Merge tag 'for-4.19/dm-fixes' of...

Merge tag 'for-4.19/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - DM verity fix for crash due to using vmalloc'd buffers with the
   asynchronous crypto hadsh API.

 - Fix to both DM crypt and DM integrity targets to discontinue using
   CRYPTO_TFM_REQ_MAY_SLEEP because its use of GFP_KERNEL can lead to
   deadlock by recursing back into a filesystem.

 - Various DM raid fixes related to reshape and rebuild races.

 - Fix for DM thin-provisioning to avoid data corruption that was a
   side-effect of needing to abort DM thin metadata transaction due to
   running out of metadata space. Fix is to reserve a small amount of
   metadata space so that once it is used the DM thin-pool can finish
   its active transaction before switching to read-only mode.

* tag 'for-4.19/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm thin metadata: try to avoid ever aborting transactions
  dm raid: bump target version, update comments and documentation
  dm raid: fix RAID leg rebuild errors
  dm raid: fix rebuild of specific devices by updating superblock
  dm raid: fix stripe adding reshape deadlock
  dm raid: fix reshape race on small devices
  dm: disable CRYPTO_TFM_REQ_MAY_SLEEP to fix a GFP_KERNEL recursion deadlock
  dm verity: fix crash on bufio buffer that was allocated with vmalloc

Documentation/device-mapper/dm-raid.txt

@@ -348,3 +348,7 @@ Version History
 1.13.1  Fix deadlock caused by early md_stop_writes().  Also fix size an
 	state races.
 1.13.2  Fix raid redundancy validation and avoid keeping raid set frozen
+1.14.0  Fix reshape race on small devices.  Fix stripe adding reshape
+	deadlock/potential data corruption.  Update superblock when
+	specific devices are requested via rebuild.  Fix RAID leg
+	rebuild errors.

drivers/md/dm-crypt.c

@@ -332,7 +332,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc)
 	int err;
 
 	desc->tfm = essiv->hash_tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 
 	err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt);
 	shash_desc_zero(desc);
@@ -606,7 +606,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 	int i, r;
 
 	desc->tfm = lmk->hash_tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 
 	r = crypto_shash_init(desc);
 	if (r)
@@ -768,7 +768,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 
 	/* calculate crc32 for every 32bit part and xor it */
 	desc->tfm = tcw->crc32_tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 	for (i = 0; i < 4; i++) {
 		r = crypto_shash_init(desc);
 		if (r)
@@ -1251,7 +1251,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
 	 * requests if driver request queue is full.
 	 */
 	skcipher_request_set_callback(ctx->r.req,
-	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req));
 }
 
@@ -1268,7 +1268,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
 	 * requests if driver request queue is full.
 	 */
 	aead_request_set_callback(ctx->r.req_aead,
-	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+	    CRYPTO_TFM_REQ_MAY_BACKLOG,
 	    kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead));
 }
 

drivers/md/dm-integrity.c

@@ -532,7 +532,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result
 	unsigned j, size;
 
 	desc->tfm = ic->journal_mac;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	desc->flags = 0;
 
 	r = crypto_shash_init(desc);
 	if (unlikely(r)) {
@@ -676,7 +676,7 @@ static void complete_journal_encrypt(struct crypto_async_request *req, int err)
 static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp)
 {
 	int r;
-	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      complete_journal_encrypt, comp);
 	if (likely(encrypt))
 		r = crypto_skcipher_encrypt(req);

drivers/md/dm-thin-metadata.c

@@ -188,6 +188,12 @@ struct dm_pool_metadata {
 	unsigned long flags;
 	sector_t data_block_size;
 
+	/*
+	 * We reserve a section of the metadata for commit overhead.
+	 * All reported space does *not* include this.
+	 */
+	dm_block_t metadata_reserve;
+
 	/*
 	 * Set if a transaction has to be aborted but the attempt to roll back
 	 * to the previous (good) transaction failed.  The only pool metadata
@@ -816,6 +822,22 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	return dm_tm_commit(pmd->tm, sblock);
 }
 
+static void __set_metadata_reserve(struct dm_pool_metadata *pmd)
+{
+	int r;
+	dm_block_t total;
+	dm_block_t max_blocks = 4096; /* 16M */
+
+	r = dm_sm_get_nr_blocks(pmd->metadata_sm, &total);
+	if (r) {
+		DMERR("could not get size of metadata device");
+		pmd->metadata_reserve = max_blocks;
+	} else {
+		sector_div(total, 10);
+		pmd->metadata_reserve = min(max_blocks, total);
+	}
+}
+
 struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
 					       sector_t data_block_size,
 					       bool format_device)
@@ -849,6 +871,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
 		return ERR_PTR(r);
 	}
 
+	__set_metadata_reserve(pmd);
+
 	return pmd;
 }
 
@@ -1820,6 +1844,13 @@ int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd,
 	down_read(&pmd->root_lock);
 	if (!pmd->fail_io)
 		r = dm_sm_get_nr_free(pmd->metadata_sm, result);
+
+	if (!r) {
+		if (*result < pmd->metadata_reserve)
+			*result = 0;
+		else
+			*result -= pmd->metadata_reserve;
+	}
 	up_read(&pmd->root_lock);
 
 	return r;
@@ -1932,8 +1963,11 @@ int dm_pool_resize_metadata_dev(struct dm_pool_metadata *pmd, dm_block_t new_cou
 	int r = -EINVAL;
 
 	down_write(&pmd->root_lock);
-	if (!pmd->fail_io)
+	if (!pmd->fail_io) {
 		r = __resize_space_map(pmd->metadata_sm, new_count);
+		if (!r)
+			__set_metadata_reserve(pmd);
+	}
 	up_write(&pmd->root_lock);
 
 	return r;

drivers/md/dm-thin.c

@@ -200,7 +200,13 @@ struct dm_thin_new_mapping;
 enum pool_mode {
 	PM_WRITE,		/* metadata may be changed */
 	PM_OUT_OF_DATA_SPACE,	/* metadata may be changed, though data may not be allocated */
+
+	/*
+	 * Like READ_ONLY, except may switch back to WRITE on metadata resize. Reported as READ_ONLY.
+	 */
+	PM_OUT_OF_METADATA_SPACE,
 	PM_READ_ONLY,		/* metadata may not be changed */
+
 	PM_FAIL,		/* all I/O fails */
 };
 
@@ -1371,7 +1377,35 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode);
 
 static void requeue_bios(struct pool *pool);
 
-static void check_for_space(struct pool *pool)
+static bool is_read_only_pool_mode(enum pool_mode mode)
+{
+	return (mode == PM_OUT_OF_METADATA_SPACE || mode == PM_READ_ONLY);
+}
+
+static bool is_read_only(struct pool *pool)
+{
+	return is_read_only_pool_mode(get_pool_mode(pool));
+}
+
+static void check_for_metadata_space(struct pool *pool)
+{
+	int r;
+	const char *ooms_reason = NULL;
+	dm_block_t nr_free;
+
+	r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free);
+	if (r)
+		ooms_reason = "Could not get free metadata blocks";
+	else if (!nr_free)
+		ooms_reason = "No free metadata blocks";
+
+	if (ooms_reason && !is_read_only(pool)) {
+		DMERR("%s", ooms_reason);
+		set_pool_mode(pool, PM_OUT_OF_METADATA_SPACE);
+	}
+}
+
+static void check_for_data_space(struct pool *pool)
 {
 	int r;
 	dm_block_t nr_free;
@@ -1397,14 +1431,16 @@ static int commit(struct pool *pool)
 {
 	int r;
 
-	if (get_pool_mode(pool) >= PM_READ_ONLY)
+	if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE)
 		return -EINVAL;
 
 	r = dm_pool_commit_metadata(pool->pmd);
 	if (r)
 		metadata_operation_failed(pool, "dm_pool_commit_metadata", r);
-	else
-		check_for_space(pool);
+	else {
+		check_for_metadata_space(pool);
+		check_for_data_space(pool);
+	}
 
 	return r;
 }
@@ -1470,6 +1506,19 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result)
 		return r;
 	}
 
+	r = dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks);
+	if (r) {
+		metadata_operation_failed(pool, "dm_pool_get_free_metadata_block_count", r);
+		return r;
+	}
+
+	if (!free_blocks) {
+		/* Let's commit before we use up the metadata reserve. */
+		r = commit(pool);
+		if (r)
+			return r;
+	}
+
 	return 0;
 }
 
@@ -1501,6 +1550,7 @@ static blk_status_t should_error_unserviceable_bio(struct pool *pool)
 	case PM_OUT_OF_DATA_SPACE:
 		return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0;
 
+	case PM_OUT_OF_METADATA_SPACE:
 	case PM_READ_ONLY:
 	case PM_FAIL:
 		return BLK_STS_IOERR;
@@ -2464,8 +2514,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		error_retry_list(pool);
 		break;
 
+	case PM_OUT_OF_METADATA_SPACE:
 	case PM_READ_ONLY:
-		if (old_mode != new_mode)
+		if (!is_read_only_pool_mode(old_mode))
 			notify_of_pool_mode_change(pool, "read-only");
 		dm_pool_metadata_read_only(pool->pmd);
 		pool->process_bio = process_bio_read_only;
@@ -3403,6 +3454,10 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit)
 		DMINFO("%s: growing the metadata device from %llu to %llu blocks",
 		       dm_device_name(pool->pool_md),
 		       sb_metadata_dev_size, metadata_dev_size);
+
+		if (get_pool_mode(pool) == PM_OUT_OF_METADATA_SPACE)
+			set_pool_mode(pool, PM_WRITE);
+
 		r = dm_pool_resize_metadata_dev(pool->pmd, metadata_dev_size);
 		if (r) {
 			metadata_operation_failed(pool, "dm_pool_resize_metadata_dev", r);
@@ -3707,7 +3762,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv,
 	struct pool_c *pt = ti->private;
 	struct pool *pool = pt->pool;
 
-	if (get_pool_mode(pool) >= PM_READ_ONLY) {
+	if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) {
 		DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode",
 		      dm_device_name(pool->pool_md));
 		return -EOPNOTSUPP;
@@ -3781,6 +3836,7 @@ static void pool_status(struct dm_target *ti, status_type_t type,
 	dm_block_t nr_blocks_data;
 	dm_block_t nr_blocks_metadata;
 	dm_block_t held_root;
+	enum pool_mode mode;
 	char buf[BDEVNAME_SIZE];
 	char buf2[BDEVNAME_SIZE];
 	struct pool_c *pt = ti->private;
@@ -3851,9 +3907,10 @@ static void pool_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("- ");
 
-		if (pool->pf.mode == PM_OUT_OF_DATA_SPACE)
+		mode = get_pool_mode(pool);
+		if (mode == PM_OUT_OF_DATA_SPACE)
 			DMEMIT("out_of_data_space ");
-		else if (pool->pf.mode == PM_READ_ONLY)
+		else if (is_read_only_pool_mode(mode))
 			DMEMIT("ro ");
 		else
 			DMEMIT("rw ");

drivers/md/dm-verity-target.c

@@ -99,10 +99,26 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
 {
 	struct scatterlist sg;
 
-	sg_init_one(&sg, data, len);
-	ahash_request_set_crypt(req, &sg, NULL, len);
-
-	return crypto_wait_req(crypto_ahash_update(req), wait);
+	if (likely(!is_vmalloc_addr(data))) {
+		sg_init_one(&sg, data, len);
+		ahash_request_set_crypt(req, &sg, NULL, len);
+		return crypto_wait_req(crypto_ahash_update(req), wait);
+	} else {
+		do {
+			int r;
+			size_t this_step = min_t(size_t, len, PAGE_SIZE - offset_in_page(data));
+			flush_kernel_vmap_range((void *)data, this_step);
+			sg_init_table(&sg, 1);
+			sg_set_page(&sg, vmalloc_to_page(data), this_step, offset_in_page(data));
+			ahash_request_set_crypt(req, &sg, NULL, this_step);
+			r = crypto_wait_req(crypto_ahash_update(req), wait);
+			if (unlikely(r))
+				return r;
+			data += this_step;
+			len -= this_step;
+		} while (len);
+		return 0;
+	}
 }
 
 /*