1 files changed, 105 insertions, 84 deletions

diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index c88ed14d49e6..f90679cfec5b 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2011-2012 Red Hat, Inc.
  *
@@ -14,7 +15,8 @@
 #include <linux/device-mapper.h>
 #include <linux/workqueue.h>
 
-/*--------------------------------------------------------------------------
+/*
+ *--------------------------------------------------------------------------
  * As far as the metadata goes, there is:
  *
  * - A superblock in block zero, taking up fewer than 512 bytes for
@@ -70,7 +72,8 @@
  *
  * All metadata io is in THIN_METADATA_BLOCK_SIZE sized/aligned chunks
  * from the block manager.
- *--------------------------------------------------------------------------*/
+ *--------------------------------------------------------------------------
+ */
 
 #define DM_MSG_PREFIX   "thin metadata"
 
@@ -239,13 +242,14 @@ struct dm_thin_device {
 	uint32_t snapshotted_time;
 };
 
-/*----------------------------------------------------------------
+/*
+ *--------------------------------------------------------------
  * superblock validator
- *--------------------------------------------------------------*/
-
+ *--------------------------------------------------------------
+ */
 #define SUPERBLOCK_CSUM_XOR 160774
 
-static void sb_prepare_for_write(struct dm_block_validator *v,
+static void sb_prepare_for_write(const struct dm_block_validator *v,
 				 struct dm_block *b,
 				 size_t block_size)
 {
@@ -257,7 +261,7 @@ static void sb_prepare_for_write(struct dm_block_validator *v,
 						      SUPERBLOCK_CSUM_XOR));
 }
 
-static int sb_check(struct dm_block_validator *v,
+static int sb_check(const struct dm_block_validator *v,
 		    struct dm_block *b,
 		    size_t block_size)
 {
@@ -265,15 +269,15 @@ static int sb_check(struct dm_block_validator *v,
 	__le32 csum_le;
 
 	if (dm_block_location(b) != le64_to_cpu(disk_super->blocknr)) {
-		DMERR("sb_check failed: blocknr %llu: "
-		      "wanted %llu", le64_to_cpu(disk_super->blocknr),
+		DMERR("%s failed: blocknr %llu: wanted %llu",
+		      __func__, le64_to_cpu(disk_super->blocknr),
 		      (unsigned long long)dm_block_location(b));
 		return -ENOTBLK;
 	}
 
 	if (le64_to_cpu(disk_super->magic) != THIN_SUPERBLOCK_MAGIC) {
-		DMERR("sb_check failed: magic %llu: "
-		      "wanted %llu", le64_to_cpu(disk_super->magic),
+		DMERR("%s failed: magic %llu: wanted %llu",
+		      __func__, le64_to_cpu(disk_super->magic),
 		      (unsigned long long)THIN_SUPERBLOCK_MAGIC);
 		return -EILSEQ;
 	}
@@ -282,24 +286,25 @@ static int sb_check(struct dm_block_validator *v,
 					     block_size - sizeof(__le32),
 					     SUPERBLOCK_CSUM_XOR));
 	if (csum_le != disk_super->csum) {
-		DMERR("sb_check failed: csum %u: wanted %u",
-		      le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum));
+		DMERR("%s failed: csum %u: wanted %u",
+		      __func__, le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum));
 		return -EILSEQ;
 	}
 
 	return 0;
 }
 
-static struct dm_block_validator sb_validator = {
+static const struct dm_block_validator sb_validator = {
 	.name = "superblock",
 	.prepare_for_write = sb_prepare_for_write,
 	.check = sb_check
 };
 
-/*----------------------------------------------------------------
+/*
+ *--------------------------------------------------------------
  * Methods for the btree value types
- *--------------------------------------------------------------*/
-
+ *--------------------------------------------------------------
+ */
 static uint64_t pack_block_time(dm_block_t b, uint32_t t)
 {
 	return (b << 24) | t;
@@ -318,12 +323,12 @@ static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t)
  */
 typedef int (*run_fn)(struct dm_space_map *, dm_block_t, dm_block_t);
 
-static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned count, run_fn fn)
+static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned int count, run_fn fn)
 {
 	uint64_t b, begin, end;
 	uint32_t t;
 	bool in_run = false;
-	unsigned i;
+	unsigned int i;
 
 	for (i = 0; i < count; i++, value_le++) {
 		/* We know value_le is 8 byte aligned */
@@ -348,13 +353,13 @@ static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned
 		fn(sm, begin, end);
 }
 
-static void data_block_inc(void *context, const void *value_le, unsigned count)
+static void data_block_inc(void *context, const void *value_le, unsigned int count)
 {
 	with_runs((struct dm_space_map *) context,
 		  (const __le64 *) value_le, count, dm_sm_inc_blocks);
 }
 
-static void data_block_dec(void *context, const void *value_le, unsigned count)
+static void data_block_dec(void *context, const void *value_le, unsigned int count)
 {
 	with_runs((struct dm_space_map *) context,
 		  (const __le64 *) value_le, count, dm_sm_dec_blocks);
@@ -374,21 +379,21 @@ static int data_block_equal(void *context, const void *value1_le, const void *va
 	return b1 == b2;
 }
 
-static void subtree_inc(void *context, const void *value, unsigned count)
+static void subtree_inc(void *context, const void *value, unsigned int count)
 {
 	struct dm_btree_info *info = context;
 	const __le64 *root_le = value;
-	unsigned i;
+	unsigned int i;
 
 	for (i = 0; i < count; i++, root_le++)
 		dm_tm_inc(info->tm, le64_to_cpu(*root_le));
 }
 
-static void subtree_dec(void *context, const void *value, unsigned count)
+static void subtree_dec(void *context, const void *value, unsigned int count)
 {
 	struct dm_btree_info *info = context;
 	const __le64 *root_le = value;
-	unsigned i;
+	unsigned int i;
 
 	for (i = 0; i < count; i++, root_le++)
 		if (dm_btree_del(info, le64_to_cpu(*root_le)))
@@ -398,6 +403,7 @@ static void subtree_dec(void *context, const void *value, unsigned count)
 static int subtree_equal(void *context, const void *value1_le, const void *value2_le)
 {
 	__le64 v1_le, v2_le;
+
 	memcpy(&v1_le, value1_le, sizeof(v1_le));
 	memcpy(&v2_le, value2_le, sizeof(v2_le));
 
@@ -448,10 +454,10 @@ static int superblock_lock(struct dm_pool_metadata *pmd,
 static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result)
 {
 	int r;
-	unsigned i;
+	unsigned int i;
 	struct dm_block *b;
 	__le64 *data_le, zero = cpu_to_le64(0);
-	unsigned block_size = dm_bm_block_size(bm) / sizeof(__le64);
+	unsigned int block_size = dm_bm_block_size(bm) / sizeof(__le64);
 
 	/*
 	 * We can't use a validator here - it may be all zeroes.
@@ -549,7 +555,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	int r;
 	struct dm_block *sblock;
 	struct thin_disk_superblock *disk_super;
-	sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT;
+	sector_t bdev_size = bdev_nr_sectors(pmd->bdev);
 
 	if (bdev_size > THIN_METADATA_MAX_SECTORS)
 		bdev_size = THIN_METADATA_MAX_SECTORS;
@@ -597,6 +603,8 @@ static int __format_metadata(struct dm_pool_metadata *pmd)
 	r = dm_tm_create_with_sm(pmd->bm, THIN_SUPERBLOCK_LOCATION,
 				 &pmd->tm, &pmd->metadata_sm);
 	if (r < 0) {
+		pmd->tm = NULL;
+		pmd->metadata_sm = NULL;
 		DMERR("tm_create_with_sm failed");
 		return r;
 	}
@@ -605,6 +613,7 @@ static int __format_metadata(struct dm_pool_metadata *pmd)
 	if (IS_ERR(pmd->data_sm)) {
 		DMERR("sm_disk_create failed");
 		r = PTR_ERR(pmd->data_sm);
+		pmd->data_sm = NULL;
 		goto bad_cleanup_tm;
 	}
 
@@ -635,11 +644,15 @@ static int __format_metadata(struct dm_pool_metadata *pmd)
 
 bad_cleanup_nb_tm:
 	dm_tm_destroy(pmd->nb_tm);
+	pmd->nb_tm = NULL;
 bad_cleanup_data_sm:
 	dm_sm_destroy(pmd->data_sm);
+	pmd->data_sm = NULL;
 bad_cleanup_tm:
 	dm_tm_destroy(pmd->tm);
+	pmd->tm = NULL;
 	dm_sm_destroy(pmd->metadata_sm);
+	pmd->metadata_sm = NULL;
 
 	return r;
 }
@@ -705,6 +718,8 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 			       sizeof(disk_super->metadata_space_map_root),
 			       &pmd->tm, &pmd->metadata_sm);
 	if (r < 0) {
+		pmd->tm = NULL;
+		pmd->metadata_sm = NULL;
 		DMERR("tm_open_with_sm failed");
 		goto bad_unlock_sblock;
 	}
@@ -714,6 +729,7 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 	if (IS_ERR(pmd->data_sm)) {
 		DMERR("sm_disk_open failed");
 		r = PTR_ERR(pmd->data_sm);
+		pmd->data_sm = NULL;
 		goto bad_cleanup_tm;
 	}
 
@@ -724,6 +740,15 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 		goto bad_cleanup_data_sm;
 	}
 
+	/*
+	 * For pool metadata opening process, root setting is redundant
+	 * because it will be set again in __begin_transaction(). But dm
+	 * pool aborting process really needs to get last transaction's
+	 * root to avoid accessing broken btree.
+	 */
+	pmd->root = le64_to_cpu(disk_super->data_mapping_root);
+	pmd->details_root = le64_to_cpu(disk_super->device_details_root);
+
 	__setup_btree_details(pmd);
 	dm_bm_unlock(sblock);
 
@@ -731,9 +756,12 @@ static int __open_metadata(struct dm_pool_metadata *pmd)
 
 bad_cleanup_data_sm:
 	dm_sm_destroy(pmd->data_sm);
+	pmd->data_sm = NULL;
 bad_cleanup_tm:
 	dm_tm_destroy(pmd->tm);
+	pmd->tm = NULL;
 	dm_sm_destroy(pmd->metadata_sm);
+	pmd->metadata_sm = NULL;
 bad_unlock_sblock:
 	dm_bm_unlock(sblock);
 
@@ -776,13 +804,19 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f
 	return r;
 }
 
-static void __destroy_persistent_data_objects(struct dm_pool_metadata *pmd)
+static void __destroy_persistent_data_objects(struct dm_pool_metadata *pmd,
+					      bool destroy_bm)
 {
 	dm_sm_destroy(pmd->data_sm);
+	pmd->data_sm = NULL;
 	dm_sm_destroy(pmd->metadata_sm);
+	pmd->metadata_sm = NULL;
 	dm_tm_destroy(pmd->nb_tm);
+	pmd->nb_tm = NULL;
 	dm_tm_destroy(pmd->tm);
-	dm_block_manager_destroy(pmd->bm);
+	pmd->tm = NULL;
+	if (destroy_bm)
+		dm_block_manager_destroy(pmd->bm);
 }
 
 static int __begin_transaction(struct dm_pool_metadata *pmd)
@@ -960,7 +994,7 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
 int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 {
 	int r;
-	unsigned open_devices = 0;
+	unsigned int open_devices = 0;
 	struct dm_thin_device *td, *tmp;
 
 	down_read(&pmd->root_lock);
@@ -988,8 +1022,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 			       __func__, r);
 	}
 	pmd_write_unlock(pmd);
-	if (!pmd->fail_io)
-		__destroy_persistent_data_objects(pmd);
+	__destroy_persistent_data_objects(pmd, true);
 
 	kfree(pmd);
 	return 0;
@@ -1519,9 +1552,9 @@ static int __find_block(struct dm_thin_device *td, dm_block_t block,
 	dm_block_t keys[2] = { td->id, block };
 	struct dm_btree_info *info;
 
-	if (can_issue_io) {
+	if (can_issue_io)
 		info = &pmd->info;
-	} else
+	else
 		info = &pmd->nb_info;
 
 	r = dm_btree_lookup(info, pmd->root, keys, &value);
@@ -1595,8 +1628,8 @@ static int __find_mapped_range(struct dm_thin_device *td,
 		if (r) {
 			if (r == -ENODATA)
 				break;
-			else
-				return r;
+
+			return r;
 		}
 
 		if ((lookup.block != pool_end) ||
@@ -1665,26 +1698,10 @@ int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block,
 	return r;
 }
 
-static int __remove(struct dm_thin_device *td, dm_block_t block)
-{
-	int r;
-	struct dm_pool_metadata *pmd = td->pmd;
-	dm_block_t keys[2] = { td->id, block };
-
-	r = dm_btree_remove(&pmd->info, pmd->root, keys, &pmd->root);
-	if (r)
-		return r;
-
-	td->mapped_blocks--;
-	td->changed = true;
-
-	return 0;
-}
-
 static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end)
 {
 	int r;
-	unsigned count, total_count = 0;
+	unsigned int count, total_count = 0;
 	struct dm_pool_metadata *pmd = td->pmd;
 	dm_block_t keys[1] = { td->id };
 	__le64 value;
@@ -1740,18 +1757,6 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_
 	return dm_btree_insert(&pmd->tl_info, pmd->root, keys, &value, &pmd->root);
 }
 
-int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block)
-{
-	int r = -EINVAL;
-
-	pmd_write_lock(td->pmd);
-	if (!td->pmd->fail_io)
-		r = __remove(td, block);
-	pmd_write_unlock(td->pmd);
-
-	return r;
-}
-
 int dm_thin_remove_range(struct dm_thin_device *td,
 			 dm_block_t begin, dm_block_t end)
 {
@@ -1767,13 +1772,15 @@ int dm_thin_remove_range(struct dm_thin_device *td,
 
 int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *result)
 {
-	int r;
+	int r = -EINVAL;
 	uint32_t ref_count;
 
 	down_read(&pmd->root_lock);
-	r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
-	if (!r)
-		*result = (ref_count > 1);
+	if (!pmd->fail_io) {
+		r = dm_sm_get_count(pmd->data_sm, b, &ref_count);
+		if (!r)
+			*result = (ref_count > 1);
+	}
 	up_read(&pmd->root_lock);
 
 	return r;
@@ -1781,10 +1788,11 @@ int dm_pool_block_is_shared(struct dm_pool_metadata *pmd, dm_block_t b, bool *re
 
 int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
 {
-	int r = 0;
+	int r = -EINVAL;
 
 	pmd_write_lock(pmd);
-	r = dm_sm_inc_blocks(pmd->data_sm, b, e);
+	if (!pmd->fail_io)
+		r = dm_sm_inc_blocks(pmd->data_sm, b, e);
 	pmd_write_unlock(pmd);
 
 	return r;
@@ -1792,10 +1800,11 @@ int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_
 
 int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_t e)
 {
-	int r = 0;
+	int r = -EINVAL;
 
 	pmd_write_lock(pmd);
-	r = dm_sm_dec_blocks(pmd->data_sm, b, e);
+	if (!pmd->fail_io)
+		r = dm_sm_dec_blocks(pmd->data_sm, b, e);
 	pmd_write_unlock(pmd);
 
 	return r;
@@ -1889,19 +1898,28 @@ int dm_pool_abort_metadata(struct dm_pool_metadata *pmd)
 {
 	int r = -EINVAL;
 
-	pmd_write_lock(pmd);
-	if (pmd->fail_io)
-		goto out;
+	/* fail_io is double-checked with pmd->root_lock held below */
+	if (unlikely(pmd->fail_io))
+		return r;
 
+	pmd_write_lock(pmd);
+	if (pmd->fail_io) {
+		pmd_write_unlock(pmd);
+		return r;
+	}
 	__set_abort_with_changes_flags(pmd);
-	__destroy_persistent_data_objects(pmd);
-	r = __create_persistent_data_objects(pmd, false);
+
+	/* destroy data_sm/metadata_sm/nb_tm/tm */
+	__destroy_persistent_data_objects(pmd, false);
+
+	/* reset bm */
+	dm_block_manager_reset(pmd->bm);
+
+	/* rebuild data_sm/metadata_sm/nb_tm/tm */
+	r = __open_or_format_metadata(pmd, false);
 	if (r)
 		pmd->fail_io = true;
-
-out:
 	pmd_write_unlock(pmd);
-
 	return r;
 }
 
@@ -2073,10 +2091,13 @@ int dm_pool_register_metadata_threshold(struct dm_pool_metadata *pmd,
 					dm_sm_threshold_fn fn,
 					void *context)
 {
-	int r;
+	int r = -EINVAL;
 
 	pmd_write_lock_in_core(pmd);
-	r = dm_sm_register_threshold_callback(pmd->metadata_sm, threshold, fn, context);
+	if (!pmd->fail_io) {
+		r = dm_sm_register_threshold_callback(pmd->metadata_sm,
+						      threshold, fn, context);
+	}
 	pmd_write_unlock(pmd);
 
 	return r;