Merge tag 'dm-4.5-changes' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - The most significant set of changes this cycle is the Forward Error
   Correction (FEC) support that has been added to the DM verity target.

   Google uses DM verity on all Android devices and it is believed that
   this FEC support will enable DM verity to recover from storage
   failures seen since DM verity was first deployed as part of Android.

 - A stable fix for a race in the destruction of DM thin pool's
   workqueue

 - A stable fix for hung IO if a DM snapshot copy hit an error

 - A few small cleanups in DM core and DM persistent data.

 - A couple DM thinp range discard improvements (address atomicity of
   finding a range and the efficiency of discarding a partially mapped
   thin device)

 - Add ability to debug DM bufio leaks by recording stack trace when a
   buffer is allocated.  Upon detected leak the recorded stack is
   dumped.

* tag 'dm-4.5-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm snapshot: fix hung bios when copy error occurs
  dm thin: bump thin and thin-pool target versions
  dm thin: fix race condition when destroying thin pool workqueue
  dm space map metadata: remove unused variable in brb_pop()
  dm verity: add ignore_zero_blocks feature
  dm verity: add support for forward error correction
  dm verity: factor out verity_for_bv_block()
  dm verity: factor out structures and functions useful to separate object
  dm verity: move dm-verity.c to dm-verity-target.c
  dm verity: separate function for parsing opt args
  dm verity: clean up duplicate hashing code
  dm btree: factor out need_insert() helper
  dm bufio: use BUG_ON instead of conditional call to BUG
  dm bufio: store stacktrace in buffers to help find buffer leaks
  dm bufio: return NULL to improve code clarity
  dm block manager: cleanup code that prints stacktrace
  dm: don't save and restore bi_private
  dm thin metadata: make dm_thin_find_mapped_range() atomic
  dm thin metadata: speed up discard of partially mapped volumes

Documentation/device-mapper/verity.txt

@@ -18,11 +18,11 @@ Construction Parameters
 
     0 is the original format used in the Chromium OS.
       The salt is appended when hashing, digests are stored continuously and
-      the rest of the block is padded with zeros.
+      the rest of the block is padded with zeroes.
 
     1 is the current format that should be used for new devices.
       The salt is prepended when hashing and each digest is
-      padded with zeros to the power of two.
+      padded with zeroes to the power of two.
 
 <dev>
     This is the device containing data, the integrity of which needs to be
@@ -79,6 +79,37 @@ restart_on_corruption
     not compatible with ignore_corruption and requires user space support to
     avoid restart loops.
 
+ignore_zero_blocks
+    Do not verify blocks that are expected to contain zeroes and always return
+    zeroes instead. This may be useful if the partition contains unused blocks
+    that are not guaranteed to contain zeroes.
+
+use_fec_from_device <fec_dev>
+    Use forward error correction (FEC) to recover from corruption if hash
+    verification fails. Use encoding data from the specified device. This
+    may be the same device where data and hash blocks reside, in which case
+    fec_start must be outside data and hash areas.
+
+    If the encoding data covers additional metadata, it must be accessible
+    on the hash device after the hash blocks.
+
+    Note: block sizes for data and hash devices must match. Also, if the
+    verity <dev> is encrypted the <fec_dev> should be too.
+
+fec_roots <num>
+    Number of generator roots. This equals to the number of parity bytes in
+    the encoding data. For example, in RS(M, N) encoding, the number of roots
+    is M-N.
+
+fec_blocks <num>
+    The number of encoding data blocks on the FEC device. The block size for
+    the FEC device is <data_block_size>.
+
+fec_start <offset>
+    This is the offset, in <data_block_size> blocks, from the start of the
+    FEC device to the beginning of the encoding data.
+
+
 Theory of operation
 ===================
 
@@ -98,6 +129,11 @@ per-block basis. This allows for a lightweight hash computation on first read
 into the page cache. Block hashes are stored linearly, aligned to the nearest
 block size.
 
+If forward error correction (FEC) support is enabled any recovery of
+corrupted data will be verified using the cryptographic hash of the
+corresponding data. This is why combining error correction with
+integrity checking is essential.
+
 Hash Tree
 ---------
 

drivers/md/Kconfig

@@ -240,6 +240,15 @@ config DM_BUFIO
 	 as a cache, holding recently-read blocks in memory and performing
 	 delayed writes.
 
+config DM_DEBUG_BLOCK_STACK_TRACING
+       bool "Keep stack trace of persistent data block lock holders"
+       depends on STACKTRACE_SUPPORT && DM_BUFIO
+       select STACKTRACE
+       ---help---
+	 Enable this for messages that may help debug problems with the
+	 block manager locking used by thin provisioning and caching.
+
+	 If unsure, say N.
 config DM_BIO_PRISON
        tristate
        depends on BLK_DEV_DM
@@ -458,6 +467,18 @@ config DM_VERITY
 
 	  If unsure, say N.
 
+config DM_VERITY_FEC
+	bool "Verity forward error correction support"
+	depends on DM_VERITY
+	select REED_SOLOMON
+	select REED_SOLOMON_DEC8
+	---help---
+	  Add forward error correction support to dm-verity. This option
+	  makes it possible to use pre-generated error correction data to
+	  recover from corrupted blocks.
+
+	  If unsure, say N.
+
 config DM_SWITCH
 	tristate "Switch target support (EXPERIMENTAL)"
 	depends on BLK_DEV_DM

drivers/md/Makefile

@@ -16,6 +16,7 @@ dm-cache-mq-y   += dm-cache-policy-mq.o
 dm-cache-smq-y   += dm-cache-policy-smq.o
 dm-cache-cleaner-y += dm-cache-policy-cleaner.o
 dm-era-y	+= dm-era-target.o
+dm-verity-y	+= dm-verity-target.o
 md-mod-y	+= md.o bitmap.o
 raid456-y	+= raid5.o raid5-cache.o
 
@@ -63,3 +64,7 @@ obj-$(CONFIG_DM_LOG_WRITES)	+= dm-log-writes.o
 ifeq ($(CONFIG_DM_UEVENT),y)
 dm-mod-objs			+= dm-uevent.o
 endif
+
+ifeq ($(CONFIG_DM_VERITY_FEC),y)
+dm-verity-objs			+= dm-verity-fec.o
+endif

drivers/md/dm-bufio.c

@@ -16,6 +16,7 @@
 #include <linux/shrinker.h>
 #include <linux/module.h>
 #include <linux/rbtree.h>
+#include <linux/stacktrace.h>
 
 #define DM_MSG_PREFIX "bufio"
 
@@ -149,6 +150,11 @@ struct dm_buffer {
 	struct list_head write_list;
 	struct bio bio;
 	struct bio_vec bio_vec[DM_BUFIO_INLINE_VECS];
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+#define MAX_STACK 10
+	struct stack_trace stack_trace;
+	unsigned long stack_entries[MAX_STACK];
+#endif
 };
 
 /*----------------------------------------------------------------*/
@@ -253,6 +259,17 @@ static LIST_HEAD(dm_bufio_all_clients);
  */
 static DEFINE_MUTEX(dm_bufio_clients_lock);
 
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+static void buffer_record_stack(struct dm_buffer *b)
+{
+	b->stack_trace.nr_entries = 0;
+	b->stack_trace.max_entries = MAX_STACK;
+	b->stack_trace.entries = b->stack_entries;
+	b->stack_trace.skip = 2;
+	save_stack_trace(&b->stack_trace);
+}
+#endif
+
 /*----------------------------------------------------------------
  * A red/black tree acts as an index for all the buffers.
  *--------------------------------------------------------------*/
@@ -454,6 +471,9 @@ static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask)
 
 	adjust_total_allocated(b->data_mode, (long)c->block_size);
 
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+	memset(&b->stack_trace, 0, sizeof(b->stack_trace));
+#endif
 	return b;
 }
 
@@ -1063,12 +1083,16 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 
 	dm_bufio_lock(c);
 	b = __bufio_new(c, block, nf, &need_submit, &write_list);
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+	if (b && b->hold_count == 1)
+		buffer_record_stack(b);
+#endif
 	dm_bufio_unlock(c);
 
 	__flush_write_list(&write_list);
 
 	if (!b)
-		return b;
+		return NULL;
 
 	if (need_submit)
 		submit_io(b, READ, b->block, read_endio);
@@ -1462,6 +1486,7 @@ static void drop_buffers(struct dm_bufio_client *c)
 {
 	struct dm_buffer *b;
 	int i;
+	bool warned = false;
 
 	BUG_ON(dm_bufio_in_request());
 
@@ -1476,9 +1501,21 @@ static void drop_buffers(struct dm_bufio_client *c)
 		__free_buffer_wake(b);
 
 	for (i = 0; i < LIST_SIZE; i++)
-		list_for_each_entry(b, &c->lru[i], lru_list)
+		list_for_each_entry(b, &c->lru[i], lru_list) {
+			WARN_ON(!warned);
+			warned = true;
 			DMERR("leaked buffer %llx, hold count %u, list %d",
 			      (unsigned long long)b->block, b->hold_count, i);
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+			print_stack_trace(&b->stack_trace, 1);
+			b->hold_count = 0; /* mark unclaimed to avoid BUG_ON below */
+#endif
+		}
+
+#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
+	while ((b = __get_unclaimed_buffer(c)))
+		__free_buffer_wake(b);
+#endif
 
 	for (i = 0; i < LIST_SIZE; i++)
 		BUG_ON(!list_empty(&c->lru[i]));
@@ -1891,8 +1928,7 @@ static void __exit dm_bufio_exit(void)
 		bug = 1;
 	}
 
-	if (bug)
-		BUG();
+	BUG_ON(bug);
 }
 
 module_init(dm_bufio_init)

drivers/md/dm-cache-target.c

@@ -118,14 +118,12 @@ static void iot_io_end(struct io_tracker *iot, sector_t len)
  */
 struct dm_hook_info {
 	bio_end_io_t *bi_end_io;
-	void *bi_private;
 };
 
 static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio,
 			bio_end_io_t *bi_end_io, void *bi_private)
 {
 	h->bi_end_io = bio->bi_end_io;
-	h->bi_private = bio->bi_private;
 
 	bio->bi_end_io = bi_end_io;
 	bio->bi_private = bi_private;
@@ -134,7 +132,6 @@ static void dm_hook_bio(struct dm_hook_info *h, struct bio *bio,
 static void dm_unhook_bio(struct dm_hook_info *h, struct bio *bio)
 {
 	bio->bi_end_io = h->bi_end_io;
-	bio->bi_private = h->bi_private;
 }
 
 /*----------------------------------------------------------------*/

drivers/md/dm-exception-store.h

@@ -69,7 +69,7 @@ struct dm_exception_store_type {
 	 * Update the metadata with this exception.
 	 */
 	void (*commit_exception) (struct dm_exception_store *store,
-				  struct dm_exception *e,
+				  struct dm_exception *e, int valid,
 				  void (*callback) (void *, int success),
 				  void *callback_context);
 

drivers/md/dm-snap-persistent.c

@@ -695,7 +695,7 @@ static int persistent_prepare_exception(struct dm_exception_store *store,
 }
 
 static void persistent_commit_exception(struct dm_exception_store *store,
-					struct dm_exception *e,
+					struct dm_exception *e, int valid,
 					void (*callback) (void *, int success),
 					void *callback_context)
 {
@@ -704,6 +704,9 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	struct core_exception ce;
 	struct commit_callback *cb;
 
+	if (!valid)
+		ps->valid = 0;
+
 	ce.old_chunk = e->old_chunk;
 	ce.new_chunk = e->new_chunk;
 	write_exception(ps, ps->current_committed++, &ce);

drivers/md/dm-snap-transient.c

@@ -52,12 +52,12 @@ static int transient_prepare_exception(struct dm_exception_store *store,
 }
 
 static void transient_commit_exception(struct dm_exception_store *store,
-				       struct dm_exception *e,
+				       struct dm_exception *e, int valid,
 				       void (*callback) (void *, int success),
 				       void *callback_context)
 {
 	/* Just succeed */
-	callback(callback_context, 1);
+	callback(callback_context, valid);
 }
 
 static void transient_usage(struct dm_exception_store *store,

drivers/md/dm-snap.c

@@ -207,7 +207,6 @@ struct dm_snap_pending_exception {
 	 */
 	struct bio *full_bio;
 	bio_end_io_t *full_bio_end_io;
-	void *full_bio_private;
 };
 
 /*
@@ -1438,8 +1437,9 @@ static void __invalidate_snapshot(struct dm_snapshot *s, int err)
 	dm_table_event(s->ti->table);
 }
 
-static void pending_complete(struct dm_snap_pending_exception *pe, int success)
+static void pending_complete(void *context, int success)
 {
+	struct dm_snap_pending_exception *pe = context;
 	struct dm_exception *e;
 	struct dm_snapshot *s = pe->snap;
 	struct bio *origin_bios = NULL;
@@ -1485,10 +1485,8 @@ static void pending_complete(struct dm_snap_pending_exception *pe, int success)
 	snapshot_bios = bio_list_get(&pe->snapshot_bios);
 	origin_bios = bio_list_get(&pe->origin_bios);
 	full_bio = pe->full_bio;
-	if (full_bio) {
+	if (full_bio)
 		full_bio->bi_end_io = pe->full_bio_end_io;
-		full_bio->bi_private = pe->full_bio_private;
-	}
 	increment_pending_exceptions_done_count();
 
 	up_write(&s->lock);
@@ -1509,24 +1507,13 @@ static void pending_complete(struct dm_snap_pending_exception *pe, int success)
 	free_pending_exception(pe);
 }
 
-static void commit_callback(void *context, int success)
-{
-	struct dm_snap_pending_exception *pe = context;
-
-	pending_complete(pe, success);
-}
-
 static void complete_exception(struct dm_snap_pending_exception *pe)
 {
 	struct dm_snapshot *s = pe->snap;
 
-	if (unlikely(pe->copy_error))
-		pending_complete(pe, 0);
-
-	else
-		/* Update the metadata if we are persistent */
-		s->store->type->commit_exception(s->store, &pe->e,
-						 commit_callback, pe);
+	/* Update the metadata if we are persistent */
+	s->store->type->commit_exception(s->store, &pe->e, !pe->copy_error,
+					 pending_complete, pe);
 }
 
 /*
@@ -1605,7 +1592,6 @@ static void start_full_bio(struct dm_snap_pending_exception *pe,
 
 	pe->full_bio = bio;
 	pe->full_bio_end_io = bio->bi_end_io;
-	pe->full_bio_private = bio->bi_private;
 
 	callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client,
 						   copy_callback, pe);