summaryrefslogtreecommitdiff
path: root/block/blk-mq.c
AgeCommit message (Collapse)AuthorFilesLines
2021-05-14blk-mq: Swap two calls in blk_mq_exit_queue()Bart Van Assche1-2/+4
If a tag set is shared across request queues (e.g. SCSI LUNs) then the block layer core keeps track of the number of active request queues in tags->active_queues. blk_mq_tag_busy() and blk_mq_tag_idle() update that atomic counter if the hctx flag BLK_MQ_F_TAG_QUEUE_SHARED is set. Make sure that blk_mq_exit_queue() calls blk_mq_tag_idle() before that flag is cleared by blk_mq_del_queue_tag_set(). Cc: Christoph Hellwig <hch@infradead.org> Cc: Ming Lei <ming.lei@redhat.com> Cc: Hannes Reinecke <hare@suse.com> Fixes: 0d2602ca30e4 ("blk-mq: improve support for shared tags maps") Signed-off-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20210513171529.7977-1-bvanassche@acm.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-05-14blk-mq: plug request for shared sbitmapMing Lei1-2/+3
In case of shared sbitmap, request won't be held in plug list any more sine commit 32bc15afed04 ("blk-mq: Facilitate a shared sbitmap per tagset"), this way makes request merge from flush plug list & batching submission not possible, so cause performance regression. Yanhui reports performance regression when running sequential IO test(libaio, 16 jobs, 8 depth for each job) in VM, and the VM disk is emulated with image stored on xfs/megaraid_sas. Fix the issue by recovering original behavior to allow to hold request in plug list. Cc: Yanhui Ma <yama@redhat.com> Cc: John Garry <john.garry@huawei.com> Cc: Bart Van Assche <bvanassche@acm.org> Cc: kashyap.desai@broadcom.com Fixes: 32bc15afed04 ("blk-mq: Facilitate a shared sbitmap per tagset") Signed-off-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20210514022052.1047665-1-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-04-29Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiLinus Torvalds1-12/+26
Pull SCSI updates from James Bottomley: "This consists of the usual driver updates (ufs, target, tcmu, smartpqi, lpfc, zfcp, qla2xxx, mpt3sas, pm80xx). The major core change is using a sbitmap instead of an atomic for queue tracking" * tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (412 commits) scsi: target: tcm_fc: Fix a kernel-doc header scsi: target: Shorten ALUA error messages scsi: target: Fix two format specifiers scsi: target: Compare explicitly with SAM_STAT_GOOD scsi: sd: Introduce a new local variable in sd_check_events() scsi: dc395x: Open-code status_byte(u8) calls scsi: 53c700: Open-code status_byte(u8) calls scsi: smartpqi: Remove unused functions scsi: qla4xxx: Remove an unused function scsi: myrs: Remove unused functions scsi: myrb: Remove unused functions scsi: mpt3sas: Fix two kernel-doc headers scsi: fcoe: Suppress a compiler warning scsi: libfc: Fix a format specifier scsi: aacraid: Remove an unused function scsi: core: Introduce enum scsi_disposition scsi: core: Modify the scsi_send_eh_cmnd() return value for the SDEV_BLOCK case scsi: core: Rename scsi_softirq_done() into scsi_complete() scsi: core: Remove an incorrect comment scsi: core: Make the scsi_alloc_sgtables() documentation more accurate ...
2021-04-29Merge tag 'for-5.13/block-2021-04-27' of git://git.kernel.dk/linux-blockLinus Torvalds1-1/+2
Pull block updates from Jens Axboe: "Pretty quiet round this time, which is nice. In detail: - Series revamping bounce buffer support (Christoph) - Dead code removal (Christoph, Bart) - Partition iteration revamp, now using xarray (Christoph) - Passthrough request scheduler improvements (Lin) - Series of BFQ improvements (Paolo) - Fix ioprio task iteration (Peter) - Various little tweaks and fixes (Tejun, Saravanan, Bhaskar, Max, Nikolay)" * tag 'for-5.13/block-2021-04-27' of git://git.kernel.dk/linux-block: (41 commits) blk-iocost: don't ignore vrate_min on QD contention blk-mq: Fix spurious debugfs directory creation during initialization bfq/mq-deadline: remove redundant check for passthrough request blk-mq: bypass IO scheduler's limit_depth for passthrough request block: Remove an obsolete comment from sg_io() block: move bio_list_copy_data to pktcdvd block: remove zero_fill_bio_iter block: add queue_to_disk() to get gendisk from request_queue block: remove an incorrect check from blk_rq_append_bio block: initialize ret in bdev_disk_changed block: Fix sys_ioprio_set(.which=IOPRIO_WHO_PGRP) task iteration block: remove disk_part_iter block: simplify diskstats_show block: simplify show_partition block: simplify printk_all_partitions block: simplify partition_overlaps block: simplify partition removal block: take bd_mutex around delete_partitions in del_gendisk block: refactor blk_drop_partitions block: move more syncing and invalidation to delete_partition ...
2021-04-16blk-mq: bypass IO scheduler's limit_depth for passthrough requestLin Feng1-1/+2
Commit 01e99aeca39796003 ("blk-mq: insert passthrough request into hctx->dispatch directly") gives high priority to passthrough requests and bypass underlying IO scheduler. But as we allocate tag for such request it still runs io-scheduler's callback limit_depth, while we really want is to give full sbitmap-depth capabity to such request for acquiring available tag. blktrace shows PC requests(dmraid -s -c -i) hit bfq's limit_depth: 8,0 2 0 0.000000000 39952 1,0 m N bfq [bfq_limit_depth] wr_busy 0 sync 0 depth 8 8,0 2 1 0.000008134 39952 D R 4 [dmraid] 8,0 2 2 0.000021538 24 C R [0] 8,0 2 0 0.000035442 39952 1,0 m N bfq [bfq_limit_depth] wr_busy 0 sync 0 depth 8 8,0 2 3 0.000038813 39952 D R 24 [dmraid] 8,0 2 4 0.000044356 24 C R [0] This patch introduce a new wrapper to make code not that ugly. Signed-off-by: Lin Feng <linf@wangsu.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20210415033920.213963-1-linf@wangsu.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-04-09treewide: Change list_sort to use const pointersSami Tolvanen1-1/+2
list_sort() internally casts the comparison function passed to it to a different type with constant struct list_head pointers, and uses this pointer to call the functions, which trips indirect call Control-Flow Integrity (CFI) checking. Instead of removing the consts, this change defines the list_cmp_func_t type and changes the comparison function types of all list_sort() callers to use const pointers, thus avoiding type mismatches. Suggested-by: Nick Desaulniers <ndesaulniers@google.com> Signed-off-by: Sami Tolvanen <samitolvanen@google.com> Reviewed-by: Nick Desaulniers <ndesaulniers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Kees Cook <keescook@chromium.org> Tested-by: Nick Desaulniers <ndesaulniers@google.com> Tested-by: Nathan Chancellor <nathan@kernel.org> Signed-off-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20210408182843.1754385-10-samitolvanen@google.com
2021-03-05scsi: blk-mq: Return budget token from .get_budget callbackMing Lei1-11/+25
SCSI uses a global atomic variable to track queue depth for each LUN/request queue. This doesn't scale well when there are lots of CPU cores and the disk is very fast. It has been observed that IOPS is affected a lot by tracking queue depth via sdev->device_busy in the I/O path. Return budget token from .get_budget callback. The budget token can be passed to driver so that we can replace the atomic variable with sbitmap_queue and alleviate the scaling problems that way. Link: https://lore.kernel.org/r/20210122023317.687987-9-ming.lei@redhat.com Cc: Omar Sandoval <osandov@fb.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com> Cc: Ewan D. Milne <emilne@redhat.com> Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2021-03-05scsi: sbitmap: Move allocation hint into sbitmapMing Lei1-1/+1
Allocation hint should have belonged to sbitmap. Also, when sbitmap's depth is high and there is no need to use mulitple wakeup queues, user can benefit from percpu allocation hint too. Move allocation hint into sbitmap, then SCSI device queue can benefit from allocation hint when converting to plain sbitmap. Convert vhost/scsi.c to use sbitmap allocation with percpu alloc hint. This is more efficient than the previous approach. Link: https://lore.kernel.org/r/20210122023317.687987-5-ming.lei@redhat.com Cc: Omar Sandoval <osandov@fb.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com> Cc: Ewan D. Milne <emilne@redhat.com> Cc: Mike Christie <michael.christie@oracle.com> Cc: virtualization@lists.linux-foundation.org Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2021-03-05scsi: sbitmap: Maintain allocation round_robin in sbitmapMing Lei1-1/+1
Currently the allocation round_robin info is maintained by sbitmap_queue. However, bit allocation really belongs to sbitmap. Move it there. Link: https://lore.kernel.org/r/20210122023317.687987-3-ming.lei@redhat.com Cc: Omar Sandoval <osandov@fb.com> Cc: Kashyap Desai <kashyap.desai@broadcom.com> Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com> Cc: Ewan D. Milne <emilne@redhat.com> Cc: Hannes Reinecke <hare@suse.de> Cc: virtualization@lists.linux-foundation.org Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2021-02-22Merge tag 'for-5.12/block-ipi-2021-02-21' of git://git.kernel.dk/linux-blockLinus Torvalds1-68/+41
Pull block IPI updates from Jens Axboe: "Avoid IRQ locking for the block IPI handling (Sebastian Andrzej Siewior)" * tag 'for-5.12/block-ipi-2021-02-21' of git://git.kernel.dk/linux-block: blk-mq: Use llist_head for blk_cpu_done blk-mq: Always complete remote completions requests in softirq smp: Process pending softirqs in flush_smp_call_function_from_idle()
2021-02-12blk-mq: Use llist_head for blk_cpu_doneSebastian Andrzej Siewior1-56/+41
With llist_head it is possible to avoid the locking (the irq-off region) when items are added. This makes it possible to add items on a remote CPU without additional locking. llist_add() returns true if the list was previously empty. This can be used to invoke the SMP function call / raise sofirq only if the first item was added (otherwise it is already pending). This simplifies the code a little and reduces the IRQ-off regions. blk_mq_raise_softirq() needs a preempt-disable section to ensure the request is enqueued on the same CPU as the softirq is raised. Some callers (USB-storage) invoke this path in preemptible context. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Daniel Wagner <dwagner@suse.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-02-12blk-mq: Always complete remote completions requests in softirqSebastian Andrzej Siewior1-13/+1
Controllers with multiple queues have their IRQ-handelers pinned to a CPU. The core shouldn't need to complete the request on a remote CPU. Remove this case and always raise the softirq to complete the request. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Daniel Wagner <dwagner@suse.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-01-25blk-mq: Improve performance of non-mq IO schedulers with multiple HW queuesJan Kara1-6/+60
Currently when non-mq aware IO scheduler (BFQ, mq-deadline) is used for a queue with multiple HW queues, the performance it rather bad. The problem is that these IO schedulers use queue-wide locking and their dispatch function does not respect the hctx it is passed in and returns any request it finds appropriate. Thus locality of request access is broken and dispatch from multiple CPUs just contends on IO scheduler locks. For these IO schedulers there's little point in dispatching from multiple CPUs. Instead dispatch always only from a single CPU to limit contention. Below is a comparison of dbench runs on XFS filesystem where the storage is a raid card with 64 HW queues and to it attached a single rotating disk. BFQ is used as IO scheduler: clients MQ SQ MQ-Patched Amean 1 39.12 (0.00%) 43.29 * -10.67%* 36.09 * 7.74%* Amean 2 128.58 (0.00%) 101.30 * 21.22%* 96.14 * 25.23%* Amean 4 577.42 (0.00%) 494.47 * 14.37%* 508.49 * 11.94%* Amean 8 610.95 (0.00%) 363.86 * 40.44%* 362.12 * 40.73%* Amean 16 391.78 (0.00%) 261.49 * 33.25%* 282.94 * 27.78%* Amean 32 324.64 (0.00%) 267.71 * 17.54%* 233.00 * 28.23%* Amean 64 295.04 (0.00%) 253.02 * 14.24%* 242.37 * 17.85%* Amean 512 10281.61 (0.00%) 10211.16 * 0.69%* 10447.53 * -1.61%* Numbers are times so lower is better. MQ is stock 5.10-rc6 kernel. SQ is the same kernel with megaraid_sas.host_tagset_enable=0 so that the card advertises just a single HW queue. MQ-Patched is a kernel with this patch applied. You can see multiple hardware queues heavily hurt performance in combination with BFQ. The patch restores the performance. Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-01-25Revert "blk-mq, elevator: Count requests per hctx to improve performance"Jan Kara1-1/+0
This reverts commit b445547ec1bbd3e7bf4b1c142550942f70527d95. Since both mq-deadline and BFQ completely ignore hctx they are passed to their dispatch function and dispatch whatever request they deem fit checking whether any request for a particular hctx is queued is just pointless since we'll very likely get a request from a different hctx anyway. In the following commit we'll deal with lock contention in these IO schedulers in presence of multiple HW queues in a different way. Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-01-25block: store a block_device pointer in struct bioChristoph Hellwig1-1/+1
Replace the gendisk pointer in struct bio with a pointer to the newly improved struct block device. From that the gendisk can be trivially accessed with an extra indirection, but it also allows to directly look up all information related to partition remapping. Signed-off-by: Christoph Hellwig <hch@lst.de> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-01-01Merge tag 'scsi-fixes' of ↵Linus Torvalds1-2/+2
git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi Pull SCSI fixes from James Bottomley: "This is a load of driver fixes (12 ufs, 1 mpt3sas, 1 cxgbi). The big core two fixes are for power management ("block: Do not accept any requests while suspended" and "block: Fix a race in the runtime power management code") which finally sorts out the resume problems we've occasionally been having. To make the resume fix, there are seven necessary precursors which effectively renames REQ_PREEMPT to REQ_PM, so every "special" request in block is automatically a power management exempt one. All of the non-PM preempt cases are removed except for the one in the SCSI Parallel Interface (spi) domain validation which is a genuine case where we have to run requests at high priority to validate the bus so this becomes an autopm get/put protected request" * tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (22 commits) scsi: cxgb4i: Fix TLS dependency scsi: ufs: Un-inline ufshcd_vops_device_reset function scsi: ufs: Re-enable WriteBooster after device reset scsi: ufs-mediatek: Use correct path to fix compile error scsi: mpt3sas: Signedness bug in _base_get_diag_triggers() scsi: block: Do not accept any requests while suspended scsi: block: Remove RQF_PREEMPT and BLK_MQ_REQ_PREEMPT scsi: core: Only process PM requests if rpm_status != RPM_ACTIVE scsi: scsi_transport_spi: Set RQF_PM for domain validation commands scsi: ide: Mark power management requests with RQF_PM instead of RQF_PREEMPT scsi: ide: Do not set the RQF_PREEMPT flag for sense requests scsi: block: Introduce BLK_MQ_REQ_PM scsi: block: Fix a race in the runtime power management code scsi: ufs-pci: Enable UFSHCD_CAP_RPM_AUTOSUSPEND for Intel controllers scsi: ufs-pci: Fix recovery from hibernate exit errors for Intel controllers scsi: ufs-pci: Ensure UFS device is in PowerDown mode for suspend-to-disk ->poweroff() scsi: ufs-pci: Fix restore from S4 for Intel controllers scsi: ufs-mediatek: Keep VCC always-on for specific devices scsi: ufs: Allow regulators being always-on scsi: ufs: Clear UAC for RPMB after ufshcd resets ...
2020-12-17blk-mq: Don't complete on a remote CPU in force threaded modeSebastian Andrzej Siewior1-0/+8
With force threaded interrupts enabled, raising softirq from an SMP function call will always result in waking the ksoftirqd thread. This is not optimal given that the thread runs at SCHED_OTHER priority. Completing the request in hard IRQ-context on PREEMPT_RT (which enforces the force threaded mode) is bad because the completion handler may acquire sleeping locks which violate the locking context. Disable request completing on a remote CPU in force threaded mode. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Daniel Wagner <dwagner@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-17blk-mq: Remove 'running from the wrong CPU' warningDaniel Wagner1-25/+0
It's guaranteed that no request is in flight when a hctx is going offline. This warning is only triggered when the wq's CPU is hot plugged and the blk-mq is not synced up yet. As this state is temporary and the request is still processed correctly, better remove the warning as this is the fast path. Suggested-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Daniel Wagner <dwagner@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-17Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiLinus Torvalds1-1/+1
Pull SCSI updates from James Bottomley: "This consists of the usual driver updates (ufs, qla2xxx, smartpqi, target, zfcp, fnic, mpt3sas, ibmvfc) plus a load of cleanups, a major power management rework and a load of assorted minor updates. There are a few core updates (formatting fixes being the big one) but nothing major this cycle" * tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (279 commits) scsi: mpt3sas: Update driver version to 36.100.00.00 scsi: mpt3sas: Handle trigger page after firmware update scsi: mpt3sas: Add persistent MPI trigger page scsi: mpt3sas: Add persistent SCSI sense trigger page scsi: mpt3sas: Add persistent Event trigger page scsi: mpt3sas: Add persistent Master trigger page scsi: mpt3sas: Add persistent trigger pages support scsi: mpt3sas: Sync time periodically between driver and firmware scsi: qla2xxx: Update version to 10.02.00.104-k scsi: qla2xxx: Fix device loss on 4G and older HBAs scsi: qla2xxx: If fcport is undergoing deletion complete I/O with retry scsi: qla2xxx: Fix the call trace for flush workqueue scsi: qla2xxx: Fix flash update in 28XX adapters on big endian machines scsi: qla2xxx: Handle aborts correctly for port undergoing deletion scsi: qla2xxx: Fix N2N and NVMe connect retry failure scsi: qla2xxx: Fix FW initialization error on big endian machines scsi: qla2xxx: Fix crash during driver load on big endian machines scsi: qla2xxx: Fix compilation issue in PPC systems scsi: qla2xxx: Don't check for fw_started while posting NVMe command scsi: qla2xxx: Tear down session if FW say it is down ...
2020-12-16Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-blockLinus Torvalds1-16/+30
Pull block updates from Jens Axboe: "Another series of killing more code than what is being added, again thanks to Christoph's relentless cleanups and tech debt tackling. This contains: - blk-iocost improvements (Baolin Wang) - part0 iostat fix (Jeffle Xu) - Disable iopoll for split bios (Jeffle Xu) - block tracepoint cleanups (Christoph Hellwig) - Merging of struct block_device and hd_struct (Christoph Hellwig) - Rework/cleanup of how block device sizes are updated (Christoph Hellwig) - Simplification of gendisk lookup and removal of block device aliasing (Christoph Hellwig) - Block device ioctl cleanups (Christoph Hellwig) - Removal of bdget()/blkdev_get() as exported API (Christoph Hellwig) - Disk change rework, avoid ->revalidate_disk() (Christoph Hellwig) - sbitmap improvements (Pavel Begunkov) - Hybrid polling fix (Pavel Begunkov) - bvec iteration improvements (Pavel Begunkov) - Zone revalidation fixes (Damien Le Moal) - blk-throttle limit fix (Yu Kuai) - Various little fixes" * tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block: (126 commits) blk-mq: fix msec comment from micro to milli seconds blk-mq: update arg in comment of blk_mq_map_queue blk-mq: add helper allocating tagset->tags Revert "block: Fix a lockdep complaint triggered by request queue flushing" nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class blk-mq: add new API of blk_mq_hctx_set_fq_lock_class block: disable iopoll for split bio block: Improve blk_revalidate_disk_zones() checks sbitmap: simplify wrap check sbitmap: replace CAS with atomic and sbitmap: remove swap_lock sbitmap: optimise sbitmap_deferred_clear() blk-mq: skip hybrid polling if iopoll doesn't spin blk-iocost: Factor out the base vrate change into a separate function blk-iocost: Factor out the active iocgs' state check into a separate function blk-iocost: Move the usage ratio calculation to the correct place blk-iocost: Remove unnecessary advance declaration blk-iocost: Fix some typos in comments blktrace: fix up a kerneldoc comment block: remove the request_queue to argument request based tracepoints ...
2020-12-12blk-mq: fix msec comment from micro to milli secondsMinwoo Im1-3/+3
Delay to wait for queue running is milli second unit which is passed to delayed work via msecs_to_jiffies() which is to convert milliseconds to jiffies. Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com> Reviewed-by: John Garry <john.garry@huawei.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-12blk-mq: add helper allocating tagset->tagsMinwoo Im1-1/+7
tagset->set is allocated from blk_mq_alloc_tag_set() rather than being reallocated. This patch added a helper to make its meaning explicitly which is to allocate rather than to reallocate. Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-09scsi: block: Remove RQF_PREEMPT and BLK_MQ_REQ_PREEMPTBart Van Assche1-2/+0
Remove flag RQF_PREEMPT and BLK_MQ_REQ_PREEMPT since these are no longer used by any kernel code. Link: https://lore.kernel.org/r/20201209052951.16136-8-bvanassche@acm.org Cc: Can Guo <cang@codeaurora.org> Cc: Stanley Chu <stanley.chu@mediatek.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Ming Lei <ming.lei@redhat.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Martin Kepplinger <martin.kepplinger@puri.sm> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Jens Axboe <axboe@kernel.dk> Reviewed-by: Can Guo <cang@codeaurora.org> Signed-off-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2020-12-09scsi: block: Introduce BLK_MQ_REQ_PMBart Van Assche1-0/+2
Introduce the BLK_MQ_REQ_PM flag. This flag makes the request allocation functions set RQF_PM. This is the first step towards removing BLK_MQ_REQ_PREEMPT. Link: https://lore.kernel.org/r/20201209052951.16136-3-bvanassche@acm.org Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Stanley Chu <stanley.chu@mediatek.com> Cc: Ming Lei <ming.lei@redhat.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Can Guo <cang@codeaurora.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Jens Axboe <axboe@kernel.dk> Reviewed-by: Can Guo <cang@codeaurora.org> Signed-off-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2020-12-08block: disable iopoll for split bioJeffle Xu1-0/+5
iopoll is initially for small size, latency sensitive IO. It doesn't work well for big IO, especially when it needs to be split to multiple bios. In this case, the returned cookie of __submit_bio_noacct_mq() is indeed the cookie of the last split bio. The completion of *this* last split bio done by iopoll doesn't mean the whole original bio has completed. Callers of iopoll still need to wait for completion of other split bios. Besides bio splitting may cause more trouble for iopoll which isn't supposed to be used in case of big IO. iopoll for split bio may cause potential race if CPU migration happens during bio submission. Since the returned cookie is that of the last split bio, polling on the corresponding hardware queue doesn't help complete other split bios, if these split bios are enqueued into different hardware queues. Since interrupts are disabled for polling queues, the completion of these other split bios depends on timeout mechanism, thus causing a potential hang. iopoll for split bio may also cause hang for sync polling. Currently both the blkdev and iomap-based fs (ext4/xfs, etc) support sync polling in direct IO routine. These routines will submit bio without REQ_NOWAIT flag set, and then start sync polling in current process context. The process may hang in blk_mq_get_tag() if the submitted bio has to be split into multiple bios and can rapidly exhaust the queue depth. The process are waiting for the completion of the previously allocated requests, which should be reaped by the following polling, and thus causing a deadlock. To avoid these subtle trouble described above, just disable iopoll for split bio and return BLK_QC_T_NONE in this case. The side effect is that non-HIPRI IO also returns BLK_QC_T_NONE now. It should be acceptable since the returned cookie is never used for non-HIPRI IO. Suggested-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-08blk-mq: skip hybrid polling if iopoll doesn't spinPavel Begunkov1-2/+3
If blk_poll() is not going to spin (i.e. @spin=false), it also must not sleep in hybrid polling, otherwise it might be pretty suprising for users trying to do a quick check and expecting no-wait behaviour. Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-04block: remove the request_queue to argument request based tracepointsChristoph Hellwig1-4/+4
The request_queue can trivially be derived from the request. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-04block: simplify and extend the block_bio_merge tracepoint classChristoph Hellwig1-1/+1
The block_bio_merge tracepoint class can be reused for most bio-based tracepoints. For that it just needs to lose the superfluous q and rq parameters. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-02block: fix inflight statistics of part0Jeffle Xu1-1/+2
The inflight of partition 0 doesn't include inflight IOs to all sub-partitions, since currently mq calculates inflight of specific partition by simply camparing the value of the partition pointer. Thus the following case is possible: $ cat /sys/block/vda/inflight        0        0 $ cat /sys/block/vda/vda1/inflight        0      128 While single queue device (on a previous version, e.g. v3.10) has no this issue: $cat /sys/block/sda/sda3/inflight 0 33 $cat /sys/block/sda/inflight 0 33 Partition 0 should be specially handled since it represents the whole disk. This issue is introduced since commit bf0ddaba65dd ("blk-mq: fix sysfs inflight counter"). Besides, this patch can also fix the inflight statistics of part 0 in /proc/diskstats. Before this patch, the inflight statistics of part 0 doesn't include that of sub partitions. (I have marked the 'inflight' field with asterisk.) $cat /proc/diskstats 259 0 nvme0n1 45974469 0 367814768 6445794 1 0 1 0 *0* 111062 6445794 0 0 0 0 0 0 259 2 nvme0n1p1 45974058 0 367797952 6445727 0 0 0 0 *33* 111001 6445727 0 0 0 0 0 0 This is introduced since commit f299b7c7a9de ("blk-mq: provide internal in-flight variant"). Fixes: bf0ddaba65dd ("blk-mq: fix sysfs inflight counter") Fixes: f299b7c7a9de ("blk-mq: provide internal in-flight variant") Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Reviewed-by: Christoph Hellwig <hch@lst.de> [axboe: adapt for 5.11 partition change] Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-12-02block: switch partition lookup to use struct block_deviceChristoph Hellwig1-4/+5
Use struct block_device to lookup partitions on a disk. This removes all usage of struct hd_struct from the I/O path. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Hannes Reinecke <hare@suse.de> Acked-by: Coly Li <colyli@suse.de> [bcache] Acked-by: Chao Yu <yuchao0@huawei.com> [f2fs] Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-11-24smp: Cleanup smp_call_function*()Peter Zijlstra1-3/+1
Get rid of the __call_single_node union and cleanup the API a little to avoid external code relying on the structure layout as much. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2020-11-11scsi: block: Return status code in blk_mq_end_request()Hannes Reinecke1-1/+1
blk_mq_end_request() will use the block status returned from queue_rq() as argument, except in one instance in blk_mq_dispatch_rq_list(), where the generic BLK_STS_IOERR is used. Link: https://lore.kernel.org/r/20200930080256.90964-2-hare@suse.de Reviewed-by: Ewan D. Milne <emilne@redhat.com> Signed-off-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2020-10-24Merge tag 'block-5.10-2020-10-24' of git://git.kernel.dk/linux-blockLinus Torvalds1-2/+2
Pull block fixes from Jens Axboe: - NVMe pull request from Christoph - rdma error handling fixes (Chao Leng) - fc error handling and reconnect fixes (James Smart) - fix the qid displace when tracing ioctl command (Keith Busch) - don't use BLK_MQ_REQ_NOWAIT for passthru (Chaitanya Kulkarni) - fix MTDT for passthru (Logan Gunthorpe) - blacklist Write Same on more devices (Kai-Heng Feng) - fix an uninitialized work struct (zhenwei pi)" - lightnvm out-of-bounds fix (Colin) - SG allocation leak fix (Doug) - rnbd fixes (Gioh, Guoqing, Jack) - zone error translation fixes (Keith) - kerneldoc markup fix (Mauro) - zram lockdep fix (Peter) - Kill unused io_context members (Yufen) - NUMA memory allocation cleanup (Xianting) - NBD config wakeup fix (Xiubo) * tag 'block-5.10-2020-10-24' of git://git.kernel.dk/linux-block: (27 commits) block: blk-mq: fix a kernel-doc markup nvme-fc: shorten reconnect delay if possible for FC nvme-fc: wait for queues to freeze before calling update_hr_hw_queues nvme-fc: fix error loop in create_hw_io_queues nvme-fc: fix io timeout to abort I/O null_blk: use zone status for max active/open nvmet: don't use BLK_MQ_REQ_NOWAIT for passthru nvmet: cleanup nvmet_passthru_map_sg() nvmet: limit passthru MTDS by BIO_MAX_PAGES nvmet: fix uninitialized work for zero kato nvme-pci: disable Write Zeroes on Sandisk Skyhawk nvme: use queuedata for nvme_req_qid nvme-rdma: fix crash due to incorrect cqe nvme-rdma: fix crash when connect rejected block: remove unused members for io_context blk-mq: remove the calling of local_memory_node() zram: Fix __zram_bvec_{read,write}() locking order skd_main: remove unused including <linux/version.h> sgl_alloc_order: fix memory leak lightnvm: fix out-of-bounds write to array devices->info[] ...
2020-10-23block: blk-mq: fix a kernel-doc markupMauro Carvalho Chehab1-1/+1
Fix a typo: blk_mq_run_hw_queue -> blk_mq_run_hw_queues Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-10-20blk-mq: remove the calling of local_memory_node()Xianting Tian1-1/+1
We don't need to check whether the node is memoryless numa node before calling allocator interface. SLUB(and SLAB,SLOB) relies on the page allocator to pick a node. Page allocator should deal with memoryless nodes just fine. It has zonelists constructed for each possible nodes. And it will automatically fall back into a node which is closest to the requested node. As long as __GFP_THISNODE is not enforced of course. The code comments of kmem_cache_alloc_node() of SLAB also showed this: * Fallback to other node is possible if __GFP_THISNODE is not set. blk-mq code doesn't set __GFP_THISNODE, so we can remove the calling of local_memory_node(). Signed-off-by: Xianting Tian <tian.xianting@h3c.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-10-15Merge tag 'for-5.10/dm-changes' of ↵Linus Torvalds1-1/+0
git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm Pull device mapper updates from Mike Snitzer: - Improve DM core's bio splitting to use blk_max_size_offset(). Also fix bio splitting for bios that were deferred to the worker thread due to a DM device being suspended. - Remove DM core's special handling of NVMe devices now that block core has internalized efficiencies drivers previously needed to be concerned about (via now removed direct_make_request). - Fix request-based DM to not bounce through indirect dm_submit_bio; instead have block core make direct call to blk_mq_submit_bio(). - Various DM core cleanups to simplify and improve code. - Update DM cryot to not use drivers that set CRYPTO_ALG_ALLOCATES_MEMORY. - Fix DM raid's raid1 and raid10 discard limits for the purposes of linux-stable. But then remove DM raid's discard limits settings now that MD raid can efficiently handle large discards. - A couple small cleanups across various targets. * tag 'for-5.10/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: dm: fix request-based DM to not bounce through indirect dm_submit_bio dm: remove special-casing of bio-based immutable singleton target on NVMe dm: export dm_copy_name_and_uuid dm: fix comment in __dm_suspend() dm: fold dm_process_bio() into dm_submit_bio() dm: fix missing imposition of queue_limits from dm_wq_work() thread dm snap persistent: simplify area_io() dm thin metadata: Remove unused local variable when create thin and snap dm raid: remove unnecessary discard limits for raid10 dm raid: fix discard limits for raid1 and raid10 dm crypt: don't use drivers that have CRYPTO_ALG_ALLOCATES_MEMORY dm: use dm_table_get_device_name() where appropriate in targets dm table: make 'struct dm_table' definition accessible to all of DM core dm: eliminate need for start_io_acct() forward declaration dm: simplify __process_abnormal_io() dm: push use of on-stack flush_bio down to __send_empty_flush() dm: optimize max_io_len() by inlining max_io_len_target_boundary() dm: push md->immutable_target optimization down to __process_bio() dm: change max_io_len() to use blk_max_size_offset() dm table: stack 'chunk_sectors' limit to account for target-specific splitting
2020-10-13Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-blockLinus Torvalds1-36/+65
Pull block updates from Jens Axboe: - Series of merge handling cleanups (Baolin, Christoph) - Series of blk-throttle fixes and cleanups (Baolin) - Series cleaning up BDI, seperating the block device from the backing_dev_info (Christoph) - Removal of bdget() as a generic API (Christoph) - Removal of blkdev_get() as a generic API (Christoph) - Cleanup of is-partition checks (Christoph) - Series reworking disk revalidation (Christoph) - Series cleaning up bio flags (Christoph) - bio crypt fixes (Eric) - IO stats inflight tweak (Gabriel) - blk-mq tags fixes (Hannes) - Buffer invalidation fixes (Jan) - Allow soft limits for zone append (Johannes) - Shared tag set improvements (John, Kashyap) - Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel) - DM no-wait support (Mike, Konstantin) - Request allocation improvements (Ming) - Allow md/dm/bcache to use IO stat helpers (Song) - Series improving blk-iocost (Tejun) - Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang, Xianting, Yang, Yufen, yangerkun) * tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits) block: fix uapi blkzoned.h comments blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue blk-mq: get rid of the dead flush handle code path block: get rid of unnecessary local variable block: fix comment and add lockdep assert blk-mq: use helper function to test hw stopped block: use helper function to test queue register block: remove redundant mq check block: invoke blk_mq_exit_sched no matter whether have .exit_sched percpu_ref: don't refer to ref->data if it isn't allocated block: ratelimit handle_bad_sector() message blk-throttle: Re-use the throtl_set_slice_end() blk-throttle: Open code __throtl_de/enqueue_tg() blk-throttle: Move service tree validation out of the throtl_rb_first() blk-throttle: Move the list operation after list validation blk-throttle: Fix IO hang for a corner case blk-throttle: Avoid tracking latency if low limit is invalid blk-throttle: Avoid getting the current time if tg->last_finish_time is 0 blk-throttle: Remove a meaningless parameter for throtl_downgrade_state() block: Remove redundant 'return' statement ...
2020-10-09blk-mq: use helper function to test hw stoppedYufen Yu1-1/+1
We have introduced helper function blk_mq_hctx_stopped() to test BLK_MQ_S_STOPPED. Signed-off-by: Yufen Yu <yuyufen@huawei.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-10-08dm: fix request-based DM to not bounce through indirect dm_submit_bioMike Snitzer1-1/+0
It is unnecessary to force request-based DM to call into bio-based dm_submit_bio (via indirect disk->fops->submit_bio) only to have it then call blk_mq_submit_bio(). Fix this by establishing a request-based DM block_device_operations (dm_rq_blk_dops, which doesn't have .submit_bio) and update dm_setup_md_queue() to set md->disk->fops to it for DM_TYPE_REQUEST_BASED. Remove DM_TYPE_REQUEST_BASED conditional in dm_submit_bio and unexport blk_mq_submit_bio. Fixes: c62b37d96b6eb ("block: move ->make_request_fn to struct block_device_operations") Signed-off-by: Mike Snitzer <snitzer@redhat.com>
2020-10-06block: Consider only dispatched requests for inflight statisticGabriel Krisman Bertazi1-1/+1
According to Documentation/block/stat.rst, inflight should not include I/O requests that are in the queue but not yet dispatched to the device, but blk-mq identifies as inflight any request that has a tag allocated, which, for queues without elevator, happens at request allocation time and before it is queued in the ctx (default case in blk_mq_submit_bio). In addition, current behavior is different for queues with elevator from queues without it, since for the former the driver tag is allocated at dispatch time. A more precise approach would be to only consider requests with state MQ_RQ_IN_FLIGHT. This effectively reverts commit 6131837b1de6 ("blk-mq: count allocated but not started requests in iostats inflight") to consolidate blk-mq behavior with itself (elevator case) and with original documentation, but it differs from the behavior used by the legacy path. This version differs from v1 by using blk_mq_rq_state to access the state attribute. Avoid using blk_mq_request_started, which was suggested, since we don't want to include MQ_RQ_COMPLETE. Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com> Cc: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-10-05block: make blk_crypto_rq_bio_prep() able to failEric Biggers1-1/+6
blk_crypto_rq_bio_prep() assumes its gfp_mask argument always includes __GFP_DIRECT_RECLAIM, so that the mempool_alloc() will always succeed. However, blk_crypto_rq_bio_prep() might be called with GFP_ATOMIC via setup_clone() in drivers/md/dm-rq.c. This case isn't currently reachable with a bio that actually has an encryption context. However, it's fragile to rely on this. Just make blk_crypto_rq_bio_prep() able to fail. Suggested-by: Satya Tangirala <satyat@google.com> Signed-off-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Satya Tangirala <satyat@google.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-29blk-mq: call commit_rqs while list empty but error happenyangerkun1-9/+9
Blk-mq should call commit_rqs once 'bd.last != true' and no more request will come(so virtscsi can kick the virtqueue, e.g.). We already do that in 'blk_mq_dispatch_rq_list/blk_mq_try_issue_list_directly' while list not empty and 'queued > 0'. However, we can seen the same scene once the last request in list call queue_rq and return error like BLK_STS_IOERR which will not requeue the request, and lead that list empty but need call commit_rqs too(Or the request for virtscsi will stay timeout until other request kick virtqueue). We found this problem by do fsstress test with offline/online virtscsi device repeat quickly. Fixes: d666ba98f849 ("blk-mq: add mq_ops->commit_rqs()") Reported-by: zhangyi (F) <yi.zhang@huawei.com> Signed-off-by: yangerkun <yangerkun@huawei.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-28blk-mq: add cond_resched() in __blk_mq_alloc_rq_maps()Xianting Tian1-1/+3
We found blk_mq_alloc_rq_maps() takes more time in kernel space when testing nvme device hot-plugging. The test and anlysis as below. Debug code, 1, blk_mq_alloc_rq_maps(): u64 start, end; depth = set->queue_depth; start = ktime_get_ns(); pr_err("[%d:%s switch:%ld,%ld] queue depth %d, nr_hw_queues %d\n", current->pid, current->comm, current->nvcsw, current->nivcsw, set->queue_depth, set->nr_hw_queues); do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); end = ktime_get_ns(); pr_err("[%d:%s switch:%ld,%ld] all hw queues init cost time %lld ns\n", current->pid, current->comm, current->nvcsw, current->nivcsw, end - start); 2, __blk_mq_alloc_rq_maps(): u64 start, end; for (i = 0; i < set->nr_hw_queues; i++) { start = ktime_get_ns(); if (!__blk_mq_alloc_rq_map(set, i)) goto out_unwind; end = ktime_get_ns(); pr_err("hw queue %d init cost time %lld ns\n", i, end - start); } Test nvme hot-plugging with above debug code, we found it totally cost more than 3ms in kernel space without being scheduled out when alloc rqs for all 16 hw queues with depth 1023, each hw queue cost about 140-250us. The cost time will be increased with hw queue number and queue depth increasing. And in an extreme case, if __blk_mq_alloc_rq_maps() returns -ENOMEM, it will try "queue_depth >>= 1", more time will be consumed. [ 428.428771] nvme nvme0: pci function 10000:01:00.0 [ 428.428798] nvme 10000:01:00.0: enabling device (0000 -> 0002) [ 428.428806] pcieport 10000:00:00.0: can't derive routing for PCI INT A [ 428.428809] nvme 10000:01:00.0: PCI INT A: no GSI [ 432.593374] [4688:kworker/u33:8 switch:663,2] queue depth 30, nr_hw_queues 1 [ 432.593404] hw queue 0 init cost time 22883 ns [ 432.593408] [4688:kworker/u33:8 switch:663,2] all hw queues init cost time 35960 ns [ 432.595953] nvme nvme0: 16/0/0 default/read/poll queues [ 432.595958] [4688:kworker/u33:8 switch:700,2] queue depth 1023, nr_hw_queues 16 [ 432.596203] hw queue 0 init cost time 242630 ns [ 432.596441] hw queue 1 init cost time 235913 ns [ 432.596659] hw queue 2 init cost time 216461 ns [ 432.596877] hw queue 3 init cost time 215851 ns [ 432.597107] hw queue 4 init cost time 228406 ns [ 432.597336] hw queue 5 init cost time 227298 ns [ 432.597564] hw queue 6 init cost time 224633 ns [ 432.597785] hw queue 7 init cost time 219954 ns [ 432.597937] hw queue 8 init cost time 150930 ns [ 432.598082] hw queue 9 init cost time 143496 ns [ 432.598231] hw queue 10 init cost time 147261 ns [ 432.598397] hw queue 11 init cost time 164522 ns [ 432.598542] hw queue 12 init cost time 143401 ns [ 432.598692] hw queue 13 init cost time 148934 ns [ 432.598841] hw queue 14 init cost time 147194 ns [ 432.598991] hw queue 15 init cost time 148942 ns [ 432.598993] [4688:kworker/u33:8 switch:700,2] all hw queues init cost time 3035099 ns [ 432.602611] nvme0n1: p1 So use this patch to trigger schedule between each hw queue init, to avoid other threads getting stuck. It is not in atomic context when executing __blk_mq_alloc_rq_maps(), so it is safe to call cond_resched(). Signed-off-by: Xianting Tian <tian.xianting@h3c.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-11blk-mq: always allow reserved allocation in hctx_may_queueMing Lei1-2/+3
NVMe shares tagset between fabric queue and admin queue or between connect_q and NS queue, so hctx_may_queue() can be called to allocate request for these queues. Tags can be reserved in these tagset. Before error recovery, there is often lots of in-flight requests which can't be completed, and new reserved request may be needed in error recovery path. However, hctx_may_queue() can always return false because there is too many in-flight requests which can't be completed during error handling. Finally, nothing can proceed. Fix this issue by always allowing reserved tag allocation in hctx_may_queue(). This is reasonable because reserved tags are supposed to always be available. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Cc: David Milburn <dmilburn@redhat.com> Cc: Ewan D. Milne <emilne@redhat.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-04blk-mq, elevator: Count requests per hctx to improve performanceKashyap Desai1-0/+1
High CPU utilization on "native_queued_spin_lock_slowpath" due to lock contention is possible for mq-deadline and bfq IO schedulers when nr_hw_queues is more than one. It is because kblockd work queue can submit IO from all online CPUs (through blk_mq_run_hw_queues()) even though only one hctx has pending commands. The elevator callback .has_work for mq-deadline and bfq scheduler considers pending work if there are any IOs on request queue but it does not account hctx context. Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering the elevator even though there are no requests queued. [jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap] Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com> Signed-off-by: Hannes Reinecke <hare@suse.de> Signed-off-by: John Garry <john.garry@huawei.com> Tested-by: Douglas Gilbert <dgilbert@interlog.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-04blk-mq: Record active_queues_shared_sbitmap per tag_set for when using ↵John Garry1-0/+2
shared sbitmap For when using a shared sbitmap, no longer should the number of active request queues per hctx be relied on for when judging how to share the tag bitmap. Instead maintain the number of active request queues per tag_set, and make the judgement based on that. Originally-from: Kashyap Desai <kashyap.desai@broadcom.com> Signed-off-by: John Garry <john.garry@huawei.com> Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used Tested-by: Douglas Gilbert <dgilbert@interlog.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-04blk-mq: Record nr_active_requests per queue for when using shared sbitmapJohn Garry1-2/+2
The per-hctx nr_active value can no longer be used to fairly assign a share of tag depth per request queue for when using a shared sbitmap, as it does not consider that the tags are shared tags over all hctx's. For this case, record the nr_active_requests per request_queue, and make the judgement based on that value. Co-developed-with: Kashyap Desai <kashyap.desai@broadcom.com> Signed-off-by: John Garry <john.garry@huawei.com> Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used Tested-by: Douglas Gilbert <dgilbert@interlog.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-04blk-mq: Facilitate a shared sbitmap per tagsetJohn Garry1-0/+15
Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support multiple reply queues with single hostwide tags. In addition, these drivers want to use interrupt assignment in pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0], CPU hotplug may cause in-flight IO completion to not be serviced when an interrupt is shutdown. That problem is solved in commit bf0beec0607d ("blk-mq: drain I/O when all CPUs in a hctx are offline"). However, to take advantage of that blk-mq feature, the HBA HW queuess are required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW queues need to be exposed to the upper layer. In making that transition, the per-SCSI command request tags are no longer unique per Scsi host - they are just unique per hctx. As such, the HBA LLDD would have to generate this tag internally, which has a certain performance overhead. However another problem is that blk-mq assumes the host may accept (Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy counter was removed, which would stop the LLDD being sent more than .can_queue commands; however, it should still be ensured that the block layer does not issue more than .can_queue commands to the Scsi host. To solve this problem, introduce a shared sbitmap per blk_mq_tag_set, which may be requested at init time. New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the tagset to indicate whether the shared sbitmap should be used. Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests are still allocated per hctx; the reason for this is that if tags and requests were only allocated for a single hctx - like hctx0 - it may break block drivers which expect a request be associated with a specific hctx, i.e. not always hctx0. This will introduce extra memory usage. This change is based on work originally from Ming Lei in [1] and from Bart's suggestion in [2]. [0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/ [2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be Signed-off-by: John Garry <john.garry@huawei.com> Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used Tested-by: Douglas Gilbert <dgilbert@interlog.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-04blk-mq: Use pointers for blk_mq_tags bitmap tagsJohn Garry1-4/+4
Introduce pointers for the blk_mq_tags regular and reserved bitmap tags, with the goal of later being able to use a common shared tag bitmap across all HW contexts in a set. Signed-off-by: John Garry <john.garry@huawei.com> Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used Tested-by: Douglas Gilbert <dgilbert@interlog.com> Reviewed-by: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-09-04blk-mq: Pass flags for tag init/freeJohn Garry1-10/+13
Pass hctx/tagset flags argument down to blk_mq_init_tags() and blk_mq_free_tags() for selective init/free. For now, make it include the alloc policy flag, which can be evaluated when needed (in blk_mq_init_tags()). Signed-off-by: John Garry <john.garry@huawei.com> Tested-by: Douglas Gilbert <dgilbert@interlog.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>