From 36e1f3d107867b25c616c2fd294f5a1c9d4e5d09 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Tue, 6 Dec 2016 13:31:44 -0200 Subject: [PATCH] blk-mq: Avoid memory reclaim when remapping queues 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 --- block/blk-mq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index d79fdc11b1ee..7ad7c11fe01d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1605,7 +1605,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, INIT_LIST_HEAD(&tags->page_list); tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *), - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, set->numa_node); if (!tags->rqs) { blk_mq_free_tags(tags); @@ -1631,7 +1631,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, do { page = alloc_pages_node(set->numa_node, - GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, + GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) break; @@ -1652,7 +1652,7 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set, * Allow kmemleak to scan these pages as they contain pointers * to additional allocations like via ops->init_request(). */ - kmemleak_alloc(p, order_to_size(this_order), 1, GFP_KERNEL); + kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO); entries_per_page = order_to_size(this_order) / rq_size; to_do = min(entries_per_page, set->queue_depth - i); left -= to_do * rq_size; -- 2.39.5