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/blk-merge.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) (limited to 'block/blk-merge.c') diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a9e91d..72627e3cf91e 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) -- cgit v1.2.3 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/blk-merge.c') diff --git a/block/blk-merge.c b/block/blk-merge.c index 72627e3cf91e..2642e5fc8b69 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,8 +94,30 @@ 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 v1.2.3