aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* sgiioc4: kill duplicate ioremap()Sergei Shtylyov2008-10-171-12/+2
| | | | | | | | | | | | By the time ide_dma_sgiioc4() gets called, sgiioc4_ide_setup_pci_device() will have called ioremap() on the whole BAR0 region, so calling ioremap() on the DMA registers means wasting a page. Replace this call by a mere address calculation, based on the fact that IRQ registers (pointed to by 'hwif->io_ports.irq_addr') are situated at offset 0 from BAR0. Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: jeremy@sgi.com Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* sgiioc4: kill useless address checksSergei Shtylyov2008-10-171-17/+9
| | | | | | | | | | | | | | | | | | The driver performs a number of checks on the virtual/physical addresses which would always evaluate as true (except ide_dma_sgiioc4() -- always false): - for sgiioc4_init_hwif_ports(), its caller, sgiioc4_ide_setup_pci_device(), guarantees that 'ctrl_port' and 'irq_port' parameters are never 0; - in sgiioc4_read_status(), we always read the IDE status register, so there's no need to check the register's address (must be a leftover from the times when this function implemented the INB() method); - in ide_dma_sgiioc4(), 'dma_base' can never be 0 as IOC4_DMA_OFFSET is not 0. Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: jeremy@sgi.com Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* delkin_cb: add PM supportBartlomiej Zolnierkiewicz2008-10-171-7/+56
| | | | | | | | | | | | | | | | | * Factor out chipset initialization code from delkin_cb_probe() to delkin_cb_init_chipset(). * Assign ->init_chipset in struct delkin_cb_port_info. * Add delkin_cb_{suspend,resume}() (->suspend/->resume methods). Fixes kernel bugzilla bug #11735: http://bugzilla.kernel.org/show_bug.cgi?id=11735 Tested-by: bumble.bee@xs4all.nl Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: remove broken hpt34x driverBartlomiej Zolnierkiewicz2008-10-173-217/+1
| | | | | | | No big loss since HPT343/363 controllers are properly supported by pata_hpt3x3 driver from Alan Cox. Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-floppy: remove idefloppy_floppy_t typedefBartlomiej Zolnierkiewicz2008-10-173-15/+13
| | | | | | | | There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* sgiioc4: remove maskproc() methodSergei Shtylyov2008-10-171-9/+0
| | | | | | | | | | | | Since the maskproc() method calls either mirror the interrupt en/disable via the nIEN bit of the device control register done by the IDE core before issuing a command or unmask the interrupt after a command executed in polled mode (when interrupt is already not expected), it is pointless to implement this method by manipulating the nIEN bit... Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: jeremy@sgi.com Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* hpt366: cleanup maskproc() methodSergei Shtylyov2008-10-171-18/+16
| | | | | | | | | | | | | | Since the maskproc() method calls either mirror the interrupt en/disable via the nIEN bit of the device control register done by the IDE core before issuing a command or unmask the interrupt after a command executed in polled mode (when interrupt is already not expected), it is pointless to manipulate the nIEN bit in this method; therefore, just do nothing for the drives not on the quirk list. Move the code to the left by using an early return and the 'else if' construct, while at it.... Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> [bart: fix checkpatch.pl warning] Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: mask interrupt in ide_config_drive_speed()Sergei Shtylyov2008-10-171-1/+1
| | | | | | | | | | Apparently, there is no sense in unmasking IRQ on the controller when you call disable_irq_nosync() before doing this, set the nIEN bit afterwards, and then unmask IRQ again after the command completion, hence 0 passed to SELECT_MASK() before issuing the command in ide_config_drive_speed() is probably just a typo. Signed-off-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* hpt366: fix compile warningBartlomiej Zolnierkiewicz2008-10-171-1/+0
| | | | | | | | | | | | | Fixup for commit 1785192b5310ee25165768f5bb80f13146788e3e ("hpt366: add hpt3xx_disable_fast_irq() helper"):    CC      drivers/ide/pci/hpt366.o drivers/ide/pci/hpt366.c: In function `init_hwif_hpt366': drivers/ide/pci/hpt366.c:1290: warning: unused variable `dev' Reported-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Acked-by: Sergei Shtylyov <sshtylyov@ru.mvista.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: remove unused macros from <asm-parisc/ide.h>Bartlomiej Zolnierkiewicz2008-10-171-4/+0
| | | | | Acked-by: Kyle McMartin <kyle@mcmartin.ca> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: remove M68K_IDE_SWAPW define from <asm-m68k/ide.h>Bartlomiej Zolnierkiewicz2008-10-171-9/+0
| | | | | | | | | Since we solved this by overriding default ->{in,out}put_data methods in {q40,falcon}ide M68K_IDE_SWAP define can go away. Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: remove dead <asm-arm/arch-sa1100/ide.h>Bartlomiej Zolnierkiewicz2008-10-171-75/+0
| | | | | | | | It has been dead for more than 3 years and needs to be converted to use platform PATA support anyway. Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: fix support for IDE PCI controllers using MMIO on frvBartlomiej Zolnierkiewicz2008-10-171-9/+1
| | | | | | | | | Just include <asm-generic/ide_iops.h> for __ide_mm_*() instead of defining them to normal I/O helpers so PCI bus <-> CPU byte-swapping is done as needed. Cc: David Howells <dhowells@redhat.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-cd: remove stale commentBorislav Petkov2008-10-171-4/+0
| | | | | | Signed-off-by: Borislav Petkov <petkovbb@gmail.com> [bart: split-up this change from a bigger patch] Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-cd: small drive type print fixBorislav Petkov2008-10-171-1/+1
| | | | | Signed-off-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-cd: debug log enhancementsBorislav Petkov2008-10-171-12/+21
| | | | | | | | Add some more verbosity to key function calls in ide-cd debug code. While at it, delete a superfluous comment. Signed-off-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: add generic ATA/ATAPI disk driverBartlomiej Zolnierkiewicz2008-10-1713-455/+303
| | | | | | | | | | | | | | | | * Add struct ide_disk_ops containing protocol specific methods. * Add 'struct ide_disk_ops *' to ide_drive_t. * Convert ide-{disk,floppy} drivers to use struct ide_disk_ops. * Merge ide-{disk,floppy} drivers into generic ide-gd driver. While at it: - ide_disk_init_capacity() -> ide_disk_get_capacity() Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: allow device drivers to specify per-device type /proc settingsBartlomiej Zolnierkiewicz2008-10-177-22/+74
| | | | | | | | | | | Turn ide_driver_t's 'proc' field into ->proc_entries method (and also 'settings' field into ->proc_devsets method). Then update all device drivers accordingly. There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: prepare for merging ide-gd-floppy.c with ide-gd.cBartlomiej Zolnierkiewicz2008-10-173-92/+91
| | | | | | | | | | | | | | | | | | | | | | | | | | | - idefloppy_ref_mutex -> ide_disk_ref_mutex - idefloppy_cleanup_obj() -> ide_disk_release() - ide_floppy_get() -> ide_disk_get() - ide_floppy_put() -> ide_disk_put() - ide_floppy_capacity() -> ide_gd_capacity() - ide_floppy_remove() -> ide_gd_remove() - ide_floppy_probe() -> ide_gd_probe() - idefloppy_driver -> ide_gd_driver - idefloppy_open() -> ide_gd_open() - idefloppy_release() -> ide_gd_release() - idefloppy_getgeo() -> ide_gd_getgeo() - idefloppy_media_changed() -> ide_gd_media_changed() - idefloppy_revalidate_disk() -> ide_gd_revalidate_disk() - idefloppy_ops -> ide_gd_ops - idefloppy_init() -> ide_gd_init() - idefloppy_exit() -> ide_gd_exit() - 'floppy' -> 'idkp' in ide_disk_*() and ide_gd_*() - idefloppy_floppy_t -> struct ide_floppy_obj There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-floppy: factor out generic disk handling code to ide-gd-floppy.cBartlomiej Zolnierkiewicz2008-10-174-311/+327
| | | | | | | | | | | | While at it: - idefloppy_do_request() -> ide_floppy_do_request() - idefloppy_end_request() -> ide_floppy_end_request() - idefloppy_setup() -> ide_floppy_setup() There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-disk: use IDE_DFLAG_MEDIA_CHANGEDBartlomiej Zolnierkiewicz2008-10-171-2/+6
| | | | | | | | | | | Set IDE_DFLAG_MEDIA_CHANGED in ide_gd_open() to signalize ide_gd_media_changed() that that media has changed (instead of relying on IDE_DFLAG_REMOVABLE). There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-disk: factor out generic disk handling code to ide-gd.cBartlomiej Zolnierkiewicz2008-10-175-299/+314
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | While at it: - IDEDISK_VERSION -> IDE_GD_VERSION - ide_cacheflush_p() -> ide_disk_flush() - init_idedisk_capacity() -> ide_disk_init_capacity() - idedisk_set_doorlock() -> ide_disk_set_doorlock() - idedisk_setup() -> ide_disk_setup() - ide_disk_capacity() -> ide_gd_capacity() - ide_disk_remove() -> ide_gd_remove() - ide_disk_probe() -> ide_gd_probe() - ide_disk_resume() -> ide_gd_resume() - ide_device_shutdown() -> ide_gd_shutdown() - idedisk_driver -> ide_gd_driver - idedisk_open() -> ide_gd_open() - idedisk_release() -> ide_gd_release() - idedisk_getgeo() -> ide_gd_getgeo() - idedisk_media_changed() -> ide_gd_media_changed() - idedisk_revalidate_disk() -> ide_gd_revalidate_disk() - idedisk_ops -> ide_gd_ops - idedisk_init() -> ide_gd_init() - idedisk_exit() -> ide_gd_exit() There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: remove IDE_AFLAG_NO_DOORLOCKINGBartlomiej Zolnierkiewicz2008-10-177-8/+7
| | | | | | | | | Just use IDE_DFLAG_DOORLOCKING instead. There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: IDE_AFLAG_FORMAT_IN_PROGRESS -> IDE_DFLAG_FORMAT_IN_PROGRESSBartlomiej Zolnierkiewicz2008-10-173-8/+7
| | | | | | | There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: IDE_AFLAG_WP -> IDE_DFLAG_WPBartlomiej Zolnierkiewicz2008-10-172-6/+6
| | | | | | | There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide: IDE_AFLAG_MEDIA_CHANGED -> IDE_DFLAG_MEDIA_CHANGEDBartlomiej Zolnierkiewicz2008-10-174-10/+10
| | | | | | | There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-floppy: use drive->capacity64 for caching current capacityBartlomiej Zolnierkiewicz2008-10-171-10/+13
| | | | | | | | | | | | | | * Use drive->capacity64 for caching current capacity. * Switch ide_floppy_capacity() to use drive->capacity64. * Call set_capacity() in idefloppy_open() and ide_floppy_probe() instead of ide_floppy_get_capacity(). There should be no functional changes caused by this patch. Cc: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-floppy: drop 'floppy' argument from idefloppy_setup()Bartlomiej Zolnierkiewicz2008-10-171-2/+3
| | | | | Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-{disk,floppy}: set IDE_DFLAG_ATTACH in *_setup()Bartlomiej Zolnierkiewicz2008-10-172-9/+12
| | | | | | | There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-disk: move IDE_DFLAG_DOORLOCKING flag handling to idedisk_set_doorlock()Bartlomiej Zolnierkiewicz2008-10-171-9/+13
| | | | | | | There should be no functional changes caused by this patch. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-disk: use to_ide_drv() and ide_drv_g()Bartlomiej Zolnierkiewicz2008-10-173-12/+7
| | | | | | | There should be no functional changes caused by this patch. Cc: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-floppy: use alloc_disk_node()Bartlomiej Zolnierkiewicz2008-10-171-1/+1
| | | | | Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-disk: lock media before checking for media changeBartlomiej Zolnierkiewicz2008-10-171-1/+1
| | | | | Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* ide-disk: fix IDE_DFLAG_LBA48 handling on resumeBartlomiej Zolnierkiewicz2008-10-171-20/+20
| | | | | | | Some code in idedisk_setup() should be in idedisk_capacity() instead. Acked-by: Borislav Petkov <petkovbb@gmail.com> Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
* {pci,pnp} quirks.c: don't use deprecated print_fn_descriptor_symbol()Linus Torvalds2008-10-162-4/+2
| | | | | | | | | | | I dunno how this missed Bjorn and his quest to use %pF in commit c80cfb0406c01bb5da91bfe30f5cb1fd96831138 ("vsprintf: use new vsprintf symbolic function pointer format"), but it did. So use %pF in the two remaining places that still tried to print out function pointers by hand. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* Merge git://git.linux-nfs.org/projects/trondmy/nfs-2.6Linus Torvalds2008-10-1626-500/+955
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (53 commits) NFS: Fix a resolution problem with nfs_inode->cache_change_attribute NFS: Fix the resolution problem with nfs_inode_attrs_need_update() NFS: Changes to inode->i_nlinks must set the NFS_INO_INVALID_ATTR flag RPC/RDMA: ensure connection attempt is complete before signalling. RPC/RDMA: correct the reconnect timer backoff RPC/RDMA: optionally emit useful transport info upon connect/disconnect. RPC/RDMA: reformat a debug printk to keep lines together. RPC/RDMA: harden connection logic against missing/late rdma_cm upcalls. RPC/RDMA: fix connect/reconnect resource leak. RPC/RDMA: return a consistent error, when connect fails. RPC/RDMA: adhere to protocol for unpadded client trailing write chunks. RPC/RDMA: avoid an oops due to disconnect racing with async upcalls. RPC/RDMA: maintain the RPC task bytes-sent statistic. RPC/RDMA: suppress retransmit on RPC/RDMA clients. RPC/RDMA: fix connection IRD/ORD setting RPC/RDMA: support FRMR client memory registration. RPC/RDMA: check selected memory registration mode at runtime. RPC/RDMA: add data types and new FRMR memory registration enum. RPC/RDMA: refactor the inline memory registration code. NFS: fix nfs_parse_ip_address() corner case ...
| * Merge branch 'next'Trond Myklebust2008-10-1526-500/+955
| |\
| | * NFS: Fix a resolution problem with nfs_inode->cache_change_attributeTrond Myklebust2008-10-142-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The cache_change_attribute is used to decide whether or not a directory has changed, in which case we may need to look it up again. Again, the use of 'jiffies' leads to an issue of resolution. Once again, the fix is to change nfs_inode->cache_change_attribute, and just make it a simple counter. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * NFS: Fix the resolution problem with nfs_inode_attrs_need_update()Trond Myklebust2008-10-144-18/+44
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It appears that 'jiffies' timestamps do not have high enough resolution for nfs_inode_attrs_need_update(). One problem is that a GETATTR can be launched within < 1 jiffy of the last operation that updated the attribute. Another problem is that RPC calls can take < 1 jiffy to execute. We can fix this by switching the variables to use a simple global counter that gets incremented every time we start another GETATTR call. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * NFS: Changes to inode->i_nlinks must set the NFS_INO_INVALID_ATTR flagTrond Myklebust2008-10-141-0/+3
| | | | | | | | | | | | Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: ensure connection attempt is complete before signalling.Tom Talpey2008-10-101-5/+1
| | | | | | | | | | | | | | | | | | | | | | | | The RPC/RDMA connection logic could return early from reconnection attempts, leading to additional spurious retries. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: correct the reconnect timer backoffTom Talpey2008-10-101-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The RPC/RDMA code had a constant 5-second reconnect backoff, and always performed it, even when re-establishing a connection to a server after the RPC layer closed it due to being idle. Make it an geometric backoff (up to 30 seconds), and don't delay idle reconnect. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: optionally emit useful transport info upon connect/disconnect.Tom Talpey2008-10-102-1/+22
| | | | | | | | | | | | | | | Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: reformat a debug printk to keep lines together.Tom Talpey2008-10-101-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | The send marshaling code split a particular dprintk across two lines, which makes it hard to extract from logfiles. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: harden connection logic against missing/late rdma_cm upcalls.Tom Talpey2008-10-103-7/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | Add defensive timeouts to wait_for_completion() calls in RDMA address resolution, and make them interruptible. Fix the timeout units to milliseconds (formerly jiffies) and move to private header. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: fix connect/reconnect resource leak.Tom Talpey2008-10-101-5/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | The RPC/RDMA code can leak RDMA connection manager endpoints in certain error cases on connect. Don't signal unwanted events, and be certain to destroy any allocated qp. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: return a consistent error, when connect fails.Tom Talpey2008-10-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The xprt_connect call path does not expect such errors as ECONNREFUSED to be returned from failed transport connection attempts, otherwise it translates them to EIO and signals fatal errors. For example, mount.nfs prints simply "internal error". Translate all such errors to ENOTCONN from RPC/RDMA to match sockets behavior. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: adhere to protocol for unpadded client trailing write chunks.Tom Talpey2008-10-103-2/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The RPC/RDMA protocol allows clients and servers to avoid RDMA operations for data which is purely the result of XDR padding. On the client, automatically insert the necessary padding for such server replies, and optionally don't marshal such chunks. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: avoid an oops due to disconnect racing with async upcalls.Tom Talpey2008-10-101-11/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | RDMA disconnects yield an upcall from the RDMA connection manager, which can race with rpc transport close, e.g. on ^C of a mount. Ensure any rdma cm_id and qp are fully destroyed before continuing. Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
| | * RPC/RDMA: maintain the RPC task bytes-sent statistic.Tom Talpey2008-10-101-0/+1
| | | | | | | | | | | | | | | Signed-off-by: Tom Talpey <talpey@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
generated by cgit v1.1 at 2024-10-29 20:29:18 +0000