642,6 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) /* May as well allow recovery to be retried once */ mddev->recovery_disabled = 0; - md_integrity_check(rdev, mddev); return 0; fail: @@ -1925,17 +1975,14 @@ repeat: /* otherwise we have to go forward and ... */ mddev->events ++; if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */ - /* .. if the array isn't clean, insist on an odd 'events' */ - if ((mddev->events&1)==0) { - mddev->events++; + /* .. if the array isn't clean, an 'even' event must also go + * to spares. */ + if ((mddev->events&1)==0) nospares = 0; - } } else { - /* otherwise insist on an even 'events' (for clean states) */ - if ((mddev->events&1)) { - mddev->events++; + /* otherwise an 'odd' event must go to spares */ + if ((mddev->events&1)) nospares = 0; - } } } @@ -2657,6 +2704,7 @@ level_store(mddev_t *mddev, const char *buf, size_t len) ssize_t rv = len; struct mdk_personality *pers; void *priv; + mdk_rdev_t *rdev; if (mddev->pers == NULL) { if (len == 0) @@ -2736,6 +2784,12 @@ level_store(mddev_t *mddev, const char *buf, size_t len) mddev_suspend(mddev); mddev->pers->stop(mddev); module_put(mddev->pers->owner); + /* Invalidate devices that are now superfluous */ + list_for_each_entry(rdev, &mddev->disks, same_set) + if (rdev->raid_disk >= mddev->raid_disks) { + rdev->raid_disk = -1; + clear_bit(In_sync, &rdev->flags); + } mddev->pers = pers; mddev->private = priv; strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); @@ -3545,6 +3599,7 @@ max_sync_store(mddev_t *mddev, const char *buf, size_t len) if (max < mddev->resync_min) return -EINVAL; if (max < mddev->resync_max && + mddev->ro == 0 && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) return -EBUSY; @@ -3685,17 +3740,8 @@ array_size_store(mddev_t *mddev, const char *buf, size_t len) mddev->array_sectors = sectors; set_capacity(mddev->gendisk, mddev->array_sectors); - if (mddev->pers) { - struct block_device *bdev = bdget_disk(mddev->gendisk, 0); - - if (bdev) { - mutex_lock(&bdev->bd_inode->i_mutex); - i_size_write(bdev->bd_inode, - (loff_t)mddev->array_sectors << 9); - mutex_unlock(&bdev->bd_inode->i_mutex); - bdput(bdev); - } - } + if (mddev->pers) + revalidate_disk(mddev->gendisk); return len; } @@ -4048,10 +4094,6 @@ static int do_md_run(mddev_t * mddev) } strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel)); - if (pers->level >= 4 && pers->level <= 6) - /* Cannot support integrity (yet) */ - blk_integrity_unregister(mddev->gendisk); - if (mddev->reshape_position != MaxSector && pers->start_reshape == NULL) { /* This personality cannot handle reshaping... */ @@ -4189,6 +4231,7 @@ static int do_md_run(mddev_t * mddev) md_wakeup_thread(mddev->thread); md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */ + revalidate_disk(mddev->gendisk); mddev->changed = 1; md_new_event(mddev); sysfs_notify_dirent(mddev->sysfs_state); @@ -4260,12 +4303,11 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) struct gendisk *disk = mddev->gendisk; mdk_rdev_t *rdev; + mutex_lock(&mddev->open_mutex); if (atomic_read(&mddev->openers) > is_open) { printk("md: %s still in use.\n",mdname(mddev)); - return -EBUSY; - } - - if (mddev->pers) { + err = -EBUSY; + } else if (mddev->pers) { if (mddev->sync_thread) { set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); @@ -4323,7 +4365,10 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) set_disk_ro(disk, 1); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); } - +out: + mutex_unlock(&mddev->open_mutex); + if (err) + return err; /* * Free resources if final stop */ @@ -4389,7 +4434,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) blk_integrity_unregister(disk); md_new_event(mddev); sysfs_notify_dirent(mddev->sysfs_state); -out: return err; } @@ -5087,18 +5131,8 @@ static int update_size(mddev_t *mddev, sector_t num_sectors) return -ENOSPC; } rv = mddev->pers->resize(mddev, num_sectors); - if (!rv) { - struct block_device *bdev; - - bdev = bdget_disk(mddev->gendisk, 0); - if (bdev) { - mutex_lock(&bdev->bd_inode->i_mutex); - i_size_write(bdev->bd_inode, - (loff_t)mddev->array_sectors << 9); - mutex_unlock(&bdev->bd_inode->i_mutex); - bdput(bdev); - } - } + if (!rv) + revalidate_disk(mddev->gendisk); return rv; } @@ -5484,12 +5518,12 @@ static int md_open(struct block_device *bdev, fmode_t mode) } BUG_ON(mddev != bdev->bd_disk->private_data); - if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1))) + if ((err = mutex_lock_interruptible(&mddev->open_mutex))) goto out; err = 0; atomic_inc(&mddev->openers); - mddev_unlock(mddev); + mutex_unlock(&mddev->open_mutex); check_disk_change(bdev); out: diff --git a/drivers/md/md.h b/drivers/md/md.h index 9430a11..f8fc188 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -223,6 +223,16 @@ struct mddev_s * so we don't loop trying */ int in_sync; /* know to not need resync */ + /* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so + * that we are never stopping an array while it is open. + * 'reconfig_mutex' protects all other reconfiguration. + * These locks are separate due to conflicting interactions + * with bdev->bd_mutex. + * Lock ordering is: + * reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk + * bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open + */ + struct mutex open_mutex; struct mutex reconfig_mutex; atomic_t active; /* general refcount */ atomic_t openers; /* number of active opens */ @@ -431,5 +441,7 @@ extern int md_allow_write(mddev_t *mddev); extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors); extern int md_check_no_bitmap(mddev_t *mddev); +extern int md_integrity_register(mddev_t *mddev); +void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev); #endif /* _MD_MD_H */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 237fe3f..7140909 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -313,6 +313,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) set_bit(In_sync, &rdev->flags); rcu_assign_pointer(p->rdev, rdev); err = 0; + md_integrity_add_rdev(rdev, mddev); break; } @@ -345,7 +346,9 @@ static int multipath_remove_disk(mddev_t *mddev, int number) /* lost the race, try later */ err = -EBUSY; p->rdev = rdev; + goto abort; } + md_integrity_register(mddev); } abort: @@ -519,7 +522,7 @@ static int multipath_run (mddev_t *mddev) mddev->queue->unplug_fn = multipath_unplug; mddev->queue->backing_dev_info.congested_fn = multipath_congested; mddev->queue->backing_dev_info.congested_data = mddev; - + md_integrity_register(mddev); return 0; out_free_conf: diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 335f490..898e2bd 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -351,6 +351,7 @@ static int raid0_run(mddev_t *mddev) blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec); dump_zones(mddev); + md_integrity_register(mddev); return 0; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 0569efb..8726fd7 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1144,7 +1144,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) rcu_assign_pointer(p->rdev, rdev); break; } - + md_integrity_add_rdev(rdev, mddev); print_conf(conf); return err; } @@ -1178,7 +1178,9 @@ static int raid1_remove_disk(mddev_t *mddev, int number) /* lost the race, try later */ err = -EBUSY; p->rdev = rdev; + goto abort; } + md_integrity_register(mddev); } abort: @@ -2067,7 +2069,7 @@ static int run(mddev_t *mddev) mddev->queue->unplug_fn = raid1_unplug; mddev->queue->backing_dev_info.congested_fn = raid1_congested; mddev->queue->backing_dev_info.congested_data = mddev; - + md_integrity_register(mddev); return 0; out_no_mem: @@ -2132,6 +2134,7 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors) return -EINVAL; set_capacity(mddev->gendisk, mddev->array_sectors); mddev->changed = 1; + revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) { mddev->recovery_cp = mddev->dev_sectors; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7298a5e..3d9020c 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1170,6 +1170,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) break; } + md_integrity_add_rdev(rdev, mddev); print_conf(conf); return err; } @@ -1203,7 +1204,9 @@ static int raid10_remove_disk(mddev_t *mddev, int number) /* lost the race, try later */ err = -EBUSY; p->rdev = rdev; + goto abort; } + md_integrity_register(mddev); } abort: @@ -2225,6 +2228,7 @@ static int run(mddev_t *mddev) if (conf->near_copies < mddev->raid_disks) blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec); + md_integrity_register(mddev); return 0; out_free_conf: diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 3783553..b8a2c5d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3785,7 +3785,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped conf->reshape_progress < raid5_size(mddev, 0, 0)) { sector_nr = raid5_size(mddev, 0, 0) - conf->reshape_progress; - } else if (mddev->delta_disks > 0 && + } else if (mddev->delta_disks >= 0 && conf->reshape_progress > 0) sector_nr = conf->reshape_progress; sector_div(sector_nr, new_data_disks); @@ -3999,6 +3999,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski return 0; } + /* Allow raid5_quiesce to complete */ + wait_event(conf->wait_for_overlap, conf->quiesce != 2); + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) return reshape_request(mddev, sector_nr, skipped); @@ -4316,6 +4319,15 @@ raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks) return sectors * (raid_disks - conf->max_degraded); } +static void free_conf(raid5_conf_t *conf) +{ + shrink_stripes(conf); + safe_put_page(conf->spare_page); + kfree(conf->disks); + kfree(conf->stripe_hashtbl); + kfree(conf); +} + static raid5_conf_t *setup_conf(mddev_t *mddev) { raid5_conf_t *conf; @@ -4447,11 +4459,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) abort: if (conf) { - shrink_stripes(conf); - safe_put_page(conf->spare_page); - kfree(conf->disks); - kfree(conf->stripe_hashtbl); - kfree(conf); + free_conf(conf); return ERR_PTR(-EIO); } else return ERR_PTR(-ENOMEM); @@ -4501,7 +4509,26 @@ static int run(mddev_t *mddev) (old_disks-max_degraded)); /* here_old is the first stripe that we might need to read * from */ - if (here_new >= here_old) { + if (mddev->delta_disks == 0) { + /* We cannot be sure it is safe to start an in-place + * reshape. It is only safe if user-space if monitoring + * and taking constant backups. + * mdadm always starts a situation like this in + * readonly mode so it can take control before + * allowing any writes. So just check for that. + */ + if ((here_new * mddev->new_chunk_sectors != + here_old * mddev->chunk_sectors) || + mddev->ro == 0) { + printk(KERN_ERR "raid5: in-place reshape must be started" + " in read-only mode - aborting\n"); + return -EINVAL; + } + } else if (mddev->delta_disks < 0 + ? (here_new * mddev->new_chunk_sectors <= + here_old * mddev->chunk_sectors) + : (here_new * mddev->new_chunk_sectors >= + here_old * mddev->chunk_sectors)) { /* Reading from the same stripe as writing to - bad */ printk(KERN_ERR "raid5: reshape_position too early for " "auto-recovery - aborting.\n"); @@ -4629,12 +4656,8 @@ abort: md_unregister_thread(mddev->thread); mddev->thread = NULL; if (conf) { - shrink_stripes(conf); print_raid5_conf(conf); - safe_put_page(conf->spare_page); - kfree(conf->disks); - kfree(conf->stripe_hashtbl); - kfree(conf); + free_conf(conf); } mddev->private = NULL; printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev)); @@ -4649,13 +4672,10 @@ static int stop(mddev_t *mddev) md_unregister_thread(mddev->thread); mddev->thread = NULL; - shrink_stripes(conf); - kfree(conf->stripe_hashtbl); mddev->queue->backing_dev_info.congested_fn = NULL; blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ sysfs_remove_group(&mddev->kobj, &raid5_attrs_group); - kfree(conf->disks); - kfree(conf); + free_conf(conf); mddev->private = NULL; return 0; } @@ -4857,6 +4877,7 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors) return -EINVAL; set_capacity(mddev->gendisk, mddev->array_sectors); mddev->changed = 1; + revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) { mddev->recovery_cp = mddev->dev_sectors; set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); @@ -5002,7 +5023,7 @@ static int raid5_start_reshape(mddev_t *mddev) spin_unlock_irqrestore(&conf->device_lock, flags); } mddev->raid_disks = conf->raid_disks; - mddev->reshape_position = 0; + mddev->reshape_position = conf->reshape_progress; set_bit(MD_CHANGE_DEVS, &mddev->flags); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); @@ -5057,7 +5078,6 @@ static void end_reshape(raid5_conf_t *conf) */ static void raid5_finish_reshape(mddev_t *mddev) { - struct block_device *bdev; raid5_conf_t *conf = mddev->private; if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { @@ -5066,15 +5086,7 @@ static void raid5_finish_reshape(mddev_t *mddev) md_set_array_sectors(mddev, raid5_size(mddev, 0, 0)); set_capacity(mddev->gendisk, mddev->array_sectors); mddev->changed = 1; - - bdev = bdget_disk(mddev->gendisk, 0); - if (bdev) { - mutex_lock(&bdev->bd_inode->i_mutex); - i_size_write(bdev->bd_inode, - (loff_t)mddev->array_sectors << 9); - mutex_unlock(&bdev->bd_inode->i_mutex); - bdput(bdev); - } + revalidate_disk(mddev->gendisk); } else { int d; mddev->degraded = conf->raid_disks; @@ -5085,8 +5097,15 @@ static void raid5_finish_reshape(mddev_t *mddev) mddev->degraded--; for (d = conf->raid_disks ; d < conf->raid_disks - mddev->delta_disks; - d++) - raid5_remove_disk(mddev, d); + d++) { + mdk_rdev_t *rdev = conf->disks[d].rdev; + if (rdev && raid5_remove_disk(mddev, d) == 0) { + char nm[20]; + sprintf(nm, "rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + rdev->raid_disk = -1; + } + } } mddev->layout = conf->algorithm; mddev->chunk_sectors = conf->chunk_sectors; @@ -5106,12 +5125,18 @@ static void raid5_quiesce(mddev_t *mddev, int state) case 1: /* stop all writes */ spin_lock_irq(&conf->device_lock); - conf->quiesce = 1; + /* '2' tells resync/reshape to pause so that all + * active stripes can drain + */ + conf->quiesce = 2; wait_event_lock_irq(conf->wait_for_stripe, atomic_read(&conf->active_stripes) == 0 && atomic_read(&conf->active_aligned_reads) == 0, conf->device_lock, /* nothing */); + conf->quiesce = 1; spin_unlock_irq(&conf->device_lock); + /* allow reshape to continue */ + wake_up(&conf->wait_for_overlap); break; case 0: /* re-enable writes */ diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c index bae61b2..7d43083 100644 --- a/drivers/mfd/twl4030-irq.c +++ b/drivers/mfd/twl4030-irq.c @@ -180,14 +180,9 @@ static struct completion irq_event; static int twl4030_irq_thread(void *data) { long irq = (long)data; - struct irq_desc *desc = irq_to_desc(irq); static unsigned i2c_errors; static const unsigned max_i2c_errors = 100; - if (!desc) { - pr_err("twl4030: Invalid IRQ: %ld\n", irq); - return -EINVAL; - } current->flags |= PF_NOFREEZE; @@ -240,7 +235,7 @@ static int twl4030_irq_thread(void *data) } local_irq_enable(); - desc->chip->unmask(irq); + enable_irq(irq); } return 0; @@ -255,25 +250,13 @@ static int twl4030_irq_thread(void *data) * thread. All we do here is acknowledge and mask the interrupt and wakeup * the kernel thread. */ -static void handle_twl4030_pih(unsigned int irq, struct irq_desc *desc) +static irqreturn_t handle_twl4030_pih(int irq, void *devid) { /* Acknowledge, clear *AND* mask the interrupt... */ - desc->chip->ack(irq); - complete(&irq_event); -} - -static struct task_struct *start_twl4030_irq_thread(long irq) -{ - struct task_struct *thread; - - init_completion(&irq_event); - thread = kthread_run(twl4030_irq_thread, (void *)irq, "twl4030-irq"); - if (!thread) - pr_err("twl4030: could not create irq %ld thread!\n", irq); - - return thread; + disable_irq_nosync(irq); + complete(devid); + return IRQ_HANDLED; } - /*----------------------------------------------------------------------*/ /* @@ -734,18 +717,28 @@ int twl_init_irq(int irq_num, unsigned irq_base, unsigned irq_end) } /* install an irq handler to demultiplex the TWL4030 interrupt */ - task = start_twl4030_irq_thread(irq_num); - if (!task) { - pr_err("twl4030: irq thread FAIL\n"); - status = -ESRCH; - goto fail; - } - set_irq_data(irq_num, task); - set_irq_chained_handler(irq_num, handle_twl4030_pih); - return status; + init_completion(&irq_event); + status = request_irq(irq_num, handle_twl4030_pih, IRQF_DISABLED, + "TWL4030-PIH", &irq_event); + if (status < 0) { + pr_err("twl4030: could not claim irq%d: %d\n", irq_num, status); + goto fail_rqirq; + } + + task = kthread_run(twl4030_irq_thread, (void *)irq_num, "twl4030-irq"); + if (IS_ERR(task)) { + pr_err("twl4030: could not create irq %d thread!\n", irq_num); + status = PTR_ERR(task); + goto fail_kthread; + } + return status; +fail_kthread: + free_irq(irq_num, &irq_event); +fail_rqirq: + /* clean up twl4030_sih_setup */ fail: for (i = irq_base; i < irq_end; i++) set_irq_chip_and_handler(i, NULL, NULL); diff --git a/drivers/mmc/host/sdhci-of.c b/drivers/mmc/host/sdhci-of.c index 9088443..1e8aa590 100644 --- a/drivers/mmc/host/sdhci-of.c +++ b/drivers/mmc/host/sdhci-of.c @@ -234,7 +234,7 @@ static int __devinit sdhci_of_probe(struct of_device *ofdev, return -ENODEV; host = sdhci_alloc_host(&ofdev->dev, sizeof(*of_host)); - if (!host) + if (IS_ERR(host)) return -ENOMEM; of_host = sdhci_priv(host); diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig index 0b98654..7a58bd5 100644 --- a/drivers/mtd/maps/Kconfig +++ b/drivers/mtd/maps/Kconfig @@ -284,13 +284,6 @@ config MTD_L440GX BE VERY CAREFUL. -config MTD_SBC8240 - tristate "Flash device on SBC8240" - depends on MTD_JEDECPROBE && 8260 - help - Flash access on the SBC8240 board from Wind River. See - <http://www.windriver.com/products/sbc8240/> - config MTD_TQM8XXL tristate "CFI Flash device mapped on TQM8XXL" depends on MTD_CFI && TQM8xxL diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile index 8bae7f9..5beb066 100644 --- a/drivers/mtd/maps/Makefile +++ b/drivers/mtd/maps/Makefile @@ -50,7 +50,6 @@ obj-$(CONFIG_MTD_UCLINUX) += uclinux.o obj-$(CONFIG_MTD_NETtel) += nettel.o obj-$(CONFIG_MTD_SCB2_FLASH) += scb2_flash.o obj-$(CONFIG_MTD_H720X) += h720x-flash.o -obj-$(CONFIG_MTD_SBC8240) += sbc8240.o obj-$(CONFIG_MTD_IXP4XX) += ixp4xx.o obj-$(CONFIG_MTD_IXP2000) += ixp2000.o obj-$(CONFIG_MTD_WRSBC8260) += wr_sbc82xx_flash.o diff --git a/drivers/mtd/maps/sbc8240.c b/drivers/mtd/maps/sbc8240.c deleted file mode 100644 index d5374cd..0000000 --- a/drivers/mtd/maps/sbc8240.c +++ /dev/null @@ -1,250 +0,0 @@ -/* - * Handle mapping of the flash memory access routines on the SBC8240 board. - * - * Carolyn Smith, Tektronix, Inc. - * - * This code is GPLed - */ - -/* - * The SBC8240 has 2 flash banks. - * Bank 0 is a 512 KiB AMD AM29F040B; 8 x 64 KiB sectors. - * It contains the U-Boot code (7 sectors) and the environment (1 sector). - * Bank 1 is 4 x 1 MiB AMD AM29LV800BT; 15 x 64 KiB sectors, 1 x 32 KiB sector, - * 2 x 8 KiB sectors, 1 x 16 KiB sectors. - * Both parts are JEDEC compatible. - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <asm/io.h> - -#include <linux/mtd/mtd.h> -#include <linux/mtd/map.h> -#include <linux/mtd/cfi.h> - -#ifdef CONFIG_MTD_PARTITIONS -#include <linux/mtd/partitions.h> -#endif - -#define DEBUG - -#ifdef DEBUG -# define debugk(fmt,args...) printk(fmt ,##args) -#else -# define debugk(fmt,args...) -#endif - - -#define WINDOW_ADDR0 0xFFF00000 /* 512 KiB */ -#define WINDOW_SIZE0 0x00080000 -#define BUSWIDTH0 1 - -#define WINDOW_ADDR1 0xFF000000 /* 4 MiB */ -#define WINDOW_SIZE1 0x00400000 -#define BUSWIDTH1 8 - -#define MSG_PREFIX "sbc8240:" /* prefix for our printk()'s */ -#define MTDID "sbc8240-%d" /* for mtdparts= partitioning */ - - -static struct map_info sbc8240_map[2] = { - { - .name = "sbc8240 Flash Bank #0", - .size = WINDOW_SIZE0, - .bankwidth = BUSWIDTH0, - }, - { - .name = "sbc8240 Flash Bank #1", - .size = WINDOW_SIZE1, - .bankwidth = BUSWIDTH1, - } -}; - -#define NUM_FLASH_BANKS ARRAY_SIZE(sbc8240_map) - -/* - * The following defines the partition layout of SBC8240 boards. - * - * See include/linux/mtd/partitions.h for definition of the - * mtd_partition structure. - * - * The *_max_flash_size is the maximum possible mapped flash size - * which is not necessarily the actual flash size. It must correspond - * to the value specified in the mapping definition defined by the - * "struct map_desc *_io_desc" for the corresponding machine. - */ - -#ifdef CONFIG_MTD_PARTITIONS - -static struct mtd_partition sbc8240_uboot_partitions [] = { - /* Bank 0 */ - { - .name = "U-boot", /* U-Boot Firmware */ - .offset = 0, - .size = 0x00070000, /* 7 x 64 KiB sectors */ - .mask_flags = MTD_WRITEABLE, /* force read-only */ - }, - { - .name = "environment", /* U-Boot environment */ - .offset = 0x00070000, - .size = 0x00010000, /* 1 x 64 KiB sector */ - }, -}; - -static struct mtd_partition sbc8240_fs_partitions [] = { - { - .name = "jffs", /* JFFS filesystem */ - .offset = 0, - .size = 0x003C0000, /* 4 * 15 * 64KiB */ - }, - { - .name = "tmp32", - .offset = 0x003C0000, - .size = 0x00020000, /* 4 * 32KiB */ - }, - { - .name = "tmp8a", - .offset = 0x003E0000, - .size = 0x00008000, /* 4 * 8KiB */ - }, - { - .name = "tmp8b", - .offset = 0x003E8000, - .size = 0x00008000, /* 4 * 8KiB */ - }, - { - .name = "tmp16", - .offset = 0x003F0000, - .size = 0x00010000, /* 4 * 16KiB */ - } -}; - -/* trivial struct to describe partition information */ -struct mtd_part_def -{ - int nums; - unsigned char *type; - struct mtd_partition* mtd_part; -}; - -static struct mtd_info *sbc8240_mtd[NUM_FLASH_BANKS]; -static struct mtd_part_def sbc8240_part_banks[NUM_FLASH_BANKS]; - - -#endif /* CONFIG_MTD_PARTITIONS */ - - -static int __init init_sbc8240_mtd (void) -{ - static struct _cjs { - u_long addr; - u_long size; - } pt[NUM_FLASH_BANKS] = { - { - .addr = WINDOW_ADDR0, - .size = WINDOW_SIZE0 - }, - { - .addr = WINDOW_ADDR1, - .size = WINDOW_SIZE1 - }, - }; - - int devicesfound = 0; - int i,j; - - for (i = 0; i < NUM_FLASH_BANKS; i++) { - printk (KERN_NOTICE MSG_PREFIX - "Probing 0x%08lx at 0x%08lx\n", pt[i].size, pt[i].addr); - - sbc8240_map[i].map_priv_1 = - (unsigned long) ioremap (pt[i].addr, pt[i].size); - if (!sbc8240_map[i].map_priv_1) { - printk (MSG_PREFIX "failed to ioremap\n"); - for (j = 0; j < i; j++) { - iounmap((void *) sbc8240_map[j].map_priv_1); - sbc8240_map[j].map_priv_1 = 0; - } - return -EIO; - } - simple_map_init(&sbc8240_mtd[i]); - - sbc8240_mtd[i] = do_map_probe("jedec_probe", &sbc8240_map[i]); - - if (sbc8240_mtd[i]) { - sbc8240_mtd[i]->module = THIS_MODULE; - devicesfound++; - } else { - if (sbc8240_map[i].map_priv_1) { - iounmap((void *) sbc8240_map[i].map_priv_1); - sbc8240_map[i].map_priv_1 = 0; - } - } - } - - if (!devicesfound) { - printk(KERN_NOTICE MSG_PREFIX - "No suppported flash chips found!\n"); - return -ENXIO; - } - -#ifdef CONFIG_MTD_PARTITIONS - sbc8240_part_banks[0].mtd_part = sbc8240_uboot_partitions; - sbc8240_part_banks[0].type = "static image"; - sbc8240_part_banks[0].nums = ARRAY_SIZE(sbc8240_uboot_partitions); - sbc8240_part_banks[1].mtd_part = sbc8240_fs_partitions; - sbc8240_part_banks[1].type = "static file system"; - sbc8240_part_banks[1].nums = ARRAY_SIZE(sbc8240_fs_partitions); - - for (i = 0; i < NUM_FLASH_BANKS; i++) { - - if (!sbc8240_mtd[i]) continue; - if (sbc8240_part_banks[i].nums == 0) { - printk (KERN_NOTICE MSG_PREFIX - "No partition info available, registering whole device\n"); - add_mtd_device(sbc8240_mtd[i]); - } else { - printk (KERN_NOTICE MSG_PREFIX - "Using %s partition definition\n", sbc8240_part_banks[i].mtd_part->name); - add_mtd_partitions (sbc8240_mtd[i], - sbc8240_part_banks[i].mtd_part, - sbc8240_part_banks[i].nums); - } - } -#else - printk(KERN_NOTICE MSG_PREFIX - "Registering %d flash banks at once\n", devicesfound); - - for (i = 0; i < devicesfound; i++) { - add_mtd_device(sbc8240_mtd[i]); - } -#endif /* CONFIG_MTD_PARTITIONS */ - - return devicesfound == 0 ? -ENXIO : 0; -} - -static void __exit cleanup_sbc8240_mtd (void) -{ - int i; - - for (i = 0; i < NUM_FLASH_BANKS; i++) { - if (sbc8240_mtd[i]) { - del_mtd_device (sbc8240_mtd[i]); - map_destroy (sbc8240_mtd[i]); - } - if (sbc8240_map[i].map_priv_1) { - iounmap ((void *) sbc8240_map[i].map_priv_1); - sbc8240_map[i].map_priv_1 = 0; - } - } -} - -module_init (init_sbc8240_mtd); -module_exit (cleanup_sbc8240_mtd); - -MODULE_LICENSE ("GPL"); -MODULE_AUTHOR ("Carolyn Smith <carolyn.smith@tektronix.com>"); -MODULE_DESCRIPTION ("MTD map driver for SBC8240 boards"); - diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index c3f6265..7baba40 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -144,7 +144,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) struct mtd_blktrans_ops *tr = dev->tr; int ret = -ENODEV; - if (!try_module_get(dev->mtd->owner)) + if (!get_mtd_device(NULL, dev->mtd->index)) goto out; if (!try_module_get(tr->owner)) @@ -158,7 +158,7 @@ static int blktrans_open(struct block_device *bdev, fmode_t mode) ret = 0; if (tr->open && (ret = tr->open(dev))) { dev->mtd->usecount--; - module_put(dev->mtd->owner); + put_mtd_device(dev->mtd); out_tr: module_put(tr->owner); } @@ -177,7 +177,7 @@ static int blktrans_release(struct gendisk *disk, fmode_t mode) if (!ret) { dev->mtd->usecount--; - module_put(dev->mtd->owner); + put_mtd_device(dev->mtd); module_put(tr->owner); } diff --git a/drivers/mtd/mtdblock.c b/drivers/mtd/mtdblock.c index 208c6fa..77db5ce 100644 --- a/drivers/mtd/mtdblock.c +++ b/drivers/mtd/mtdblock.c @@ -29,6 +29,8 @@ static struct mtdblk_dev { enum { STATE_EMPTY, STATE_CLEAN, STATE_DIRTY } cache_state; } *mtdblks[MAX_MTD_DEVICES]; +static struct mutex mtdblks_lock; + /* * Cache stuff... * @@ -270,15 +272,19 @@ static int mtdblock_open(struct mtd_blktrans_dev *mbd) DEBUG(MTD_DEBUG_LEVEL1,"mtdblock_open\n"); + mutex_lock(&mtdblks_lock); if (mtdblks[dev]) { mtdblks[dev]->count++; + mutex_unlock(&mtdblks_lock); return 0; } /* OK, it's not open. Create cache info for it */ mtdblk = kzalloc(sizeof(struct mtdblk_dev), GFP_KERNEL); - if (!mtdblk) + if (!mtdblk) { + mutex_unlock(&mtdblks_lock); return -ENOMEM; + } mtdblk->count = 1; mtdblk->mtd = mtd; @@ -291,6 +297,7 @@ static int mtdblock_open(struct mtd_blktrans_dev *mbd) } mtdblks[dev] = mtdblk; + mutex_unlock(&mtdblks_lock); DEBUG(MTD_DEBUG_LEVEL1, "ok\n"); @@ -304,6 +311,8 @@ static int mtdblock_release(struct mtd_blktrans_dev *mbd) DEBUG(MTD_DEBUG_LEVEL1, "mtdblock_release\n"); + mutex_lock(&mtdblks_lock); + mutex_lock(&mtdblk->cache_mutex); write_cached_data(mtdblk); mutex_unlock(&mtdblk->cache_mutex); @@ -316,6 +325,9 @@ static int mtdblock_release(struct mtd_blktrans_dev *mbd) vfree(mtdblk->cache_data); kfree(mtdblk); } + + mutex_unlock(&mtdblks_lock); + DEBUG(MTD_DEBUG_LEVEL1, "ok\n"); return 0; @@ -376,6 +388,8 @@ static struct mtd_blktrans_ops mtdblock_tr = { static int __init init_mtdblock(void) { + mutex_init(&mtdblks_lock); + return register_mtd_blktrans(&mtdblock_tr); } diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index fac54a3..00ebf7a 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -65,8 +65,8 @@ static void mtd_release(struct device *dev) static int mtd_cls_suspend(struct device *dev, pm_message_t state) { struct mtd_info *mtd = dev_to_mtd(dev); - - if (mtd->suspend) + + if (mtd && mtd->suspend) return mtd->suspend(mtd); else return 0; @@ -76,7 +76,7 @@ static int mtd_cls_resume(struct device *dev) { struct mtd_info *mtd = dev_to_mtd(dev); - if (mtd->resume) + if (mtd && mtd->resume) mtd->resume(mtd); return 0; } @@ -298,6 +298,7 @@ int add_mtd_device(struct mtd_info *mtd) mtd->dev.class = &mtd_class; mtd->dev.devt = MTD_DEVT(i); dev_set_name(&mtd->dev, "mtd%d", i); + dev_set_drvdata(&mtd->dev, mtd); if (device_register(&mtd->dev) != 0) { mtd_table[i] = NULL; break; diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c index 38d656b..0108ed4 100644 --- a/drivers/mtd/onenand/omap2.c +++ b/drivers/mtd/onenand/omap2.c @@ -266,7 +266,7 @@ static inline int omap2_onenand_bufferram_offset(struct mtd_info *mtd, int area) if (ONENAND_CURRENT_BUFFERRAM(this)) { if (area == ONENAND_DATARAM) - return mtd->writesize; + return this->writesize; if (area == ONENAND_SPARERAM) return mtd->oobsize; } @@ -770,6 +770,7 @@ static int __devexit omap2_onenand_remove(struct platform_device *pdev) } iounmap(c->onenand.base); release_mem_region(c->phys_base, ONENAND_IO_SIZE); + gpmc_cs_free(c->gpmc_cs); kfree(c); return 0; diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c index 0f2034c..e4d9ef0 100644 --- a/drivers/mtd/ubi/eba.c +++ b/drivers/mtd/ubi/eba.c @@ -1254,6 +1254,7 @@ out_free: if (!ubi->volumes[i]) continue; kfree(ubi->volumes[i]->eba_tbl); + ubi->volumes[i]->eba_tbl = NULL; } return err; } diff --git a/drivers/mtd/ubi/scan.c b/drivers/mtd/ubi/scan.c index a423131..b847745 100644 --- a/drivers/mtd/ubi/scan.c +++ b/drivers/mtd/ubi/scan.c @@ -781,11 +781,22 @@ static int process_eb(struct ubi_device *ubi, struct ubi_scan_info *si, return -EINVAL; } + /* + * Make sure that all PEBs have the same image sequence number. + * This allows us to detect situations when users flash UBI + * images incorrectly, so that the flash has the new UBI image + * and leftovers from the old one. This feature was added + * relatively recently, and the sequence number was always + * zero, because old UBI implementations always set it to zero. + * For this reasons, we do not panic if some PEBs have zero + * sequence number, while other PEBs have non-zero sequence + * number. + */ image_seq = be32_to_cpu(ech->image_seq); if (!si->image_seq_set) { ubi->image_seq = image_seq; si->image_seq_set = 1; - } else if (ubi->image_seq != image_seq) { + } else if (ubi->image_seq && ubi->image_seq != image_seq) { ubi_err("bad image sequence number %d in PEB %d, " "expected %d", image_seq, pnum, ubi->image_seq); ubi_dbg_dump_ec_hdr(ech); diff --git a/drivers/net/3c515.c b/drivers/net/3c515.c index 3e00fa8..4a7c328 100644 --- a/drivers/net/3c515.c +++ b/drivers/net/3c515.c @@ -832,7 +832,9 @@ static int corkscrew_open(struct net_device *dev) skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ vp->rx_ring[i].addr = isa_virt_to_bus(skb->data); } - vp->rx_ring[i - 1].next = isa_virt_to_bus(&vp->rx_ring[0]); /* Wrap the ring. */ + if (i != 0) + vp->rx_ring[i - 1].next = + isa_virt_to_bus(&vp->rx_ring[0]); /* Wrap the ring. */ outl(isa_virt_to_bus(&vp->rx_ring[0]), ioaddr + UpListPtr); } if (vp->full_bus_master_tx) { /* Boomerang bus master Tx. */ diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c index c34aee9..c204168 100644 --- a/drivers/net/3c59x.c +++ b/drivers/net/3c59x.c @@ -2721,13 +2721,15 @@ dump_tx_ring(struct net_device *dev) &vp->tx_ring[vp->dirty_tx % TX_RING_SIZE]); issue_and_wait(dev, DownStall); for (i = 0; i < TX_RING_SIZE; i++) { - pr_err(" %d: @%p length %8.8x status %8.8x\n", i, - &vp->tx_ring[i], + unsigned int length; + #if DO_ZEROCOPY - le32_to_cpu(vp->tx_ring[i].frag[0].length), + length = le32_to_cpu(vp->tx_ring[i].frag[0].length); #else - le32_to_cpu(vp->tx_ring[i].length), + length = le32_to_cpu(vp->tx_ring[i].length); #endif + pr_err(" %d: @%p length %8.8x status %8.8x\n", + i, &vp->tx_ring[i], length, le32_to_cpu(vp->tx_ring[i].status)); } if (!stalled) diff --git a/drivers/net/eexpress.c b/drivers/net/eexpress.c index 1686dca..1f016d6 100644 --- a/drivers/net/eexpress.c +++ b/drivers/net/eexpress.c @@ -1474,13 +1474,13 @@ static void eexp_hw_init586(struct net_device *dev) outw(0x0000, ioaddr + 0x800c); outw(0x0000, ioaddr + 0x800e); - for (i = 0; i < (sizeof(start_code)); i+=32) { + for (i = 0; i < ARRAY_SIZE(start_code) * 2; i+=32) { int j; outw(i, ioaddr + SM_PTR); - for (j = 0; j < 16; j+=2) + for (j = 0; j < 16 && (i+j)/2 < ARRAY_SIZE(start_code); j+=2) outw(start_code[(i+j)/2], ioaddr+0x4000+j); - for (j = 0; j < 16; j+=2) + for (j = 0; j < 16 && (i+j+16)/2 < ARRAY_SIZE(start_code); j+=2) outw(start_code[(i+j+16)/2], ioaddr+0x8000+j); } diff --git a/drivers/net/ehea/ehea.h b/drivers/net/ehea/ehea.h index 78952f8..fa311a9 100644 --- a/drivers/net/ehea/ehea.h +++ b/drivers/net/ehea/ehea.h @@ -40,7 +40,7 @@ #include <asm/io.h> #define DRV_NAME "ehea" -#define DRV_VERSION "EHEA_0101" +#define DRV_VERSION "EHEA_0102" /* eHEA capability flags */ #define DLPAR_PORT_ADD_REM 1 diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index e8d46cc..977c3d3 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -1545,6 +1545,9 @@ static int ehea_clean_portres(struct ehea_port *port, struct ehea_port_res *pr) { int ret, i; + if (pr->qp) + netif_napi_del(&pr->napi); + ret = ehea_destroy_qp(pr->qp); if (!ret) { diff --git a/drivers/net/gianfar_ethtool.c b/drivers/net/gianfar_ethtool.c index dbf06e9..2234118 100644 --- a/drivers/net/gianfar_ethtool.c +++ b/drivers/net/gianfar_ethtool.c @@ -366,9 +366,8 @@ static int gfar_scoalesce(struct net_device *dev, struct ethtool_coalesce *cvals return -EINVAL; } - priv->rxic = mk_ic_value( - gfar_usecs2ticks(priv, cvals->rx_coalesce_usecs), - cvals->rx_max_coalesced_frames); + priv->rxic = mk_ic_value(cvals->rx_max_coalesced_frames, + gfar_usecs2ticks(priv, cvals->rx_coalesce_usecs)); /* Set up tx coalescing */ if ((cvals->tx_coalesce_usecs == 0) || @@ -390,9 +389,8 @@ static int gfar_scoalesce(struct net_device *dev, struct ethtool_coalesce *cvals return -EINVAL; } - priv->txic = mk_ic_value( - gfar_usecs2ticks(priv, cvals->tx_coalesce_usecs), - cvals->tx_max_coalesced_frames); + priv->txic = mk_ic_value(cvals->tx_max_coalesced_frames, + gfar_usecs2ticks(priv, cvals->tx_coalesce_usecs)); gfar_write(&priv->regs->rxic, 0); if (priv->rxcoalescing) diff --git a/drivers/net/igbvf/vf.c b/drivers/net/igbvf/vf.c index 2a4faf9..a9a61ef 100644 --- a/drivers/net/igbvf/vf.c +++ b/drivers/net/igbvf/vf.c @@ -274,6 +274,8 @@ static s32 e1000_set_vfta_vf(struct e1000_hw *hw, u16 vid, bool set) err = mbx->ops.read_posted(hw, msgbuf, 2); + msgbuf[0] &= ~E1000_VT_MSGTYPE_CTS; + /* if nacked the vlan was rejected */ if (!err && (msgbuf[0] == (E1000_VF_SET_VLAN | E1000_VT_MSGTYPE_NACK))) err = -E1000_ERR_MAC_INIT; @@ -317,6 +319,8 @@ static void e1000_rar_set_vf(struct e1000_hw *hw, u8 * addr, u32 index) if (!ret_val) ret_val = mbx->ops.read_posted(hw, msgbuf, 3); + msgbuf[0] &= ~E1000_VT_MSGTYPE_CTS; + /* if nacked the address was rejected, use "perm_addr" */ if (!ret_val && (msgbuf[0] == (E1000_VF_SET_MAC_ADDR | E1000_VT_MSGTYPE_NACK))) diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h index 1b12c7b..e11d83d 100644 --- a/drivers/net/ixgbe/ixgbe.h +++ b/drivers/net/ixgbe/ixgbe.h @@ -96,6 +96,8 @@ #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 #define IXGBE_TX_FLAGS_VLAN_SHIFT 16 +#define IXGBE_MAX_RSC_INT_RATE 162760 + /* wrapper around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer */ struct ixgbe_tx_buffer { diff --git a/drivers/net/ixgbe/ixgbe_82598.c b/drivers/net/ixgbe/ixgbe_82598.c index b992304..522c03b 100644 --- a/drivers/net/ixgbe/ixgbe_82598.c +++ b/drivers/net/ixgbe/ixgbe_82598.c @@ -50,6 +50,51 @@ static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, u8 *eeprom_data); /** + * ixgbe_set_pcie_completion_timeout - set pci-e completion timeout + * @hw: pointer to the HW structure + * + * The defaults for 82598 should be in the range of 50us to 50ms, + * however the hardware default for these parts is 500us to 1ms which is less + * than the 10ms recommended by the pci-e spec. To address this we need to + * increase the value to either 10ms to 250ms for capability version 1 config, + * or 16ms to 55ms for version 2. + **/ +void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 gcr = IXGBE_READ_REG(hw, IXGBE_GCR); + u16 pcie_devctl2; + + /* only take action if timeout value is defaulted to 0 */ + if (gcr & IXGBE_GCR_CMPL_TMOUT_MASK) + goto out; + + /* + * if capababilities version is type 1 we can write the + * timeout of 10ms to 250ms through the GCR register + */ + if (!(gcr & IXGBE_GCR_CAP_VER2)) { + gcr |= IXGBE_GCR_CMPL_TMOUT_10ms; + goto out; + } + + /* + * for version 2 capabilities we need to write the config space + * directly in order to set the completion timeout value for + * 16ms to 55ms + */ + pci_read_config_word(adapter->pdev, + IXGBE_PCI_DEVICE_CONTROL2, &pcie_devctl2); + pcie_devctl2 |= IXGBE_PCI_DEVICE_CONTROL2_16ms; + pci_write_config_word(adapter->pdev, + IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2); +out: + /* disable completion timeout resend */ + gcr &= ~IXGBE_GCR_CMPL_TMOUT_RESEND; + IXGBE_WRITE_REG(hw, IXGBE_GCR, gcr); +} + +/** * ixgbe_get_pcie_msix_count_82598 - Gets MSI-X vector count * @hw: pointer to hardware structure * @@ -153,6 +198,26 @@ out: } /** + * ixgbe_start_hw_82598 - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Starts the hardware using the generic start_hw function. + * Then set pcie completion timeout + **/ +s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) +{ + s32 ret_val = 0; + + ret_val = ixgbe_start_hw_generic(hw); + + /* set the completion timeout for interface */ + if (ret_val == 0) + ixgbe_set_pcie_completion_timeout(hw); + + return ret_val; +} + +/** * ixgbe_get_link_capabilities_82598 - Determines link capabilities * @hw: pointer to hardware structure * @speed: pointer to link speed @@ -1085,7 +1150,7 @@ out: static struct ixgbe_mac_operations mac_ops_82598 = { .init_hw = &ixgbe_init_hw_generic, .reset_hw = &ixgbe_reset_hw_82598, - .start_hw = &ixgbe_start_hw_generic, + .start_hw = &ixgbe_start_hw_82598, .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic, .get_media_type = &ixgbe_get_media_type_82598, .get_supported_physical_layer = &ixgbe_get_supported_physical_layer_82598, diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c index 2a97800..79144e9 100644 --- a/drivers/net/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ixgbe/ixgbe_ethtool.c @@ -1975,7 +1975,10 @@ static int ixgbe_set_coalesce(struct net_device *netdev, * any other value means disable eitr, which is best * served by setting the interrupt rate very high */ - adapter->eitr_param = IXGBE_MAX_INT_RATE; + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + adapter->eitr_param = IXGBE_MAX_RSC_INT_RATE; + else + adapter->eitr_param = IXGBE_MAX_INT_RATE; adapter->itr_setting = 0; } @@ -1999,13 +2002,13 @@ static int ixgbe_set_flags(struct net_device *netdev, u32 data) ethtool_op_set_flags(netdev, data); - if (!(adapter->flags & IXGBE_FLAG2_RSC_CAPABLE)) + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) return 0; /* if state changes we need to update adapter->flags and reset */ if ((!!(data & ETH_FLAG_LRO)) != - (!!(adapter->flags & IXGBE_FLAG2_RSC_ENABLED))) { - adapter->flags ^= IXGBE_FLAG2_RSC_ENABLED; + (!!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED))) { + adapter->flags2 ^= IXGBE_FLAG2_RSC_ENABLED; if (netif_running(netdev)) ixgbe_reinit_locked(adapter); else diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index 200454f..110c65a 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -780,7 +780,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, prefetch(next_rxd); cleaned_count++; - if (adapter->flags & IXGBE_FLAG2_RSC_CAPABLE) + if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) rsc_count = ixgbe_get_rsc_count(rx_desc); if (rsc_count) { @@ -2036,7 +2036,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(0), psrtype); } } else { - if (!(adapter->flags & IXGBE_FLAG2_RSC_ENABLED) && + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) && (netdev->mtu <= ETH_DATA_LEN)) rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; else @@ -2165,7 +2165,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl); } - if (adapter->flags & IXGBE_FLAG2_RSC_ENABLED) { + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) { /* Enable 82599 HW-RSC */ for (i = 0; i < adapter->num_rx_queues; i++) { j = adapter->rx_ring[i].reg_idx; @@ -3812,8 +3812,8 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82598; } else if (hw->mac.type == ixgbe_mac_82599EB) { adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82599; - adapter->flags |= IXGBE_FLAG2_RSC_CAPABLE; - adapter->flags |= IXGBE_FLAG2_RSC_ENABLED; + adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE; + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; adapter->ring_feature[RING_F_FDIR].indices = IXGBE_MAX_FDIR_INDICES; @@ -5360,12 +5360,19 @@ static int ixgbe_del_sanmac_netdev(struct net_device *dev) static void ixgbe_netpoll(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); + int i; - disable_irq(adapter->pdev->irq); adapter->flags |= IXGBE_FLAG_IN_NETPOLL; - ixgbe_intr(adapter->pdev->irq, netdev); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + for (i = 0; i < num_q_vectors; i++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[i]; + ixgbe_msix_clean_many(0, q_vector); + } + } else { + ixgbe_intr(adapter->pdev->irq, netdev); + } adapter->flags &= ~IXGBE_FLAG_IN_NETPOLL; - enable_irq(adapter->pdev->irq); } #endif @@ -5611,7 +5618,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; - if (adapter->flags & IXGBE_FLAG2_RSC_ENABLED) + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) netdev->features |= NETIF_F_LRO; /* make sure the EEPROM is good */ diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h index fa87309..be90eb4 100644 --- a/drivers/net/ixgbe/ixgbe_type.h +++ b/drivers/net/ixgbe/ixgbe_type.h @@ -718,6 +718,12 @@ #define IXGBE_ECC_STATUS_82599 0x110E0 #define IXGBE_BAR_CTRL_82599 0x110F4 +/* PCI Express Control */ +#define IXGBE_GCR_CMPL_TMOUT_MASK 0x0000F000 +#define IXGBE_GCR_CMPL_TMOUT_10ms 0x00001000 +#define IXGBE_GCR_CMPL_TMOUT_RESEND 0x00010000 +#define IXGBE_GCR_CAP_VER2 0x00040000 + /* Time Sync Registers */ #define IXGBE_TSYNCRXCTL 0x05188 /* Rx Time Sync Control register - RW */ #define IXGBE_TSYNCTXCTL 0x08C00 /* Tx Time Sync Control register - RW */ @@ -1521,6 +1527,7 @@ /* PCI Bus Info */ #define IXGBE_PCI_LINK_STATUS 0xB2 +#define IXGBE_PCI_DEVICE_CONTROL2 0xC8 #define IXGBE_PCI_LINK_WIDTH 0x3F0 #define IXGBE_PCI_LINK_WIDTH_1 0x10 #define IXGBE_PCI_LINK_WIDTH_2 0x20 @@ -1531,6 +1538,7 @@ #define IXGBE_PCI_LINK_SPEED_5000 0x2 #define IXGBE_PCI_HEADER_TYPE_REGISTER 0x0E #define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80 +#define IXGBE_PCI_DEVICE_CONTROL2_16ms 0x0005 /* Number of 100 microseconds we wait for PCI Express master disable */ #define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 diff --git a/drivers/net/mlx4/en_tx.c b/drivers/net/mlx4/en_tx.c index 08c43f2..5a88b3f5 100644 --- a/drivers/net/mlx4/en_tx.c +++ b/drivers/net/mlx4/en_tx.c @@ -249,6 +249,7 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, pci_unmap_page(mdev->pdev, (dma_addr_t) be64_to_cpu(data->addr), frag->size, PCI_DMA_TODEVICE); + ++data; } } /* Stamp the freed descriptor */ diff --git a/drivers/net/netxen/netxen_nic_main.c b/drivers/net/netxen/netxen_nic_main.c index 637ac8b..3cd8cfc 100644 --- a/drivers/net/netxen/netxen_nic_main.c +++ b/drivers/net/netxen/netxen_nic_main.c @@ -221,7 +221,7 @@ netxen_napi_disable(struct netxen_adapter *adapter) } } -static int nx_set_dma_mask(struct netxen_adapter *adapter, uint8_t revision_id) +static int nx_set_dma_mask(struct netxen_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; uint64_t mask, cmask; @@ -229,19 +229,17 @@ static int nx_set_dma_mask(struct netxen_adapter *adapter, uint8_t revision_id) adapter->pci_using_dac = 0; mask = DMA_BIT_MASK(32); - /* - * Consistent DMA mask is set to 32 bit because it cannot be set to - * 35 bits. For P3 also leave it at 32 bits for now. Only the rings - * come off this pool. - */ cmask = DMA_BIT_MASK(32); + if (NX_IS_REVISION_P2(adapter->ahw.revision_id)) { #ifndef CONFIG_IA64 - if (revision_id >= NX_P3_B0) - mask = DMA_BIT_MASK(39); - else if (revision_id == NX_P2_C1) mask = DMA_BIT_MASK(35); #endif + } else { + mask = DMA_BIT_MASK(39); + cmask = mask; + } + if (pci_set_dma_mask(pdev, mask) == 0 && pci_set_consistent_dma_mask(pdev, cmask) == 0) { adapter->pci_using_dac = 1; @@ -256,7 +254,7 @@ static int nx_update_dma_mask(struct netxen_adapter *adapter) { int change, shift, err; - uint64_t mask, old_mask; + uint64_t mask, old_mask, old_cmask; struct pci_dev *pdev = adapter->pdev; change = 0; @@ -272,14 +270,29 @@ nx_update_dma_mask(struct netxen_adapter *adapter) if (change) { old_mask = pdev->dma_mask; + old_cmask = pdev->dev.coherent_dma_mask; + mask = (1ULL<<(32+shift)) - 1; err = pci_set_dma_mask(pdev, mask); if (err) - return pci_set_dma_mask(pdev, old_mask); + goto err_out; + + if (NX_IS_REVISION_P3(adapter->ahw.revision_id)) { + + err = pci_set_consistent_dma_mask(pdev, mask); + if (err) + goto err_out; + } + dev_info(&pdev->dev, "using %d-bit dma mask\n", 32+shift); } return 0; + +err_out: + pci_set_dma_mask(pdev, old_mask); + pci_set_consistent_dma_mask(pdev, old_cmask); + return err; } static void netxen_check_options(struct netxen_adapter *adapter) @@ -1006,7 +1019,7 @@ netxen_nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) revision_id = pdev->revision; adapter->ahw.revision_id = revision_id; - err = nx_set_dma_mask(adapter, revision_id); + err = nx_set_dma_mask(adapter); if (err) goto err_out_free_netdev; diff --git a/drivers/net/pcnet32.c b/drivers/net/pcnet32.c index 2836815..a646a44 100644 --- a/drivers/net/pcnet32.c +++ b/drivers/net/pcnet32.c @@ -1611,8 +1611,11 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) if (pcnet32_dwio_read_csr(ioaddr, 0) == 4 && pcnet32_dwio_check(ioaddr)) { a = &pcnet32_dwio; - } else + } else { + if (pcnet32_debug & NETIF_MSG_PROBE) + printk(KERN_ERR PFX "No access methods\n"); goto err_release_region; + } } chip_version = @@ -1719,7 +1722,9 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) ret = -ENOMEM; goto err_release_region; } - SET_NETDEV_DEV(dev, &pdev->dev); + + if (pdev) + SET_NETDEV_DEV(dev, &pdev->dev); if (pcnet32_debug & NETIF_MSG_PROBE) printk(KERN_INFO PFX "%s at %#3lx,", chipname, ioaddr); @@ -1818,7 +1823,6 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) spin_lock_init(&lp->lock); - SET_NETDEV_DEV(dev, &pdev->dev); lp->name = chipname; lp->shared_irq = shared; lp->tx_ring_size = TX_RING_SIZE; /* default tx ring size */ @@ -1852,12 +1856,6 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) ((cards_found >= MAX_UNITS) || full_duplex[cards_found])) lp->options |= PCNET32_PORT_FD; - if (!a) { - if (pcnet32_debug & NETIF_MSG_PROBE) - printk(KERN_ERR PFX "No access methods\n"); - ret = -ENODEV; - goto err_free_consistent; - } lp->a = *a; /* prior to register_netdev, dev->name is not yet correct */ @@ -1973,14 +1971,13 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) return 0; - err_free_ring: +err_free_ring: pcnet32_free_ring(dev); - err_free_consistent: pci_free_consistent(lp->pci_dev, sizeof(*lp->init_block), lp->init_block, lp->init_dma_addr); - err_free_netdev: +err_free_netdev: free_netdev(dev); - err_release_region: +err_release_region: release_region(ioaddr, PCNET32_TOTAL_SIZE); return ret; } @@ -2089,6 +2086,7 @@ static void pcnet32_free_ring(struct net_device *dev) static int pcnet32_open(struct net_device *dev) { struct pcnet32_private *lp = netdev_priv(dev); + struct pci_dev *pdev = lp->pci_dev; unsigned long ioaddr = dev->base_addr; u16 val; int i; @@ -2149,9 +2147,9 @@ static int pcnet32_open(struct net_device *dev) lp->a.write_csr(ioaddr, 124, val); /* Allied Telesyn AT 2700/2701 FX are 100Mbit only and do not negotiate */ - if (lp->pci_dev->subsystem_vendor == PCI_VENDOR_ID_AT && - (lp->pci_dev->subsystem_device == PCI_SUBDEVICE_ID_AT_2700FX || - lp->pci_dev->subsystem_device == PCI_SUBDEVICE_ID_AT_2701FX)) { + if (pdev && pdev->subsystem_vendor == PCI_VENDOR_ID_AT && + (pdev->subsystem_device == PCI_SUBDEVICE_ID_AT_2700FX || + pdev->subsystem_device == PCI_SUBDEVICE_ID_AT_2701FX)) { if (lp->options & PCNET32_PORT_ASEL) { lp->options = PCNET32_PORT_FD | PCNET32_PORT_100; if (netif_msg_link(lp)) diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index 639d11b..cd37d73 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -1384,7 +1384,7 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) /* create a fragment for each channel */ bits = B; - while (nfree > 0 && len > 0) { + while (len > 0) { list = list->next; if (list == &ppp->channels) { i = 0; @@ -1431,29 +1431,31 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) *otherwise divide it according to the speed *of the channel we are going to transmit on */ - if (pch->speed == 0) { - flen = totlen/nfree ; - if (nbigger > 0) { - flen++; - nbigger--; - } - } else { - flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / - ((totspeed*totfree)/pch->speed)) - hdrlen; - if (nbigger > 0) { - flen += ((totfree - nzero)*pch->speed)/totspeed; - nbigger -= ((totfree - nzero)*pch->speed)/ + if (nfree > 0) { + if (pch->speed == 0) { + flen = totlen/nfree ; + if (nbigger > 0) { + flen++; + nbigger--; + } + } else { + flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / + ((totspeed*totfree)/pch->speed)) - hdrlen; + if (nbigger > 0) { + flen += ((totfree - nzero)*pch->speed)/totspeed; + nbigger -= ((totfree - nzero)*pch->speed)/ totspeed; + } } + nfree--; } - nfree--; /* *check if we are on the last channel or *we exceded the lenght of the data to *fragment */ - if ((nfree == 0) || (flen > len)) + if ((nfree <= 0) || (flen > len)) flen = len; /* *it is not worth to tx on slow channels: @@ -1467,7 +1469,7 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) continue; } - mtu = pch->chan->mtu + 2 - hdrlen; + mtu = pch->chan->mtu - hdrlen; if (mtu < 4) mtu = 4; if (flen > mtu) diff --git a/drivers/net/pppoe.c b/drivers/net/pppoe.c index f0031f1..5f20902 100644 --- a/drivers/net/pppoe.c +++ b/drivers/net/pppoe.c @@ -1063,6 +1063,7 @@ static void *pppoe_seq_next(struct seq_file *seq, void *v, loff_t *pos) else { int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote); + po = NULL; while (++hash < PPPOE_HASH_SIZE) { po = pn->hash_table[hash]; if (po) diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c index e7935d0..e0f9219 100644 --- a/drivers/net/pppol2tp.c +++ b/drivers/net/pppol2tp.c @@ -2680,6 +2680,7 @@ out_unregister_pppol2tp_proto: static void __exit pppol2tp_exit(void) { unregister_pppox_proto(PX_PROTO_OL2TP); + unregister_pernet_gen_device(pppol2tp_net_id, &pppol2tp_net_ops); proto_unregister(&pppol2tp_sk_proto); } diff --git a/drivers/net/s6gmac.c b/drivers/net/s6gmac.c index 5345e47..4525cbe 100644 --- a/drivers/net/s6gmac.c +++ b/drivers/net/s6gmac.c @@ -793,7 +793,7 @@ static inline int s6gmac_phy_start(struct net_device *dev) struct s6gmac *pd = netdev_priv(dev); int i = 0; struct phy_device *p = NULL; - while ((!(p = pd->mii.bus->phy_map[i])) && (i < PHY_MAX_ADDR)) + while ((i < PHY_MAX_ADDR) && (!(p = pd->mii.bus->phy_map[i]))) i++; p = phy_connect(dev, dev_name(&p->dev), &s6gmac_adjust_link, 0, PHY_INTERFACE_MODE_RGMII); diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index 3550c5d..0a551d8 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -1488,6 +1488,8 @@ static int sky2_up(struct net_device *dev) sky2_set_vlan_mode(hw, port, sky2->vlgrp != NULL); #endif + sky2->restarting = 0; + err = sky2_rx_start(sky2); if (err) goto err_out; @@ -1500,6 +1502,9 @@ static int sky2_up(struct net_device *dev) sky2_set_multicast(dev); + /* wake queue incase we are restarting */ + netif_wake_queue(dev); + if (netif_msg_ifup(sky2)) printk(KERN_INFO PFX "%s: enabling interface\n", dev->name); return 0; @@ -1533,6 +1538,8 @@ static inline int tx_dist(unsigned tail, unsigned head) /* Number of list elements available for next tx */ static inline int tx_avail(const struct sky2_port *sky2) { + if (unlikely(sky2->restarting)) + return 0; return sky2->tx_pending - tx_dist(sky2->tx_cons, sky2->tx_prod); } @@ -1818,6 +1825,10 @@ static int sky2_down(struct net_device *dev) if (netif_msg_ifdown(sky2)) printk(KERN_INFO PFX "%s: disabling interface\n", dev->name); + /* explicitly shut off tx incase we're restarting */ + sky2->restarting = 1; + netif_tx_disable(dev); + /* Force flow control off */ sky2_write8(hw, SK_REG(port, GMAC_CTRL), GMC_PAUSE_OFF); @@ -2359,7 +2370,7 @@ static inline void sky2_tx_done(struct net_device *dev, u16 last) { struct sky2_port *sky2 = netdev_priv(dev); - if (netif_running(dev)) { + if (likely(netif_running(dev) && !sky2->restarting)) { netif_tx_lock(dev); sky2_tx_complete(sky2, last); netif_tx_unlock(dev); @@ -4283,6 +4294,7 @@ static __devinit struct net_device *sky2_init_netdev(struct sky2_hw *hw, spin_lock_init(&sky2->phy_lock); sky2->tx_pending = TX_DEF_PENDING; sky2->rx_pending = RX_DEF_PENDING; + sky2->restarting = 0; hw->dev[port] = dev; diff --git a/drivers/net/sky2.h b/drivers/net/sky2.h index b5549c9..4486b06 100644 --- a/drivers/net/sky2.h +++ b/drivers/net/sky2.h @@ -2051,6 +2051,7 @@ struct sky2_port { u8 duplex; /* DUPLEX_HALF, DUPLEX_FULL */ u8 rx_csum; u8 wol; + u8 restarting; enum flow_control flow_mode; enum flow_control flow_status; diff --git a/drivers/net/tulip/de4x5.c b/drivers/net/tulip/de4x5.c index eb72d2e..acfdccd 100644 --- a/drivers/net/tulip/de4x5.c +++ b/drivers/net/tulip/de4x5.c @@ -5059,7 +5059,7 @@ mii_get_phy(struct net_device *dev) if ((id == 0) || (id == 65535)) continue; /* Valid ID? */ for (j=0; j<limit; j++) { /* Search PHY table */ if (id != phy_info[j].id) continue; /* ID match? */ - for (k=0; lp->phy[k].id && (k < DE4X5_MAX_PHY); k++); + for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++); if (k < DE4X5_MAX_PHY) { memcpy((char *)&lp->phy[k], (char *)&phy_info[j], sizeof(struct phy_table)); @@ -5072,7 +5072,7 @@ mii_get_phy(struct net_device *dev) break; } if ((j == limit) && (i < DE4X5_MAX_MII)) { - for (k=0; lp->phy[k].id && (k < DE4X5_MAX_PHY); k++); + for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++); lp->phy[k].addr = i; lp->phy[k].id = id; lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ @@ -5091,7 +5091,7 @@ mii_get_phy(struct net_device *dev) purgatory: lp->active = 0; if (lp->phy[0].id) { /* Reset the PHY devices */ - for (k=0; lp->phy[k].id && (k < DE4X5_MAX_PHY); k++) { /*For each PHY*/ + for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++) { /*For each PHY*/ mii_wr(MII_CR_RST, MII_CR, lp->phy[k].addr, DE4X5_MII); while (mii_rd(MII_CR, lp->phy[k].addr, DE4X5_MII) & MII_CR_RST); diff --git a/drivers/net/wireless/airo.c b/drivers/net/wireless/airo.c index c70604f..8ce5e4c 100644 --- a/drivers/net/wireless/airo.c +++ b/drivers/net/wireless/airo.c @@ -5918,20 +5918,19 @@ static int airo_set_essid(struct net_device *dev, readSsidRid(local, &SSID_rid); /* Check if we asked for `any' */ - if(dwrq->flags == 0) { + if (dwrq->flags == 0) { /* Just send an empty SSID list */ memset(&SSID_rid, 0, sizeof(SSID_rid)); } else { - int index = (dwrq->flags & IW_ENCODE_INDEX) - 1; + unsigned index = (dwrq->flags & IW_ENCODE_INDEX) - 1; /* Check the size of the string */ - if(dwrq->length > IW_ESSID_MAX_SIZE) { + if (dwrq->length > IW_ESSID_MAX_SIZE) return -E2BIG ; - } + /* Check if index is valid */ - if((index < 0) || (index >= 4)) { + if (index >= ARRAY_SIZE(SSID_rid.ssids)) return -EINVAL; - } /* Set the SSID */ memset(SSID_rid.ssids[index].ssid, 0, @@ -6819,7 +6818,7 @@ static int airo_set_txpow(struct net_device *dev, return -EINVAL; } clear_bit (FLAG_RADIO_OFF, &local->flags); - for (i = 0; cap_rid.txPowerLevels[i] && (i < 8); i++) + for (i = 0; i < 8 && cap_rid.txPowerLevels[i]; i++) if (v == cap_rid.txPowerLevels[i]) { readConfigRid(local, 1); local->config.txPower = v; diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index a2fda70..ce0e86c 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -460,7 +460,7 @@ static int ath9k_hw_4k_check_eeprom(struct ath_hw *ah) integer = swab32(eep->modalHeader.antCtrlCommon); eep->modalHeader.antCtrlCommon = integer; - for (i = 0; i < AR5416_MAX_CHAINS; i++) { + for (i = 0; i < AR5416_EEP4K_MAX_CHAINS; i++) { integer = swab32(eep->modalHeader.antCtrlChain[i]); eep->modalHeader.antCtrlChain[i] = integer; } @@ -914,7 +914,7 @@ static void ath9k_hw_set_4k_power_per_rate_table(struct ath_hw *ah, ctlMode, numCtlModes, isHt40CtlMode, (pCtlMode[ctlMode] & EXT_ADDITIVE)); - for (i = 0; (i < AR5416_NUM_CTLS) && + for (i = 0; (i < AR5416_EEP4K_NUM_CTLS) && pEepData->ctlIndex[i]; i++) { DPRINTF(ah->ah_sc, ATH_DBG_EEPROM, " LOOP-Ctlidx %d: cfgCtl 0x%2.2x " diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.h b/drivers/net/wireless/iwlwifi/iwl-3945.h index fbb3a57..2de6471 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945.h +++ b/drivers/net/wireless/iwlwifi/iwl-3945.h @@ -112,7 +112,7 @@ enum iwl3945_antenna { #define IWL_TX_FIFO_NONE 7 /* Minimum number of queues. MAX_NUM is defined in hw specific files */ -#define IWL_MIN_NUM_QUEUES 4 +#define IWL39_MIN_NUM_QUEUES 4 #define IEEE80211_DATA_LEN 2304 #define IEEE80211_4ADDR_LEN 30 diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index 6ab0716..18b135f 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -1332,6 +1332,9 @@ int iwl_setup_mac(struct iwl_priv *priv) hw->wiphy->custom_regulatory = true; + /* Firmware does not support this */ + hw->wiphy->disable_beacon_hints = true; + hw->wiphy->max_scan_ssids = PROBE_OPTION_MAX; /* we create the 802.11 header and a zero-length SSID element */ hw->wiphy->max_scan_ie_len = IWL_MAX_PROBE_REQUEST - 24 - 2; diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c index 11e08c0..ca00cc8 100644 --- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c +++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c @@ -308,18 +308,18 @@ static ssize_t iwl_dbgfs_nvm_read(struct file *file, return -ENODATA; } + ptr = priv->eeprom; + if (!ptr) { + IWL_ERR(priv, "Invalid EEPROM/OTP memory\n"); + return -ENOMEM; + } + /* 4 characters for byte 0xYY */ buf = kzalloc(buf_size, GFP_KERNEL); if (!buf) { IWL_ERR(priv, "Can not allocate Buffer\n"); return -ENOMEM; } - - ptr = priv->eeprom; - if (!ptr) { - IWL_ERR(priv, "Invalid EEPROM/OTP memory\n"); - return -ENOMEM; - } pos += scnprintf(buf + pos, buf_size - pos, "NVM Type: %s\n", (priv->nvm_device_type == NVM_DEVICE_TYPE_OTP) ? "OTP" : "EEPROM"); diff --git a/drivers/net/wireless/iwlwifi/iwl-dev.h b/drivers/net/wireless/iwlwifi/iwl-dev.h index e2d620f..650e20a 100644 --- a/drivers/net/wireless/iwlwifi/iwl-dev.h +++ b/drivers/net/wireless/iwlwifi/iwl-dev.h @@ -258,8 +258,10 @@ struct iwl_channel_info { #define IWL_TX_FIFO_HCCA_2 6 #define IWL_TX_FIFO_NONE 7 -/* Minimum number of queues. MAX_NUM is defined in hw specific files */ -#define IWL_MIN_NUM_QUEUES 4 +/* Minimum number of queues. MAX_NUM is defined in hw specific files. + * Set the minimum to accommodate the 4 standard TX queues, 1 command + * queue, 2 (unused) HCCA queues, and 4 HT queues (one for each AC) */ +#define IWL_MIN_NUM_QUEUES 10 /* Power management (not Tx power) structures */ diff --git a/drivers/net/wireless/iwlwifi/iwl-sta.c b/drivers/net/wireless/iwlwifi/iwl-sta.c index 2addf73..ffd5c61 100644 --- a/drivers/net/wireless/iwlwifi/iwl-sta.c +++ b/drivers/net/wireless/iwlwifi/iwl-sta.c @@ -566,6 +566,8 @@ int iwl_remove_default_wep_key(struct iwl_priv *priv, unsigned long flags; spin_lock_irqsave(&priv->sta_lock, flags); + IWL_DEBUG_WEP(priv, "Removing default WEP key: idx=%d\n", + keyconf->keyidx); if (!test_and_clear_bit(keyconf->keyidx, &priv->ucode_key_table)) IWL_ERR(priv, "index %d not used in uCode key table.\n", @@ -573,6 +575,11 @@ int iwl_remove_default_wep_key(struct iwl_priv *priv, priv->default_wep_key--; memset(&priv->wep_keys[keyconf->keyidx], 0, sizeof(priv->wep_keys[0])); + if (iwl_is_rfkill(priv)) { + IWL_DEBUG_WEP(priv, "Not sending REPLY_WEPKEY command due to RFKILL.\n"); + spin_unlock_irqrestore(&priv->sta_lock, flags); + return 0; + } ret = iwl_send_static_wepkey_cmd(priv, 1); IWL_DEBUG_WEP(priv, "Remove default WEP key: idx=%d ret=%d\n", keyconf->keyidx, ret); @@ -853,6 +860,11 @@ int iwl_remove_dynamic_key(struct iwl_priv *priv, priv->stations[sta_id].sta.sta.modify_mask = STA_MODIFY_KEY_MASK; priv->stations[sta_id].sta.mode = STA_CONTROL_MODIFY_MSK; + if (iwl_is_rfkill(priv)) { + IWL_DEBUG_WEP(priv, "Not sending REPLY_ADD_STA command because RFKILL enabled. \n"); + spin_unlock_irqrestore(&priv->sta_lock, flags); + return 0; + } ret = iwl_send_add_sta(priv, &priv->stations[sta_id].sta, CMD_ASYNC); spin_unlock_irqrestore(&priv->sta_lock, flags); return ret; diff --git a/drivers/net/wireless/iwlwifi/iwl-tx.c b/drivers/net/wireless/iwlwifi/iwl-tx.c index 9bbeec9..2e89040 100644 --- a/drivers/net/wireless/iwlwifi/iwl-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-tx.c @@ -720,8 +720,6 @@ int iwl_tx_skb(struct iwl_priv *priv, struct sk_buff *skb) goto drop_unlock; } - spin_unlock_irqrestore(&priv->lock, flags); - hdr_len = ieee80211_hdrlen(fc); /* Find (or create) index into station table for destination station */ @@ -729,7 +727,7 @@ int iwl_tx_skb(struct iwl_priv *priv, struct sk_buff *skb) if (sta_id == IWL_INVALID_STATION) { IWL_DEBUG_DROP(priv, "Dropping - INVALID STATION: %pM\n", hdr->addr1); - goto drop; + goto drop_unlock; } IWL_DEBUG_TX(priv, "station Id %d\n", sta_id); @@ -750,14 +748,17 @@ int iwl_tx_skb(struct iwl_priv *priv, struct sk_buff *skb) txq_id = priv->stations[sta_id].tid[tid].agg.txq_id; swq_id = iwl_virtual_agg_queue_num(swq_id, txq_id); } - priv->stations[sta_id].tid[tid].tfds_in_queue++; } txq = &priv->txq[txq_id]; q = &txq->q; txq->swq_id = swq_id; - spin_lock_irqsave(&priv->lock, flags); + if (unlikely(iwl_queue_space(q) < q->high_mark)) + goto drop_unlock; + + if (ieee80211_is_data_qos(fc)) + priv->stations[sta_id].tid[tid].tfds_in_queue++; /* Set up driver data for this TFD */ memset(&(txq->txb[q->write_ptr]), 0, sizeof(struct iwl_tx_info)); @@ -902,7 +903,6 @@ int iwl_tx_skb(struct iwl_priv *priv, struct sk_buff *skb) drop_unlock: spin_unlock_irqrestore(&priv->lock, flags); -drop: return -1; } EXPORT_SYMBOL(iwl_tx_skb); @@ -1171,6 +1171,8 @@ int iwl_tx_agg_start(struct iwl_priv *priv, const u8 *ra, u16 tid, u16 *ssn) IWL_ERR(priv, "Start AGG on invalid station\n"); return -ENXIO; } + if (unlikely(tid >= MAX_TID_COUNT)) + return -EINVAL; if (priv->stations[sta_id].tid[tid].agg.state != IWL_AGG_OFF) { IWL_ERR(priv, "Start AGG when state is not IWL_AGG_OFF !\n"); diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index 956798f..5238433 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -3968,6 +3968,9 @@ static int iwl3945_setup_mac(struct iwl_priv *priv) hw->wiphy->custom_regulatory = true; + /* Firmware does not support this */ + hw->wiphy->disable_beacon_hints = true; + hw->wiphy->max_scan_ssids = PROBE_OPTION_MAX_3945; /* we create the 802.11 header and a zero-length SSID element */ hw->wiphy->max_scan_ie_len = IWL_MAX_PROBE_REQUEST - 24 - 2; @@ -4018,10 +4021,10 @@ static int iwl3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *e SET_IEEE80211_DEV(hw, &pdev->dev); if ((iwl3945_mod_params.num_of_queues > IWL39_MAX_NUM_QUEUES) || - (iwl3945_mod_params.num_of_queues < IWL_MIN_NUM_QUEUES)) { + (iwl3945_mod_params.num_of_queues < IWL39_MIN_NUM_QUEUES)) { IWL_ERR(priv, "invalid queues_num, should be between %d and %d\n", - IWL_MIN_NUM_QUEUES, IWL39_MAX_NUM_QUEUES); + IWL39_MIN_NUM_QUEUES, IWL39_MAX_NUM_QUEUES); err = -EINVAL; goto out_ieee80211_free_hw; } diff --git a/drivers/net/wireless/iwmc3200wifi/commands.c b/drivers/net/wireless/iwmc3200wifi/commands.c index 834a7f5..e2334d1 100644 --- a/drivers/net/wireless/iwmc3200wifi/commands.c +++ b/drivers/net/wireless/iwmc3200wifi/commands.c @@ -220,6 +220,7 @@ int iwm_store_rxiq_calib_result(struct iwm_priv *iwm) eeprom_rxiq = iwm_eeprom_access(iwm, IWM_EEPROM_CALIB_RXIQ); if (IS_ERR(eeprom_rxiq)) { IWM_ERR(iwm, "Couldn't access EEPROM RX IQ entry\n"); + kfree(rxiq); return PTR_ERR(eeprom_rxiq); } diff --git a/drivers/net/wireless/iwmc3200wifi/netdev.c b/drivers/net/wireless/iwmc3200wifi/netdev.c index aea5ccf..bf294e4 100644 --- a/drivers/net/wireless/iwmc3200wifi/netdev.c +++ b/drivers/net/wireless/iwmc3200wifi/netdev.c @@ -106,10 +106,8 @@ void *iwm_if_alloc(int sizeof_bus, struct device *dev, int ret = 0; wdev = iwm_wdev_alloc(sizeof_bus, dev); - if (!wdev) { - dev_err(dev, "no memory for wireless device instance\n"); - return ERR_PTR(-ENOMEM); - } + if (IS_ERR(wdev)) + return wdev; iwm = wdev_to_iwm(wdev); iwm->bus_ops = if_ops; diff --git a/drivers/net/wireless/libertas/11d.c b/drivers/net/wireless/libertas/11d.c index 9a5408e..5c69681 100644 --- a/drivers/net/wireless/libertas/11d.c +++ b/drivers/net/wireless/libertas/11d.c @@ -47,7 +47,7 @@ static u8 lbs_region_2_code(u8 *region) { u8 i; - for (i = 0; region[i] && i < COUNTRY_CODE_LEN; i++) + for (i = 0; i < COUNTRY_CODE_LEN && region[i]; i++) region[i] = toupper(region[i]); for (i = 0; i < ARRAY_SIZE(region_code_mapping); i++) { diff --git a/drivers/net/wireless/libertas/assoc.c b/drivers/net/wireless/libertas/assoc.c index b9b3741..d699737 100644 --- a/drivers/net/wireless/libertas/assoc.c +++ b/drivers/net/wireless/libertas/assoc.c @@ -1,6 +1,7 @@ /* Copyright (C) 2006, Red Hat, Inc. */ #include <linux/types.h> +#include <linux/kernel.h> #include <linux/etherdevice.h> #include <linux/ieee80211.h> #include <linux/if_arp.h> @@ -43,21 +44,21 @@ static int get_common_rates(struct lbs_private *priv, u16 *rates_size) { u8 *card_rates = lbs_bg_rates; - size_t num_card_rates = sizeof(lbs_bg_rates); int ret = 0, i, j; - u8 tmp[30]; + u8 tmp[(ARRAY_SIZE(lbs_bg_rates) - 1) * (*rates_size - 1)]; size_t tmp_size = 0; /* For each rate in card_rates that exists in rate1, copy to tmp */ - for (i = 0; card_rates[i] && (i < num_card_rates); i++) { - for (j = 0; rates[j] && (j < *rates_size); j++) { + for (i = 0; i < ARRAY_SIZE(lbs_bg_rates) && card_rates[i]; i++) { + for (j = 0; j < *rates_size && rates[j]; j++) { if (rates[j] == card_rates[i]) tmp[tmp_size++] = card_rates[i]; } } lbs_deb_hex(LBS_DEB_JOIN, "AP rates ", rates, *rates_size); - lbs_deb_hex(LBS_DEB_JOIN, "card rates ", card_rates, num_card_rates); + lbs_deb_hex(LBS_DEB_JOIN, "card rates ", card_rates, + ARRAY_SIZE(lbs_bg_rates)); lbs_deb_hex(LBS_DEB_JOIN, "common rates", tmp, tmp_size); lbs_deb_join("TX data rate 0x%02x\n", priv->cur_rate); @@ -69,10 +70,7 @@ static int get_common_rates(struct lbs_private *priv, lbs_pr_alert("Previously set fixed data rate %#x isn't " "compatible with the network.\n", priv->cur_rate); ret = -1; - goto done; } - ret = 0; - done: memset(rates, 0, *rates_size); *rates_size = min_t(int, tmp_size, *rates_size); @@ -322,7 +320,7 @@ static int lbs_associate(struct lbs_private *priv, rates = (struct mrvl_ie_rates_param_set *) pos; rates->header.type = cpu_to_le16(TLV_TYPE_RATES); memcpy(&rates->rates, &bss->rates, MAX_RATES); - tmplen = MAX_RATES; + tmplen = min_t(u16, ARRAY_SIZE(rates->rates), MAX_RATES); if (get_common_rates(priv, rates->rates, &tmplen)) { ret = -1; goto done; @@ -598,7 +596,7 @@ static int lbs_adhoc_join(struct lbs_private *priv, /* Copy Data rates from the rates recorded in scan response */ memset(cmd.bss.rates, 0, sizeof(cmd.bss.rates)); - ratesize = min_t(u16, sizeof(cmd.bss.rates), MAX_RATES); + ratesize = min_t(u16, ARRAY_SIZE(cmd.bss.rates), MAX_RATES); memcpy(cmd.bss.rates, bss->rates, ratesize); if (get_common_rates(priv, cmd.bss.rates, &ratesize)) { lbs_deb_join("ADHOC_JOIN: get_common_rates returned error.\n"); diff --git a/drivers/net/wireless/libertas/scan.c b/drivers/net/wireless/libertas/scan.c index 601b542..6c95af3 100644 --- a/drivers/net/wireless/libertas/scan.c +++ b/drivers/net/wireless/libertas/scan.c @@ -5,6 +5,7 @@ * for sending scan commands to the firmware. */ #include <linux/types.h> +#include <linux/kernel.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <asm/unaligned.h> @@ -876,7 +877,7 @@ static inline char *lbs_translate_scan(struct lbs_private *priv, iwe.u.bitrate.disabled = 0; iwe.u.bitrate.value = 0; - for (j = 0; bss->rates[j] && (j < sizeof(bss->rates)); j++) { + for (j = 0; j < ARRAY_SIZE(bss->rates) && bss->rates[j]; j++) { /* Bit rate given in 500 kb/s units */ iwe.u.bitrate.value = bss->rates[j] * 500000; current_val = iwe_stream_add_value(info, start, current_val, diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c index 40b07b9..3bd3c77 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zd1211rw/zd_mac.c @@ -698,7 +698,7 @@ int zd_mac_rx(struct ieee80211_hw *hw, const u8 *buffer, unsigned int length) && !mac->pass_ctrl) return 0; - fc = *(__le16 *)buffer; + fc = get_unaligned((__le16*)buffer); need_padding = ieee80211_is_data_qos(fc) ^ ieee80211_has_a4(fc); skb = dev_alloc_skb(length + (need_padding ? 2 : 0)); diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c index 0f0e0b9..a45b0c0 100644 --- a/drivers/parisc/ccio-dma.c +++ b/drivers/parisc/ccio-dma.c @@ -70,7 +70,6 @@ #undef CCIO_COLLECT_STATS #endif -#include <linux/proc_fs.h> #include <asm/runway.h> /* for proc_runway_root */ #ifdef DEBUG_CCIO_INIT diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c index c590974..d69bde6 100644 --- a/drivers/parisc/dino.c +++ b/drivers/parisc/dino.c @@ -614,7 +614,7 @@ dino_fixup_bus(struct pci_bus *bus) dev_name(&bus->self->dev), i, bus->self->resource[i].start, bus->self->resource[i].end); - pci_assign_resource(bus->self, i); + WARN_ON(pci_assign_resource(bus->self, i)); DBG("DEBUG %s after assign %d [0x%lx,0x%lx]\n", dev_name(&bus->self->dev), i, bus->self->resource[i].start, diff --git a/drivers/parisc/eisa_eeprom.c b/drivers/parisc/eisa_eeprom.c index 685d94e..8c0b26e9 100644 --- a/drivers/parisc/eisa_eeprom.c +++ b/drivers/parisc/eisa_eeprom.c @@ -55,7 +55,7 @@ static ssize_t eisa_eeprom_read(struct file * file, ssize_t ret; int i; - if (*ppos >= HPEE_MAX_LENGTH) + if (*ppos < 0 || *ppos >= HPEE_MAX_LENGTH) return 0; count = *ppos + count < HPEE_MAX_LENGTH ? count : HPEE_MAX_LENGTH - *ppos; diff --git a/drivers/parisc/hppb.c b/drivers/parisc/hppb.c index 1385641..815db17 100644 --- a/drivers/parisc/hppb.c +++ b/drivers/parisc/hppb.c @@ -62,7 +62,8 @@ static int hppb_probe(struct parisc_device *dev) } card = card->next; } - printk(KERN_INFO "Found GeckoBoa at 0x%x\n", dev->hpa.start); + printk(KERN_INFO "Found GeckoBoa at 0x%llx\n", + (unsigned long long) dev->hpa.start); card->hpa = dev->hpa.start; card->mmio_region.name = "HP-PB Bus"; @@ -73,8 +74,10 @@ static int hppb_probe(struct parisc_device *dev) status = ccio_request_resource(dev, &card->mmio_region); if(status < 0) { - printk(KERN_ERR "%s: failed to claim HP-PB bus space (%08x, %08x)\n", - __FILE__, card->mmio_region.start, card->mmio_region.end); + printk(KERN_ERR "%s: failed to claim HP-PB " + "bus space (0x%08llx, 0x%08llx)\n", + __FILE__, (unsigned long long) card->mmio_region.start, + (unsigned long long) card->mmio_region.end); } return 0; diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index ede6146..3aeb327 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -992,7 +992,7 @@ lba_pat_resources(struct parisc_device *pa_dev, struct lba_device *lba_dev) return; io_pdc_cell = kzalloc(sizeof(pdc_pat_cell_mod_maddr_block_t), GFP_KERNEL); - if (!pa_pdc_cell) { + if (!io_pdc_cell) { kfree(pa_pdc_cell); return; } diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index f9f9a5f..13a64bc 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -370,7 +370,7 @@ pdcspath_layer_read(struct pdcspath_entry *entry, char *buf) if (!i) /* entry is not ready */ return -ENODATA; - for (i = 0; devpath->layers[i] && (likely(i < 6)); i++) + for (i = 0; i < 6 && devpath->layers[i]; i++) out += sprintf(out, "%u ", devpath->layers[i]); out += sprintf(out, "\n"); diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c index a4494d7..8aebe1e9 100644 --- a/drivers/pci/hotplug/sgi_hotplug.c +++ b/drivers/pci/hotplug/sgi_hotplug.c @@ -90,11 +90,10 @@ static struct hotplug_slot_ops sn_hotplug_slot_ops = { static DEFINE_MUTEX(sn_hotplug_mutex); -static ssize_t path_show (struct hotplug_slot *bss_hotplug_slot, - char *buf) +static ssize_t path_show(struct pci_slot *pci_slot, char *buf) { int retval = -ENOENT; - struct slot *slot = bss_hotplug_slot->private; + struct slot *slot = pci_slot->hotplug->private; if (!slot) return retval; @@ -103,7 +102,7 @@ static ssize_t path_show (struct hotplug_slot *bss_hotplug_slot, return retval; } -static struct hotplug_slot_attribute sn_slot_path_attr = __ATTR_RO(path); +static struct pci_slot_attribute sn_slot_path_attr = __ATTR_RO(path); static int sn_pci_slot_valid(struct pci_bus *pci_bus, int device) { diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c index ebc9b8d..2314ad7 100644 --- a/drivers/pci/intel-iommu.c +++ b/drivers/pci/intel-iommu.c @@ -1505,7 +1505,6 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment, } set_bit(num, iommu->domain_ids); - set_bit(iommu->seq_id, &domain->iommu_bmp); iommu->domains[num] = domain; id = num; } @@ -1648,6 +1647,14 @@ static int domain_context_mapped(struct pci_dev *pdev) tmp->devfn); } +/* Returns a number of VTD pages, but aligned to MM page size */ +static inline unsigned long aligned_nrpages(unsigned long host_addr, + size_t size) +{ + host_addr &= ~PAGE_MASK; + return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; +} + static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, struct scatterlist *sg, unsigned long phys_pfn, unsigned long nr_pages, int prot) @@ -1675,7 +1682,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, uint64_t tmp; if (!sg_res) { - sg_res = (sg->offset + sg->length + VTD_PAGE_SIZE - 1) >> VTD_PAGE_SHIFT; + sg_res = aligned_nrpages(sg->offset, sg->length); sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset; sg->dma_length = sg->length; pteval = page_to_phys(sg_page(sg)) | prot; @@ -2415,14 +2422,6 @@ error: return ret; } -/* Returns a number of VTD pages, but aligned to MM page size */ -static inline unsigned long aligned_nrpages(unsigned long host_addr, - size_t size) -{ - host_addr &= ~PAGE_MASK; - return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT; -} - /* This takes a number of _MM_ pages, not VTD pages */ static struct iova *intel_alloc_iova(struct device *dev, struct dmar_domain *domain, @@ -2551,6 +2550,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, int prot = 0; int ret; struct intel_iommu *iommu; + unsigned long paddr_pfn = paddr >> PAGE_SHIFT; BUG_ON(dir == DMA_NONE); @@ -2585,7 +2585,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr, * is not a big problem */ ret = domain_pfn_mapping(domain, mm_to_dma_pfn(iova->pfn_lo), - paddr >> VTD_PAGE_SHIFT, size, prot); + mm_to_dma_pfn(paddr_pfn), size, prot); if (ret) goto error; @@ -2875,7 +2875,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne start_vpfn = mm_to_dma_pfn(iova->pfn_lo); - ret = domain_sg_mapping(domain, start_vpfn, sglist, mm_to_dma_pfn(size), prot); + ret = domain_sg_mapping(domain, start_vpfn, sglist, size, prot); if (unlikely(ret)) { /* clear the page */ dma_pte_clear_range(domain, start_vpfn, @@ -3408,6 +3408,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width) domain->iommu_count = 0; domain->iommu_coherency = 0; + domain->iommu_snooping = 0; domain->max_addr = 0; /* always allocate the top pgd */ diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index b711fb7..1898c7b 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -100,16 +100,16 @@ int pci_claim_resource(struct pci_dev *dev, int resource) { struct resource *res = &dev->resource[resource]; struct resource *root; - char *dtype = resource < PCI_BRIDGE_RESOURCES ? "device" : "bridge"; int err; root = pci_find_parent_resource(dev, res); err = -EINVAL; if (root != NULL) - err = insert_resource(root, res); + err = request_resource(root, res); if (err) { + const char *dtype = resource < PCI_BRIDGE_RESOURCES ? "device" : "bridge"; dev_err(&dev->dev, "BAR %d: %s of %s %pR\n", resource, root ? "address space collision on" : diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 46dad12..77c6097 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -277,31 +277,6 @@ config THINKPAD_ACPI_UNSAFE_LEDS Say N here, unless you are building a kernel for your own use, and need to control the important firmware LEDs. -config THINKPAD_ACPI_DOCK - bool "Legacy Docking Station Support" - depends on THINKPAD_ACPI - depends on ACPI_DOCK=n - default n - ---help--- - Allows the thinkpad_acpi driver to handle docking station events. - This support was made obsolete by the generic ACPI docking station - support (CONFIG_ACPI_DOCK). It will allow locking and removing the - laptop from the docking station, but will not properly connect PCI - devices. - - If you are not sure, say N here. - -config THINKPAD_ACPI_BAY - bool "Legacy Removable Bay Support" - depends on THINKPAD_ACPI - default y - ---help--- - Allows the thinkpad_acpi driver to handle removable bays. It will - electrically disable the device in the bay, and also generate - notifications when the bay lever is ejected or inserted. - - If you are not sure, say Y here. - config THINKPAD_ACPI_VIDEO bool "Video output control support" depends on THINKPAD_ACPI diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index ec560f1..222ffb89 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -143,6 +143,7 @@ struct eeepc_hotk { struct rfkill *bluetooth_rfkill; struct rfkill *wwan3g_rfkill; struct hotplug_slot *hotplug_slot; + struct work_struct hotplug_work; }; /* The actual device the driver binds to */ @@ -660,7 +661,7 @@ static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot, return 0; } -static void eeepc_rfkill_hotplug(void) +static void eeepc_hotplug_work(struct work_struct *work) { struct pci_dev *dev; struct pci_bus *bus = pci_find_bus(0, 1); @@ -701,7 +702,7 @@ static void eeepc_rfkill_notify(acpi_handle handle, u32 event, void *data) if (event != ACPI_NOTIFY_BUS_CHECK) return; - eeepc_rfkill_hotplug(); + schedule_work(&ehotk->hotplug_work); } static void eeepc_hotk_notify(struct acpi_device *device, u32 event) @@ -892,7 +893,7 @@ static int eeepc_hotk_resume(struct acpi_device *device) rfkill_set_sw_state(ehotk->wlan_rfkill, wlan != 1); - eeepc_rfkill_hotplug(); + schedule_work(&ehotk->hotplug_work); } if (ehotk->bluetooth_rfkill) @@ -1093,6 +1094,8 @@ static int eeepc_rfkill_init(struct device *dev) { int result = 0; + INIT_WORK(&ehotk->hotplug_work, eeepc_hotplug_work); + eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P6"); eeepc_register_rfkill_notifier("\\_SB.PCI0.P0P7"); diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index ca50856..a2ad53e 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -520,11 +520,13 @@ static int hp_wmi_resume_handler(struct platform_device *device) * the input layer will only actually pass it on if the state * changed. */ - - input_report_switch(hp_wmi_input_dev, SW_DOCK, hp_wmi_dock_state()); - input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, - hp_wmi_tablet_state()); - input_sync(hp_wmi_input_dev); + if (hp_wmi_input_dev) { + input_report_switch(hp_wmi_input_dev, SW_DOCK, + hp_wmi_dock_state()); + input_report_switch(hp_wmi_input_dev, SW_TABLET_MODE, + hp_wmi_tablet_state()); + input_sync(hp_wmi_input_dev); + } return 0; } diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index a463fd7..e856008 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -239,12 +239,6 @@ struct ibm_init_struct { }; static struct { -#ifdef CONFIG_THINKPAD_ACPI_BAY - u32 bay_status:1; - u32 bay_eject:1; - u32 bay_status2:1; - u32 bay_eject2:1; -#endif u32 bluetooth:1; u32 hotkey:1; u32 hotkey_mask:1; @@ -589,18 +583,6 @@ static int acpi_ec_write(int i, u8 v) return 1; } -#if defined(CONFIG_THINKPAD_ACPI_DOCK) || defined(CONFIG_THINKPAD_ACPI_BAY) -static int _sta(acpi_handle handle) -{ - int status; - - if (!handle || !acpi_evalf(handle, &status, "_STA", "d")) - status = 0; - - return status; -} -#endif - static int issue_thinkpad_cmos_command(int cmos_cmd) { if (!cmos_handle) @@ -784,6 +766,8 @@ static int dispatch_procfs_write(struct file *file, if (!ibm || !ibm->write) return -EINVAL; + if (count > PAGE_SIZE - 2) + return -EINVAL; kernbuf = kmalloc(count + 2, GFP_KERNEL); if (!kernbuf) @@ -4442,293 +4426,6 @@ static struct ibm_struct light_driver_data = { }; /************************************************************************* - * Dock subdriver - */ - -#ifdef CONFIG_THINKPAD_ACPI_DOCK - -static void dock_notify(struct ibm_struct *ibm, u32 event); -static int dock_read(char *p); -static int dock_write(char *buf); - -TPACPI_HANDLE(dock, root, "\\_SB.GDCK", /* X30, X31, X40 */ - "\\_SB.PCI0.DOCK", /* 600e/x,770e,770x,A2xm/p,T20-22,X20-21 */ - "\\_SB.PCI0.PCI1.DOCK", /* all others */ - "\\_SB.PCI.ISA.SLCE", /* 570 */ - ); /* A21e,G4x,R30,R31,R32,R40,R40e,R50e */ - -/* don't list other alternatives as we install a notify handler on the 570 */ -TPACPI_HANDLE(pci, root, "\\_SB.PCI"); /* 570 */ - -static const struct acpi_device_id ibm_pci_device_ids[] = { - {PCI_ROOT_HID_STRING, 0}, - {"", 0}, -}; - -static struct tp_acpi_drv_struct ibm_dock_acpidriver[2] = { - { - .notify = dock_notify, - .handle = &dock_handle, - .type = ACPI_SYSTEM_NOTIFY, - }, - { - /* THIS ONE MUST NEVER BE USED FOR DRIVER AUTOLOADING. - * We just use it to get notifications of dock hotplug - * in very old thinkpads */ - .hid = ibm_pci_device_ids, - .notify = dock_notify, - .handle = &pci_handle, - .type = ACPI_SYSTEM_NOTIFY, - }, -}; - -static struct ibm_struct dock_driver_data[2] = { - { - .name = "dock", - .read = dock_read, - .write = dock_write, - .acpi = &ibm_dock_acpidriver[0], - }, - { - .name = "dock", - .acpi = &ibm_dock_acpidriver[1], - }, -}; - -#define dock_docked() (_sta(dock_handle) & 1) - -static int __init dock_init(struct ibm_init_struct *iibm) -{ - vdbg_printk(TPACPI_DBG_INIT, "initializing dock subdriver\n"); - - TPACPI_ACPIHANDLE_INIT(dock); - - vdbg_printk(TPACPI_DBG_INIT, "dock is %s\n", - str_supported(dock_handle != NULL)); - - return (dock_handle)? 0 : 1; -} - -static int __init dock_init2(struct ibm_init_struct *iibm) -{ - int dock2_needed; - - vdbg_printk(TPACPI_DBG_INIT, "initializing dock subdriver part 2\n"); - - if (dock_driver_data[0].flags.acpi_driver_registered && - dock_driver_data[0].flags.acpi_notify_installed) { - TPACPI_ACPIHANDLE_INIT(pci); - dock2_needed = (pci_handle != NULL); - vdbg_printk(TPACPI_DBG_INIT, - "dock PCI handler for the TP 570 is %s\n", - str_supported(dock2_needed)); - } else { - vdbg_printk(TPACPI_DBG_INIT, - "dock subdriver part 2 not required\n"); - dock2_needed = 0; - } - - return (dock2_needed)? 0 : 1; -} - -static void dock_notify(struct ibm_struct *ibm, u32 event) -{ - int docked = dock_docked(); - int pci = ibm->acpi->hid && ibm->acpi->device && - acpi_match_device_ids(ibm->acpi->device, ibm_pci_device_ids); - int data; - - if (event == 1 && !pci) /* 570 */ - data = 1; /* button */ - else if (event == 1 && pci) /* 570 */ - data = 3; /* dock */ - else if (event == 3 && docked) - data = 1; /* button */ - else if (event == 3 && !docked) - data = 2; /* undock */ - else if (event == 0 && docked) - data = 3; /* dock */ - else { - printk(TPACPI_ERR "unknown dock event %d, status %d\n", - event, _sta(dock_handle)); - data = 0; /* unknown */ - } - acpi_bus_generate_proc_event(ibm->acpi->device, event, data); - acpi_bus_generate_netlink_event(ibm->acpi->device->pnp.device_class, - dev_name(&ibm->acpi->device->dev), - event, data); -} - -static int dock_read(char *p) -{ - int len = 0; - int docked = dock_docked(); - - if (!dock_handle) - len += sprintf(p + len, "status:\t\tnot supported\n"); - else if (!docked) - len += sprintf(p + len, "status:\t\tundocked\n"); - else { - len += sprintf(p + len, "status:\t\tdocked\n"); - len += sprintf(p + len, "commands:\tdock, undock\n"); - } - - return len; -} - -static int dock_write(char *buf) -{ - char *cmd; - - if (!dock_docked()) - return -ENODEV; - - while ((cmd = next_cmd(&buf))) { - if (strlencmp(cmd, "undock") == 0) { - if (!acpi_evalf(dock_handle, NULL, "_DCK", "vd", 0) || - !acpi_evalf(dock_handle, NULL, "_EJ0", "vd", 1)) - return -EIO; - } else if (strlencmp(cmd, "dock") == 0) { - if (!acpi_evalf(dock_handle, NULL, "_DCK", "vd", 1)) - return -EIO; - } else - return -EINVAL; - } - - return 0; -} - -#endif /* CONFIG_THINKPAD_ACPI_DOCK */ - -/************************************************************************* - * Bay subdriver - */ - -#ifdef CONFIG_THINKPAD_ACPI_BAY - -TPACPI_HANDLE(bay, root, "\\_SB.PCI.IDE.SECN.MAST", /* 570 */ - "\\_SB.PCI0.IDE0.IDES.IDSM", /* 600e/x, 770e, 770x */ - "\\_SB.PCI0.SATA.SCND.MSTR", /* T60, X60, Z60 */ - "\\_SB.PCI0.IDE0.SCND.MSTR", /* all others */ - ); /* A21e, R30, R31 */ -TPACPI_HANDLE(bay_ej, bay, "_EJ3", /* 600e/x, A2xm/p, A3x */ - "_EJ0", /* all others */ - ); /* 570,A21e,G4x,R30,R31,R32,R40e,R50e */ -TPACPI_HANDLE(bay2, root, "\\_SB.PCI0.IDE0.PRIM.SLAV", /* A3x, R32 */ - "\\_SB.PCI0.IDE0.IDEP.IDPS", /* 600e/x, 770e, 770x */ - ); /* all others */ -TPACPI_HANDLE(bay2_ej, bay2, "_EJ3", /* 600e/x, 770e, A3x */ - "_EJ0", /* 770x */ - ); /* all others */ - -static int __init bay_init(struct ibm_init_struct *iibm) -{ - vdbg_printk(TPACPI_DBG_INIT, "initializing bay subdriver\n"); - - TPACPI_ACPIHANDLE_INIT(bay); - if (bay_handle) - TPACPI_ACPIHANDLE_INIT(bay_ej); - TPACPI_ACPIHANDLE_INIT(bay2); - if (bay2_handle) - TPACPI_ACPIHANDLE_INIT(bay2_ej); - - tp_features.bay_status = bay_handle && - acpi_evalf(bay_handle, NULL, "_STA", "qv"); - tp_features.bay_status2 = bay2_handle && - acpi_evalf(bay2_handle, NULL, "_STA", "qv"); - - tp_features.bay_eject = bay_handle && bay_ej_handle && - (strlencmp(bay_ej_path, "_EJ0") == 0 || experimental); - tp_features.bay_eject2 = bay2_handle && bay2_ej_handle && - (strlencmp(bay2_ej_path, "_EJ0") == 0 || experimental); - - vdbg_printk(TPACPI_DBG_INIT, - "bay 1: status %s, eject %s; bay 2: status %s, eject %s\n", - str_supported(tp_features.bay_status), - str_supported(tp_features.bay_eject), - str_supported(tp_features.bay_status2), - str_supported(tp_features.bay_eject2)); - - return (tp_features.bay_status || tp_features.bay_eject || - tp_features.bay_status2 || tp_features.bay_eject2)? 0 : 1; -} - -static void bay_notify(struct ibm_struct *ibm, u32 event) -{ - acpi_bus_generate_proc_event(ibm->acpi->device, event, 0); - acpi_bus_generate_netlink_event(ibm->acpi->device->pnp.device_class, - dev_name(&ibm->acpi->device->dev), - event, 0); -} - -#define bay_occupied(b) (_sta(b##_handle) & 1) - -static int bay_read(char *p) -{ - int len = 0; - int occupied = bay_occupied(bay); - int occupied2 = bay_occupied(bay2); - int eject, eject2; - - len += sprintf(p + len, "status:\t\t%s\n", - tp_features.bay_status ? - (occupied ? "occupied" : "unoccupied") : - "not supported"); - if (tp_features.bay_status2) - len += sprintf(p + len, "status2:\t%s\n", occupied2 ? - "occupied" : "unoccupied"); - - eject = tp_features.bay_eject && occupied; - eject2 = tp_features.bay_eject2 && occupied2; - - if (eject && eject2) - len += sprintf(p + len, "commands:\teject, eject2\n"); - else if (eject) - len += sprintf(p + len, "commands:\teject\n"); - else if (eject2) - len += sprintf(p + len, "commands:\teject2\n"); - - return len; -} - -static int bay_write(char *buf) -{ - char *cmd; - - if (!tp_features.bay_eject && !tp_features.bay_eject2) - return -ENODEV; - - while ((cmd = next_cmd(&buf))) { - if (tp_features.bay_eject && strlencmp(cmd, "eject") == 0) { - if (!acpi_evalf(bay_ej_handle, NULL, NULL, "vd", 1)) - return -EIO; - } else if (tp_features.bay_eject2 && - strlencmp(cmd, "eject2") == 0) { - if (!acpi_evalf(bay2_ej_handle, NULL, NULL, "vd", 1)) - return -EIO; - } else - return -EINVAL; - } - - return 0; -} - -static struct tp_acpi_drv_struct ibm_bay_acpidriver = { - .notify = bay_notify, - .handle = &bay_handle, - .type = ACPI_SYSTEM_NOTIFY, -}; - -static struct ibm_struct bay_driver_data = { - .name = "bay", - .read = bay_read, - .write = bay_write, - .acpi = &ibm_bay_acpidriver, -}; - -#endif /* CONFIG_THINKPAD_ACPI_BAY */ - -/************************************************************************* * CMOS subdriver */ @@ -5945,14 +5642,48 @@ static struct backlight_ops ibm_backlight_data = { /* --------------------------------------------------------------------- */ +/* + * These are only useful for models that have only one possibility + * of GPU. If the BIOS model handles both ATI and Intel, don't use + * these quirks. + */ +#define TPACPI_BRGHT_Q_NOEC 0x0001 /* Must NOT use EC HBRV */ +#define TPACPI_BRGHT_Q_EC 0x0002 /* Should or must use EC HBRV */ +#define TPACPI_BRGHT_Q_ASK 0x8000 /* Ask for user report */ + +static const struct tpacpi_quirk brightness_quirk_table[] __initconst = { + /* Models with ATI GPUs known to require ECNVRAM mode */ + TPACPI_Q_IBM('1', 'Y', TPACPI_BRGHT_Q_EC), /* T43/p ATI */ + + /* Models with ATI GPUs (waiting confirmation) */ + TPACPI_Q_IBM('1', 'R', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_EC), + TPACPI_Q_IBM('1', 'Q', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_EC), + TPACPI_Q_IBM('7', '6', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_EC), + TPACPI_Q_IBM('7', '8', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_EC), + + /* Models with Intel Extreme Graphics 2 (waiting confirmation) */ + TPACPI_Q_IBM('1', 'V', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_NOEC), + TPACPI_Q_IBM('1', 'W', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_NOEC), + TPACPI_Q_IBM('1', 'U', TPACPI_BRGHT_Q_ASK|TPACPI_BRGHT_Q_NOEC), + + /* Models with Intel GMA900 */ + TPACPI_Q_IBM('7', '0', TPACPI_BRGHT_Q_NOEC), /* T43, R52 */ + TPACPI_Q_IBM('7', '4', TPACPI_BRGHT_Q_NOEC), /* X41 */ + TPACPI_Q_IBM('7', '5', TPACPI_BRGHT_Q_NOEC), /* X41 Tablet */ +}; + static int __init brightness_init(struct ibm_init_struct *iibm) { int b; + unsigned long quirks; vdbg_printk(TPACPI_DBG_INIT, "initializing brightness subdriver\n"); mutex_init(&brightness_mutex); + quirks = tpacpi_check_quirks(brightness_quirk_table, + ARRAY_SIZE(brightness_quirk_table)); + /* * We always attempt to detect acpi support, so as to switch * Lenovo Vista BIOS to ACPI brightness mode even if we are not @@ -6009,23 +5740,13 @@ static int __init brightness_init(struct ibm_init_struct *iibm) /* TPACPI_BRGHT_MODE_AUTO not implemented yet, just use default */ if (brightness_mode == TPACPI_BRGHT_MODE_AUTO || brightness_mode == TPACPI_BRGHT_MODE_MAX) { - if (thinkpad_id.vendor == PCI_VENDOR_ID_IBM) { - /* - * IBM models that define HBRV probably have - * EC-based backlight level control - */ - if (acpi_evalf(ec_handle, NULL, "HBRV", "qd")) - /* T40-T43, R50-R52, R50e, R51e, X31-X41 */ - brightness_mode = TPACPI_BRGHT_MODE_ECNVRAM; - else - /* all other IBM ThinkPads */ - brightness_mode = TPACPI_BRGHT_MODE_UCMS_STEP; - } else - /* All Lenovo ThinkPads */ + if (quirks & TPACPI_BRGHT_Q_EC) + brightness_mode = TPACPI_BRGHT_MODE_ECNVRAM; + else brightness_mode = TPACPI_BRGHT_MODE_UCMS_STEP; dbg_printk(TPACPI_DBG_BRGHT, - "selected brightness_mode=%d\n", + "driver auto-selected brightness_mode=%d\n", brightness_mode); } @@ -6052,6 +5773,15 @@ static int __init brightness_init(struct ibm_init_struct *iibm) vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_BRGHT, "brightness is supported\n"); + if (quirks & TPACPI_BRGHT_Q_ASK) { + printk(TPACPI_NOTICE + "brightness: will use unverified default: " + "brightness_mode=%d\n", brightness_mode); + printk(TPACPI_NOTICE + "brightness: please report to %s whether it works well " + "or not on your ThinkPad\n", TPACPI_MAIL); + } + ibm_backlight_device->props.max_brightness = (tp_features.bright_16levels)? 15 : 7; ibm_backlight_device->props.brightness = b & TP_EC_BACKLIGHT_LVLMSK; @@ -7854,22 +7584,6 @@ static struct ibm_init_struct ibms_init[] __initdata = { .init = light_init, .data = &light_driver_data, }, -#ifdef CONFIG_THINKPAD_ACPI_DOCK - { - .init = dock_init, - .data = &dock_driver_data[0], - }, - { - .init = dock_init2, - .data = &dock_driver_data[1], - }, -#endif -#ifdef CONFIG_THINKPAD_ACPI_BAY - { - .init = bay_init, - .data = &bay_driver_data, - }, -#endif { .init = cmos_init, .data = &cmos_driver_data, @@ -7968,12 +7682,6 @@ TPACPI_PARAM(hotkey); TPACPI_PARAM(bluetooth); TPACPI_PARAM(video); TPACPI_PARAM(light); -#ifdef CONFIG_THINKPAD_ACPI_DOCK -TPACPI_PARAM(dock); -#endif -#ifdef CONFIG_THINKPAD_ACPI_BAY -TPACPI_PARAM(bay); -#endif /* CONFIG_THINKPAD_ACPI_BAY */ TPACPI_PARAM(cmos); TPACPI_PARAM(led); TPACPI_PARAM(beep); diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 8030e25..c75d6f3 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -553,40 +553,35 @@ static void _zfcp_erp_unit_reopen_all(struct zfcp_port *port, int clear, _zfcp_erp_unit_reopen(unit, clear, id, ref); } -static void zfcp_erp_strategy_followup_actions(struct zfcp_erp_action *act) +static void zfcp_erp_strategy_followup_failed(struct zfcp_erp_action *act) { - struct zfcp_adapter *adapter = act->adapter; - struct zfcp_port *port = act->port; - struct zfcp_unit *unit = act->unit; - u32 status = act->status; - - /* initiate follow-up actions depending on success of finished action */ switch (act->action) { - case ZFCP_ERP_ACTION_REOPEN_ADAPTER: - if (status == ZFCP_ERP_SUCCEEDED) - _zfcp_erp_port_reopen_all(adapter, 0, "ersfa_1", NULL); - else - _zfcp_erp_adapter_reopen(adapter, 0, "ersfa_2", NULL); + _zfcp_erp_adapter_reopen(act->adapter, 0, "ersff_1", NULL); break; - case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: - if (status == ZFCP_ERP_SUCCEEDED) - _zfcp_erp_port_reopen(port, 0, "ersfa_3", NULL); - else - _zfcp_erp_adapter_reopen(adapter, 0, "ersfa_4", NULL); + _zfcp_erp_port_forced_reopen(act->port, 0, "ersff_2", NULL); break; - case ZFCP_ERP_ACTION_REOPEN_PORT: - if (status == ZFCP_ERP_SUCCEEDED) - _zfcp_erp_unit_reopen_all(port, 0, "ersfa_5", NULL); - else - _zfcp_erp_port_forced_reopen(port, 0, "ersfa_6", NULL); + _zfcp_erp_port_reopen(act->port, 0, "ersff_3", NULL); break; - case ZFCP_ERP_ACTION_REOPEN_UNIT: - if (status != ZFCP_ERP_SUCCEEDED) - _zfcp_erp_port_reopen(unit->port, 0, "ersfa_7", NULL); + _zfcp_erp_unit_reopen(act->unit, 0, "ersff_4", NULL); + break; + } +} + +static void zfcp_erp_strategy_followup_success(struct zfcp_erp_action *act) +{ + switch (act->action) { + case ZFCP_ERP_ACTION_REOPEN_ADAPTER: + _zfcp_erp_port_reopen_all(act->adapter, 0, "ersfs_1", NULL); + break; + case ZFCP_ERP_ACTION_REOPEN_PORT_FORCED: + _zfcp_erp_port_reopen(act->port, 0, "ersfs_2", NULL); + break; + case ZFCP_ERP_ACTION_REOPEN_PORT: + _zfcp_erp_unit_reopen_all(act->port, 0, "ersfs_3", NULL); break; } } @@ -801,7 +796,7 @@ static int zfcp_erp_port_forced_strategy(struct zfcp_erp_action *erp_action) return ZFCP_ERP_FAILED; case ZFCP_ERP_STEP_PHYS_PORT_CLOSING: - if (status & ZFCP_STATUS_PORT_PHYS_OPEN) + if (!(status & ZFCP_STATUS_PORT_PHYS_OPEN)) return ZFCP_ERP_SUCCEEDED; } return ZFCP_ERP_FAILED; @@ -853,11 +848,17 @@ void zfcp_erp_port_strategy_open_lookup(struct work_struct *work) gid_pn_work); retval = zfcp_fc_ns_gid_pn(&port->erp_action); - if (retval == -ENOMEM) - zfcp_erp_notify(&port->erp_action, ZFCP_ERP_NOMEM); - port->erp_action.step = ZFCP_ERP_STEP_NAMESERVER_LOOKUP; - if (retval) - zfcp_erp_notify(&port->erp_action, ZFCP_ERP_FAILED); + if (!retval) { + port->erp_action.step = ZFCP_ERP_STEP_NAMESERVER_LOOKUP; + goto out; + } + if (retval == -ENOMEM) { + zfcp_erp_notify(&port->erp_action, ZFCP_STATUS_ERP_LOWMEM); + goto out; + } + /* all other error condtions */ + zfcp_erp_notify(&port->erp_action, 0); +out: zfcp_port_put(port); } @@ -1289,7 +1290,10 @@ static int zfcp_erp_strategy(struct zfcp_erp_action *erp_action) retval = zfcp_erp_strategy_statechange(erp_action, retval); if (retval == ZFCP_ERP_EXIT) goto unlock; - zfcp_erp_strategy_followup_actions(erp_action); + if (retval == ZFCP_ERP_SUCCEEDED) + zfcp_erp_strategy_followup_success(erp_action); + if (retval == ZFCP_ERP_FAILED) + zfcp_erp_strategy_followup_failed(erp_action); unlock: write_unlock(&adapter->erp_lock); diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index 2f0705d..47daebf 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -79,11 +79,9 @@ static int zfcp_wka_port_get(struct zfcp_wka_port *wka_port) mutex_unlock(&wka_port->mutex); - wait_event_timeout( - wka_port->completion_wq, - wka_port->status == ZFCP_WKA_PORT_ONLINE || - wka_port->status == ZFCP_WKA_PORT_OFFLINE, - HZ >> 1); + wait_event(wka_port->completion_wq, + wka_port->status == ZFCP_WKA_PORT_ONLINE || + wka_port->status == ZFCP_WKA_PORT_OFFLINE); if (wka_port->status == ZFCP_WKA_PORT_ONLINE) { atomic_inc(&wka_port->refcount); diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index c57658f..47795fb 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -670,8 +670,11 @@ static int zfcp_fsf_req_sbal_get(struct zfcp_adapter *adapter) zfcp_fsf_sbal_check(adapter), 5 * HZ); if (ret > 0) return 0; - if (!ret) + if (!ret) { atomic_inc(&adapter->qdio_outb_full); + /* assume hanging outbound queue, try queue recovery */ + zfcp_erp_adapter_reopen(adapter, 0, "fsrsg_1", NULL); + } spin_lock_bh(&adapter->req_q_lock); return -EIO; @@ -722,7 +725,7 @@ static struct zfcp_fsf_req *zfcp_fsf_req_create(struct zfcp_adapter *adapter, req = zfcp_fsf_alloc_qtcb(pool); if (unlikely(!req)) - return ERR_PTR(-EIO); + return ERR_PTR(-ENOMEM); if (adapter->req_no == 0) adapter->req_no++; @@ -1010,6 +1013,23 @@ skip_fsfstatus: send_ct->handler(send_ct->handler_data); } +static void zfcp_fsf_setup_ct_els_unchained(struct qdio_buffer_element *sbale, + struct scatterlist *sg_req, + struct scatterlist *sg_resp) +{ + sbale[0].flags |= SBAL_FLAGS0_TYPE_WRITE_READ; + sbale[2].addr = sg_virt(sg_req); + sbale[2].length = sg_req->length; + sbale[3].addr = sg_virt(sg_resp); + sbale[3].length = sg_resp->length; + sbale[3].flags |= SBAL_FLAGS_LAST_ENTRY; +} + +static int zfcp_fsf_one_sbal(struct scatterlist *sg) +{ + return sg_is_last(sg) && sg->length <= PAGE_SIZE; +} + static int zfcp_fsf_setup_ct_els_sbals(struct zfcp_fsf_req *req, struct scatterlist *sg_req, struct scatterlist *sg_resp, @@ -1020,30 +1040,30 @@ static int zfcp_fsf_setup_ct_els_sbals(struct zfcp_fsf_req *req, int bytes; if (!(feat & FSF_FEATURE_ELS_CT_CHAINED_SBALS)) { - if (sg_req->length > PAGE_SIZE || sg_resp->length > PAGE_SIZE || - !sg_is_last(sg_req) || !sg_is_last(sg_resp)) + if (!zfcp_fsf_one_sbal(sg_req) || !zfcp_fsf_one_sbal(sg_resp)) return -EOPNOTSUPP; - sbale[0].flags |= SBAL_FLAGS0_TYPE_WRITE_READ; - sbale[2].addr = sg_virt(sg_req); - sbale[2].length = sg_req->length; - sbale[3].addr = sg_virt(sg_resp); - sbale[3].length = sg_resp->length; - sbale[3].flags |= SBAL_FLAGS_LAST_ENTRY; + zfcp_fsf_setup_ct_els_unchained(sbale, sg_req, sg_resp); + return 0; + } + + /* use single, unchained SBAL if it can hold the request */ + if (zfcp_fsf_one_sbal(sg_req) && zfcp_fsf_one_sbal(sg_resp)) { + zfcp_fsf_setup_ct_els_unchained(sbale, sg_req, sg_resp); return 0; } bytes = zfcp_qdio_sbals_from_sg(req, SBAL_FLAGS0_TYPE_WRITE_READ, sg_req, max_sbals); if (bytes <= 0) - return -ENOMEM; + return -EIO; req->qtcb->bottom.support.req_buf_length = bytes; req->sbale_curr = ZFCP_LAST_SBALE_PER_SBAL; bytes = zfcp_qdio_sbals_from_sg(req, SBAL_FLAGS0_TYPE_WRITE_READ, sg_resp, max_sbals); if (bytes <= 0) - return -ENOMEM; + return -EIO; req->qtcb->bottom.support.resp_buf_length = bytes; return 0; @@ -1607,10 +1627,10 @@ static void zfcp_fsf_open_wka_port_handler(struct zfcp_fsf_req *req) case FSF_ACCESS_DENIED: wka_port->status = ZFCP_WKA_PORT_OFFLINE; break; - case FSF_PORT_ALREADY_OPEN: - break; case FSF_GOOD: wka_port->handle = header->port_handle; + /* fall through */ + case FSF_PORT_ALREADY_OPEN: wka_port->status = ZFCP_WKA_PORT_ONLINE; } out: @@ -1731,15 +1751,16 @@ static void zfcp_fsf_close_physical_port_handler(struct zfcp_fsf_req *req) zfcp_fsf_access_denied_port(req, port); break; case FSF_PORT_BOXED: - zfcp_erp_port_boxed(port, "fscpph2", req); - req->status |= ZFCP_STATUS_FSFREQ_ERROR | - ZFCP_STATUS_FSFREQ_RETRY; /* can't use generic zfcp_erp_modify_port_status because * ZFCP_STATUS_COMMON_OPEN must not be reset for the port */ atomic_clear_mask(ZFCP_STATUS_PORT_PHYS_OPEN, &port->status); list_for_each_entry(unit, &port->unit_list_head, list) atomic_clear_mask(ZFCP_STATUS_COMMON_OPEN, &unit->status); + zfcp_erp_port_boxed(port, "fscpph2", req); + req->status |= ZFCP_STATUS_FSFREQ_ERROR | + ZFCP_STATUS_FSFREQ_RETRY; + break; case FSF_ADAPTER_STATUS_AVAILABLE: switch (header->fsf_status_qual.word[0]) { @@ -2541,7 +2562,6 @@ struct zfcp_fsf_req *zfcp_fsf_control_file(struct zfcp_adapter *adapter, bytes = zfcp_qdio_sbals_from_sg(req, direction, fsf_cfdc->sg, FSF_MAX_SBALS_PER_REQ); if (bytes != ZFCP_CFDC_MAX_SIZE) { - retval = -ENOMEM; zfcp_fsf_req_free(req); goto out; } diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 967ede7..6925a17 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -167,20 +167,21 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt) struct zfcp_unit *unit = scpnt->device->hostdata; struct zfcp_fsf_req *old_req, *abrt_req; unsigned long flags; - unsigned long old_req_id = (unsigned long) scpnt->host_scribble; + unsigned long old_reqid = (unsigned long) scpnt->host_scribble; int retval = SUCCESS; int retry = 3; + char *dbf_tag; /* avoid race condition between late normal completion and abort */ write_lock_irqsave(&adapter->abort_lock, flags); spin_lock(&adapter->req_list_lock); - old_req = zfcp_reqlist_find(adapter, old_req_id); + old_req = zfcp_reqlist_find(adapter, old_reqid); spin_unlock(&adapter->req_list_lock); if (!old_req) { write_unlock_irqrestore(&adapter->abort_lock, flags); zfcp_scsi_dbf_event_abort("lte1", adapter, scpnt, NULL, - old_req_id); + old_reqid); return FAILED; /* completion could be in progress */ } old_req->data = NULL; @@ -189,7 +190,7 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt) write_unlock_irqrestore(&adapter->abort_lock, flags); while (retry--) { - abrt_req = zfcp_fsf_abort_fcp_command(old_req_id, unit); + abrt_req = zfcp_fsf_abort_fcp_command(old_reqid, unit); if (abrt_req) break; @@ -197,7 +198,7 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt) if (!(atomic_read(&adapter->status) & ZFCP_STATUS_COMMON_RUNNING)) { zfcp_scsi_dbf_event_abort("nres", adapter, scpnt, NULL, - old_req_id); + old_reqid); return SUCCESS; } } @@ -208,13 +209,14 @@ static int zfcp_scsi_eh_abort_handler(struct scsi_cmnd *scpnt) abrt_req->status & ZFCP_STATUS_FSFREQ_COMPLETED); if (abrt_req->status & ZFCP_STATUS_FSFREQ_ABORTSUCCEEDED) - zfcp_scsi_dbf_event_abort("okay", adapter, scpnt, abrt_req, 0); + dbf_tag = "okay"; else if (abrt_req->status & ZFCP_STATUS_FSFREQ_ABORTNOTNEEDED) - zfcp_scsi_dbf_event_abort("lte2", adapter, scpnt, abrt_req, 0); + dbf_tag = "lte2"; else { - zfcp_scsi_dbf_event_abort("fail", adapter, scpnt, abrt_req, 0); + dbf_tag = "fail"; retval = FAILED; } + zfcp_scsi_dbf_event_abort(dbf_tag, adapter, scpnt, abrt_req, old_reqid); zfcp_fsf_req_free(abrt_req); return retval; } @@ -534,6 +536,9 @@ static void zfcp_scsi_rport_register(struct zfcp_port *port) struct fc_rport_identifiers ids; struct fc_rport *rport; + if (port->rport) + return; + ids.node_name = port->wwnn; ids.port_name = port->wwpn; ids.port_id = port->d_id; @@ -557,8 +562,10 @@ static void zfcp_scsi_rport_block(struct zfcp_port *port) { struct fc_rport *rport = port->rport; - if (rport) + if (rport) { fc_remote_port_delete(rport); + port->rport = NULL; + } } void zfcp_scsi_schedule_rport_register(struct zfcp_port *port) diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 3e51e64..0fe5cce 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -494,9 +494,14 @@ static ssize_t zfcp_sysfs_adapter_q_full_show(struct device *dev, struct Scsi_Host *scsi_host = class_to_shost(dev); struct zfcp_adapter *adapter = (struct zfcp_adapter *) scsi_host->hostdata[0]; + u64 util; + + spin_lock_bh(&adapter->qdio_stat_lock); + util = adapter->req_q_util; + spin_unlock_bh(&adapter->qdio_stat_lock); return sprintf(buf, "%d %llu\n", atomic_read(&adapter->qdio_outb_full), - (unsigned long long)adapter->req_q_util); + (unsigned long long)util); } static DEVICE_ATTR(queue_full, S_IRUGO, zfcp_sysfs_adapter_q_full_show, NULL); diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c index 2bc22be..145ab9b 100644 --- a/drivers/scsi/libfc/fc_exch.c +++ b/drivers/scsi/libfc/fc_exch.c @@ -415,9 +415,9 @@ static void fc_exch_timeout(struct work_struct *work) e_stat = ep->esb_stat; if (e_stat & ESB_ST_COMPLETE) { ep->esb_stat = e_stat & ~ESB_ST_REC_QUAL; + spin_unlock_bh(&ep->ex_lock); if (e_stat & ESB_ST_REC_QUAL) fc_exch_rrq(ep); - spin_unlock_bh(&ep->ex_lock); goto done; } else { resp = ep->resp; @@ -1624,14 +1624,14 @@ static void fc_exch_rrq(struct fc_exch *ep) struct fc_lport *lp; struct fc_els_rrq *rrq; struct fc_frame *fp; - struct fc_seq *rrq_sp; u32 did; lp = ep->lp; fp = fc_frame_alloc(lp, sizeof(*rrq)); if (!fp) - return; + goto retry; + rrq = fc_frame_payload_get(fp, sizeof(*rrq)); memset(rrq, 0, sizeof(*rrq)); rrq->rrq_cmd = ELS_RRQ; @@ -1647,13 +1647,20 @@ static void fc_exch_rrq(struct fc_exch *ep) fc_host_port_id(lp->host), FC_TYPE_ELS, FC_FC_FIRST_SEQ | FC_FC_END_SEQ | FC_FC_SEQ_INIT, 0); - rrq_sp = fc_exch_seq_send(lp, fp, fc_exch_rrq_resp, NULL, ep, - lp->e_d_tov); - if (!rrq_sp) { - ep->esb_stat |= ESB_ST_REC_QUAL; - fc_exch_timer_set_locked(ep, ep->r_a_tov); + if (fc_exch_seq_send(lp, fp, fc_exch_rrq_resp, NULL, ep, lp->e_d_tov)) + return; + +retry: + spin_lock_bh(&ep->ex_lock); + if (ep->state & (FC_EX_RST_CLEANUP | FC_EX_DONE)) { + spin_unlock_bh(&ep->ex_lock); + /* drop hold for rec qual */ + fc_exch_release(ep); return; } + ep->esb_stat |= ESB_ST_REC_QUAL; + fc_exch_timer_set_locked(ep, ep->r_a_tov); + spin_unlock_bh(&ep->ex_lock); } diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 716cc34..a751f62 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1974,10 +1974,10 @@ int iscsi_eh_abort(struct scsi_cmnd *sc) * good and have never sent us a successful tmf response * then sent more data for the cmd. */ - spin_lock(&session->lock); + spin_lock_bh(&session->lock); fail_scsi_task(task, DID_ABORT); conn->tmf_state = TMF_INITIAL; - spin_unlock(&session->lock); + spin_unlock_bh(&session->lock); iscsi_start_tx(conn); goto success_unlocked; case TMF_TIMEDOUT: diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 54fa1e4..b338195 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -766,6 +766,7 @@ static int sas_ex_join_wide_port(struct domain_device *parent, int phy_id) if (!memcmp(phy->attached_sas_addr, ephy->attached_sas_addr, SAS_ADDR_SIZE) && ephy->port) { sas_port_add_phy(ephy->port, phy->phy); + phy->port = ephy->port; phy->phy_state = PHY_DEVICE_DISCOVERED; return 0; } @@ -945,11 +946,21 @@ static int sas_ex_discover_dev(struct domain_device *dev, int phy_id) if (ex->ex_phy[i].phy_state == PHY_VACANT || ex->ex_phy[i].phy_state == PHY_NOT_PRESENT) continue; - + /* + * Due to races, the phy might not get added to the + * wide port, so we add the phy to the wide port here. + */ if (SAS_ADDR(ex->ex_phy[i].attached_sas_addr) == - SAS_ADDR(child->sas_addr)) + SAS_ADDR(child->sas_addr)) { ex->ex_phy[i].phy_state= PHY_DEVICE_DISCOVERED; + res = sas_ex_join_wide_port(dev, i); + if (!res) + SAS_DPRINTK("Attaching ex phy%d to wide port %016llx\n", + i, SAS_ADDR(ex->ex_phy[i].attached_sas_addr)); + + } } + res = 0; } return res; @@ -1598,7 +1609,7 @@ static int sas_get_phy_attached_sas_addr(struct domain_device *dev, } static int sas_find_bcast_phy(struct domain_device *dev, int *phy_id, - int from_phy) + int from_phy, bool update) { struct expander_device *ex = &dev->ex_dev; int res = 0; @@ -1611,7 +1622,9 @@ static int sas_find_bcast_phy(struct domain_device *dev, int *phy_id, if (res) goto out; else if (phy_change_count != ex->ex_phy[i].phy_change_count) { - ex->ex_phy[i].phy_change_count = phy_change_count; + if (update) + ex->ex_phy[i].phy_change_count = + phy_change_count; *phy_id = i; return 0; } @@ -1653,31 +1666,52 @@ out: kfree(rg_req); return res; } +/** + * sas_find_bcast_dev - find the device issue BROADCAST(CHANGE). + * @dev:domain device to be detect. + * @src_dev: the device which originated BROADCAST(CHANGE). + * + * Add self-configuration expander suport. Suppose two expander cascading, + * when the first level expander is self-configuring, hotplug the disks in + * second level expander, BROADCAST(CHANGE) will not only be originated + * in the second level expander, but also be originated in the first level + * expander (see SAS protocol SAS 2r-14, 7.11 for detail), it is to say, + * expander changed count in two level expanders will all increment at least + * once, but the phy which chang count has changed is the source device which + * we concerned. + */ static int sas_find_bcast_dev(struct domain_device *dev, struct domain_device **src_dev) { struct expander_device *ex = &dev->ex_dev; int ex_change_count = -1; + int phy_id = -1; int res; + struct domain_device *ch; res = sas_get_ex_change_count(dev, &ex_change_count); if (res) goto out; - if (ex_change_count != -1 && - ex_change_count != ex->ex_change_count) { - *src_dev = dev; - ex->ex_change_count = ex_change_count; - } else { - struct domain_device *ch; - - list_for_each_entry(ch, &ex->children, siblings) { - if (ch->dev_type == EDGE_DEV || - ch->dev_type == FANOUT_DEV) { - res = sas_find_bcast_dev(ch, src_dev); - if (src_dev) - return res; - } + if (ex_change_count != -1 && ex_change_count != ex->ex_change_count) { + /* Just detect if this expander phys phy change count changed, + * in order to determine if this expander originate BROADCAST, + * and do not update phy change count field in our structure. + */ + res = sas_find_bcast_phy(dev, &phy_id, 0, false); + if (phy_id != -1) { + *src_dev = dev; + ex->ex_change_count = ex_change_count; + SAS_DPRINTK("Expander phy change count has changed\n"); + return res; + } else + SAS_DPRINTK("Expander phys DID NOT change\n"); + } + list_for_each_entry(ch, &ex->children, siblings) { + if (ch->dev_type == EDGE_DEV || ch->dev_type == FANOUT_DEV) { + res = sas_find_bcast_dev(ch, src_dev); + if (src_dev) + return res; } } out: @@ -1700,24 +1734,26 @@ static void sas_unregister_ex_tree(struct domain_device *dev) } static void sas_unregister_devs_sas_addr(struct domain_device *parent, - int phy_id) + int phy_id, bool last) { struct expander_device *ex_dev = &parent->ex_dev; struct ex_phy *phy = &ex_dev->ex_phy[phy_id]; struct domain_device *child, *n; - - list_for_each_entry_safe(child, n, &ex_dev->children, siblings) { - if (SAS_ADDR(child->sas_addr) == - SAS_ADDR(phy->attached_sas_addr)) { - if (child->dev_type == EDGE_DEV || - child->dev_type == FANOUT_DEV) - sas_unregister_ex_tree(child); - else - sas_unregister_dev(child); - break; + if (last) { + list_for_each_entry_safe(child, n, + &ex_dev->children, siblings) { + if (SAS_ADDR(child->sas_addr) == + SAS_ADDR(phy->attached_sas_addr)) { + if (child->dev_type == EDGE_DEV || + child->dev_type == FANOUT_DEV) + sas_unregister_ex_tree(child); + else + sas_unregister_dev(child); + break; + } } + sas_disable_routing(parent, phy->attached_sas_addr); } - sas_disable_routing(parent, phy->attached_sas_addr); memset(phy->attached_sas_addr, 0, SAS_ADDR_SIZE); sas_port_delete_phy(phy->port, phy->phy); if (phy->port->num_phys == 0) @@ -1770,15 +1806,31 @@ static int sas_discover_new(struct domain_device *dev, int phy_id) { struct ex_phy *ex_phy = &dev->ex_dev.ex_phy[phy_id]; struct domain_device *child; - int res; + bool found = false; + int res, i; SAS_DPRINTK("ex %016llx phy%d new device attached\n", SAS_ADDR(dev->sas_addr), phy_id); res = sas_ex_phy_discover(dev, phy_id); if (res) goto out; + /* to support the wide port inserted */ + for (i = 0; i < dev->ex_dev.num_phys; i++) { + struct ex_phy *ex_phy_temp = &dev->ex_dev.ex_phy[i]; + if (i == phy_id) + continue; + if (SAS_ADDR(ex_phy_temp->attached_sas_addr) == + SAS_ADDR(ex_phy->attached_sas_addr)) { + found = true; + break; + } + } + if (found) { + sas_ex_join_wide_port(dev, phy_id); + return 0; + } res = sas_ex_discover_devices(dev, phy_id); - if (res) + if (!res) goto out; list_for_each_entry(child, &dev->ex_dev.children, siblings) { if (SAS_ADDR(child->sas_addr) == @@ -1793,7 +1845,7 @@ out: return res; } -static int sas_rediscover_dev(struct domain_device *dev, int phy_id) +static int sas_rediscover_dev(struct domain_device *dev, int phy_id, bool last) { struct expander_device *ex = &dev->ex_dev; struct ex_phy *phy = &ex->ex_phy[phy_id]; @@ -1804,11 +1856,11 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id) switch (res) { case SMP_RESP_NO_PHY: phy->phy_state = PHY_NOT_PRESENT; - sas_unregister_devs_sas_addr(dev, phy_id); + sas_unregister_devs_sas_addr(dev, phy_id, last); goto out; break; case SMP_RESP_PHY_VACANT: phy->phy_state = PHY_VACANT; - sas_unregister_devs_sas_addr(dev, phy_id); + sas_unregister_devs_sas_addr(dev, phy_id, last); goto out; break; case SMP_RESP_FUNC_ACC: break; @@ -1816,7 +1868,7 @@ static int sas_rediscover_dev(struct domain_device *dev, int phy_id) if (SAS_ADDR(attached_sas_addr) == 0) { phy->phy_state = PHY_EMPTY; - sas_unregister_devs_sas_addr(dev, phy_id); + sas_unregister_devs_sas_addr(dev, phy_id, last); } else if (SAS_ADDR(attached_sas_addr) == SAS_ADDR(phy->attached_sas_addr)) { SAS_DPRINTK("ex %016llx phy 0x%x broadcast flutter\n", @@ -1828,12 +1880,27 @@ out: return res; } +/** + * sas_rediscover - revalidate the domain. + * @dev:domain device to be detect. + * @phy_id: the phy id will be detected. + * + * NOTE: this process _must_ quit (return) as soon as any connection + * errors are encountered. Connection recovery is done elsewhere. + * Discover process only interrogates devices in order to discover the + * domain.For plugging out, we un-register the device only when it is + * the last phy in the port, for other phys in this port, we just delete it + * from the port.For inserting, we do discovery when it is the + * first phy,for other phys in this port, we add it to the port to + * forming the wide-port. + */ static int sas_rediscover(struct domain_device *dev, const int phy_id) { struct expander_device *ex = &dev->ex_dev; struct ex_phy *changed_phy = &ex->ex_phy[phy_id]; int res = 0; int i; + bool last = true; /* is this the last phy of the port */ SAS_DPRINTK("ex %016llx phy%d originated BROADCAST(CHANGE)\n", SAS_ADDR(dev->sas_addr), phy_id); @@ -1848,13 +1915,13 @@ static int sas_rediscover(struct domain_device *dev, const int phy_id) SAS_ADDR(changed_phy->attached_sas_addr)) { SAS_DPRINTK("phy%d part of wide port with " "phy%d\n", phy_id, i); - goto out; + last = false; + break; } } - res = sas_rediscover_dev(dev, phy_id); + res = sas_rediscover_dev(dev, phy_id, last); } else res = sas_discover_new(dev, phy_id); -out: return res; } @@ -1881,7 +1948,7 @@ int sas_ex_revalidate_domain(struct domain_device *port_dev) do { phy_id = -1; - res = sas_find_bcast_phy(dev, &phy_id, i); + res = sas_find_bcast_phy(dev, &phy_id, i, true); if (phy_id == -1) break; res = sas_rediscover(dev, phy_id); diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c index e6ac59c..fe8b74c 100644 --- a/drivers/scsi/libsas/sas_port.c +++ b/drivers/scsi/libsas/sas_port.c @@ -56,7 +56,7 @@ static void sas_form_port(struct asd_sas_phy *phy) } } - /* find a port */ + /* see if the phy should be part of a wide port */ spin_lock_irqsave(&sas_ha->phy_port_lock, flags); for (i = 0; i < sas_ha->num_phys; i++) { port = sas_ha->sas_port[i]; @@ -69,12 +69,23 @@ static void sas_form_port(struct asd_sas_phy *phy) SAS_DPRINTK("phy%d matched wide port%d\n", phy->id, port->id); break; - } else if (*(u64 *) port->sas_addr == 0 && port->num_phys==0) { - memcpy(port->sas_addr, phy->sas_addr, SAS_ADDR_SIZE); - break; } spin_unlock(&port->phy_list_lock); } + /* The phy does not match any existing port, create a new one */ + if (i == sas_ha->num_phys) { + for (i = 0; i < sas_ha->num_phys; i++) { + port = sas_ha->sas_port[i]; + spin_lock(&port->phy_list_lock); + if (*(u64 *)port->sas_addr == 0 + && port->num_phys == 0) { + memcpy(port->sas_addr, phy->sas_addr, + SAS_ADDR_SIZE); + break; + } + spin_unlock(&port->phy_list_lock); + } + } if (i >= sas_ha->num_phys) { printk(KERN_NOTICE "%s: couldn't find a free port, bug?\n", diff --git a/drivers/scsi/qla4xxx/ql4_dbg.c b/drivers/scsi/qla4xxx/ql4_dbg.c index fcc184c..cbceb0e 100644 --- a/drivers/scsi/qla4xxx/ql4_dbg.c +++ b/drivers/scsi/qla4xxx/ql4_dbg.c @@ -15,19 +15,18 @@ void qla4xxx_dump_buffer(void *b, uint32_t size) uint32_t cnt; uint8_t *c = b; - printk(" 0 1 2 3 4 5 6 7 8 9 Ah Bh Ch Dh Eh " + printk(" 0 1 2 3 4 5 6 7 8 9 Ah Bh Ch Dh Eh " "Fh\n"); printk("------------------------------------------------------------" "--\n"); - for (cnt = 0; cnt < size; cnt++, c++) { - printk(KERN_DEBUG "%02x", *c); - if (!(cnt % 16)) - printk(KERN_DEBUG "\n"); + for (cnt = 0; cnt < size; c++) { + printk(KERN_INFO "%02x", *c); + if (!(++cnt % 16)) + printk(KERN_INFO "\n"); else - printk(KERN_DEBUG " "); + printk(KERN_INFO " "); } - if (cnt % 16) - printk(KERN_DEBUG "\n"); + printk(KERN_INFO "\n"); } diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index b586f27..81b5f29 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -100,7 +100,6 @@ #define MAX_SRBS MAX_CMDS_TO_RISC #define MBOX_AEN_REG_COUNT 5 #define MAX_INIT_RETRIES 5 -#define IOCB_HIWAT_CUSHION 16 /* * Buffer sizes @@ -184,6 +183,11 @@ struct srb { uint16_t cc_stat; u_long r_start; /* Time we recieve a cmd from OS */ u_long u_start; /* Time when we handed the cmd to F/W */ + + /* Used for extended sense / status continuation */ + uint8_t *req_sense_ptr; + uint16_t req_sense_len; + uint16_t reserved2; }; /* @@ -302,7 +306,6 @@ struct scsi_qla_host { uint32_t tot_ddbs; uint16_t iocb_cnt; - uint16_t iocb_hiwat; /* SRB cache. */ #define SRB_MIN_REQ 128 @@ -436,6 +439,8 @@ struct scsi_qla_host { /* Map ddb_list entry by FW ddb index */ struct ddb_entry *fw_ddb_index_map[MAX_DDB_ENTRIES]; + /* Saved srb for status continuation entry processing */ + struct srb *status_srb; }; static inline int is_qla4010(struct scsi_qla_host *ha) diff --git a/drivers/scsi/qla4xxx/ql4_fw.h b/drivers/scsi/qla4xxx/ql4_fw.h index 1b667a7..9cd7a60 100644 --- a/drivers/scsi/qla4xxx/ql4_fw.h +++ b/drivers/scsi/qla4xxx/ql4_fw.h @@ -572,6 +572,7 @@ struct conn_event_log_entry { *************************************************************************/ #define IOCB_MAX_CDB_LEN 16 /* Bytes in a CBD */ #define IOCB_MAX_SENSEDATA_LEN 32 /* Bytes of sense data */ +#define IOCB_MAX_EXT_SENSEDATA_LEN 60 /* Bytes of extended sense data */ /* IOCB header structure */ struct qla4_header { @@ -733,6 +734,12 @@ struct status_entry { }; +/* Status Continuation entry */ +struct status_cont_entry { + struct qla4_header hdr; /* 00-03 */ + uint8_t ext_sense_data[IOCB_MAX_EXT_SENSEDATA_LEN]; /* 04-63 */ +}; + struct passthru0 { struct qla4_header hdr; /* 00-03 */ uint32_t handle; /* 04-07 */ diff --git a/drivers/scsi/qla4xxx/ql4_iocb.c b/drivers/scsi/qla4xxx/ql4_iocb.c index 912a674..e0c3215 100644 --- a/drivers/scsi/qla4xxx/ql4_iocb.c +++ b/drivers/scsi/qla4xxx/ql4_iocb.c @@ -10,9 +10,42 @@ #include "ql4_dbg.h" #include "ql4_inline.h" - #include <scsi/scsi_tcq.h> +static int +qla4xxx_space_in_req_ring(struct scsi_qla_host *ha, uint16_t req_cnt) +{ + uint16_t cnt; + + /* Calculate number of free request entries. */ + if ((req_cnt + 2) >= ha->req_q_count) { + cnt = (uint16_t) le32_to_cpu(ha->shadow_regs->req_q_out); + if (ha->request_in < cnt) + ha->req_q_count = cnt - ha->request_in; + else + ha->req_q_count = REQUEST_QUEUE_DEPTH - + (ha->request_in - cnt); + } + + /* Check if room for request in request ring. */ + if ((req_cnt + 2) < ha->req_q_count) + return 1; + else + return 0; +} + +static void qla4xxx_advance_req_ring_ptr(struct scsi_qla_host *ha) +{ + /* Advance request queue pointer */ + if (ha->request_in == (REQUEST_QUEUE_DEPTH - 1)) { + ha->request_in = 0; + ha->request_ptr = ha->request_ring; + } else { + ha->request_in++; + ha->request_ptr++; + } +} + /** * qla4xxx_get_req_pkt - returns a valid entry in request queue. * @ha: Pointer to host adapter structure. @@ -26,35 +59,18 @@ static int qla4xxx_get_req_pkt(struct scsi_qla_host *ha, struct queue_entry **queue_entry) { - uint16_t request_in; - uint8_t status = QLA_SUCCESS; - - *queue_entry = ha->request_ptr; + uint16_t req_cnt = 1; - /* get the latest request_in and request_out index */ - request_in = ha->request_in; - ha->request_out = (uint16_t) le32_to_cpu(ha->shadow_regs->req_q_out); - - /* Advance request queue pointer and check for queue full */ - if (request_in == (REQUEST_QUEUE_DEPTH - 1)) { - request_in = 0; - ha->request_ptr = ha->request_ring; - } else { - request_in++; - ha->request_ptr++; - } - - /* request queue is full, try again later */ - if ((ha->iocb_cnt + 1) >= ha->iocb_hiwat) { - /* restore request pointer */ - ha->request_ptr = *queue_entry; - status = QLA_ERROR; - } else { - ha->request_in = request_in; + if (qla4xxx_space_in_req_ring(ha, req_cnt)) { + *queue_entry = ha->request_ptr; memset(*queue_entry, 0, sizeof(**queue_entry)); + + qla4xxx_advance_req_ring_ptr(ha); + ha->req_q_count -= req_cnt; + return QLA_SUCCESS; } - return status; + return QLA_ERROR; } /** @@ -100,21 +116,14 @@ exit_send_marker: return status; } -static struct continuation_t1_entry* qla4xxx_alloc_cont_entry( - struct scsi_qla_host *ha) +static struct continuation_t1_entry * +qla4xxx_alloc_cont_entry(struct scsi_qla_host *ha) { struct continuation_t1_entry *cont_entry; cont_entry = (struct continuation_t1_entry *)ha->request_ptr; - /* Advance request queue pointer */ - if (ha->request_in == (REQUEST_QUEUE_DEPTH - 1)) { - ha->request_in = 0; - ha->request_ptr = ha->request_ring; - } else { - ha->request_in++; - ha->request_ptr++; - } + qla4xxx_advance_req_ring_ptr(ha); /* Load packet defaults */ cont_entry->hdr.entryType = ET_CONTINUE; @@ -197,13 +206,10 @@ int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb * srb) struct scsi_cmnd *cmd = srb->cmd; struct ddb_entry *ddb_entry; struct command_t3_entry *cmd_entry; - int nseg; uint16_t tot_dsds; uint16_t req_cnt; - unsigned long flags; - uint16_t cnt; uint32_t index; char tag[2]; @@ -217,6 +223,19 @@ int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb * srb) index = (uint32_t)cmd->request->tag; + /* + * Check to see if adapter is online before placing request on + * request queue. If a reset occurs and a request is in the queue, + * the firmware will still attempt to process the request, retrieving + * garbage for pointers. + */ + if (!test_bit(AF_ONLINE, &ha->flags)) { + DEBUG2(printk("scsi%ld: %s: Adapter OFFLINE! " + "Do not issue command.\n", + ha->host_no, __func__)); + goto queuing_error; + } + /* Calculate the number of request entries needed. */ nseg = scsi_dma_map(cmd); if (nseg < 0) @@ -224,17 +243,7 @@ int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb * srb) tot_dsds = nseg; req_cnt = qla4xxx_calc_request_entries(tot_dsds); - - if (ha->req_q_count < (req_cnt + 2)) { - cnt = (uint16_t) le32_to_cpu(ha->shadow_regs->req_q_out); - if (ha->request_in < cnt) - ha->req_q_count = cnt - ha->request_in; - else - ha->req_q_count = REQUEST_QUEUE_DEPTH - - (ha->request_in - cnt); - } - - if (ha->req_q_count < (req_cnt + 2)) + if (!qla4xxx_space_in_req_ring(ha, req_cnt)) goto queuing_error; /* total iocbs active */ @@ -286,32 +295,10 @@ int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb * srb) break; } - - /* Advance request queue pointer */ - ha->request_in++; - if (ha->request_in == REQUEST_QUEUE_DEPTH) { - ha->request_in = 0; - ha->request_ptr = ha->request_ring; - } else - ha->request_ptr++; - - + qla4xxx_advance_req_ring_ptr(ha); qla4xxx_build_scsi_iocbs(srb, cmd_entry, tot_dsds); wmb(); - /* - * Check to see if adapter is online before placing request on - * request queue. If a reset occurs and a request is in the queue, - * the firmware will still attempt to process the request, retrieving - * garbage for pointers. - */ - if (!test_bit(AF_ONLINE, &ha->flags)) { - DEBUG2(printk("scsi%ld: %s: Adapter OFFLINE! " - "Do not issue command.\n", - ha->host_no, __func__)); - goto queuing_error; - } - srb->cmd->host_scribble = (unsigned char *)srb; /* update counters */ diff --git a/drivers/scsi/qla4xxx/ql4_isr.c b/drivers/scsi/qla4xxx/ql4_isr.c index 799120f..8025ee1 100644 --- a/drivers/scsi/qla4xxx/ql4_isr.c +++ b/drivers/scsi/qla4xxx/ql4_isr.c @@ -11,6 +11,98 @@ #include "ql4_inline.h" /** + * qla4xxx_copy_sense - copy sense data into cmd sense buffer + * @ha: Pointer to host adapter structure. + * @sts_entry: Pointer to status entry structure. + * @srb: Pointer to srb structure. + **/ +static void qla4xxx_copy_sense(struct scsi_qla_host *ha, + struct status_entry *sts_entry, + struct srb *srb) +{ + struct scsi_cmnd *cmd = srb->cmd; + uint16_t sense_len; + + memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + sense_len = le16_to_cpu(sts_entry->senseDataByteCnt); + if (sense_len == 0) + return; + + /* Save total available sense length, + * not to exceed cmd's sense buffer size */ + sense_len = min_t(uint16_t, sense_len, SCSI_SENSE_BUFFERSIZE); + srb->req_sense_ptr = cmd->sense_buffer; + srb->req_sense_len = sense_len; + + /* Copy sense from sts_entry pkt */ + sense_len = min_t(uint16_t, sense_len, IOCB_MAX_SENSEDATA_LEN); + memcpy(cmd->sense_buffer, sts_entry->senseData, sense_len); + + DEBUG2(printk(KERN_INFO "scsi%ld:%d:%d:%d: %s: sense key = %x, " + "ASL= %02x, ASC/ASCQ = %02x/%02x\n", ha->host_no, + cmd->device->channel, cmd->device->id, + cmd->device->lun, __func__, + sts_entry->senseData[2] & 0x0f, + sts_entry->senseData[7], + sts_entry->senseData[12], + sts_entry->senseData[13])); + + DEBUG5(qla4xxx_dump_buffer(cmd->sense_buffer, sense_len)); + srb->flags |= SRB_GOT_SENSE; + + /* Update srb, in case a sts_cont pkt follows */ + srb->req_sense_ptr += sense_len; + srb->req_sense_len -= sense_len; + if (srb->req_sense_len != 0) + ha->status_srb = srb; + else + ha->status_srb = NULL; +} + +/** + * qla4xxx_status_cont_entry - Process a Status Continuations entry. + * @ha: SCSI driver HA context + * @sts_cont: Entry pointer + * + * Extended sense data. + */ +static void +qla4xxx_status_cont_entry(struct scsi_qla_host *ha, + struct status_cont_entry *sts_cont) +{ + struct srb *srb = ha->status_srb; + struct scsi_cmnd *cmd; + uint8_t sense_len; + + if (srb == NULL) + return; + + cmd = srb->cmd; + if (cmd == NULL) { + DEBUG2(printk(KERN_INFO "scsi%ld: %s: Cmd already returned " + "back to OS srb=%p srb->state:%d\n", ha->host_no, + __func__, srb, srb->state)); + ha->status_srb = NULL; + return; + } + + /* Copy sense data. */ + sense_len = min_t(uint16_t, srb->req_sense_len, + IOCB_MAX_EXT_SENSEDATA_LEN); + memcpy(srb->req_sense_ptr, sts_cont->ext_sense_data, sense_len); + DEBUG5(qla4xxx_dump_buffer(srb->req_sense_ptr, sense_len)); + + srb->req_sense_ptr += sense_len; + srb->req_sense_len -= sense_len; + + /* Place command on done queue. */ + if (srb->req_sense_len == 0) { + qla4xxx_srb_compl(ha, srb); + ha->status_srb = NULL; + } +} + +/** * qla4xxx_status_entry - processes status IOCBs * @ha: Pointer to host adapter structure. * @sts_entry: Pointer to status entry structure. @@ -23,7 +115,6 @@ static void qla4xxx_status_entry(struct scsi_qla_host *ha, struct srb *srb; struct ddb_entry *ddb_entry; uint32_t residual; - uint16_t sensebytecnt; srb = qla4xxx_del_from_active_array(ha, le32_to_cpu(sts_entry->handle)); if (!srb) { @@ -92,24 +183,7 @@ static void qla4xxx_status_entry(struct scsi_qla_host *ha, break; /* Copy Sense Data into sense buffer. */ - memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); - - sensebytecnt = le16_to_cpu(sts_entry->senseDataByteCnt); - if (sensebytecnt == 0) - break; - - memcpy(cmd->sense_buffer, sts_entry->senseData, - min_t(uint16_t, sensebytecnt, SCSI_SENSE_BUFFERSIZE)); - - DEBUG2(printk("scsi%ld:%d:%d:%d: %s: sense key = %x, " - "ASC/ASCQ = %02x/%02x\n", ha->host_no, - cmd->device->channel, cmd->device->id, - cmd->device->lun, __func__, - sts_entry->senseData[2] & 0x0f, - sts_entry->senseData[12], - sts_entry->senseData[13])); - - srb->flags |= SRB_GOT_SENSE; + qla4xxx_copy_sense(ha, sts_entry, srb); break; case SCS_INCOMPLETE: @@ -176,23 +250,7 @@ static void qla4xxx_status_entry(struct scsi_qla_host *ha, break; /* Copy Sense Data into sense buffer. */ - memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); - - sensebytecnt = - le16_to_cpu(sts_entry->senseDataByteCnt); - if (sensebytecnt == 0) - break; - - memcpy(cmd->sense_buffer, sts_entry->senseData, - min_t(uint16_t, sensebytecnt, SCSI_SENSE_BUFFERSIZE)); - - DEBUG2(printk("scsi%ld:%d:%d:%d: %s: sense key = %x, " - "ASC/ASCQ = %02x/%02x\n", ha->host_no, - cmd->device->channel, cmd->device->id, - cmd->device->lun, __func__, - sts_entry->senseData[2] & 0x0f, - sts_entry->senseData[12], - sts_entry->senseData[13])); + qla4xxx_copy_sense(ha, sts_entry, srb); } else { /* * If RISC reports underrun and target does not @@ -268,9 +326,10 @@ static void qla4xxx_status_entry(struct scsi_qla_host *ha, status_entry_exit: - /* complete the request */ + /* complete the request, if not waiting for status_continuation pkt */ srb->cc_stat = sts_entry->completionStatus; - qla4xxx_srb_compl(ha, srb); + if (ha->status_srb == NULL) + qla4xxx_srb_compl(ha, srb); } /** @@ -305,10 +364,7 @@ static void qla4xxx_process_response_queue(struct scsi_qla_host * ha) /* process entry */ switch (sts_entry->hdr.entryType) { case ET_STATUS: - /* - * Common status - Single completion posted in single - * IOSB. - */ + /* Common status */ qla4xxx_status_entry(ha, sts_entry); break; @@ -316,9 +372,8 @@ static void qla4xxx_process_response_queue(struct scsi_qla_host * ha) break; case ET_STATUS_CONTINUATION: - /* Just throw away the status continuation entries */ - DEBUG2(printk("scsi%ld: %s: Status Continuation entry " - "- ignoring\n", ha->host_no, __func__)); + qla4xxx_status_cont_entry(ha, + (struct status_cont_entry *) sts_entry); break; case ET_COMMAND: diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c index 051b0f5..09d6d4b 100644 --- a/drivers/scsi/qla4xxx/ql4_mbx.c +++ b/drivers/scsi/qla4xxx/ql4_mbx.c @@ -385,16 +385,6 @@ int qla4xxx_get_firmware_status(struct scsi_qla_host * ha) mbox_sts[0])); return QLA_ERROR; } - - /* High-water mark of IOCBs */ - ha->iocb_hiwat = mbox_sts[2]; - if (ha->iocb_hiwat > IOCB_HIWAT_CUSHION) - ha->iocb_hiwat -= IOCB_HIWAT_CUSHION; - else - dev_info(&ha->pdev->dev, "WARNING!!! You have less than %d " - "firmware IOCBs available (%d).\n", - IOCB_HIWAT_CUSHION, ha->iocb_hiwat); - return QLA_SUCCESS; } diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index ec9da6c..40e3caf 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -66,6 +66,7 @@ static int qla4xxx_sess_get_param(struct iscsi_cls_session *sess, static int qla4xxx_host_get_param(struct Scsi_Host *shost, enum iscsi_host_param param, char *buf); static void qla4xxx_recovery_timedout(struct iscsi_cls_session *session); +static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc); /* * SCSI host template entry points @@ -89,6 +90,7 @@ static struct scsi_host_template qla4xxx_driver_template = { .eh_device_reset_handler = qla4xxx_eh_device_reset, .eh_target_reset_handler = qla4xxx_eh_target_reset, .eh_host_reset_handler = qla4xxx_eh_host_reset, + .eh_timed_out = qla4xxx_eh_cmd_timed_out, .slave_configure = qla4xxx_slave_configure, .slave_alloc = qla4xxx_slave_alloc, @@ -124,6 +126,21 @@ static struct iscsi_transport qla4xxx_iscsi_transport = { static struct scsi_transport_template *qla4xxx_scsi_transport; +static enum blk_eh_timer_return qla4xxx_eh_cmd_timed_out(struct scsi_cmnd *sc) +{ + struct iscsi_cls_session *session; + struct ddb_entry *ddb_entry; + + session = starget_to_session(scsi_target(sc->device)); + ddb_entry = session->dd_data; + + /* if we are not logged in then the LLD is going to clean up the cmd */ + if (atomic_read(&ddb_entry->state) != DDB_STATE_ONLINE) + return BLK_EH_RESET_TIMER; + else + return BLK_EH_NOT_HANDLED; +} + static void qla4xxx_recovery_timedout(struct iscsi_cls_session *session) { struct ddb_entry *ddb_entry = session->dd_data; @@ -904,18 +921,17 @@ static int qla4xxx_recover_adapter(struct scsi_qla_host *ha, /* Flush any pending ddb changed AENs */ qla4xxx_process_aen(ha, FLUSH_DDB_CHANGED_AENS); + qla4xxx_flush_active_srbs(ha); + /* Reset the firmware. If successful, function * returns with ISP interrupts enabled. */ - if (status == QLA_SUCCESS) { - DEBUG2(printk("scsi%ld: %s - Performing soft reset..\n", - ha->host_no, __func__)); - qla4xxx_flush_active_srbs(ha); - if (ql4xxx_lock_drvr_wait(ha) == QLA_SUCCESS) - status = qla4xxx_soft_reset(ha); - else - status = QLA_ERROR; - } + DEBUG2(printk("scsi%ld: %s - Performing soft reset..\n", + ha->host_no, __func__)); + if (ql4xxx_lock_drvr_wait(ha) == QLA_SUCCESS) + status = qla4xxx_soft_reset(ha); + else + status = QLA_ERROR; /* Flush any pending ddb changed AENs */ qla4xxx_process_aen(ha, FLUSH_DDB_CHANGED_AENS); @@ -1527,11 +1543,9 @@ static int qla4xxx_eh_device_reset(struct scsi_cmnd *cmd) { struct scsi_qla_host *ha = to_qla_host(cmd->device->host); struct ddb_entry *ddb_entry = cmd->device->hostdata; - struct srb *sp; int ret = FAILED, stat; - sp = (struct srb *) cmd->SCp.ptr; - if (!sp || !ddb_entry) + if (!ddb_entry) return ret; dev_info(&ha->pdev->dev, @@ -1644,7 +1658,7 @@ static int qla4xxx_eh_host_reset(struct scsi_cmnd *cmd) ha = (struct scsi_qla_host *) cmd->device->host->hostdata; dev_info(&ha->pdev->dev, - "scsi(%ld:%d:%d:%d): ADAPTER RESET ISSUED.\n", ha->host_no, + "scsi(%ld:%d:%d:%d): HOST RESET ISSUED.\n", ha->host_no, cmd->device->channel, cmd->device->id, cmd->device->lun); if (qla4xxx_wait_for_hba_online(ha) != QLA_SUCCESS) { diff --git a/drivers/scsi/qla4xxx/ql4_version.h b/drivers/scsi/qla4xxx/ql4_version.h index ab984cb..6980cb2 100644 --- a/drivers/scsi/qla4xxx/ql4_version.h +++ b/drivers/scsi/qla4xxx/ql4_version.h @@ -5,5 +5,5 @@ * See LICENSE.qla4xxx for copyright and licensing details. */ -#define QLA4XXX_DRIVER_VERSION "5.01.00-k8" +#define QLA4XXX_DRIVER_VERSION "5.01.00-k9" diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 783e33c..b47240c 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -990,7 +990,7 @@ int iscsi_offload_mesg(struct Scsi_Host *shost, struct iscsi_uevent *ev; int len = NLMSG_SPACE(sizeof(*ev) + data_size); - skb = alloc_skb(len, GFP_NOIO); + skb = alloc_skb(len, GFP_ATOMIC); if (!skb) { printk(KERN_ERR "can not deliver iscsi offload message:OOM\n"); return -ENOMEM; @@ -1012,7 +1012,7 @@ int iscsi_offload_mesg(struct Scsi_Host *shost, memcpy((char *)ev + sizeof(*ev), data, data_size); - return iscsi_multicast_skb(skb, ISCSI_NL_GRP_UIP, GFP_NOIO); + return iscsi_multicast_skb(skb, ISCSI_NL_GRP_UIP, GFP_ATOMIC); } EXPORT_SYMBOL_GPL(iscsi_offload_mesg); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 5616cd7..b7b9fec 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1840,6 +1840,18 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) kfree(buffer); } +static int sd_try_extended_inquiry(struct scsi_device *sdp) +{ + /* + * Although VPD inquiries can go to SCSI-2 type devices, + * some USB ones crash on receiving them, and the pages + * we currently ask for are for SPC-3 and beyond + */ + if (sdp->scsi_level > SCSI_SPC_2) + return 1; + return 0; +} + /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. @@ -1877,8 +1889,12 @@ static int sd_revalidate_disk(struct gendisk *disk) */ if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); - sd_read_block_limits(sdkp); - sd_read_block_characteristics(sdkp); + + if (sd_try_extended_inquiry(sdp)) { + sd_read_block_limits(sdkp); + sd_read_block_characteristics(sdkp); + } + sd_read_write_protect_flag(sdkp, buffer); sd_read_cache_type(sdkp, buffer); sd_read_app_tag_own(sdkp, buffer); diff --git a/drivers/serial/s3c2400.c b/drivers/serial/s3c2400.c index fb00ed5..fed1a9a 100644 --- a/drivers/serial/s3c2400.c +++ b/drivers/serial/s3c2400.c @@ -76,7 +76,7 @@ static int s3c2400_serial_probe(struct platform_device *dev) return s3c24xx_serial_probe(dev, &s3c2400_uart_inf); } -static struct platform_driver s3c2400_serial_drv = { +static struct platform_driver s3c2400_serial_driver = { .probe = s3c2400_serial_probe, .remove = __devexit_p(s3c24xx_serial_remove), .driver = { @@ -85,16 +85,16 @@ static struct platform_driver s3c2400_serial_drv = { }, }; -s3c24xx_console_init(&s3c2400_serial_drv, &s3c2400_uart_inf); +s3c24xx_console_init(&s3c2400_serial_driver, &s3c2400_uart_inf); static inline int s3c2400_serial_init(void) { - return s3c24xx_serial_init(&s3c2400_serial_drv, &s3c2400_uart_inf); + return s3c24xx_serial_init(&s3c2400_serial_driver, &s3c2400_uart_inf); } static inline void s3c2400_serial_exit(void) { - platform_driver_unregister(&s3c2400_serial_drv); + platform_driver_unregister(&s3c2400_serial_driver); } module_init(s3c2400_serial_init); diff --git a/drivers/serial/s3c2410.c b/drivers/serial/s3c2410.c index b5d7cbc..c99f082 100644 --- a/drivers/serial/s3c2410.c +++ b/drivers/serial/s3c2410.c @@ -88,7 +88,7 @@ static int s3c2410_serial_probe(struct platform_device *dev) return s3c24xx_serial_probe(dev, &s3c2410_uart_inf); } -static struct platform_driver s3c2410_serial_drv = { +static struct platform_driver s3c2410_serial_driver = { .probe = s3c2410_serial_probe, .remove = __devexit_p(s3c24xx_serial_remove), .driver = { @@ -97,16 +97,16 @@ static struct platform_driver s3c2410_serial_drv = { }, }; -s3c24xx_console_init(&s3c2410_serial_drv, &s3c2410_uart_inf); +s3c24xx_console_init(&s3c2410_serial_driver, &s3c2410_uart_inf); static int __init s3c2410_serial_init(void) { - return s3c24xx_serial_init(&s3c2410_serial_drv, &s3c2410_uart_inf); + return s3c24xx_serial_init(&s3c2410_serial_driver, &s3c2410_uart_inf); } static void __exit s3c2410_serial_exit(void) { - platform_driver_unregister(&s3c2410_serial_drv); + platform_driver_unregister(&s3c2410_serial_driver); } module_init(s3c2410_serial_init); diff --git a/drivers/serial/s3c2412.c b/drivers/serial/s3c2412.c index 11dcb90..6e057d8 100644 --- a/drivers/serial/s3c2412.c +++ b/drivers/serial/s3c2412.c @@ -121,7 +121,7 @@ static int s3c2412_serial_probe(struct platform_device *dev) return s3c24xx_serial_probe(dev, &s3c2412_uart_inf); } -static struct platform_driver s3c2412_serial_drv = { +static struct platform_driver s3c2412_serial_driver = { .probe = s3c2412_serial_probe, .remove = __devexit_p(s3c24xx_serial_remove), .driver = { @@ -130,16 +130,16 @@ static struct platform_driver s3c2412_serial_drv = { }, }; -s3c24xx_console_init(&s3c2412_serial_drv, &s3c2412_uart_inf); +s3c24xx_console_init(&s3c2412_serial_driver, &s3c2412_uart_inf); static inline int s3c2412_serial_init(void) { - return s3c24xx_serial_init(&s3c2412_serial_drv, &s3c2412_uart_inf); + return s3c24xx_serial_init(&s3c2412_serial_driver, &s3c2412_uart_inf); } static inline void s3c2412_serial_exit(void) { - platform_driver_unregister(&s3c2412_serial_drv); + platform_driver_unregister(&s3c2412_serial_driver); } module_init(s3c2412_serial_init); diff --git a/drivers/serial/s3c2440.c b/drivers/serial/s3c2440.c index 06c5b0c..69ff5d3 100644 --- a/drivers/serial/s3c2440.c +++ b/drivers/serial/s3c2440.c @@ -151,7 +151,7 @@ static int s3c2440_serial_probe(struct platform_device *dev) return s3c24xx_serial_probe(dev, &s3c2440_uart_inf); } -static struct platform_driver s3c2440_serial_drv = { +static struct platform_driver s3c2440_serial_driver = { .probe = s3c2440_serial_probe, .remove = __devexit_p(s3c24xx_serial_remove), .driver = { @@ -160,16 +160,16 @@ static struct platform_driver s3c2440_serial_drv = { }, }; -s3c24xx_console_init(&s3c2440_serial_drv, &s3c2440_uart_inf); +s3c24xx_console_init(&s3c2440_serial_driver, &s3c2440_uart_inf); static int __init s3c2440_serial_init(void) { - return s3c24xx_serial_init(&s3c2440_serial_drv, &s3c2440_uart_inf); + return s3c24xx_serial_init(&s3c2440_serial_driver, &s3c2440_uart_inf); } static void __exit s3c2440_serial_exit(void) { - platform_driver_unregister(&s3c2440_serial_drv); + platform_driver_unregister(&s3c2440_serial_driver); } module_init(s3c2440_serial_init); diff --git a/drivers/serial/s3c24a0.c b/drivers/serial/s3c24a0.c index 786a067..26c49e1 100644 --- a/drivers/serial/s3c24a0.c +++ b/drivers/serial/s3c24a0.c @@ -92,7 +92,7 @@ static int s3c24a0_serial_probe(struct platform_device *dev) return s3c24xx_serial_probe(dev, &s3c24a0_uart_inf); } -static struct platform_driver s3c24a0_serial_drv = { +static struct platform_driver s3c24a0_serial_driver = { .probe = s3c24a0_serial_probe, .remove = __devexit_p(s3c24xx_serial_remove), .driver = { @@ -101,16 +101,16 @@ static struct platform_driver s3c24a0_serial_drv = { }, }; -s3c24xx_console_init(&s3c24a0_serial_drv, &s3c24a0_uart_inf); +s3c24xx_console_init(&s3c24a0_serial_driver, &s3c24a0_uart_inf); static int __init s3c24a0_serial_init(void) { - return s3c24xx_serial_init(&s3c24a0_serial_drv, &s3c24a0_uart_inf); + return s3c24xx_serial_init(&s3c24a0_serial_driver, &s3c24a0_uart_inf); } static void __exit s3c24a0_serial_exit(void) { - platform_driver_unregister(&s3c24a0_serial_drv); + platform_driver_unregister(&s3c24a0_serial_driver); } module_init(s3c24a0_serial_init); diff --git a/drivers/serial/s3c6400.c b/drivers/serial/s3c6400.c index 48f1a37..4be92ab 100644 --- a/drivers/serial/s3c6400.c +++ b/drivers/serial/s3c6400.c @@ -122,7 +122,7 @@ static int s3c6400_serial_probe(struct platform_device *dev) return s3c24xx_serial_probe(dev, &s3c6400_uart_inf); } -static struct platform_driver s3c6400_serial_drv = { +static struct platform_driver s3c6400_serial_driver = { .probe = s3c6400_serial_probe, .remove = __devexit_p(s3c24xx_serial_remove), .driver = { @@ -131,16 +131,16 @@ static struct platform_driver s3c6400_serial_drv = { }, }; -s3c24xx_console_init(&s3c6400_serial_drv, &s3c6400_uart_inf); +s3c24xx_console_init(&s3c6400_serial_driver, &s3c6400_uart_inf); static int __init s3c6400_serial_init(void) { - return s3c24xx_serial_init(&s3c6400_serial_drv, &s3c6400_uart_inf); + return s3c24xx_serial_init(&s3c6400_serial_driver, &s3c6400_uart_inf); } static void __exit s3c6400_serial_exit(void) { - platform_driver_unregister(&s3c6400_serial_drv); + platform_driver_unregister(&s3c6400_serial_driver); } module_init(s3c6400_serial_init); diff --git a/drivers/serial/serial_ks8695.c b/drivers/serial/serial_ks8695.c index 998e89d..e066563 100644 --- a/drivers/serial/serial_ks8695.c +++ b/drivers/serial/serial_ks8695.c @@ -549,7 +549,7 @@ static struct uart_port ks8695uart_ports[SERIAL_KS8695_NR] = { .mapbase = KS8695_UART_VA, .iotype = SERIAL_IO_MEM, .irq = KS8695_IRQ_UART_TX, - .uartclk = CLOCK_TICK_RATE * 16, + .uartclk = KS8695_CLOCK_RATE * 16, .fifosize = 16, .ops = &ks8695uart_pops, .flags = ASYNC_BOOT_AUTOCONF, diff --git a/drivers/staging/b3dfg/Kconfig b/drivers/staging/b3dfg/Kconfig index 5242310..9e6573c 100644 --- a/drivers/staging/b3dfg/Kconfig +++ b/drivers/staging/b3dfg/Kconfig @@ -1,5 +1,6 @@ config B3DFG tristate "Brontes 3d Frame Framegrabber" + depends on PCI default n ---help--- This driver provides support for the Brontes 3d Framegrabber diff --git a/drivers/staging/heci/Kconfig b/drivers/staging/heci/Kconfig index ae8d588..c7206f8 100644 --- a/drivers/staging/heci/Kconfig +++ b/drivers/staging/heci/Kconfig @@ -1,5 +1,6 @@ config HECI tristate "Intel Management Engine Interface (MEI) Support" + depends on PCI ---help--- The Intel Management Engine Interface (Intel MEI) driver allows applications to access the Active Management Technology diff --git a/drivers/staging/rspiusb/rspiusb.c b/drivers/staging/rspiusb/rspiusb.c index 2f8155c..04e2f92 100644 --- a/drivers/staging/rspiusb/rspiusb.c +++ b/drivers/staging/rspiusb/rspiusb.c @@ -716,6 +716,8 @@ static int MapUserBuffer(struct ioctl_struct *io, struct device_extension *pdx) pdx->PixelUrb[frameInfo][i]->transfer_flags = URB_NO_TRANSFER_DMA_MAP | URB_NO_INTERRUPT; } + if (i == 0) + return -EINVAL; /* only interrupt when last URB completes */ pdx->PixelUrb[frameInfo][--i]->transfer_flags &= ~URB_NO_INTERRUPT; pdx->pendedPixelUrbs[frameInfo] = diff --git a/drivers/staging/rt2860/rt_linux.h b/drivers/staging/rt2860/rt_linux.h index 85175c1..25b53ac 100644 --- a/drivers/staging/rt2860/rt_linux.h +++ b/drivers/staging/rt2860/rt_linux.h @@ -43,9 +43,6 @@ #include "rtmp_type.h" #include <linux/module.h> #include <linux/kernel.h> -#if !defined(RT2860) && !defined(RT30xx) -#include <linux/kthread.h> -#endif #include <linux/spinlock.h> #include <linux/init.h> @@ -166,9 +163,7 @@ typedef int (*HARD_START_XMIT_FUNC)(struct sk_buff *skb, struct net_device *net_ #ifndef RT30xx typedef struct pid * THREAD_PID; -#ifdef RT2860 #define THREAD_PID_INIT_VALUE NULL -#endif #define GET_PID(_v) find_get_pid(_v) #define GET_PID_NUMBER(_v) pid_nr(_v) #define CHECK_PID_LEGALITY(_pid) if (pid_nr(_pid) >= 0) @@ -188,12 +183,12 @@ struct os_cookie { dma_addr_t pAd_pa; #endif #ifdef RT2870 - struct usb_device *pUsb_Dev; + struct usb_device *pUsb_Dev; #ifndef RT30xx - struct task_struct *MLMEThr_task; - struct task_struct *RTUSBCmdThr_task; - struct task_struct *TimerQThr_task; + THREAD_PID MLMEThr_pid; + THREAD_PID RTUSBCmdThr_pid; + THREAD_PID TimerQThr_pid; #endif #ifdef RT30xx struct pid *MLMEThr_pid; diff --git a/drivers/staging/rt2870/2870_main_dev.c b/drivers/staging/rt2870/2870_main_dev.c index dd01c64..a4e8696 100644 --- a/drivers/staging/rt2870/2870_main_dev.c +++ b/drivers/staging/rt2870/2870_main_dev.c @@ -235,7 +235,7 @@ INT MlmeThread( DBGPRINT(RT_DEBUG_TRACE,( "<---%s\n",__func__)); #ifndef RT30xx - pObj->MLMEThr_task = NULL; + pObj->MLMEThr_pid = THREAD_PID_INIT_VALUE; #endif #ifdef RT30xx pObj->MLMEThr_pid = NULL; @@ -348,7 +348,7 @@ INT RTUSBCmdThread( DBGPRINT(RT_DEBUG_TRACE,( "<---RTUSBCmdThread\n")); #ifndef RT30xx - pObj->RTUSBCmdThr_task = NULL; + pObj->RTUSBCmdThr_pid = THREAD_PID_INIT_VALUE; #endif #ifdef RT30xx pObj->RTUSBCmdThr_pid = NULL; @@ -447,7 +447,7 @@ INT TimerQThread( DBGPRINT(RT_DEBUG_TRACE,( "<---%s\n",__func__)); #ifndef RT30xx - pObj->TimerQThr_task = NULL; + pObj->TimerQThr_pid = THREAD_PID_INIT_VALUE; #endif #ifdef RT30xx pObj->TimerQThr_pid = NULL; @@ -883,46 +883,69 @@ VOID RT28xxThreadTerminate( // Terminate Threads #ifndef RT30xx - BUG_ON(pObj->TimerQThr_task == NULL); - CHECK_PID_LEGALITY(task_pid(pObj->TimerQThr_task)) + CHECK_PID_LEGALITY(pObj->TimerQThr_pid) { POS_COOKIE pObj = (POS_COOKIE)pAd->OS_Cookie; - printk(KERN_DEBUG "Terminate the TimerQThr pid=%d!\n", - pid_nr(task_pid(pObj->TimerQThr_task))); + printk("Terminate the TimerQThr_pid=%d!\n", GET_PID_NUMBER(pObj->TimerQThr_pid)); mb(); pAd->TimerFunc_kill = 1; mb(); - kthread_stop(pObj->TimerQThr_task); - pObj->TimerQThr_task = NULL; + ret = KILL_THREAD_PID(pObj->TimerQThr_pid, SIGTERM, 1); + if (ret) + { + printk(KERN_WARNING "%s: unable to stop TimerQThread, pid=%d, ret=%d!\n", + pAd->net_dev->name, GET_PID_NUMBER(pObj->TimerQThr_pid), ret); + } + else + { + wait_for_completion(&pAd->TimerQComplete); + pObj->TimerQThr_pid = THREAD_PID_INIT_VALUE; + } } - BUG_ON(pObj->MLMEThr_task == NULL); - CHECK_PID_LEGALITY(task_pid(pObj->MLMEThr_task)) + CHECK_PID_LEGALITY(pObj->MLMEThr_pid) { - printk(KERN_DEBUG "Terminate the MLMEThr pid=%d!\n", - pid_nr(task_pid(pObj->MLMEThr_task))); + printk("Terminate the MLMEThr_pid=%d!\n", GET_PID_NUMBER(pObj->MLMEThr_pid)); mb(); pAd->mlme_kill = 1; //RT28XX_MLME_HANDLER(pAd); mb(); - kthread_stop(pObj->MLMEThr_task); - pObj->MLMEThr_task = NULL; + ret = KILL_THREAD_PID(pObj->MLMEThr_pid, SIGTERM, 1); + if (ret) + { + printk (KERN_WARNING "%s: unable to Mlme thread, pid=%d, ret=%d!\n", + pAd->net_dev->name, GET_PID_NUMBER(pObj->MLMEThr_pid), ret); + } + else + { + //wait_for_completion (&pAd->notify); + wait_for_completion (&pAd->mlmeComplete); + pObj->MLMEThr_pid = THREAD_PID_INIT_VALUE; + } } - BUG_ON(pObj->RTUSBCmdThr_task == NULL); - CHECK_PID_LEGALITY(task_pid(pObj->RTUSBCmdThr_task)) + CHECK_PID_LEGALITY(pObj->RTUSBCmdThr_pid) { - printk(KERN_DEBUG "Terminate the RTUSBCmdThr pid=%d!\n", - pid_nr(task_pid(pObj->RTUSBCmdThr_task))); + printk("Terminate the RTUSBCmdThr_pid=%d!\n", GET_PID_NUMBER(pObj->RTUSBCmdThr_pid)); mb(); NdisAcquireSpinLock(&pAd->CmdQLock); pAd->CmdQ.CmdQState = RT2870_THREAD_STOPED; NdisReleaseSpinLock(&pAd->CmdQLock); mb(); //RTUSBCMDUp(pAd); - kthread_stop(pObj->RTUSBCmdThr_task); - pObj->RTUSBCmdThr_task = NULL; + ret = KILL_THREAD_PID(pObj->RTUSBCmdThr_pid, SIGTERM, 1); + if (ret) + { + printk(KERN_WARNING "%s: unable to RTUSBCmd thread, pid=%d, ret=%d!\n", + pAd->net_dev->name, GET_PID_NUMBER(pObj->RTUSBCmdThr_pid), ret); + } + else + { + //wait_for_completion (&pAd->notify); + wait_for_completion (&pAd->CmdQComplete); + pObj->RTUSBCmdThr_pid = THREAD_PID_INIT_VALUE; + } } #endif #ifdef RT30xx @@ -1045,7 +1068,7 @@ BOOLEAN RT28XXChipsetCheck( dev_p->descriptor.idProduct == rtusb_usb_id[i].idProduct) { #ifndef RT30xx - printk(KERN_DEBUG "rt2870: idVendor = 0x%x, idProduct = 0x%x\n", + printk("rt2870: idVendor = 0x%x, idProduct = 0x%x\n", #endif #ifdef RT30xx printk("rt2870: idVendor = 0x%x, idProduct = 0x%x\n", diff --git a/drivers/staging/rt2870/common/2870_rtmp_init.c b/drivers/staging/rt2870/common/2870_rtmp_init.c index 0f4c8af..80909e9 100644 --- a/drivers/staging/rt2870/common/2870_rtmp_init.c +++ b/drivers/staging/rt2870/common/2870_rtmp_init.c @@ -700,8 +700,8 @@ NDIS_STATUS AdapterBlockAllocateMemory( usb_dev = pObj->pUsb_Dev; #ifndef RT30xx - pObj->MLMEThr_task = NULL; - pObj->RTUSBCmdThr_task = NULL; + pObj->MLMEThr_pid = THREAD_PID_INIT_VALUE; + pObj->RTUSBCmdThr_pid = THREAD_PID_INIT_VALUE; #endif #ifdef RT30xx pObj->MLMEThr_pid = NULL; @@ -743,7 +743,7 @@ NDIS_STATUS CreateThreads( PRTMP_ADAPTER pAd = net_dev->ml_priv; POS_COOKIE pObj = (POS_COOKIE) pAd->OS_Cookie; #ifndef RT30xx - struct task_struct *tsk; + pid_t pid_number = -1; #endif #ifdef RT30xx pid_t pid_number; @@ -762,10 +762,10 @@ NDIS_STATUS CreateThreads( // Creat MLME Thread #ifndef RT30xx - pObj->MLMEThr_task = NULL; - tsk = kthread_run(MlmeThread, pAd, "%s", pAd->net_dev->name); - - if (IS_ERR(tsk)) { + pObj->MLMEThr_pid= THREAD_PID_INIT_VALUE; + pid_number = kernel_thread(MlmeThread, pAd, CLONE_VM); + if (pid_number < 0) + { #endif #ifdef RT30xx pObj->MLMEThr_pid = NULL; @@ -778,7 +778,7 @@ NDIS_STATUS CreateThreads( } #ifndef RT30xx - pObj->MLMEThr_task = tsk; + pObj->MLMEThr_pid = GET_PID(pid_number); #endif #ifdef RT30xx pObj->MLMEThr_pid = find_get_pid(pid_number); @@ -788,10 +788,9 @@ NDIS_STATUS CreateThreads( // Creat Command Thread #ifndef RT30xx - pObj->RTUSBCmdThr_task = NULL; - tsk = kthread_run(RTUSBCmdThread, pAd, "%s", pAd->net_dev->name); - - if (IS_ERR(tsk) < 0) + pObj->RTUSBCmdThr_pid= THREAD_PID_INIT_VALUE; + pid_number = kernel_thread(RTUSBCmdThread, pAd, CLONE_VM); + if (pid_number < 0) #endif #ifdef RT30xx pObj->RTUSBCmdThr_pid = NULL; @@ -804,7 +803,7 @@ NDIS_STATUS CreateThreads( } #ifndef RT30xx - pObj->RTUSBCmdThr_task = tsk; + pObj->RTUSBCmdThr_pid = GET_PID(pid_number); #endif #ifdef RT30xx pObj->RTUSBCmdThr_pid = find_get_pid(pid_number); @@ -812,9 +811,9 @@ NDIS_STATUS CreateThreads( wait_for_completion(&(pAd->CmdQComplete)); #ifndef RT30xx - pObj->TimerQThr_task = NULL; - tsk = kthread_run(TimerQThread, pAd, "%s", pAd->net_dev->name); - if (IS_ERR(tsk) < 0) + pObj->TimerQThr_pid= THREAD_PID_INIT_VALUE; + pid_number = kernel_thread(TimerQThread, pAd, CLONE_VM); + if (pid_number < 0) #endif #ifdef RT30xx pObj->TimerQThr_pid = NULL; @@ -826,7 +825,7 @@ NDIS_STATUS CreateThreads( return NDIS_STATUS_FAILURE; } #ifndef RT30xx - pObj->TimerQThr_task = tsk; + pObj->TimerQThr_pid = GET_PID(pid_number); #endif #ifdef RT30xx pObj->TimerQThr_pid = find_get_pid(pid_number); diff --git a/drivers/staging/rt2870/common/rtusb_io.c b/drivers/staging/rt2870/common/rtusb_io.c index fd1b0c1..704b5c2 100644 --- a/drivers/staging/rt2870/common/rtusb_io.c +++ b/drivers/staging/rt2870/common/rtusb_io.c @@ -984,8 +984,7 @@ NDIS_STATUS RTUSBEnqueueCmdFromNdis( POS_COOKIE pObj = (POS_COOKIE) pAd->OS_Cookie; #ifndef RT30xx - BUG_ON(pObj->RTUSBCmdThr_task == NULL); - CHECK_PID_LEGALITY(task_pid(pObj->RTUSBCmdThr_task)) + CHECK_PID_LEGALITY(pObj->RTUSBCmdThr_pid) #endif #ifdef RT30xx if (pObj->RTUSBCmdThr_pid < 0) diff --git a/drivers/staging/rt2870/rt2870.h b/drivers/staging/rt2870/rt2870.h index 29e3b53..2b8872b 100644 --- a/drivers/staging/rt2870/rt2870.h +++ b/drivers/staging/rt2870/rt2870.h @@ -79,6 +79,7 @@ { \ {USB_DEVICE(0x148F,0x2770)}, /* Ralink */ \ {USB_DEVICE(0x1737,0x0071)}, /* Linksys WUSB600N */ \ + {USB_DEVICE(0x1737,0x0070)}, /* Linksys */ \ {USB_DEVICE(0x148F,0x2870)}, /* Ralink */ \ {USB_DEVICE(0x148F,0x3070)}, /* Ralink */ \ {USB_DEVICE(0x0B05,0x1731)}, /* Asus */ \ @@ -93,12 +94,14 @@ {USB_DEVICE(0x14B2,0x3C06)}, /* Conceptronic */ \ {USB_DEVICE(0x14B2,0x3C28)}, /* Conceptronic */ \ {USB_DEVICE(0x2019,0xED06)}, /* Planex Communications, Inc. */ \ + {USB_DEVICE(0x2019,0xED14)}, /* Planex Communications, Inc. */ \ {USB_DEVICE(0x2019,0xAB25)}, /* Planex Communications, Inc. RT3070 */ \ {USB_DEVICE(0x07D1,0x3C09)}, /* D-Link */ \ {USB_DEVICE(0x07D1,0x3C11)}, /* D-Link */ \ {USB_DEVICE(0x14B2,0x3C07)}, /* AL */ \ {USB_DEVICE(0x14B2,0x3C12)}, /* AL */ \ {USB_DEVICE(0x050D,0x8053)}, /* Belkin */ \ + {USB_DEVICE(0x050D,0x815C)}, /* Belkin */ \ {USB_DEVICE(0x14B2,0x3C23)}, /* Airlink */ \ {USB_DEVICE(0x14B2,0x3C27)}, /* Airlink */ \ {USB_DEVICE(0x07AA,0x002F)}, /* Corega */ \ @@ -587,16 +590,14 @@ VOID RTUSBBulkRxComplete(purbb_t pUrb, struct pt_regs *pt_regs); #define RTUSBMlmeUp(pAd) \ { \ POS_COOKIE pObj = (POS_COOKIE) pAd->OS_Cookie; \ - BUG_ON(pObj->MLMEThr_task == NULL); \ - CHECK_PID_LEGALITY(task_pid(pObj->MLMEThr_task)) \ + CHECK_PID_LEGALITY(pObj->MLMEThr_pid) \ up(&(pAd->mlme_semaphore)); \ } #define RTUSBCMDUp(pAd) \ { \ POS_COOKIE pObj = (POS_COOKIE) pAd->OS_Cookie; \ - BUG_ON(pObj->RTUSBCmdThr_task == NULL); \ - CHECK_PID_LEGALITY(task_pid(pObj->RTUSBCmdThr_task)) \ + CHECK_PID_LEGALITY(pObj->RTUSBCmdThr_pid) \ up(&(pAd->RTUSBCmd_semaphore)); \ } #endif diff --git a/drivers/staging/rtl8192su/ieee80211.h b/drivers/staging/rtl8192su/ieee80211.h index 0edb09a..ea97393 100644 --- a/drivers/staging/rtl8192su/ieee80211.h +++ b/drivers/staging/rtl8192su/ieee80211.h @@ -2645,7 +2645,7 @@ extern int ieee80211_encrypt_fragment( struct sk_buff *frag, int hdr_len); -extern int ieee80211_xmit(struct sk_buff *skb, +extern int rtl8192_ieee80211_xmit(struct sk_buff *skb, struct net_device *dev); extern void ieee80211_txb_free(struct ieee80211_txb *); diff --git a/drivers/staging/rtl8192su/ieee80211/ieee80211.h b/drivers/staging/rtl8192su/ieee80211/ieee80211.h index 720bfcb..5e3a2cb 100644 --- a/drivers/staging/rtl8192su/ieee80211/ieee80211.h +++ b/drivers/staging/rtl8192su/ieee80211/ieee80211.h @@ -2645,7 +2645,7 @@ extern int ieee80211_encrypt_fragment( struct sk_buff *frag, int hdr_len); -extern int ieee80211_xmit(struct sk_buff *skb, +extern int rtl8192_ieee80211_xmit(struct sk_buff *skb, struct net_device *dev); extern void ieee80211_txb_free(struct ieee80211_txb *); diff --git a/drivers/staging/rtl8192su/ieee80211/ieee80211_tx.c b/drivers/staging/rtl8192su/ieee80211/ieee80211_tx.c index 7294572..cba12b8 100644 --- a/drivers/staging/rtl8192su/ieee80211/ieee80211_tx.c +++ b/drivers/staging/rtl8192su/ieee80211/ieee80211_tx.c @@ -618,7 +618,7 @@ void ieee80211_query_seqnum(struct ieee80211_device*ieee, struct sk_buff* skb, u } } -int ieee80211_xmit(struct sk_buff *skb, struct net_device *dev) +int rtl8192_ieee80211_xmit(struct sk_buff *skb, struct net_device *dev) { #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,5,0)) struct ieee80211_device *ieee = netdev_priv(dev); @@ -943,5 +943,6 @@ int ieee80211_xmit(struct sk_buff *skb, struct net_device *dev) return 1; } +EXPORT_SYMBOL(rtl8192_ieee80211_xmit); EXPORT_SYMBOL(ieee80211_txb_free); diff --git a/drivers/staging/rtl8192su/r8192U_core.c b/drivers/staging/rtl8192su/r8192U_core.c index 4ab2507..70f81a8 100644 --- a/drivers/staging/rtl8192su/r8192U_core.c +++ b/drivers/staging/rtl8192su/r8192U_core.c @@ -12142,7 +12142,7 @@ static const struct net_device_ops rtl8192_netdev_ops = { .ndo_set_mac_address = r8192_set_mac_adr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = eth_change_mtu, - .ndo_start_xmit = ieee80211_xmit, + .ndo_start_xmit = rtl8192_ieee80211_xmit, }; #if LINUX_VERSION_CODE > KERNEL_VERSION(2,5,0) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index e1f8941..2bfc41e 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -387,7 +387,6 @@ static void acm_rx_tasklet(unsigned long _acm) struct acm_ru *rcv; unsigned long flags; unsigned char throttled; - struct usb_host_endpoint *ep; dbg("Entering acm_rx_tasklet"); @@ -463,14 +462,12 @@ urbs: rcv->buffer = buf; - ep = (usb_pipein(acm->rx_endpoint) ? acm->dev->ep_in : acm->dev->ep_out) - [usb_pipeendpoint(acm->rx_endpoint)]; - if (usb_endpoint_xfer_int(&ep->desc)) + if (acm->is_int_ep) usb_fill_int_urb(rcv->urb, acm->dev, acm->rx_endpoint, buf->base, acm->readsize, - acm_read_bulk, rcv, ep->desc.bInterval); + acm_read_bulk, rcv, acm->bInterval); else usb_fill_bulk_urb(rcv->urb, acm->dev, acm->rx_endpoint, @@ -1183,6 +1180,9 @@ made_compressed_probe: spin_lock_init(&acm->read_lock); mutex_init(&acm->mutex); acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress); + acm->is_int_ep = usb_endpoint_xfer_int(epread); + if (acm->is_int_ep) + acm->bInterval = epread->bInterval; tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 1602324..c4a0ee8 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -126,6 +126,8 @@ struct acm { unsigned int ctrl_caps; /* control capabilities from the class specific header */ unsigned int susp_count; /* number of suspended interfaces */ int combined_interfaces:1; /* control and data collapsed */ + int is_int_ep:1; /* interrupt endpoints contrary to spec used */ + u8 bInterval; struct acm_wb *delayed_wb; /* write queued for a device about to be woken */ }; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 38b8bce..4247ecc 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -595,7 +595,7 @@ static int usbdev_open(struct inode *inode, struct file *file) if (!ps) goto out; - ret = -ENOENT; + ret = -ENODEV; /* usbdev device-node */ if (imajor(inode) == USB_DEVICE_MAJOR) @@ -1321,7 +1321,8 @@ static int get_urb32(struct usbdevfs_urb *kurb, struct usbdevfs_urb32 __user *uurb) { __u32 uptr; - if (get_user(kurb->type, &uurb->type) || + if (!access_ok(VERIFY_READ, uurb, sizeof(*uurb)) || + __get_user(kurb->type, &uurb->type) || __get_user(kurb->endpoint, &uurb->endpoint) || __get_user(kurb->status, &uurb->status) || __get_user(kurb->flags, &uurb->flags) || @@ -1536,8 +1537,9 @@ static int proc_ioctl_compat(struct dev_state *ps, compat_uptr_t arg) u32 udata; uioc = compat_ptr((long)arg); - if (get_user(ctrl.ifno, &uioc->ifno) || - get_user(ctrl.ioctl_code, &uioc->ioctl_code) || + if (!access_ok(VERIFY_READ, uioc, sizeof(*uioc)) || + __get_user(ctrl.ifno, &uioc->ifno) || + __get_user(ctrl.ioctl_code, &uioc->ioctl_code) || __get_user(udata, &uioc->data)) return -EFAULT; ctrl.data = compat_ptr(udata); diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 7d03549..11c627c 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -903,7 +903,8 @@ static int ehci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) /* already started */ break; case QH_STATE_IDLE: - WARN_ON(1); + /* QH might be waiting for a Clear-TT-Buffer */ + qh_completions(ehci, qh); break; } break; diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 9a13847..7673554 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -375,12 +375,11 @@ qh_completions (struct ehci_hcd *ehci, struct ehci_qh *qh) */ if ((token & QTD_STS_XACT) && QTD_CERR(token) == 0 && - --qh->xacterrs > 0 && + ++qh->xacterrs < QH_XACTERR_MAX && !urb->unlinked) { ehci_dbg(ehci, "detected XactErr len %zu/%zu retry %d\n", - qtd->length - QTD_LENGTH(token), qtd->length, - QH_XACTERR_MAX - qh->xacterrs); + qtd->length - QTD_LENGTH(token), qtd->length, qh->xacterrs); /* reset the token in the qtd and the * qh overlay (which still contains @@ -494,7 +493,7 @@ halt: last = qtd; /* reinit the xacterr counter for the next qtd */ - qh->xacterrs = QH_XACTERR_MAX; + qh->xacterrs = 0; } /* last urb's completion might still need calling */ @@ -940,7 +939,8 @@ static void qh_link_async (struct ehci_hcd *ehci, struct ehci_qh *qh) head->qh_next.qh = qh; head->hw_next = dma; - qh->xacterrs = QH_XACTERR_MAX; + qh_get(qh); + qh->xacterrs = 0; qh->qh_state = QH_STATE_LINKED; /* qtd completions reported later by interrupt */ } @@ -1080,7 +1080,7 @@ submit_async ( * the HC and TT handle it when the TT has a buffer ready. */ if (likely (qh->qh_state == QH_STATE_IDLE)) - qh_link_async (ehci, qh_get (qh)); + qh_link_async(ehci, qh); done: spin_unlock_irqrestore (&ehci->lock, flags); if (unlikely (qh == NULL)) @@ -1115,8 +1115,6 @@ static void end_unlink_async (struct ehci_hcd *ehci) && HC_IS_RUNNING (ehci_to_hcd(ehci)->state)) qh_link_async (ehci, qh); else { - qh_put (qh); // refcount from async list - /* it's not free to turn the async schedule on/off; leave it * active but idle for a while once it empties. */ @@ -1124,6 +1122,7 @@ static void end_unlink_async (struct ehci_hcd *ehci) && ehci->async->qh_next.qh == NULL) timer_action (ehci, TIMER_ASYNC_OFF); } + qh_put(qh); /* refcount from async list */ if (next) { ehci->reclaim = NULL; diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c index 74f7f83..edd61ee 100644 --- a/drivers/usb/host/ehci-sched.c +++ b/drivers/usb/host/ehci-sched.c @@ -542,6 +542,7 @@ static int qh_link_periodic (struct ehci_hcd *ehci, struct ehci_qh *qh) } } qh->qh_state = QH_STATE_LINKED; + qh->xacterrs = 0; qh_get (qh); /* update per-qh bandwidth for usbfs */ diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig index 70073b1..803adcb 100644 --- a/drivers/usb/musb/Kconfig +++ b/drivers/usb/musb/Kconfig @@ -12,6 +12,7 @@ config USB_MUSB_HDRC depends on !SUPERH select NOP_USB_XCEIV if ARCH_DAVINCI select TWL4030_USB if MACH_OMAP_3430SDP + select NOP_USB_XCEIV if MACH_OMAP3EVM select USB_OTG_UTILS tristate 'Inventra Highspeed Dual Role Controller (TI, ADI, ...)' help diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index b574878..8fec5d4 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -699,6 +699,9 @@ static struct usb_device_id id_table_combined [] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(LARSENBRUSGAARD_VID, LB_ALTITRACK_PID) }, { USB_DEVICE(GN_OTOMETRICS_VID, AURICAL_USB_PID) }, + { USB_DEVICE(BAYER_VID, BAYER_CONTOUR_CABLE_PID) }, + { USB_DEVICE(FTDI_VID, MARVELL_OPENRD_PID), + .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { }, /* Optional parameter entry */ { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio.h b/drivers/usb/serial/ftdi_sio.h index 24dbd99..8c92b88 100644 --- a/drivers/usb/serial/ftdi_sio.h +++ b/drivers/usb/serial/ftdi_sio.h @@ -954,6 +954,20 @@ #define AURICAL_USB_PID 0x0010 /* Aurical USB Audiometer */ /* + * Bayer Ascensia Contour blood glucose meter USB-converter cable. + * http://winglucofacts.com/cables/ + */ +#define BAYER_VID 0x1A79 +#define BAYER_CONTOUR_CABLE_PID 0x6001 + +/* + * Marvell OpenRD Base, Client + * http://www.open-rd.org + * OpenRD Base, Client use VID 0x0403 + */ +#define MARVELL_OPENRD_PID 0x9e90 + +/* * BmRequestType: 1100 0000b * bRequest: FTDI_E2_READ * wValue: 0 diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 7d15bfa..3e86815 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -95,6 +95,7 @@ static struct usb_device_id id_table [] = { { USB_DEVICE(SUPERIAL_VENDOR_ID, SUPERIAL_PRODUCT_ID) }, { USB_DEVICE(HP_VENDOR_ID, HP_LD220_PRODUCT_ID) }, { USB_DEVICE(CRESSI_VENDOR_ID, CRESSI_EDY_PRODUCT_ID) }, + { USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h index 12aac7d..ee9505e 100644 --- a/drivers/usb/serial/pl2303.h +++ b/drivers/usb/serial/pl2303.h @@ -126,3 +126,7 @@ /* Cressi Edy (diving computer) PC interface */ #define CRESSI_VENDOR_ID 0x04b8 #define CRESSI_EDY_PRODUCT_ID 0x0521 + +/* Sony, USB data cable for CMD-Jxx mobile phones */ +#define SONY_VENDOR_ID 0x054c +#define SONY_QN3USB_PRODUCT_ID 0x0437 diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 1b9c5dd..7477d41 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -838,6 +838,13 @@ UNUSUAL_DEV( 0x066f, 0x8000, 0x0001, 0x0001, US_SC_DEVICE, US_PR_DEVICE, NULL, US_FL_FIX_CAPACITY ), +/* Reported by Rogerio Brito <rbrito@ime.usp.br> */ +UNUSUAL_DEV( 0x067b, 0x2317, 0x0001, 0x001, + "Prolific Technology, Inc.", + "Mass Storage Device", + US_SC_DEVICE, US_PR_DEVICE, NULL, + US_FL_NOT_LOCKABLE ), + /* Reported by Richard -=[]=- <micro_flyer@hotmail.com> */ /* Change to bcdDeviceMin (0x0100 to 0x0001) reported by * Thomas Bartosik <tbartdev@gmx-topmail.de> */ diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c index 471a9a6..3a44695 100644 --- a/drivers/video/console/fbcon.c +++ b/drivers/video/console/fbcon.c @@ -1082,7 +1082,6 @@ static void fbcon_init(struct vc_data *vc, int init) new_rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); new_cols /= vc->vc_font.width; new_rows /= vc->vc_font.height; - vc_resize(vc, new_cols, new_rows); /* * We must always set the mode. The mode of the previous console @@ -1111,10 +1110,11 @@ static void fbcon_init(struct vc_data *vc, int init) * vc_{cols,rows}, but we must not set those if we are only * resizing the console. */ - if (!init) { + if (init) { vc->vc_cols = new_cols; vc->vc_rows = new_rows; - } + } else + vc_resize(vc, new_cols, new_rows); if (logo) fbcon_prepare_logo(vc, info, cols, rows, new_cols, new_rows); diff --git a/drivers/video/console/fbcon_rotate.h b/drivers/video/console/fbcon_rotate.h index 75be5ce..e233444 100644 --- a/drivers/video/console/fbcon_rotate.h +++ b/drivers/video/console/fbcon_rotate.h @@ -45,7 +45,7 @@ static inline void rotate_ud(const char *in, char *out, u32 width, u32 height) width = (width + 7) & ~7; for (i = 0; i < height; i++) { - for (j = 0; j < width; j++) { + for (j = 0; j < width - shift; j++) { if (pattern_test_bit(j, i, width, in)) pattern_set_bit(width - (1 + j + shift), height - (1 + i), diff --git a/drivers/video/console/sticore.c b/drivers/video/console/sticore.c index ef7870f..857b366 100644 --- a/drivers/video/console/sticore.c +++ b/drivers/video/console/sticore.c @@ -957,9 +957,14 @@ static int __devinit sticore_pci_init(struct pci_dev *pd, #ifdef CONFIG_PCI unsigned long fb_base, rom_base; unsigned int fb_len, rom_len; + int err; struct sti_struct *sti; - pci_enable_device(pd); + err = pci_enable_device(pd); + if (err < 0) { + dev_err(&pd->dev, "Cannot enable PCI device\n"); + return err; + } fb_base = pci_resource_start(pd, 0); fb_len = pci_resource_len(pd, 0); @@ -1048,7 +1053,7 @@ static void __devinit sti_init_roms(void) /* Register drivers for native & PCI cards */ register_parisc_driver(&pa_sti_driver); - pci_register_driver(&pci_sti_driver); + WARN_ON(pci_register_driver(&pci_sti_driver)); /* if we didn't find the given default sti, take the first one */ if (!default_sti) diff --git a/drivers/video/mx3fb.c b/drivers/video/mx3fb.c index f8778cd..054ef29 100644 --- a/drivers/video/mx3fb.c +++ b/drivers/video/mx3fb.c @@ -669,7 +669,8 @@ static uint32_t bpp_to_pixfmt(int bpp) } static int mx3fb_blank(int blank, struct fb_info *fbi); -static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len); +static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len, + bool lock); static int mx3fb_unmap_video_memory(struct fb_info *fbi); /** @@ -711,12 +712,7 @@ static void mx3fb_dma_done(void *arg) complete(&mx3_fbi->flip_cmpl); } -/** - * mx3fb_set_par() - set framebuffer parameters and change the operating mode. - * @fbi: framebuffer information pointer. - * @return: 0 on success or negative error code on failure. - */ -static int mx3fb_set_par(struct fb_info *fbi) +static int __set_par(struct fb_info *fbi, bool lock) { u32 mem_len; struct ipu_di_signal_cfg sig_cfg; @@ -727,10 +723,6 @@ static int mx3fb_set_par(struct fb_info *fbi) struct idmac_video_param *video = &ichan->params.video; struct scatterlist *sg = mx3_fbi->sg; - dev_dbg(mx3fb->dev, "%s [%c]\n", __func__, list_empty(&ichan->queue) ? '-' : '+'); - - mutex_lock(&mx3_fbi->mutex); - /* Total cleanup */ if (mx3_fbi->txd) sdc_disable_channel(mx3_fbi); @@ -742,10 +734,8 @@ static int mx3fb_set_par(struct fb_info *fbi) if (fbi->fix.smem_start) mx3fb_unmap_video_memory(fbi); - if (mx3fb_map_video_memory(fbi, mem_len) < 0) { - mutex_unlock(&mx3_fbi->mutex); + if (mx3fb_map_video_memory(fbi, mem_len, lock) < 0) return -ENOMEM; - } } sg_init_table(&sg[0], 1); @@ -791,7 +781,6 @@ static int mx3fb_set_par(struct fb_info *fbi) fbi->var.vsync_len, fbi->var.lower_margin + fbi->var.vsync_len, sig_cfg) != 0) { - mutex_unlock(&mx3_fbi->mutex); dev_err(fbi->device, "mx3fb: Error initializing panel.\n"); return -EINVAL; @@ -810,9 +799,30 @@ static int mx3fb_set_par(struct fb_info *fbi) if (mx3_fbi->blank == FB_BLANK_UNBLANK) sdc_enable_channel(mx3_fbi); + return 0; +} + +/** + * mx3fb_set_par() - set framebuffer parameters and change the operating mode. + * @fbi: framebuffer information pointer. + * @return: 0 on success or negative error code on failure. + */ +static int mx3fb_set_par(struct fb_info *fbi) +{ + struct mx3fb_info *mx3_fbi = fbi->par; + struct mx3fb_data *mx3fb = mx3_fbi->mx3fb; + struct idmac_channel *ichan = mx3_fbi->idmac_channel; + int ret; + + dev_dbg(mx3fb->dev, "%s [%c]\n", __func__, list_empty(&ichan->queue) ? '-' : '+'); + + mutex_lock(&mx3_fbi->mutex); + + ret = __set_par(fbi, true); + mutex_unlock(&mx3_fbi->mutex); - return 0; + return ret; } /** @@ -966,21 +976,11 @@ static int mx3fb_setcolreg(unsigned int regno, unsigned int red, return ret; } -/** - * mx3fb_blank() - blank the display. - */ -static int mx3fb_blank(int blank, struct fb_info *fbi) +static void __blank(int blank, struct fb_info *fbi) { struct mx3fb_info *mx3_fbi = fbi->par; struct mx3fb_data *mx3fb = mx3_fbi->mx3fb; - dev_dbg(fbi->device, "%s, blank = %d, base %p, len %u\n", __func__, - blank, fbi->screen_base, fbi->fix.smem_len); - - if (mx3_fbi->blank == blank) - return 0; - - mutex_lock(&mx3_fbi->mutex); mx3_fbi->blank = blank; switch (blank) { @@ -999,6 +999,23 @@ static int mx3fb_blank(int blank, struct fb_info *fbi) sdc_set_brightness(mx3fb, mx3fb->backlight_level); break; } +} + +/** + * mx3fb_blank() - blank the display. + */ +static int mx3fb_blank(int blank, struct fb_info *fbi) +{ + struct mx3fb_info *mx3_fbi = fbi->par; + + dev_dbg(fbi->device, "%s, blank = %d, base %p, len %u\n", __func__, + blank, fbi->screen_base, fbi->fix.smem_len); + + if (mx3_fbi->blank == blank) + return 0; + + mutex_lock(&mx3_fbi->mutex); + __blank(blank, fbi); mutex_unlock(&mx3_fbi->mutex); return 0; @@ -1198,6 +1215,7 @@ static int mx3fb_resume(struct platform_device *pdev) * mx3fb_map_video_memory() - allocates the DRAM memory for the frame buffer. * @fbi: framebuffer information pointer * @mem_len: length of mapped memory + * @lock: do not lock during initialisation * @return: Error code indicating success or failure * * This buffer is remapped into a non-cached, non-buffered, memory region to @@ -1205,7 +1223,8 @@ static int mx3fb_resume(struct platform_device *pdev) * area is remapped, all virtual memory access to the video memory should occur * at the new region. */ -static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len) +static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len, + bool lock) { int retval = 0; dma_addr_t addr; @@ -1221,10 +1240,12 @@ static int mx3fb_map_video_memory(struct fb_info *fbi, unsigned int mem_len) goto err0; } - mutex_lock(&fbi->mm_lock); + if (lock) + mutex_lock(&fbi->mm_lock); fbi->fix.smem_start = addr; fbi->fix.smem_len = mem_len; - mutex_unlock(&fbi->mm_lock); + if (lock) + mutex_unlock(&fbi->mm_lock); dev_dbg(fbi->device, "allocated fb @ p=0x%08x, v=0x%p, size=%d.\n", (uint32_t) fbi->fix.smem_start, fbi->screen_base, fbi->fix.smem_len); @@ -1365,6 +1386,11 @@ static int init_fb_chan(struct mx3fb_data *mx3fb, struct idmac_channel *ichan) init_completion(&mx3fbi->flip_cmpl); disable_irq(ichan->eof_irq); dev_dbg(mx3fb->dev, "disabling irq %d\n", ichan->eof_irq); + ret = __set_par(fbi, false); + if (ret < 0) + goto esetpar; + + __blank(FB_BLANK_UNBLANK, fbi); dev_info(dev, "registered, using mode %s\n", fb_mode); diff --git a/drivers/video/via/hw.c b/drivers/video/via/hw.c index fcd53ce..c896000 100644 --- a/drivers/video/via/hw.c +++ b/drivers/video/via/hw.c @@ -2407,14 +2407,14 @@ int viafb_setmode(int vmode_index, int hor_res, int ver_res, int video_bpp, viafb_dvi_set_mode(viafb_get_mode_index (viaparinfo->tmds_setting_info->h_active, viaparinfo->tmds_setting_info-> - v_active, 1), + v_active), video_bpp1, viaparinfo-> tmds_setting_info->iga_path); } else { viafb_dvi_set_mode(viafb_get_mode_index (viaparinfo->tmds_setting_info->h_active, viaparinfo-> - tmds_setting_info->v_active, 0), + tmds_setting_info->v_active), video_bpp, viaparinfo-> tmds_setting_info->iga_path); } diff --git a/drivers/video/via/lcd.c b/drivers/video/via/lcd.c index 6c7290a..78c6b33 100644 --- a/drivers/video/via/lcd.c +++ b/drivers/video/via/lcd.c @@ -580,10 +580,7 @@ static void load_lcd_k400_patch_tbl(int set_hres, int set_vres, int reg_num = 0; struct io_reg *lcd_patch_reg = NULL; - if (viaparinfo->lvds_setting_info->iga_path == IGA2) - vmode_index = viafb_get_mode_index(set_hres, set_vres, 1); - else - vmode_index = viafb_get_mode_index(set_hres, set_vres, 0); + vmode_index = viafb_get_mode_index(set_hres, set_vres); switch (panel_id) { /* LCD 800x600 */ case LCD_PANEL_ID1_800X600: @@ -761,10 +758,7 @@ static void load_lcd_p880_patch_tbl(int set_hres, int set_vres, int reg_num = 0; struct io_reg *lcd_patch_reg = NULL; - if (viaparinfo->lvds_setting_info->iga_path == IGA2) - vmode_index = viafb_get_mode_index(set_hres, set_vres, 1); - else - vmode_index = viafb_get_mode_index(set_hres, set_vres, 0); + vmode_index = viafb_get_mode_index(set_hres, set_vres); switch (panel_id) { case LCD_PANEL_ID5_1400X1050: @@ -832,10 +826,7 @@ static void load_lcd_patch_regs(int set_hres, int set_vres, { int vmode_index; - if (viaparinfo->lvds_setting_info->iga_path == IGA2) - vmode_index = viafb_get_mode_index(set_hres, set_vres, 1); - else - vmode_index = viafb_get_mode_index(set_hres, set_vres, 0); + vmode_index = viafb_get_mode_index(set_hres, set_vres); viafb_unlock_crt(); diff --git a/drivers/video/via/viafbdev.c b/drivers/video/via/viafbdev.c index a0fec29..72833f3 100644 --- a/drivers/video/via/viafbdev.c +++ b/drivers/video/via/viafbdev.c @@ -32,7 +32,6 @@ static u32 pseudo_pal[17]; /* video mode */ static char *viafb_mode = "640x480"; static char *viafb_mode1 = "640x480"; -static int viafb_resMode = VIA_RES_640X480; /* Added for specifying active devices.*/ char *viafb_active_dev = ""; @@ -56,47 +55,47 @@ static void viafb_get_video_device(u32 *video_dev_info); /* Mode information */ static const struct viafb_modeinfo viafb_modentry[] = { - {480, 640, VIA_RES_480X640, "480x640"}, - {640, 480, VIA_RES_640X480, "640x480"}, - {800, 480, VIA_RES_800X480, "800x480"}, - {800, 600, VIA_RES_800X600, "800x600"}, - {1024, 768, VIA_RES_1024X768, "1024x768"}, - {1152, 864, VIA_RES_1152X864, "1152x864"}, - {1280, 1024, VIA_RES_1280X1024, "1280x1024"}, - {1600, 1200, VIA_RES_1600X1200, "1600x1200"}, - {1440, 1050, VIA_RES_1440X1050, "1440x1050"}, - {1280, 768, VIA_RES_1280X768, "1280x768"}, - {1280, 800, VIA_RES_1280X800, "1280x800"}, - {1280, 960, VIA_RES_1280X960, "1280x960"}, - {1920, 1440, VIA_RES_1920X1440, "1920x1440"}, - {848, 480, VIA_RES_848X480, "848x480"}, - {1400, 1050, VIA_RES_1400X1050, "1400x1050"}, - {720, 480, VIA_RES_720X480, "720x480"}, - {720, 576, VIA_RES_720X576, "720x576"}, - {1024, 512, VIA_RES_1024X512, "1024x512"}, - {1024, 576, VIA_RES_1024X576, "1024x576"}, - {1024, 600, VIA_RES_1024X600, "1024x600"}, - {1280, 720, VIA_RES_1280X720, "1280x720"}, - {1920, 1080, VIA_RES_1920X1080, "1920x1080"}, - {1366, 768, VIA_RES_1368X768, "1368x768"}, - {1680, 1050, VIA_RES_1680X1050, "1680x1050"}, - {960, 600, VIA_RES_960X600, "960x600"}, - {1000, 600, VIA_RES_1000X600, "1000x600"}, - {1024, 576, VIA_RES_1024X576, "1024x576"}, - {1024, 600, VIA_RES_1024X600, "1024x600"}, - {1088, 612, VIA_RES_1088X612, "1088x612"}, - {1152, 720, VIA_RES_1152X720, "1152x720"}, - {1200, 720, VIA_RES_1200X720, "1200x720"}, - {1280, 600, VIA_RES_1280X600, "1280x600"}, - {1360, 768, VIA_RES_1360X768, "1360x768"}, - {1440, 900, VIA_RES_1440X900, "1440x900"}, - {1600, 900, VIA_RES_1600X900, "1600x900"}, - {1600, 1024, VIA_RES_1600X1024, "1600x1024"}, - {1792, 1344, VIA_RES_1792X1344, "1792x1344"}, - {1856, 1392, VIA_RES_1856X1392, "1856x1392"}, - {1920, 1200, VIA_RES_1920X1200, "1920x1200"}, - {2048, 1536, VIA_RES_2048X1536, "2048x1536"}, - {0, 0, VIA_RES_INVALID, "640x480"} + {480, 640, VIA_RES_480X640}, + {640, 480, VIA_RES_640X480}, + {800, 480, VIA_RES_800X480}, + {800, 600, VIA_RES_800X600}, + {1024, 768, VIA_RES_1024X768}, + {1152, 864, VIA_RES_1152X864}, + {1280, 1024, VIA_RES_1280X1024}, + {1600, 1200, VIA_RES_1600X1200}, + {1440, 1050, VIA_RES_1440X1050}, + {1280, 768, VIA_RES_1280X768,}, + {1280, 800, VIA_RES_1280X800}, + {1280, 960, VIA_RES_1280X960}, + {1920, 1440, VIA_RES_1920X1440}, + {848, 480, VIA_RES_848X480}, + {1400, 1050, VIA_RES_1400X1050}, + {720, 480, VIA_RES_720X480}, + {720, 576, VIA_RES_720X576}, + {1024, 512, VIA_RES_1024X512}, + {1024, 576, VIA_RES_1024X576}, + {1024, 600, VIA_RES_1024X600}, + {1280, 720, VIA_RES_1280X720}, + {1920, 1080, VIA_RES_1920X1080}, + {1366, 768, VIA_RES_1368X768}, + {1680, 1050, VIA_RES_1680X1050}, + {960, 600, VIA_RES_960X600}, + {1000, 600, VIA_RES_1000X600}, + {1024, 576, VIA_RES_1024X576}, + {1024, 600, VIA_RES_1024X600}, + {1088, 612, VIA_RES_1088X612}, + {1152, 720, VIA_RES_1152X720}, + {1200, 720, VIA_RES_1200X720}, + {1280, 600, VIA_RES_1280X600}, + {1360, 768, VIA_RES_1360X768}, + {1440, 900, VIA_RES_1440X900}, + {1600, 900, VIA_RES_1600X900}, + {1600, 1024, VIA_RES_1600X1024}, + {1792, 1344, VIA_RES_1792X1344}, + {1856, 1392, VIA_RES_1856X1392}, + {1920, 1200, VIA_RES_1920X1200}, + {2048, 1536, VIA_RES_2048X1536}, + {0, 0, VIA_RES_INVALID} }; static struct fb_ops viafb_ops; @@ -177,7 +176,7 @@ static int viafb_check_var(struct fb_var_screeninfo *var, if (var->vmode & FB_VMODE_INTERLACED || var->vmode & FB_VMODE_DOUBLE) return -EINVAL; - vmode_index = viafb_get_mode_index(var->xres, var->yres, 0); + vmode_index = viafb_get_mode_index(var->xres, var->yres); if (vmode_index == VIA_RES_INVALID) { DEBUG_MSG(KERN_INFO "viafb: Mode %dx%dx%d not supported!!\n", @@ -233,14 +232,14 @@ static int viafb_set_par(struct fb_info *info) viafb_update_device_setting(info->var.xres, info->var.yres, info->var.bits_per_pixel, viafb_refresh, 0); - vmode_index = viafb_get_mode_index(info->var.xres, info->var.yres, 0); + vmode_index = viafb_get_mode_index(info->var.xres, info->var.yres); if (viafb_SAMM_ON == 1) { DEBUG_MSG(KERN_INFO "viafb_second_xres = %d, viafb_second_yres = %d, bpp = %d\n", viafb_second_xres, viafb_second_yres, viafb_bpp1); vmode_index1 = viafb_get_mode_index(viafb_second_xres, - viafb_second_yres, 1); + viafb_second_yres); DEBUG_MSG(KERN_INFO "->viafb_SAMM_ON: index=%d\n", vmode_index1); @@ -1262,7 +1261,7 @@ static int viafb_sync(struct fb_info *info) return 0; } -int viafb_get_mode_index(int hres, int vres, int flag) +int viafb_get_mode_index(int hres, int vres) { u32 i; DEBUG_MSG(KERN_INFO "viafb_get_mode_index!\n"); @@ -1272,13 +1271,7 @@ int viafb_get_mode_index(int hres, int vres, int flag) viafb_modentry[i].yres == vres) break; - viafb_resMode = viafb_modentry[i].mode_index; - if (flag) - viafb_mode1 = viafb_modentry[i].mode_res; - else - viafb_mode = viafb_modentry[i].mode_res; - - return viafb_resMode; + return viafb_modentry[i].mode_index; } static void check_available_device_to_enable(int device_id) @@ -2199,7 +2192,7 @@ static int __devinit via_pci_probe(void) strict_strtoul(tmpc, 0, &default_xres); strict_strtoul(tmpm, 0, &default_yres); - vmode_index = viafb_get_mode_index(default_xres, default_yres, 0); + vmode_index = viafb_get_mode_index(default_xres, default_yres); DEBUG_MSG(KERN_INFO "0->index=%d\n", vmode_index); if (viafb_SAMM_ON == 1) { diff --git a/drivers/video/via/viafbdev.h b/drivers/video/via/viafbdev.h index a4158e8..227b000 100644 --- a/drivers/video/via/viafbdev.h +++ b/drivers/video/via/viafbdev.h @@ -81,7 +81,6 @@ struct viafb_modeinfo { u32 xres; u32 yres; int mode_index; - char *mode_res; }; extern unsigned int viafb_second_virtual_yres; extern unsigned int viafb_second_virtual_xres; @@ -102,7 +101,7 @@ extern int strict_strtoul(const char *cp, unsigned int base, void viafb_memory_pitch_patch(struct fb_info *info); void viafb_fill_var_timing_info(struct fb_var_screeninfo *var, int refresh, int mode_index); -int viafb_get_mode_index(int hres, int vres, int flag); +int viafb_get_mode_index(int hres, int vres); u8 viafb_gpio_i2c_read_lvds(struct lvds_setting_information *plvds_setting_info, struct lvds_chip_information *plvds_chip_info, u8 index); diff --git a/drivers/w1/masters/omap_hdq.c b/drivers/w1/masters/omap_hdq.c index a7e3b70..0d92969 100644 --- a/drivers/w1/masters/omap_hdq.c +++ b/drivers/w1/masters/omap_hdq.c @@ -687,6 +687,7 @@ static int omap_hdq_remove(struct platform_device *pdev) if (hdq_data->hdq_usecount) { dev_dbg(&pdev->dev, "removed when use count is not zero\n"); + mutex_unlock(&hdq_data->hdq_mutex); return -EBUSY; } diff --git a/drivers/watchdog/coh901327_wdt.c b/drivers/watchdog/coh901327_wdt.c index fecb307..aec7cef 100644 --- a/drivers/watchdog/coh901327_wdt.c +++ b/drivers/watchdog/coh901327_wdt.c @@ -18,6 +18,7 @@ #include <linux/bitops.h> #include <linux/uaccess.h> #include <linux/clk.h> +#include <linux/delay.h> #define DRV_NAME "WDOG COH 901 327" @@ -92,6 +93,8 @@ static struct clk *clk; static void coh901327_enable(u16 timeout) { u16 val; + unsigned long freq; + unsigned long delay_ns; clk_enable(clk); /* Restart timer if it is disabled */ @@ -102,6 +105,14 @@ static void coh901327_enable(u16 timeout) /* Acknowledge any pending interrupt so it doesn't just fire off */ writew(U300_WDOG_IER_WILL_BARK_IRQ_ACK_ENABLE, virtbase + U300_WDOG_IER); + /* + * The interrupt is cleared in the 32 kHz clock domain. + * Wait 3 32 kHz cycles for it to take effect + */ + freq = clk_get_rate(clk); + delay_ns = (1000000000 + freq - 1) / freq; /* Freq to ns and round up */ + delay_ns = 3 * delay_ns; /* Wait 3 cycles */ + ndelay(delay_ns); /* Enable the watchdog interrupt */ writew(U300_WDOG_IMR_WILL_BARK_IRQ_ENABLE, virtbase + U300_WDOG_IMR); /* Activate the watchdog timer */ diff --git a/drivers/watchdog/ks8695_wdt.c b/drivers/watchdog/ks8695_wdt.c index 00b03eb..e1c8276 100644 --- a/drivers/watchdog/ks8695_wdt.c +++ b/drivers/watchdog/ks8695_wdt.c @@ -66,7 +66,7 @@ static inline void ks8695_wdt_stop(void) static inline void ks8695_wdt_start(void) { unsigned long tmcon; - unsigned long tval = wdt_time * CLOCK_TICK_RATE; + unsigned long tval = wdt_time * KS8695_CLOCK_RATE; spin_lock(&ks8695_lock); /* disable timer0 */ @@ -103,7 +103,7 @@ static inline void ks8695_wdt_reload(void) static int ks8695_wdt_settimeout(int new_time) { /* - * All counting occurs at SLOW_CLOCK / 128 = 0.256 Hz + * All counting occurs at KS8695_CLOCK_RATE / 128 = 0.256 Hz * * Since WDV is a 16-bit counter, the maximum period is * 65536 / 0.256 = 256 seconds. diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 697f6b5..e92f229 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -828,15 +828,22 @@ static int load_flat_shared_library(int id, struct lib_info *libs) if (IS_ERR(bprm.file)) return res; + bprm.cred = prepare_exec_creds(); + res = -ENOMEM; + if (!bprm.cred) + goto out; + res = prepare_binprm(&bprm); if (res <= (unsigned long)-4096) res = load_flat_file(&bprm, libs, id, NULL); - if (bprm.file) { - allow_write_access(bprm.file); - fput(bprm.file); - bprm.file = NULL; - } + + abort_creds(bprm.cred); + +out: + allow_write_access(bprm.file); + fput(bprm.file); + return(res); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index dc84dae..72a2b9c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -265,10 +265,6 @@ static int caching_kthread(void *data) atomic_inc(&block_group->space_info->caching_threads); last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET); -again: - /* need to make sure the commit_root doesn't disappear */ - down_read(&fs_info->extent_commit_sem); - /* * We don't want to deadlock with somebody trying to allocate a new * extent for the extent root while also trying to search the extent @@ -282,6 +278,10 @@ again: key.objectid = last; key.offset = 0; btrfs_set_key_type(&key, BTRFS_EXTENT_ITEM_KEY); +again: + /* need to make sure the commit_root doesn't disappear */ + down_read(&fs_info->extent_commit_sem); + ret = btrfs_search_slot(NULL, fs_info->extent_root, &key, path, 0, 0); if (ret < 0) goto err; @@ -304,6 +304,19 @@ again: if (need_resched() || btrfs_transaction_in_commit(fs_info)) { + leaf = path->nodes[0]; + + /* this shouldn't happen, but if the + * leaf is empty just move on. + */ + if (btrfs_header_nritems(leaf) == 0) + break; + /* + * we need to copy the key out so that + * we are sure the next search advances + * us forward in the btree. + */ + btrfs_item_key_to_cpu(leaf, &key, 0); btrfs_release_path(fs_info->extent_root, path); up_read(&fs_info->extent_commit_sem); schedule_timeout(1); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index af99b78..5edcee3 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -414,11 +414,29 @@ static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_gro u64 *offset, u64 *bytes) { u64 end; + u64 search_start, search_bytes; + int ret; again: end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * block_group->sectorsize) - 1; + /* + * XXX - this can go away after a few releases. + * + * since the only user of btrfs_remove_free_space is the tree logging + * stuff, and the only way to test that is under crash conditions, we + * want to have this debug stuff here just in case somethings not + * working. Search the bitmap for the space we are trying to use to + * make sure its actually there. If its not there then we need to stop + * because something has gone wrong. + */ + search_start = *offset; + search_bytes = *bytes; + ret = search_bitmap(block_group, bitmap_info, &search_start, + &search_bytes); + BUG_ON(ret < 0 || search_start != *offset); + if (*offset > bitmap_info->offset && *offset + *bytes > end) { bitmap_clear_bits(block_group, bitmap_info, *offset, end - *offset + 1); @@ -430,6 +448,7 @@ again: } if (*bytes) { + struct rb_node *next = rb_next(&bitmap_info->offset_index); if (!bitmap_info->bytes) { unlink_free_space(block_group, bitmap_info); kfree(bitmap_info->bitmap); @@ -438,16 +457,36 @@ again: recalculate_thresholds(block_group); } - bitmap_info = tree_search_offset(block_group, - offset_to_bitmap(block_group, - *offset), - 1, 0); - if (!bitmap_info) + /* + * no entry after this bitmap, but we still have bytes to + * remove, so something has gone wrong. + */ + if (!next) return -EINVAL; + bitmap_info = rb_entry(next, struct btrfs_free_space, + offset_index); + + /* + * if the next entry isn't a bitmap we need to return to let the + * extent stuff do its work. + */ if (!bitmap_info->bitmap) return -EAGAIN; + /* + * Ok the next item is a bitmap, but it may not actually hold + * the information for the rest of this free space stuff, so + * look for it, and if we don't find it return so we can try + * everything over again. + */ + search_start = *offset; + search_bytes = *bytes; + ret = search_bitmap(block_group, bitmap_info, &search_start, + &search_bytes); + if (ret < 0 || search_start != *offset) + return -EAGAIN; + goto again; } else if (!bitmap_info->bytes) { unlink_free_space(block_group, bitmap_info); @@ -644,8 +683,17 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, again: info = tree_search_offset(block_group, offset, 0, 0); if (!info) { - WARN_ON(1); - goto out_lock; + /* + * oops didn't find an extent that matched the space we wanted + * to remove, look for a bitmap instead + */ + info = tree_search_offset(block_group, + offset_to_bitmap(block_group, offset), + 1, 0); + if (!info) { + WARN_ON(1); + goto out_lock; + } } if (info->bytes < bytes && rb_next(&info->offset_index)) { @@ -957,8 +1005,15 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, if (cluster->block_group != block_group) goto out; - entry = tree_search_offset(block_group, search_start, 0, 0); - + /* + * search_start is the beginning of the bitmap, but at some point it may + * be a good idea to point to the actual start of the free area in the + * bitmap, so do the offset_to_bitmap trick anyway, and set bitmap_only + * to 1 to make sure we get the bitmap entry + */ + entry = tree_search_offset(block_group, + offset_to_bitmap(block_group, search_start), + 1, 0); if (!entry || !entry->bitmap) goto out; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 56fe83f..272b9b2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4785,8 +4785,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, * and the replacement file is large. Start IO on it now so * we don't add too much work to the end of the transaction */ - if (new_inode && old_inode && S_ISREG(old_inode->i_mode) && - new_inode->i_size && + if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size && old_inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT) filemap_flush(old_inode->i_mapping); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e71264d..c04f7f2 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2553,8 +2553,13 @@ int relocate_inode_pages(struct inode *inode, u64 start, u64 len) last_index = (start + len - 1) >> PAGE_CACHE_SHIFT; /* make sure the dirty trick played by the caller work */ - ret = invalidate_inode_pages2_range(inode->i_mapping, - first_index, last_index); + while (1) { + ret = invalidate_inode_pages2_range(inode->i_mapping, + first_index, last_index); + if (ret != -EBUSY) + break; + schedule_timeout(HZ/10); + } if (ret) goto out_unlock; diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index ecfbce8..3e2b90e 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -208,7 +208,7 @@ int btrfs_zlib_compress_pages(struct address_space *mapping, *total_in = 0; workspace = find_zlib_workspace(); - if (!workspace) + if (IS_ERR(workspace)) return -1; if (Z_OK != zlib_deflateInit(&workspace->def_strm, 3)) { @@ -366,7 +366,7 @@ int btrfs_zlib_decompress_biovec(struct page **pages_in, char *kaddr; workspace = find_zlib_workspace(); - if (!workspace) + if (IS_ERR(workspace)) return -ENOMEM; data_in = kmap(pages_in[page_in_index]); @@ -547,7 +547,7 @@ int btrfs_zlib_decompress(unsigned char *data_in, return -ENOMEM; workspace = find_zlib_workspace(); - if (!workspace) + if (IS_ERR(workspace)) return -ENOMEM; workspace->inf_strm.next_in = data_in; diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 92888aa..e85b1e4 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,10 @@ +Version 1.60 +------------- +Fix memory leak in reconnect. Fix oops in DFS mount error path. +Set s_maxbytes to smaller (the max that vfs can handle) so that +sendfile will now work over cifs mounts again. Add noforcegid +and noforceuid mount parameters. + Version 1.59 ------------ Client uses server inode numbers (which are persistent) rather than diff --git a/fs/cifs/README b/fs/cifs/README index ad92921..79c1a93 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -262,11 +262,11 @@ A partial list of the supported mount options follows: mount. domain Set the SMB/CIFS workgroup name prepended to the username during CIFS session establishment - forceuid Set the default uid for inodes based on the uid - passed in. For mounts to servers + forceuid Set the default uid for inodes to the uid + passed in on mount. For mounts to servers which do support the CIFS Unix extensions, such as a properly configured Samba server, the server provides - the uid, gid and mode so this parameter should not be + the uid, gid and mode so this parameter should not be specified unless the server and clients uid and gid numbering differ. If the server and client are in the same domain (e.g. running winbind or nss_ldap) and @@ -278,11 +278,7 @@ A partial list of the supported mount options follows: of existing files will be the uid (gid) of the person who executed the mount (root, except when mount.cifs is configured setuid for user mounts) unless the "uid=" - (gid) mount option is specified. For the uid (gid) of newly - created files and directories, ie files created since - the last mount of the server share, the expected uid - (gid) is cached as long as the inode remains in - memory on the client. Also note that permission + (gid) mount option is specified. Also note that permission checks (authorization checks) on accesses to a file occur at the server, but there are cases in which an administrator may want to restrict at the client as well. For those @@ -290,12 +286,15 @@ A partial list of the supported mount options follows: (such as Windows), permissions can also be checked at the client, and a crude form of client side permission checking can be enabled by specifying file_mode and dir_mode on - the client. Note that the mount.cifs helper must be - at version 1.10 or higher to support specifying the uid - (or gid) in non-numeric form. - forcegid (similar to above but for the groupid instead of uid) + the client. (default) + forcegid (similar to above but for the groupid instead of uid) (default) + noforceuid Fill in file owner information (uid) by requesting it from + the server if possible. With this option, the value given in + the uid= option (on mount) will only be used if the server + can not support returning uids on inodes. + noforcegid (similar to above but for the group owner, gid, instead of uid) uid Set the default uid for inodes, and indicate to the - cifs kernel driver which local user mounted . If the server + cifs kernel driver which local user mounted. If the server supports the unix extensions the default uid is not used to fill in the owner fields of inodes (files) unless the "forceuid" parameter is specified. diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 3bb11be..606912d 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -55,7 +55,7 @@ void cifs_dfs_release_automount_timer(void) * i.e. strips from UNC trailing path that is not part of share * name and fixup missing '\' in the begining of DFS node refferal * if neccessary. - * Returns pointer to share name on success or NULL on error. + * Returns pointer to share name on success or ERR_PTR on error. * Caller is responsible for freeing returned string. */ static char *cifs_get_share_name(const char *node_name) @@ -68,7 +68,7 @@ static char *cifs_get_share_name(const char *node_name) UNC = kmalloc(len+2 /*for term null and additional \ if it's missed */, GFP_KERNEL); if (!UNC) - return NULL; + return ERR_PTR(-ENOMEM); /* get share name and server name */ if (node_name[1] != '\\') { @@ -87,7 +87,7 @@ static char *cifs_get_share_name(const char *node_name) cERROR(1, ("%s: no server name end in node name: %s", __func__, node_name)); kfree(UNC); - return NULL; + return ERR_PTR(-EINVAL); } /* find sharename end */ @@ -133,6 +133,12 @@ char *cifs_compose_mount_options(const char *sb_mountdata, return ERR_PTR(-EINVAL); *devname = cifs_get_share_name(ref->node_name); + if (IS_ERR(*devname)) { + rc = PTR_ERR(*devname); + *devname = NULL; + goto compose_mount_options_err; + } + rc = dns_resolve_server_name_to_ip(*devname, &srvIP); if (rc != 0) { cERROR(1, ("%s: Failed to resolve server part of %s to IP: %d", diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 60e3c42..714a542 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -44,7 +44,7 @@ cifs_ucs2_bytes(const __le16 *from, int maxbytes, int maxwords = maxbytes / 2; char tmp[NLS_MAX_CHARSET_SIZE]; - for (i = 0; from[i] && i < maxwords; i++) { + for (i = 0; i < maxwords && from[i]; i++) { charlen = codepage->uni2char(le16_to_cpu(from[i]), tmp, NLS_MAX_CHARSET_SIZE); if (charlen > 0) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 44f3050..84b7525 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -376,10 +376,14 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m) seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) seq_printf(s, ",forceuid"); + else + seq_printf(s, ",noforceuid"); seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) seq_printf(s, ",forcegid"); + else + seq_printf(s, ",noforcegid"); cifs_show_address(s, tcon->ses->server); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index fc44d31..1f3345d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -803,6 +803,10 @@ cifs_parse_mount_options(char *options, const char *devname, char *data; unsigned int temp_len, i, j; char separator[2]; + short int override_uid = -1; + short int override_gid = -1; + bool uid_specified = false; + bool gid_specified = false; separator[0] = ','; separator[1] = 0; @@ -1093,18 +1097,20 @@ cifs_parse_mount_options(char *options, const char *devname, "too long.\n"); return 1; } - } else if (strnicmp(data, "uid", 3) == 0) { - if (value && *value) - vol->linux_uid = - simple_strtoul(value, &value, 0); - } else if (strnicmp(data, "forceuid", 8) == 0) { - vol->override_uid = 1; - } else if (strnicmp(data, "gid", 3) == 0) { - if (value && *value) - vol->linux_gid = - simple_strtoul(value, &value, 0); - } else if (strnicmp(data, "forcegid", 8) == 0) { - vol->override_gid = 1; + } else if (!strnicmp(data, "uid", 3) && value && *value) { + vol->linux_uid = simple_strtoul(value, &value, 0); + uid_specified = true; + } else if (!strnicmp(data, "forceuid", 8)) { + override_uid = 1; + } else if (!strnicmp(data, "noforceuid", 10)) { + override_uid = 0; + } else if (!strnicmp(data, "gid", 3) && value && *value) { + vol->linux_gid = simple_strtoul(value, &value, 0); + gid_specified = true; + } else if (!strnicmp(data, "forcegid", 8)) { + override_gid = 1; + } else if (!strnicmp(data, "noforcegid", 10)) { + override_gid = 0; } else if (strnicmp(data, "file_mode", 4) == 0) { if (value && *value) { vol->file_mode = @@ -1355,6 +1361,18 @@ cifs_parse_mount_options(char *options, const char *devname, if (vol->UNCip == NULL) vol->UNCip = &vol->UNC[2]; + if (uid_specified) + vol->override_uid = override_uid; + else if (override_uid == 1) + printk(KERN_NOTICE "CIFS: ignoring forceuid mount option " + "specified with no uid= option.\n"); + + if (gid_specified) + vol->override_gid = override_gid; + else if (override_gid == 1) + printk(KERN_NOTICE "CIFS: ignoring forcegid mount option " + "specified with no gid= option.\n"); + return 0; } @@ -2544,11 +2562,20 @@ remote_path_check: if (mount_data != mount_data_global) kfree(mount_data); + mount_data = cifs_compose_mount_options( cifs_sb->mountdata, full_path + 1, referrals, &fake_devname); - kfree(fake_devname); + free_dfs_info_array(referrals, num_referrals); + kfree(fake_devname); + kfree(full_path); + + if (IS_ERR(mount_data)) { + rc = PTR_ERR(mount_data); + mount_data = NULL; + goto mount_fail_check; + } if (tcon) cifs_put_tcon(tcon); @@ -2556,8 +2583,6 @@ remote_path_check: cifs_put_smb_ses(pSesInfo); cleanup_volume_info(&volume_info); - FreeXid(xid); - kfree(full_path); referral_walks_count++; goto try_mount_again; } diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index f28f070..f91fd51 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1905,6 +1905,7 @@ COMPATIBLE_IOCTL(FIONCLEX) COMPATIBLE_IOCTL(FIOASYNC) COMPATIBLE_IOCTL(FIONBIO) COMPATIBLE_IOCTL(FIONREAD) /* This is also TIOCINQ */ +COMPATIBLE_IOCTL(FS_IOC_FIEMAP) /* 0x00 */ COMPATIBLE_IOCTL(FIBMAP) COMPATIBLE_IOCTL(FIGETBSZ) @@ -120,12 +120,11 @@ static void wake_up_inode(struct inode *inode) * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ -struct inode *inode_init_always(struct super_block *sb, struct inode *inode) +int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct address_space_operations empty_aops; static struct inode_operations empty_iops; static const struct file_operations empty_fops; - struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; @@ -152,7 +151,7 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->dirtied_when = 0; if (security_inode_alloc(inode)) - goto out_free_inode; + goto out; /* allocate and initialize an i_integrity */ if (ima_inode_alloc(inode)) @@ -198,16 +197,12 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif - return inode; + return 0; out_free_security: security_inode_free(inode); -out_free_inode: - if (inode->i_sb->s_op->destroy_inode) - inode->i_sb->s_op->destroy_inode(inode); - else - kmem_cache_free(inode_cachep, (inode)); - return NULL; +out: + return -ENOMEM; } EXPORT_SYMBOL(inode_init_always); @@ -220,12 +215,21 @@ static struct inode *alloc_inode(struct super_block *sb) else inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL); - if (inode) - return inode_init_always(sb, inode); - return NULL; + if (!inode) + return NULL; + + if (unlikely(inode_init_always(sb, inode))) { + if (inode->i_sb->s_op->destroy_inode) + inode->i_sb->s_op->destroy_inode(inode); + else + kmem_cache_free(inode_cachep, inode); + return NULL; + } + + return inode; } -void destroy_inode(struct inode *inode) +void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); ima_inode_free(inode); @@ -237,13 +241,17 @@ void destroy_inode(struct inode *inode) if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) posix_acl_release(inode->i_default_acl); #endif +} +EXPORT_SYMBOL(__destroy_inode); + +void destroy_inode(struct inode *inode) +{ + __destroy_inode(inode); if (inode->i_sb->s_op->destroy_inode) inode->i_sb->s_op->destroy_inode(inode); else kmem_cache_free(inode_cachep, (inode)); } -EXPORT_SYMBOL(destroy_inode); - /* * These are initializations that only need to be done diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 5edc2bf..23c9475 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -99,7 +99,7 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) kunmap(pg); D2(printk(KERN_DEBUG "readpage finished\n")); - return 0; + return ret; } int jffs2_do_readpage_unlock(struct inode *inode, struct page *pg) diff --git a/fs/namespace.c b/fs/namespace.c index 277c28a..7230787 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -316,7 +316,8 @@ EXPORT_SYMBOL_GPL(mnt_clone_write); */ int mnt_want_write_file(struct file *file) { - if (!(file->f_mode & FMODE_WRITE)) + struct inode *inode = file->f_dentry->d_inode; + if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode)) return mnt_want_write(file->f_path.mnt); else return mnt_clone_write(file->f_path.mnt); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 489fc01..e4e089a 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -255,7 +255,7 @@ static void nfs_direct_read_release(void *calldata) if (put_dreq(dreq)) nfs_direct_complete(dreq); - nfs_readdata_release(calldata); + nfs_readdata_free(data); } static const struct rpc_call_ops nfs_read_direct_ops = { @@ -314,14 +314,14 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, data->npages, 1, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { - nfs_readdata_release(data); + nfs_readdata_free(data); break; } if ((unsigned)result < data->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { nfs_direct_release_pages(data->pagevec, result); - nfs_readdata_release(data); + nfs_readdata_free(data); break; } bytes -= pgbase; @@ -334,7 +334,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, data->inode = inode; data->cred = msg.rpc_cred; data->args.fh = NFS_FH(inode); - data->args.context = get_nfs_open_context(ctx); + data->args.context = ctx; data->args.offset = pos; data->args.pgbase = pgbase; data->args.pages = data->pagevec; @@ -441,7 +441,7 @@ static void nfs_direct_free_writedata(struct nfs_direct_req *dreq) struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages); list_del(&data->pages); nfs_direct_release_pages(data->pagevec, data->npages); - nfs_writedata_release(data); + nfs_writedata_free(data); } } @@ -534,7 +534,7 @@ static void nfs_direct_commit_release(void *calldata) dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status); nfs_direct_write_complete(dreq, data->inode); - nfs_commitdata_release(calldata); + nfs_commit_free(data); } static const struct rpc_call_ops nfs_commit_direct_ops = { @@ -570,7 +570,7 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) data->args.fh = NFS_FH(data->inode); data->args.offset = 0; data->args.count = 0; - data->args.context = get_nfs_open_context(dreq->ctx); + data->args.context = dreq->ctx; data->res.count = 0; data->res.fattr = &data->fattr; data->res.verf = &data->verf; @@ -734,14 +734,14 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, data->npages, 0, 0, data->pagevec, NULL); up_read(¤t->mm->mmap_sem); if (result < 0) { - nfs_writedata_release(data); + nfs_writedata_free(data); break; } if ((unsigned)result < data->npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { nfs_direct_release_pages(data->pagevec, result); - nfs_writedata_release(data); + nfs_writedata_free(data); break; } bytes -= pgbase; @@ -756,7 +756,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, data->inode = inode; data->cred = msg.rpc_cred; data->args.fh = NFS_FH(inode); - data->args.context = get_nfs_open_context(ctx); + data->args.context = ctx; data->args.offset = pos; data->args.pgbase = pgbase; data->args.pages = data->pagevec; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 73ea5e8..12c9e66 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -60,17 +60,15 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) return p; } -static void nfs_readdata_free(struct nfs_read_data *p) +void nfs_readdata_free(struct nfs_read_data *p) { if (p && (p->pagevec != &p->page_array[0])) kfree(p->pagevec); mempool_free(p, nfs_rdata_mempool); } -void nfs_readdata_release(void *data) +static void nfs_readdata_release(struct nfs_read_data *rdata) { - struct nfs_read_data *rdata = data; - put_nfs_open_context(rdata->args.context); nfs_readdata_free(rdata); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 0a0a2ff..a34fae2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -87,17 +87,15 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) return p; } -static void nfs_writedata_free(struct nfs_write_data *p) +void nfs_writedata_free(struct nfs_write_data *p) { if (p && (p->pagevec != &p->page_array[0])) kfree(p->pagevec); mempool_free(p, nfs_wdata_mempool); } -void nfs_writedata_release(void *data) +static void nfs_writedata_release(struct nfs_write_data *wdata) { - struct nfs_write_data *wdata = data; - put_nfs_open_context(wdata->args.context); nfs_writedata_free(wdata); } diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 3d3ddb3..2dfd477 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -412,8 +412,10 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) return 0; /* Do not request flush for shadow page cache */ if (!sb) { writer = nilfs_get_writer(NILFS_MDT(inode)->mi_nilfs); - if (!writer) + if (!writer) { + nilfs_put_writer(NILFS_MDT(inode)->mi_nilfs); return -EROFS; + } sb = writer->s_super; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 8b5e477..51ff3d0 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1859,12 +1859,26 @@ static void nilfs_end_page_io(struct page *page, int err) if (!page) return; - if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page)) + if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page)) { /* * For b-tree node pages, this function may be called twice * or more because they might be split in a segment. */ + if (PageDirty(page)) { + /* + * For pages holding split b-tree node buffers, dirty + * flag on the buffers may be cleared discretely. + * In that case, the page is once redirtied for + * remaining buffers, and it must be cancelled if + * all the buffers get cleaned later. + */ + lock_page(page); + if (nilfs_page_buffers_clean(page)) + __nilfs_clear_page_dirty(page); + unlock_page(page); + } return; + } __nilfs_end_page_io(page, err); } diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 9edcde4..f9a3e89 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -1914,7 +1914,8 @@ static void ocfs2_adjust_adjacent_records(struct ocfs2_extent_rec *left_rec, * immediately to their right. */ left_clusters = le32_to_cpu(right_child_el->l_recs[0].e_cpos); - if (ocfs2_is_empty_extent(&right_child_el->l_recs[0])) { + if (!ocfs2_rec_clusters(right_child_el, &right_child_el->l_recs[0])) { + BUG_ON(right_child_el->l_tree_depth); BUG_ON(le16_to_cpu(right_child_el->l_next_free_rec) <= 1); left_clusters = le32_to_cpu(right_child_el->l_recs[1].e_cpos); } @@ -2476,15 +2477,37 @@ out_ret_path: return ret; } -static void ocfs2_update_edge_lengths(struct inode *inode, handle_t *handle, - struct ocfs2_path *path) +static int ocfs2_update_edge_lengths(struct inode *inode, handle_t *handle, + int subtree_index, struct ocfs2_path *path) { - int i, idx; + int i, idx, ret; struct ocfs2_extent_rec *rec; struct ocfs2_extent_list *el; struct ocfs2_extent_block *eb; u32 range; + /* + * In normal tree rotation process, we will never touch the + * tree branch above subtree_index and ocfs2_extend_rotate_transaction + * doesn't reserve the credits for them either. + * + * But we do have a special case here which will update the rightmost + * records for all the bh in the path. + * So we have to allocate extra credits and access them. + */ + ret = ocfs2_extend_trans(handle, + handle->h_buffer_credits + subtree_index); + if (ret) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access_path(inode, handle, path); + if (ret) { + mlog_errno(ret); + goto out; + } + /* Path should always be rightmost. */ eb = (struct ocfs2_extent_block *)path_leaf_bh(path)->b_data; BUG_ON(eb->h_next_leaf_blk != 0ULL); @@ -2505,6 +2528,8 @@ static void ocfs2_update_edge_lengths(struct inode *inode, handle_t *handle, ocfs2_journal_dirty(handle, path->p_node[i].bh); } +out: + return ret; } static void ocfs2_unlink_path(struct inode *inode, handle_t *handle, @@ -2717,7 +2742,12 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle, if (del_right_subtree) { ocfs2_unlink_subtree(inode, handle, left_path, right_path, subtree_index, dealloc); - ocfs2_update_edge_lengths(inode, handle, left_path); + ret = ocfs2_update_edge_lengths(inode, handle, subtree_index, + left_path); + if (ret) { + mlog_errno(ret); + goto out; + } eb = (struct ocfs2_extent_block *)path_leaf_bh(left_path)->b_data; ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno)); @@ -3034,7 +3064,12 @@ static int ocfs2_remove_rightmost_path(struct inode *inode, handle_t *handle, ocfs2_unlink_subtree(inode, handle, left_path, path, subtree_index, dealloc); - ocfs2_update_edge_lengths(inode, handle, left_path); + ret = ocfs2_update_edge_lengths(inode, handle, subtree_index, + left_path); + if (ret) { + mlog_errno(ret); + goto out; + } eb = (struct ocfs2_extent_block *)path_leaf_bh(left_path)->b_data; ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno)); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index b2c52b3..b401654 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -193,6 +193,7 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock, (unsigned long long)OCFS2_I(inode)->ip_blkno); mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters); dump_stack(); + goto bail; } past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode)); @@ -894,18 +895,17 @@ struct ocfs2_write_cluster_desc { */ unsigned c_new; unsigned c_unwritten; + unsigned c_needs_zero; }; -static inline int ocfs2_should_zero_cluster(struct ocfs2_write_cluster_desc *d) -{ - return d->c_new || d->c_unwritten; -} - struct ocfs2_write_ctxt { /* Logical cluster position / len of write */ u32 w_cpos; u32 w_clen; + /* First cluster allocated in a nonsparse extend */ + u32 w_first_new_cpos; + struct ocfs2_write_cluster_desc w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE]; /* @@ -983,6 +983,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp, return -ENOMEM; wc->w_cpos = pos >> osb->s_clustersize_bits; + wc->w_first_new_cpos = UINT_MAX; cend = (pos + len - 1) >> osb->s_clustersize_bits; wc->w_clen = cend - wc->w_cpos + 1; get_bh(di_bh); @@ -1217,20 +1218,18 @@ out: */ static int ocfs2_write_cluster(struct address_space *mapping, u32 phys, unsigned int unwritten, + unsigned int should_zero, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, struct ocfs2_write_ctxt *wc, u32 cpos, loff_t user_pos, unsigned user_len) { - int ret, i, new, should_zero = 0; + int ret, i, new; u64 v_blkno, p_blkno; struct inode *inode = mapping->host; struct ocfs2_extent_tree et; new = phys == 0 ? 1 : 0; - if (new || unwritten) - should_zero = 1; - if (new) { u32 tmp_pos; @@ -1301,7 +1300,7 @@ static int ocfs2_write_cluster(struct address_space *mapping, if (tmpret) { mlog_errno(tmpret); if (ret == 0) - tmpret = ret; + ret = tmpret; } } @@ -1341,7 +1340,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping, local_len = osb->s_clustersize - cluster_off; ret = ocfs2_write_cluster(mapping, desc->c_phys, - desc->c_unwritten, data_ac, meta_ac, + desc->c_unwritten, + desc->c_needs_zero, + data_ac, meta_ac, wc, desc->c_cpos, pos, local_len); if (ret) { mlog_errno(ret); @@ -1391,14 +1392,14 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb, * newly allocated cluster. */ desc = &wc->w_desc[0]; - if (ocfs2_should_zero_cluster(desc)) + if (desc->c_needs_zero) ocfs2_figure_cluster_boundaries(osb, desc->c_cpos, &wc->w_target_from, NULL); desc = &wc->w_desc[wc->w_clen - 1]; - if (ocfs2_should_zero_cluster(desc)) + if (desc->c_needs_zero) ocfs2_figure_cluster_boundaries(osb, desc->c_cpos, NULL, @@ -1466,13 +1467,28 @@ static int ocfs2_populate_write_desc(struct inode *inode, phys++; } + /* + * If w_first_new_cpos is < UINT_MAX, we have a non-sparse + * file that got extended. w_first_new_cpos tells us + * where the newly allocated clusters are so we can + * zero them. + */ + if (desc->c_cpos >= wc->w_first_new_cpos) { + BUG_ON(phys == 0); + desc->c_needs_zero = 1; + } + desc->c_phys = phys; if (phys == 0) { desc->c_new = 1; + desc->c_needs_zero = 1; *clusters_to_alloc = *clusters_to_alloc + 1; } - if (ext_flags & OCFS2_EXT_UNWRITTEN) + + if (ext_flags & OCFS2_EXT_UNWRITTEN) { desc->c_unwritten = 1; + desc->c_needs_zero = 1; + } num_clusters--; } @@ -1632,10 +1648,13 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos, if (newsize <= i_size_read(inode)) return 0; - ret = ocfs2_extend_no_holes(inode, newsize, newsize - len); + ret = ocfs2_extend_no_holes(inode, newsize, pos); if (ret) mlog_errno(ret); + wc->w_first_new_cpos = + ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)); + return ret; } @@ -1644,7 +1663,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, struct page **pagep, void **fsdata, struct buffer_head *di_bh, struct page *mmap_page) { - int ret, credits = OCFS2_INODE_UPDATE_CREDITS; + int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS; unsigned int clusters_to_alloc, extents_to_split; struct ocfs2_write_ctxt *wc; struct inode *inode = mapping->host; @@ -1722,8 +1741,19 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, } - ocfs2_set_target_boundaries(osb, wc, pos, len, - clusters_to_alloc + extents_to_split); + /* + * We have to zero sparse allocated clusters, unwritten extent clusters, + * and non-sparse clusters we just extended. For non-sparse writes, + * we know zeros will only be needed in the first and/or last cluster. + */ + if (clusters_to_alloc || extents_to_split || + wc->w_desc[0].c_needs_zero || + wc->w_desc[wc->w_clen - 1].c_needs_zero) + cluster_of_pages = 1; + else + cluster_of_pages = 0; + + ocfs2_set_target_boundaries(osb, wc, pos, len, cluster_of_pages); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { @@ -1756,8 +1786,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping, * extent. */ ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, - clusters_to_alloc + extents_to_split, - mmap_page); + cluster_of_pages, mmap_page); if (ret) { mlog_errno(ret); goto out_quota; diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index b574431..2f28b7d 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -310,22 +310,19 @@ out_attach: return ret; } -static DEFINE_SPINLOCK(dentry_list_lock); +DEFINE_SPINLOCK(dentry_list_lock); /* We limit the number of dentry locks to drop in one go. We have * this limit so that we don't starve other users of ocfs2_wq. */ #define DL_INODE_DROP_COUNT 64 /* Drop inode references from dentry locks */ -void ocfs2_drop_dl_inodes(struct work_struct *work) +static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count) { - struct ocfs2_super *osb = container_of(work, struct ocfs2_super, - dentry_lock_work); struct ocfs2_dentry_lock *dl; - int drop_count = DL_INODE_DROP_COUNT; spin_lock(&dentry_list_lock); - while (osb->dentry_lock_list && drop_count--) { + while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) { dl = osb->dentry_lock_list; osb->dentry_lock_list = dl->dl_next; spin_unlock(&dentry_list_lock); @@ -333,11 +330,32 @@ void ocfs2_drop_dl_inodes(struct work_struct *work) kfree(dl); spin_lock(&dentry_list_lock); } - if (osb->dentry_lock_list) + spin_unlock(&dentry_list_lock); +} + +void ocfs2_drop_dl_inodes(struct work_struct *work) +{ + struct ocfs2_super *osb = container_of(work, struct ocfs2_super, + dentry_lock_work); + + __ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT); + /* + * Don't queue dropping if umount is in progress. We flush the + * list in ocfs2_dismount_volume + */ + spin_lock(&dentry_list_lock); + if (osb->dentry_lock_list && + !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED)) queue_work(ocfs2_wq, &osb->dentry_lock_work); spin_unlock(&dentry_list_lock); } +/* Flush the whole work queue */ +void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb) +{ + __ocfs2_drop_dl_inodes(osb, -1); +} + /* * ocfs2_dentry_iput() and friends. * @@ -368,7 +386,8 @@ static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb, /* We leave dropping of inode reference to ocfs2_wq as that can * possibly lead to inode deletion which gets tricky */ spin_lock(&dentry_list_lock); - if (!osb->dentry_lock_list) + if (!osb->dentry_lock_list && + !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED)) queue_work(ocfs2_wq, &osb->dentry_lock_work); dl->dl_next = osb->dentry_lock_list; osb->dentry_lock_list = dl; diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h index faa12e7..f5dd178 100644 --- a/fs/ocfs2/dcache.h +++ b/fs/ocfs2/dcache.h @@ -49,10 +49,13 @@ struct ocfs2_dentry_lock { int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode, u64 parent_blkno); +extern spinlock_t dentry_list_lock; + void ocfs2_dentry_lock_put(struct ocfs2_super *osb, struct ocfs2_dentry_lock *dl); void ocfs2_drop_dl_inodes(struct work_struct *work); +void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb); struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno, int skip_unhashed); diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index d07ddbe..81eff8e 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -103,7 +103,6 @@ static void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock) lock->ast_pending, lock->ml.type); BUG(); } - BUG_ON(!list_empty(&lock->ast_list)); if (lock->ast_pending) mlog(0, "lock has an ast getting flushed right now\n"); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index bcb9260..43e6e32 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1118,7 +1118,7 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, mlog(0, "%s:%.*s: sending mig lockres (%s) to %u\n", dlm->name, res->lockname.len, res->lockname.name, - orig_flags & DLM_MRES_MIGRATION ? "migrate" : "recovery", + orig_flags & DLM_MRES_MIGRATION ? "migration" : "recovery", send_to); /* send it */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 62442e4..aa501d3 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1851,6 +1851,7 @@ relock: if (ret) goto out_dio; + count = ocount; ret = generic_write_checks(file, ppos, &count, S_ISBLK(inode->i_mode)); if (ret) @@ -1918,8 +1919,10 @@ out_sems: mutex_unlock(&inode->i_mutex); + if (written) + ret = written; mlog_exit(ret); - return written ? written : ret; + return ret; } static int ocfs2_splice_to_file(struct pipe_inode_info *pipe, diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index f033760..c48b93a 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1954,10 +1954,16 @@ void ocfs2_orphan_scan_init(struct ocfs2_super *osb) os->os_osb = osb; os->os_count = 0; os->os_seqno = 0; - os->os_scantime = CURRENT_TIME; mutex_init(&os->os_lock); INIT_DELAYED_WORK(&os->os_orphan_scan_work, ocfs2_orphan_scan_work); +} +void ocfs2_orphan_scan_start(struct ocfs2_super *osb) +{ + struct ocfs2_orphan_scan *os; + + os = &osb->osb_orphan_scan; + os->os_scantime = CURRENT_TIME; if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb)) atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE); else { diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 5432c7f..2c3222a 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -145,6 +145,7 @@ static inline void ocfs2_inode_set_new(struct ocfs2_super *osb, /* Exported only for the journal struct init code in super.c. Do not call. */ void ocfs2_orphan_scan_init(struct ocfs2_super *osb); +void ocfs2_orphan_scan_start(struct ocfs2_super *osb); void ocfs2_orphan_scan_stop(struct ocfs2_super *osb); void ocfs2_orphan_scan_exit(struct ocfs2_super *osb); @@ -329,20 +330,27 @@ int ocfs2_journal_dirty(handle_t *handle, /* extended attribute block update */ #define OCFS2_XATTR_BLOCK_UPDATE_CREDITS 1 +/* Update of a single quota block */ +#define OCFS2_QUOTA_BLOCK_UPDATE_CREDITS 1 + /* global quotafile inode update, data block */ -#define OCFS2_QINFO_WRITE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1) +#define OCFS2_QINFO_WRITE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + \ + OCFS2_QUOTA_BLOCK_UPDATE_CREDITS) +#define OCFS2_LOCAL_QINFO_WRITE_CREDITS OCFS2_QUOTA_BLOCK_UPDATE_CREDITS /* * The two writes below can accidentally see global info dirty due * to set_info() quotactl so make them prepared for the writes. */ /* quota data block, global info */ /* Write to local quota file */ -#define OCFS2_QWRITE_CREDITS (OCFS2_QINFO_WRITE_CREDITS + 1) +#define OCFS2_QWRITE_CREDITS (OCFS2_QINFO_WRITE_CREDITS + \ + OCFS2_QUOTA_BLOCK_UPDATE_CREDITS) /* global quota data block, local quota data block, global quota inode, * global quota info */ -#define OCFS2_QSYNC_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 3) +#define OCFS2_QSYNC_CREDITS (OCFS2_QINFO_WRITE_CREDITS + \ + 2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS) static inline int ocfs2_quota_trans_credits(struct super_block *sb) { @@ -355,11 +363,6 @@ static inline int ocfs2_quota_trans_credits(struct super_block *sb) return credits; } -/* Number of credits needed for removing quota structure from file */ -int ocfs2_calc_qdel_credits(struct super_block *sb, int type); -/* Number of credits needed for initialization of new quota structure */ -int ocfs2_calc_qinit_credits(struct super_block *sb, int type); - /* group extend. inode update and last group update. */ #define OCFS2_GROUP_EXTEND_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1) diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index c9345eb..39e1d5a 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -224,10 +224,12 @@ enum ocfs2_mount_options OCFS2_MOUNT_GRPQUOTA = 1 << 10, /* We support group quotas */ }; -#define OCFS2_OSB_SOFT_RO 0x0001 -#define OCFS2_OSB_HARD_RO 0x0002 -#define OCFS2_OSB_ERROR_FS 0x0004 -#define OCFS2_DEFAULT_ATIME_QUANTUM 60 +#define OCFS2_OSB_SOFT_RO 0x0001 +#define OCFS2_OSB_HARD_RO 0x0002 +#define OCFS2_OSB_ERROR_FS 0x0004 +#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED 0x0008 + +#define OCFS2_DEFAULT_ATIME_QUANTUM 60 struct ocfs2_journal; struct ocfs2_slot_info; @@ -490,6 +492,18 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb, spin_unlock(&osb->osb_lock); } + +static inline unsigned long ocfs2_test_osb_flag(struct ocfs2_super *osb, + unsigned long flag) +{ + unsigned long ret; + + spin_lock(&osb->osb_lock); + ret = osb->osb_flags & flag; + spin_unlock(&osb->osb_lock); + return ret; +} + static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb, int hard) { diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h index 7365e2e..3fb96fcd 100644 --- a/fs/ocfs2/quota.h +++ b/fs/ocfs2/quota.h @@ -50,7 +50,6 @@ struct ocfs2_mem_dqinfo { unsigned int dqi_chunks; /* Number of chunks in local quota file */ unsigned int dqi_blocks; /* Number of blocks allocated for local quota file */ unsigned int dqi_syncms; /* How often should we sync with other nodes */ - unsigned int dqi_syncjiff; /* Precomputed dqi_syncms in jiffies */ struct list_head dqi_chunk; /* List of chunks */ struct inode *dqi_gqinode; /* Global quota file inode */ struct ocfs2_lock_res dqi_gqlock; /* Lock protecting quota information structure */ diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index edfa60c..bf7742d 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -69,6 +69,7 @@ static void ocfs2_global_mem2diskdqb(void *dp, struct dquot *dquot) d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_itime = cpu_to_le64(m->dqb_itime); + d->dqb_pad1 = d->dqb_pad2 = 0; } static int ocfs2_global_is_id(void *dp, struct dquot *dquot) @@ -211,14 +212,13 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type, mutex_lock_nested(&gqinode->i_mutex, I_MUTEX_QUOTA); if (gqinode->i_size < off + len) { - down_write(&OCFS2_I(gqinode)->ip_alloc_sem); - err = ocfs2_extend_no_holes(gqinode, off + len, off); - up_write(&OCFS2_I(gqinode)->ip_alloc_sem); - if (err < 0) - goto out; + loff_t rounded_end = + ocfs2_align_bytes_to_blocks(sb, off + len); + + /* Space is already allocated in ocfs2_global_read_dquot() */ err = ocfs2_simple_size_update(gqinode, oinfo->dqi_gqi_bh, - off + len); + rounded_end); if (err < 0) goto out; new = 1; @@ -234,7 +234,7 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type, } if (err) { mlog_errno(err); - return err; + goto out; } lock_buffer(bh); if (new) @@ -342,7 +342,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type) info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); oinfo->dqi_syncms = le32_to_cpu(dinfo.dqi_syncms); - oinfo->dqi_syncjiff = msecs_to_jiffies(oinfo->dqi_syncms); oinfo->dqi_gi.dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); oinfo->dqi_gi.dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk); oinfo->dqi_gi.dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry); @@ -352,7 +351,7 @@ int ocfs2_global_read_info(struct super_block *sb, int type) oinfo->dqi_gi.dqi_qtree_depth = qtree_depth(&oinfo->dqi_gi); INIT_DELAYED_WORK(&oinfo->dqi_sync_work, qsync_work_fn); queue_delayed_work(ocfs2_quota_wq, &oinfo->dqi_sync_work, - oinfo->dqi_syncjiff); + msecs_to_jiffies(oinfo->dqi_syncms)); out_err: mlog_exit(status); @@ -402,13 +401,36 @@ int ocfs2_global_write_info(struct super_block *sb, int type) return err; } +static int ocfs2_global_qinit_alloc(struct super_block *sb, int type) +{ + struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv; + + /* + * We may need to allocate tree blocks and a leaf block but not the + * root block + */ + return oinfo->dqi_gi.dqi_qtree_depth; +} + +static int ocfs2_calc_global_qinit_credits(struct super_block *sb, int type) +{ + /* We modify all the allocated blocks, tree root, and info block */ + return (ocfs2_global_qinit_alloc(sb, type) + 2) * + OCFS2_QUOTA_BLOCK_UPDATE_CREDITS; +} + /* Read in information from global quota file and acquire a reference to it. * dquot_acquire() has already started the transaction and locked quota file */ int ocfs2_global_read_dquot(struct dquot *dquot) { int err, err2, ex = 0; - struct ocfs2_mem_dqinfo *info = - sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv; + struct super_block *sb = dquot->dq_sb; + int type = dquot->dq_type; + struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv; + struct ocfs2_super *osb = OCFS2_SB(sb); + struct inode *gqinode = info->dqi_gqinode; + int need_alloc = ocfs2_global_qinit_alloc(sb, type); + handle_t *handle = NULL; err = ocfs2_qinfo_lock(info, 0); if (err < 0) @@ -419,14 +441,33 @@ int ocfs2_global_read_dquot(struct dquot *dquot) OCFS2_DQUOT(dquot)->dq_use_count++; OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace; OCFS2_DQUOT(dquot)->dq_originodes = dquot->dq_dqb.dqb_curinodes; + ocfs2_qinfo_unlock(info, 0); + if (!dquot->dq_off) { /* No real quota entry? */ - /* Upgrade to exclusive lock for allocation */ - ocfs2_qinfo_unlock(info, 0); - err = ocfs2_qinfo_lock(info, 1); - if (err < 0) - goto out_qlock; ex = 1; + /* + * Add blocks to quota file before we start a transaction since + * locking allocators ranks above a transaction start + */ + WARN_ON(journal_current_handle()); + down_write(&OCFS2_I(gqinode)->ip_alloc_sem); + err = ocfs2_extend_no_holes(gqinode, + gqinode->i_size + (need_alloc << sb->s_blocksize_bits), + gqinode->i_size); + up_write(&OCFS2_I(gqinode)->ip_alloc_sem); + if (err < 0) + goto out; } + + handle = ocfs2_start_trans(osb, + ocfs2_calc_global_qinit_credits(sb, type)); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out; + } + err = ocfs2_qinfo_lock(info, ex); + if (err < 0) + goto out_trans; err = qtree_write_dquot(&info->dqi_gi, dquot); if (ex && info_dirty(sb_dqinfo(dquot->dq_sb, dquot->dq_type))) { err2 = __ocfs2_global_write_info(dquot->dq_sb, dquot->dq_type); @@ -438,6 +479,9 @@ out_qlock: ocfs2_qinfo_unlock(info, 1); else ocfs2_qinfo_unlock(info, 0); +out_trans: + if (handle) + ocfs2_commit_trans(osb, handle); out: if (err < 0) mlog_errno(err); @@ -607,7 +651,7 @@ static void qsync_work_fn(struct work_struct *work) dquot_scan_active(sb, ocfs2_sync_dquot_helper, oinfo->dqi_type); queue_delayed_work(ocfs2_quota_wq, &oinfo->dqi_sync_work, - oinfo->dqi_syncjiff); + msecs_to_jiffies(oinfo->dqi_syncms)); } /* @@ -635,20 +679,18 @@ out: return status; } -int ocfs2_calc_qdel_credits(struct super_block *sb, int type) +static int ocfs2_calc_qdel_credits(struct super_block *sb, int type) { - struct ocfs2_mem_dqinfo *oinfo; - int features[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA, - OCFS2_FEATURE_RO_COMPAT_GRPQUOTA }; - - if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, features[type])) - return 0; - - oinfo = sb_dqinfo(sb, type)->dqi_priv; - /* We modify tree, leaf block, global info, local chunk header, - * global and local inode */ - return oinfo->dqi_gi.dqi_qtree_depth + 2 + 1 + - 2 * OCFS2_INODE_UPDATE_CREDITS; + struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv; + /* + * We modify tree, leaf block, global info, local chunk header, + * global and local inode; OCFS2_QINFO_WRITE_CREDITS already + * accounts for inode update + */ + return (oinfo->dqi_gi.dqi_qtree_depth + 2) * + OCFS2_QUOTA_BLOCK_UPDATE_CREDITS + + OCFS2_QINFO_WRITE_CREDITS + + OCFS2_INODE_UPDATE_CREDITS; } static int ocfs2_release_dquot(struct dquot *dquot) @@ -680,33 +722,10 @@ out: return status; } -int ocfs2_calc_qinit_credits(struct super_block *sb, int type) -{ - struct ocfs2_mem_dqinfo *oinfo; - int features[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA, - OCFS2_FEATURE_RO_COMPAT_GRPQUOTA }; - struct ocfs2_dinode *lfe, *gfe; - - if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, features[type])) - return 0; - - oinfo = sb_dqinfo(sb, type)->dqi_priv; - gfe = (struct ocfs2_dinode *)oinfo->dqi_gqi_bh->b_data; - lfe = (struct ocfs2_dinode *)oinfo->dqi_lqi_bh->b_data; - /* We can extend local file + global file. In local file we - * can modify info, chunk header block and dquot block. In - * global file we can modify info, tree and leaf block */ - return ocfs2_calc_extend_credits(sb, &lfe->id2.i_list, 0) + - ocfs2_calc_extend_credits(sb, &gfe->id2.i_list, 0) + - 3 + oinfo->dqi_gi.dqi_qtree_depth + 2; -} - static int ocfs2_acquire_dquot(struct dquot *dquot) { - handle_t *handle; struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv; - struct ocfs2_super *osb = OCFS2_SB(dquot->dq_sb); int status = 0; mlog_entry("id=%u, type=%d", dquot->dq_id, dquot->dq_type); @@ -715,16 +734,7 @@ static int ocfs2_acquire_dquot(struct dquot *dquot) status = ocfs2_lock_global_qf(oinfo, 1); if (status < 0) goto out; - handle = ocfs2_start_trans(osb, - ocfs2_calc_qinit_credits(dquot->dq_sb, dquot->dq_type)); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto out_ilock; - } status = dquot_acquire(dquot); - ocfs2_commit_trans(osb, handle); -out_ilock: ocfs2_unlock_global_qf(oinfo, 1); out: mlog_exit(status); diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 5a460fa..bdb09cb 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -20,6 +20,7 @@ #include "sysfile.h" #include "dlmglue.h" #include "quota.h" +#include "uptodate.h" /* Number of local quota structures per block */ static inline unsigned int ol_quota_entries_per_block(struct super_block *sb) @@ -100,7 +101,8 @@ static int ocfs2_modify_bh(struct inode *inode, struct buffer_head *bh, handle_t *handle; int status; - handle = ocfs2_start_trans(OCFS2_SB(sb), 1); + handle = ocfs2_start_trans(OCFS2_SB(sb), + OCFS2_QUOTA_BLOCK_UPDATE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); @@ -610,7 +612,8 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, goto out_bh; /* Mark quota file as clean if we are recovering quota file of * some other node. */ - handle = ocfs2_start_trans(osb, 1); + handle = ocfs2_start_trans(osb, + OCFS2_LOCAL_QINFO_WRITE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); @@ -940,7 +943,7 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( struct ocfs2_local_disk_chunk *dchunk; int status; handle_t *handle; - struct buffer_head *bh = NULL; + struct buffer_head *bh = NULL, *dbh = NULL; u64 p_blkno; /* We are protected by dqio_sem so no locking needed */ @@ -964,32 +967,35 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( mlog_errno(status); goto out; } + /* Local quota info and two new blocks we initialize */ + handle = ocfs2_start_trans(OCFS2_SB(sb), + OCFS2_LOCAL_QINFO_WRITE_CREDITS + + 2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS); + if (IS_ERR(handle)) { + status = PTR_ERR(handle); + mlog_errno(status); + goto out; + } + /* Initialize chunk header */ down_read(&OCFS2_I(lqinode)->ip_alloc_sem); status = ocfs2_extent_map_get_blocks(lqinode, oinfo->dqi_blocks, &p_blkno, NULL, NULL); up_read(&OCFS2_I(lqinode)->ip_alloc_sem); if (status < 0) { mlog_errno(status); - goto out; + goto out_trans; } bh = sb_getblk(sb, p_blkno); if (!bh) { status = -ENOMEM; mlog_errno(status); - goto out; + goto out_trans; } dchunk = (struct ocfs2_local_disk_chunk *)bh->b_data; - - handle = ocfs2_start_trans(OCFS2_SB(sb), 2); - if (IS_ERR(handle)) { - status = PTR_ERR(handle); - mlog_errno(status); - goto out; - } - + ocfs2_set_new_buffer_uptodate(lqinode, bh); status = ocfs2_journal_access_dq(handle, lqinode, bh, - OCFS2_JOURNAL_ACCESS_WRITE); + OCFS2_JOURNAL_ACCESS_CREATE); if (status < 0) { mlog_errno(status); goto out_trans; @@ -999,7 +1005,6 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( memset(dchunk->dqc_bitmap, 0, sb->s_blocksize - sizeof(struct ocfs2_local_disk_chunk) - OCFS2_QBLK_RESERVED_SPACE); - set_buffer_uptodate(bh); unlock_buffer(bh); status = ocfs2_journal_dirty(handle, bh); if (status < 0) { @@ -1007,6 +1012,38 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk( goto out_trans; } + /* Initialize new block with structures */ + down_read(&OCFS2_I(lqinode)->ip_alloc_sem); + status = ocfs2_extent_map_get_blocks(lqinode, oinfo->dqi_blocks + 1, + &p_blkno, NULL, NULL); + up_read(&OCFS2_I(lqinode)->ip_alloc_sem); + if (status < 0) { + mlog_errno(status); + goto out_trans; + } + dbh = sb_getblk(sb, p_blkno); + if (!dbh) { + status = -ENOMEM; + mlog_errno(status); + goto out_trans; + } + ocfs2_set_new_buffer_uptodate(lqinode, dbh); + status = ocfs2_journal_access_dq(handle, lqinode, dbh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (status < 0) { + mlog_errno(status); + goto out_trans; + } + lock_buffer(dbh); + memset(dbh->b_data, 0, sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE); + unlock_buffer(dbh); + status = ocfs2_journal_dirty(handle, dbh); + if (status < 0) { + mlog_errno(status); + goto out_trans; + } + + /* Update local quotafile info */ oinfo->dqi_blocks += 2; oinfo->dqi_chunks++; status = ocfs2_local_write_info(sb, type); @@ -1031,6 +1068,7 @@ out_trans: ocfs2_commit_trans(OCFS2_SB(sb), handle); out: brelse(bh); + brelse(dbh); kmem_cache_free(ocfs2_qf_chunk_cachep, chunk); return ERR_PTR(status); } @@ -1048,6 +1086,8 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file( struct ocfs2_local_disk_chunk *dchunk; int epb = ol_quota_entries_per_block(sb); unsigned int chunk_blocks; + struct buffer_head *bh; + u64 p_blkno; int status; handle_t *handle; @@ -1075,12 +1115,49 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file( mlog_errno(status); goto out; } - handle = ocfs2_start_trans(OCFS2_SB(sb), 2); + + /* Get buffer from the just added block */ + down_read(&OCFS2_I(lqinode)->ip_alloc_sem); + status = ocfs2_extent_map_get_blocks(lqinode, oinfo->dqi_blocks, + &p_blkno, NULL, NULL); + up_read(&OCFS2_I(lqinode)->ip_alloc_sem); + if (status < 0) { + mlog_errno(status); + goto out; + } + bh = sb_getblk(sb, p_blkno); + if (!bh) { + status = -ENOMEM; + mlog_errno(status); + goto out; + } + ocfs2_set_new_buffer_uptodate(lqinode, bh); + + /* Local quota info, chunk header and the new block we initialize */ + handle = ocfs2_start_trans(OCFS2_SB(sb), + OCFS2_LOCAL_QINFO_WRITE_CREDITS + + 2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); goto out; } + /* Zero created block */ + status = ocfs2_journal_access_dq(handle, lqinode, bh, + OCFS2_JOURNAL_ACCESS_CREATE); + if (status < 0) { + mlog_errno(status); + goto out_trans; + } + lock_buffer(bh); + memset(bh->b_data, 0, sb->s_blocksize); + unlock_buffer(bh); + status = ocfs2_journal_dirty(handle, bh); + if (status < 0) { + mlog_errno(status); + goto out_trans; + } + /* Update chunk header */ status = ocfs2_journal_access_dq(handle, lqinode, chunk->qc_headerbh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { @@ -1097,6 +1174,7 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file( mlog_errno(status); goto out_trans; } + /* Update file header */ oinfo->dqi_blocks++; status = ocfs2_local_write_info(sb, type); if (status < 0) { diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index 3f66137..e49c410 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -17,6 +17,7 @@ * General Public License for more details. */ +#include <linux/kernel.h> #include <linux/crc32.h> #include <linux/module.h> @@ -153,7 +154,7 @@ static int status_map[] = { static int dlm_status_to_errno(enum dlm_status status) { - BUG_ON(status > (sizeof(status_map) / sizeof(status_map[0]))); + BUG_ON(status < 0 || status >= ARRAY_SIZE(status_map)); return status_map[status]; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 7efb349..b0ee0fd 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -777,6 +777,7 @@ static int ocfs2_sb_probe(struct super_block *sb, } di = (struct ocfs2_dinode *) (*bh)->b_data; memset(stats, 0, sizeof(struct ocfs2_blockcheck_stats)); + spin_lock_init(&stats->b_lock); status = ocfs2_verify_volume(di, *bh, blksize, stats); if (status >= 0) goto bail; @@ -1182,7 +1183,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) wake_up(&osb->osb_mount_event); /* Start this when the mount is almost sure of being successful */ - ocfs2_orphan_scan_init(osb); + ocfs2_orphan_scan_start(osb); mlog_exit(status); return status; @@ -1213,14 +1214,27 @@ static int ocfs2_get_sb(struct file_system_type *fs_type, mnt); } +static void ocfs2_kill_sb(struct super_block *sb) +{ + struct ocfs2_super *osb = OCFS2_SB(sb); + + /* Prevent further queueing of inode drop events */ + spin_lock(&dentry_list_lock); + ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED); + spin_unlock(&dentry_list_lock); + /* Wait for work to finish and/or remove it */ + cancel_work_sync(&osb->dentry_lock_work); + + kill_block_super(sb); +} + static struct file_system_type ocfs2_fs_type = { .owner = THIS_MODULE, .name = "ocfs2", .get_sb = ocfs2_get_sb, /* is this called when we mount * the fs? */ - .kill_sb = kill_block_super, /* set to the generic one - * right now, but do we - * need to change that? */ + .kill_sb = ocfs2_kill_sb, + .fs_flags = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE, .next = NULL }; @@ -1819,6 +1833,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) debugfs_remove(osb->osb_ctxt); + /* + * Flush inode dropping work queue so that deletes are + * performed while the filesystem is still working + */ + ocfs2_drop_all_dl_inodes(osb); + /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); @@ -1981,6 +2001,8 @@ static int ocfs2_initialize_super(struct super_block *sb, snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u", MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev)); + ocfs2_orphan_scan_init(osb); + status = ocfs2_recovery_init(osb); if (status) { mlog(ML_ERROR, "Unable to initialize recovery state\n"); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index ba320e2..d1a27cd 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1052,7 +1052,8 @@ static int ocfs2_xattr_block_get(struct inode *inode, struct ocfs2_xattr_block *xb; struct ocfs2_xattr_value_root *xv; size_t size; - int ret = -ENODATA, name_offset, name_len, block_off, i; + int ret = -ENODATA, name_offset, name_len, i; + int uninitialized_var(block_off); xs->bucket = ocfs2_xattr_bucket_new(inode); if (!xs->bucket) { diff --git a/fs/proc/base.c b/fs/proc/base.c index 3ce5ae9..175db25 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -234,23 +234,20 @@ static int check_mem_permission(struct task_struct *task) struct mm_struct *mm_for_maps(struct task_struct *task) { - struct mm_struct *mm = get_task_mm(task); - if (!mm) + struct mm_struct *mm; + + if (mutex_lock_killable(&task->cred_guard_mutex)) return NULL; - down_read(&mm->mmap_sem); - task_lock(task); - if (task->mm != mm) - goto out; - if (task->mm != current->mm && - __ptrace_may_access(task, PTRACE_MODE_READ) < 0) - goto out; - task_unlock(task); + + mm = get_task_mm(task); + if (mm && mm != current->mm && + !ptrace_may_access(task, PTRACE_MODE_READ)) { + mmput(mm); + mm = NULL; + } + mutex_unlock(&task->cred_guard_mutex); + return mm; -out: - task_unlock(task); - up_read(&mm->mmap_sem); - mmput(mm); - return NULL; } static int proc_pid_cmdline(struct task_struct *task, char * buffer) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6f61b7c..9bd8be1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -119,6 +119,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) mm = mm_for_maps(priv->task); if (!mm) return NULL; + down_read(&mm->mmap_sem); tail_vma = get_gate_vma(priv->task); priv->tail_vma = tail_vma; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 64a72e2..8f5c05d 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -189,6 +189,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) priv->task = NULL; return NULL; } + down_read(&mm->mmap_sem); /* start from the Nth VMA */ for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index 0c93c7e..965df12 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -770,7 +770,7 @@ xfs_buf_associate_memory( bp->b_pages = NULL; bp->b_addr = mem; - rval = _xfs_buf_get_pages(bp, page_count, 0); + rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK); if (rval) return rval; diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index db15feb..4ece190 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -2010,7 +2010,9 @@ xfs_attr_rmtval_get(xfs_da_args_t *args) dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock); blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno, - blkcnt, XFS_BUF_LOCK, &bp); + blkcnt, + XFS_BUF_LOCK | XBF_DONT_BLOCK, + &bp); if (error) return(error); @@ -2141,8 +2143,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args) dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock), blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); - bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno, - blkcnt, XFS_BUF_LOCK); + bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno, blkcnt, + XFS_BUF_LOCK | XBF_DONT_BLOCK); ASSERT(bp); ASSERT(!XFS_BUF_GETERROR(bp)); diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 7928b99..8ee5b5a 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -6009,7 +6009,7 @@ xfs_getbmap( */ error = ENOMEM; subnex = 16; - map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL); + map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS); if (!map) goto out_unlock_ilock; diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index e9df995..2671738 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -120,8 +120,8 @@ xfs_btree_check_sblock( XFS_RANDOM_BTREE_CHECK_SBLOCK))) { if (bp) xfs_buftrace("SBTREE ERROR", bp); - XFS_ERROR_REPORT("xfs_btree_check_sblock", XFS_ERRLEVEL_LOW, - cur->bc_mp); + XFS_CORRUPTION_ERROR("xfs_btree_check_sblock", + XFS_ERRLEVEL_LOW, cur->bc_mp, block); return XFS_ERROR(EFSCORRUPTED); } return 0; diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 9ff6e57..2847bbc 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -2201,7 +2201,7 @@ kmem_zone_t *xfs_dabuf_zone; /* dabuf zone */ xfs_da_state_t * xfs_da_state_alloc(void) { - return kmem_zone_zalloc(xfs_da_state_zone, KM_SLEEP); + return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS); } /* @@ -2261,9 +2261,9 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra) int off; if (nbuf == 1) - dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_SLEEP); + dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS); else - dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_SLEEP); + dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS); dabuf->dirty = 0; #ifdef XFS_DABUF_DEBUG dabuf->ra = ra; diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c index c657bec..bb1d58e 100644 --- a/fs/xfs/xfs_dir2.c +++ b/fs/xfs/xfs_dir2.c @@ -256,7 +256,7 @@ xfs_dir_cilookup_result( !(args->op_flags & XFS_DA_OP_CILOOKUP)) return EEXIST; - args->value = kmem_alloc(len, KM_MAYFAIL); + args->value = kmem_alloc(len, KM_NOFS | KM_MAYFAIL); if (!args->value) return ENOMEM; diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index cbd451b..2d0b3e1 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -167,17 +167,25 @@ xfs_growfs_data_private( new = nb - mp->m_sb.sb_dblocks; oagcount = mp->m_sb.sb_agcount; if (nagcount > oagcount) { + void *new_perag, *old_perag; + xfs_filestream_flush(mp); + + new_perag = kmem_zalloc(sizeof(xfs_perag_t) * nagcount, + KM_MAYFAIL); + if (!new_perag) + return XFS_ERROR(ENOMEM); + down_write(&mp->m_peraglock); - mp->m_perag = kmem_realloc(mp->m_perag, - sizeof(xfs_perag_t) * nagcount, - sizeof(xfs_perag_t) * oagcount, - KM_SLEEP); - memset(&mp->m_perag[oagcount], 0, - (nagcount - oagcount) * sizeof(xfs_perag_t)); + memcpy(new_perag, mp->m_perag, sizeof(xfs_perag_t) * oagcount); + old_perag = mp->m_perag; + mp->m_perag = new_perag; + mp->m_flags |= XFS_MOUNT_32BITINODES; nagimax = xfs_initialize_perag(mp, nagcount); up_write(&mp->m_peraglock); + + kmem_free(old_perag); } tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFS); tp->t_flags |= XFS_TRANS_RESERVE; diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index 5fcec6f..34ec869 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -64,6 +64,10 @@ xfs_inode_alloc( ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP); if (!ip) return NULL; + if (inode_init_always(mp->m_super, VFS_I(ip))) { + kmem_zone_free(xfs_inode_zone, ip); + return NULL; + } ASSERT(atomic_read(&ip->i_iocount) == 0); ASSERT(atomic_read(&ip->i_pincount) == 0); @@ -105,17 +109,6 @@ xfs_inode_alloc( #ifdef XFS_DIR2_TRACE ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS); #endif - /* - * Now initialise the VFS inode. We do this after the xfs_inode - * initialisation as internal failures will result in ->destroy_inode - * being called and that will pass down through the reclaim path and - * free the XFS inode. This path requires the XFS inode to already be - * initialised. Hence if this call fails, the xfs_inode has already - * been freed and we should not reference it at all in the error - * handling. - */ - if (!inode_init_always(mp->m_super, VFS_I(ip))) - return NULL; /* prevent anyone from using this yet */ VFS_I(ip)->i_state = I_NEW|I_LOCK; @@ -123,6 +116,71 @@ xfs_inode_alloc( return ip; } +STATIC void +xfs_inode_free( + struct xfs_inode *ip) +{ + switch (ip->i_d.di_mode & S_IFMT) { + case S_IFREG: + case S_IFDIR: + case S_IFLNK: + xfs_idestroy_fork(ip, XFS_DATA_FORK); + break; + } + + if (ip->i_afp) + xfs_idestroy_fork(ip, XFS_ATTR_FORK); + +#ifdef XFS_INODE_TRACE + ktrace_free(ip->i_trace); +#endif +#ifdef XFS_BMAP_TRACE + ktrace_free(ip->i_xtrace); +#endif +#ifdef XFS_BTREE_TRACE + ktrace_free(ip->i_btrace); +#endif +#ifdef XFS_RW_TRACE + ktrace_free(ip->i_rwtrace); +#endif +#ifdef XFS_ILOCK_TRACE + ktrace_free(ip->i_lock_trace); +#endif +#ifdef XFS_DIR2_TRACE + ktrace_free(ip->i_dir_trace); +#endif + + if (ip->i_itemp) { + /* + * Only if we are shutting down the fs will we see an + * inode still in the AIL. If it is there, we should remove + * it to prevent a use-after-free from occurring. + */ + xfs_log_item_t *lip = &ip->i_itemp->ili_item; + struct xfs_ail *ailp = lip->li_ailp; + + ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) || + XFS_FORCED_SHUTDOWN(ip->i_mount)); + if (lip->li_flags & XFS_LI_IN_AIL) { + spin_lock(&ailp->xa_lock); + if (lip->li_flags & XFS_LI_IN_AIL) + xfs_trans_ail_delete(ailp, lip); + else + spin_unlock(&ailp->xa_lock); + } + xfs_inode_item_destroy(ip); + ip->i_itemp = NULL; + } + + /* asserts to verify all state is correct here */ + ASSERT(atomic_read(&ip->i_iocount) == 0); + ASSERT(atomic_read(&ip->i_pincount) == 0); + ASSERT(!spin_is_locked(&ip->i_flags_lock)); + ASSERT(completion_done(&ip->i_flush)); + + kmem_zone_free(xfs_inode_zone, ip); +} + /* * Check the validity of the inode we just found it the cache */ @@ -167,7 +225,7 @@ xfs_iget_cache_hit( * errors cleanly, then tag it so it can be set up correctly * later. */ - if (!inode_init_always(mp->m_super, VFS_I(ip))) { + if (inode_init_always(mp->m_super, VFS_I(ip))) { error = ENOMEM; goto out_error; } @@ -299,7 +357,8 @@ out_preload_end: if (lock_flags) xfs_iunlock(ip, lock_flags); out_destroy: - xfs_destroy_inode(ip); + __destroy_inode(VFS_I(ip)); + xfs_inode_free(ip); return error; } @@ -504,62 +563,7 @@ xfs_ireclaim( xfs_qm_dqdetach(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL); - switch (ip->i_d.di_mode & S_IFMT) { - case S_IFREG: - case S_IFDIR: - case S_IFLNK: - xfs_idestroy_fork(ip, XFS_DATA_FORK); - break; - } - - if (ip->i_afp) - xfs_idestroy_fork(ip, XFS_ATTR_FORK); - -#ifdef XFS_INODE_TRACE - ktrace_free(ip->i_trace); -#endif -#ifdef XFS_BMAP_TRACE - ktrace_free(ip->i_xtrace); -#endif -#ifdef XFS_BTREE_TRACE - ktrace_free(ip->i_btrace); -#endif -#ifdef XFS_RW_TRACE - ktrace_free(ip->i_rwtrace); -#endif -#ifdef XFS_ILOCK_TRACE - ktrace_free(ip->i_lock_trace); -#endif -#ifdef XFS_DIR2_TRACE - ktrace_free(ip->i_dir_trace); -#endif - if (ip->i_itemp) { - /* - * Only if we are shutting down the fs will we see an - * inode still in the AIL. If it is there, we should remove - * it to prevent a use-after-free from occurring. - */ - xfs_log_item_t *lip = &ip->i_itemp->ili_item; - struct xfs_ail *ailp = lip->li_ailp; - - ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) || - XFS_FORCED_SHUTDOWN(ip->i_mount)); - if (lip->li_flags & XFS_LI_IN_AIL) { - spin_lock(&ailp->xa_lock); - if (lip->li_flags & XFS_LI_IN_AIL) - xfs_trans_ail_delete(ailp, lip); - else - spin_unlock(&ailp->xa_lock); - } - xfs_inode_item_destroy(ip); - ip->i_itemp = NULL; - } - /* asserts to verify all state is correct here */ - ASSERT(atomic_read(&ip->i_iocount) == 0); - ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!spin_is_locked(&ip->i_flags_lock)); - ASSERT(completion_done(&ip->i_flush)); - kmem_zone_free(xfs_inode_zone, ip); + xfs_inode_free(ip); } /* diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 1f22d65..da428b3 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -343,6 +343,16 @@ xfs_iformat( return XFS_ERROR(EFSCORRUPTED); } + if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) && + !ip->i_mount->m_rtdev_targp)) { + xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount, + "corrupt dinode %Lu, has realtime flag set.", + ip->i_ino); + XFS_CORRUPTION_ERROR("xfs_iformat(realtime)", + XFS_ERRLEVEL_LOW, ip->i_mount, dip); + return XFS_ERROR(EFSCORRUPTED); + } + switch (ip->i_d.di_mode & S_IFMT) { case S_IFIFO: case S_IFCHR: diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 1804f86..65f24a3 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -310,23 +310,6 @@ static inline struct inode *VFS_I(struct xfs_inode *ip) } /* - * Get rid of a partially initialized inode. - * - * We have to go through destroy_inode to make sure allocations - * from init_inode_always like the security data are undone. - * - * We mark the inode bad so that it takes the short cut in - * the reclaim path instead of going through the flush path - * which doesn't make sense for an inode that has never seen the - * light of day. - */ -static inline void xfs_destroy_inode(struct xfs_inode *ip) -{ - make_bad_inode(VFS_I(ip)); - return destroy_inode(VFS_I(ip)); -} - -/* * i_flags helper functions */ static inline void diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 3750f04..9dbdff3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -3180,7 +3180,7 @@ try_again: STATIC void xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog) { - ASSERT(spin_is_locked(&log->l_icloglock)); + assert_spin_locked(&log->l_icloglock); if (iclog->ic_state == XLOG_STATE_ACTIVE) { xlog_state_switch_iclogs(log, iclog, 0); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index c4eca5e..492d75b 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -538,7 +538,9 @@ xfs_readlink_bmap( d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); - bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0); + bp = xfs_buf_read_flags(mp->m_ddev_targp, d, BTOBB(byte_cnt), + XBF_LOCK | XBF_MAPPED | + XBF_DONT_BLOCK); error = XFS_BUF_GETERROR(bp); if (error) { xfs_ioerror_alert("xfs_readlink", diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h index 3e79859..ab0b85c 100644 --- a/include/acpi/acpiosxf.h +++ b/include/acpi/acpiosxf.h @@ -242,6 +242,10 @@ acpi_os_derive_pci_id(acpi_handle rhandle, acpi_status acpi_os_validate_interface(char *interface); acpi_status acpi_osi_invalidate(char* interface); +acpi_status +acpi_os_validate_address(u8 space_id, acpi_physical_address address, + acpi_size length, char *name); + u64 acpi_os_get_timer(void); acpi_status acpi_os_signal(u32 function, void *info); diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 7174818..8535084 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -257,9 +257,12 @@ {0x1002, 0x940F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R600|RADEON_NEW_MEMMAP}, \ {0x1002, 0x94A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x94A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x94A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x94B1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \ {0x1002, 0x94B3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x94B4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \ {0x1002, 0x94B5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x94B9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9440, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9441, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9442, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \ @@ -288,6 +291,7 @@ {0x1002, 0x948F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9490, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9491, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x9495, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9498, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x949C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ {0x1002, 0x949E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \ @@ -325,6 +329,7 @@ {0x1002, 0x9552, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9553, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9555, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x9557, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9580, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9581, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x9583, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ @@ -365,6 +370,11 @@ {0x1002, 0x9614, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9615, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0x1002, 0x9616, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9711, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9713, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ + {0x1002, 0x9714, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \ {0, 0, 0} #define r128_PCI_IDS \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e7cb5db..69103e0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short) extern void blk_queue_physical_block_size(struct request_queue *, unsigned short); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_limits(struct queue_limits *lim); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 1219be4..83d2fbd8 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -14,6 +14,7 @@ #include <linux/list.h> #include <linux/cache.h> #include <linux/timer.h> +#include <linux/init.h> #include <asm/div64.h> #include <asm/io.h> @@ -148,14 +149,11 @@ extern u64 timecounter_cyc2time(struct timecounter *tc, * @disable: optional function to disable the clocksource * @mask: bitmask for two's complement * subtraction of non 64 bit counters - * @mult: cycle to nanosecond multiplier (adjusted by NTP) - * @mult_orig: cycle to nanosecond multiplier (unadjusted by NTP) + * @mult: cycle to nanosecond multiplier * @shift: cycle to nanosecond divisor (power of two) * @flags: flags describing special properties * @vread: vsyscall based read * @resume: resume function for the clocksource, if necessary - * @cycle_interval: Used internally by timekeeping core, please ignore. - * @xtime_interval: Used internally by timekeeping core, please ignore. */ struct clocksource { /* @@ -169,7 +167,6 @@ struct clocksource { void (*disable)(struct clocksource *cs); cycle_t mask; u32 mult; - u32 mult_orig; u32 shift; unsigned long flags; cycle_t (*vread)(void); @@ -181,19 +178,12 @@ struct clocksource { #define CLKSRC_FSYS_MMIO_SET(mmio, addr) do { } while (0) #endif - /* timekeeping specific data, ignore */ - cycle_t cycle_interval; - u64 xtime_interval; - u32 raw_interval; /* * Second part is written at each timer interrupt * Keep it in a different cache line to dirty no * more than one cache line. */ cycle_t cycle_last ____cacheline_aligned_in_smp; - u64 xtime_nsec; - s64 error; - struct timespec raw_time; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ @@ -202,8 +192,6 @@ struct clocksource { #endif }; -extern struct clocksource *clock; /* current clocksource */ - /* * Clock source flags bits:: */ @@ -212,6 +200,7 @@ extern struct clocksource *clock; /* current clocksource */ #define CLOCK_SOURCE_WATCHDOG 0x10 #define CLOCK_SOURCE_VALID_FOR_HRES 0x20 +#define CLOCK_SOURCE_UNSTABLE 0x40 /* simplify initialization of mask field */ #define CLOCKSOURCE_MASK(bits) (cycle_t)((bits) < 64 ? ((1ULL<<(bits))-1) : -1) @@ -268,108 +257,15 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant) } /** - * clocksource_read: - Access the clocksource's current cycle value - * @cs: pointer to clocksource being read - * - * Uses the clocksource to return the current cycle_t value - */ -static inline cycle_t clocksource_read(struct clocksource *cs) -{ - return cs->read(cs); -} - -/** - * clocksource_enable: - enable clocksource - * @cs: pointer to clocksource - * - * Enables the specified clocksource. The clocksource callback - * function should start up the hardware and setup mult and field - * members of struct clocksource to reflect hardware capabilities. - */ -static inline int clocksource_enable(struct clocksource *cs) -{ - int ret = 0; - - if (cs->enable) - ret = cs->enable(cs); - - /* - * The frequency may have changed while the clocksource - * was disabled. If so the code in ->enable() must update - * the mult value to reflect the new frequency. Make sure - * mult_orig follows this change. - */ - cs->mult_orig = cs->mult; - - return ret; -} - -/** - * clocksource_disable: - disable clocksource - * @cs: pointer to clocksource - * - * Disables the specified clocksource. The clocksource callback - * function should power down the now unused hardware block to - * save power. - */ -static inline void clocksource_disable(struct clocksource *cs) -{ - /* - * Save mult_orig in mult so clocksource_enable() can - * restore the value regardless if ->enable() updates - * the value of mult or not. - */ - cs->mult = cs->mult_orig; - - if (cs->disable) - cs->disable(cs); -} - -/** - * cyc2ns - converts clocksource cycles to nanoseconds - * @cs: Pointer to clocksource - * @cycles: Cycles + * clocksource_cyc2ns - converts clocksource cycles to nanoseconds * - * Uses the clocksource and ntp ajdustment to convert cycle_ts to nanoseconds. + * Converts cycles to nanoseconds, using the given mult and shift. * * XXX - This could use some mult_lxl_ll() asm optimization */ -static inline s64 cyc2ns(struct clocksource *cs, cycle_t cycles) -{ - u64 ret = (u64)cycles; - ret = (ret * cs->mult) >> cs->shift; - return ret; -} - -/** - * clocksource_calculate_interval - Calculates a clocksource interval struct - * - * @c: Pointer to clocksource. - * @length_nsec: Desired interval length in nanoseconds. - * - * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment - * pair and interval request. - * - * Unless you're the timekeeping code, you should not be using this! - */ -static inline void clocksource_calculate_interval(struct clocksource *c, - unsigned long length_nsec) +static inline s64 clocksource_cyc2ns(cycle_t cycles, u32 mult, u32 shift) { - u64 tmp; - - /* Do the ns -> cycle conversion first, using original mult */ - tmp = length_nsec; - tmp <<= c->shift; - tmp += c->mult_orig/2; - do_div(tmp, c->mult_orig); - - c->cycle_interval = (cycle_t)tmp; - if (c->cycle_interval == 0) - c->cycle_interval = 1; - - /* Go back from cycles -> shifted ns, this time use ntp adjused mult */ - c->xtime_interval = (u64)c->cycle_interval * c->mult; - c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift; + return ((u64) cycles * mult) >> shift; } @@ -380,6 +276,8 @@ extern void clocksource_touch_watchdog(void); extern struct clocksource* clocksource_get_next(void); extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_resume(void); +extern struct clocksource * __init __weak clocksource_default_clock(void); +extern void clocksource_mark_unstable(struct clocksource *cs); #ifdef CONFIG_GENERIC_TIME_VSYSCALL extern void update_vsyscall(struct timespec *ts, struct clocksource *c); @@ -394,4 +292,6 @@ static inline void update_vsyscall_tz(void) } #endif +extern void timekeeping_notify(struct clocksource *clock); + #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/decompress/generic.h b/include/linux/decompress/generic.h index 6dfb856..0c7111a 100644 --- a/include/linux/decompress/generic.h +++ b/include/linux/decompress/generic.h @@ -1,31 +1,37 @@ #ifndef DECOMPRESS_GENERIC_H #define DECOMPRESS_GENERIC_H -/* Minimal chunksize to be read. - *Bzip2 prefers at least 4096 - *Lzma prefers 0x10000 */ -#define COMPR_IOBUF_SIZE 4096 - typedef int (*decompress_fn) (unsigned char *inbuf, int len, int(*fill)(void*, unsigned int), - int(*writebb)(void*, unsigned int), - unsigned char *output, + int(*flush)(void*, unsigned int), + unsigned char *outbuf, int *posp, void(*error)(char *x)); /* inbuf - input buffer *len - len of pre-read data in inbuf - *fill - function to fill inbuf if empty - *writebb - function to write out outbug + *fill - function to fill inbuf when empty + *flush - function to write out outbuf + *outbuf - output buffer *posp - if non-null, input position (number of bytes read) will be * returned here * - *If len != 0, the inbuf is initialized (with as much data), and fill - *should not be called - *If len = 0, the inbuf is allocated, but empty. Its size is IOBUF_SIZE - *fill should be called (repeatedly...) to read data, at most IOBUF_SIZE + *If len != 0, inbuf should contain all the necessary input data, and fill + *should be NULL + *If len = 0, inbuf can be NULL, in which case the decompressor will allocate + *the input buffer. If inbuf != NULL it must be at least XXX_IOBUF_SIZE bytes. + *fill will be called (repeatedly...) to read data, at most XXX_IOBUF_SIZE + *bytes should be read per call. Replace XXX with the appropriate decompressor + *name, i.e. LZMA_IOBUF_SIZE. + * + *If flush = NULL, outbuf must be large enough to buffer all the expected + *output. If flush != NULL, the output buffer will be allocated by the + *decompressor (outbuf = NULL), and the flush function will be called to + *flush the output buffer at the appropriate time (decompressor and stream + *dependent). */ + /* Utility routine to detect the decompression method */ decompress_fn decompress_method(const unsigned char *inbuf, int len, const char **name); diff --git a/include/linux/fs.h b/include/linux/fs.h index a36ffa5..67888a9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2137,7 +2137,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin); extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin); -extern struct inode * inode_init_always(struct super_block *, struct inode *); +extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void inode_add_to_lists(struct super_block *, struct inode *); extern void iput(struct inode *); @@ -2164,6 +2164,7 @@ extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void destroy_inode(struct inode *); +extern void __destroy_inode(struct inode *); extern struct inode *new_inode(struct super_block *); extern int should_remove_suid(struct dentry *); extern int file_remove_suid(struct file *); diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index 5c093ff..a81170d 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -89,7 +89,9 @@ enum print_line_t { TRACE_TYPE_NO_CONSUME = 3 /* Handled but ask to not consume */ }; - +void tracing_generic_entry_update(struct trace_entry *entry, + unsigned long flags, + int pc); struct ring_buffer_event * trace_current_buffer_lock_reserve(int type, unsigned long len, unsigned long flags, int pc); @@ -119,11 +121,9 @@ struct ftrace_event_call { void *filter; void *mod; -#ifdef CONFIG_EVENT_PROFILE - atomic_t profile_count; - int (*profile_enable)(struct ftrace_event_call *); - void (*profile_disable)(struct ftrace_event_call *); -#endif + atomic_t profile_count; + int (*profile_enable)(struct ftrace_event_call *); + void (*profile_disable)(struct ftrace_event_call *); }; #define MAX_FILTER_PRED 32 diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 4759917..ff037f0 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -91,7 +91,6 @@ enum hrtimer_restart { * @function: timer expiry callback function * @base: pointer to the timer base (per cpu and per clock) * @state: state information (See bit values above) - * @cb_entry: list head to enqueue an expired timer into the callback list * @start_site: timer statistics field to store the site where the timer * was started * @start_comm: timer statistics field to store the name of the process which @@ -108,7 +107,6 @@ struct hrtimer { enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; unsigned long state; - struct list_head cb_entry; #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index acef2a7..ad27c7d 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -82,7 +82,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) -#define IN_DEV_RPFILTER(in_dev) IN_DEV_ANDCONF((in_dev), RP_FILTER) +#define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h index 7964516..15d5903 100644 --- a/include/linux/input/matrix_keypad.h +++ b/include/linux/input/matrix_keypad.h @@ -15,12 +15,13 @@ #define KEY_COL(k) (((k) >> 16) & 0xff) #define KEY_VAL(k) ((k) & 0xffff) +#define MATRIX_SCAN_CODE(row, col, row_shift) (((row) << (row_shift)) + (col)) + /** * struct matrix_keymap_data - keymap for matrix keyboards * @keymap: pointer to array of uint32 values encoded with KEY() macro * representing keymap * @keymap_size: number of entries (initialized) in this keymap - * @max_keymap_size: maximum size of keymap supported by the device * * This structure is supposed to be used by platform code to supply * keymaps to drivers that implement matrix-like keypads/keyboards. @@ -28,14 +29,13 @@ struct matrix_keymap_data { const uint32_t *keymap; unsigned int keymap_size; - unsigned int max_keymap_size; }; /** * struct matrix_keypad_platform_data - platform-dependent keypad data * @keymap_data: pointer to &matrix_keymap_data - * @row_gpios: array of gpio numbers reporesenting rows - * @col_gpios: array of gpio numbers reporesenting colums + * @row_gpios: pointer to array of gpio numbers representing rows + * @col_gpios: pointer to array of gpio numbers reporesenting colums * @num_row_gpios: actual number of row gpios used by device * @num_col_gpios: actual number of col gpios used by device * @col_scan_delay_us: delay, measured in microseconds, that is @@ -48,8 +48,9 @@ struct matrix_keymap_data { struct matrix_keypad_platform_data { const struct matrix_keymap_data *keymap_data; - unsigned int row_gpios[MATRIX_MAX_ROWS]; - unsigned int col_gpios[MATRIX_MAX_COLS]; + const unsigned int *row_gpios; + const unsigned int *col_gpios; + unsigned int num_row_gpios; unsigned int num_col_gpios; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 16713dc..3060bdc 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -110,6 +110,7 @@ struct kvm_memory_slot { struct kvm_kernel_irq_routing_entry { u32 gsi; + u32 type; int (*set)(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int level); union { diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 5675b63..0f32a9b 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -251,7 +251,7 @@ struct mtd_info { static inline struct mtd_info *dev_to_mtd(struct device *dev) { - return dev ? container_of(dev, struct mtd_info, dev) : NULL; + return dev ? dev_get_drvdata(dev) : NULL; } static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd) diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index af6dcb9..b70313d 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -47,6 +47,8 @@ struct mtd_partition { #define MTDPART_SIZ_FULL (0) +struct mtd_info; + int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int); int del_mtd_partitions(struct mtd_info *); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index fdffb41..f6b9024 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -473,7 +473,6 @@ extern int nfs_writepages(struct address_space *, struct writeback_control *); extern int nfs_flush_incompatible(struct file *file, struct page *page); extern int nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int); extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *); -extern void nfs_writedata_release(void *); /* * Try to write back everything synchronously (but check the @@ -488,7 +487,6 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_write_data *nfs_commitdata_alloc(void); extern void nfs_commit_free(struct nfs_write_data *wdata); -extern void nfs_commitdata_release(void *wdata); #else static inline int nfs_commit_inode(struct inode *inode, int how) @@ -507,6 +505,7 @@ nfs_have_writebacks(struct inode *inode) * Allocate nfs_write_data structures */ extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages); +extern void nfs_writedata_free(struct nfs_write_data *); /* * linux/fs/nfs/read.c @@ -515,7 +514,6 @@ extern int nfs_readpage(struct file *, struct page *); extern int nfs_readpages(struct file *, struct address_space *, struct list_head *, unsigned); extern int nfs_readpage_result(struct rpc_task *, struct nfs_read_data *); -extern void nfs_readdata_release(void *data); extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, struct page *); @@ -523,6 +521,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, * Allocate nfs_read_data structures */ extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages); +extern void nfs_readdata_free(struct nfs_read_data *); /* * linux/fs/nfs3proc.c diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 829b94b..b359c4a 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -82,6 +82,12 @@ * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. + * + * NODEMASK_SCRATCH + * When doing above logical AND, OR, XOR, Remap operations the callers tend to + * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, + * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper + * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/kernel.h> @@ -473,4 +479,26 @@ static inline int num_node_state(enum node_states state) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) +/* + * For nodemask scrach area.(See CPUMASK_ALLOC() in cpumask.h) + */ + +#if NODES_SHIFT > 8 /* nodemask_t > 64 bytes */ +#define NODEMASK_ALLOC(x, m) struct x *m = kmalloc(sizeof(*m), GFP_KERNEL) +#define NODEMASK_FREE(m) kfree(m) +#else +#define NODEMASK_ALLOC(x, m) struct x _m, *m = &_m +#define NODEMASK_FREE(m) +#endif + +/* A example struture for using NODEMASK_ALLOC, used in mempolicy. */ +struct nodemask_scratch { + nodemask_t mask1; + nodemask_t mask2; +}; + +#define NODEMASK_SCRATCH(x) NODEMASK_ALLOC(nodemask_scratch, x) +#define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) + + #endif /* __LINUX_NODEMASK_H */ diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h index bd15d7a..b53f700 100644 --- a/include/linux/perf_counter.h +++ b/include/linux/perf_counter.h @@ -115,27 +115,44 @@ enum perf_counter_sample_format { PERF_SAMPLE_TID = 1U << 1, PERF_SAMPLE_TIME = 1U << 2, PERF_SAMPLE_ADDR = 1U << 3, - PERF_SAMPLE_GROUP = 1U << 4, + PERF_SAMPLE_READ = 1U << 4, PERF_SAMPLE_CALLCHAIN = 1U << 5, PERF_SAMPLE_ID = 1U << 6, PERF_SAMPLE_CPU = 1U << 7, PERF_SAMPLE_PERIOD = 1U << 8, PERF_SAMPLE_STREAM_ID = 1U << 9, + PERF_SAMPLE_RAW = 1U << 10, - PERF_SAMPLE_MAX = 1U << 10, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 11, /* non-ABI */ }; /* - * Bits that can be set in attr.read_format to request that - * reads on the counter should return the indicated quantities, - * in increasing order of bit value, after the counter value. + * The format of the data returned by read() on a perf counter fd, + * as specified by attr.read_format: + * + * struct read_format { + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * } && !PERF_FORMAT_GROUP + * + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_ENABLED + * { u64 time_running; } && PERF_FORMAT_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * } cntr[nr]; + * } && PERF_FORMAT_GROUP + * }; */ enum perf_counter_read_format { PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, PERF_FORMAT_ID = 1U << 2, + PERF_FORMAT_GROUP = 1U << 3, - PERF_FORMAT_MAX = 1U << 3, /* non-ABI */ + PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ }; #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ @@ -181,8 +198,9 @@ struct perf_counter_attr { freq : 1, /* use freq, not period */ inherit_stat : 1, /* per task counts */ enable_on_exec : 1, /* next exec enables */ + task : 1, /* trace fork/exit */ - __reserved_1 : 51; + __reserved_1 : 50; __u32 wakeup_events; /* wakeup every n events */ __u32 __reserved_2; @@ -311,6 +329,15 @@ enum perf_event_type { /* * struct { * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * }; + */ + PERF_EVENT_EXIT = 4, + + /* + * struct { + * struct perf_event_header header; * u64 time; * u64 id; * u64 stream_id; @@ -323,6 +350,7 @@ enum perf_event_type { * struct { * struct perf_event_header header; * u32 pid, ppid; + * u32 tid, ptid; * }; */ PERF_EVENT_FORK = 7, @@ -331,10 +359,8 @@ enum perf_event_type { * struct { * struct perf_event_header header; * u32 pid, tid; - * u64 value; - * { u64 time_enabled; } && PERF_FORMAT_ENABLED - * { u64 time_running; } && PERF_FORMAT_RUNNING - * { u64 parent_id; } && PERF_FORMAT_ID + * + * struct read_format values; * }; */ PERF_EVENT_READ = 8, @@ -352,11 +378,24 @@ enum perf_event_type { * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 period; } && PERF_SAMPLE_PERIOD * - * { u64 nr; - * { u64 id, val; } cnt[nr]; } && PERF_SAMPLE_GROUP + * { struct read_format values; } && PERF_SAMPLE_READ * * { u64 nr, * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # + * + * { u32 size; + * char data[size];}&& PERF_SAMPLE_RAW * }; */ PERF_EVENT_SAMPLE = 9, @@ -402,6 +441,11 @@ struct perf_callchain_entry { __u64 ip[PERF_MAX_STACK_DEPTH]; }; +struct perf_raw_record { + u32 size; + void *data; +}; + struct task_struct; /** @@ -670,10 +714,13 @@ struct perf_sample_data { struct pt_regs *regs; u64 addr; u64 period; + struct perf_raw_record *raw; }; extern int perf_counter_overflow(struct perf_counter *counter, int nmi, struct perf_sample_data *data); +extern void perf_counter_output(struct perf_counter *counter, int nmi, + struct perf_sample_data *data); /* * Return 1 for a software counter, 0 for a hardware counter diff --git a/include/linux/time.h b/include/linux/time.h index ea16c1a..256232f 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -101,7 +101,8 @@ extern struct timespec xtime; extern struct timespec wall_to_monotonic; extern seqlock_t xtime_lock; -extern unsigned long read_persistent_clock(void); +extern void read_persistent_clock(struct timespec *ts); +extern void read_boot_clock(struct timespec *ts); extern int update_persistent_clock(struct timespec now); extern int no_sync_cmos_clock __read_mostly; void timekeeping_init(void); @@ -109,6 +110,8 @@ extern int timekeeping_suspended; unsigned long get_seconds(void); struct timespec current_kernel_time(void); +struct timespec __current_kernel_time(void); /* does not hold xtime_lock */ +struct timespec get_monotonic_coarse(void); #define CURRENT_TIME (current_kernel_time()) #define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 }) @@ -147,6 +150,7 @@ extern struct timespec timespec_trunc(struct timespec t, unsigned gran); extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +extern void timekeeping_leap_insert(int leapsecond); struct tms; extern void do_sys_times(struct tms *); @@ -241,6 +245,8 @@ struct itimerval { #define CLOCK_PROCESS_CPUTIME_ID 2 #define CLOCK_THREAD_CPUTIME_ID 3 #define CLOCK_MONOTONIC_RAW 4 +#define CLOCK_REALTIME_COARSE 5 +#define CLOCK_MONOTONIC_COARSE 6 /* * The IDs of various hardware clocks: diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 40f38d8..0c4ee9b 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -144,7 +144,7 @@ struct tty_ldisc_ops { struct tty_ldisc { struct tty_ldisc_ops *ops; - int refcount; + atomic_t users; }; #define TTY_LDISC_MAGIC 0x5403 diff --git a/include/linux/wait.h b/include/linux/wait.h index 6788e1a..cf3c2f5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -77,7 +77,14 @@ struct task_struct; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } -extern void init_waitqueue_head(wait_queue_head_t *q); +extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *); + +#define init_waitqueue_head(q) \ + do { \ + static struct lock_class_key __key; \ + \ + __init_waitqueue_head((q), &__key); \ + } while (0) #ifdef CONFIG_LOCKDEP # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \ diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h index 8007261..c274993 100644 --- a/include/net/bluetooth/rfcomm.h +++ b/include/net/bluetooth/rfcomm.h @@ -355,7 +355,17 @@ struct rfcomm_dev_list_req { }; int rfcomm_dev_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); + +#ifdef CONFIG_BT_RFCOMM_TTY int rfcomm_init_ttys(void); void rfcomm_cleanup_ttys(void); - +#else +static inline int rfcomm_init_ttys(void) +{ + return 0; +} +static inline void rfcomm_cleanup_ttys(void) +{ +} +#endif #endif /* __RFCOMM_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1a21895..d1892d6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -979,6 +979,10 @@ struct cfg80211_ops { * channels at a later time. This can be used for devices which do not * have calibration information gauranteed for frequencies or settings * outside of its regulatory domain. + * @disable_beacon_hints: enable this if your driver needs to ensure that + * passive scan flags and beaconing flags may not be lifted by cfg80211 + * due to regulatory beacon hints. For more information on beacon + * hints read the documenation for regulatory_hint_found_beacon() * @reg_notifier: the driver's regulatory notification callback * @regd: the driver's regulatory domain, if one was requested via * the regulatory_hint() API. This can be used by the driver @@ -1004,6 +1008,7 @@ struct wiphy { bool custom_regulatory; bool strict_regulatory; + bool disable_beacon_hints; enum cfg80211_signal_type signal_type; diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index 1867553..f64fbaa 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -144,6 +144,9 @@ #undef TP_fast_assign #define TP_fast_assign(args...) args +#undef TP_perf_assign +#define TP_perf_assign(args...) + #undef TRACE_EVENT #define TRACE_EVENT(call, proto, args, tstruct, func, print) \ static int \ @@ -345,6 +348,56 @@ static inline int ftrace_get_offsets_##call( \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) +#ifdef CONFIG_EVENT_PROFILE + +/* + * Generate the functions needed for tracepoint perf_counter support. + * + * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later + * + * static int ftrace_profile_enable_<call>(struct ftrace_event_call *event_call) + * { + * int ret = 0; + * + * if (!atomic_inc_return(&event_call->profile_count)) + * ret = register_trace_<call>(ftrace_profile_<call>); + * + * return ret; + * } + * + * static void ftrace_profile_disable_<call>(struct ftrace_event_call *event_call) + * { + * if (atomic_add_negative(-1, &event->call->profile_count)) + * unregister_trace_<call>(ftrace_profile_<call>); + * } + * + */ + +#undef TRACE_EVENT +#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ + \ +static void ftrace_profile_##call(proto); \ + \ +static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \ +{ \ + int ret = 0; \ + \ + if (!atomic_inc_return(&event_call->profile_count)) \ + ret = register_trace_##call(ftrace_profile_##call); \ + \ + return ret; \ +} \ + \ +static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ +{ \ + if (atomic_add_negative(-1, &event_call->profile_count)) \ + unregister_trace_##call(ftrace_profile_##call); \ +} + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#endif + /* * Stage 4 of the trace events. * @@ -447,28 +500,6 @@ static inline int ftrace_get_offsets_##call( \ #define TP_FMT(fmt, args...) fmt "\n", ##args #ifdef CONFIG_EVENT_PROFILE -#define _TRACE_PROFILE(call, proto, args) \ -static void ftrace_profile_##call(proto) \ -{ \ - extern void perf_tpcounter_event(int); \ - perf_tpcounter_event(event_##call.id); \ -} \ - \ -static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \ -{ \ - int ret = 0; \ - \ - if (!atomic_inc_return(&event_call->profile_count)) \ - ret = register_trace_##call(ftrace_profile_##call); \ - \ - return ret; \ -} \ - \ -static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ -{ \ - if (atomic_add_negative(-1, &event_call->profile_count)) \ - unregister_trace_##call(ftrace_profile_##call); \ -} #define _TRACE_PROFILE_INIT(call) \ .profile_count = ATOMIC_INIT(-1), \ @@ -476,7 +507,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ .profile_disable = ftrace_profile_disable_##call, #else -#define _TRACE_PROFILE(call, proto, args) #define _TRACE_PROFILE_INIT(call) #endif @@ -502,7 +532,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\ #undef TRACE_EVENT #define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ -_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args)) \ \ static struct ftrace_event_call event_##call; \ \ @@ -586,6 +615,110 @@ __attribute__((section("_ftrace_events"))) event_##call = { \ #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) -#undef _TRACE_PROFILE +/* + * Define the insertion callback to profile events + * + * The job is very similar to ftrace_raw_event_<call> except that we don't + * insert in the ring buffer but in a perf counter. + * + * static void ftrace_profile_<call>(proto) + * { + * struct ftrace_data_offsets_<call> __maybe_unused __data_offsets; + * struct ftrace_event_call *event_call = &event_<call>; + * extern void perf_tpcounter_event(int, u64, u64, void *, int); + * struct ftrace_raw_##call *entry; + * u64 __addr = 0, __count = 1; + * unsigned long irq_flags; + * int __entry_size; + * int __data_size; + * int pc; + * + * local_save_flags(irq_flags); + * pc = preempt_count(); + * + * __data_size = ftrace_get_offsets_<call>(&__data_offsets, args); + * + * // Below we want to get the aligned size by taking into account + * // the u32 field that will later store the buffer size + * __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32), + * sizeof(u64)); + * __entry_size -= sizeof(u32); + * + * do { + * char raw_data[__entry_size]; <- allocate our sample in the stack + * struct trace_entry *ent; + * + * zero dead bytes from alignment to avoid stack leak to userspace: + * + * *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; + * entry = (struct ftrace_raw_<call> *)raw_data; + * ent = &entry->ent; + * tracing_generic_entry_update(ent, irq_flags, pc); + * ent->type = event_call->id; + * + * <tstruct> <- do some jobs with dynamic arrays + * + * <assign> <- affect our values + * + * perf_tpcounter_event(event_call->id, __addr, __count, entry, + * __entry_size); <- submit them to perf counter + * } while (0); + * + * } + */ + +#ifdef CONFIG_EVENT_PROFILE + +#undef __perf_addr +#define __perf_addr(a) __addr = (a) + +#undef __perf_count +#define __perf_count(c) __count = (c) + +#undef TRACE_EVENT +#define TRACE_EVENT(call, proto, args, tstruct, assign, print) \ +static void ftrace_profile_##call(proto) \ +{ \ + struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\ + struct ftrace_event_call *event_call = &event_##call; \ + extern void perf_tpcounter_event(int, u64, u64, void *, int); \ + struct ftrace_raw_##call *entry; \ + u64 __addr = 0, __count = 1; \ + unsigned long irq_flags; \ + int __entry_size; \ + int __data_size; \ + int pc; \ + \ + local_save_flags(irq_flags); \ + pc = preempt_count(); \ + \ + __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \ + __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\ + sizeof(u64)); \ + __entry_size -= sizeof(u32); \ + \ + do { \ + char raw_data[__entry_size]; \ + struct trace_entry *ent; \ + \ + *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; \ + entry = (struct ftrace_raw_##call *)raw_data; \ + ent = &entry->ent; \ + tracing_generic_entry_update(ent, irq_flags, pc); \ + ent->type = event_call->id; \ + \ + tstruct \ + \ + { assign; } \ + \ + perf_tpcounter_event(event_call->id, __addr, __count, entry,\ + __entry_size); \ + } while (0); \ + \ +} + +#include TRACE_INCLUDE(TRACE_INCLUDE_FILE) +#endif /* CONFIG_EVENT_PROFILE */ + #undef _TRACE_PROFILE_INIT diff --git a/init/Kconfig b/init/Kconfig index cb2c092..3f7e609 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -940,6 +940,7 @@ menu "Performance Counters" config PERF_COUNTERS bool "Kernel Performance Counters" + default y if PROFILING depends on HAVE_PERF_COUNTERS select ANON_INODES help @@ -961,9 +962,17 @@ config PERF_COUNTERS Say Y if unsure. config EVENT_PROFILE - bool "Tracepoint profile sources" + bool "Tracepoint profiling sources" depends on PERF_COUNTERS && EVENT_TRACING default y + help + Allow the use of tracepoints as software performance counters. + + When this is enabled, you can create perf counters based on + tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID + found in debugfs://tracing/events/*/*/id. (The -e/--events + option to the perf tool can parse and interpret symbolic + tracepoints, in the subsystem:tracepoint_name format.) endmenu diff --git a/kernel/fork.c b/kernel/fork.c index 893ab0b..14cf79f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -569,18 +569,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) * the value intact in a core dump, and to save the unnecessary * trouble otherwise. Userland only wants this done for a sys_exit. */ - if (tsk->clear_child_tid - && !(tsk->flags & PF_SIGNALED) - && atomic_read(&mm->mm_users) > 1) { - u32 __user * tidptr = tsk->clear_child_tid; + if (tsk->clear_child_tid) { + if (!(tsk->flags & PF_SIGNALED) && + atomic_read(&mm->mm_users) > 1) { + /* + * We don't check the error code - if userspace has + * not set up a proper pointer then tough luck. + */ + put_user(0, tsk->clear_child_tid); + sys_futex(tsk->clear_child_tid, FUTEX_WAKE, + 1, NULL, NULL, 0); + } tsk->clear_child_tid = NULL; - - /* - * We don't check the error code - if userspace has - * not set up a proper pointer then tough luck. - */ - put_user(0, tidptr); - sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0); } } @@ -1270,6 +1270,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); + perf_counter_fork(p); return p; bad_fork_free_pid: @@ -1411,9 +1412,6 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - if (!(clone_flags & CLONE_THREAD)) - perf_counter_fork(p); - audit_finish_fork(p); tracehook_report_clone(regs, clone_flags, nr, p); diff --git a/kernel/futex.c b/kernel/futex.c index 0672ff8..e18cfbd 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1010,15 +1010,19 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue * q: the futex_q * key: the key of the requeue target futex + * hb: the hash_bucket of the requeue target futex * * During futex_requeue, with requeue_pi=1, it is possible to acquire the * target futex if it is uncontended or via a lock steal. Set the futex_q key * to the requeue target futex so the waiter can detect the wakeup on the right * futex, but remove it from the hb and NULL the rt_waiter so it can detect - * atomic lock acquisition. Must be called with the q->lock_ptr held. + * atomic lock acquisition. Set the q->lock_ptr to the requeue target hb->lock + * to protect access to the pi_state to fixup the owner later. Must be called + * with both q->lock_ptr and hb->lock held. */ static inline -void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key) +void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key, + struct futex_hash_bucket *hb) { drop_futex_key_refs(&q->key); get_futex_key_refs(key); @@ -1030,6 +1034,11 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key) WARN_ON(!q->rt_waiter); q->rt_waiter = NULL; + q->lock_ptr = &hb->lock; +#ifdef CONFIG_DEBUG_PI_LIST + q->list.plist.lock = &hb->lock; +#endif + wake_up_state(q->task, TASK_NORMAL); } @@ -1088,7 +1097,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex, ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task, set_waiters); if (ret == 1) - requeue_pi_wake_futex(top_waiter, key2); + requeue_pi_wake_futex(top_waiter, key2, hb2); return ret; } @@ -1247,8 +1256,15 @@ retry_private: if (!match_futex(&this->key, &key1)) continue; - WARN_ON(!requeue_pi && this->rt_waiter); - WARN_ON(requeue_pi && !this->rt_waiter); + /* + * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always + * be paired with each other and no other futex ops. + */ + if ((requeue_pi && !this->rt_waiter) || + (!requeue_pi && this->rt_waiter)) { + ret = -EINVAL; + break; + } /* * Wake nr_wake waiters. For requeue_pi, if we acquired the @@ -1273,7 +1289,7 @@ retry_private: this->task, 1); if (ret == 1) { /* We got the lock. */ - requeue_pi_wake_futex(this, &key2); + requeue_pi_wake_futex(this, &key2, hb2); continue; } else if (ret) { /* -EDEADLK */ diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index d607a5b..2357165 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -180,7 +180,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, int cmd = op & FUTEX_CMD_MASK; if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI || - cmd == FUTEX_WAIT_BITSET)) { + cmd == FUTEX_WAIT_BITSET || + cmd == FUTEX_WAIT_REQUEUE_PI)) { if (get_compat_timespec(&ts, utime)) return -EFAULT; if (!timespec_valid(&ts)) @@ -191,7 +192,8 @@ asmlinkage long compat_sys_futex(u32 __user *uaddr, int op, u32 val, t = ktime_add_safe(ktime_get(), t); tp = &t; } - if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE) + if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE || + cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP) val2 = (int) (unsigned long) utime; return do_futex(uaddr, op, val, tp, uaddr2, val2, val3); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 49da79a..e2f91ec 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -48,37 +48,6 @@ #include <asm/uaccess.h> -/** - * ktime_get - get the monotonic time in ktime_t format - * - * returns the time in ktime_t format - */ -ktime_t ktime_get(void) -{ - struct timespec now; - - ktime_get_ts(&now); - - return timespec_to_ktime(now); -} -EXPORT_SYMBOL_GPL(ktime_get); - -/** - * ktime_get_real - get the real (wall-) time in ktime_t format - * - * returns the time in ktime_t format - */ -ktime_t ktime_get_real(void) -{ - struct timespec now; - - getnstimeofday(&now); - - return timespec_to_ktime(now); -} - -EXPORT_SYMBOL_GPL(ktime_get_real); - /* * The timer bases: * @@ -106,31 +75,6 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = } }; -/** - * ktime_get_ts - get the monotonic clock in timespec format - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime - * clock and the wall_to_monotonic offset and stores the result - * in normalized timespec format in the variable pointed to by @ts. - */ -void ktime_get_ts(struct timespec *ts) -{ - struct timespec tomono; - unsigned long seq; - - do { - seq = read_seqbegin(&xtime_lock); - getnstimeofday(ts); - tomono = wall_to_monotonic; - - } while (read_seqretry(&xtime_lock, seq)); - - set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, - ts->tv_nsec + tomono.tv_nsec); -} -EXPORT_SYMBOL_GPL(ktime_get_ts); - /* * Get the coarse grained time at the softirq based on xtime and * wall_to_monotonic. @@ -1154,7 +1098,6 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, clock_id = CLOCK_MONOTONIC; timer->base = &cpu_base->clock_base[clock_id]; - INIT_LIST_HEAD(&timer->cb_entry); hrtimer_init_timer_hres(timer); #ifdef CONFIG_TIMER_STATS diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 61c679d..d222515 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -761,7 +761,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action, **action_ptr; - struct task_struct *irqthread; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); @@ -809,9 +808,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) desc->chip->disable(irq); } - irqthread = action->thread; - action->thread = NULL; - spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); @@ -819,12 +815,6 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* Make sure it's not being used on another CPU: */ synchronize_irq(irq); - if (irqthread) { - if (!test_bit(IRQTF_DIED, &action->thread_flags)) - kthread_stop(irqthread); - put_task_struct(irqthread); - } - #ifdef CONFIG_DEBUG_SHIRQ /* * It's a shared IRQ -- the driver ought to be prepared for an IRQ @@ -840,6 +830,13 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) local_irq_restore(flags); } #endif + + if (action->thread) { + if (!test_bit(IRQTF_DIED, &action->thread_flags)) + kthread_stop(action->thread); + put_task_struct(action->thread); + } + return action; } diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index 2f69bee..3fd3019 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -107,8 +107,8 @@ out_unlock: struct irq_desc *move_irq_desc(struct irq_desc *desc, int node) { - /* those all static, do move them */ - if (desc->irq < NR_IRQS_LEGACY) + /* those static or target node is -1, do not move them */ + if (desc->irq < NR_IRQS_LEGACY || node == -1) return desc; if (desc->node != node) diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index d7135aa..e94caa6 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -758,7 +758,8 @@ static int __init lockdep_proc_init(void) &proc_lockdep_stats_operations); #ifdef CONFIG_LOCK_STAT - proc_create("lock_stat", S_IRUSR, NULL, &proc_lock_stat_operations); + proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, + &proc_lock_stat_operations); #endif return 0; diff --git a/kernel/panic.c b/kernel/panic.c index 984b3ec..512ab73 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -301,6 +301,7 @@ int oops_may_print(void) */ void oops_enter(void) { + tracing_off(); /* can't trust the integrity of the kernel anymore: */ debug_locks_off(); do_oops_enter_exit(); diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c index 9509310..534e20d 100644 --- a/kernel/perf_counter.c +++ b/kernel/perf_counter.c @@ -42,6 +42,7 @@ static int perf_overcommit __read_mostly = 1; static atomic_t nr_counters __read_mostly; static atomic_t nr_mmap_counters __read_mostly; static atomic_t nr_comm_counters __read_mostly; +static atomic_t nr_task_counters __read_mostly; /* * perf counter paranoia level: @@ -87,6 +88,7 @@ void __weak hw_perf_disable(void) { barrier(); } void __weak hw_perf_enable(void) { barrier(); } void __weak hw_perf_counter_setup(int cpu) { barrier(); } +void __weak hw_perf_counter_setup_online(int cpu) { barrier(); } int __weak hw_perf_group_sched_in(struct perf_counter *group_leader, @@ -305,6 +307,10 @@ counter_sched_out(struct perf_counter *counter, return; counter->state = PERF_COUNTER_STATE_INACTIVE; + if (counter->pending_disable) { + counter->pending_disable = 0; + counter->state = PERF_COUNTER_STATE_OFF; + } counter->tstamp_stopped = ctx->time; counter->pmu->disable(counter); counter->oncpu = -1; @@ -1103,7 +1109,7 @@ static void perf_counter_sync_stat(struct perf_counter_context *ctx, __perf_counter_sync_stat(counter, next_counter); counter = list_next_entry(counter, event_entry); - next_counter = list_next_entry(counter, event_entry); + next_counter = list_next_entry(next_counter, event_entry); } } @@ -1654,6 +1660,8 @@ static void free_counter(struct perf_counter *counter) atomic_dec(&nr_mmap_counters); if (counter->attr.comm) atomic_dec(&nr_comm_counters); + if (counter->attr.task) + atomic_dec(&nr_task_counters); } if (counter->destroy) @@ -1688,14 +1696,133 @@ static int perf_release(struct inode *inode, struct file *file) return 0; } +static int perf_counter_read_size(struct perf_counter *counter) +{ + int entry = sizeof(u64); /* value */ + int size = 0; + int nr = 1; + + if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + size += sizeof(u64); + + if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + size += sizeof(u64); + + if (counter->attr.read_format & PERF_FORMAT_ID) + entry += sizeof(u64); + + if (counter->attr.read_format & PERF_FORMAT_GROUP) { + nr += counter->group_leader->nr_siblings; + size += sizeof(u64); + } + + size += entry * nr; + + return size; +} + +static u64 perf_counter_read_value(struct perf_counter *counter) +{ + struct perf_counter *child; + u64 total = 0; + + total += perf_counter_read(counter); + list_for_each_entry(child, &counter->child_list, child_list) + total += perf_counter_read(child); + + return total; +} + +static int perf_counter_read_entry(struct perf_counter *counter, + u64 read_format, char __user *buf) +{ + int n = 0, count = 0; + u64 values[2]; + + values[n++] = perf_counter_read_value(counter); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(counter); + + count = n * sizeof(u64); + + if (copy_to_user(buf, values, count)) + return -EFAULT; + + return count; +} + +static int perf_counter_read_group(struct perf_counter *counter, + u64 read_format, char __user *buf) +{ + struct perf_counter *leader = counter->group_leader, *sub; + int n = 0, size = 0, err = -EFAULT; + u64 values[3]; + + values[n++] = 1 + leader->nr_siblings; + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = leader->total_time_enabled + + atomic64_read(&leader->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = leader->total_time_running + + atomic64_read(&leader->child_total_time_running); + } + + size = n * sizeof(u64); + + if (copy_to_user(buf, values, size)) + return -EFAULT; + + err = perf_counter_read_entry(leader, read_format, buf + size); + if (err < 0) + return err; + + size += err; + + list_for_each_entry(sub, &leader->sibling_list, list_entry) { + err = perf_counter_read_entry(counter, read_format, + buf + size); + if (err < 0) + return err; + + size += err; + } + + return size; +} + +static int perf_counter_read_one(struct perf_counter *counter, + u64 read_format, char __user *buf) +{ + u64 values[4]; + int n = 0; + + values[n++] = perf_counter_read_value(counter); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = counter->total_time_enabled + + atomic64_read(&counter->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = counter->total_time_running + + atomic64_read(&counter->child_total_time_running); + } + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(counter); + + if (copy_to_user(buf, values, n * sizeof(u64))) + return -EFAULT; + + return n * sizeof(u64); +} + /* * Read the performance counter - simple non blocking version for now */ static ssize_t perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count) { - u64 values[4]; - int n; + u64 read_format = counter->attr.read_format; + int ret; /* * Return end-of-file for a read on a counter that is in @@ -1705,28 +1832,18 @@ perf_read_hw(struct perf_counter *counter, char __user *buf, size_t count) if (counter->state == PERF_COUNTER_STATE_ERROR) return 0; + if (count < perf_counter_read_size(counter)) + return -ENOSPC; + WARN_ON_ONCE(counter->ctx->parent_ctx); mutex_lock(&counter->child_mutex); - values[0] = perf_counter_read(counter); - n = 1; - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - values[n++] = counter->total_time_enabled + - atomic64_read(&counter->child_total_time_enabled); - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - values[n++] = counter->total_time_running + - atomic64_read(&counter->child_total_time_running); - if (counter->attr.read_format & PERF_FORMAT_ID) - values[n++] = primary_counter_id(counter); + if (read_format & PERF_FORMAT_GROUP) + ret = perf_counter_read_group(counter, read_format, buf); + else + ret = perf_counter_read_one(counter, read_format, buf); mutex_unlock(&counter->child_mutex); - if (count < n * sizeof(u64)) - return -EINVAL; - count = n * sizeof(u64); - - if (copy_to_user(buf, values, count)) - return -EFAULT; - - return count; + return ret; } static ssize_t @@ -2230,7 +2347,7 @@ static void perf_pending_counter(struct perf_pending_entry *entry) if (counter->pending_disable) { counter->pending_disable = 0; - perf_counter_disable(counter); + __perf_counter_disable(counter); } if (counter->pending_wakeup) { @@ -2615,7 +2732,80 @@ static u32 perf_counter_tid(struct perf_counter *counter, struct task_struct *p) return task_pid_nr_ns(p, counter->ns); } -static void perf_counter_output(struct perf_counter *counter, int nmi, +static void perf_output_read_one(struct perf_output_handle *handle, + struct perf_counter *counter) +{ + u64 read_format = counter->attr.read_format; + u64 values[4]; + int n = 0; + + values[n++] = atomic64_read(&counter->count); + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] = counter->total_time_enabled + + atomic64_read(&counter->child_total_time_enabled); + } + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] = counter->total_time_running + + atomic64_read(&counter->child_total_time_running); + } + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(counter); + + perf_output_copy(handle, values, n * sizeof(u64)); +} + +/* + * XXX PERF_FORMAT_GROUP vs inherited counters seems difficult. + */ +static void perf_output_read_group(struct perf_output_handle *handle, + struct perf_counter *counter) +{ + struct perf_counter *leader = counter->group_leader, *sub; + u64 read_format = counter->attr.read_format; + u64 values[5]; + int n = 0; + + values[n++] = 1 + leader->nr_siblings; + + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + values[n++] = leader->total_time_enabled; + + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + values[n++] = leader->total_time_running; + + if (leader != counter) + leader->pmu->read(leader); + + values[n++] = atomic64_read(&leader->count); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(leader); + + perf_output_copy(handle, values, n * sizeof(u64)); + + list_for_each_entry(sub, &leader->sibling_list, list_entry) { + n = 0; + + if (sub != counter) + sub->pmu->read(sub); + + values[n++] = atomic64_read(&sub->count); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_counter_id(sub); + + perf_output_copy(handle, values, n * sizeof(u64)); + } +} + +static void perf_output_read(struct perf_output_handle *handle, + struct perf_counter *counter) +{ + if (counter->attr.read_format & PERF_FORMAT_GROUP) + perf_output_read_group(handle, counter); + else + perf_output_read_one(handle, counter); +} + +void perf_counter_output(struct perf_counter *counter, int nmi, struct perf_sample_data *data) { int ret; @@ -2626,10 +2816,6 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, struct { u32 pid, tid; } tid_entry; - struct { - u64 id; - u64 counter; - } group_entry; struct perf_callchain_entry *callchain = NULL; int callchain_size = 0; u64 time; @@ -2684,10 +2870,8 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, if (sample_type & PERF_SAMPLE_PERIOD) header.size += sizeof(u64); - if (sample_type & PERF_SAMPLE_GROUP) { - header.size += sizeof(u64) + - counter->nr_siblings * sizeof(group_entry); - } + if (sample_type & PERF_SAMPLE_READ) + header.size += perf_counter_read_size(counter); if (sample_type & PERF_SAMPLE_CALLCHAIN) { callchain = perf_callchain(data->regs); @@ -2699,6 +2883,18 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, header.size += sizeof(u64); } + if (sample_type & PERF_SAMPLE_RAW) { + int size = sizeof(u32); + + if (data->raw) + size += data->raw->size; + else + size += sizeof(u32); + + WARN_ON_ONCE(size & (sizeof(u64)-1)); + header.size += size; + } + ret = perf_output_begin(&handle, counter, header.size, nmi, 1); if (ret) return; @@ -2732,26 +2928,8 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, if (sample_type & PERF_SAMPLE_PERIOD) perf_output_put(&handle, data->period); - /* - * XXX PERF_SAMPLE_GROUP vs inherited counters seems difficult. - */ - if (sample_type & PERF_SAMPLE_GROUP) { - struct perf_counter *leader, *sub; - u64 nr = counter->nr_siblings; - - perf_output_put(&handle, nr); - - leader = counter->group_leader; - list_for_each_entry(sub, &leader->sibling_list, list_entry) { - if (sub != counter) - sub->pmu->read(sub); - - group_entry.id = primary_counter_id(sub); - group_entry.counter = atomic64_read(&sub->count); - - perf_output_put(&handle, group_entry); - } - } + if (sample_type & PERF_SAMPLE_READ) + perf_output_read(&handle, counter); if (sample_type & PERF_SAMPLE_CALLCHAIN) { if (callchain) @@ -2762,6 +2940,22 @@ static void perf_counter_output(struct perf_counter *counter, int nmi, } } + if (sample_type & PERF_SAMPLE_RAW) { + if (data->raw) { + perf_output_put(&handle, data->raw->size); + perf_output_copy(&handle, data->raw->data, data->raw->size); + } else { + struct { + u32 size; + u32 data; + } raw = { + .size = sizeof(u32), + .data = 0, + }; + perf_output_put(&handle, raw); + } + } + perf_output_end(&handle); } @@ -2774,8 +2968,6 @@ struct perf_read_event { u32 pid; u32 tid; - u64 value; - u64 format[3]; }; static void @@ -2787,80 +2979,74 @@ perf_counter_read_event(struct perf_counter *counter, .header = { .type = PERF_EVENT_READ, .misc = 0, - .size = sizeof(event) - sizeof(event.format), + .size = sizeof(event) + perf_counter_read_size(counter), }, .pid = perf_counter_pid(counter, task), .tid = perf_counter_tid(counter, task), - .value = atomic64_read(&counter->count), }; - int ret, i = 0; - - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { - event.header.size += sizeof(u64); - event.format[i++] = counter->total_time_enabled; - } - - if (counter->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { - event.header.size += sizeof(u64); - event.format[i++] = counter->total_time_running; - } - - if (counter->attr.read_format & PERF_FORMAT_ID) { - event.header.size += sizeof(u64); - event.format[i++] = primary_counter_id(counter); - } + int ret; ret = perf_output_begin(&handle, counter, event.header.size, 0, 0); if (ret) return; - perf_output_copy(&handle, &event, event.header.size); + perf_output_put(&handle, event); + perf_output_read(&handle, counter); + perf_output_end(&handle); } /* - * fork tracking + * task tracking -- fork/exit + * + * enabled by: attr.comm | attr.mmap | attr.task */ -struct perf_fork_event { - struct task_struct *task; +struct perf_task_event { + struct task_struct *task; + struct perf_counter_context *task_ctx; struct { struct perf_event_header header; u32 pid; u32 ppid; + u32 tid; + u32 ptid; } event; }; -static void perf_counter_fork_output(struct perf_counter *counter, - struct perf_fork_event *fork_event) +static void perf_counter_task_output(struct perf_counter *counter, + struct perf_task_event *task_event) { struct perf_output_handle handle; - int size = fork_event->event.header.size; - struct task_struct *task = fork_event->task; + int size = task_event->event.header.size; + struct task_struct *task = task_event->task; int ret = perf_output_begin(&handle, counter, size, 0, 0); if (ret) return; - fork_event->event.pid = perf_counter_pid(counter, task); - fork_event->event.ppid = perf_counter_pid(counter, task->real_parent); + task_event->event.pid = perf_counter_pid(counter, task); + task_event->event.ppid = perf_counter_pid(counter, current); + + task_event->event.tid = perf_counter_tid(counter, task); + task_event->event.ptid = perf_counter_tid(counter, current); - perf_output_put(&handle, fork_event->event); + perf_output_put(&handle, task_event->event); perf_output_end(&handle); } -static int perf_counter_fork_match(struct perf_counter *counter) +static int perf_counter_task_match(struct perf_counter *counter) { - if (counter->attr.comm || counter->attr.mmap) + if (counter->attr.comm || counter->attr.mmap || counter->attr.task) return 1; return 0; } -static void perf_counter_fork_ctx(struct perf_counter_context *ctx, - struct perf_fork_event *fork_event) +static void perf_counter_task_ctx(struct perf_counter_context *ctx, + struct perf_task_event *task_event) { struct perf_counter *counter; @@ -2869,54 +3055,62 @@ static void perf_counter_fork_ctx(struct perf_counter_context *ctx, rcu_read_lock(); list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) { - if (perf_counter_fork_match(counter)) - perf_counter_fork_output(counter, fork_event); + if (perf_counter_task_match(counter)) + perf_counter_task_output(counter, task_event); } rcu_read_unlock(); } -static void perf_counter_fork_event(struct perf_fork_event *fork_event) +static void perf_counter_task_event(struct perf_task_event *task_event) { struct perf_cpu_context *cpuctx; - struct perf_counter_context *ctx; + struct perf_counter_context *ctx = task_event->task_ctx; cpuctx = &get_cpu_var(perf_cpu_context); - perf_counter_fork_ctx(&cpuctx->ctx, fork_event); + perf_counter_task_ctx(&cpuctx->ctx, task_event); put_cpu_var(perf_cpu_context); rcu_read_lock(); - /* - * doesn't really matter which of the child contexts the - * events ends up in. - */ - ctx = rcu_dereference(current->perf_counter_ctxp); + if (!ctx) + ctx = rcu_dereference(task_event->task->perf_counter_ctxp); if (ctx) - perf_counter_fork_ctx(ctx, fork_event); + perf_counter_task_ctx(ctx, task_event); rcu_read_unlock(); } -void perf_counter_fork(struct task_struct *task) +static void perf_counter_task(struct task_struct *task, + struct perf_counter_context *task_ctx, + int new) { - struct perf_fork_event fork_event; + struct perf_task_event task_event; if (!atomic_read(&nr_comm_counters) && - !atomic_read(&nr_mmap_counters)) + !atomic_read(&nr_mmap_counters) && + !atomic_read(&nr_task_counters)) return; - fork_event = (struct perf_fork_event){ - .task = task, - .event = { + task_event = (struct perf_task_event){ + .task = task, + .task_ctx = task_ctx, + .event = { .header = { - .type = PERF_EVENT_FORK, + .type = new ? PERF_EVENT_FORK : PERF_EVENT_EXIT, .misc = 0, - .size = sizeof(fork_event.event), + .size = sizeof(task_event.event), }, /* .pid */ /* .ppid */ + /* .tid */ + /* .ptid */ }, }; - perf_counter_fork_event(&fork_event); + perf_counter_task_event(&task_event); +} + +void perf_counter_fork(struct task_struct *task) +{ + perf_counter_task(task, NULL, 1); } /* @@ -3305,125 +3499,111 @@ int perf_counter_overflow(struct perf_counter *counter, int nmi, * Generic software counter infrastructure */ -static void perf_swcounter_update(struct perf_counter *counter) +/* + * We directly increment counter->count and keep a second value in + * counter->hw.period_left to count intervals. This period counter + * is kept in the range [-sample_period, 0] so that we can use the + * sign as trigger. + */ + +static u64 perf_swcounter_set_period(struct perf_counter *counter) { struct hw_perf_counter *hwc = &counter->hw; - u64 prev, now; - s64 delta; + u64 period = hwc->last_period; + u64 nr, offset; + s64 old, val; + + hwc->last_period = hwc->sample_period; again: - prev = atomic64_read(&hwc->prev_count); - now = atomic64_read(&hwc->count); - if (atomic64_cmpxchg(&hwc->prev_count, prev, now) != prev) - goto again; + old = val = atomic64_read(&hwc->period_left); + if (val < 0) + return 0; - delta = now - prev; + nr = div64_u64(period + val, period); + offset = nr * period; + val -= offset; + if (atomic64_cmpxchg(&hwc->period_left, old, val) != old) + goto again; - atomic64_add(delta, &counter->count); - atomic64_sub(delta, &hwc->period_left); + return nr; } -static void perf_swcounter_set_period(struct perf_counter *counter) +static void perf_swcounter_overflow(struct perf_counter *counter, + int nmi, struct perf_sample_data *data) { struct hw_perf_counter *hwc = &counter->hw; - s64 left = atomic64_read(&hwc->period_left); - s64 period = hwc->sample_period; + u64 overflow; - if (unlikely(left <= -period)) { - left = period; - atomic64_set(&hwc->period_left, left); - hwc->last_period = period; - } + data->period = counter->hw.last_period; + overflow = perf_swcounter_set_period(counter); - if (unlikely(left <= 0)) { - left += period; - atomic64_add(period, &hwc->period_left); - hwc->last_period = period; - } + if (hwc->interrupts == MAX_INTERRUPTS) + return; - atomic64_set(&hwc->prev_count, -left); - atomic64_set(&hwc->count, -left); + for (; overflow; overflow--) { + if (perf_counter_overflow(counter, nmi, data)) { + /* + * We inhibit the overflow from happening when + * hwc->interrupts == MAX_INTERRUPTS. + */ + break; + } + } } -static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer) +static void perf_swcounter_unthrottle(struct perf_counter *counter) { - enum hrtimer_restart ret = HRTIMER_RESTART; - struct perf_sample_data data; - struct perf_counter *counter; - u64 period; - - counter = container_of(hrtimer, struct perf_counter, hw.hrtimer); - counter->pmu->read(counter); - - data.addr = 0; - data.regs = get_irq_regs(); /* - * In case we exclude kernel IPs or are somehow not in interrupt - * context, provide the next best thing, the user IP. + * Nothing to do, we already reset hwc->interrupts. */ - if ((counter->attr.exclude_kernel || !data.regs) && - !counter->attr.exclude_user) - data.regs = task_pt_regs(current); +} - if (data.regs) { - if (perf_counter_overflow(counter, 0, &data)) - ret = HRTIMER_NORESTART; - } +static void perf_swcounter_add(struct perf_counter *counter, u64 nr, + int nmi, struct perf_sample_data *data) +{ + struct hw_perf_counter *hwc = &counter->hw; - period = max_t(u64, 10000, counter->hw.sample_period); - hrtimer_forward_now(hrtimer, ns_to_ktime(period)); + atomic64_add(nr, &counter->count); - return ret; -} + if (!hwc->sample_period) + return; -static void perf_swcounter_overflow(struct perf_counter *counter, - int nmi, struct perf_sample_data *data) -{ - data->period = counter->hw.last_period; + if (!data->regs) + return; - perf_swcounter_update(counter); - perf_swcounter_set_period(counter); - if (perf_counter_overflow(counter, nmi, data)) - /* soft-disable the counter */ - ; + if (!atomic64_add_negative(nr, &hwc->period_left)) + perf_swcounter_overflow(counter, nmi, data); } static int perf_swcounter_is_counting(struct perf_counter *counter) { - struct perf_counter_context *ctx; - unsigned long flags; - int count; - + /* + * The counter is active, we're good! + */ if (counter->state == PERF_COUNTER_STATE_ACTIVE) return 1; + /* + * The counter is off/error, not counting. + */ if (counter->state != PERF_COUNTER_STATE_INACTIVE) return 0; /* - * If the counter is inactive, it could be just because - * its task is scheduled out, or because it's in a group - * which could not go on the PMU. We want to count in - * the first case but not the second. If the context is - * currently active then an inactive software counter must - * be the second case. If it's not currently active then - * we need to know whether the counter was active when the - * context was last active, which we can determine by - * comparing counter->tstamp_stopped with ctx->time. - * - * We are within an RCU read-side critical section, - * which protects the existence of *ctx. + * The counter is inactive, if the context is active + * we're part of a group that didn't make it on the 'pmu', + * not counting. */ - ctx = counter->ctx; - spin_lock_irqsave(&ctx->lock, flags); - count = 1; - /* Re-check state now we have the lock */ - if (counter->state < PERF_COUNTER_STATE_INACTIVE || - counter->ctx->is_active || - counter->tstamp_stopped < ctx->time) - count = 0; - spin_unlock_irqrestore(&ctx->lock, flags); - return count; + if (counter->ctx->is_active) + return 0; + + /* + * We're inactive and the context is too, this means the + * task is scheduled out, we're counting events that happen + * to us, like migration events. + */ + return 1; } static int perf_swcounter_match(struct perf_counter *counter, @@ -3449,15 +3629,6 @@ static int perf_swcounter_match(struct perf_counter *counter, return 1; } -static void perf_swcounter_add(struct perf_counter *counter, u64 nr, - int nmi, struct perf_sample_data *data) -{ - int neg = atomic64_add_negative(nr, &counter->hw.count); - - if (counter->hw.sample_period && !neg && data->regs) - perf_swcounter_overflow(counter, nmi, data); -} - static void perf_swcounter_ctx_event(struct perf_counter_context *ctx, enum perf_type_id type, u32 event, u64 nr, int nmi, @@ -3536,27 +3707,66 @@ void __perf_swcounter_event(u32 event, u64 nr, int nmi, static void perf_swcounter_read(struct perf_counter *counter) { - perf_swcounter_update(counter); } static int perf_swcounter_enable(struct perf_counter *counter) { - perf_swcounter_set_period(counter); + struct hw_perf_counter *hwc = &counter->hw; + + if (hwc->sample_period) { + hwc->last_period = hwc->sample_period; + perf_swcounter_set_period(counter); + } return 0; } static void perf_swcounter_disable(struct perf_counter *counter) { - perf_swcounter_update(counter); } static const struct pmu perf_ops_generic = { .enable = perf_swcounter_enable, .disable = perf_swcounter_disable, .read = perf_swcounter_read, + .unthrottle = perf_swcounter_unthrottle, }; /* + * hrtimer based swcounter callback + */ + +static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer) +{ + enum hrtimer_restart ret = HRTIMER_RESTART; + struct perf_sample_data data; + struct perf_counter *counter; + u64 period; + + counter = container_of(hrtimer, struct perf_counter, hw.hrtimer); + counter->pmu->read(counter); + + data.addr = 0; + data.regs = get_irq_regs(); + /* + * In case we exclude kernel IPs or are somehow not in interrupt + * context, provide the next best thing, the user IP. + */ + if ((counter->attr.exclude_kernel || !data.regs) && + !counter->attr.exclude_user) + data.regs = task_pt_regs(current); + + if (data.regs) { + if (perf_counter_overflow(counter, 0, &data)) + ret = HRTIMER_NORESTART; + } + + period = max_t(u64, 10000, counter->hw.sample_period); + hrtimer_forward_now(hrtimer, ns_to_ktime(period)); + + return ret; +} + +/* * Software counter: cpu wall time clock */ @@ -3673,17 +3883,24 @@ static const struct pmu perf_ops_task_clock = { }; #ifdef CONFIG_EVENT_PROFILE -void perf_tpcounter_event(int event_id) +void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record, + int entry_size) { + struct perf_raw_record raw = { + .size = entry_size, + .data = record, + }; + struct perf_sample_data data = { .regs = get_irq_regs(), - .addr = 0, + .addr = addr, + .raw = &raw, }; if (!data.regs) data.regs = task_pt_regs(current); - do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, &data); + do_perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, count, 1, &data); } EXPORT_SYMBOL_GPL(perf_tpcounter_event); @@ -3697,6 +3914,14 @@ static void tp_perf_counter_destroy(struct perf_counter *counter) static const struct pmu *tp_perf_counter_init(struct perf_counter *counter) { + /* + * Raw tracepoint data is a severe data leak, only allow root to + * have these. + */ + if ((counter->attr.sample_type & PERF_SAMPLE_RAW) && + !capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + if (ftrace_profile_enable(counter->attr.config)) return NULL; @@ -3830,9 +4055,9 @@ perf_counter_alloc(struct perf_counter_attr *attr, atomic64_set(&hwc->period_left, hwc->sample_period); /* - * we currently do not support PERF_SAMPLE_GROUP on inherited counters + * we currently do not support PERF_FORMAT_GROUP on inherited counters */ - if (attr->inherit && (attr->sample_type & PERF_SAMPLE_GROUP)) + if (attr->inherit && (attr->read_format & PERF_FORMAT_GROUP)) goto done; switch (attr->type) { @@ -3875,6 +4100,8 @@ done: atomic_inc(&nr_mmap_counters); if (counter->attr.comm) atomic_inc(&nr_comm_counters); + if (counter->attr.task) + atomic_inc(&nr_task_counters); } return counter; @@ -4236,8 +4463,10 @@ void perf_counter_exit_task(struct task_struct *child) struct perf_counter_context *child_ctx; unsigned long flags; - if (likely(!child->perf_counter_ctxp)) + if (likely(!child->perf_counter_ctxp)) { + perf_counter_task(child, NULL, 0); return; + } local_irq_save(flags); /* @@ -4262,8 +4491,14 @@ void perf_counter_exit_task(struct task_struct *child) * the counters from it. */ unclone_ctx(child_ctx); - spin_unlock(&child_ctx->lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&child_ctx->lock, flags); + + /* + * Report the task dead after unscheduling the counters so that we + * won't get any samples after PERF_EVENT_EXIT. We can however still + * get a few PERF_EVENT_READ events. + */ + perf_counter_task(child, child_ctx, 0); /* * We can recurse on the same lock type through: @@ -4484,6 +4719,11 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) perf_counter_init_cpu(cpu); break; + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + hw_perf_counter_setup_online(cpu); + break; + case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: perf_counter_exit_cpu(cpu); @@ -4508,6 +4748,8 @@ void __init perf_counter_init(void) { perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); + perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE, + (void *)(long)smp_processor_id()); register_cpu_notifier(&perf_cpu_nb); } diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 18bdde6..12161f7 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -521,11 +521,12 @@ void posix_cpu_timers_exit(struct task_struct *tsk) } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - struct task_cputime cputime; + struct signal_struct *const sig = tsk->signal; - thread_group_cputimer(tsk, &cputime); cleanup_timers(tsk->signal->cpu_timers, - cputime.utime, cputime.stime, cputime.sum_exec_runtime); + cputime_add(tsk->utime, sig->utime), + cputime_add(tsk->stime, sig->stime), + tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 052ec4d..4954407 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -202,6 +202,12 @@ static int no_timer_create(struct k_itimer *new_timer) return -EOPNOTSUPP; } +static int no_nsleep(const clockid_t which_clock, int flags, + struct timespec *tsave, struct timespec __user *rmtp) +{ + return -EOPNOTSUPP; +} + /* * Return nonzero if we know a priori this clockid_t value is bogus. */ @@ -236,6 +242,25 @@ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp) return 0; } + +static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec *tp) +{ + *tp = current_kernel_time(); + return 0; +} + +static int posix_get_monotonic_coarse(clockid_t which_clock, + struct timespec *tp) +{ + *tp = get_monotonic_coarse(); + return 0; +} + +int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp) +{ + *tp = ktime_to_timespec(KTIME_LOW_RES); + return 0; +} /* * Initialize everything, well, just everything in Posix clocks/timers ;) */ @@ -254,11 +279,28 @@ static __init int init_posix_timers(void) .clock_get = posix_get_monotonic_raw, .clock_set = do_posix_clock_nosettime, .timer_create = no_timer_create, + .nsleep = no_nsleep, + }; + struct k_clock clock_realtime_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_realtime_coarse, + .clock_set = do_posix_clock_nosettime, + .timer_create = no_timer_create, + .nsleep = no_nsleep, + }; + struct k_clock clock_monotonic_coarse = { + .clock_getres = posix_get_coarse_res, + .clock_get = posix_get_monotonic_coarse, + .clock_set = do_posix_clock_nosettime, + .timer_create = no_timer_create, + .nsleep = no_nsleep, }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic); register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); + register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse); + register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse); posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof (struct k_itimer), 0, SLAB_PANIC, diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index fcd107a..29bd4ba 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -1039,16 +1039,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) { /* We got the lock for task. */ debug_rt_mutex_lock(lock); - rt_mutex_set_owner(lock, task, 0); - + spin_unlock(&lock->wait_lock); rt_mutex_deadlock_account_lock(lock, task); return 1; } ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock); - if (ret && !waiter->task) { /* * Reset the return value. We might have diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c index e6c2517..d014efb 100644 --- a/kernel/sched_cpupri.c +++ b/kernel/sched_cpupri.c @@ -81,8 +81,21 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) continue; - if (lowest_mask) + if (lowest_mask) { cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + + /* + * We have to ensure that we have at least one bit + * still set in the array, since the map could have + * been concurrently emptied between the first and + * second reads of vec->mask. If we hit this + * condition, simply act as though we never hit this + * priority level and continue on. + */ + if (cpumask_any(lowest_mask) >= nr_cpu_ids) + continue; + } + return 1; } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 9ffb2b2..652e8bd 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -611,9 +611,13 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { #ifdef CONFIG_SCHEDSTATS + struct task_struct *tsk = NULL; + + if (entity_is_task(se)) + tsk = task_of(se); + if (se->sleep_start) { u64 delta = rq_of(cfs_rq)->clock - se->sleep_start; - struct task_struct *tsk = task_of(se); if ((s64)delta < 0) delta = 0; @@ -624,11 +628,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->sleep_start = 0; se->sum_sleep_runtime += delta; - account_scheduler_latency(tsk, delta >> 10, 1); + if (tsk) + account_scheduler_latency(tsk, delta >> 10, 1); } if (se->block_start) { u64 delta = rq_of(cfs_rq)->clock - se->block_start; - struct task_struct *tsk = task_of(se); if ((s64)delta < 0) delta = 0; @@ -639,17 +643,19 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->block_start = 0; se->sum_sleep_runtime += delta; - /* - * Blocking time is in units of nanosecs, so shift by 20 to - * get a milliseconds-range estimation of the amount of - * time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - - profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk), - delta >> 20); + if (tsk) { + /* + * Blocking time is in units of nanosecs, so shift by + * 20 to get a milliseconds-range estimation of the + * amount of time that the task spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + profile_hits(SLEEP_PROFILING, + (void *)get_wchan(tsk), + delta >> 20); + } + account_scheduler_latency(tsk, delta >> 10, 0); } - account_scheduler_latency(tsk, delta >> 10, 0); } #endif } diff --git a/kernel/signal.c b/kernel/signal.c index ccf1cee..64c5dee 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2454,11 +2454,9 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s stack_t oss; int error; - if (uoss) { - oss.ss_sp = (void __user *) current->sas_ss_sp; - oss.ss_size = current->sas_ss_size; - oss.ss_flags = sas_ss_flags(sp); - } + oss.ss_sp = (void __user *) current->sas_ss_sp; + oss.ss_size = current->sas_ss_size; + oss.ss_flags = sas_ss_flags(sp); if (uss) { void __user *ss_sp; @@ -2466,10 +2464,12 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s int ss_flags; error = -EFAULT; - if (!access_ok(VERIFY_READ, uss, sizeof(*uss)) - || __get_user(ss_sp, &uss->ss_sp) - || __get_user(ss_flags, &uss->ss_flags) - || __get_user(ss_size, &uss->ss_size)) + if (!access_ok(VERIFY_READ, uss, sizeof(*uss))) + goto out; + error = __get_user(ss_sp, &uss->ss_sp) | + __get_user(ss_flags, &uss->ss_flags) | + __get_user(ss_size, &uss->ss_size); + if (error) goto out; error = -EPERM; @@ -2501,13 +2501,16 @@ do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long s current->sas_ss_size = ss_size; } + error = 0; if (uoss) { error = -EFAULT; - if (copy_to_user(uoss, &oss, sizeof(oss))) + if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss))) goto out; + error = __put_user(oss.ss_sp, &uoss->ss_sp) | + __put_user(oss.ss_size, &uoss->ss_size) | + __put_user(oss.ss_flags, &uoss->ss_flags); } - error = 0; out: return error; } diff --git a/kernel/smp.c b/kernel/smp.c index ad63d85..94188b8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -57,7 +57,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu) return NOTIFY_BAD; break; -#ifdef CONFIG_CPU_HOTPLUG +#ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 7466cb8..a0af4ff 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -21,7 +21,6 @@ * * TODO WishList: * o Allow clocksource drivers to be unregistered - * o get rid of clocksource_jiffies extern */ #include <linux/clocksource.h> @@ -30,6 +29,7 @@ #include <linux/module.h> #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */ #include <linux/tick.h> +#include <linux/kthread.h> void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, @@ -107,50 +107,32 @@ u64 timecounter_cyc2time(struct timecounter *tc, } EXPORT_SYMBOL(timecounter_cyc2time); -/* XXX - Would like a better way for initializing curr_clocksource */ -extern struct clocksource clocksource_jiffies; - /*[Clocksource internal variables]--------- * curr_clocksource: - * currently selected clocksource. Initialized to clocksource_jiffies. - * next_clocksource: - * pending next selected clocksource. + * currently selected clocksource. * clocksource_list: * linked list with the registered clocksources - * clocksource_lock: - * protects manipulations to curr_clocksource and next_clocksource - * and the clocksource_list + * clocksource_mutex: + * protects manipulations to curr_clocksource and the clocksource_list * override_name: * Name of the user-specified clocksource. */ -static struct clocksource *curr_clocksource = &clocksource_jiffies; -static struct clocksource *next_clocksource; -static struct clocksource *clocksource_override; +static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); -static DEFINE_SPINLOCK(clocksource_lock); +static DEFINE_MUTEX(clocksource_mutex); static char override_name[32]; -static int finished_booting; - -/* clocksource_done_booting - Called near the end of core bootup - * - * Hack to avoid lots of clocksource churn at boot time. - * We use fs_initcall because we want this to start before - * device_initcall but after subsys_initcall. - */ -static int __init clocksource_done_booting(void) -{ - finished_booting = 1; - return 0; -} -fs_initcall(clocksource_done_booting); #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static LIST_HEAD(watchdog_list); static struct clocksource *watchdog; static struct timer_list watchdog_timer; +static struct work_struct watchdog_work; static DEFINE_SPINLOCK(watchdog_lock); static cycle_t watchdog_last; -static unsigned long watchdog_resumed; +static int watchdog_running; + +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); /* * Interval: 0.5sec Threshold: 0.0625s @@ -158,135 +140,247 @@ static unsigned long watchdog_resumed; #define WATCHDOG_INTERVAL (HZ >> 1) #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) -static void clocksource_ratewd(struct clocksource *cs, int64_t delta) +static void clocksource_watchdog_work(struct work_struct *work) { - if (delta > -WATCHDOG_THRESHOLD && delta < WATCHDOG_THRESHOLD) - return; + /* + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); +} +static void __clocksource_unstable(struct clocksource *cs) +{ + cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); + cs->flags |= CLOCK_SOURCE_UNSTABLE; + schedule_work(&watchdog_work); +} + +static void clocksource_unstable(struct clocksource *cs, int64_t delta) +{ printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n", cs->name, delta); - cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); - clocksource_change_rating(cs, 0); - list_del(&cs->wd_list); + __clocksource_unstable(cs); +} + +/** + * clocksource_mark_unstable - mark clocksource unstable via watchdog + * @cs: clocksource to be marked unstable + * + * This function is called instead of clocksource_change_rating from + * cpu hotplug code to avoid a deadlock between the clocksource mutex + * and the cpu hotplug mutex. It defers the update of the clocksource + * to the watchdog thread. + */ +void clocksource_mark_unstable(struct clocksource *cs) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) { + if (list_empty(&cs->wd_list)) + list_add(&cs->wd_list, &watchdog_list); + __clocksource_unstable(cs); + } + spin_unlock_irqrestore(&watchdog_lock, flags); } static void clocksource_watchdog(unsigned long data) { - struct clocksource *cs, *tmp; + struct clocksource *cs; cycle_t csnow, wdnow; int64_t wd_nsec, cs_nsec; - int resumed; + int next_cpu; spin_lock(&watchdog_lock); - - resumed = test_and_clear_bit(0, &watchdog_resumed); + if (!watchdog_running) + goto out; wdnow = watchdog->read(watchdog); - wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask); + wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask, + watchdog->mult, watchdog->shift); watchdog_last = wdnow; - list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { - csnow = cs->read(cs); + list_for_each_entry(cs, &watchdog_list, wd_list) { - if (unlikely(resumed)) { - cs->wd_last = csnow; + /* Clocksource already marked unstable? */ + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + schedule_work(&watchdog_work); continue; } - /* Initialized ? */ + csnow = cs->read(cs); + + /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { - if ((cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && - (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { - cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; - /* - * We just marked the clocksource as - * highres-capable, notify the rest of the - * system as well so that we transition - * into high-res mode: - */ - tick_clock_notify(); - } cs->flags |= CLOCK_SOURCE_WATCHDOG; cs->wd_last = csnow; - } else { - cs_nsec = cyc2ns(cs, (csnow - cs->wd_last) & cs->mask); - cs->wd_last = csnow; - /* Check the delta. Might remove from the list ! */ - clocksource_ratewd(cs, cs_nsec - wd_nsec); + continue; } - } - if (!list_empty(&watchdog_list)) { - /* - * Cycle through CPUs to check if the CPUs stay - * synchronized to each other. - */ - int next_cpu = cpumask_next(raw_smp_processor_id(), - cpu_online_mask); + /* Check the deviation from the watchdog clocksource. */ + cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) & + cs->mask, cs->mult, cs->shift); + cs->wd_last = csnow; + if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { + clocksource_unstable(cs, cs_nsec - wd_nsec); + continue; + } - if (next_cpu >= nr_cpu_ids) - next_cpu = cpumask_first(cpu_online_mask); - watchdog_timer.expires += WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, next_cpu); + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && + (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && + (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + /* + * We just marked the clocksource as highres-capable, + * notify the rest of the system as well so that we + * transition into high-res mode: + */ + tick_clock_notify(); + } } + + /* + * Cycle through CPUs to check if the CPUs stay synchronized + * to each other. + */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + watchdog_timer.expires += WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, next_cpu); +out: spin_unlock(&watchdog_lock); } + +static inline void clocksource_start_watchdog(void) +{ + if (watchdog_running || !watchdog || list_empty(&watchdog_list)) + return; + INIT_WORK(&watchdog_work, clocksource_watchdog_work); + init_timer(&watchdog_timer); + watchdog_timer.function = clocksource_watchdog; + watchdog_last = watchdog->read(watchdog); + watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); + watchdog_running = 1; +} + +static inline void clocksource_stop_watchdog(void) +{ + if (!watchdog_running || (watchdog && !list_empty(&watchdog_list))) + return; + del_timer(&watchdog_timer); + watchdog_running = 0; +} + +static inline void clocksource_reset_watchdog(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &watchdog_list, wd_list) + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; +} + static void clocksource_resume_watchdog(void) { - set_bit(0, &watchdog_resumed); + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + clocksource_reset_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); } -static void clocksource_check_watchdog(struct clocksource *cs) +static void clocksource_enqueue_watchdog(struct clocksource *cs) { - struct clocksource *cse; unsigned long flags; spin_lock_irqsave(&watchdog_lock, flags); if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { - int started = !list_empty(&watchdog_list); - + /* cs is a clocksource to be watched. */ list_add(&cs->wd_list, &watchdog_list); - if (!started && watchdog) { - watchdog_last = watchdog->read(watchdog); - watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, - cpumask_first(cpu_online_mask)); - } + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; } else { + /* cs is a watchdog. */ if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; - + /* Pick the best watchdog. */ if (!watchdog || cs->rating > watchdog->rating) { - if (watchdog) - del_timer(&watchdog_timer); watchdog = cs; - init_timer(&watchdog_timer); - watchdog_timer.function = clocksource_watchdog; - /* Reset watchdog cycles */ - list_for_each_entry(cse, &watchdog_list, wd_list) - cse->flags &= ~CLOCK_SOURCE_WATCHDOG; - /* Start if list is not empty */ - if (!list_empty(&watchdog_list)) { - watchdog_last = watchdog->read(watchdog); - watchdog_timer.expires = - jiffies + WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, - cpumask_first(cpu_online_mask)); - } + clocksource_reset_watchdog(); + } + } + /* Check if the watchdog timer needs to be started. */ + clocksource_start_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_dequeue_watchdog(struct clocksource *cs) +{ + struct clocksource *tmp; + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + } else if (cs == watchdog) { + /* Reset watchdog cycles */ + clocksource_reset_watchdog(); + /* Current watchdog is removed. Find an alternative. */ + watchdog = NULL; + list_for_each_entry(tmp, &clocksource_list, list) { + if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY) + continue; + if (!watchdog || tmp->rating > watchdog->rating) + watchdog = tmp; } } + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static int clocksource_watchdog_kthread(void *data) +{ + struct clocksource *cs, *tmp; + unsigned long flags; + LIST_HEAD(unstable); + + mutex_lock(&clocksource_mutex); + spin_lock_irqsave(&watchdog_lock, flags); + list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + list_del_init(&cs->wd_list); + list_add(&cs->wd_list, &unstable); + } + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); + + /* Needs to be done outside of watchdog lock */ + list_for_each_entry_safe(cs, tmp, &unstable, wd_list) { + list_del_init(&cs->wd_list); + __clocksource_change_rating(cs, 0); + } + mutex_unlock(&clocksource_mutex); + return 0; } -#else -static void clocksource_check_watchdog(struct clocksource *cs) + +#else /* CONFIG_CLOCKSOURCE_WATCHDOG */ + +static void clocksource_enqueue_watchdog(struct clocksource *cs) { if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; } +static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -#endif + +#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ /** * clocksource_resume - resume the clocksource(s) @@ -294,18 +388,16 @@ static inline void clocksource_resume_watchdog(void) { } void clocksource_resume(void) { struct clocksource *cs; - unsigned long flags; - spin_lock_irqsave(&clocksource_lock, flags); + mutex_lock(&clocksource_mutex); - list_for_each_entry(cs, &clocksource_list, list) { + list_for_each_entry(cs, &clocksource_list, list) if (cs->resume) cs->resume(); - } clocksource_resume_watchdog(); - spin_unlock_irqrestore(&clocksource_lock, flags); + mutex_unlock(&clocksource_mutex); } /** @@ -320,75 +412,88 @@ void clocksource_touch_watchdog(void) clocksource_resume_watchdog(); } +#ifdef CONFIG_GENERIC_TIME + +static int finished_booting; + /** - * clocksource_get_next - Returns the selected clocksource + * clocksource_select - Select the best clocksource available + * + * Private function. Must hold clocksource_mutex when called. * + * Select the clocksource with the best rating, or the clocksource, + * which is selected by userspace override. */ -struct clocksource *clocksource_get_next(void) +static void clocksource_select(void) { - unsigned long flags; + struct clocksource *best, *cs; - spin_lock_irqsave(&clocksource_lock, flags); - if (next_clocksource && finished_booting) { - curr_clocksource = next_clocksource; - next_clocksource = NULL; + if (!finished_booting || list_empty(&clocksource_list)) + return; + /* First clocksource on the list has the best rating. */ + best = list_first_entry(&clocksource_list, struct clocksource, list); + /* Check for the override clocksource. */ + list_for_each_entry(cs, &clocksource_list, list) { + if (strcmp(cs->name, override_name) != 0) + continue; + /* + * Check to make sure we don't switch to a non-highres + * capable clocksource if the tick code is in oneshot + * mode (highres or nohz) + */ + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && + tick_oneshot_mode_active()) { + /* Override clocksource cannot be used. */ + printk(KERN_WARNING "Override clocksource %s is not " + "HRT compatible. Cannot switch while in " + "HRT/NOHZ mode\n", cs->name); + override_name[0] = 0; + } else + /* Override clocksource can be used. */ + best = cs; + break; + } + if (curr_clocksource != best) { + printk(KERN_INFO "Switching to clocksource %s\n", best->name); + curr_clocksource = best; + timekeeping_notify(curr_clocksource); } - spin_unlock_irqrestore(&clocksource_lock, flags); - - return curr_clocksource; } -/** - * select_clocksource - Selects the best registered clocksource. - * - * Private function. Must hold clocksource_lock when called. +/* + * clocksource_done_booting - Called near the end of core bootup * - * Select the clocksource with the best rating, or the clocksource, - * which is selected by userspace override. + * Hack to avoid lots of clocksource churn at boot time. + * We use fs_initcall because we want this to start before + * device_initcall but after subsys_initcall. */ -static struct clocksource *select_clocksource(void) +static int __init clocksource_done_booting(void) { - struct clocksource *next; - - if (list_empty(&clocksource_list)) - return NULL; + finished_booting = 1; + clocksource_select(); + return 0; +} +fs_initcall(clocksource_done_booting); - if (clocksource_override) - next = clocksource_override; - else - next = list_entry(clocksource_list.next, struct clocksource, - list); +#else /* CONFIG_GENERIC_TIME */ - if (next == curr_clocksource) - return NULL; +static inline void clocksource_select(void) { } - return next; -} +#endif /* * Enqueue the clocksource sorted by rating */ -static int clocksource_enqueue(struct clocksource *c) +static void clocksource_enqueue(struct clocksource *cs) { - struct list_head *tmp, *entry = &clocksource_list; - - list_for_each(tmp, &clocksource_list) { - struct clocksource *cs; + struct list_head *entry = &clocksource_list; + struct clocksource *tmp; - cs = list_entry(tmp, struct clocksource, list); - if (cs == c) - return -EBUSY; + list_for_each_entry(tmp, &clocksource_list, list) /* Keep track of the place, where to insert */ - if (cs->rating >= c->rating) - entry = tmp; - } - list_add(&c->list, entry); - - if (strlen(c->name) == strlen(override_name) && - !strcmp(c->name, override_name)) - clocksource_override = c; - - return 0; + if (tmp->rating >= cs->rating) + entry = &tmp->list; + list_add(&cs->list, entry); } /** @@ -397,52 +502,48 @@ static int clocksource_enqueue(struct clocksource *c) * * Returns -EBUSY if registration fails, zero otherwise. */ -int clocksource_register(struct clocksource *c) +int clocksource_register(struct clocksource *cs) { - unsigned long flags; - int ret; - - spin_lock_irqsave(&clocksource_lock, flags); - ret = clocksource_enqueue(c); - if (!ret) - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); - if (!ret) - clocksource_check_watchdog(c); - return ret; + mutex_lock(&clocksource_mutex); + clocksource_enqueue(cs); + clocksource_select(); + clocksource_enqueue_watchdog(cs); + mutex_unlock(&clocksource_mutex); + return 0; } EXPORT_SYMBOL(clocksource_register); +static void __clocksource_change_rating(struct clocksource *cs, int rating) +{ + list_del(&cs->list); + cs->rating = rating; + clocksource_enqueue(cs); + clocksource_select(); +} + /** * clocksource_change_rating - Change the rating of a registered clocksource - * */ void clocksource_change_rating(struct clocksource *cs, int rating) { - unsigned long flags; - - spin_lock_irqsave(&clocksource_lock, flags); - list_del(&cs->list); - cs->rating = rating; - clocksource_enqueue(cs); - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); + mutex_lock(&clocksource_mutex); + __clocksource_change_rating(cs, rating); + mutex_unlock(&clocksource_mutex); } +EXPORT_SYMBOL(clocksource_change_rating); /** * clocksource_unregister - remove a registered clocksource */ void clocksource_unregister(struct clocksource *cs) { - unsigned long flags; - - spin_lock_irqsave(&clocksource_lock, flags); + mutex_lock(&clocksource_mutex); + clocksource_dequeue_watchdog(cs); list_del(&cs->list); - if (clocksource_override == cs) - clocksource_override = NULL; - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); + clocksource_select(); + mutex_unlock(&clocksource_mutex); } +EXPORT_SYMBOL(clocksource_unregister); #ifdef CONFIG_SYSFS /** @@ -458,9 +559,9 @@ sysfs_show_current_clocksources(struct sys_device *dev, { ssize_t count = 0; - spin_lock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); - spin_unlock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); return count; } @@ -478,9 +579,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t count) { - struct clocksource *ovr = NULL; size_t ret = count; - int len; /* strings from sysfs write are not 0 terminated! */ if (count >= sizeof(override_name)) @@ -490,44 +589,14 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, if (buf[count-1] == '\n') count--; - spin_lock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); if (count > 0) memcpy(override_name, buf, count); override_name[count] = 0; + clocksource_select(); - len = strlen(override_name); - if (len) { - struct clocksource *cs; - - ovr = clocksource_override; - /* try to select it: */ - list_for_each_entry(cs, &clocksource_list, list) { - if (strlen(cs->name) == len && - !strcmp(cs->name, override_name)) - ovr = cs; - } - } - - /* - * Check to make sure we don't switch to a non-highres capable - * clocksource if the tick code is in oneshot mode (highres or nohz) - */ - if (tick_oneshot_mode_active() && ovr && - !(ovr->flags & CLOCK_SOURCE_VALID_FOR_HRES)) { - printk(KERN_WARNING "%s clocksource is not HRT compatible. " - "Cannot switch while in HRT/NOHZ mode\n", ovr->name); - ovr = NULL; - override_name[0] = 0; - } - - /* Reselect, when the override name has changed */ - if (ovr != clocksource_override) { - clocksource_override = ovr; - next_clocksource = select_clocksource(); - } - - spin_unlock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); return ret; } @@ -547,7 +616,7 @@ sysfs_show_available_clocksources(struct sys_device *dev, struct clocksource *src; ssize_t count = 0; - spin_lock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); list_for_each_entry(src, &clocksource_list, list) { /* * Don't show non-HRES clocksource if the tick code is @@ -559,7 +628,7 @@ sysfs_show_available_clocksources(struct sys_device *dev, max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "%s ", src->name); } - spin_unlock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); count += snprintf(buf + count, max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n"); @@ -614,11 +683,10 @@ device_initcall(init_clocksource_sysfs); */ static int __init boot_override_clocksource(char* str) { - unsigned long flags; - spin_lock_irqsave(&clocksource_lock, flags); + mutex_lock(&clocksource_mutex); if (str) strlcpy(override_name, str, sizeof(override_name)); - spin_unlock_irqrestore(&clocksource_lock, flags); + mutex_unlock(&clocksource_mutex); return 1; } diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index c3f6c30..5404a84 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -61,7 +61,6 @@ struct clocksource clocksource_jiffies = { .read = jiffies_read, .mask = 0xffffffff, /*32bits*/ .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ - .mult_orig = NSEC_PER_JIFFY << JIFFIES_SHIFT, .shift = JIFFIES_SHIFT, }; @@ -71,3 +70,8 @@ static int __init init_jiffies_clocksource(void) } core_initcall(init_jiffies_clocksource); + +struct clocksource * __init __weak clocksource_default_clock(void) +{ + return &clocksource_jiffies; +} diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 7fc6437..4800f93 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -194,8 +194,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) case TIME_OK: break; case TIME_INS: - xtime.tv_sec--; - wall_to_monotonic.tv_sec++; + timekeeping_leap_insert(-1); time_state = TIME_OOP; printk(KERN_NOTICE "Clock: inserting leap second 23:59:60 UTC\n"); @@ -203,9 +202,8 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) res = HRTIMER_RESTART; break; case TIME_DEL: - xtime.tv_sec++; + timekeeping_leap_insert(1); time_tai--; - wall_to_monotonic.tv_sec--; time_state = TIME_WAIT; printk(KERN_NOTICE "Clock: deleting leap second 23:59:59 UTC\n"); @@ -219,7 +217,6 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) time_state = TIME_OK; break; } - update_vsyscall(&xtime, clock); write_sequnlock(&xtime_lock); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e8c77d9..fb0f46f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -18,7 +18,117 @@ #include <linux/jiffies.h> #include <linux/time.h> #include <linux/tick.h> +#include <linux/stop_machine.h> + +/* Structure holding internal timekeeping values. */ +struct timekeeper { + /* Current clocksource used for timekeeping. */ + struct clocksource *clock; + /* The shift value of the current clocksource. */ + int shift; + + /* Number of clock cycles in one NTP interval. */ + cycle_t cycle_interval; + /* Number of clock shifted nano seconds in one NTP interval. */ + u64 xtime_interval; + /* Raw nano seconds accumulated per NTP interval. */ + u32 raw_interval; + + /* Clock shifted nano seconds remainder not stored in xtime.tv_nsec. */ + u64 xtime_nsec; + /* Difference between accumulated time and NTP time in ntp + * shifted nano seconds. */ + s64 ntp_error; + /* Shift conversion between clock shifted nano seconds and + * ntp shifted nano seconds. */ + int ntp_error_shift; + /* NTP adjusted clock multiplier */ + u32 mult; +}; + +struct timekeeper timekeeper; + +/** + * timekeeper_setup_internals - Set up internals to use clocksource clock. + * + * @clock: Pointer to clocksource. + * + * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment + * pair and interval request. + * + * Unless you're the timekeeping code, you should not be using this! + */ +static void timekeeper_setup_internals(struct clocksource *clock) +{ + cycle_t interval; + u64 tmp; + + timekeeper.clock = clock; + clock->cycle_last = clock->read(clock); + /* Do the ns -> cycle conversion first, using original mult */ + tmp = NTP_INTERVAL_LENGTH; + tmp <<= clock->shift; + tmp += clock->mult/2; + do_div(tmp, clock->mult); + if (tmp == 0) + tmp = 1; + + interval = (cycle_t) tmp; + timekeeper.cycle_interval = interval; + + /* Go back from cycles -> shifted ns */ + timekeeper.xtime_interval = (u64) interval * clock->mult; + timekeeper.raw_interval = + ((u64) interval * clock->mult) >> clock->shift; + + timekeeper.xtime_nsec = 0; + timekeeper.shift = clock->shift; + + timekeeper.ntp_error = 0; + timekeeper.ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; + + /* + * The timekeeper keeps its own mult values for the currently + * active clocksource. These value will be adjusted via NTP + * to counteract clock drifting. + */ + timekeeper.mult = clock->mult; +} + +/* Timekeeper helper functions. */ +static inline s64 timekeeping_get_ns(void) +{ + cycle_t cycle_now, cycle_delta; + struct clocksource *clock; + + /* read clocksource: */ + clock = timekeeper.clock; + cycle_now = clock->read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* return delta convert to nanoseconds using ntp adjusted mult. */ + return clocksource_cyc2ns(cycle_delta, timekeeper.mult, + timekeeper.shift); +} + +static inline s64 timekeeping_get_ns_raw(void) +{ + cycle_t cycle_now, cycle_delta; + struct clocksource *clock; + + /* read clocksource: */ + clock = timekeeper.clock; + cycle_now = clock->read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* return delta convert to nanoseconds using ntp adjusted mult. */ + return clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); +} /* * This read-write spinlock protects us from races in SMP while @@ -44,7 +154,12 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); */ struct timespec xtime __attribute__ ((aligned (16))); struct timespec wall_to_monotonic __attribute__ ((aligned (16))); -static unsigned long total_sleep_time; /* seconds */ +static struct timespec total_sleep_time; + +/* + * The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. + */ +struct timespec raw_time; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -56,35 +171,44 @@ void update_xtime_cache(u64 nsec) timespec_add_ns(&xtime_cache, nsec); } -struct clocksource *clock; - +/* must hold xtime_lock */ +void timekeeping_leap_insert(int leapsecond) +{ + xtime.tv_sec += leapsecond; + wall_to_monotonic.tv_sec -= leapsecond; + update_vsyscall(&xtime, timekeeper.clock); +} #ifdef CONFIG_GENERIC_TIME + /** - * clocksource_forward_now - update clock to the current time + * timekeeping_forward_now - update clock to the current time * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ -static void clocksource_forward_now(void) +static void timekeeping_forward_now(void) { cycle_t cycle_now, cycle_delta; + struct clocksource *clock; s64 nsec; - cycle_now = clocksource_read(clock); + clock = timekeeper.clock; + cycle_now = clock->read(clock); cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; clock->cycle_last = cycle_now; - nsec = cyc2ns(clock, cycle_delta); + nsec = clocksource_cyc2ns(cycle_delta, timekeeper.mult, + timekeeper.shift); /* If arch requires, add in gettimeoffset() */ nsec += arch_gettimeoffset(); timespec_add_ns(&xtime, nsec); - nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; - clock->raw_time.tv_nsec += nsec; + nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift); + timespec_add_ns(&raw_time, nsec); } /** @@ -95,7 +219,6 @@ static void clocksource_forward_now(void) */ void getnstimeofday(struct timespec *ts) { - cycle_t cycle_now, cycle_delta; unsigned long seq; s64 nsecs; @@ -105,15 +228,7 @@ void getnstimeofday(struct timespec *ts) seq = read_seqbegin(&xtime_lock); *ts = xtime; - - /* read clocksource: */ - cycle_now = clocksource_read(clock); - - /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - - /* convert to nanoseconds: */ - nsecs = cyc2ns(clock, cycle_delta); + nsecs = timekeeping_get_ns(); /* If arch requires, add in gettimeoffset() */ nsecs += arch_gettimeoffset(); @@ -125,6 +240,57 @@ void getnstimeofday(struct timespec *ts) EXPORT_SYMBOL(getnstimeofday); +ktime_t ktime_get(void) +{ + unsigned int seq; + s64 secs, nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqbegin(&xtime_lock); + secs = xtime.tv_sec + wall_to_monotonic.tv_sec; + nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec; + nsecs += timekeeping_get_ns(); + + } while (read_seqretry(&xtime_lock, seq)); + /* + * Use ktime_set/ktime_add_ns to create a proper ktime on + * 32-bit architectures without CONFIG_KTIME_SCALAR. + */ + return ktime_add_ns(ktime_set(secs, 0), nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get); + +/** + * ktime_get_ts - get the monotonic clock in timespec format + * @ts: pointer to timespec variable + * + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by @ts. + */ +void ktime_get_ts(struct timespec *ts) +{ + struct timespec tomono; + unsigned int seq; + s64 nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqbegin(&xtime_lock); + *ts = xtime; + tomono = wall_to_monotonic; + nsecs = timekeeping_get_ns(); + + } while (read_seqretry(&xtime_lock, seq)); + + set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, + ts->tv_nsec + tomono.tv_nsec + nsecs); +} +EXPORT_SYMBOL_GPL(ktime_get_ts); + /** * do_gettimeofday - Returns the time of day in a timeval * @tv: pointer to the timeval to be set @@ -157,7 +323,7 @@ int do_settimeofday(struct timespec *tv) write_seqlock_irqsave(&xtime_lock, flags); - clocksource_forward_now(); + timekeeping_forward_now(); ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec; ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec; @@ -167,10 +333,10 @@ int do_settimeofday(struct timespec *tv) update_xtime_cache(0); - clock->error = 0; + timekeeper.ntp_error = 0; ntp_clear(); - update_vsyscall(&xtime, clock); + update_vsyscall(&xtime, timekeeper.clock); write_sequnlock_irqrestore(&xtime_lock, flags); @@ -187,44 +353,97 @@ EXPORT_SYMBOL(do_settimeofday); * * Accumulates current time interval and initializes new clocksource */ -static void change_clocksource(void) +static int change_clocksource(void *data) { struct clocksource *new, *old; - new = clocksource_get_next(); + new = (struct clocksource *) data; + + timekeeping_forward_now(); + if (!new->enable || new->enable(new) == 0) { + old = timekeeper.clock; + timekeeper_setup_internals(new); + if (old->disable) + old->disable(old); + } + return 0; +} - if (clock == new) +/** + * timekeeping_notify - Install a new clock source + * @clock: pointer to the clock source + * + * This function is called from clocksource.c after a new, better clock + * source has been registered. The caller holds the clocksource_mutex. + */ +void timekeeping_notify(struct clocksource *clock) +{ + if (timekeeper.clock == clock) return; + stop_machine(change_clocksource, clock, NULL); + tick_clock_notify(); +} - clocksource_forward_now(); +#else /* GENERIC_TIME */ - if (clocksource_enable(new)) - return; +static inline void timekeeping_forward_now(void) { } - new->raw_time = clock->raw_time; - old = clock; - clock = new; - clocksource_disable(old); +/** + * ktime_get - get the monotonic time in ktime_t format + * + * returns the time in ktime_t format + */ +ktime_t ktime_get(void) +{ + struct timespec now; - clock->cycle_last = 0; - clock->cycle_last = clocksource_read(clock); - clock->error = 0; - clock->xtime_nsec = 0; - clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); + ktime_get_ts(&now); - tick_clock_notify(); + return timespec_to_ktime(now); +} +EXPORT_SYMBOL_GPL(ktime_get); - /* - * We're holding xtime lock and waking up klogd would deadlock - * us on enqueue. So no printing! - printk(KERN_INFO "Time: %s clocksource has been installed.\n", - clock->name); - */ +/** + * ktime_get_ts - get the monotonic clock in timespec format + * @ts: pointer to timespec variable + * + * The function calculates the monotonic clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by @ts. + */ +void ktime_get_ts(struct timespec *ts) +{ + struct timespec tomono; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + getnstimeofday(ts); + tomono = wall_to_monotonic; + + } while (read_seqretry(&xtime_lock, seq)); + + set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec, + ts->tv_nsec + tomono.tv_nsec); } -#else -static inline void clocksource_forward_now(void) { } -static inline void change_clocksource(void) { } -#endif +EXPORT_SYMBOL_GPL(ktime_get_ts); + +#endif /* !GENERIC_TIME */ + +/** + * ktime_get_real - get the real (wall-) time in ktime_t format + * + * returns the time in ktime_t format + */ +ktime_t ktime_get_real(void) +{ + struct timespec now; + + getnstimeofday(&now); + + return timespec_to_ktime(now); +} +EXPORT_SYMBOL_GPL(ktime_get_real); /** * getrawmonotonic - Returns the raw monotonic time in a timespec @@ -236,21 +455,11 @@ void getrawmonotonic(struct timespec *ts) { unsigned long seq; s64 nsecs; - cycle_t cycle_now, cycle_delta; do { seq = read_seqbegin(&xtime_lock); - - /* read clocksource: */ - cycle_now = clocksource_read(clock); - - /* calculate the delta since the last update_wall_time: */ - cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; - - /* convert to nanoseconds: */ - nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; - - *ts = clock->raw_time; + nsecs = timekeeping_get_ns_raw(); + *ts = raw_time; } while (read_seqretry(&xtime_lock, seq)); @@ -270,7 +479,7 @@ int timekeeping_valid_for_hres(void) do { seq = read_seqbegin(&xtime_lock); - ret = clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; + ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqretry(&xtime_lock, seq)); @@ -278,17 +487,33 @@ int timekeeping_valid_for_hres(void) } /** - * read_persistent_clock - Return time in seconds from the persistent clock. + * read_persistent_clock - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. - * Returns seconds from epoch using the battery backed persistent clock. - * Returns zero if unsupported. + * Reads the time from the battery backed persistent clock. + * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ -unsigned long __attribute__((weak)) read_persistent_clock(void) +void __attribute__((weak)) read_persistent_clock(struct timespec *ts) { - return 0; + ts->tv_sec = 0; + ts->tv_nsec = 0; +} + +/** + * read_boot_clock - Return time of the system start. + * + * Weak dummy function for arches that do not yet support it. + * Function to read the exact time the system has been started. + * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. + * + * XXX - Do be sure to remove it once all arches implement it. + */ +void __attribute__((weak)) read_boot_clock(struct timespec *ts) +{ + ts->tv_sec = 0; + ts->tv_nsec = 0; } /* @@ -296,29 +521,40 @@ unsigned long __attribute__((weak)) read_persistent_clock(void) */ void __init timekeeping_init(void) { + struct clocksource *clock; unsigned long flags; - unsigned long sec = read_persistent_clock(); + struct timespec now, boot; + + read_persistent_clock(&now); + read_boot_clock(&boot); write_seqlock_irqsave(&xtime_lock, flags); ntp_init(); - clock = clocksource_get_next(); - clocksource_enable(clock); - clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); - clock->cycle_last = clocksource_read(clock); - - xtime.tv_sec = sec; - xtime.tv_nsec = 0; + clock = clocksource_default_clock(); + if (clock->enable) + clock->enable(clock); + timekeeper_setup_internals(clock); + + xtime.tv_sec = now.tv_sec; + xtime.tv_nsec = now.tv_nsec; + raw_time.tv_sec = 0; + raw_time.tv_nsec = 0; + if (boot.tv_sec == 0 && boot.tv_nsec == 0) { + boot.tv_sec = xtime.tv_sec; + boot.tv_nsec = xtime.tv_nsec; + } set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); + -boot.tv_sec, -boot.tv_nsec); update_xtime_cache(0); - total_sleep_time = 0; + total_sleep_time.tv_sec = 0; + total_sleep_time.tv_nsec = 0; write_sequnlock_irqrestore(&xtime_lock, flags); } /* time in seconds when suspend began */ -static unsigned long timekeeping_suspend_time; +static struct timespec timekeeping_suspend_time; /** * timekeeping_resume - Resumes the generic timekeeping subsystem. @@ -331,24 +567,24 @@ static unsigned long timekeeping_suspend_time; static int timekeeping_resume(struct sys_device *dev) { unsigned long flags; - unsigned long now = read_persistent_clock(); + struct timespec ts; + + read_persistent_clock(&ts); clocksource_resume(); write_seqlock_irqsave(&xtime_lock, flags); - if (now && (now > timekeeping_suspend_time)) { - unsigned long sleep_length = now - timekeeping_suspend_time; - - xtime.tv_sec += sleep_length; - wall_to_monotonic.tv_sec -= sleep_length; - total_sleep_time += sleep_length; + if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) { + ts = timespec_sub(ts, timekeeping_suspend_time); + xtime = timespec_add_safe(xtime, ts); + wall_to_monotonic = timespec_sub(wall_to_monotonic, ts); + total_sleep_time = timespec_add_safe(total_sleep_time, ts); } update_xtime_cache(0); /* re-base the last cycle value */ - clock->cycle_last = 0; - clock->cycle_last = clocksource_read(clock); - clock->error = 0; + timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock); + timekeeper.ntp_error = 0; timekeeping_suspended = 0; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -366,10 +602,10 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) { unsigned long flags; - timekeeping_suspend_time = read_persistent_clock(); + read_persistent_clock(&timekeeping_suspend_time); write_seqlock_irqsave(&xtime_lock, flags); - clocksource_forward_now(); + timekeeping_forward_now(); timekeeping_suspended = 1; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -404,7 +640,7 @@ device_initcall(timekeeping_init_device); * If the error is already larger, we look ahead even further * to compensate for late or lost adjustments. */ -static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, +static __always_inline int timekeeping_bigadjust(s64 error, s64 *interval, s64 *offset) { s64 tick_error, i; @@ -420,7 +656,7 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, * here. This is tuned so that an error of about 1 msec is adjusted * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). */ - error2 = clock->error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); + error2 = timekeeper.ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ); error2 = abs(error2); for (look_ahead = 0; error2 > 0; look_ahead++) error2 >>= 2; @@ -429,8 +665,8 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, * Now calculate the error in (1 << look_ahead) ticks, but first * remove the single look ahead already included in the error. */ - tick_error = tick_length >> (NTP_SCALE_SHIFT - clock->shift + 1); - tick_error -= clock->xtime_interval >> 1; + tick_error = tick_length >> (timekeeper.ntp_error_shift + 1); + tick_error -= timekeeper.xtime_interval >> 1; error = ((error - tick_error) >> look_ahead) + tick_error; /* Finally calculate the adjustment shift value. */ @@ -455,18 +691,18 @@ static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, * this is optimized for the most common adjustments of -1,0,1, * for other values we can do a bit more work. */ -static void clocksource_adjust(s64 offset) +static void timekeeping_adjust(s64 offset) { - s64 error, interval = clock->cycle_interval; + s64 error, interval = timekeeper.cycle_interval; int adj; - error = clock->error >> (NTP_SCALE_SHIFT - clock->shift - 1); + error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1); if (error > interval) { error >>= 2; if (likely(error <= interval)) adj = 1; else - adj = clocksource_bigadjust(error, &interval, &offset); + adj = timekeeping_bigadjust(error, &interval, &offset); } else if (error < -interval) { error >>= 2; if (likely(error >= -interval)) { @@ -474,15 +710,15 @@ static void clocksource_adjust(s64 offset) interval = -interval; offset = -offset; } else - adj = clocksource_bigadjust(error, &interval, &offset); + adj = timekeeping_bigadjust(error, &interval, &offset); } else return; - clock->mult += adj; - clock->xtime_interval += interval; - clock->xtime_nsec -= offset; - clock->error -= (interval - offset) << - (NTP_SCALE_SHIFT - clock->shift); + timekeeper.mult += adj; + timekeeper.xtime_interval += interval; + timekeeper.xtime_nsec -= offset; + timekeeper.ntp_error -= (interval - offset) << + timekeeper.ntp_error_shift; } /** @@ -492,53 +728,59 @@ static void clocksource_adjust(s64 offset) */ void update_wall_time(void) { + struct clocksource *clock; cycle_t offset; + u64 nsecs; /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return; + clock = timekeeper.clock; #ifdef CONFIG_GENERIC_TIME - offset = (clocksource_read(clock) - clock->cycle_last) & clock->mask; + offset = (clock->read(clock) - clock->cycle_last) & clock->mask; #else - offset = clock->cycle_interval; + offset = timekeeper.cycle_interval; #endif - clock->xtime_nsec = (s64)xtime.tv_nsec << clock->shift; + timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift; /* normally this loop will run just once, however in the * case of lost or late ticks, it will accumulate correctly. */ - while (offset >= clock->cycle_interval) { + while (offset >= timekeeper.cycle_interval) { + u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; + /* accumulate one interval */ - offset -= clock->cycle_interval; - clock->cycle_last += clock->cycle_interval; + offset -= timekeeper.cycle_interval; + clock->cycle_last += timekeeper.cycle_interval; - clock->xtime_nsec += clock->xtime_interval; - if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { - clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; + timekeeper.xtime_nsec += timekeeper.xtime_interval; + if (timekeeper.xtime_nsec >= nsecps) { + timekeeper.xtime_nsec -= nsecps; xtime.tv_sec++; second_overflow(); } - clock->raw_time.tv_nsec += clock->raw_interval; - if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) { - clock->raw_time.tv_nsec -= NSEC_PER_SEC; - clock->raw_time.tv_sec++; + raw_time.tv_nsec += timekeeper.raw_interval; + if (raw_time.tv_nsec >= NSEC_PER_SEC) { + raw_time.tv_nsec -= NSEC_PER_SEC; + raw_time.tv_sec++; } /* accumulate error between NTP and clock interval */ - clock->error += tick_length; - clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift); + timekeeper.ntp_error += tick_length; + timekeeper.ntp_error -= timekeeper.xtime_interval << + timekeeper.ntp_error_shift; } /* correct the clock when NTP error is too big */ - clocksource_adjust(offset); + timekeeping_adjust(offset); /* * Since in the loop above, we accumulate any amount of time * in xtime_nsec over a second into xtime.tv_sec, its possible for * xtime_nsec to be fairly small after the loop. Further, if we're - * slightly speeding the clocksource up in clocksource_adjust(), + * slightly speeding the clocksource up in timekeeping_adjust(), * its possible the required corrective factor to xtime_nsec could * cause it to underflow. * @@ -550,24 +792,25 @@ void update_wall_time(void) * We'll correct this error next time through this function, when * xtime_nsec is not as small. */ - if (unlikely((s64)clock->xtime_nsec < 0)) { - s64 neg = -(s64)clock->xtime_nsec; - clock->xtime_nsec = 0; - clock->error += neg << (NTP_SCALE_SHIFT - clock->shift); + if (unlikely((s64)timekeeper.xtime_nsec < 0)) { + s64 neg = -(s64)timekeeper.xtime_nsec; + timekeeper.xtime_nsec = 0; + timekeeper.ntp_error += neg << timekeeper.ntp_error_shift; } /* store full nanoseconds into xtime after rounding it up and * add the remainder to the error difference. */ - xtime.tv_nsec = ((s64)clock->xtime_nsec >> clock->shift) + 1; - clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift; - clock->error += clock->xtime_nsec << (NTP_SCALE_SHIFT - clock->shift); + xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1; + timekeeper.xtime_nsec -= (s64) xtime.tv_nsec << timekeeper.shift; + timekeeper.ntp_error += timekeeper.xtime_nsec << + timekeeper.ntp_error_shift; - update_xtime_cache(cyc2ns(clock, offset)); + nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift); + update_xtime_cache(nsecs); /* check to see if there is a new clocksource to use */ - change_clocksource(); - update_vsyscall(&xtime, clock); + update_vsyscall(&xtime, timekeeper.clock); } /** @@ -583,9 +826,12 @@ void update_wall_time(void) */ void getboottime(struct timespec *ts) { - set_normalized_timespec(ts, - - (wall_to_monotonic.tv_sec + total_sleep_time), - - wall_to_monotonic.tv_nsec); + struct timespec boottime = { + .tv_sec = wall_to_monotonic.tv_sec + total_sleep_time.tv_sec, + .tv_nsec = wall_to_monotonic.tv_nsec + total_sleep_time.tv_nsec + }; + + set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec); } /** @@ -594,7 +840,7 @@ void getboottime(struct timespec *ts) */ void monotonic_to_bootbased(struct timespec *ts) { - ts->tv_sec += total_sleep_time; + *ts = timespec_add_safe(*ts, total_sleep_time); } unsigned long get_seconds(void) @@ -603,6 +849,10 @@ unsigned long get_seconds(void) } EXPORT_SYMBOL(get_seconds); +struct timespec __current_kernel_time(void) +{ + return xtime_cache; +} struct timespec current_kernel_time(void) { @@ -618,3 +868,20 @@ struct timespec current_kernel_time(void) return now; } EXPORT_SYMBOL(current_kernel_time); + +struct timespec get_monotonic_coarse(void) +{ + struct timespec now, mono; + unsigned long seq; + + do { + seq = read_seqbegin(&xtime_lock); + + now = xtime_cache; + mono = wall_to_monotonic; + } while (read_seqretry(&xtime_lock, seq)); + + set_normalized_timespec(&now, now.tv_sec + mono.tv_sec, + now.tv_nsec + mono.tv_nsec); + return now; +} diff --git a/kernel/timer.c b/kernel/timer.c index a7f07d5..8e92be6 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -72,6 +72,7 @@ struct tvec_base { spinlock_t lock; struct timer_list *running_timer; unsigned long timer_jiffies; + unsigned long next_timer; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -622,6 +623,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires, if (timer_pending(timer)) { detach_timer(timer, 0); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; ret = 1; } else { if (pending_only) @@ -663,6 +667,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires, } timer->expires = expires; + if (time_before(timer->expires, base->next_timer) && + !tbase_get_deferrable(timer->base)) + base->next_timer = timer->expires; internal_add_timer(base, timer); out_unlock: @@ -781,6 +788,9 @@ void add_timer_on(struct timer_list *timer, int cpu) spin_lock_irqsave(&base->lock, flags); timer_set_base(timer, base); debug_timer_activate(timer); + if (time_before(timer->expires, base->next_timer) && + !tbase_get_deferrable(timer->base)) + base->next_timer = timer->expires; internal_add_timer(base, timer); /* * Check whether the other CPU is idle and needs to be @@ -817,6 +827,9 @@ int del_timer(struct timer_list *timer) base = lock_timer_base(timer, &flags); if (timer_pending(timer)) { detach_timer(timer, 1); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; ret = 1; } spin_unlock_irqrestore(&base->lock, flags); @@ -850,6 +863,9 @@ int try_to_del_timer_sync(struct timer_list *timer) ret = 0; if (timer_pending(timer)) { detach_timer(timer, 1); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; ret = 1; } out: @@ -1007,8 +1023,8 @@ static inline void __run_timers(struct tvec_base *base) #ifdef CONFIG_NO_HZ /* * Find out when the next timer event is due to happen. This - * is used on S/390 to stop all activity when a cpus is idle. - * This functions needs to be called disabled. + * is used on S/390 to stop all activity when a CPU is idle. + * This function needs to be called with interrupts disabled. */ static unsigned long __next_timer_interrupt(struct tvec_base *base) { @@ -1134,7 +1150,9 @@ unsigned long get_next_timer_interrupt(unsigned long now) unsigned long expires; spin_lock(&base->lock); - expires = __next_timer_interrupt(base); + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; spin_unlock(&base->lock); if (time_before_eq(expires, now)) @@ -1523,6 +1541,7 @@ static int __cpuinit init_timers_cpu(int cpu) INIT_LIST_HEAD(base->tv1.vec + j); base->timer_jiffies = jiffies; + base->next_timer = base->timer_jiffies; return 0; } @@ -1535,6 +1554,9 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea timer = list_first_entry(head, struct timer_list, entry); detach_timer(timer, 0); timer_set_base(timer, new_base); + if (time_before(timer->expires, new_base->next_timer) && + !tbase_get_deferrable(timer->base)) + new_base->next_timer = timer->expires; internal_add_timer(new_base, timer); } } diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 1090b0a..7a34cb5 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -267,8 +267,8 @@ static void blk_trace_free(struct blk_trace *bt) { debugfs_remove(bt->msg_file); debugfs_remove(bt->dropped_file); - debugfs_remove(bt->dir); relay_close(bt->rchan); + debugfs_remove(bt->dir); free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); @@ -378,18 +378,8 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf, static int blk_remove_buf_file_callback(struct dentry *dentry) { - struct dentry *parent = dentry->d_parent; debugfs_remove(dentry); - /* - * this will fail for all but the last file, but that is ok. what we - * care about is the top level buts->name directory going away, when - * the last trace file is gone. Then we don't have to rmdir() that - * manually on trace stop, so it nicely solves the issue with - * force killing of running traces. - */ - - debugfs_remove(parent); return 0; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1f3ec2a..1e1d23c 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1662,7 +1662,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) mutex_lock(&ftrace_regex_lock); if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) + (file->f_flags & O_TRUNC)) ftrace_filter_reset(enable); if (file->f_mode & FMODE_READ) { @@ -2577,7 +2577,7 @@ ftrace_graph_open(struct inode *inode, struct file *file) mutex_lock(&graph_lock); if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) { + (file->f_flags & O_TRUNC)) { ftrace_graph_count = 0; memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs)); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index bf27bb7..a330513 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -735,6 +735,7 @@ ring_buffer_free(struct ring_buffer *buffer) put_online_cpus(); + kfree(buffer->buffers); free_cpumask_var(buffer->cpumask); kfree(buffer); @@ -1785,7 +1786,7 @@ void ring_buffer_discard_commit(struct ring_buffer *buffer, */ RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing)); - if (!rb_try_to_discard(cpu_buffer, event)) + if (rb_try_to_discard(cpu_buffer, event)) goto out; /* @@ -2383,7 +2384,6 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) * the box. Return the padding, and we will release * the current locks, and try again. */ - rb_advance_reader(cpu_buffer); return event; case RINGBUF_TYPE_TIME_EXTEND: @@ -2486,7 +2486,7 @@ static inline int rb_ok_to_lock(void) * buffer too. A one time deal is all you get from reading * the ring buffer from an NMI. */ - if (likely(!in_nmi() && !oops_in_progress)) + if (likely(!in_nmi())) return 1; tracing_off_permanent(); @@ -2519,6 +2519,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) if (dolock) spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(buffer, cpu, ts); + if (event && event->type_len == RINGBUF_TYPE_PADDING) + rb_advance_reader(cpu_buffer); if (dolock) spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); @@ -2590,12 +2592,9 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts) spin_lock(&cpu_buffer->reader_lock); event = rb_buffer_peek(buffer, cpu, ts); - if (!event) - goto out_unlock; - - rb_advance_reader(cpu_buffer); + if (event) + rb_advance_reader(cpu_buffer); - out_unlock: if (dolock) spin_unlock(&cpu_buffer->reader_lock); local_irq_restore(flags); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8bc8d8a..c22b40f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -848,6 +848,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); } +EXPORT_SYMBOL_GPL(tracing_generic_entry_update); struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr, int type, @@ -2031,7 +2032,7 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) { + (file->f_flags & O_TRUNC)) { long cpu = (long) inode->i_private; if (cpu == TRACE_PIPE_ALL_CPU) @@ -3085,7 +3086,8 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) break; } - trace_consume(iter); + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(iter); rem -= count; if (!find_next_entry_inc(iter)) { rem = 0; @@ -4233,8 +4235,11 @@ static void __ftrace_dump(bool disable_tracing) iter.pos = -1; if (find_next_entry_inc(&iter) != NULL) { - print_trace_line(&iter); - trace_consume(&iter); + int ret; + + ret = print_trace_line(&iter); + if (ret != TRACE_TYPE_NO_CONSUME) + trace_consume(&iter); } trace_printk_seq(&iter.seq); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3548ae5..8b9f4f6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -438,10 +438,6 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); -void tracing_generic_entry_update(struct trace_entry *entry, - unsigned long flags, - int pc); - void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_profile.c index 5b5895a..11ba5bb 100644 --- a/kernel/trace/trace_event_profile.c +++ b/kernel/trace/trace_event_profile.c @@ -14,7 +14,7 @@ int ftrace_profile_enable(int event_id) mutex_lock(&event_mutex); list_for_each_entry(event, &ftrace_events, list) { - if (event->id == event_id) { + if (event->id == event_id && event->profile_enable) { ret = event->profile_enable(event); break; } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 53c8fd3..e75276a 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -376,7 +376,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file) const struct seq_operations *seq_ops; if ((file->f_mode & FMODE_WRITE) && - !(file->f_flags & O_APPEND)) + (file->f_flags & O_TRUNC)) ftrace_clear_events(); seq_ops = inode->i_private; @@ -940,7 +940,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, entry = trace_create_file("enable", 0644, call->dir, call, enable); - if (call->id) + if (call->id && call->profile_enable) entry = trace_create_file("id", 0444, call->dir, call, id); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 936c621..f32dc9d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -624,9 +624,6 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, return -ENOSPC; } - filter->preds[filter->n_preds] = pred; - filter->n_preds++; - list_for_each_entry(call, &ftrace_events, list) { if (!call->define_fields) @@ -643,6 +640,9 @@ static int filter_add_subsystem_pred(struct filter_parse_state *ps, } replace_filter_string(call->filter, filter_string); } + + filter->preds[filter->n_preds] = pred; + filter->n_preds++; out: return err; } @@ -1029,12 +1029,17 @@ static int replace_preds(struct event_subsystem *system, if (elt->op == OP_AND || elt->op == OP_OR) { pred = create_logical_pred(elt->op); + if (!pred) + return -ENOMEM; if (call) { err = filter_add_pred(ps, call, pred); filter_free_pred(pred); - } else + } else { err = filter_add_subsystem_pred(ps, system, pred, filter_string); + if (err) + filter_free_pred(pred); + } if (err) return err; @@ -1048,12 +1053,17 @@ static int replace_preds(struct event_subsystem *system, } pred = create_pred(elt->op, operand1, operand2); + if (!pred) + return -ENOMEM; if (call) { err = filter_add_pred(ps, call, pred); filter_free_pred(pred); - } else + } else { err = filter_add_subsystem_pred(ps, system, pred, filter_string); + if (err) + filter_free_pred(pred); + } if (err) return err; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index d2249ab..420ec34 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -843,9 +843,16 @@ print_graph_function(struct trace_iterator *iter) switch (entry->type) { case TRACE_GRAPH_ENT: { - struct ftrace_graph_ent_entry *field; + /* + * print_graph_entry() may consume the current event, + * thus @field may become invalid, so we need to save it. + * sizeof(struct ftrace_graph_ent_entry) is very small, + * it can be safely saved at the stack. + */ + struct ftrace_graph_ent_entry *field, saved; trace_assign_type(field, entry); - return print_graph_entry(field, s, iter); + saved = *field; + return print_graph_entry(&saved, s, iter); } case TRACE_GRAPH_RET: { struct ftrace_graph_ret_entry *field; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index 7b62781..687699d 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -176,7 +176,7 @@ static int t_show(struct seq_file *m, void *v) const char *str = *fmt; int i; - seq_printf(m, "0x%lx : \"", (unsigned long)fmt); + seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt); /* * Tabs and new lines need to be converted. diff --git a/kernel/wait.c b/kernel/wait.c index ea7c3b4..c4bd3d8 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -10,13 +10,14 @@ #include <linux/wait.h> #include <linux/hash.h> -void init_waitqueue_head(wait_queue_head_t *q) +void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *key) { spin_lock_init(&q->lock); + lockdep_set_class(&q->lock, key); INIT_LIST_HEAD(&q->task_list); } -EXPORT_SYMBOL(init_waitqueue_head); +EXPORT_SYMBOL(__init_waitqueue_head); void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) { diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index 708e2a8..600f473 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -45,12 +45,14 @@ */ -#ifndef STATIC +#ifdef STATIC +#define PREBOOT +#else #include <linux/decompress/bunzip2.h> -#endif /* !STATIC */ +#include <linux/slab.h> +#endif /* STATIC */ #include <linux/decompress/mm.h> -#include <linux/slab.h> #ifndef INT_MAX #define INT_MAX 0x7fffffff @@ -681,9 +683,7 @@ STATIC int INIT bunzip2(unsigned char *buf, int len, set_error_fn(error_fn); if (flush) outbuf = malloc(BZIP2_IOBUF_SIZE); - else - len -= 4; /* Uncompressed size hack active in pre-boot - environment */ + if (!outbuf) { error("Could not allocate output bufer"); return -1; @@ -733,4 +733,14 @@ exit_0: return i; } -#define decompress bunzip2 +#ifdef PREBOOT +STATIC int INIT decompress(unsigned char *buf, int len, + int(*fill)(void*, unsigned int), + int(*flush)(void*, unsigned int), + unsigned char *outbuf, + int *pos, + void(*error_fn)(char *x)) +{ + return bunzip2(buf, len - 4, fill, flush, outbuf, pos, error_fn); +} +#endif diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c index e36b296..68dfce5 100644 --- a/lib/decompress_inflate.c +++ b/lib/decompress_inflate.c @@ -19,13 +19,13 @@ #include "zlib_inflate/inflate.h" #include "zlib_inflate/infutil.h" +#include <linux/slab.h> #endif /* STATIC */ #include <linux/decompress/mm.h> -#include <linux/slab.h> -#define INBUF_LEN (16*1024) +#define GZIP_IOBUF_SIZE (16*1024) /* Included from initramfs et al code */ STATIC int INIT gunzip(unsigned char *buf, int len, @@ -55,7 +55,7 @@ STATIC int INIT gunzip(unsigned char *buf, int len, if (buf) zbuf = buf; else { - zbuf = malloc(INBUF_LEN); + zbuf = malloc(GZIP_IOBUF_SIZE); len = 0; } if (!zbuf) { @@ -77,7 +77,7 @@ STATIC int INIT gunzip(unsigned char *buf, int len, } if (len == 0) - len = fill(zbuf, INBUF_LEN); + len = fill(zbuf, GZIP_IOBUF_SIZE); /* verify the gzip header */ if (len < 10 || @@ -113,7 +113,7 @@ STATIC int INIT gunzip(unsigned char *buf, int len, while (rc == Z_OK) { if (strm->avail_in == 0) { /* TODO: handle case where both pos and fill are set */ - len = fill(zbuf, INBUF_LEN); + len = fill(zbuf, GZIP_IOBUF_SIZE); if (len < 0) { rc = -1; error("read error"); diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c index 32123a1..0b954e0 100644 --- a/lib/decompress_unlzma.c +++ b/lib/decompress_unlzma.c @@ -29,12 +29,14 @@ *Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ -#ifndef STATIC +#ifdef STATIC +#define PREBOOT +#else #include <linux/decompress/unlzma.h> +#include <linux/slab.h> #endif /* STATIC */ #include <linux/decompress/mm.h> -#include <linux/slab.h> #define MIN(a, b) (((a) < (b)) ? (a) : (b)) @@ -543,9 +545,7 @@ STATIC inline int INIT unlzma(unsigned char *buf, int in_len, int ret = -1; set_error_fn(error_fn); - if (!flush) - in_len -= 4; /* Uncompressed size hack active in pre-boot - environment */ + if (buf) inbuf = buf; else @@ -645,4 +645,15 @@ exit_0: return ret; } -#define decompress unlzma +#ifdef PREBOOT +STATIC int INIT decompress(unsigned char *buf, int in_len, + int(*fill)(void*, unsigned int), + int(*flush)(void*, unsigned int), + unsigned char *output, + int *posp, + void(*error_fn)(char *x) + ) +{ + return unlzma(buf, in_len - 4, fill, flush, output, posp, error_fn); +} +#endif diff --git a/lib/flex_array.c b/lib/flex_array.c index 0e7894c..08f1636 100644 --- a/lib/flex_array.c +++ b/lib/flex_array.c @@ -254,7 +254,6 @@ void *flex_array_get(struct flex_array *fa, int element_nr) { int part_nr = fa_element_to_part_nr(fa, element_nr); struct flex_array_part *part; - int index; if (element_nr >= fa->total_nr_elements) return NULL; @@ -264,6 +263,5 @@ void *flex_array_get(struct flex_array *fa, int element_nr) part = (struct flex_array_part *)&fa->parts[0]; else part = fa->parts[part_nr]; - index = index_inside_part(fa, element_nr); return &part->elements[index_inside_part(fa, element_nr)]; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e08e2c4..7dd9d9f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -191,25 +191,27 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_semaphore for write. */ -static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes) +static int mpol_set_nodemask(struct mempolicy *pol, + const nodemask_t *nodes, struct nodemask_scratch *nsc) { - nodemask_t cpuset_context_nmask; int ret; /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ if (pol == NULL) return 0; + /* Check N_HIGH_MEMORY */ + nodes_and(nsc->mask1, + cpuset_current_mems_allowed, node_states[N_HIGH_MEMORY]); VM_BUG_ON(!nodes); if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) nodes = NULL; /* explicit local allocation */ else { if (pol->flags & MPOL_F_RELATIVE_NODES) - mpol_relative_nodemask(&cpuset_context_nmask, nodes, - &cpuset_current_mems_allowed); + mpol_relative_nodemask(&nsc->mask2, nodes,&nsc->mask1); else - nodes_and(cpuset_context_nmask, *nodes, - cpuset_current_mems_allowed); + nodes_and(nsc->mask2, *nodes, nsc->mask1); + if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else @@ -217,8 +219,10 @@ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes) cpuset_current_mems_allowed; } - ret = mpol_ops[pol->mode].create(pol, - nodes ? &cpuset_context_nmask : NULL); + if (nodes) + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + else + ret = mpol_ops[pol->mode].create(pol, NULL); return ret; } @@ -620,12 +624,17 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, { struct mempolicy *new, *old; struct mm_struct *mm = current->mm; + NODEMASK_SCRATCH(scratch); int ret; - new = mpol_new(mode, flags, nodes); - if (IS_ERR(new)) - return PTR_ERR(new); + if (!scratch) + return -ENOMEM; + new = mpol_new(mode, flags, nodes); + if (IS_ERR(new)) { + ret = PTR_ERR(new); + goto out; + } /* * prevent changing our mempolicy while show_numa_maps() * is using it. @@ -635,13 +644,13 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, if (mm) down_write(&mm->mmap_sem); task_lock(current); - ret = mpol_set_nodemask(new, nodes); + ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); if (mm) up_write(&mm->mmap_sem); mpol_put(new); - return ret; + goto out; } old = current->mempolicy; current->mempolicy = new; @@ -654,7 +663,10 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags, up_write(&mm->mmap_sem); mpol_put(old); - return 0; + ret = 0; +out: + NODEMASK_SCRATCH_FREE(scratch); + return ret; } /* @@ -1014,12 +1026,20 @@ static long do_mbind(unsigned long start, unsigned long len, if (err) return err; } - down_write(&mm->mmap_sem); - task_lock(current); - err = mpol_set_nodemask(new, nmask); - task_unlock(current); + { + NODEMASK_SCRATCH(scratch); + if (scratch) { + down_write(&mm->mmap_sem); + task_lock(current); + err = mpol_set_nodemask(new, nmask, scratch); + task_unlock(current); + if (err) + up_write(&mm->mmap_sem); + } else + err = -ENOMEM; + NODEMASK_SCRATCH_FREE(scratch); + } if (err) { - up_write(&mm->mmap_sem); mpol_put(new); return err; } @@ -1891,6 +1911,7 @@ restart: * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. + * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { @@ -1902,19 +1923,24 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) if (mpol) { struct vm_area_struct pvma; struct mempolicy *new; + NODEMASK_SCRATCH(scratch); + if (!scratch) + return; /* contextualize the tmpfs mount point mempolicy */ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(new)) { mpol_put(mpol); /* drop our ref on sb mpol */ + NODEMASK_SCRATCH_FREE(scratch); return; /* no valid nodemask intersection */ } task_lock(current); - ret = mpol_set_nodemask(new, &mpol->w.user_nodemask); + ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); task_unlock(current); mpol_put(mpol); /* drop our ref on sb mpol */ if (ret) { + NODEMASK_SCRATCH_FREE(scratch); mpol_put(new); return; } @@ -1924,6 +1950,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ mpol_put(new); /* drop initial ref */ + NODEMASK_SCRATCH_FREE(scratch); } } @@ -2140,13 +2167,18 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context) err = 1; else { int ret; - - task_lock(current); - ret = mpol_set_nodemask(new, &nodes); - task_unlock(current); - if (ret) + NODEMASK_SCRATCH(scratch); + if (scratch) { + task_lock(current); + ret = mpol_set_nodemask(new, &nodes, scratch); + task_unlock(current); + } else + ret = -ENOMEM; + NODEMASK_SCRATCH_FREE(scratch); + if (ret) { err = 1; - else if (no_context) { + mpol_put(new); + } else if (no_context) { /* save for contextualization */ new->w.user_nodemask = nodes; } diff --git a/mm/mempool.c b/mm/mempool.c index a46eb1b..32e75d4 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -303,14 +303,14 @@ EXPORT_SYMBOL(mempool_free_slab); */ void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data) { - size_t size = (size_t)(long)pool_data; + size_t size = (size_t)pool_data; return kmalloc(size, gfp_mask); } EXPORT_SYMBOL(mempool_kmalloc); void *mempool_kzalloc(gfp_t gfp_mask, void *pool_data) { - size_t size = (size_t) pool_data; + size_t size = (size_t)pool_data; return kzalloc(size, gfp_mask); } EXPORT_SYMBOL(mempool_kzalloc); diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index e50566e..94b3388 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -2080,28 +2080,41 @@ static CLASS_ATTR(rfcomm_dlc, S_IRUGO, rfcomm_dlc_sysfs_show, NULL); /* ---- Initialization ---- */ static int __init rfcomm_init(void) { + int ret; + l2cap_load(); hci_register_cb(&rfcomm_cb); rfcomm_thread = kthread_run(rfcomm_run, NULL, "krfcommd"); if (IS_ERR(rfcomm_thread)) { - hci_unregister_cb(&rfcomm_cb); - return PTR_ERR(rfcomm_thread); + ret = PTR_ERR(rfcomm_thread); + goto out_thread; } if (class_create_file(bt_class, &class_attr_rfcomm_dlc) < 0) BT_ERR("Failed to create RFCOMM info file"); - rfcomm_init_sockets(); + ret = rfcomm_init_ttys(); + if (ret) + goto out_tty; -#ifdef CONFIG_BT_RFCOMM_TTY - rfcomm_init_ttys(); -#endif + ret = rfcomm_init_sockets(); + if (ret) + goto out_sock; BT_INFO("RFCOMM ver %s", VERSION); return 0; + +out_sock: + rfcomm_cleanup_ttys(); +out_tty: + kthread_stop(rfcomm_thread); +out_thread: + hci_unregister_cb(&rfcomm_cb); + + return ret; } static void __exit rfcomm_exit(void) @@ -2112,9 +2125,7 @@ static void __exit rfcomm_exit(void) kthread_stop(rfcomm_thread); -#ifdef CONFIG_BT_RFCOMM_TTY rfcomm_cleanup_ttys(); -#endif rfcomm_cleanup_sockets(); } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 7f48278..0b85e81 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -1132,7 +1132,7 @@ error: return err; } -void __exit rfcomm_cleanup_sockets(void) +void rfcomm_cleanup_sockets(void) { class_remove_file(bt_class, &class_attr_rfcomm); diff --git a/net/core/dev.c b/net/core/dev.c index 70c27e0..6a94475 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3865,10 +3865,12 @@ int dev_unicast_delete(struct net_device *dev, void *addr) ASSERT_RTNL(); + netif_addr_lock_bh(dev); err = __hw_addr_del(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_delete); @@ -3889,10 +3891,12 @@ int dev_unicast_add(struct net_device *dev, void *addr) ASSERT_RTNL(); + netif_addr_lock_bh(dev); err = __hw_addr_add(&dev->uc, addr, dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_add); @@ -3949,7 +3953,8 @@ void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, * @from: source device * * Add newly added addresses to the destination device and release - * addresses that have no users left. + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. @@ -3958,14 +3963,14 @@ int dev_unicast_sync(struct net_device *to, struct net_device *from) { int err = 0; - ASSERT_RTNL(); - if (to->addr_len != from->addr_len) return -EINVAL; + netif_addr_lock_bh(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); return err; } EXPORT_SYMBOL(dev_unicast_sync); @@ -3981,27 +3986,27 @@ EXPORT_SYMBOL(dev_unicast_sync); */ void dev_unicast_unsync(struct net_device *to, struct net_device *from) { - ASSERT_RTNL(); - if (to->addr_len != from->addr_len) return; + netif_addr_lock_bh(from); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); } EXPORT_SYMBOL(dev_unicast_unsync); static void dev_unicast_flush(struct net_device *dev) { - /* rtnl_mutex must be held here */ - + netif_addr_lock_bh(dev); __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); } static void dev_unicast_init(struct net_device *dev) { - /* rtnl_mutex must be held here */ - __hw_addr_init(&dev->uc); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b7292a2..1972830 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -488,7 +488,7 @@ int net_assign_generic(struct net *net, int id, void *data) */ ng->len = id; - memcpy(&ng->ptr, &old_ng->ptr, old_ng->len); + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); rcu_assign_pointer(net->gen, ng); call_rcu(&old_ng->rcu, net_generic_release); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c29d75d..090e999 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1304,7 +1304,9 @@ static void arp_format_neigh_entry(struct seq_file *seq, hbuffer[k++] = hex_asc_lo(n->ha[j]); hbuffer[k++] = ':'; } - hbuffer[--k] = 0; + if (k != 0) + --k; + hbuffer[k] = 0; #if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) } #endif diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index aca22b0..07e7e41 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -721,7 +721,7 @@ void ieee80211_dynamic_ps_timer(unsigned long data) { struct ieee80211_local *local = (void *) data; - if (local->quiescing) + if (local->quiescing || local->suspended) return; queue_work(local->hw.workqueue, &local->dynamic_ps_enable_work); diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 7a549f9..5e3d476 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -55,15 +55,6 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) rcu_read_unlock(); - /* flush again, in case driver queued work */ - flush_workqueue(local->hw.workqueue); - - /* stop hardware - this must stop RX */ - if (local->open_count) { - ieee80211_led_radio(local, false); - drv_stop(local); - } - /* remove STAs */ spin_lock_irqsave(&local->sta_lock, flags); list_for_each_entry(sta, &local->sta_list, list) { @@ -111,7 +102,22 @@ int __ieee80211_suspend(struct ieee80211_hw *hw) drv_remove_interface(local, &conf); } + /* stop hardware - this must stop RX */ + if (local->open_count) { + ieee80211_led_radio(local, false); + drv_stop(local); + } + + /* + * flush again, in case driver queued work -- it + * shouldn't be doing (or cancel everything in the + * stop callback) that but better safe than sorry. + */ + flush_workqueue(local->hw.workqueue); + local->suspended = true; + /* need suspended to be visible before quiescing is false */ + barrier(); local->quiescing = false; return 0; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index de5bba7..0936fc2 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2453,6 +2453,18 @@ void __ieee80211_rx(struct ieee80211_hw *hw, struct sk_buff *skb, return; } + /* + * If we're suspending, it is possible although not too likely + * that we'd be receiving frames after having already partially + * quiesced the stack. We can't process such frames then since + * that might, for example, cause stations to be added or other + * driver callbacks be invoked. + */ + if (unlikely(local->quiescing || local->suspended)) { + kfree_skb(skb); + return; + } + if (status->flag & RX_FLAG_HT) { /* rate_idx is MCS index */ if (WARN_ON(status->rate_idx < 0 || diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index b0e582f..16e6c43 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -151,7 +151,7 @@ int netlbl_cfg_unlbl_map_add(const char *domain, addr6 = addr; mask6 = mask; map6 = kzalloc(sizeof(*map6), GFP_ATOMIC); - if (map4 == NULL) + if (map6 == NULL) goto cfg_unlbl_map_add_failure; map6->type = NETLBL_NLTYPE_UNLABELED; ipv6_addr_copy(&map6->list.addr, addr6); diff --git a/net/socket.c b/net/socket.c index 791d71a..6d47165 100644 --- a/net/socket.c +++ b/net/socket.c @@ -736,7 +736,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, if (more) flags |= MSG_MORE; - return sock->ops->sendpage(sock, page, offset, size, flags); + return kernel_sendpage(sock, page, offset, size, flags); } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5e14371..75a406d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1089,17 +1089,18 @@ static void handle_reg_beacon(struct wiphy *wiphy, chan->beacon_found = true; + if (wiphy->disable_beacon_hints) + return; + chan_before.center_freq = chan->center_freq; chan_before.flags = chan->flags; - if ((chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) && - !(chan->orig_flags & IEEE80211_CHAN_PASSIVE_SCAN)) { + if (chan->flags & IEEE80211_CHAN_PASSIVE_SCAN) { chan->flags &= ~IEEE80211_CHAN_PASSIVE_SCAN; channel_changed = true; } - if ((chan->flags & IEEE80211_CHAN_NO_IBSS) && - !(chan->orig_flags & IEEE80211_CHAN_NO_IBSS)) { + if (chan->flags & IEEE80211_CHAN_NO_IBSS) { chan->flags &= ~IEEE80211_CHAN_NO_IBSS; channel_changed = true; } diff --git a/net/wireless/reg.h b/net/wireless/reg.h index e37829a..4e167a8 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -30,7 +30,8 @@ int set_regdom(const struct ieee80211_regdomain *rd); * non-radar 5 GHz channels. * * Drivers do not need to call this, cfg80211 will do it for after a scan - * on a newly found BSS. + * on a newly found BSS. If you cannot make use of this feature you can + * set the wiphy->disable_beacon_hints to true. */ int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 9271118..7e595ce 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -118,7 +118,7 @@ static int cmp_ies(u8 num, u8 *ies1, size_t len1, u8 *ies2, size_t len2) if (!ie1 && !ie2) return 0; - if (!ie1) + if (!ie1 || !ie2) return -1; r = memcmp(ie1 + 2, ie2 + 2, min(ie1[1], ie2[1])); @@ -171,6 +171,8 @@ static bool is_mesh(struct cfg80211_bss *a, ie = find_ie(WLAN_EID_MESH_CONFIG, a->information_elements, a->len_information_elements); + if (!ie) + return false; if (ie[1] != IEEE80211_MESH_CONFIG_LEN) return false; diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 7109e2b..911ba7f 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -393,7 +393,7 @@ while (<IN>) { $read_function = 0; } # print out any recorded offsets - update_funcs() if ($text_found); + update_funcs() if (defined($ref_func)); # reset all markers and arrays $text_found = 0; @@ -403,7 +403,6 @@ while (<IN>) { # section found, now is this a start of a function? } elsif ($read_function && /$function_regex/) { $text_found = 1; - $offset = hex $1; $text = $2; # if this is either a local function or a weak function @@ -412,10 +411,15 @@ while (<IN>) { if (!defined($locals{$text}) && !defined($weak{$text})) { $ref_func = $text; $read_function = 0; + $offset = hex $1; } else { # if we already have a function, and this is weak, skip it - if (!defined($ref_func) || !defined($weak{$text})) { + if (!defined($ref_func) && !defined($weak{$text}) && + # PPC64 can have symbols that start with .L and + # gcc considers these special. Don't use them! + $text !~ /^\.L/) { $ref_func = $text; + $offset = hex $1; } } } elsif ($read_headers && /$mcount_section/) { @@ -440,7 +444,7 @@ while (<IN>) { } # dump out anymore offsets that may have been found -update_funcs() if ($text_found); +update_funcs() if (defined($ref_func)); # If we did not find any mcount callers, we are done (do nothing). if (!$opened) { diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 15c2a08..1e8cfc4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1285,6 +1285,8 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { + kfree(context); + /* Need a larger buffer. Query for the right size. */ rc = inode->i_op->getxattr(dentry, XATTR_NAME_SELINUX, NULL, 0); @@ -1292,7 +1294,6 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent dput(dentry); goto out_unlock; } - kfree(context); len = rc; context = kmalloc(len+1, GFP_NOFS); if (!context) { diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 88480c0..c7df01b 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -174,7 +174,7 @@ static int codec_exec_verb(struct hda_codec *codec, unsigned int cmd, mutex_lock(&bus->cmd_mutex); err = bus->ops.command(bus, cmd); if (!err && res) - *res = bus->ops.get_response(bus); + *res = bus->ops.get_response(bus, codec->addr); mutex_unlock(&bus->cmd_mutex); snd_hda_power_down(codec); if (res && *res == -1 && bus->rirb_error) { diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h index cad79ef..1b75f28 100644 --- a/sound/pci/hda/hda_codec.h +++ b/sound/pci/hda/hda_codec.h @@ -568,7 +568,7 @@ struct hda_bus_ops { /* send a single command */ int (*command)(struct hda_bus *bus, unsigned int cmd); /* get a response from the last command */ - unsigned int (*get_response)(struct hda_bus *bus); + unsigned int (*get_response)(struct hda_bus *bus, unsigned int addr); /* free the private data */ void (*private_free)(struct hda_bus *); /* attach a PCM stream */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 77c1b84..175f07a 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -253,7 +253,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; /* STATESTS int mask: S3,SD2,SD1,SD0 */ #define AZX_MAX_CODECS 4 -#define STATESTS_INT_MASK 0x0f +#define STATESTS_INT_MASK ((1 << AZX_MAX_CODECS) - 1) /* SD_CTL bits */ #define SD_CTL_STREAM_RESET 0x01 /* stream reset bit */ @@ -361,8 +361,8 @@ struct azx_rb { dma_addr_t addr; /* physical address of CORB/RIRB buffer */ /* for RIRB */ unsigned short rp, wp; /* read/write pointers */ - int cmds; /* number of pending requests */ - u32 res; /* last read value */ + int cmds[AZX_MAX_CODECS]; /* number of pending requests */ + u32 res[AZX_MAX_CODECS]; /* last read value */ }; struct azx { @@ -418,7 +418,7 @@ struct azx { unsigned int probing :1; /* codec probing phase */ /* for debugging */ - unsigned int last_cmd; /* last issued command (to sync) */ + unsigned int last_cmd[AZX_MAX_CODECS]; /* for pending irqs */ struct work_struct irq_pending_work; @@ -513,6 +513,7 @@ static int azx_alloc_cmd_io(struct azx *chip) static void azx_init_cmd_io(struct azx *chip) { + spin_lock_irq(&chip->reg_lock); /* CORB set up */ chip->corb.addr = chip->rb.addr; chip->corb.buf = (u32 *)chip->rb.area; @@ -531,7 +532,8 @@ static void azx_init_cmd_io(struct azx *chip) /* RIRB set up */ chip->rirb.addr = chip->rb.addr + 2048; chip->rirb.buf = (u32 *)(chip->rb.area + 2048); - chip->rirb.wp = chip->rirb.rp = chip->rirb.cmds = 0; + chip->rirb.wp = chip->rirb.rp = 0; + memset(chip->rirb.cmds, 0, sizeof(chip->rirb.cmds)); azx_writel(chip, RIRBLBASE, (u32)chip->rirb.addr); azx_writel(chip, RIRBUBASE, upper_32_bits(chip->rirb.addr)); @@ -543,30 +545,60 @@ static void azx_init_cmd_io(struct azx *chip) azx_writew(chip, RINTCNT, 1); /* enable rirb dma and response irq */ azx_writeb(chip, RIRBCTL, ICH6_RBCTL_DMA_EN | ICH6_RBCTL_IRQ_EN); + spin_unlock_irq(&chip->reg_lock); } static void azx_free_cmd_io(struct azx *chip) { + spin_lock_irq(&chip->reg_lock); /* disable ringbuffer DMAs */ azx_writeb(chip, RIRBCTL, 0); azx_writeb(chip, CORBCTL, 0); + spin_unlock_irq(&chip->reg_lock); +} + +static unsigned int azx_command_addr(u32 cmd) +{ + unsigned int addr = cmd >> 28; + + if (addr >= AZX_MAX_CODECS) { + snd_BUG(); + addr = 0; + } + + return addr; +} + +static unsigned int azx_response_addr(u32 res) +{ + unsigned int addr = res & 0xf; + + if (addr >= AZX_MAX_CODECS) { + snd_BUG(); + addr = 0; + } + + return addr; } /* send a command */ static int azx_corb_send_cmd(struct hda_bus *bus, u32 val) { struct azx *chip = bus->private_data; + unsigned int addr = azx_command_addr(val); unsigned int wp; + spin_lock_irq(&chip->reg_lock); + /* add command to corb */ wp = azx_readb(chip, CORBWP); wp++; wp %= ICH6_MAX_CORB_ENTRIES; - spin_lock_irq(&chip->reg_lock); - chip->rirb.cmds++; + chip->rirb.cmds[addr]++; chip->corb.buf[wp] = cpu_to_le32(val); azx_writel(chip, CORBWP, wp); + spin_unlock_irq(&chip->reg_lock); return 0; @@ -578,13 +610,14 @@ static int azx_corb_send_cmd(struct hda_bus *bus, u32 val) static void azx_update_rirb(struct azx *chip) { unsigned int rp, wp; + unsigned int addr; u32 res, res_ex; wp = azx_readb(chip, RIRBWP); if (wp == chip->rirb.wp) return; chip->rirb.wp = wp; - + while (chip->rirb.rp != wp) { chip->rirb.rp++; chip->rirb.rp %= ICH6_MAX_RIRB_ENTRIES; @@ -592,18 +625,24 @@ static void azx_update_rirb(struct azx *chip) rp = chip->rirb.rp << 1; /* an RIRB entry is 8-bytes */ res_ex = le32_to_cpu(chip->rirb.buf[rp + 1]); res = le32_to_cpu(chip->rirb.buf[rp]); + addr = azx_response_addr(res_ex); if (res_ex & ICH6_RIRB_EX_UNSOL_EV) snd_hda_queue_unsol_event(chip->bus, res, res_ex); - else if (chip->rirb.cmds) { - chip->rirb.res = res; + else if (chip->rirb.cmds[addr]) { + chip->rirb.res[addr] = res; smp_wmb(); - chip->rirb.cmds--; - } + chip->rirb.cmds[addr]--; + } else + snd_printk(KERN_ERR SFX "spurious response %#x:%#x, " + "last cmd=%#08x\n", + res, res_ex, + chip->last_cmd[addr]); } } /* receive a response */ -static unsigned int azx_rirb_get_response(struct hda_bus *bus) +static unsigned int azx_rirb_get_response(struct hda_bus *bus, + unsigned int addr) { struct azx *chip = bus->private_data; unsigned long timeout; @@ -616,10 +655,10 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus) azx_update_rirb(chip); spin_unlock_irq(&chip->reg_lock); } - if (!chip->rirb.cmds) { + if (!chip->rirb.cmds[addr]) { smp_rmb(); bus->rirb_error = 0; - return chip->rirb.res; /* the last value */ + return chip->rirb.res[addr]; /* the last value */ } if (time_after(jiffies, timeout)) break; @@ -633,7 +672,8 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus) if (chip->msi) { snd_printk(KERN_WARNING SFX "No response from codec, " - "disabling MSI: last cmd=0x%08x\n", chip->last_cmd); + "disabling MSI: last cmd=0x%08x\n", + chip->last_cmd[addr]); free_irq(chip->irq, chip); chip->irq = -1; pci_disable_msi(chip->pci); @@ -648,7 +688,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus) if (!chip->polling_mode) { snd_printk(KERN_WARNING SFX "azx_get_response timeout, " "switching to polling mode: last cmd=0x%08x\n", - chip->last_cmd); + chip->last_cmd[addr]); chip->polling_mode = 1; goto again; } @@ -672,7 +712,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus) snd_printk(KERN_ERR "hda_intel: azx_get_response timeout, " "switching to single_cmd mode: last cmd=0x%08x\n", - chip->last_cmd); + chip->last_cmd[addr]); chip->single_cmd = 1; bus->response_reset = 0; /* re-initialize CORB/RIRB */ @@ -692,7 +732,7 @@ static unsigned int azx_rirb_get_response(struct hda_bus *bus) */ /* receive a response */ -static int azx_single_wait_for_response(struct azx *chip) +static int azx_single_wait_for_response(struct azx *chip, unsigned int addr) { int timeout = 50; @@ -700,7 +740,7 @@ static int azx_single_wait_for_response(struct azx *chip) /* check IRV busy bit */ if (azx_readw(chip, IRS) & ICH6_IRS_VALID) { /* reuse rirb.res as the response return value */ - chip->rirb.res = azx_readl(chip, IR); + chip->rirb.res[addr] = azx_readl(chip, IR); return 0; } udelay(1); @@ -708,7 +748,7 @@ static int azx_single_wait_for_response(struct azx *chip) if (printk_ratelimit()) snd_printd(SFX "get_response timeout: IRS=0x%x\n", azx_readw(chip, IRS)); - chip->rirb.res = -1; + chip->rirb.res[addr] = -1; return -EIO; } @@ -716,6 +756,7 @@ static int azx_single_wait_for_response(struct azx *chip) static int azx_single_send_cmd(struct hda_bus *bus, u32 val) { struct azx *chip = bus->private_data; + unsigned int addr = azx_command_addr(val); int timeout = 50; bus->rirb_error = 0; @@ -728,7 +769,7 @@ static int azx_single_send_cmd(struct hda_bus *bus, u32 val) azx_writel(chip, IC, val); azx_writew(chip, IRS, azx_readw(chip, IRS) | ICH6_IRS_BUSY); - return azx_single_wait_for_response(chip); + return azx_single_wait_for_response(chip, addr); } udelay(1); } @@ -739,10 +780,11 @@ static int azx_single_send_cmd(struct hda_bus *bus, u32 val) } /* receive a response */ -static unsigned int azx_single_get_response(struct hda_bus *bus) +static unsigned int azx_single_get_response(struct hda_bus *bus, + unsigned int addr) { struct azx *chip = bus->private_data; - return chip->rirb.res; + return chip->rirb.res[addr]; } /* @@ -757,7 +799,7 @@ static int azx_send_cmd(struct hda_bus *bus, unsigned int val) { struct azx *chip = bus->private_data; - chip->last_cmd = val; + chip->last_cmd[azx_command_addr(val)] = val; if (chip->single_cmd) return azx_single_send_cmd(bus, val); else @@ -765,13 +807,14 @@ static int azx_send_cmd(struct hda_bus *bus, unsigned int val) } /* get a response */ -static unsigned int azx_get_response(struct hda_bus *bus) +static unsigned int azx_get_response(struct hda_bus *bus, + unsigned int addr) { struct azx *chip = bus->private_data; if (chip->single_cmd) - return azx_single_get_response(bus); + return azx_single_get_response(bus, addr); else - return azx_rirb_get_response(bus); + return azx_rirb_get_response(bus, addr); } #ifdef CONFIG_SND_HDA_POWER_SAVE @@ -1243,10 +1286,12 @@ static int probe_codec(struct azx *chip, int addr) (AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID; unsigned int res; + mutex_lock(&chip->bus->cmd_mutex); chip->probing = 1; azx_send_cmd(chip->bus, cmd); - res = azx_get_response(chip->bus); + res = azx_get_response(chip->bus, addr); chip->probing = 0; + mutex_unlock(&chip->bus->cmd_mutex); if (res == -1) return -EIO; snd_printdd(SFX "codec #%d probed OK\n", addr); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b95df5d..fea9767 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -559,7 +559,7 @@ static int alc_pin_mode_get(struct snd_kcontrol *kcontrol, /* Find enumerated value for current pinctl setting */ i = alc_pin_mode_min(dir); - while (alc_pin_mode_values[i] != pinctl && i <= alc_pin_mode_max(dir)) + while (i <= alc_pin_mode_max(dir) && alc_pin_mode_values[i] != pinctl) i++; *valp = i <= alc_pin_mode_max(dir) ? i: alc_pin_mode_min(dir); return 0; @@ -13563,6 +13563,8 @@ static int patch_alc269(struct hda_codec *codec) set_capture_mixer(spec); set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT); + spec->vmaster_nid = 0x02; + codec->patch_ops = alc_patch_ops; if (board_config == ALC269_AUTO) spec->init_hook = alc269_auto_init; @@ -15157,7 +15159,7 @@ static struct snd_pci_quirk alc861vd_cfg_tbl[] = { SND_PCI_QUIRK(0x10de, 0x03f0, "Realtek ALC660 demo", ALC660VD_3ST), SND_PCI_QUIRK(0x1179, 0xff00, "Toshiba A135", ALC861VD_LENOVO), /*SND_PCI_QUIRK(0x1179, 0xff00, "DALLAS", ALC861VD_DALLAS),*/ /*lenovo*/ - SND_PCI_QUIRK(0x1179, 0xff01, "DALLAS", ALC861VD_DALLAS), + SND_PCI_QUIRK(0x1179, 0xff01, "Toshiba A135", ALC861VD_LENOVO), SND_PCI_QUIRK(0x1179, 0xff03, "Toshiba P205", ALC861VD_LENOVO), SND_PCI_QUIRK(0x1179, 0xff31, "Toshiba L30-149", ALC861VD_DALLAS), SND_PCI_QUIRK(0x1565, 0x820d, "Biostar NF61S SE", ALC861VD_6ST_DIG), @@ -15577,9 +15579,12 @@ static int patch_alc861vd(struct hda_codec *codec) spec->stream_digital_playback = &alc861vd_pcm_digital_playback; spec->stream_digital_capture = &alc861vd_pcm_digital_capture; - spec->adc_nids = alc861vd_adc_nids; - spec->num_adc_nids = ARRAY_SIZE(alc861vd_adc_nids); - spec->capsrc_nids = alc861vd_capsrc_nids; + if (!spec->adc_nids) { + spec->adc_nids = alc861vd_adc_nids; + spec->num_adc_nids = ARRAY_SIZE(alc861vd_adc_nids); + } + if (!spec->capsrc_nids) + spec->capsrc_nids = alc861vd_capsrc_nids; set_capture_mixer(spec); set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT); @@ -17496,9 +17501,12 @@ static int patch_alc662(struct hda_codec *codec) spec->stream_digital_playback = &alc662_pcm_digital_playback; spec->stream_digital_capture = &alc662_pcm_digital_capture; - spec->adc_nids = alc662_adc_nids; - spec->num_adc_nids = ARRAY_SIZE(alc662_adc_nids); - spec->capsrc_nids = alc662_capsrc_nids; + if (!spec->adc_nids) { + spec->adc_nids = alc662_adc_nids; + spec->num_adc_nids = ARRAY_SIZE(alc662_adc_nids); + } + if (!spec->capsrc_nids) + spec->capsrc_nids = alc662_capsrc_nids; if (!spec->cap_mixer) set_capture_mixer(spec); diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 5383d8c..456ef6a 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -2266,7 +2266,7 @@ static struct snd_pci_quirk stac927x_cfg_tbl[] = { SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x01f3, "Dell Inspiron 1420", STAC_DELL_BIOS), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0227, "Dell Vostro 1400 ", STAC_DELL_BIOS), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x022e, "Dell ", STAC_DELL_BIOS), - SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x022f, "Dell Inspiron 1525", STAC_DELL_3ST), + SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x022f, "Dell Inspiron 1525", STAC_DELL_BIOS), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0242, "Dell ", STAC_DELL_BIOS), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0243, "Dell ", STAC_DELL_BIOS), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x02ff, "Dell ", STAC_DELL_BIOS), @@ -5645,6 +5645,13 @@ static int patch_stac927x(struct hda_codec *codec) /* GPIO2 High = Enable EAPD */ spec->eapd_mask = spec->gpio_mask = spec->gpio_dir = 0x04; spec->gpio_data = 0x04; + switch (codec->subsystem_id) { + case 0x1028022f: + /* correct EAPD to be GPIO0 */ + spec->eapd_mask = spec->gpio_mask = 0x01; + spec->gpio_dir = spec->gpio_data = 0x01; + break; + }; spec->dmic_nids = stac927x_dmic_nids; spec->num_dmics = STAC927X_NUM_DMICS; diff --git a/sound/soc/fsl/efika-audio-fabric.c b/sound/soc/fsl/efika-audio-fabric.c index 85b0e75..3326e2a 100644 --- a/sound/soc/fsl/efika-audio-fabric.c +++ b/sound/soc/fsl/efika-audio-fabric.c @@ -30,6 +30,8 @@ #include "mpc5200_psc_ac97.h" #include "../codecs/stac9766.h" +#define DRV_NAME "efika-audio-fabric" + static struct snd_soc_device device; static struct snd_soc_card card; diff --git a/sound/soc/fsl/pcm030-audio-fabric.c b/sound/soc/fsl/pcm030-audio-fabric.c index 8766f7a..b928ef7 100644 --- a/sound/soc/fsl/pcm030-audio-fabric.c +++ b/sound/soc/fsl/pcm030-audio-fabric.c @@ -30,6 +30,8 @@ #include "mpc5200_psc_ac97.h" #include "../codecs/wm9712.h" +#define DRV_NAME "pcm030-audio-fabric" + static struct snd_soc_device device; static struct snd_soc_card card; diff --git a/tools/perf/Documentation/perf-examples.txt b/tools/perf/Documentation/perf-examples.txt new file mode 100644 index 0000000..8eb6c48 --- /dev/null +++ b/tools/perf/Documentation/perf-examples.txt @@ -0,0 +1,225 @@ + + ------------------------------ + ****** perf by examples ****** + ------------------------------ + +[ From an e-mail by Ingo Molnar, http://lkml.org/lkml/2009/8/4/346 ] + + +First, discovery/enumeration of available counters can be done via +'perf list': + +titan:~> perf list + [...] + kmem:kmalloc [Tracepoint event] + kmem:kmem_cache_alloc [Tracepoint event] + kmem:kmalloc_node [Tracepoint event] + kmem:kmem_cache_alloc_node [Tracepoint event] + kmem:kfree [Tracepoint event] + kmem:kmem_cache_free [Tracepoint event] + kmem:mm_page_free_direct [Tracepoint event] + kmem:mm_pagevec_free [Tracepoint event] + kmem:mm_page_alloc [Tracepoint event] + kmem:mm_page_alloc_zone_locked [Tracepoint event] + kmem:mm_page_pcpu_drain [Tracepoint event] + kmem:mm_page_alloc_extfrag [Tracepoint event] + +Then any (or all) of the above event sources can be activated and +measured. For example the page alloc/free properties of a 'hackbench +run' are: + + titan:~> perf stat -e kmem:mm_page_pcpu_drain -e kmem:mm_page_alloc + -e kmem:mm_pagevec_free -e kmem:mm_page_free_direct ./hackbench 10 + Time: 0.575 + + Performance counter stats for './hackbench 10': + + 13857 kmem:mm_page_pcpu_drain + 27576 kmem:mm_page_alloc + 6025 kmem:mm_pagevec_free + 20934 kmem:mm_page_free_direct + + 0.613972165 seconds time elapsed + +You can observe the statistical properties as well, by using the +'repeat the workload N times' feature of perf stat: + + titan:~> perf stat --repeat 5 -e kmem:mm_page_pcpu_drain -e + kmem:mm_page_alloc -e kmem:mm_pagevec_free -e + kmem:mm_page_free_direct ./hackbench 10 + Time: 0.627 + Time: 0.644 + Time: 0.564 + Time: 0.559 + Time: 0.626 + + Performance counter stats for './hackbench 10' (5 runs): + + 12920 kmem:mm_page_pcpu_drain ( +- 3.359% ) + 25035 kmem:mm_page_alloc ( +- 3.783% ) + 6104 kmem:mm_pagevec_free ( +- 0.934% ) + 18376 kmem:mm_page_free_direct ( +- 4.941% ) + + 0.643954516 seconds time elapsed ( +- 2.363% ) + +Furthermore, these tracepoints can be used to sample the workload as +well. For example the page allocations done by a 'git gc' can be +captured the following way: + + titan:~/git> perf record -f -e kmem:mm_page_alloc -c 1 ./git gc + Counting objects: 1148, done. + Delta compression using up to 2 threads. + Compressing objects: 100% (450/450), done. + Writing objects: 100% (1148/1148), done. + Total 1148 (delta 690), reused 1148 (delta 690) + [ perf record: Captured and wrote 0.267 MB perf.data (~11679 samples) ] + +To check which functions generated page allocations: + + titan:~/git> perf report + # Samples: 10646 + # + # Overhead Command Shared Object + # ........ ............... .......................... + # + 23.57% git-repack /lib64/libc-2.5.so + 21.81% git /lib64/libc-2.5.so + 14.59% git ./git + 11.79% git-repack ./git + 7.12% git /lib64/ld-2.5.so + 3.16% git-repack /lib64/libpthread-2.5.so + 2.09% git-repack /bin/bash + 1.97% rm /lib64/libc-2.5.so + 1.39% mv /lib64/ld-2.5.so + 1.37% mv /lib64/libc-2.5.so + 1.12% git-repack /lib64/ld-2.5.so + 0.95% rm /lib64/ld-2.5.so + 0.90% git-update-serv /lib64/libc-2.5.so + 0.73% git-update-serv /lib64/ld-2.5.so + 0.68% perf /lib64/libpthread-2.5.so + 0.64% git-repack /usr/lib64/libz.so.1.2.3 + +Or to see it on a more finegrained level: + +titan:~/git> perf report --sort comm,dso,symbol +# Samples: 10646 +# +# Overhead Command Shared Object Symbol +# ........ ............... .......................... ...... +# + 9.35% git-repack ./git [.] insert_obj_hash + 9.12% git ./git [.] insert_obj_hash + 7.31% git /lib64/libc-2.5.so [.] memcpy + 6.34% git-repack /lib64/libc-2.5.so [.] _int_malloc + 6.24% git-repack /lib64/libc-2.5.so [.] memcpy + 5.82% git-repack /lib64/libc-2.5.so [.] __GI___fork + 5.47% git /lib64/libc-2.5.so [.] _int_malloc + 2.99% git /lib64/libc-2.5.so [.] memset + +Furthermore, call-graph sampling can be done too, of page +allocations - to see precisely what kind of page allocations there +are: + + titan:~/git> perf record -f -g -e kmem:mm_page_alloc -c 1 ./git gc + Counting objects: 1148, done. + Delta compression using up to 2 threads. + Compressing objects: 100% (450/450), done. + Writing objects: 100% (1148/1148), done. + Total 1148 (delta 690), reused 1148 (delta 690) + [ perf record: Captured and wrote 0.963 MB perf.data (~42069 samples) ] + + titan:~/git> perf report -g + # Samples: 10686 + # + # Overhead Command Shared Object + # ........ ............... .......................... + # + 23.25% git-repack /lib64/libc-2.5.so + | + |--50.00%-- _int_free + | + |--37.50%-- __GI___fork + | make_child + | + |--12.50%-- ptmalloc_unlock_all2 + | make_child + | + --6.25%-- __GI_strcpy + 21.61% git /lib64/libc-2.5.so + | + |--30.00%-- __GI_read + | | + | --83.33%-- git_config_from_file + | git_config + | | + [...] + +Or you can observe the whole system's page allocations for 10 +seconds: + +titan:~/git> perf stat -a -e kmem:mm_page_pcpu_drain -e +kmem:mm_page_alloc -e kmem:mm_pagevec_free -e +kmem:mm_page_free_direct sleep 10 + + Performance counter stats for 'sleep 10': + + 171585 kmem:mm_page_pcpu_drain + 322114 kmem:mm_page_alloc + 73623 kmem:mm_pagevec_free + 254115 kmem:mm_page_free_direct + + 10.000591410 seconds time elapsed + +Or observe how fluctuating the page allocations are, via statistical +analysis done over ten 1-second intervals: + + titan:~/git> perf stat --repeat 10 -a -e kmem:mm_page_pcpu_drain -e + kmem:mm_page_alloc -e kmem:mm_pagevec_free -e + kmem:mm_page_free_direct sleep 1 + + Performance counter stats for 'sleep 1' (10 runs): + + 17254 kmem:mm_page_pcpu_drain ( +- 3.709% ) + 34394 kmem:mm_page_alloc ( +- 4.617% ) + 7509 kmem:mm_pagevec_free ( +- 4.820% ) + 25653 kmem:mm_page_free_direct ( +- 3.672% ) + + 1.058135029 seconds time elapsed ( +- 3.089% ) + +Or you can annotate the recorded 'git gc' run on a per symbol basis +and check which instructions/source-code generated page allocations: + + titan:~/git> perf annotate __GI___fork + ------------------------------------------------ + Percent | Source code & Disassembly of libc-2.5.so + ------------------------------------------------ + : + : + : Disassembly of section .plt: + : Disassembly of section .text: + : + : 00000031a2e95560 <__fork>: + [...] + 0.00 : 31a2e95602: b8 38 00 00 00 mov $0x38,%eax + 0.00 : 31a2e95607: 0f 05 syscall + 83.42 : 31a2e95609: 48 3d 00 f0 ff ff cmp $0xfffffffffffff000,%rax + 0.00 : 31a2e9560f: 0f 87 4d 01 00 00 ja 31a2e95762 <__fork+0x202> + 0.00 : 31a2e95615: 85 c0 test %eax,%eax + +( this shows that 83.42% of __GI___fork's page allocations come from + the 0x38 system call it performs. ) + +etc. etc. - a lot more is possible. I could list a dozen of +other different usecases straight away - neither of which is +possible via /proc/vmstat. + +/proc/vmstat is not in the same league really, in terms of +expressive power of system analysis and performance +analysis. + +All that the above results needed were those new tracepoints +in include/tracing/events/kmem.h. + + Ingo + + diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 1dbc1ee..6be696b 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -29,13 +29,67 @@ OPTIONS Select the PMU event. Selection can be a symbolic event name (use 'perf list' to list all events) or a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + hexadecimal event descriptor. -a:: - system-wide collection + System-wide collection. -l:: - scale counter values + Scale counter values. + +-p:: +--pid=:: + Record events on existing pid. + +-r:: +--realtime=:: + Collect data with this RT SCHED_FIFO priority. +-A:: +--append:: + Append to the output file to do incremental profiling. + +-f:: +--force:: + Overwrite existing data file. + +-c:: +--count=:: + Event period to sample. + +-o:: +--output=:: + Output file name. + +-i:: +--inherit:: + Child tasks inherit counters. +-F:: +--freq=:: + Profile at this frequency. + +-m:: +--mmap-pages=:: + Number of mmap data pages. + +-g:: +--call-graph:: + Do call-graph (stack chain/backtrace) recording. + +-v:: +--verbose:: + Be more verbose (show counter open errors, etc). + +-s:: +--stat:: + Per thread counts. + +-d:: +--data:: + Sample addresses. + +-n:: +--no-samples:: + Don't sample. SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 0d74346..484080d 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -40,7 +40,7 @@ OPTIONS -a:: system-wide collection --S:: +-c:: scale counter values EXAMPLES diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 539d012..4a7d558 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -3,36 +3,122 @@ perf-top(1) NAME ---- -perf-top - Run a command and profile it +perf-top - System profiling tool. SYNOPSIS -------- [verse] -'perf top' [-e <EVENT> | --event=EVENT] [-l] [-a] <command> +'perf top' [-e <EVENT> | --event=EVENT] [<options>] DESCRIPTION ----------- -This command runs a command and gathers a performance counter profile -from it. +This command generates and displays a performance counter profile in realtime. OPTIONS ------- -<command>...:: - Any command you can specify in a shell. +-a:: +--all-cpus:: + System-wide collection. (default) + +-c <count>:: +--count=<count>:: + Event period to sample. + +-C <cpu>:: +--CPU=<cpu>:: + CPU to profile. + +-d <seconds>:: +--delay=<seconds>:: + Number of seconds to delay between refreshes. --e:: ---event=:: +-e <event>:: +--event=<event>:: Select the PMU event. Selection can be a symbolic event name (use 'perf list' to list all events) or a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a - hexadecimal event descriptor. + hexadecimal event descriptor. --a:: - system-wide collection +-E <entries>:: +--entries=<entries>:: + Display this many functions. + +-f <count>:: +--count-filter=<count>:: + Only display functions with more events than this. + +-F <freq>:: +--freq=<freq>:: + Profile at this frequency. + +-i:: +--inherit:: + Child tasks inherit counters, only makes sens with -p option. + +-k <path>:: +--vmlinux=<path>:: + Path to vmlinux. Required for annotation functionality. + +-m <pages>:: +--mmap-pages=<pages>:: + Number of mmapped data pages. + +-p <pid>:: +--pid=<pid>:: + Profile events on existing pid. + +-r <priority>:: +--realtime=<priority>:: + Collect data with this RT SCHED_FIFO priority. + +-s <symbol>:: +--sym-annotate=<symbol>:: + Annotate this symbol. Requires -k option. + +-v:: +--verbose:: + Be more verbose (show counter open errors, etc). + +-z:: +--zero:: + Zero history across display updates. + +INTERACTIVE PROMPTING KEYS +-------------------------- + +[d]:: + Display refresh delay. + +[e]:: + Number of entries to display. + +[E]:: + Event to display when multiple counters are active. + +[f]:: + Profile display filter (>= hit count). + +[F]:: + Annotation display filter (>= % of total). + +[s]:: + Annotate symbol. + +[S]:: + Stop annotation, return to full profile display. + +[w]:: + Toggle between weighted sum and individual count[E]r profile. + +[z]:: + Toggle event count zeroing across display updates. + +[qQ]:: + Quit. + +Pressing any unmapped key displays a menu, and prompts for input. --l:: - scale counter values SEE ALSO -------- diff --git a/tools/perf/Makefile b/tools/perf/Makefile index a5e9b87..c045b42 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -158,8 +158,10 @@ uname_P := $(shell sh -c 'uname -p 2>/dev/null || echo not') uname_V := $(shell sh -c 'uname -v 2>/dev/null || echo not') # If we're on a 64-bit kernel, use -m64 -ifneq ($(patsubst %64,%,$(uname_M)),$(uname_M)) - M64 := -m64 +ifndef NO_64BIT + ifneq ($(patsubst %64,%,$(uname_M)),$(uname_M)) + M64 := -m64 + endif endif # CFLAGS and LDFLAGS are for the users to override from the command line. @@ -345,7 +347,6 @@ BUILTIN_OBJS += builtin-stat.o BUILTIN_OBJS += builtin-top.o PERFLIBS = $(LIB_FILE) -EXTLIBS = -lbfd # # Platform specific tweaks @@ -374,6 +375,39 @@ ifeq ($(uname_S),Darwin) PTHREAD_LIBS = endif +ifneq ($(shell sh -c "(echo '\#include <libelf.h>'; echo 'int main(void) { Elf * elf = elf_begin(0, ELF_C_READ_MMAP, 0); return (long)elf; }') | $(CC) -x c - $(ALL_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -o /dev/null $(ALL_LDFLAGS) > /dev/null 2>&1 && echo y"), y) + msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel); +endif + +ifdef NO_DEMANGLE + BASIC_CFLAGS += -DNO_DEMANGLE +else + has_bfd := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd > /dev/null 2>&1 && echo y") + + ifeq ($(has_bfd),y) + EXTLIBS += -lbfd + else + has_bfd_iberty := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd -liberty > /dev/null 2>&1 && echo y") + ifeq ($(has_bfd_iberty),y) + EXTLIBS += -lbfd -liberty + else + has_bfd_iberty_z := $(shell sh -c "(echo '\#include <bfd.h>'; echo 'int main(void) { bfd_demangle(0, 0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -lbfd -liberty -lz > /dev/null 2>&1 && echo y") + ifeq ($(has_bfd_iberty_z),y) + EXTLIBS += -lbfd -liberty -lz + else + has_cplus_demangle := $(shell sh -c "(echo 'extern char *cplus_demangle(const char *, int);'; echo 'int main(void) { cplus_demangle(0, 0); return 0; }') | $(CC) -x c - $(ALL_CFLAGS) -o /dev/null $(ALL_LDFLAGS) -liberty > /dev/null 2>&1 && echo y") + ifeq ($(has_cplus_demangle),y) + EXTLIBS += -liberty + BASIC_CFLAGS += -DHAVE_CPLUS_DEMANGLE + else + msg := $(warning No bfd.h/libbfd found, install binutils-dev[el] to gain symbol demangling) + BASIC_CFLAGS += -DNO_DEMANGLE + endif + endif + endif + endif +endif + ifndef CC_LD_DYNPATH ifdef NO_R_TO_GCC_LINKER # Some gcc does not accept and pass -R to the linker to specify diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index f990fa8..d88c696 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -10,11 +10,12 @@ #include "perf.h" -#include "util/parse-options.h" #include "util/parse-events.h" +#include "util/cache.h" int cmd_list(int argc __used, const char **argv __used, const char *prefix __used) { + setup_pager(); print_events(); return 0; } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 6da0992..3d051b9 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -34,7 +34,9 @@ static int output; static const char *output_name = "perf.data"; static int group = 0; static unsigned int realtime_prio = 0; +static int raw_samples = 0; static int system_wide = 0; +static int profile_cpu = -1; static pid_t target_pid = -1; static int inherit = 1; static int force = 0; @@ -203,46 +205,48 @@ static void sig_atexit(void) kill(getpid(), signr); } -static void pid_synthesize_comm_event(pid_t pid, int full) +static pid_t pid_synthesize_comm_event(pid_t pid, int full) { struct comm_event comm_ev; char filename[PATH_MAX]; char bf[BUFSIZ]; - int fd; - size_t size; - char *field, *sep; + FILE *fp; + size_t size = 0; DIR *tasks; struct dirent dirent, *next; + pid_t tgid = 0; - snprintf(filename, sizeof(filename), "/proc/%d/stat", pid); + snprintf(filename, sizeof(filename), "/proc/%d/status", pid); - fd = open(filename, O_RDONLY); - if (fd < 0) { + fp = fopen(filename, "r"); + if (fd == NULL) { /* * We raced with a task exiting - just return: */ if (verbose) fprintf(stderr, "couldn't open %s\n", filename); - return; + return 0; } - if (read(fd, bf, sizeof(bf)) < 0) { - fprintf(stderr, "couldn't read %s\n", filename); - exit(EXIT_FAILURE); - } - close(fd); - /* 9027 (cat) R 6747 9027 6747 34816 9027 ... */ memset(&comm_ev, 0, sizeof(comm_ev)); - field = strchr(bf, '('); - if (field == NULL) - goto out_failure; - sep = strchr(++field, ')'); - if (sep == NULL) - goto out_failure; - size = sep - field; - memcpy(comm_ev.comm, field, size++); - - comm_ev.pid = pid; + while (!comm_ev.comm[0] || !comm_ev.pid) { + if (fgets(bf, sizeof(bf), fp) == NULL) + goto out_failure; + + if (memcmp(bf, "Name:", 5) == 0) { + char *name = bf + 5; + while (*name && isspace(*name)) + ++name; + size = strlen(name) - 1; + memcpy(comm_ev.comm, name, size++); + } else if (memcmp(bf, "Tgid:", 5) == 0) { + char *tgids = bf + 5; + while (*tgids && isspace(*tgids)) + ++tgids; + tgid = comm_ev.pid = atoi(tgids); + } + } + comm_ev.header.type = PERF_EVENT_COMM; size = ALIGN(size, sizeof(u64)); comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size); @@ -251,7 +255,7 @@ static void pid_synthesize_comm_event(pid_t pid, int full) comm_ev.tid = pid; write_output(&comm_ev, comm_ev.header.size); - return; + goto out_fclose; } snprintf(filename, sizeof(filename), "/proc/%d/task", pid); @@ -268,7 +272,10 @@ static void pid_synthesize_comm_event(pid_t pid, int full) write_output(&comm_ev, comm_ev.header.size); } closedir(tasks); - return; + +out_fclose: + fclose(fp); + return tgid; out_failure: fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n", @@ -276,7 +283,7 @@ out_failure: exit(EXIT_FAILURE); } -static void pid_synthesize_mmap_samples(pid_t pid) +static void pid_synthesize_mmap_samples(pid_t pid, pid_t tgid) { char filename[PATH_MAX]; FILE *fp; @@ -328,7 +335,7 @@ static void pid_synthesize_mmap_samples(pid_t pid) mmap_ev.len -= mmap_ev.start; mmap_ev.header.size = (sizeof(mmap_ev) - (sizeof(mmap_ev.filename) - size)); - mmap_ev.pid = pid; + mmap_ev.pid = tgid; mmap_ev.tid = pid; write_output(&mmap_ev, mmap_ev.header.size); @@ -347,14 +354,14 @@ static void synthesize_all(void) while (!readdir_r(proc, &dirent, &next) && next) { char *end; - pid_t pid; + pid_t pid, tgid; pid = strtol(dirent.d_name, &end, 10); if (*end) /* only interested in proper numerical dirents */ continue; - pid_synthesize_comm_event(pid, 1); - pid_synthesize_mmap_samples(pid); + tgid = pid_synthesize_comm_event(pid, 1); + pid_synthesize_mmap_samples(pid, tgid); } closedir(proc); @@ -392,7 +399,7 @@ static void create_counter(int counter, int cpu, pid_t pid) PERF_FORMAT_TOTAL_TIME_RUNNING | PERF_FORMAT_ID; - attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID; + attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID; if (freq) { attr->sample_type |= PERF_SAMPLE_PERIOD; @@ -412,6 +419,9 @@ static void create_counter(int counter, int cpu, pid_t pid) if (call_graph) attr->sample_type |= PERF_SAMPLE_CALLCHAIN; + if (raw_samples) + attr->sample_type |= PERF_SAMPLE_RAW; + attr->mmap = track; attr->comm = track; attr->inherit = (cpu < 0) && inherit; @@ -425,6 +435,8 @@ try_again: if (err == EPERM) die("Permission error - are you root?\n"); + else if (err == ENODEV && profile_cpu != -1) + die("No such device - did you specify an out-of-range profile CPU?\n"); /* * If it's cycles then fall back to hrtimer @@ -524,10 +536,14 @@ static int __cmd_record(int argc, const char **argv) signal(SIGCHLD, sig_handler); signal(SIGINT, sig_handler); - if (!stat(output_name, &st) && !force && !append_file) { - fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n", - output_name); - exit(-1); + if (!stat(output_name, &st) && st.st_size) { + if (!force && !append_file) { + fprintf(stderr, "Error, output file %s exists, use -A to append or -f to overwrite.\n", + output_name); + exit(-1); + } + } else { + append_file = 0; } flags = O_CREAT|O_RDWR; @@ -554,16 +570,22 @@ static int __cmd_record(int argc, const char **argv) if (pid == -1) pid = getpid(); - open_counters(-1, pid); - } else for (i = 0; i < nr_cpus; i++) - open_counters(i, target_pid); + open_counters(profile_cpu, pid); + } else { + if (profile_cpu != -1) { + open_counters(profile_cpu, target_pid); + } else { + for (i = 0; i < nr_cpus; i++) + open_counters(i, target_pid); + } + } if (file_new) perf_header__write(header, output); if (!system_wide) { - pid_synthesize_comm_event(pid, 0); - pid_synthesize_mmap_samples(pid); + pid_t tgid = pid_synthesize_comm_event(pid, 0); + pid_synthesize_mmap_samples(pid, tgid); } else synthesize_all(); @@ -631,10 +653,14 @@ static const struct option options[] = { "record events on existing pid"), OPT_INTEGER('r', "realtime", &realtime_prio, "collect data with this RT SCHED_FIFO priority"), + OPT_BOOLEAN('R', "raw-samples", &raw_samples, + "collect raw sample records from all opened counters"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_BOOLEAN('A', "append", &append_file, "append to the output file to do incremental profiling"), + OPT_INTEGER('C', "profile_cpu", &profile_cpu, + "CPU to profile on"), OPT_BOOLEAN('f', "force", &force, "overwrite existing data file"), OPT_LONG('c', "count", &default_interval, diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index b20a4b6..b53a60f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -31,7 +31,7 @@ static char const *input_name = "perf.data"; static char *vmlinux = NULL; -static char default_sort_order[] = "comm,dso"; +static char default_sort_order[] = "comm,dso,symbol"; static char *sort_order = default_sort_order; static char *dso_list_str, *comm_list_str, *sym_list_str, *col_width_list_str; @@ -68,7 +68,7 @@ static int callchain; static struct callchain_param callchain_param = { - .mode = CHAIN_GRAPH_ABS, + .mode = CHAIN_GRAPH_REL, .min_percent = 0.5 }; @@ -99,6 +99,7 @@ struct comm_event { struct fork_event { struct perf_event_header header; u32 pid, ppid; + u32 tid, ptid; }; struct lost_event { @@ -111,7 +112,9 @@ struct read_event { struct perf_event_header header; u32 pid,tid; u64 value; - u64 format[3]; + u64 time_enabled; + u64 time_running; + u64 id; }; typedef union event_union { @@ -252,7 +255,7 @@ static int strcommon(const char *pathname) { int n = 0; - while (pathname[n] == cwd[n] && n < cwdlen) + while (n < cwdlen && pathname[n] == cwd[n]) ++n; return n; @@ -697,7 +700,8 @@ sort__sym_print(FILE *fp, struct hist_entry *self, unsigned int width __used) size_t ret = 0; if (verbose) - ret += repsep_fprintf(fp, "%#018llx ", (u64)self->ip); + ret += repsep_fprintf(fp, "%#018llx %c ", (u64)self->ip, + dso__symtab_origin(self->dso)); ret += repsep_fprintf(fp, "[%c] ", self->level); if (self->sym) { @@ -887,6 +891,21 @@ ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain, int depth, return ret; } +static struct symbol *rem_sq_bracket; +static struct callchain_list rem_hits; + +static void init_rem_hits(void) +{ + rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6); + if (!rem_sq_bracket) { + fprintf(stderr, "Not enough memory to display remaining hits\n"); + return; + } + + strcpy(rem_sq_bracket->name, "[...]"); + rem_hits.sym = rem_sq_bracket; +} + static size_t callchain__fprintf_graph(FILE *fp, struct callchain_node *self, u64 total_samples, int depth, int depth_mask) @@ -896,25 +915,34 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self, struct callchain_list *chain; int new_depth_mask = depth_mask; u64 new_total; + u64 remaining; size_t ret = 0; int i; if (callchain_param.mode == CHAIN_GRAPH_REL) - new_total = self->cumul_hit; + new_total = self->children_hit; else new_total = total_samples; + remaining = new_total; + node = rb_first(&self->rb_root); while (node) { + u64 cumul; + child = rb_entry(node, struct callchain_node, rb_node); + cumul = cumul_hits(child); + remaining -= cumul; /* * The depth mask manages the output of pipes that show * the depth. We don't want to keep the pipes of the current - * level for the last child of this depth + * level for the last child of this depth. + * Except if we have remaining filtered hits. They will + * supersede the last child */ next = rb_next(node); - if (!next) + if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining)) new_depth_mask &= ~(1 << (depth - 1)); /* @@ -929,7 +957,7 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self, ret += ipchain__fprintf_graph(fp, chain, depth, new_depth_mask, i++, new_total, - child->cumul_hit); + cumul); } ret += callchain__fprintf_graph(fp, child, new_total, depth + 1, @@ -937,6 +965,19 @@ callchain__fprintf_graph(FILE *fp, struct callchain_node *self, node = next; } + if (callchain_param.mode == CHAIN_GRAPH_REL && + remaining && remaining != new_total) { + + if (!rem_sq_bracket) + return ret; + + new_depth_mask &= ~(1 << (depth - 1)); + + ret += ipchain__fprintf_graph(fp, &rem_hits, depth, + new_depth_mask, 0, new_total, + remaining); + } + return ret; } @@ -1357,6 +1398,8 @@ static size_t output__fprintf(FILE *fp, u64 total_samples) unsigned int width; char *col_width = col_width_list_str; + init_rem_hits(); + fprintf(fp, "# Samples: %Ld\n", (u64)total_samples); fprintf(fp, "#\n"); @@ -1423,11 +1466,13 @@ print_entries: if (sort_order == default_sort_order && parent_pattern == default_parent_pattern) { fprintf(fp, "#\n"); - fprintf(fp, "# (For more details, try: perf report --sort comm,dso,symbol)\n"); + fprintf(fp, "# (For a higher level overview, try: perf report --sort comm,dso)\n"); fprintf(fp, "#\n"); } fprintf(fp, "\n"); + free(rem_sq_bracket); + return ret; } @@ -1481,11 +1526,11 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) more_data += sizeof(u64); } - dprintf("%p [%p]: PERF_EVENT_SAMPLE (IP, %d): %d: %p period: %Ld\n", + dprintf("%p [%p]: PERF_EVENT_SAMPLE (IP, %d): %d/%d: %p period: %Ld\n", (void *)(offset + head), (void *)(long)(event->header.size), event->header.misc, - event->ip.pid, + event->ip.pid, event->ip.tid, (void *)(long)ip, (long long)period); @@ -1545,10 +1590,11 @@ process_sample_event(event_t *event, unsigned long offset, unsigned long head) if (show & show_mask) { struct symbol *sym = resolve_symbol(thread, &map, &dso, &ip); - if (dso_list && dso && dso->name && !strlist__has_entry(dso_list, dso->name)) + if (dso_list && (!dso || !dso->name || + !strlist__has_entry(dso_list, dso->name))) return 0; - if (sym_list && sym && !strlist__has_entry(sym_list, sym->name)) + if (sym_list && (!sym || !strlist__has_entry(sym_list, sym->name))) return 0; if (hist_entry__add(thread, map, dso, sym, ip, chain, level, period)) { @@ -1567,10 +1613,11 @@ process_mmap_event(event_t *event, unsigned long offset, unsigned long head) struct thread *thread = threads__findnew(event->mmap.pid); struct map *map = map__new(&event->mmap); - dprintf("%p [%p]: PERF_EVENT_MMAP %d: [%p(%p) @ %p]: %s\n", + dprintf("%p [%p]: PERF_EVENT_MMAP %d/%d: [%p(%p) @ %p]: %s\n", (void *)(offset + head), (void *)(long)(event->header.size), event->mmap.pid, + event->mmap.tid, (void *)(long)event->mmap.start, (void *)(long)event->mmap.len, (void *)(long)event->mmap.pgoff, @@ -1608,15 +1655,27 @@ process_comm_event(event_t *event, unsigned long offset, unsigned long head) } static int -process_fork_event(event_t *event, unsigned long offset, unsigned long head) +process_task_event(event_t *event, unsigned long offset, unsigned long head) { struct thread *thread = threads__findnew(event->fork.pid); struct thread *parent = threads__findnew(event->fork.ppid); - dprintf("%p [%p]: PERF_EVENT_FORK: %d:%d\n", + dprintf("%p [%p]: PERF_EVENT_%s: (%d:%d):(%d:%d)\n", (void *)(offset + head), (void *)(long)(event->header.size), - event->fork.pid, event->fork.ppid); + event->header.type == PERF_EVENT_FORK ? "FORK" : "EXIT", + event->fork.pid, event->fork.tid, + event->fork.ppid, event->fork.ptid); + + /* + * A thread clone will have the same PID for both + * parent and child. + */ + if (thread == parent) + return 0; + + if (event->header.type == PERF_EVENT_EXIT) + return 0; if (!thread || !parent || thread__fork(thread, parent)) { dprintf("problem processing PERF_EVENT_FORK, skipping event.\n"); @@ -1677,14 +1736,37 @@ static void trace_event(event_t *event) dprintf(".\n"); } +static struct perf_header *header; + +static struct perf_counter_attr *perf_header__find_attr(u64 id) +{ + int i; + + for (i = 0; i < header->attrs; i++) { + struct perf_header_attr *attr = header->attr[i]; + int j; + + for (j = 0; j < attr->ids; j++) { + if (attr->id[j] == id) + return &attr->attr; + } + } + + return NULL; +} + static int process_read_event(event_t *event, unsigned long offset, unsigned long head) { - dprintf("%p [%p]: PERF_EVENT_READ: %d %d %Lu\n", + struct perf_counter_attr *attr = perf_header__find_attr(event->read.id); + + dprintf("%p [%p]: PERF_EVENT_READ: %d %d %s %Lu\n", (void *)(offset + head), (void *)(long)(event->header.size), event->read.pid, event->read.tid, + attr ? __event_name(attr->type, attr->config) + : "FAIL", event->read.value); return 0; @@ -1706,7 +1788,8 @@ process_event(event_t *event, unsigned long offset, unsigned long head) return process_comm_event(event, offset, head); case PERF_EVENT_FORK: - return process_fork_event(event, offset, head); + case PERF_EVENT_EXIT: + return process_task_event(event, offset, head); case PERF_EVENT_LOST: return process_lost_event(event, offset, head); @@ -1729,8 +1812,6 @@ process_event(event_t *event, unsigned long offset, unsigned long head) return 0; } -static struct perf_header *header; - static u64 perf_header__sample_type(void) { u64 sample_type = 0; @@ -1798,6 +1879,13 @@ static int __cmd_report(void) " -g?\n"); exit(-1); } + } else if (callchain_param.mode != CHAIN_NONE && !callchain) { + callchain = 1; + if (register_callchain_param(&callchain_param) < 0) { + fprintf(stderr, "Can't register callchain" + " params\n"); + exit(-1); + } } if (load_kernel() < 0) { @@ -1936,6 +2024,13 @@ parse_callchain_opt(const struct option *opt __used, const char *arg, else if (!strncmp(tok, "fractal", strlen(arg))) callchain_param.mode = CHAIN_GRAPH_REL; + else if (!strncmp(tok, "none", strlen(arg))) { + callchain_param.mode = CHAIN_NONE; + callchain = 0; + + return 0; + } + else return -1; diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f9510ee..b4b06c7 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -496,7 +496,7 @@ static const struct option options[] = { "stat events on existing pid"), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), - OPT_BOOLEAN('S', "scale", &scale, + OPT_BOOLEAN('c', "scale", &scale, "scale/normalize counters"), OPT_BOOLEAN('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"), diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c0a4230..7de28ce 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -31,6 +31,8 @@ #include <fcntl.h> #include <stdio.h> +#include <termios.h> +#include <unistd.h> #include <errno.h> #include <time.h> @@ -54,7 +56,7 @@ static int system_wide = 0; static int default_interval = 100000; -static u64 count_filter = 5; +static int count_filter = 5; static int print_entries = 15; static int target_pid = -1; @@ -69,15 +71,28 @@ static int freq = 0; static int verbose = 0; static char *vmlinux = NULL; -static char *sym_filter; -static unsigned long filter_start; -static unsigned long filter_end; - static int delay_secs = 2; static int zero; static int dump_symtab; /* + * Source + */ + +struct source_line { + u64 eip; + unsigned long count[MAX_COUNTERS]; + char *line; + struct source_line *next; +}; + +static char *sym_filter = NULL; +struct sym_entry *sym_filter_entry = NULL; +static int sym_pcnt_filter = 5; +static int sym_counter = 0; +static int display_weighted = -1; + +/* * Symbols */ @@ -91,9 +106,237 @@ struct sym_entry { unsigned long snap_count; double weight; int skip; + struct source_line *source; + struct source_line *lines; + struct source_line **lines_tail; + pthread_mutex_t source_lock; }; -struct sym_entry *sym_filter_entry; +/* + * Source functions + */ + +static void parse_source(struct sym_entry *syme) +{ + struct symbol *sym; + struct module *module; + struct section *section = NULL; + FILE *file; + char command[PATH_MAX*2], *path = vmlinux; + u64 start, end, len; + + if (!syme) + return; + + if (syme->lines) { + pthread_mutex_lock(&syme->source_lock); + goto out_assign; + } + + sym = (struct symbol *)(syme + 1); + module = sym->module; + + if (module) + path = module->path; + if (!path) + return; + + start = sym->obj_start; + if (!start) + start = sym->start; + + if (module) { + section = module->sections->find_section(module->sections, ".text"); + if (section) + start -= section->vma; + } + + end = start + sym->end - sym->start + 1; + len = sym->end - sym->start; + + sprintf(command, "objdump --start-address=0x%016Lx --stop-address=0x%016Lx -dS %s", start, end, path); + + file = popen(command, "r"); + if (!file) + return; + + pthread_mutex_lock(&syme->source_lock); + syme->lines_tail = &syme->lines; + while (!feof(file)) { + struct source_line *src; + size_t dummy = 0; + char *c; + + src = malloc(sizeof(struct source_line)); + assert(src != NULL); + memset(src, 0, sizeof(struct source_line)); + + if (getline(&src->line, &dummy, file) < 0) + break; + if (!src->line) + break; + + c = strchr(src->line, '\n'); + if (c) + *c = 0; + + src->next = NULL; + *syme->lines_tail = src; + syme->lines_tail = &src->next; + + if (strlen(src->line)>8 && src->line[8] == ':') { + src->eip = strtoull(src->line, NULL, 16); + if (section) + src->eip += section->vma; + } + if (strlen(src->line)>8 && src->line[16] == ':') { + src->eip = strtoull(src->line, NULL, 16); + if (section) + src->eip += section->vma; + } + } + pclose(file); +out_assign: + sym_filter_entry = syme; + pthread_mutex_unlock(&syme->source_lock); +} + +static void __zero_source_counters(struct sym_entry *syme) +{ + int i; + struct source_line *line; + + line = syme->lines; + while (line) { + for (i = 0; i < nr_counters; i++) + line->count[i] = 0; + line = line->next; + } +} + +static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip) +{ + struct source_line *line; + + if (syme != sym_filter_entry) + return; + + if (pthread_mutex_trylock(&syme->source_lock)) + return; + + if (!syme->source) + goto out_unlock; + + for (line = syme->lines; line; line = line->next) { + if (line->eip == ip) { + line->count[counter]++; + break; + } + if (line->eip > ip) + break; + } +out_unlock: + pthread_mutex_unlock(&syme->source_lock); +} + +static void lookup_sym_source(struct sym_entry *syme) +{ + struct symbol *symbol = (struct symbol *)(syme + 1); + struct source_line *line; + char pattern[PATH_MAX]; + char *idx; + + sprintf(pattern, "<%s>:", symbol->name); + + if (symbol->module) { + idx = strstr(pattern, "\t"); + if (idx) + *idx = 0; + } + + pthread_mutex_lock(&syme->source_lock); + for (line = syme->lines; line; line = line->next) { + if (strstr(line->line, pattern)) { + syme->source = line; + break; + } + } + pthread_mutex_unlock(&syme->source_lock); +} + +static void show_lines(struct source_line *queue, int count, int total) +{ + int i; + struct source_line *line; + + line = queue; + for (i = 0; i < count; i++) { + float pcnt = 100.0*(float)line->count[sym_counter]/(float)total; + + printf("%8li %4.1f%%\t%s\n", line->count[sym_counter], pcnt, line->line); + line = line->next; + } +} + +#define TRACE_COUNT 3 + +static void show_details(struct sym_entry *syme) +{ + struct symbol *symbol; + struct source_line *line; + struct source_line *line_queue = NULL; + int displayed = 0; + int line_queue_count = 0, total = 0, more = 0; + + if (!syme) + return; + + if (!syme->source) + lookup_sym_source(syme); + + if (!syme->source) + return; + + symbol = (struct symbol *)(syme + 1); + printf("Showing %s for %s\n", event_name(sym_counter), symbol->name); + printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter); + + pthread_mutex_lock(&syme->source_lock); + line = syme->source; + while (line) { + total += line->count[sym_counter]; + line = line->next; + } + + line = syme->source; + while (line) { + float pcnt = 0.0; + + if (!line_queue_count) + line_queue = line; + line_queue_count++; + + if (line->count[sym_counter]) + pcnt = 100.0 * line->count[sym_counter] / (float)total; + if (pcnt >= (float)sym_pcnt_filter) { + if (displayed <= print_entries) + show_lines(line_queue, line_queue_count, total); + else more++; + displayed += line_queue_count; + line_queue_count = 0; + line_queue = NULL; + } else if (line_queue_count > TRACE_COUNT) { + line_queue = line_queue->next; + line_queue_count--; + } + + line->count[sym_counter] = zero ? 0 : line->count[sym_counter] * 7 / 8; + line = line->next; + } + pthread_mutex_unlock(&syme->source_lock); + if (more) + printf("%d lines not displayed, maybe increase display entries [e]\n", more); +} struct dso *kernel_dso; @@ -112,6 +355,9 @@ static double sym_weight(const struct sym_entry *sym) double weight = sym->snap_count; int counter; + if (!display_weighted) + return weight; + for (counter = 1; counter < nr_counters-1; counter++) weight *= sym->count[counter]; @@ -159,7 +405,7 @@ static void rb_insert_active_sym(struct rb_root *tree, struct sym_entry *se) static void print_sym_table(void) { int printed = 0, j; - int counter; + int counter, snap = !display_weighted ? sym_counter : 0; float samples_per_sec = samples/delay_secs; float ksamples_per_sec = (samples-userspace_samples)/delay_secs; float sum_ksamples = 0.0; @@ -175,7 +421,7 @@ static void print_sym_table(void) pthread_mutex_unlock(&active_symbols_lock); list_for_each_entry_safe_from(syme, n, &active_symbols, node) { - syme->snap_count = syme->count[0]; + syme->snap_count = syme->count[snap]; if (syme->snap_count != 0) { syme->weight = sym_weight(syme); rb_insert_active_sym(&tmp, syme); @@ -195,7 +441,7 @@ static void print_sym_table(void) samples_per_sec, 100.0 - (100.0*((samples_per_sec-ksamples_per_sec)/samples_per_sec))); - if (nr_counters == 1) { + if (nr_counters == 1 || !display_weighted) { printf("%Ld", (u64)attrs[0].sample_period); if (freq) printf("Hz "); @@ -203,7 +449,9 @@ static void print_sym_table(void) printf(" "); } - for (counter = 0; counter < nr_counters; counter++) { + if (!display_weighted) + printf("%s", event_name(sym_counter)); + else for (counter = 0; counter < nr_counters; counter++) { if (counter) printf("/"); @@ -228,6 +476,11 @@ static void print_sym_table(void) printf("------------------------------------------------------------------------------\n\n"); + if (sym_filter_entry) { + show_details(sym_filter_entry); + return; + } + if (nr_counters == 1) printf(" samples pcnt"); else @@ -242,13 +495,13 @@ static void print_sym_table(void) struct symbol *sym = (struct symbol *)(syme + 1); double pcnt; - if (++printed > print_entries || syme->snap_count < count_filter) + if (++printed > print_entries || (int)syme->snap_count < count_filter) continue; pcnt = 100.0 - (100.0 * ((sum_ksamples - syme->snap_count) / sum_ksamples)); - if (nr_counters == 1) + if (nr_counters == 1 || !display_weighted) printf("%20.2f - ", syme->weight); else printf("%9.1f %10ld - ", syme->weight, syme->snap_count); @@ -261,19 +514,250 @@ static void print_sym_table(void) } } +static void prompt_integer(int *target, const char *msg) +{ + char *buf = malloc(0), *p; + size_t dummy = 0; + int tmp; + + fprintf(stdout, "\n%s: ", msg); + if (getline(&buf, &dummy, stdin) < 0) + return; + + p = strchr(buf, '\n'); + if (p) + *p = 0; + + p = buf; + while(*p) { + if (!isdigit(*p)) + goto out_free; + p++; + } + tmp = strtoul(buf, NULL, 10); + *target = tmp; +out_free: + free(buf); +} + +static void prompt_percent(int *target, const char *msg) +{ + int tmp = 0; + + prompt_integer(&tmp, msg); + if (tmp >= 0 && tmp <= 100) + *target = tmp; +} + +static void prompt_symbol(struct sym_entry **target, const char *msg) +{ + char *buf = malloc(0), *p; + struct sym_entry *syme = *target, *n, *found = NULL; + size_t dummy = 0; + + /* zero counters of active symbol */ + if (syme) { + pthread_mutex_lock(&syme->source_lock); + __zero_source_counters(syme); + *target = NULL; + pthread_mutex_unlock(&syme->source_lock); + } + + fprintf(stdout, "\n%s: ", msg); + if (getline(&buf, &dummy, stdin) < 0) + goto out_free; + + p = strchr(buf, '\n'); + if (p) + *p = 0; + + pthread_mutex_lock(&active_symbols_lock); + syme = list_entry(active_symbols.next, struct sym_entry, node); + pthread_mutex_unlock(&active_symbols_lock); + + list_for_each_entry_safe_from(syme, n, &active_symbols, node) { + struct symbol *sym = (struct symbol *)(syme + 1); + + if (!strcmp(buf, sym->name)) { + found = syme; + break; + } + } + + if (!found) { + fprintf(stderr, "Sorry, %s is not active.\n", sym_filter); + sleep(1); + return; + } else + parse_source(found); + +out_free: + free(buf); +} + +static void print_mapped_keys(void) +{ + char *name = NULL; + + if (sym_filter_entry) { + struct symbol *sym = (struct symbol *)(sym_filter_entry+1); + name = sym->name; + } + + fprintf(stdout, "\nMapped keys:\n"); + fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", delay_secs); + fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", print_entries); + + if (nr_counters > 1) + fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(sym_counter)); + + fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", count_filter); + + if (vmlinux) { + fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter); + fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL"); + fprintf(stdout, "\t[S] stop annotation.\n"); + } + + if (nr_counters > 1) + fprintf(stdout, "\t[w] toggle display weighted/count[E]r. \t(%d)\n", display_weighted ? 1 : 0); + + fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", zero ? 1 : 0); + fprintf(stdout, "\t[qQ] quit.\n"); +} + +static int key_mapped(int c) +{ + switch (c) { + case 'd': + case 'e': + case 'f': + case 'z': + case 'q': + case 'Q': + return 1; + case 'E': + case 'w': + return nr_counters > 1 ? 1 : 0; + case 'F': + case 's': + case 'S': + return vmlinux ? 1 : 0; + } + + return 0; +} + +static void handle_keypress(int c) +{ + if (!key_mapped(c)) { + struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; + struct termios tc, save; + + print_mapped_keys(); + fprintf(stdout, "\nEnter selection, or unmapped key to continue: "); + fflush(stdout); + + tcgetattr(0, &save); + tc = save; + tc.c_lflag &= ~(ICANON | ECHO); + tc.c_cc[VMIN] = 0; + tc.c_cc[VTIME] = 0; + tcsetattr(0, TCSANOW, &tc); + + poll(&stdin_poll, 1, -1); + c = getc(stdin); + + tcsetattr(0, TCSAFLUSH, &save); + if (!key_mapped(c)) + return; + } + + switch (c) { + case 'd': + prompt_integer(&delay_secs, "Enter display delay"); + break; + case 'e': + prompt_integer(&print_entries, "Enter display entries (lines)"); + break; + case 'E': + if (nr_counters > 1) { + int i; + + fprintf(stderr, "\nAvailable events:"); + for (i = 0; i < nr_counters; i++) + fprintf(stderr, "\n\t%d %s", i, event_name(i)); + + prompt_integer(&sym_counter, "Enter details event counter"); + + if (sym_counter >= nr_counters) { + fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(0)); + sym_counter = 0; + sleep(1); + } + } else sym_counter = 0; + break; + case 'f': + prompt_integer(&count_filter, "Enter display event count filter"); + break; + case 'F': + prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)"); + break; + case 'q': + case 'Q': + printf("exiting.\n"); + exit(0); + case 's': + prompt_symbol(&sym_filter_entry, "Enter details symbol"); + break; + case 'S': + if (!sym_filter_entry) + break; + else { + struct sym_entry *syme = sym_filter_entry; + + pthread_mutex_lock(&syme->source_lock); + sym_filter_entry = NULL; + __zero_source_counters(syme); + pthread_mutex_unlock(&syme->source_lock); + } + break; + case 'w': + display_weighted = ~display_weighted; + break; + case 'z': + zero = ~zero; + break; + } +} + static void *display_thread(void *arg __used) { struct pollfd stdin_poll = { .fd = 0, .events = POLLIN }; - int delay_msecs = delay_secs * 1000; + struct termios tc, save; + int delay_msecs, c; + + tcgetattr(0, &save); + tc = save; + tc.c_lflag &= ~(ICANON | ECHO); + tc.c_cc[VMIN] = 0; + tc.c_cc[VTIME] = 0; - printf("PerfTop refresh period: %d seconds\n", delay_secs); +repeat: + delay_msecs = delay_secs * 1000; + tcsetattr(0, TCSANOW, &tc); + /* trash return*/ + getc(stdin); do { print_sym_table(); } while (!poll(&stdin_poll, 1, delay_msecs) == 1); - printf("key pressed - exiting.\n"); - exit(0); + c = getc(stdin); + tcsetattr(0, TCSAFLUSH, &save); + + handle_keypress(c); + goto repeat; return NULL; } @@ -285,6 +769,7 @@ static const char *skip_symbols[] = { "enter_idle", "exit_idle", "mwait_idle", + "mwait_idle_with_hints", "ppc64_runlatch_off", "pseries_dedicated_idle_sleep", NULL @@ -292,7 +777,6 @@ static const char *skip_symbols[] = { static int symbol_filter(struct dso *self, struct symbol *sym) { - static int filter_match; struct sym_entry *syme; const char *name = sym->name; int i; @@ -314,6 +798,10 @@ static int symbol_filter(struct dso *self, struct symbol *sym) return 1; syme = dso__sym_priv(self, sym); + pthread_mutex_init(&syme->source_lock, NULL); + if (!sym_filter_entry && sym_filter && !strcmp(name, sym_filter)) + sym_filter_entry = syme; + for (i = 0; skip_symbols[i]; i++) { if (!strcmp(skip_symbols[i], name)) { syme->skip = 1; @@ -321,29 +809,6 @@ static int symbol_filter(struct dso *self, struct symbol *sym) } } - if (filter_match == 1) { - filter_end = sym->start; - filter_match = -1; - if (filter_end - filter_start > 10000) { - fprintf(stderr, - "hm, too large filter symbol <%s> - skipping.\n", - sym_filter); - fprintf(stderr, "symbol filter start: %016lx\n", - filter_start); - fprintf(stderr, " end: %016lx\n", - filter_end); - filter_end = filter_start = 0; - sym_filter = NULL; - sleep(1); - } - } - - if (filter_match == 0 && sym_filter && !strcmp(name, sym_filter)) { - filter_match = 1; - filter_start = sym->start; - } - - return 0; } @@ -379,8 +844,6 @@ out_delete_dso: return -1; } -#define TRACE_COUNT 3 - /* * Binary search in the histogram table and record the hit: */ @@ -393,6 +856,7 @@ static void record_ip(u64 ip, int counter) if (!syme->skip) { syme->count[counter]++; + record_precise_ip(syme, counter, ip); pthread_mutex_lock(&active_symbols_lock); if (list_empty(&syme->node) || !syme->node.next) __list_insert_active_sym(syme); @@ -689,8 +1153,8 @@ static const struct option options[] = { "put the counters into a counter group"), OPT_BOOLEAN('i', "inherit", &inherit, "child tasks inherit counters"), - OPT_STRING('s', "sym-filter", &sym_filter, "pattern", - "only display symbols matchig this pattern"), + OPT_STRING('s', "sym-annotate", &sym_filter, "symbol name", + "symbol to annotate - requires -k option"), OPT_BOOLEAN('z', "zero", &zero, "zero history across updates"), OPT_INTEGER('F', "freq", &freq, @@ -733,6 +1197,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used) delay_secs = 1; parse_symbols(); + parse_source(sym_filter_entry); /* * Fill in the ones not specifically initialized via -c: diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 9d3c814..0114734 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -13,6 +13,7 @@ #include <stdio.h> #include <stdbool.h> #include <errno.h> +#include <math.h> #include "callchain.h" @@ -26,10 +27,14 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct callchain_node *rnode; + u64 chain_cumul = cumul_hits(chain); while (*p) { + u64 rnode_cumul; + parent = *p; rnode = rb_entry(parent, struct callchain_node, rb_node); + rnode_cumul = cumul_hits(rnode); switch (mode) { case CHAIN_FLAT: @@ -40,7 +45,7 @@ rb_insert_callchain(struct rb_root *root, struct callchain_node *chain, break; case CHAIN_GRAPH_ABS: /* Falldown */ case CHAIN_GRAPH_REL: - if (rnode->cumul_hit < chain->cumul_hit) + if (rnode_cumul < chain_cumul) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -87,7 +92,7 @@ static void __sort_chain_graph_abs(struct callchain_node *node, chain_for_each_child(child, node) { __sort_chain_graph_abs(child, min_hit); - if (child->cumul_hit >= min_hit) + if (cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, CHAIN_GRAPH_ABS); } @@ -108,11 +113,11 @@ static void __sort_chain_graph_rel(struct callchain_node *node, u64 min_hit; node->rb_root = RB_ROOT; - min_hit = node->cumul_hit * min_percent / 100.0; + min_hit = ceil(node->children_hit * min_percent); chain_for_each_child(child, node) { __sort_chain_graph_rel(child, min_percent); - if (child->cumul_hit >= min_hit) + if (cumul_hits(child) >= min_hit) rb_insert_callchain(&node->rb_root, child, CHAIN_GRAPH_REL); } @@ -122,7 +127,7 @@ static void sort_chain_graph_rel(struct rb_root *rb_root, struct callchain_node *chain_root, u64 min_hit __used, struct callchain_param *param) { - __sort_chain_graph_rel(chain_root, param->min_percent); + __sort_chain_graph_rel(chain_root, param->min_percent / 100.0); rb_root->rb_node = chain_root->rb_root.rb_node; } @@ -211,7 +216,8 @@ add_child(struct callchain_node *parent, struct ip_callchain *chain, new = create_child(parent, false); fill_node(new, chain, start, syms); - new->cumul_hit = new->hit = 1; + new->children_hit = 0; + new->hit = 1; } /* @@ -241,7 +247,8 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, /* split the hits */ new->hit = parent->hit; - new->cumul_hit = parent->cumul_hit; + new->children_hit = parent->children_hit; + parent->children_hit = cumul_hits(new); new->val_nr = parent->val_nr - idx_local; parent->val_nr = idx_local; @@ -249,6 +256,7 @@ split_add_child(struct callchain_node *parent, struct ip_callchain *chain, if (idx_total < chain->nr) { parent->hit = 0; add_child(parent, chain, idx_total, syms); + parent->children_hit++; } else { parent->hit = 1; } @@ -269,13 +277,13 @@ __append_chain_children(struct callchain_node *root, struct ip_callchain *chain, unsigned int ret = __append_chain(rnode, chain, start, syms); if (!ret) - goto cumul; + goto inc_children_hit; } /* nothing in children, add to the current node */ add_child(root, chain, start, syms); -cumul: - root->cumul_hit++; +inc_children_hit: + root->children_hit++; } static int @@ -317,8 +325,6 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, /* we match 100% of the path, increment the hit */ if (i - start == root->val_nr && i == chain->nr) { root->hit++; - root->cumul_hit++; - return 0; } @@ -331,5 +337,7 @@ __append_chain(struct callchain_node *root, struct ip_callchain *chain, void append_chain(struct callchain_node *root, struct ip_callchain *chain, struct symbol **syms) { + if (!chain->nr) + return; __append_chain_children(root, chain, syms, 0); } diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 7812122..a926ae4 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -7,6 +7,7 @@ #include "symbol.h" enum chain_mode { + CHAIN_NONE, CHAIN_FLAT, CHAIN_GRAPH_ABS, CHAIN_GRAPH_REL @@ -21,7 +22,7 @@ struct callchain_node { struct rb_root rb_root; /* sorted tree of children */ unsigned int val_nr; u64 hit; - u64 cumul_hit; /* hit + hits of children */ + u64 children_hit; }; struct callchain_param; @@ -48,6 +49,11 @@ static inline void callchain_init(struct callchain_node *node) INIT_LIST_HEAD(&node->val); } +static inline u64 cumul_hits(struct callchain_node *node) +{ + return node->hit + node->children_hit; +} + int register_callchain_param(struct callchain_param *param); void append_chain(struct callchain_node *root, struct ip_callchain *chain, struct symbol **syms); diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 450384b..b92a457 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -185,6 +185,8 @@ static void do_read(int fd, void *buf, size_t size) if (ret < 0) die("failed to read"); + if (ret == 0) + die("failed to read: missing data"); size -= ret; buf += ret; @@ -213,9 +215,10 @@ struct perf_header *perf_header__read(int fd) for (i = 0; i < nr_attrs; i++) { struct perf_header_attr *attr; - off_t tmp = lseek(fd, 0, SEEK_CUR); + off_t tmp; do_read(fd, &f_attr, sizeof(f_attr)); + tmp = lseek(fd, 0, SEEK_CUR); attr = perf_header_attr__new(&f_attr.attr); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 7bdad8d..0441784 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -121,13 +121,29 @@ static unsigned long hw_cache_stat[C(MAX)] = { (strcmp(sys_dirent.d_name, ".")) && \ (strcmp(sys_dirent.d_name, ".."))) +static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir) +{ + char evt_path[MAXPATHLEN]; + int fd; + + snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path, + sys_dir->d_name, evt_dir->d_name); + fd = open(evt_path, O_RDONLY); + if (fd < 0) + return -EINVAL; + close(fd); + + return 0; +} + #define for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next, file, st) \ while (!readdir_r(evt_dir, &evt_dirent, &evt_next) && evt_next) \ if (snprintf(file, MAXPATHLEN, "%s/%s/%s", debugfs_path, \ sys_dirent.d_name, evt_dirent.d_name) && \ (!stat(file, &st)) && (S_ISDIR(st.st_mode)) && \ (strcmp(evt_dirent.d_name, ".")) && \ - (strcmp(evt_dirent.d_name, ".."))) + (strcmp(evt_dirent.d_name, "..")) && \ + (!tp_event_has_id(&sys_dirent, &evt_dirent))) #define MAX_EVENT_LENGTH 30 @@ -223,9 +239,15 @@ char *event_name(int counter) { u64 config = attrs[counter].config; int type = attrs[counter].type; + + return __event_name(type, config); +} + +char *__event_name(int type, u64 config) +{ static char buf[32]; - if (attrs[counter].type == PERF_TYPE_RAW) { + if (type == PERF_TYPE_RAW) { sprintf(buf, "raw 0x%llx", config); return buf; } @@ -357,6 +379,7 @@ static int parse_tracepoint_event(const char **strp, struct perf_counter_attr *attr) { const char *evt_name; + char *flags; char sys_name[MAX_EVENT_LENGTH]; char id_buf[4]; int fd; @@ -378,6 +401,15 @@ static int parse_tracepoint_event(const char **strp, strncpy(sys_name, *strp, sys_length); sys_name[sys_length] = '\0'; evt_name = evt_name + 1; + + flags = strchr(evt_name, ':'); + if (flags) { + *flags = '\0'; + flags++; + if (!strncmp(flags, "record", strlen(flags))) + attr->sample_type |= PERF_SAMPLE_RAW; + } + evt_length = strlen(evt_name); if (evt_length >= MAX_EVENT_LENGTH) return 0; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 1ea5d09..192a962 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -10,6 +10,7 @@ extern int nr_counters; extern struct perf_counter_attr attrs[MAX_COUNTERS]; extern char *event_name(int ctr); +extern char *__event_name(int type, u64 config); extern int parse_events(const struct option *opt, const char *str, int unset); diff --git a/tools/perf/util/quote.c b/tools/perf/util/quote.c index c6e5dc0..2726fe4 100644 --- a/tools/perf/util/quote.c +++ b/tools/perf/util/quote.c @@ -318,7 +318,7 @@ char *quote_path_relative(const char *in, int len, strbuf_addch(out, '"'); if (prefix) { int off = 0; - while (prefix[off] && off < len && prefix[off] == in[off]) + while (off < len && prefix[off] && prefix[off] == in[off]) if (prefix[off] == '/') { prefix += off + 1; in += off + 1; diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 2810605..5c0f42e 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -6,14 +6,18 @@ #include <libelf.h> #include <gelf.h> #include <elf.h> -#include <bfd.h> const char *sym_hist_filter; -#ifndef DMGL_PARAMS -#define DMGL_PARAMS (1 << 0) /* Include function args */ -#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ -#endif +enum dso_origin { + DSO__ORIG_KERNEL = 0, + DSO__ORIG_JAVA_JIT, + DSO__ORIG_FEDORA, + DSO__ORIG_UBUNTU, + DSO__ORIG_BUILDID, + DSO__ORIG_DSO, + DSO__ORIG_NOT_FOUND, +}; static struct symbol *symbol__new(u64 start, u64 len, const char *name, unsigned int priv_size, @@ -72,6 +76,7 @@ struct dso *dso__new(const char *name, unsigned int sym_priv_size) self->sym_priv_size = sym_priv_size; self->find_symbol = dso__find_symbol; self->slen_calculated = 0; + self->origin = DSO__ORIG_NOT_FOUND; } return self; @@ -565,7 +570,7 @@ static int dso__load_sym(struct dso *self, int fd, const char *name, goto out_elf_end; secstrs = elf_getdata(sec_strndx, NULL); - if (symstrs == NULL) + if (secstrs == NULL) goto out_elf_end; nr_syms = shdr.sh_size / shdr.sh_entsize; @@ -652,11 +657,85 @@ out_close: return err; } +#define BUILD_ID_SIZE 128 + +static char *dso__read_build_id(struct dso *self, int verbose) +{ + int i; + GElf_Ehdr ehdr; + GElf_Shdr shdr; + Elf_Data *build_id_data; + Elf_Scn *sec; + char *build_id = NULL, *bid; + unsigned char *raw; + Elf *elf; + int fd = open(self->name, O_RDONLY); + + if (fd < 0) + goto out; + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (elf == NULL) { + if (verbose) + fprintf(stderr, "%s: cannot read %s ELF file.\n", + __func__, self->name); + goto out_close; + } + + if (gelf_getehdr(elf, &ehdr) == NULL) { + if (verbose) + fprintf(stderr, "%s: cannot get elf header.\n", __func__); + goto out_elf_end; + } + + sec = elf_section_by_name(elf, &ehdr, &shdr, ".note.gnu.build-id", NULL); + if (sec == NULL) + goto out_elf_end; + + build_id_data = elf_getdata(sec, NULL); + if (build_id_data == NULL) + goto out_elf_end; + build_id = malloc(BUILD_ID_SIZE); + if (build_id == NULL) + goto out_elf_end; + raw = build_id_data->d_buf + 16; + bid = build_id; + + for (i = 0; i < 20; ++i) { + sprintf(bid, "%02x", *raw); + ++raw; + bid += 2; + } + if (verbose >= 2) + printf("%s(%s): %s\n", __func__, self->name, build_id); +out_elf_end: + elf_end(elf); +out_close: + close(fd); +out: + return build_id; +} + +char dso__symtab_origin(const struct dso *self) +{ + static const char origin[] = { + [DSO__ORIG_KERNEL] = 'k', + [DSO__ORIG_JAVA_JIT] = 'j', + [DSO__ORIG_FEDORA] = 'f', + [DSO__ORIG_UBUNTU] = 'u', + [DSO__ORIG_BUILDID] = 'b', + [DSO__ORIG_DSO] = 'd', + }; + + if (self == NULL || self->origin == DSO__ORIG_NOT_FOUND) + return '!'; + return origin[self->origin]; +} + int dso__load(struct dso *self, symbol_filter_t filter, int verbose) { - int size = strlen(self->name) + sizeof("/usr/lib/debug%s.debug"); - char *name = malloc(size); - int variant = 0; + int size = PATH_MAX; + char *name = malloc(size), *build_id = NULL; int ret = -1; int fd; @@ -665,26 +744,43 @@ int dso__load(struct dso *self, symbol_filter_t filter, int verbose) self->adjust_symbols = 0; - if (strncmp(self->name, "/tmp/perf-", 10) == 0) - return dso__load_perf_map(self, filter, verbose); + if (strncmp(self->name, "/tmp/perf-", 10) == 0) { + ret = dso__load_perf_map(self, filter, verbose); + self->origin = ret > 0 ? DSO__ORIG_JAVA_JIT : + DSO__ORIG_NOT_FOUND; + return ret; + } + + self->origin = DSO__ORIG_FEDORA - 1; more: do { - switch (variant) { - case 0: /* Fedora */ + self->origin++; + switch (self->origin) { + case DSO__ORIG_FEDORA: snprintf(name, size, "/usr/lib/debug%s.debug", self->name); break; - case 1: /* Ubuntu */ + case DSO__ORIG_UBUNTU: snprintf(name, size, "/usr/lib/debug%s", self->name); break; - case 2: /* Sane people */ + case DSO__ORIG_BUILDID: + build_id = dso__read_build_id(self, verbose); + if (build_id != NULL) { + snprintf(name, size, + "/usr/lib/debug/.build-id/%.2s/%s.debug", + build_id, build_id + 2); + free(build_id); + break; + } + self->origin++; + /* Fall thru */ + case DSO__ORIG_DSO: snprintf(name, size, "%s", self->name); break; default: goto out; } - variant++; fd = open(name, O_RDONLY); } while (fd < 0); @@ -705,6 +801,8 @@ more: } out: free(name); + if (ret < 0 && strstr(self->name, " (deleted)") != NULL) + return 0; return ret; } @@ -820,6 +918,9 @@ int dso__load_kernel(struct dso *self, const char *vmlinux, if (err <= 0) err = dso__load_kallsyms(self, filter, verbose); + if (err > 0) + self->origin = DSO__ORIG_KERNEL; + return err; } diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 2f92b21..b53bf01 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -7,6 +7,30 @@ #include <linux/rbtree.h> #include "module.h" +#ifdef HAVE_CPLUS_DEMANGLE +extern char *cplus_demangle(const char *, int); + +static inline char *bfd_demangle(void __used *v, const char *c, int i) +{ + return cplus_demangle(c, i); +} +#else +#ifdef NO_DEMANGLE +static inline char *bfd_demangle(void __used *v, const char __used *c, + int __used i) +{ + return NULL; +} +#else +#include <bfd.h> +#endif +#endif + +#ifndef DMGL_PARAMS +#define DMGL_PARAMS (1 << 0) /* Include function args */ +#define DMGL_ANSI (1 << 1) /* Include const, volatile, etc */ +#endif + struct symbol { struct rb_node rb_node; u64 start; @@ -26,6 +50,7 @@ struct dso { unsigned int sym_priv_size; unsigned char adjust_symbols; unsigned char slen_calculated; + unsigned char origin; char name[0]; }; @@ -49,6 +74,7 @@ int dso__load_modules(struct dso *self, symbol_filter_t filter, int verbose); int dso__load(struct dso *self, symbol_filter_t filter, int verbose); size_t dso__fprintf(struct dso *self, FILE *fp); +char dso__symtab_origin(const struct dso *self); void symbol__init(void); #endif /* _PERF_SYMBOL_ */ diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c index 1eddae9..1150c6d 100644 --- a/virt/kvm/ioapic.c +++ b/virt/kvm/ioapic.c @@ -95,8 +95,6 @@ static int ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) if (injected && pent->fields.trig_mode == IOAPIC_LEVEL_TRIG) pent->fields.remote_irr = 1; } - if (!pent->fields.trig_mode) - ioapic->irr &= ~(1 << idx); return injected; } @@ -136,7 +134,8 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) mask_after = ioapic->redirtbl[index].fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, index, mask_after); - if (ioapic->irr & (1 << index)) + if (ioapic->redirtbl[index].fields.trig_mode == IOAPIC_LEVEL_TRIG + && ioapic->irr & (1 << index)) ioapic_service(ioapic, index); break; } @@ -184,9 +183,10 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) if (!level) ioapic->irr &= ~mask; else { + int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG); ioapic->irr |= mask; - if ((!entry.fields.trig_mode && old_irr != ioapic->irr) - || !entry.fields.remote_irr) + if ((edge && old_irr != ioapic->irr) || + (!edge && !entry.fields.remote_irr)) ret = ioapic_service(ioapic, irq); } } diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c index a8bd466..ddc17f0 100644 --- a/virt/kvm/irq_comm.c +++ b/virt/kvm/irq_comm.c @@ -160,7 +160,8 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin) unsigned gsi = pin; list_for_each_entry(e, &kvm->irq_routing, link) - if (e->irqchip.irqchip == irqchip && + if (e->type == KVM_IRQ_ROUTING_IRQCHIP && + e->irqchip.irqchip == irqchip && e->irqchip.pin == pin) { gsi = e->gsi; break; @@ -259,6 +260,7 @@ static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e, int delta; e->gsi = ue->gsi; + e->type = ue->type; switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: delta = 0; |