From 7afafc8a44bf0ab841b17d450b02aedb3a138985 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 16 Aug 2016 10:59:35 +0300 Subject: block: Fix secure erase Commit 288dab8a35a0 ("block: add a separate operation type for secure erase") split REQ_OP_SECURE_ERASE from REQ_OP_DISCARD without considering all the places REQ_OP_DISCARD was being used to mean either. Fix those. Signed-off-by: Adrian Hunter Fixes: 288dab8a35a0 ("block: add a separate operation type for secure erase") Signed-off-by: Jens Axboe --- block/bio.c | 21 +++++++++++---------- block/blk-merge.c | 33 +++++++++++++++++++-------------- block/elevator.c | 2 +- 3 files changed, 31 insertions(+), 25 deletions(-) (limited to 'block') diff --git a/block/bio.c b/block/bio.c index f394775..aa73540 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a..72627e3 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -172,12 +172,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +219,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +391,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +401,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/elevator.c b/block/elevator.c index 7096c22..f7d973a 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; -- cgit v1.1 From 1b856086813be9371929b6cc62045f9fd470f5a0 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 16 Aug 2016 16:48:36 -0700 Subject: block: Fix race triggered by blk_set_queue_dying() blk_set_queue_dying() can be called while another thread is submitting I/O or changing queue flags, e.g. through dm_stop_queue(). Hence protect the QUEUE_FLAG_DYING flag change with locking. Signed-off-by: Bart Van Assche Cc: Christoph Hellwig Cc: Mike Snitzer Cc: stable Signed-off-by: Jens Axboe --- block/blk-core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 999442e..36c7ac3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end); void blk_set_queue_dying(struct request_queue *q) { - queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); if (q->mq_ops) blk_mq_wake_waiters(q); -- cgit v1.1 From 4d70dca4eadf2f95abe389116ac02b8439c2d16c Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 23 Aug 2016 21:49:45 +0800 Subject: block: make sure a big bio is split into at most 256 bvecs After arbitrary bio size was introduced, the incoming bio may be very big. We have to split the bio into small bios so that each holds at most BIO_MAX_PAGES bvecs for safety reason, such as bio_clone(). This patch fixes the following kernel crash: > [ 172.660142] BUG: unable to handle kernel NULL pointer dereference at 0000000000000028 > [ 172.660229] IP: [] bio_trim+0xf/0x2a > [ 172.660289] PGD 7faf3e067 PUD 7f9279067 PMD 0 > [ 172.660399] Oops: 0000 [#1] SMP > [...] > [ 172.664780] Call Trace: > [ 172.664813] [] ? raid1_make_request+0x2e8/0xad7 [raid1] > [ 172.664846] [] ? blk_queue_split+0x377/0x3d4 > [ 172.664880] [] ? md_make_request+0xf6/0x1e9 [md_mod] > [ 172.664912] [] ? generic_make_request+0xb5/0x155 > [ 172.664947] [] ? prio_io+0x85/0x95 [bcache] > [ 172.664981] [] ? register_cache_set+0x355/0x8d0 [bcache] > [ 172.665016] [] ? register_bcache+0x1006/0x1174 [bcache] The issue can be reproduced by the following steps: - create one raid1 over two virtio-blk - build bcache device over the above raid1 and another cache device and bucket size is set as 2Mbytes - set cache mode as writeback - run random write over ext4 on the bcache device Fixes: 54efd50(block: make generic_make_request handle arbitrarily sized bios) Reported-by: Sebastian Roesner Reported-by: Eric Wheeler Cc: stable@vger.kernel.org (4.3+) Cc: Shaohua Li Acked-by: Kent Overstreet Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-merge.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'block') diff --git a/block/blk-merge.c b/block/blk-merge.c index 72627e3..2642e5f 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,9 +94,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is the + * bio_clone() in bio bounce. + * + * If bio is splitted by this reason, we should have + * allowed to continue bios merging, but don't do + * that now for making the change simple. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs++ >= BIO_MAX_PAGES) + goto split; + + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ -- cgit v1.1 From e57690fe009b2ab0cee8a57f53be634540e49c9d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Aug 2016 15:34:35 -0600 Subject: blk-mq: don't overwrite rq->mq_ctx We do this in a few places, if the CPU is offline. This isn't allowed, though, since on multi queue hardware, we can't just move a request from one software queue to another, if they map to different hardware queues. The request and tag isn't valid on another hardware queue. This can happen if plugging races with CPU offlining. But it does no harm, since it can only happen in the window where we are currently busy freezing the queue and flushing IO, in preparation for redoing the software <-> hardware queue mappings. Signed-off-by: Jens Axboe --- block/blk-mq.c | 55 ++++++++++++++++--------------------------------------- 1 file changed, 16 insertions(+), 39 deletions(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index e931a0e..729169d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1036,10 +1036,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) EXPORT_SYMBOL(blk_mq_delay_queue); static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, struct request *rq, bool at_head) { + struct blk_mq_ctx *ctx = rq->mq_ctx; + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1053,20 +1054,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, at_head); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, - bool async) + bool async) { + struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - if (!cpu_online(ctx->cpu)) - rq->mq_ctx = ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1076,8 +1073,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, if (run_queue) blk_mq_run_hw_queue(hctx, async); - - blk_mq_put_ctx(current_ctx); } static void blk_mq_insert_requests(struct request_queue *q, @@ -1088,14 +1083,9 @@ static void blk_mq_insert_requests(struct request_queue *q, { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *current_ctx; trace_block_unplug(q, depth, !from_schedule); - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) - ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); /* @@ -1107,15 +1097,14 @@ static void blk_mq_insert_requests(struct request_queue *q, struct request *rq; rq = list_first_entry(list, struct request, queuelist); + BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); - rq->mq_ctx = ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, false); + __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); - blk_mq_put_ctx(current_ctx); } static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1630,16 +1619,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node) return 0; } +/* + * 'cpu' is going away. splice any existing rq_list entries from this + * software queue to the hw queue dispatch list, and ensure that it + * gets run. + */ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) { - struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); - /* - * Move ctx entries to new CPU, if this one is going away. - */ - ctx = __blk_mq_get_ctx(q, cpu); + ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { @@ -1651,24 +1641,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) if (list_empty(&tmp)) return NOTIFY_OK; - ctx = blk_mq_get_ctx(q); - spin_lock(&ctx->lock); - - while (!list_empty(&tmp)) { - struct request *rq; - - rq = list_first_entry(&tmp, struct request, queuelist); - rq->mq_ctx = ctx; - list_move_tail(&rq->queuelist, &ctx->rq_list); - } - - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_hctx_mark_pending(hctx, ctx); - - spin_unlock(&ctx->lock); + spin_lock(&hctx->lock); + list_splice_tail_init(&tmp, &hctx->dispatch); + spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); - blk_mq_put_ctx(ctx); return NOTIFY_OK; } -- cgit v1.1 From 0e87e58bf60edb6bb28e493c7a143f41b091a5e5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Aug 2016 15:38:01 -0600 Subject: blk-mq: improve warning for running a queue on the wrong CPU __blk_mq_run_hw_queue() currently warns if we are running the queue on a CPU that isn't set in its mask. However, this can happen if a CPU is being offlined, and the workqueue handling will place the work on CPU0 instead. Improve the warning so that it only triggers if the batch cpu in the hardware queue is currently online. If it triggers for that case, then it's indicative of a flow problem in blk-mq, so we want to retain it for that case. Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index 729169d..13f5a6c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -793,11 +793,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) struct list_head *dptr; int queued; - WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)); - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; + WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && + cpu_online(hctx->next_cpu)); + hctx->run++; /* -- cgit v1.1