user/sven/linux.git/block, branch v4.4.63

blk-mq: Avoid memory reclaim when remapping queues

2017-04-18T05:14:37Z

commit 36e1f3d107867b25c616c2fd294f5a1c9d4e5d09 upstream. While stressing memory and IO at the same time we changed SMT settings, we were able to consistently trigger deadlocks in the mm system, which froze the entire machine. I think that under memory stress conditions, the large allocations performed by blk_mq_init_rq_map may trigger a reclaim, which stalls waiting on the block layer remmaping completion, thus deadlocking the system. The trace below was collected after the machine stalled, waiting for the hotplug event completion. The simplest fix for this is to make allocations in this path non-reclaimable, with GFP_NOIO. With this patch, We couldn't hit the issue anymore. This should apply on top of Jens's for-next branch cleanly. Changes since v1: - Use GFP_NOIO instead of GFP_NOWAIT. Call Trace: [c000000f0160aaf0] [c000000f0160ab50] 0xc000000f0160ab50 (unreliable) [c000000f0160acc0] [c000000000016624] __switch_to+0x2e4/0x430 [c000000f0160ad20] [c000000000b1a880] __schedule+0x310/0x9b0 [c000000f0160ae00] [c000000000b1af68] schedule+0x48/0xc0 [c000000f0160ae30] [c000000000b1b4b0] schedule_preempt_disabled+0x20/0x30 [c000000f0160ae50] [c000000000b1d4fc] __mutex_lock_slowpath+0xec/0x1f0 [c000000f0160aed0] [c000000000b1d678] mutex_lock+0x78/0xa0 [c000000f0160af00] [d000000019413cac] xfs_reclaim_inodes_ag+0x33c/0x380 [xfs] [c000000f0160b0b0] [d000000019415164] xfs_reclaim_inodes_nr+0x54/0x70 [xfs] [c000000f0160b0f0] [d0000000194297f8] xfs_fs_free_cached_objects+0x38/0x60 [xfs] [c000000f0160b120] [c0000000003172c8] super_cache_scan+0x1f8/0x210 [c000000f0160b190] [c00000000026301c] shrink_slab.part.13+0x21c/0x4c0 [c000000f0160b2d0] [c000000000268088] shrink_zone+0x2d8/0x3c0 [c000000f0160b380] [c00000000026834c] do_try_to_free_pages+0x1dc/0x520 [c000000f0160b450] [c00000000026876c] try_to_free_pages+0xdc/0x250 [c000000f0160b4e0] [c000000000251978] __alloc_pages_nodemask+0x868/0x10d0 [c000000f0160b6f0] [c000000000567030] blk_mq_init_rq_map+0x160/0x380 [c000000f0160b7a0] [c00000000056758c] blk_mq_map_swqueue+0x33c/0x360 [c000000f0160b820] [c000000000567904] blk_mq_queue_reinit+0x64/0xb0 [c000000f0160b850] [c00000000056a16c] blk_mq_queue_reinit_notify+0x19c/0x250 [c000000f0160b8a0] [c0000000000f5d38] notifier_call_chain+0x98/0x100 [c000000f0160b8f0] [c0000000000c5fb0] __cpu_notify+0x70/0xe0 [c000000f0160b930] [c0000000000c63c4] notify_prepare+0x44/0xb0 [c000000f0160b9b0] [c0000000000c52f4] cpuhp_invoke_callback+0x84/0x250 [c000000f0160ba10] [c0000000000c570c] cpuhp_up_callbacks+0x5c/0x120 [c000000f0160ba60] [c0000000000c7cb8] _cpu_up+0xf8/0x1d0 [c000000f0160bac0] [c0000000000c7eb0] do_cpu_up+0x120/0x150 [c000000f0160bb40] [c0000000006fe024] cpu_subsys_online+0x64/0xe0 [c000000f0160bb90] [c0000000006f5124] device_online+0xb4/0x120 [c000000f0160bbd0] [c0000000006f5244] online_store+0xb4/0xc0 [c000000f0160bc20] [c0000000006f0a68] dev_attr_store+0x68/0xa0 [c000000f0160bc60] [c0000000003ccc30] sysfs_kf_write+0x80/0xb0 [c000000f0160bca0] [c0000000003cbabc] kernfs_fop_write+0x17c/0x250 [c000000f0160bcf0] [c00000000030fe6c] __vfs_write+0x6c/0x1e0 [c000000f0160bd90] [c000000000311490] vfs_write+0xd0/0x270 [c000000f0160bde0] [c0000000003131fc] SyS_write+0x6c/0x110 [c000000f0160be30] [c000000000009204] system_call+0x38/0xec Signed-off-by: Gabriel Krisman Bertazi Cc: Brian King Cc: Douglas Miller Cc: linux-block@vger.kernel.org Cc: linux-scsi@vger.kernel.org Signed-off-by: Jens Axboe Signed-off-by: Sumit Semwal Signed-off-by: Greg Kroah-Hartman

blk: Ensure users for current->bio_list can see the full list.

2017-04-08T07:53:32Z

commit f5fe1b51905df7cfe4fdfd85c5fb7bc5b71a094f upstream. Commit 79bd99596b73 ("blk: improve order of bio handling in generic_make_request()") changed current->bio_list so that it did not contain *all* of the queued bios, but only those submitted by the currently running make_request_fn. There are two places which walk the list and requeue selected bios, and others that check if the list is empty. These are no longer correct. So redefine current->bio_list to point to an array of two lists, which contain all queued bios, and adjust various code to test or walk both lists. Signed-off-by: NeilBrown Fixes: 79bd99596b73 ("blk: improve order of bio handling in generic_make_request()") Signed-off-by: Jens Axboe [jwang: backport to 4.4] Signed-off-by: Jack Wang Signed-off-by: Greg Kroah-Hartman [bwh: Restore changes in device-mapper from upstream version] Signed-off-by: Ben Hutchings

blk: improve order of bio handling in generic_make_request()

2017-04-08T07:53:32Z

commit 79bd99596b7305ab08109a8bf44a6a4511dbf1cd upstream. To avoid recursion on the kernel stack when stacked block devices are in use, generic_make_request() will, when called recursively, queue new requests for later handling. They will be handled when the make_request_fn for the current bio completes. If any bios are submitted by a make_request_fn, these will ultimately be handled seqeuntially. If the handling of one of those generates further requests, they will be added to the end of the queue. This strict first-in-first-out behaviour can lead to deadlocks in various ways, normally because a request might need to wait for a previous request to the same device to complete. This can happen when they share a mempool, and can happen due to interdependencies particular to the device. Both md and dm have examples where this happens. These deadlocks can be erradicated by more selective ordering of bios. Specifically by handling them in depth-first order. That is: when the handling of one bio generates one or more further bios, they are handled immediately after the parent, before any siblings of the parent. That way, when generic_make_request() calls make_request_fn for some particular device, we can be certain that all previously submited requests for that device have been completely handled and are not waiting for anything in the queue of requests maintained in generic_make_request(). An easy way to achieve this would be to use a last-in-first-out stack instead of a queue. However this will change the order of consecutive bios submitted by a make_request_fn, which could have unexpected consequences. Instead we take a slightly more complex approach. A fresh queue is created for each call to a make_request_fn. After it completes, any bios for a different device are placed on the front of the main queue, followed by any bios for the same device, followed by all bios that were already on the queue before the make_request_fn was called. This provides the depth-first approach without reordering bios on the same level. This, by itself, it not enough to remove all deadlocks. It just makes it possible for drivers to take the extra step required themselves. To avoid deadlocks, drivers must never risk waiting for a request after submitting one to generic_make_request. This includes never allocing from a mempool twice in the one call to a make_request_fn. A common pattern in drivers is to call bio_split() in a loop, handling the first part and then looping around to possibly split the next part. Instead, a driver that finds it needs to split a bio should queue (with generic_make_request) the second part, handle the first part, and then return. The new code in generic_make_request will ensure the requests to underlying bios are processed first, then the second bio that was split off. If it splits again, the same process happens. In each case one bio will be completely handled before the next one is attempted. With this is place, it should be possible to disable the punt_bios_to_recover() recovery thread for many block devices, and eventually it may be possible to remove it completely. Ref: http://www.spinics.net/lists/raid/msg54680.html Tested-by: Jinpu Wang Inspired-by: Lars Ellenberg Signed-off-by: NeilBrown Signed-off-by: Jens Axboe [jwang: backport to 4.4] Signed-off-by: Jack Wang Signed-off-by: Greg Kroah-Hartman

block: allow WRITE_SAME commands with the SG_IO ioctl

2017-03-30T07:35:20Z

From: Mauricio Faria de Oliveira [ Upstream commit 25cdb64510644f3e854d502d69c73f21c6df88a9 ] The WRITE_SAME commands are not present in the blk_default_cmd_filter write_ok list, and thus are failed with -EPERM when the SG_IO ioctl() is executed without CAP_SYS_RAWIO capability (e.g., unprivileged users). [ sg_io() -> blk_fill_sghdr_rq() > blk_verify_command() -> -EPERM ] The problem can be reproduced with the sg_write_same command # sg_write_same --num 1 --xferlen 512 /dev/sda # # capsh --drop=cap_sys_rawio -- -c \ 'sg_write_same --num 1 --xferlen 512 /dev/sda' Write same: pass through os error: Operation not permitted # For comparison, the WRITE_VERIFY command does not observe this problem, since it is in that list: # capsh --drop=cap_sys_rawio -- -c \ 'sg_write_verify --num 1 --ilen 512 --lba 0 /dev/sda' # So, this patch adds the WRITE_SAME commands to the list, in order for the SG_IO ioctl to finish successfully: # capsh --drop=cap_sys_rawio -- -c \ 'sg_write_same --num 1 --xferlen 512 /dev/sda' # That case happens to be exercised by QEMU KVM guests with 'scsi-block' devices (qemu "-device scsi-block" [1], libvirt "" [2]), which employs the SG_IO ioctl() and runs as an unprivileged user (libvirt-qemu). In that scenario, when a filesystem (e.g., ext4) performs its zero-out calls, which are translated to write-same calls in the guest kernel, and then into SG_IO ioctls to the host kernel, SCSI I/O errors may be observed in the guest: [...] sd 0:0:0:0: [sda] tag#0 FAILED Result: hostbyte=DID_OK driverbyte=DRIVER_SENSE [...] sd 0:0:0:0: [sda] tag#0 Sense Key : Aborted Command [current] [...] sd 0:0:0:0: [sda] tag#0 Add. Sense: I/O process terminated [...] sd 0:0:0:0: [sda] tag#0 CDB: Write Same(10) 41 00 01 04 e0 78 00 00 08 00 [...] blk_update_request: I/O error, dev sda, sector 17096824 Links: [1] http://git.qemu.org/?p=qemu.git;a=commit;h=336a6915bc7089fb20fea4ba99972ad9a97c5f52 [2] https://libvirt.org/formatdomain.html#elementsDisks (see 'disk' -> 'device') Signed-off-by: Mauricio Faria de Oliveira Signed-off-by: Brahadambal Srinivasan Reported-by: Manjunatha H R Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sumit Semwal Signed-off-by: Greg Kroah-Hartman

blk-mq: really fix plug list flushing for nomerge queues

2017-02-26T10:07:49Z

commit 87c279e613f848c691111b29d49de8df3f4f56da upstream. Commit 0809e3ac6231 ("block: fix plug list flushing for nomerge queues") updated blk_mq_make_request() to set request_count even when blk_queue_nomerges() returns true. However, blk_mq_make_request() only does limited plugging and doesn't use request_count; blk_sq_make_request() is the one that should have been fixed. Do that and get rid of the unnecessary work in the mq version. Fixes: 0809e3ac6231 ("block: fix plug list flushing for nomerge queues") Signed-off-by: Omar Sandoval Reviewed-by: Ming Lei Reviewed-by: Jeff Moyer Signed-off-by: Jens Axboe Cc: Sumit Semwal Signed-off-by: Greg Kroah-Hartman

blk-mq: Always schedule hctx->next_cpu

2017-01-19T19:17:22Z

commit c02ebfdddbafa9a6a0f52fbd715e6bfa229af9d3 upstream. Commit 0e87e58bf60e ("blk-mq: improve warning for running a queue on the wrong CPU") attempts to avoid triggering the WARN_ON in __blk_mq_run_hw_queue when the expected CPU is dead. Problem is, in the last batch execution before round robin, blk_mq_hctx_next_cpu can schedule a dead CPU and also update next_cpu to the next alive CPU in the mask, which will trigger the WARN_ON despite the previous workaround. The following patch fixes this scenario by always scheduling the value in hctx->next_cpu. This changes the moment when we round-robin the CPU running the hctx, but it really doesn't matter, since it still executes BLK_MQ_CPU_WORK_BATCH times in a row before switching to another CPU. Fixes: 0e87e58bf60e ("blk-mq: improve warning for running a queue on the wrong CPU") Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

block: cfq_cpd_alloc() should use @gfp

2017-01-19T19:17:22Z

commit ebc4ff661fbe76781c6b16dfb7b754a5d5073f8e upstream. cfq_cpd_alloc() which is the cpd_alloc_fn implementation for cfq was incorrectly hard coding GFP_KERNEL instead of using the mask specified through the @gfp parameter. This currently doesn't cause any actual issues because all current callers specify GFP_KERNEL. Fix it. Signed-off-by: Tejun Heo Reported-by: Dan Carpenter Fixes: e4a9bde9589f ("blkcg: replace blkcg_policy->cpd_size with ->cpd_alloc/free_fn() methods") Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

sg_write()/bsg_write() is not fit to be called under KERNEL_DS

2017-01-09T07:07:53Z

commit 128394eff343fc6d2f32172f03e24829539c5835 upstream. Both damn things interpret userland pointers embedded into the payload; worse, they are actually traversing those. Leaving aside the bad API design, this is very much _not_ safe to call with KERNEL_DS. Bail out early if that happens. Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman

blk-mq: Do not invoke .queue_rq() for a stopped queue

2017-01-06T10:16:14Z

commit bc27c01b5c46d3bfec42c96537c7a3fae0bb2cc4 upstream. The meaning of the BLK_MQ_S_STOPPED flag is "do not call .queue_rq()". Hence modify blk_mq_make_request() such that requests are queued instead of issued if a queue has been stopped. Reported-by: Ming Lei Signed-off-by: Bart Van Assche Reviewed-by: Christoph Hellwig Reviewed-by: Ming Lei Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman

Don't feed anything but regular iovec's to blk_rq_map_user_iov

2016-12-10T18:07:26Z

commit a0ac402cfcdc904f9772e1762b3fda112dcc56a0 upstream. In theory we could map other things, but there's a reason that function is called "user_iov". Using anything else (like splice can do) just confuses it. Reported-and-tested-by: Johannes Thumshirn Cc: Al Viro Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman