aboutsummaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
authorMaurizio Lombardi <mlombard@redhat.com>2014-07-01 10:55:15 -0600
committerJens Axboe <axboe@fb.com>2014-07-01 10:55:15 -0600
commit254c4407cb84a6dec90336054615b0f0e996bb7c (patch)
tree28d91bb07d38f47d557833a2124a8e5f266bb5de /block
parent9b4231bf995996d6459c57959ead5a1829ff2c57 (diff)
bio: modify __bio_add_page() to accept pages that don't start a new segment
The original behaviour is to refuse to add a new page if the maximum number of segments has been reached, regardless of the fact the page we are going to add can be merged into the last segment or not. Unfortunately, when the system runs under heavy memory fragmentation conditions, a driver may try to add multiple pages to the last segment. The original code won't accept them and EBUSY will be reported to userspace. This patch modifies the function so it refuses to add a page only in case the latter starts a new segment and the maximum number of segments has already been reached. The bug can be easily reproduced with the st driver: 1) set CONFIG_SCSI_MPT2SAS_MAX_SGE or CONFIG_SCSI_MPT3SAS_MAX_SGE to 16 2) modprobe st buffer_kbs=1024 3) #dd if=/dev/zero of=/dev/st0 bs=1M count=10 dd: error writing `/dev/st0': Device or resource busy [ming.lei@canonical.com: update bi_iter.bi_size before recounting segments] Signed-off-by: Maurizio Lombardi <mlombard@redhat.com> Signed-off-by: Ming Lei <ming.lei@canonical.com> Tested-by: Dongsu Park <dongsu.park@profitbricks.com> Tested-by: Jet Chen <jet.chen@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'block')
-rw-r--r--block/bio.c52
1 files changed, 29 insertions, 23 deletions
diff --git a/block/bio.c b/block/bio.c
index 0ec61c9e536c..fb12df9af0fc 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -744,6 +744,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
}
}
+ bio->bi_iter.bi_size += len;
goto done;
}
@@ -760,29 +761,32 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
return 0;
/*
- * we might lose a segment or two here, but rather that than
- * make this too complex.
+ * setup the new entry, we might clear it again later if we
+ * cannot add the page
+ */
+ bvec = &bio->bi_io_vec[bio->bi_vcnt];
+ bvec->bv_page = page;
+ bvec->bv_len = len;
+ bvec->bv_offset = offset;
+ bio->bi_vcnt++;
+ bio->bi_phys_segments++;
+ bio->bi_iter.bi_size += len;
+
+ /*
+ * Perform a recount if the number of segments is greater
+ * than queue_max_segments(q).
*/
- while (bio->bi_phys_segments >= queue_max_segments(q)) {
+ while (bio->bi_phys_segments > queue_max_segments(q)) {
if (retried_segments)
- return 0;
+ goto failed;
retried_segments = 1;
blk_recount_segments(q, bio);
}
/*
- * setup the new entry, we might clear it again later if we
- * cannot add the page
- */
- bvec = &bio->bi_io_vec[bio->bi_vcnt];
- bvec->bv_page = page;
- bvec->bv_len = len;
- bvec->bv_offset = offset;
-
- /*
* if queue has other restrictions (eg varying max sector size
* depending on offset), it can specify a merge_bvec_fn in the
* queue to get further control
@@ -799,23 +803,25 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
* merge_bvec_fn() returns number of bytes it can accept
* at this offset
*/
- if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
- bvec->bv_page = NULL;
- bvec->bv_len = 0;
- bvec->bv_offset = 0;
- return 0;
- }
+ if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
+ goto failed;
}
/* If we may be able to merge these biovecs, force a recount */
- if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
+ if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
bio->bi_flags &= ~(1 << BIO_SEG_VALID);
- bio->bi_vcnt++;
- bio->bi_phys_segments++;
done:
- bio->bi_iter.bi_size += len;
return len;
+
+ failed:
+ bvec->bv_page = NULL;
+ bvec->bv_len = 0;
+ bvec->bv_offset = 0;
+ bio->bi_vcnt--;
+ bio->bi_iter.bi_size -= len;
+ blk_recount_segments(q, bio);
+ return 0;
}
/**