summaryrefslogtreecommitdiff
path: root/drivers/md/dm-crypt.c
diff options
context:
space:
mode:
authorMikulas Patocka <mpatocka@redhat.com>2015-02-13 08:24:41 -0500
committerMike Snitzer <snitzer@redhat.com>2015-02-16 11:11:13 -0500
commit7145c241a1bf2841952c3e297c4080b357b3e52d (patch)
tree12c9a8ffce670390ea5b518fbe6d9b64f90f05b9 /drivers/md/dm-crypt.c
parentcf2f1abfbd0dba701f7f16ef619e4d2485de3366 (diff)
dm crypt: avoid deadlock in mempools
Fix a theoretical deadlock introduced in the previous commit ("dm crypt: don't allocate pages for a partial request"). The function crypt_alloc_buffer may be called concurrently. If we allocate from the mempool concurrently, there is a possibility of deadlock. For example, if we have mempool of 256 pages, two processes, each wanting 256, pages allocate from the mempool concurrently, it may deadlock in a situation where both processes have allocated 128 pages and the mempool is exhausted. To avoid such a scenario we allocate the pages under a mutex. In order to not degrade performance with excessive locking, we try non-blocking allocations without a mutex first and if that fails, we fallback to a blocking allocations with a mutex. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Diffstat (limited to 'drivers/md/dm-crypt.c')
-rw-r--r--drivers/md/dm-crypt.c41
1 files changed, 36 insertions, 5 deletions
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 6199245ea6a6..fa1dba1d06f7 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -124,6 +124,7 @@ struct crypt_config {
mempool_t *req_pool;
mempool_t *page_pool;
struct bio_set *bs;
+ struct mutex bio_alloc_lock;
struct workqueue_struct *io_queue;
struct workqueue_struct *crypt_queue;
@@ -949,27 +950,51 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
/*
* Generate a new unfragmented bio with the given size
* This should never violate the device limitations
+ *
+ * This function may be called concurrently. If we allocate from the mempool
+ * concurrently, there is a possibility of deadlock. For example, if we have
+ * mempool of 256 pages, two processes, each wanting 256, pages allocate from
+ * the mempool concurrently, it may deadlock in a situation where both processes
+ * have allocated 128 pages and the mempool is exhausted.
+ *
+ * In order to avoid this scenario we allocate the pages under a mutex.
+ *
+ * In order to not degrade performance with excessive locking, we try
+ * non-blocking allocations without a mutex first but on failure we fallback
+ * to blocking allocations with a mutex.
*/
static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
- gfp_t gfp_mask = GFP_NOIO | __GFP_HIGHMEM;
- unsigned i, len;
+ gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM;
+ unsigned i, len, remaining_size;
struct page *page;
struct bio_vec *bvec;
+retry:
+ if (unlikely(gfp_mask & __GFP_WAIT))
+ mutex_lock(&cc->bio_alloc_lock);
+
clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
if (!clone)
- return NULL;
+ goto return_clone;
clone_init(io, clone);
+ remaining_size = size;
+
for (i = 0; i < nr_iovecs; i++) {
page = mempool_alloc(cc->page_pool, gfp_mask);
+ if (!page) {
+ crypt_free_buffer_pages(cc, clone);
+ bio_put(clone);
+ gfp_mask |= __GFP_WAIT;
+ goto retry;
+ }
- len = (size > PAGE_SIZE) ? PAGE_SIZE : size;
+ len = (remaining_size > PAGE_SIZE) ? PAGE_SIZE : remaining_size;
bvec = &clone->bi_io_vec[clone->bi_vcnt++];
bvec->bv_page = page;
@@ -978,9 +1003,13 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size)
clone->bi_iter.bi_size += len;
- size -= len;
+ remaining_size -= len;
}
+return_clone:
+ if (unlikely(gfp_mask & __GFP_WAIT))
+ mutex_unlock(&cc->bio_alloc_lock);
+
return clone;
}
@@ -1679,6 +1708,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
goto bad;
}
+ mutex_init(&cc->bio_alloc_lock);
+
ret = -EINVAL;
if (sscanf(argv[2], "%llu%c", &tmpll, &dummy) != 1) {
ti->error = "Invalid iv_offset sector";