summaryrefslogtreecommitdiff
path: root/block/blk-mq.c
AgeCommit message (Collapse)Author
2017-06-06blk-mq: fix direct issueMing Lei
If queue is stopped, we shouldn't dispatch request into driver and hardware, unfortunately the check is removed in bd166ef183c2(blk-mq-sched: add framework for MQ capable IO schedulers). This patch fixes the issue by moving the check back into __blk_mq_try_issue_directly(). This patch fixes request use-after-free[1][2] during canceling requets of NVMe in nvme_dev_disable(), which can be triggered easily during NVMe reset & remove test. [1] oops kernel log when CONFIG_BLK_DEV_INTEGRITY is on [ 103.412969] BUG: unable to handle kernel NULL pointer dereference at 000000000000000a [ 103.412980] IP: bio_integrity_advance+0x48/0xf0 [ 103.412981] PGD 275a88067 [ 103.412981] P4D 275a88067 [ 103.412982] PUD 276c43067 [ 103.412983] PMD 0 [ 103.412984] [ 103.412986] Oops: 0000 [#1] SMP [ 103.412989] Modules linked in: vfat fat intel_rapl sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel crypto_simd cryptd ipmi_ssif iTCO_wdt iTCO_vendor_support mxm_wmi glue_helper dcdbas ipmi_si mei_me pcspkr mei sg ipmi_devintf lpc_ich ipmi_msghandler shpchp acpi_power_meter wmi nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm crc32c_intel nvme ahci nvme_core libahci libata tg3 i2c_core megaraid_sas ptp pps_core dm_mirror dm_region_hash dm_log dm_mod [ 103.413035] CPU: 0 PID: 102 Comm: kworker/0:2 Not tainted 4.11.0+ #1 [ 103.413036] Hardware name: Dell Inc. PowerEdge R730xd/072T6D, BIOS 2.2.5 09/06/2016 [ 103.413041] Workqueue: events nvme_remove_dead_ctrl_work [nvme] [ 103.413043] task: ffff9cc8775c8000 task.stack: ffffc033c252c000 [ 103.413045] RIP: 0010:bio_integrity_advance+0x48/0xf0 [ 103.413046] RSP: 0018:ffffc033c252fc10 EFLAGS: 00010202 [ 103.413048] RAX: 0000000000000000 RBX: ffff9cc8720a8cc0 RCX: ffff9cca72958240 [ 103.413049] RDX: ffff9cca72958000 RSI: 0000000000000008 RDI: ffff9cc872537f00 [ 103.413049] RBP: ffffc033c252fc28 R08: 0000000000000000 R09: ffffffffb963a0d5 [ 103.413050] R10: 000000000000063e R11: 0000000000000000 R12: ffff9cc8720a8d18 [ 103.413051] R13: 0000000000001000 R14: ffff9cc872682e00 R15: 00000000fffffffb [ 103.413053] FS: 0000000000000000(0000) GS:ffff9cc877c00000(0000) knlGS:0000000000000000 [ 103.413054] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 103.413055] CR2: 000000000000000a CR3: 0000000276c41000 CR4: 00000000001406f0 [ 103.413056] Call Trace: [ 103.413063] bio_advance+0x2a/0xe0 [ 103.413067] blk_update_request+0x76/0x330 [ 103.413072] blk_mq_end_request+0x1a/0x70 [ 103.413074] blk_mq_dispatch_rq_list+0x370/0x410 [ 103.413076] ? blk_mq_flush_busy_ctxs+0x94/0xe0 [ 103.413080] blk_mq_sched_dispatch_requests+0x173/0x1a0 [ 103.413083] __blk_mq_run_hw_queue+0x8e/0xa0 [ 103.413085] __blk_mq_delay_run_hw_queue+0x9d/0xa0 [ 103.413088] blk_mq_start_hw_queue+0x17/0x20 [ 103.413090] blk_mq_start_hw_queues+0x32/0x50 [ 103.413095] nvme_kill_queues+0x54/0x80 [nvme_core] [ 103.413097] nvme_remove_dead_ctrl_work+0x1f/0x40 [nvme] [ 103.413103] process_one_work+0x149/0x360 [ 103.413105] worker_thread+0x4d/0x3c0 [ 103.413109] kthread+0x109/0x140 [ 103.413111] ? rescuer_thread+0x380/0x380 [ 103.413113] ? kthread_park+0x60/0x60 [ 103.413120] ret_from_fork+0x2c/0x40 [ 103.413121] Code: 08 4c 8b 63 50 48 8b 80 80 00 00 00 48 8b 90 d0 03 00 00 31 c0 48 83 ba 40 02 00 00 00 48 8d 8a 40 02 00 00 48 0f 45 c1 c1 ee 09 <0f> b6 48 0a 0f b6 40 09 41 89 f5 83 e9 09 41 d3 ed 44 0f af e8 [ 103.413145] RIP: bio_integrity_advance+0x48/0xf0 RSP: ffffc033c252fc10 [ 103.413146] CR2: 000000000000000a [ 103.413157] ---[ end trace cd6875d16eb5a11e ]--- [ 103.455368] Kernel panic - not syncing: Fatal exception [ 103.459826] Kernel Offset: 0x37600000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 103.850916] ---[ end Kernel panic - not syncing: Fatal exception [ 103.857637] sched: Unexpected reschedule of offline CPU#1! [ 103.863762] ------------[ cut here ]------------ [2] kernel hang in blk_mq_freeze_queue_wait() when CONFIG_BLK_DEV_INTEGRITY is off [ 247.129825] INFO: task nvme-test:1772 blocked for more than 120 seconds. [ 247.137311] Not tainted 4.12.0-rc2.upstream+ #4 [ 247.142954] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 247.151704] Call Trace: [ 247.154445] __schedule+0x28a/0x880 [ 247.158341] schedule+0x36/0x80 [ 247.161850] blk_mq_freeze_queue_wait+0x4b/0xb0 [ 247.166913] ? remove_wait_queue+0x60/0x60 [ 247.171485] blk_freeze_queue+0x1a/0x20 [ 247.175770] blk_cleanup_queue+0x7f/0x140 [ 247.180252] nvme_ns_remove+0xa3/0xb0 [nvme_core] [ 247.185503] nvme_remove_namespaces+0x32/0x50 [nvme_core] [ 247.191532] nvme_uninit_ctrl+0x2d/0xa0 [nvme_core] [ 247.196977] nvme_remove+0x70/0x110 [nvme] [ 247.201545] pci_device_remove+0x39/0xc0 [ 247.205927] device_release_driver_internal+0x141/0x200 [ 247.211761] device_release_driver+0x12/0x20 [ 247.216531] pci_stop_bus_device+0x8c/0xa0 [ 247.221104] pci_stop_and_remove_bus_device_locked+0x1a/0x30 [ 247.227420] remove_store+0x7c/0x90 [ 247.231320] dev_attr_store+0x18/0x30 [ 247.235409] sysfs_kf_write+0x3a/0x50 [ 247.239497] kernfs_fop_write+0xff/0x180 [ 247.243867] __vfs_write+0x37/0x160 [ 247.247757] ? selinux_file_permission+0xe5/0x120 [ 247.253011] ? security_file_permission+0x3b/0xc0 [ 247.258260] vfs_write+0xb2/0x1b0 [ 247.261964] ? syscall_trace_enter+0x1d0/0x2b0 [ 247.266924] SyS_write+0x55/0xc0 [ 247.270540] do_syscall_64+0x67/0x150 [ 247.274636] entry_SYSCALL64_slow_path+0x25/0x25 [ 247.279794] RIP: 0033:0x7f5c96740840 [ 247.283785] RSP: 002b:00007ffd00e87ee8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 247.292238] RAX: ffffffffffffffda RBX: 0000000000000002 RCX: 00007f5c96740840 [ 247.300194] RDX: 0000000000000002 RSI: 00007f5c97060000 RDI: 0000000000000001 [ 247.308159] RBP: 00007f5c97060000 R08: 000000000000000a R09: 00007f5c97059740 [ 247.316123] R10: 0000000000000001 R11: 0000000000000246 R12: 00007f5c96a14400 [ 247.324087] R13: 0000000000000002 R14: 0000000000000001 R15: 0000000000000000 [ 370.016340] INFO: task nvme-test:1772 blocked for more than 120 seconds. Fixes: 12d70958a2e8(blk-mq: don't fail allocating driver tag for stopped hw queue) Cc: stable@vger.kernel.org Signed-off-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-06-06blk-mq: pass correct hctx to blk_mq_try_issue_directlyMing Lei
When direct issue is done on request picked up from plug list, the hctx need to be updated with the actual hw queue, otherwise wrong hctx is used and may hurt performance, especially when wrong SRCU readlock is acquired/released Reported-by: Bart Van Assche <bart.vanassche@sandisk.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-30blk-mq: Take tagset lock when updating hw queuesKeith Busch
The tagset lock needs to be held when iterating the tag_list, so a lockdep assert was added when updating number of hardware queues. The drivers calling this API, however, were unaware of the new requirement, so are failing the assertion. This patch takes the lock within the blk-mq function so the drivers do not have to be modified in order to be safe. Fixes: 705cda97e ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list") Reported-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk> Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Signed-off-by: Keith Busch <keith.busch@intel.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-22blk-mq: remove blk_mq_abort_requeue_list()Ming Lei
No one uses it any more, so remove it. Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2017-05-10blk-mq: NVMe 512B/4K+T10 DIF/DIX format returns I/O error on dd with split opWen Xiong
When formatting NVMe to 512B/4K + T10 DIf/DIX, dd with split op returns "Input/output error". Looks block layer split the bio after calling bio_integrity_prep(bio). This patch fixes the issue. Below is how we debug this issue: (1)format nvme to 4K block # size with type 2 DIF (2)dd with block size bigger than 1024k. oflag=direct dd: error writing '/dev/nvme0n1': Input/output error We added some debug code in nvme device driver. It showed us the first op and the second op have the same bi and pi address. This is not correct. 1st op: nvme0n1 Op:Wr slba 0x505 length 0x100, PI ctrl=0x1400, dsmgmt=0x0, AT=0x0 & RT=0x505 Guard 0x00b1, AT 0x0000, RT physical 0x00000505 RT virtual 0x00002828 2nd op: nvme0n1 Op:Wr slba 0x605 length 0x1, PI ctrl=0x1400, dsmgmt=0x0, AT=0x0 & RT=0x605 ==> This op fails and subsequent 5 retires.. Guard 0x00b1, AT 0x0000, RT physical 0x00000605 RT virtual 0x00002828 With the fix, It showed us both of the first op and the second op have correct bi and pi address. 1st op: nvme2n1 Op:Wr slba 0x505 length 0x100, PI ctrl=0x1400, dsmgmt=0x0, AT=0x0 & RT=0x505 Guard 0x5ccb, AT 0x0000, RT physical 0x00000505 RT virtual 0x00002828 2nd op: nvme2n1 Op:Wr slba 0x605 length 0x1, PI ctrl=0x1400, dsmgmt=0x0, AT=0x0 & RT=0x605 Guard 0xab4c, AT 0x0000, RT physical 0x00000605 RT virtual 0x00003028 Signed-off-by: Wen Xiong <wenxiong@linux.vnet.ibm.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-08blk-mq: make __blk_mq_stop_hw_queues staticColin Ian King
Making __blk_mq_stop_hw_queues static fixes sparse warning: block/blk-mq.c:6: warning: symbol '__blk_mq_stop_hw_queues' was not declared. Should it be static? Fixes: 2719aa217e0d0 ("blk-mq: don't use sync workqueue flushing from drivers") Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-07block/mq: fix potential deadlock during cpu hotplugWanpeng Li
This can be triggered by hot-unplug one cpu. ====================================================== [ INFO: possible circular locking dependency detected ] 4.11.0+ #17 Not tainted ------------------------------------------------------- step_after_susp/2640 is trying to acquire lock: (all_q_mutex){+.+...}, at: [<ffffffffb33f95b8>] blk_mq_queue_reinit_work+0x18/0x110 but task is already holding lock: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffffb306d04f>] cpu_hotplug_begin+0x7f/0xe0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (cpu_hotplug.lock){+.+.+.}: lock_acquire+0x11c/0x230 __mutex_lock+0x92/0x990 mutex_lock_nested+0x1b/0x20 get_online_cpus+0x64/0x80 blk_mq_init_allocated_queue+0x3a0/0x4e0 blk_mq_init_queue+0x3a/0x60 loop_add+0xe5/0x280 loop_init+0x124/0x177 do_one_initcall+0x53/0x1c0 kernel_init_freeable+0x1e3/0x27f kernel_init+0xe/0x100 ret_from_fork+0x31/0x40 -> #0 (all_q_mutex){+.+...}: __lock_acquire+0x189a/0x18a0 lock_acquire+0x11c/0x230 __mutex_lock+0x92/0x990 mutex_lock_nested+0x1b/0x20 blk_mq_queue_reinit_work+0x18/0x110 blk_mq_queue_reinit_dead+0x1c/0x20 cpuhp_invoke_callback+0x1f2/0x810 cpuhp_down_callbacks+0x42/0x80 _cpu_down+0xb2/0xe0 freeze_secondary_cpus+0xb6/0x390 suspend_devices_and_enter+0x3b3/0xa40 pm_suspend+0x129/0x490 state_store+0x82/0xf0 kobj_attr_store+0xf/0x20 sysfs_kf_write+0x45/0x60 kernfs_fop_write+0x135/0x1c0 __vfs_write+0x37/0x160 vfs_write+0xcd/0x1d0 SyS_write+0x58/0xc0 do_syscall_64+0x8f/0x710 return_from_SYSCALL_64+0x0/0x7a other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(cpu_hotplug.lock); lock(all_q_mutex); lock(cpu_hotplug.lock); lock(all_q_mutex); *** DEADLOCK *** 8 locks held by step_after_susp/2640: #0: (sb_writers#6){.+.+.+}, at: [<ffffffffb3244aed>] vfs_write+0x1ad/0x1d0 #1: (&of->mutex){+.+.+.}, at: [<ffffffffb32d3a51>] kernfs_fop_write+0x101/0x1c0 #2: (s_active#166){.+.+.+}, at: [<ffffffffb32d3a59>] kernfs_fop_write+0x109/0x1c0 #3: (pm_mutex){+.+...}, at: [<ffffffffb30d2ecd>] pm_suspend+0x21d/0x490 #4: (acpi_scan_lock){+.+.+.}, at: [<ffffffffb34dc3d7>] acpi_scan_lock_acquire+0x17/0x20 #5: (cpu_add_remove_lock){+.+.+.}, at: [<ffffffffb306d6d7>] freeze_secondary_cpus+0x27/0x390 #6: (cpu_hotplug.dep_map){++++++}, at: [<ffffffffb306cfd5>] cpu_hotplug_begin+0x5/0xe0 #7: (cpu_hotplug.lock){+.+.+.}, at: [<ffffffffb306d04f>] cpu_hotplug_begin+0x7f/0xe0 stack backtrace: CPU: 3 PID: 2640 Comm: step_after_susp Not tainted 4.11.0+ #17 Hardware name: Dell Inc. OptiPlex 7040/0JCTF8, BIOS 1.4.9 09/12/2016 Call Trace: dump_stack+0x99/0xce print_circular_bug+0x1fa/0x270 __lock_acquire+0x189a/0x18a0 lock_acquire+0x11c/0x230 ? lock_acquire+0x11c/0x230 ? blk_mq_queue_reinit_work+0x18/0x110 ? blk_mq_queue_reinit_work+0x18/0x110 __mutex_lock+0x92/0x990 ? blk_mq_queue_reinit_work+0x18/0x110 ? kmem_cache_free+0x2cb/0x330 ? anon_transport_class_unregister+0x20/0x20 ? blk_mq_queue_reinit_work+0x110/0x110 mutex_lock_nested+0x1b/0x20 ? mutex_lock_nested+0x1b/0x20 blk_mq_queue_reinit_work+0x18/0x110 blk_mq_queue_reinit_dead+0x1c/0x20 cpuhp_invoke_callback+0x1f2/0x810 ? __flow_cache_shrink+0x160/0x160 cpuhp_down_callbacks+0x42/0x80 _cpu_down+0xb2/0xe0 freeze_secondary_cpus+0xb6/0x390 suspend_devices_and_enter+0x3b3/0xa40 ? rcu_read_lock_sched_held+0x79/0x80 pm_suspend+0x129/0x490 state_store+0x82/0xf0 kobj_attr_store+0xf/0x20 sysfs_kf_write+0x45/0x60 kernfs_fop_write+0x135/0x1c0 __vfs_write+0x37/0x160 ? rcu_read_lock_sched_held+0x79/0x80 ? rcu_sync_lockdep_assert+0x2f/0x60 ? __sb_start_write+0xd9/0x1c0 ? vfs_write+0x1ad/0x1d0 vfs_write+0xcd/0x1d0 SyS_write+0x58/0xc0 ? rcu_read_lock_sched_held+0x79/0x80 do_syscall_64+0x8f/0x710 ? trace_hardirqs_on_thunk+0x1a/0x1c entry_SYSCALL64_slow_path+0x25/0x25 The cpu hotplug path will hold cpu_hotplug.lock and then reinit all exiting queues for blk mq w/ all_q_mutex, however, blk_mq_init_allocated_queue() will contend these two locks in the inversion order. This is due to commit eabe06595d62 (blk/mq: Cure cpu hotplug lock inversion), it fixes a cpu hotplug lock inversion issue because of hotplug rework, however the hotplug rework is still work-in-progress and lives in a -tip branch and mainline cannot yet trigger that splat. The commit breaks the linus's tree in the merge window, so this patch reverts the lock order and avoids to splat linus's tree. Cc: Jens Axboe <axboe@kernel.dk> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-04blk-mq: untangle debugfs and sysfsOmar Sandoval
Originally, I tied debugfs registration/unregistration together with sysfs. There's no reason to do this, and it's getting in the way of letting schedulers define their own debugfs attributes. Instead, tie the debugfs registration to the lifetime of the structures themselves. The saner lifetimes mean we can also get rid of the extra mq directory and move everything one level up. I.e., nvme0n1/mq/hctx0/tags is now just nvme0n1/hctx0/tags. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-04block/mq: Cure cpu hotplug lock inversionPeter Zijlstra
By poking at /debug/sched_features I triggered the following splat: [] ====================================================== [] WARNING: possible circular locking dependency detected [] 4.11.0-00873-g964c8b7-dirty #694 Not tainted [] ------------------------------------------------------ [] bash/2109 is trying to acquire lock: [] (cpu_hotplug_lock.rw_sem){++++++}, at: [<ffffffff8120cb8b>] static_key_slow_dec+0x1b/0x50 [] [] but task is already holding lock: [] (&sb->s_type->i_mutex_key#4){+++++.}, at: [<ffffffff81140216>] sched_feat_write+0x86/0x170 [] [] which lock already depends on the new lock. [] [] [] the existing dependency chain (in reverse order) is: [] [] -> #2 (&sb->s_type->i_mutex_key#4){+++++.}: [] lock_acquire+0x100/0x210 [] down_write+0x28/0x60 [] start_creating+0x5e/0xf0 [] debugfs_create_dir+0x13/0x110 [] blk_mq_debugfs_register+0x21/0x70 [] blk_mq_register_dev+0x64/0xd0 [] blk_register_queue+0x6a/0x170 [] device_add_disk+0x22d/0x440 [] loop_add+0x1f3/0x280 [] loop_init+0x104/0x142 [] do_one_initcall+0x43/0x180 [] kernel_init_freeable+0x1de/0x266 [] kernel_init+0xe/0x100 [] ret_from_fork+0x31/0x40 [] [] -> #1 (all_q_mutex){+.+.+.}: [] lock_acquire+0x100/0x210 [] __mutex_lock+0x6c/0x960 [] mutex_lock_nested+0x1b/0x20 [] blk_mq_init_allocated_queue+0x37c/0x4e0 [] blk_mq_init_queue+0x3a/0x60 [] loop_add+0xe5/0x280 [] loop_init+0x104/0x142 [] do_one_initcall+0x43/0x180 [] kernel_init_freeable+0x1de/0x266 [] kernel_init+0xe/0x100 [] ret_from_fork+0x31/0x40 [] *** DEADLOCK *** [] [] 3 locks held by bash/2109: [] #0: (sb_writers#11){.+.+.+}, at: [<ffffffff81292bcd>] vfs_write+0x17d/0x1a0 [] #1: (debugfs_srcu){......}, at: [<ffffffff8155a90d>] full_proxy_write+0x5d/0xd0 [] #2: (&sb->s_type->i_mutex_key#4){+++++.}, at: [<ffffffff81140216>] sched_feat_write+0x86/0x170 [] [] stack backtrace: [] CPU: 9 PID: 2109 Comm: bash Not tainted 4.11.0-00873-g964c8b7-dirty #694 [] Hardware name: Intel Corporation S2600GZ/S2600GZ, BIOS SE5C600.86B.02.02.0002.122320131210 12/23/2013 [] Call Trace: [] lock_acquire+0x100/0x210 [] get_online_cpus+0x2a/0x90 [] static_key_slow_dec+0x1b/0x50 [] static_key_disable+0x20/0x30 [] sched_feat_write+0x131/0x170 [] full_proxy_write+0x97/0xd0 [] __vfs_write+0x28/0x120 [] vfs_write+0xb5/0x1a0 [] SyS_write+0x49/0xa0 [] entry_SYSCALL_64_fastpath+0x23/0xc2 This is because of the cpu hotplug lock rework. Break the chain at #1 by reversing the lock acquisition order. This way i_mutex_key#4 no longer depends on cpu_hotplug_lock and things are good. Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-03blk-mq: don't use sync workqueue flushing from driversJens Axboe
A previous commit introduced the sync flush, which we need from internal callers like blk_mq_quiesce_queue(). However, we also call the stop helpers from drivers, particularly from ->queue_rq() when we have to stop processing for a bit. We can't block from those locations, and we don't have to guarantee that we're fully flushed. Fixes: 9f993737906b ("blk-mq: unify hctx delayed_run_work and run_work") Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-02block: don't call blk_mq_quiesce_queue() after queue is frozenMing Lei
After queue is frozen, no request in this queue can be in use at all, so there can't be any .queue_rq() running on this queue. It isn't necessary to call blk_mq_quiesce_queue() any more, so remove it in both elevator_switch_mq() and blk_mq_update_nr_requests(). Cc: Bart Van Assche <bart.vanassche@sandisk.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Fixed up the description a bit. Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-02blk-mq: update ->init_request and ->exit_request prototypesChristoph Hellwig
Remove the request_idx parameter, which can't be used safely now that we support I/O schedulers with blk-mq. Except for a superflous check in mtip32xx it was unused anyway. Also pass the tag_set instead of just the driver data - this allows drivers to avoid some code duplication in a follow on cleanup. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-05-01Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-blockLinus Torvalds
Pull block layer updates from Jens Axboe: - Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ was initially a fork of CFQ, but subsequently changed to implement fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant to be used on desktop type single drives, providing good fairness. From Paolo. - Add Kyber IO scheduler. This is a full multiqueue aware scheduler, using a scalable token based algorithm that throttles IO based on live completion IO stats, similary to blk-wbt. From Omar. - A series from Jan, moving users to separately allocated backing devices. This continues the work of separating backing device life times, solving various problems with hot removal. - A series of updates for lightnvm, mostly from Javier. Includes a 'pblk' target that exposes an open channel SSD as a physical block device. - A series of fixes and improvements for nbd from Josef. - A series from Omar, removing queue sharing between devices on mostly legacy drivers. This helps us clean up other bits, if we know that a queue only has a single device backing. This has been overdue for more than a decade. - Fixes for the blk-stats, and improvements to unify the stats and user windows. This both improves blk-wbt, and enables other users to register a need to receive IO stats for a device. From Omar. - blk-throttle improvements from Shaohua. This provides a scalable framework for implementing scalable priotization - particularly for blk-mq, but applicable to any type of block device. The interface is marked experimental for now. - Bucketized IO stats for IO polling from Stephen Bates. This improves efficiency of polled workloads in the presence of mixed block size IO. - A few fixes for opal, from Scott. - A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics. From a variety of folks, mostly Sagi and James Smart. - A series from Bart, improving our exposed info and capabilities from the blk-mq debugfs support. - A series from Christoph, cleaning up how handle WRITE_ZEROES. - A series from Christoph, cleaning up the block layer handling of how we track errors in a request. On top of being a nice cleanup, it also shrinks the size of struct request a bit. - Removal of mg_disk and hd (sorry Linus) by Christoph. The former was never used by platforms, and the latter has outlived it's usefulness. - Various little bug fixes and cleanups from a wide variety of folks. * 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits) block: hide badblocks attribute by default blk-mq: unify hctx delay_work and run_work block: add kblock_mod_delayed_work_on() blk-mq: unify hctx delayed_run_work and run_work nbd: fix use after free on module unload MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler blk-mq-sched: alloate reserved tags out of normal pool mtip32xx: use runtime tag to initialize command header scsi: Implement blk_mq_ops.show_rq() blk-mq: Add blk_mq_ops.show_rq() blk-mq: Show operation, cmd_flags and rq_flags names blk-mq: Make blk_flags_show() callers append a newline character blk-mq: Move the "state" debugfs attribute one level down blk-mq: Unregister debugfs attributes earlier blk-mq: Only unregister hctxs for which registration succeeded blk-mq-debugfs: Rename functions for registering and unregistering the mq directory blk-mq: Let blk_mq_debugfs_register() look up the queue name blk-mq: Register <dev>/queue/mq after having registered <dev>/queue ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset ide-pm: always pass 0 error to __blk_end_request_all ..
2017-04-28blk-mq: unify hctx delay_work and run_workJens Axboe
The only difference between ->run_work and ->delay_work, is that the latter is used to defer running a queue. This is done by marking the queue stopped, and scheduling ->delay_work to run sometime in the future. While the queue is stopped, direct runs or runs through ->run_work will not run the queue. If we combine the handlers, then we need to handle two things: 1) If a delayed/stopped run is scheduled, then we should not run the queue before that has been completed. 2) If a queue is delayed/stopped, the handler needs to restart the queue. Normally a run of a queue with the stopped bit set would be a no-op. Case 1 is handled by modifying a currently pending queue run to the deadline set by the caller of blk_mq_delay_queue(). Subsequent attempts to queue a queue run will find the work item already pending, and direct runs will see a stopped queue as before. Case 2 is handled by adding a new bit, BLK_MQ_S_START_ON_RUN, that tells the work handler that it should clear a stopped queue and run the handler. Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-28blk-mq: unify hctx delayed_run_work and run_workJens Axboe
They serve the exact same purpose. Get rid of the non-delayed work variant, and just run it without delay for the normal case. Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-21blk-mq: Fix preempt count imbalanceBart Van Assche
Avoid that the following kernel bug gets triggered: BUG: sleeping function called from invalid context at ./include/linux/buffer_head.h:349 in_atomic(): 1, irqs_disabled(): 0, pid: 8019, name: find CPU: 10 PID: 8019 Comm: find Tainted: G W I 4.11.0-rc4-dbg+ #2 Call Trace: dump_stack+0x68/0x93 ___might_sleep+0x16e/0x230 __might_sleep+0x4a/0x80 __ext4_get_inode_loc+0x1e0/0x4e0 ext4_iget+0x70/0xbc0 ext4_iget_normal+0x2f/0x40 ext4_lookup+0xb6/0x1f0 lookup_slow+0x104/0x1e0 walk_component+0x19a/0x330 path_lookupat+0x4b/0x100 filename_lookup+0x9a/0x110 user_path_at_empty+0x36/0x40 vfs_statx+0x67/0xc0 SYSC_newfstatat+0x20/0x40 SyS_newfstatat+0xe/0x10 entry_SYSCALL_64_fastpath+0x18/0xad This happens since the big if/else in blk_mq_make_request() doesn't have final else section that also drops the ctx. Add that. Fixes: b00c53e8f411 ("blk-mq: fix schedule-while-atomic with scheduler attached") Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Omar Sandoval <osandov@fb.com> Added a bit more to the commit log. Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-21blk-stat: kill blk_stat_rq_ddir()Jens Axboe
No point in providing and exporting this helper. There's just one (real) user of it, just use rq_data_dir(). Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: add might_sleep check to blk_mq_get_driver_tag()Jens Axboe
If the caller passes in wait=true, it has to be able to block for a driver tag. We just had a bug where flush insertion would block on tag allocation, while we had preempt disabled. Ensure that we catch cases like that earlier next time. Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: Fix poll_stat for new size-based bucketing.Stephen Bates
Fixes an issue where the size of the poll_stat array in request_queue does not match the size expected by the new size based bucketing for IO completion polling. Fixes: 720b8ccc4500 ("blk-mq: Add a polling specific stats function") Signed-off-by: Stephen Bates <sbates@raithlin.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: fix schedule-while-atomic with scheduler attachedJens Axboe
We must have dropped the ctx before we call blk_mq_sched_insert_request() with can_block=true, otherwise we risk that a flush request can block on insertion if we are currently out of tags. [ 47.667190] BUG: scheduling while atomic: jbd2/sda2-8/2089/0x00000002 [ 47.674493] Modules linked in: x86_pkg_temp_thermal btrfs xor zlib_deflate raid6_pq sr_mod cdre [ 47.690572] Preemption disabled at: [ 47.690584] [<ffffffff81326c7c>] blk_mq_sched_get_request+0x6c/0x280 [ 47.701764] CPU: 1 PID: 2089 Comm: jbd2/sda2-8 Not tainted 4.11.0-rc7+ #271 [ 47.709630] Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016 [ 47.718081] Call Trace: [ 47.720903] dump_stack+0x4f/0x73 [ 47.724694] ? blk_mq_sched_get_request+0x6c/0x280 [ 47.730137] __schedule_bug+0x6c/0xc0 [ 47.734314] __schedule+0x559/0x780 [ 47.738302] schedule+0x3b/0x90 [ 47.741899] io_schedule+0x11/0x40 [ 47.745788] blk_mq_get_tag+0x167/0x2a0 [ 47.750162] ? remove_wait_queue+0x70/0x70 [ 47.754901] blk_mq_get_driver_tag+0x92/0xf0 [ 47.759758] blk_mq_sched_insert_request+0x134/0x170 [ 47.765398] ? blk_account_io_start+0xd0/0x270 [ 47.770679] blk_mq_make_request+0x1b2/0x850 [ 47.775766] generic_make_request+0xf7/0x2d0 [ 47.780860] submit_bio+0x5f/0x120 [ 47.784979] ? submit_bio+0x5f/0x120 [ 47.789631] submit_bh_wbc.isra.46+0x10d/0x130 [ 47.794902] submit_bh+0xb/0x10 [ 47.798719] journal_submit_commit_record+0x190/0x210 [ 47.804686] ? _raw_spin_unlock+0x13/0x30 [ 47.809480] jbd2_journal_commit_transaction+0x180a/0x1d00 [ 47.815925] kjournald2+0xb6/0x250 [ 47.820022] ? kjournald2+0xb6/0x250 [ 47.824328] ? remove_wait_queue+0x70/0x70 [ 47.829223] kthread+0x10e/0x140 [ 47.833147] ? commit_timeout+0x10/0x10 [ 47.837742] ? kthread_create_on_node+0x40/0x40 [ 47.843122] ret_from_fork+0x29/0x40 Fixes: a4d907b6a33b ("blk-mq: streamline blk_mq_make_request") Reviewed-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: Add a polling specific stats functionStephen Bates
Rather than bucketing IO statisics based on direction only we also bucket based on the IO size. This leads to improved polling performance. Update the bucket callback function and use it in the polling latency estimation. Signed-off-by: Stephen Bates <sbates@raithlin.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: fix potential oops with polling and blk-mq schedulerJens Axboe
If we have a scheduler attached, blk_mq_tag_to_rq() on the scheduled tags will return NULL if a request is no longer in flight. This is different than using the normal tags, where it will always return the fixed request. Check for this condition for polling, in case we happen to enter polling for a completed request. The request address remains valid, so this check and return should be perfectly safe. Fixes: bd166ef183c2 ("blk-mq-sched: add framework for MQ capable IO schedulers") Tested-by: Stephen Bates <sbates@raithlin.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20block: remove the errors field from struct requestChristoph Hellwig
Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Acked-by: Roger Pau Monné <roger.pau@citrix.com> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: simplify __blk_mq_complete_requestChristoph Hellwig
Merge blk_mq_ipi_complete_request and blk_mq_stat_add into their only caller. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-20blk-mq: remove the error argument to blk_mq_complete_requestChristoph Hellwig
Now that all drivers that call blk_mq_complete_requests have a ->complete callback we can remove the direct call to blk_mq_end_request, as well as the error argument to blk_mq_complete_request. Signed-off-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-19block: Export blk_init_request_from_bio()Bart Van Assche
Export this function such that it becomes available to block drivers. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matias Bjørling <m@bjorling.me> Cc: Adam Manzanares <adam.manzanares@wdc.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-14blk-mq-sched: make completed_request() callback more usefulOmar Sandoval
Currently, this callback is called right after put_request() and has no distinguishable purpose. Instead, let's call it before put_request() as soon as I/O has completed on the request, before we account it in blk-stat. With this, Kyber can enable stats when it sees a latency outlier and make sure the outlier gets accounted. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-14blk-mq: export helpersOmar Sandoval
blk_mq_finish_request() is required for schedulers that define their own put_request(). blk_mq_run_hw_queue() is required for schedulers that hold back requests to be run later. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: Clarify comments in blk_mq_dispatch_rq_list()Bart Van Assche
The blk_mq_dispatch_rq_list() implementation got modified several times but the comments in that function were not updated every time. Since it is nontrivial what is going on, update the comments in blk_mq_dispatch_rq_list(). Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Omar Sandoval <osandov@fb.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hannes Reinecke <hare@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_listBart Van Assche
Since the next patch in this series will use RCU to iterate over tag_list, make this safe. Add lockdep_assert_held() statements in functions that iterate over tag_list to make clear that using list_for_each_entry() instead of list_for_each_entry_rcu() is fine in these functions. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: use true instead of 1 for blk_mq_queue_data.lastOmar Sandoval
Trivial cleanup. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: make driver tag failure path easier to followOmar Sandoval
Minor cleanup that makes it easier to figure out what's going on in the driver tag allocation failure path of blk_mq_dispatch_rq_list(). Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07Merge branch 'for-linus' into for-4.12/blockJens Axboe
We've added a considerable amount of fixes for stalls and issues with the blk-mq scheduling in the 4.11 series since forking off the for-4.12/block branch. We need to do improvements on top of that for 4.12, so pull in the previous fixes to make our lives easier going forward. Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: Restart a single queue if tag sets are sharedBart Van Assche
To improve scalability, if hardware queues are shared, restart a single hardware queue in round-robin fashion. Rename blk_mq_sched_restart_queues() to reflect the new semantics. Remove blk_mq_sched_mark_restart_queue() because this function has no callers. Remove flag QUEUE_FLAG_RESTART because this patch removes the code that uses this flag. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hannes Reinecke <hare@suse.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: Introduce blk_mq_delay_run_hw_queue()Bart Van Assche
Introduce a function that runs a hardware queue unconditionally after a delay. Note: there is already a function that stops and restarts a hardware queue after a delay, namely blk_mq_delay_queue(). This function will be used in the next patch in this series. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Hannes Reinecke <hare@suse.de> Cc: Long Li <longli@microsoft.com> Cc: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: remap queues when adding/removing hardware queuesOmar Sandoval
blk_mq_update_nr_hw_queues() used to remap hardware queues, which is the behavior that drivers expect. However, commit 4e68a011428a changed blk_mq_queue_reinit() to not remap queues for the case of CPU hotplugging, inadvertently making blk_mq_update_nr_hw_queues() not remap queues as well. This breaks, for example, NBD's multi-connection mode, leaving the added hardware queues unused. Fix it by making blk_mq_update_nr_hw_queues() explicitly remap the queues. Fixes: 4e68a011428a ("blk-mq: don't redistribute hardware queues on a CPU hotplug event") Reviewed-by: Keith Busch <keith.busch@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq-sched: fix crash in switch error pathOmar Sandoval
In elevator_switch(), if blk_mq_init_sched() fails, we attempt to fall back to the original scheduler. However, at this point, we've already torn down the original scheduler's tags, so this causes a crash. Doing the fallback like the legacy elevator path is much harder for mq, so fix it by just falling back to none, instead. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq-sched: set up scheduler tags when bringing up new queuesOmar Sandoval
If a new hardware queue is added at runtime, we don't allocate scheduler tags for it, leading to a crash. This hooks up the scheduler framework to blk_mq_{init,exit}_hctx() to make sure everything gets properly initialized/freed. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-07blk-mq: use the right hctx when getting a driver tag failsOmar Sandoval
While dispatching requests, if we fail to get a driver tag, we mark the hardware queue as waiting for a tag and put the requests on a hctx->dispatch list to be run later when a driver tag is freed. However, blk_mq_dispatch_rq_list() may dispatch requests from multiple hardware queues if using a single-queue scheduler with a multiqueue device. If blk_mq_get_driver_tag() fails, it doesn't update the hardware queue we are processing. This means we end up using the hardware queue of the previous request, which may or may not be the same as that of the current request. If it isn't, the wrong hardware queue will end up waiting for a tag, and the requests will be on the wrong dispatch list, leading to a hang. The fix is twofold: 1. Make sure we save which hardware queue we were trying to get a request for in blk_mq_get_driver_tag() regardless of whether it succeeds or not. 2. Make blk_mq_dispatch_rq_list() take a request_queue instead of a blk_mq_hw_queue to make it clear that it must handle multiple hardware queues, since I've already messed this up on a couple of occasions. This didn't appear in testing with nvme and mq-deadline because nvme has more driver tags than the default number of scheduler tags. However, with the blk_mq_update_nr_hw_queues() fix, it showed up with nbd. Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-05blk-mq: Remove blk_mq_queue_data.listBart Van Assche
The block layer core sets blk_mq_queue_data.list but no block drivers read that member. Hence remove it and also the code that is used to set this member. Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-30blk-mq: fix schedule-under-preempt for blocking driversJens Axboe
Commit a4d907b6a33b unified the single and multi queue request handlers, but in the process, it also screwed up the locking balance and calls blk_mq_try_issue_directly() with the ctx preempt lock held. This is a problem for drivers that have set BLK_MQ_F_BLOCKING, since now they can't reliably sleep. While in there, protect against similar issues in the future, by adding a might_sleep() trigger in the BLOCKING path for direct issue or queue run. Reported-by: Josef Bacik <josef@toxicpanda.com> Tested-by: Josef Bacik <josef@toxicpanda.com> Fixes: a4d907b6a33b ("blk-mq: streamline blk_mq_make_request") Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-30block: do not put mq context in blk_mq_alloc_request_hctxMinchan Kim
In blk_mq_alloc_request_hctx, blk_mq_sched_get_request doesn't get sw context so we don't need to put the context with blk_mq_put_ctx. Unless, we will see preempt counter underflow. Cc: Omar Sandoval <osandov@fb.com> Signed-off-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-30block: do not put mq context in blk_mq_alloc_request_hctxMinchan Kim
In blk_mq_alloc_request_hctx, blk_mq_sched_get_request doesn't get sw context so we don't need to put the context with blk_mq_put_ctx. Unless, we will see preempt counter underflow. Cc: Omar Sandoval <osandov@fb.com> Signed-off-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29blk-mq: include errors in did_work calculationJens Axboe
Currently we return true in blk_mq_dispatch_rq_list() if we queued IO successfully, but we really want to return whether or not the we made progress. Progress includes if we got an error return. If we don't, this can lead to a hang in blk_mq_sched_dispatch_requests() when a driver is draining IO by returning BLK_MQ_QUEUE_ERROR instead of manually ending the IO in error and return BLK_MQ_QUEUE_OK. Tested-by: Josef Bacik <josef@toxicpanda.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29block-mq: don't re-queue if we get a queue errorJosef Bacik
When try to issue a request directly and we fail we will requeue the request, but call blk_mq_end_request() as well. This leads to the completed request being on a queuelist and getting ended twice, which causes list corruption in schedulers and other shenanigans. Signed-off-by: Josef Bacik <jbacik@fb.com> Reviewed-by: Ming Lei <tom.leiming@gmail.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29blk-mq: fix a typo and a spelling mistakeJens Axboe
Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29blk-mq: fix leak of q->statsOmar Sandoval
blk_alloc_queue_node() already allocates q->stats, so blk_mq_init_allocated_queue() is overwriting it with a new allocation. Fixes: a83b576c9c25 ("block: fix stacked driver stats init and free") Reviewed-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Omar Sandoval <osandov@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29block: rename blk_mq_freeze_queue_start()Ming Lei
As the .q_usage_counter is used by both legacy and mq path, we need to block new I/O if queue becomes dead in blk_queue_enter(). So rename it and we can use this function in both paths. Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Ming Lei <tom.leiming@gmail.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29blk-mq: comment on races related with timeout handlerMing Lei
This patch adds comment on two races related with timeout handler: - requeue from queue busy vs. timeout - rq free & reallocation vs. timeout Both the races themselves and current solution aren't explicit enough, so add comments on them. Cc: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Ming Lei <tom.leiming@gmail.com> Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-03-29blk-mq: don't complete un-started request in timeout handlerMing Lei
When iterating busy requests in timeout handler, if the STARTED flag of one request isn't set, that means the request is being processed in block layer or driver, and isn't submitted to hardware yet. In current implementation of blk_mq_check_expired(), if the request queue becomes dying, un-started requests are handled as being completed/freed immediately. This way is wrong, and can cause rq corruption or double allocation[1][2], when doing I/O and removing&resetting NVMe device at the sametime. This patch fixes several issues reported by Yi Zhang. [1]. oops log 1 [ 581.789754] ------------[ cut here ]------------ [ 581.789758] kernel BUG at block/blk-mq.c:374! [ 581.789760] invalid opcode: 0000 [#1] SMP [ 581.789761] Modules linked in: vfat fat ipmi_ssif intel_rapl sb_edac edac_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm nvme irqbypass crct10dif_pclmul nvme_core crc32_pclmul ghash_clmulni_intel intel_cstate ipmi_si mei_me ipmi_devintf intel_uncore sg ipmi_msghandler intel_rapl_perf iTCO_wdt mei iTCO_vendor_support mxm_wmi lpc_ich dcdbas shpchp pcspkr acpi_power_meter wmi nfsd auth_rpcgss nfs_acl lockd dm_multipath grace sunrpc ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm ahci libahci crc32c_intel tg3 libata megaraid_sas i2c_core ptp fjes pps_core dm_mirror dm_region_hash dm_log dm_mod [ 581.789796] CPU: 1 PID: 1617 Comm: kworker/1:1H Not tainted 4.10.0.bz1420297+ #4 [ 581.789797] Hardware name: Dell Inc. PowerEdge R730xd/072T6D, BIOS 2.2.5 09/06/2016 [ 581.789804] Workqueue: kblockd blk_mq_timeout_work [ 581.789806] task: ffff8804721c8000 task.stack: ffffc90006ee4000 [ 581.789809] RIP: 0010:blk_mq_end_request+0x58/0x70 [ 581.789810] RSP: 0018:ffffc90006ee7d50 EFLAGS: 00010202 [ 581.789811] RAX: 0000000000000001 RBX: ffff8802e4195340 RCX: ffff88028e2f4b88 [ 581.789812] RDX: 0000000000001000 RSI: 0000000000001000 RDI: 0000000000000000 [ 581.789813] RBP: ffffc90006ee7d60 R08: 0000000000000003 R09: ffff88028e2f4b00 [ 581.789814] R10: 0000000000001000 R11: 0000000000000001 R12: 00000000fffffffb [ 581.789815] R13: ffff88042abe5780 R14: 000000000000002d R15: ffff88046fbdff80 [ 581.789817] FS: 0000000000000000(0000) GS:ffff88047fc00000(0000) knlGS:0000000000000000 [ 581.789818] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 581.789819] CR2: 00007f64f403a008 CR3: 000000014d078000 CR4: 00000000001406e0 [ 581.789820] Call Trace: [ 581.789825] blk_mq_check_expired+0x76/0x80 [ 581.789828] bt_iter+0x45/0x50 [ 581.789830] blk_mq_queue_tag_busy_iter+0xdd/0x1f0 [ 581.789832] ? blk_mq_rq_timed_out+0x70/0x70 [ 581.789833] ? blk_mq_rq_timed_out+0x70/0x70 [ 581.789840] ? __switch_to+0x140/0x450 [ 581.789841] blk_mq_timeout_work+0x88/0x170 [ 581.789845] process_one_work+0x165/0x410 [ 581.789847] worker_thread+0x137/0x4c0 [ 581.789851] kthread+0x101/0x140 [ 581.789853] ? rescuer_thread+0x3b0/0x3b0 [ 581.789855] ? kthread_park+0x90/0x90 [ 581.789860] ret_from_fork+0x2c/0x40 [ 581.789861] Code: 48 85 c0 74 0d 44 89 e6 48 89 df ff d0 5b 41 5c 5d c3 48 8b bb 70 01 00 00 48 85 ff 75 0f 48 89 df e8 7d f0 ff ff 5b 41 5c 5d c3 <0f> 0b e8 71 f0 ff ff 90 eb e9 0f 1f 40 00 66 2e 0f 1f 84 00 00 [ 581.789882] RIP: blk_mq_end_request+0x58/0x70 RSP: ffffc90006ee7d50 [ 581.789889] ---[ end trace bcaf03d9a14a0a70 ]--- [2]. oops log2 [ 6984.857362] BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 [ 6984.857372] IP: nvme_queue_rq+0x6e6/0x8cd [nvme] [ 6984.857373] PGD 0 [ 6984.857374] [ 6984.857376] Oops: 0000 [#1] SMP [ 6984.857379] Modules linked in: ipmi_ssif vfat fat intel_rapl sb_edac edac_core x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ipmi_si iTCO_wdt iTCO_vendor_support mxm_wmi ipmi_devintf intel_cstate sg dcdbas intel_uncore mei_me intel_rapl_perf mei pcspkr lpc_ich ipmi_msghandler shpchp acpi_power_meter wmi nfsd auth_rpcgss dm_multipath nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect crc32c_intel sysimgblt fb_sys_fops ttm nvme drm nvme_core ahci libahci i2c_core tg3 libata ptp megaraid_sas pps_core fjes dm_mirror dm_region_hash dm_log dm_mod [ 6984.857416] CPU: 7 PID: 1635 Comm: kworker/7:1H Not tainted 4.10.0-2.el7.bz1420297.x86_64 #1 [ 6984.857417] Hardware name: Dell Inc. PowerEdge R730xd/072T6D, BIOS 2.2.5 09/06/2016 [ 6984.857427] Workqueue: kblockd blk_mq_run_work_fn [ 6984.857429] task: ffff880476e3da00 task.stack: ffffc90002e90000 [ 6984.857432] RIP: 0010:nvme_queue_rq+0x6e6/0x8cd [nvme] [ 6984.857433] RSP: 0018:ffffc90002e93c50 EFLAGS: 00010246 [ 6984.857434] RAX: 0000000000000000 RBX: ffff880275646600 RCX: 0000000000001000 [ 6984.857435] RDX: 0000000000000fff RSI: 00000002fba2a000 RDI: ffff8804734e6950 [ 6984.857436] RBP: ffffc90002e93d30 R08: 0000000000002000 R09: 0000000000001000 [ 6984.857437] R10: 0000000000001000 R11: 0000000000000000 R12: ffff8804741d8000 [ 6984.857438] R13: 0000000000000040 R14: ffff880475649f80 R15: ffff8804734e6780 [ 6984.857439] FS: 0000000000000000(0000) GS:ffff88047fcc0000(0000) knlGS:0000000000000000 [ 6984.857440] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 6984.857442] CR2: 0000000000000010 CR3: 0000000001c09000 CR4: 00000000001406e0 [ 6984.857443] Call Trace: [ 6984.857451] ? mempool_free+0x2b/0x80 [ 6984.857455] ? bio_free+0x4e/0x60 [ 6984.857459] blk_mq_dispatch_rq_list+0xf5/0x230 [ 6984.857462] blk_mq_process_rq_list+0x133/0x170 [ 6984.857465] __blk_mq_run_hw_queue+0x8c/0xa0 [ 6984.857467] blk_mq_run_work_fn+0x12/0x20 [ 6984.857473] process_one_work+0x165/0x410 [ 6984.857475] worker_thread+0x137/0x4c0 [ 6984.857478] kthread+0x101/0x140 [ 6984.857480] ? rescuer_thread+0x3b0/0x3b0 [ 6984.857481] ? kthread_park+0x90/0x90 [ 6984.857489] ret_from_fork+0x2c/0x40 [ 6984.857490] Code: 8b bd 70 ff ff ff 89 95 50 ff ff ff 89 8d 58 ff ff ff 44 89 95 60 ff ff ff e8 b7 dd 12 e1 8b 95 50 ff ff ff 48 89 85 68 ff ff ff <4c> 8b 48 10 44 8b 58 18 8b 8d 58 ff ff ff 44 8b 95 60 ff ff ff [ 6984.857511] RIP: nvme_queue_rq+0x6e6/0x8cd [nvme] RSP: ffffc90002e93c50 [ 6984.857512] CR2: 0000000000000010 [ 6984.895359] ---[ end trace 2d7ceb528432bf83 ]--- Cc: stable@vger.kernel.org Reported-by: Yi Zhang <yizhan@redhat.com> Tested-by: Yi Zhang <yizhan@redhat.com> Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> Reviewed-by: Hannes Reinecke <hare@suse.com> Signed-off-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-05 06:52:03 +0000