Merging upstream version 4.19.282.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

12 files changed, 150 insertions, 55 deletions

diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index af6d4f898..2ecd0db0f 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -551,11 +551,13 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd,
 	return r;
 }
 
-static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd)
+static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd,
+					      bool destroy_bm)
 {
 	dm_sm_destroy(cmd->metadata_sm);
 	dm_tm_destroy(cmd->tm);
-	dm_block_manager_destroy(cmd->bm);
+	if (destroy_bm)
+		dm_block_manager_destroy(cmd->bm);
 }
 
 typedef unsigned long (*flags_mutator)(unsigned long);
@@ -826,7 +828,7 @@ static struct dm_cache_metadata *lookup_or_open(struct block_device *bdev,
 		cmd2 = lookup(bdev);
 		if (cmd2) {
 			mutex_unlock(&table_lock);
-			__destroy_persistent_data_objects(cmd);
+			__destroy_persistent_data_objects(cmd, true);
 			kfree(cmd);
 			return cmd2;
 		}
@@ -874,7 +876,7 @@ void dm_cache_metadata_close(struct dm_cache_metadata *cmd)
 		mutex_unlock(&table_lock);
 
 		if (!cmd->fail_io)
-			__destroy_persistent_data_objects(cmd);
+			__destroy_persistent_data_objects(cmd, true);
 		kfree(cmd);
 	}
 }
@@ -1808,14 +1810,52 @@ int dm_cache_metadata_needs_check(struct dm_cache_metadata *cmd, bool *result)
 
 int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
 {
-	int r;
+	int r = -EINVAL;
+	struct dm_block_manager *old_bm = NULL, *new_bm = NULL;
+
+	/* fail_io is double-checked with cmd->root_lock held below */
+	if (unlikely(cmd->fail_io))
+		return r;
+
+	/*
+	 * Replacement block manager (new_bm) is created and old_bm destroyed outside of
+	 * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of
+	 * shrinker associated with the block manager's bufio client vs cmd root_lock).
+	 * - must take shrinker_rwsem without holding cmd->root_lock
+	 */
+	new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
+					 CACHE_MAX_CONCURRENT_LOCKS);
 
 	WRITE_LOCK(cmd);
-	__destroy_persistent_data_objects(cmd);
-	r = __create_persistent_data_objects(cmd, false);
+	if (cmd->fail_io) {
+		WRITE_UNLOCK(cmd);
+		goto out;
+	}
+
+	__destroy_persistent_data_objects(cmd, false);
+	old_bm = cmd->bm;
+	if (IS_ERR(new_bm)) {
+		DMERR("could not create block manager during abort");
+		cmd->bm = NULL;
+		r = PTR_ERR(new_bm);
+		goto out_unlock;
+	}
+
+	cmd->bm = new_bm;
+	r = __open_or_format_metadata(cmd, false);
+	if (r) {
+		cmd->bm = NULL;
+		goto out_unlock;
+	}
+	new_bm = NULL;
+out_unlock:
 	if (r)
 		cmd->fail_io = true;
 	WRITE_UNLOCK(cmd);
+	dm_block_manager_destroy(old_bm);
+out:
+	if (new_bm && !IS_ERR(new_bm))
+		dm_block_manager_destroy(new_bm);
 
 	return r;
 }
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 2ddd575e9..b3371812a 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -1010,16 +1010,16 @@ static void abort_transaction(struct cache *cache)
 	if (get_cache_mode(cache) >= CM_READ_ONLY)
 		return;
 
-	if (dm_cache_metadata_set_needs_check(cache->cmd)) {
-		DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name);
-		set_cache_mode(cache, CM_FAIL);
-	}
-
 	DMERR_LIMIT("%s: aborting current metadata transaction", dev_name);
 	if (dm_cache_metadata_abort(cache->cmd)) {
 		DMERR("%s: failed to abort metadata transaction", dev_name);
 		set_cache_mode(cache, CM_FAIL);
 	}
+
+	if (dm_cache_metadata_set_needs_check(cache->cmd)) {
+		DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name);
+		set_cache_mode(cache, CM_FAIL);
+	}
 }
 
 static void metadata_operation_failed(struct cache *cache, const char *op, int r)
@@ -1905,6 +1905,7 @@ static void process_deferred_bios(struct work_struct *ws)
 
 		else
 			commit_needed = process_bio(cache, bio) || commit_needed;
+		cond_resched();
 	}
 
 	if (commit_needed)
@@ -1927,6 +1928,7 @@ static void requeue_deferred_bios(struct cache *cache)
 	while ((bio = bio_list_pop(&bios))) {
 		bio->bi_status = BLK_STS_DM_REQUEUE;
 		bio_endio(bio);
+		cond_resched();
 	}
 }
 
@@ -1967,6 +1969,8 @@ static void check_migrations(struct work_struct *ws)
 		r = mg_start(cache, op, NULL);
 		if (r)
 			break;
+
+		cond_resched();
 	}
 }
 
@@ -1987,6 +1991,7 @@ static void destroy(struct cache *cache)
 	if (cache->prison)
 		dm_bio_prison_destroy_v2(cache->prison);
 
+	cancel_delayed_work_sync(&cache->waker);
 	if (cache->wq)
 		destroy_workqueue(cache->wq);
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index e38c713e8..908bf0768 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1661,6 +1661,7 @@ pop_from_list:
 			io = crypt_io_from_node(rb_first(&write_tree));
 			rb_erase(&io->rb_node, &write_tree);
 			kcryptd_io_write(io);
+			cond_resched();
 		} while (!RB_EMPTY_ROOT(&write_tree));
 		blk_finish_plug(&plug);
 	}
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 2fcf62fb2..1f1614af5 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -301,8 +301,11 @@ static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
 	 */
 	bio_for_each_segment(bvec, bio, iter) {
 		if (bio_iter_len(bio, iter) > corrupt_bio_byte) {
-			char *segment = (page_address(bio_iter_page(bio, iter))
-					 + bio_iter_offset(bio, iter));
+			char *segment;
+			struct page *page = bio_iter_page(bio, iter);
+			if (unlikely(page == ZERO_PAGE(0)))
+				break;
+			segment = (page_address(page) + bio_iter_offset(bio, iter));
 			segment[corrupt_bio_byte] = fc->corrupt_bio_value;
 			DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
 				"(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n",
@@ -364,9 +367,11 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		/*
 		 * Corrupt matching writes.
 		 */
-		if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == WRITE)) {
-			if (all_corrupt_bio_flags_match(bio, fc))
-				corrupt_bio_data(bio, fc);
+		if (fc->corrupt_bio_byte) {
+			if (fc->corrupt_bio_rw == WRITE) {
+				if (all_corrupt_bio_flags_match(bio, fc))
+					corrupt_bio_data(bio, fc);
+			}
 			goto map_bio;
 		}
 
@@ -397,13 +402,14 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	}
 
 	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
-		if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
-		    all_corrupt_bio_flags_match(bio, fc)) {
-			/*
-			 * Corrupt successful matching READs while in down state.
-			 */
-			corrupt_bio_data(bio, fc);
-
+		if (fc->corrupt_bio_byte) {
+			if ((fc->corrupt_bio_rw == READ) &&
+			    all_corrupt_bio_flags_match(bio, fc)) {
+				/*
+				 * Corrupt successful matching READs while in down state.
+				 */
+				corrupt_bio_data(bio, fc);
+			}
 		} else if (!test_bit(DROP_WRITES, &fc->flags) &&
 			   !test_bit(ERROR_WRITES, &fc->flags)) {
 			/*
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 3d59f3e20..0eb48e739 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -188,7 +188,7 @@ static int dm_stat_in_flight(struct dm_stat_shared *shared)
 	       atomic_read(&shared->in_flight[WRITE]);
 }
 
-void dm_stats_init(struct dm_stats *stats)
+int dm_stats_init(struct dm_stats *stats)
 {
 	int cpu;
 	struct dm_stats_last_position *last;
@@ -196,11 +196,16 @@ void dm_stats_init(struct dm_stats *stats)
 	mutex_init(&stats->mutex);
 	INIT_LIST_HEAD(&stats->list);
 	stats->last = alloc_percpu(struct dm_stats_last_position);
+	if (!stats->last)
+		return -ENOMEM;
+
 	for_each_possible_cpu(cpu) {
 		last = per_cpu_ptr(stats->last, cpu);
 		last->last_sector = (sector_t)ULLONG_MAX;
 		last->last_rw = UINT_MAX;
 	}
+
+	return 0;
 }
 
 void dm_stats_cleanup(struct dm_stats *stats)
diff --git a/drivers/md/dm-stats.h b/drivers/md/dm-stats.h
index 2ddfae678..dcac11fce 100644
--- a/drivers/md/dm-stats.h
+++ b/drivers/md/dm-stats.h
@@ -22,7 +22,7 @@ struct dm_stats_aux {
 	unsigned long long duration_ns;
 };
 
-void dm_stats_init(struct dm_stats *st);
+int dm_stats_init(struct dm_stats *st);
 void dm_stats_cleanup(struct dm_stats *st);
 
 struct mapped_device;
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index a6a5cee6b..f374f593f 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -660,6 +660,15 @@ 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);
 
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 435a2ee4a..a1bbf00e6 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2222,6 +2222,7 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 			throttle_work_update(&pool->throttle);
 			dm_pool_issue_prefetches(pool->pmd);
 		}
+		cond_resched();
 	}
 	blk_finish_plug(&plug);
 }
@@ -2305,6 +2306,7 @@ static void process_thin_deferred_cells(struct thin_c *tc)
 			else
 				pool->process_cell(tc, cell);
 		}
+		cond_resched();
 	} while (!list_empty(&cells));
 }
 
@@ -2921,6 +2923,8 @@ static void __pool_destroy(struct pool *pool)
 	dm_bio_prison_destroy(pool->prison);
 	dm_kcopyd_client_destroy(pool->copier);
 
+	cancel_delayed_work_sync(&pool->waker);
+	cancel_delayed_work_sync(&pool->no_space_timeout);
 	if (pool->wq)
 		destroy_workqueue(pool->wq);
 
@@ -3361,6 +3365,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	pt->low_water_blocks = low_water_blocks;
 	pt->adjusted_pf = pt->requested_pf = pf;
 	ti->num_flush_bios = 1;
+	ti->limit_swap_bios = true;
 
 	/*
 	 * Only need to enable discards if the pool should pass
@@ -3547,20 +3552,28 @@ static int pool_preresume(struct dm_target *ti)
 	 */
 	r = bind_control_target(pool, ti);
 	if (r)
-		return r;
+		goto out;
 
 	r = maybe_resize_data_dev(ti, &need_commit1);
 	if (r)
-		return r;
+		goto out;
 
 	r = maybe_resize_metadata_dev(ti, &need_commit2);
 	if (r)
-		return r;
+		goto out;
 
 	if (need_commit1 || need_commit2)
 		(void) commit(pool);
+out:
+	/*
+	 * When a thin-pool is PM_FAIL, it cannot be rebuilt if
+	 * bio is in deferred list. Therefore need to return 0
+	 * to allow pool_resume() to flush IO.
+	 */
+	if (r && get_pool_mode(pool) == PM_FAIL)
+		r = 0;
 
-	return 0;
+	return r;
 }
 
 static void pool_suspend_active_thins(struct pool *pool)
@@ -4233,6 +4246,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 
 	ti->num_flush_bios = 1;
+	ti->limit_swap_bios = true;
 	ti->flush_supported = true;
 	ti->per_io_data_size = sizeof(struct dm_thin_endio_hook);
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 324d1dd58..9a9b2adcf 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -279,7 +279,6 @@ out_free_rq_tio_cache:
 
 static void local_exit(void)
 {
-	flush_scheduled_work();
 	destroy_workqueue(deferred_remove_workqueue);
 
 	kmem_cache_destroy(_rq_cache);
@@ -2022,7 +2021,9 @@ static struct mapped_device *alloc_dev(int minor)
 	bio_set_dev(&md->flush_bio, md->bdev);
 	md->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
 
-	dm_stats_init(&md->stats);
+	r = dm_stats_init(&md->stats);
+	if (r < 0)
+		goto bad;
 
 	/* Populate the mapping, nobody knows we exist yet */
 	spin_lock(&_minor_lock);
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 7cf9d34ce..1c4c46278 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -488,7 +488,7 @@ void md_bitmap_print_sb(struct bitmap *bitmap)
 	sb = kmap_atomic(bitmap->storage.sb_page);
 	pr_debug("%s: bitmap file superblock:\n", bmname(bitmap));
 	pr_debug("         magic: %08x\n", le32_to_cpu(sb->magic));
-	pr_debug("       version: %d\n", le32_to_cpu(sb->version));
+	pr_debug("       version: %u\n", le32_to_cpu(sb->version));
 	pr_debug("          uuid: %08x.%08x.%08x.%08x\n",
 		 le32_to_cpu(*(__u32 *)(sb->uuid+0)),
 		 le32_to_cpu(*(__u32 *)(sb->uuid+4)),
@@ -499,11 +499,11 @@ void md_bitmap_print_sb(struct bitmap *bitmap)
 	pr_debug("events cleared: %llu\n",
 		 (unsigned long long) le64_to_cpu(sb->events_cleared));
 	pr_debug("         state: %08x\n", le32_to_cpu(sb->state));
-	pr_debug("     chunksize: %d B\n", le32_to_cpu(sb->chunksize));
-	pr_debug("  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
+	pr_debug("     chunksize: %u B\n", le32_to_cpu(sb->chunksize));
+	pr_debug("  daemon sleep: %us\n", le32_to_cpu(sb->daemon_sleep));
 	pr_debug("     sync size: %llu KB\n",
 		 (unsigned long long)le64_to_cpu(sb->sync_size)/2);
-	pr_debug("max write behind: %d\n", le32_to_cpu(sb->write_behind));
+	pr_debug("max write behind: %u\n", le32_to_cpu(sb->write_behind));
 	kunmap_atomic(sb);
 }
 
@@ -2101,7 +2101,8 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 			bytes = DIV_ROUND_UP(chunks, 8);
 			if (!bitmap->mddev->bitmap_info.external)
 				bytes += sizeof(bitmap_super_t);
-		} while (bytes > (space << 9));
+		} while (bytes > (space << 9) && (chunkshift + BITMAP_BLOCK_SHIFT) <
+			(BITS_PER_BYTE * sizeof(((bitmap_super_t *)0)->chunksize) - 1));
 	} else
 		chunkshift = ffz(~chunksize) - BITMAP_BLOCK_SHIFT;
 
@@ -2146,7 +2147,7 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	bitmap->counts.missing_pages = pages;
 	bitmap->counts.chunkshift = chunkshift;
 	bitmap->counts.chunks = chunks;
-	bitmap->mddev->bitmap_info.chunksize = 1 << (chunkshift +
+	bitmap->mddev->bitmap_info.chunksize = 1UL << (chunkshift +
 						     BITMAP_BLOCK_SHIFT);
 
 	blocks = min(old_counts.chunks << old_counts.chunkshift,
@@ -2172,8 +2173,8 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 				bitmap->counts.missing_pages = old_counts.pages;
 				bitmap->counts.chunkshift = old_counts.chunkshift;
 				bitmap->counts.chunks = old_counts.chunks;
-				bitmap->mddev->bitmap_info.chunksize = 1 << (old_counts.chunkshift +
-									     BITMAP_BLOCK_SHIFT);
+				bitmap->mddev->bitmap_info.chunksize =
+					1UL << (old_counts.chunkshift + BITMAP_BLOCK_SHIFT);
 				blocks = old_counts.chunks << old_counts.chunkshift;
 				pr_warn("Could not pre-allocate in-memory bitmap for cluster raid\n");
 				break;
@@ -2191,20 +2192,23 @@ int md_bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 
 		if (set) {
 			bmc_new = md_bitmap_get_counter(&bitmap->counts, block, &new_blocks, 1);
-			if (*bmc_new == 0) {
-				/* need to set on-disk bits too. */
-				sector_t end = block + new_blocks;
-				sector_t start = block >> chunkshift;
-				start <<= chunkshift;
-				while (start < end) {
-					md_bitmap_file_set_bit(bitmap, block);
-					start += 1 << chunkshift;
+			if (bmc_new) {
+				if (*bmc_new == 0) {
+					/* need to set on-disk bits too. */
+					sector_t end = block + new_blocks;
+					sector_t start = block >> chunkshift;
+
+					start <<= chunkshift;
+					while (start < end) {
+						md_bitmap_file_set_bit(bitmap, block);
+						start += 1 << chunkshift;
+					}
+					*bmc_new = 2;
+					md_bitmap_count_page(&bitmap->counts, block, 1);
+					md_bitmap_set_pending(&bitmap->counts, block);
 				}
-				*bmc_new = 2;
-				md_bitmap_count_page(&bitmap->counts, block, 1);
-				md_bitmap_set_pending(&bitmap->counts, block);
+				*bmc_new |= NEEDED_MASK;
 			}
-			*bmc_new |= NEEDED_MASK;
 			if (new_blocks < old_blocks)
 				old_blocks = new_blocks;
 		}
@@ -2496,6 +2500,9 @@ chunksize_store(struct mddev *mddev, const char *buf, size_t len)
 	if (csize < 512 ||
 	    !is_power_of_2(csize))
 		return -EINVAL;
+	if (BITS_PER_LONG > 32 && csize >= (1ULL << (BITS_PER_BYTE *
+		sizeof(((bitmap_super_t *)0)->chunksize))))
+		return -EOVERFLOW;
 	mddev->bitmap_info.chunksize = csize;
 	return len;
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 38cbde906..f8c111b36 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -417,13 +417,14 @@ static void md_end_flush(struct bio *bio)
 	struct md_rdev *rdev = bio->bi_private;
 	struct mddev *mddev = rdev->mddev;
 
+	bio_put(bio);
+
 	rdev_dec_pending(rdev, mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
 		/* The pre-request flush has finished */
 		queue_work(md_wq, &mddev->flush_work);
 	}
-	bio_put(bio);
 }
 
 static void md_submit_flush_data(struct work_struct *ws);
@@ -821,10 +822,12 @@ static void super_written(struct bio *bio)
 	} else
 		clear_bit(LastDev, &rdev->flags);
 
+	bio_put(bio);
+
+	rdev_dec_pending(rdev, mddev);
+
 	if (atomic_dec_and_test(&mddev->pending_writes))
 		wake_up(&mddev->sb_wait);
-	rdev_dec_pending(rdev, mddev);
-	bio_put(bio);
 }
 
 void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
@@ -2988,6 +2991,9 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		err = kstrtouint(buf, 10, (unsigned int *)&slot);
 		if (err < 0)
 			return err;
+		if (slot < 0)
+			/* overflow */
+			return -ENOSPC;
 	}
 	if (rdev->mddev->pers && slot == -1) {
 		/* Setting 'slot' on an active array requires also
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 876d3e133..0f8b1fb3d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3110,6 +3110,7 @@ static int raid1_run(struct mddev *mddev)
 	 * RAID1 needs at least one disk in active
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
+		md_unregister_thread(&conf->thread);
 		ret = -EINVAL;
 		goto abort;
 	}