From 297ba57dcdec7ea37e702bcf1a577ac32a034e21 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 27 Jun 2018 12:55:18 -0700 Subject: block: Fix cloning of requests with a special payload This patch avoids that removing a path controlled by the dm-mpath driver while mkfs is running triggers the following kernel bug: kernel BUG at block/blk-core.c:3347! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 20 PID: 24369 Comm: mkfs.ext4 Not tainted 4.18.0-rc1-dbg+ #2 RIP: 0010:blk_end_request_all+0x68/0x70 Call Trace: dm_softirq_done+0x326/0x3d0 [dm_mod] blk_done_softirq+0x19b/0x1e0 __do_softirq+0x128/0x60d irq_exit+0x100/0x110 smp_call_function_single_interrupt+0x90/0x330 call_function_single_interrupt+0xf/0x20 Fixes: f9d03f96b988 ("block: improve handling of the magic discard payload") Reviewed-by: Ming Lei Reviewed-by: Christoph Hellwig Acked-by: Mike Snitzer Signed-off-by: Bart Van Assche Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index afd2596ea3d3..f84a9b7b6f5a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -3473,6 +3473,10 @@ static void __blk_rq_prep_clone(struct request *dst, struct request *src) dst->cpu = src->cpu; dst->__sector = blk_rq_pos(src); dst->__data_len = blk_rq_bytes(src); + if (src->rq_flags & RQF_SPECIAL_PAYLOAD) { + dst->rq_flags |= RQF_SPECIAL_PAYLOAD; + dst->special_vec = src->special_vec; + } dst->nr_phys_segments = src->nr_phys_segments; dst->ioprio = src->ioprio; dst->extra_len = src->extra_len; -- cgit v1.2.3-58-ga151 From 1f57f8d442f8017587eeebd8617913bfc3661d3d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Jun 2018 11:54:01 -0600 Subject: blk-mq: don't queue more if we get a busy return Some devices have different queue limits depending on the type of IO. A classic case is SATA NCQ, where some commands can queue, but others cannot. If we have NCQ commands inflight and encounter a non-queueable command, the driver returns busy. Currently we attempt to dispatch more from the scheduler, if we were able to queue some commands. But for the case where we ended up stopping due to BUSY, we should not attempt to retrieve more from the scheduler. If we do, we can get into a situation where we attempt to queue a non-queueable command, get BUSY, then successfully retrieve more commands from that scheduler and queue those. This can repeat forever, starving the non-queuable command indefinitely. Fix this by NOT attempting to pull more commands from the scheduler, if we get a BUSY return. This should also be more optimal in terms of letting requests stay in the scheduler for as long as possible, if we get a BUSY due to the regular out-of-tags condition. Reviewed-by: Omar Sandoval Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index b6888ff556cf..d394cdd8d8c6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1075,6 +1075,9 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx, #define BLK_MQ_RESOURCE_DELAY 3 /* ms units */ +/* + * Returns true if we did some work AND can potentially do more. + */ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, bool got_budget) { @@ -1205,8 +1208,17 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, blk_mq_run_hw_queue(hctx, true); else if (needs_restart && (ret == BLK_STS_RESOURCE)) blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY); + + return false; } + /* + * If the host/device is unable to accept more work, inform the + * caller of that. + */ + if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) + return false; + return (queued + errors) != 0; } -- cgit v1.2.3-58-ga151