Merge tag 'for-6.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Fixes:

   - check that subvolume is writable when changing xattrs from security
     namespace

   - fix memory leak in device lookup helper

   - update generation of hole file extent item when merging holes

   - fix space cache corruption and potential double allocations; this
     is a rare bug but can be serious once it happens, stable backports
     and analysis tool will be provided

   - fix error handling when deleting root references

   - fix crash due to assert when attempting to cancel suspended device
     replace, add message what to do if mount fails due to missing
     replace item

  Regressions:

   - don't merge pages into bio if their page offset is not contiguous

   - don't allow large NOWAIT direct reads, this could lead to short
     reads eg. in io_uring"

* tag 'for-6.0-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: add info when mount fails due to stale replace target
  btrfs: replace: drop assert for suspended replace
  btrfs: fix silent failure when deleting root reference
  btrfs: fix space cache corruption and potential double allocations
  btrfs: don't allow large NOWAIT direct reads
  btrfs: don't merge pages into bio if their page offset is not contiguous
  btrfs: update generation of hole file extent item when merging holes
  btrfs: fix possible memory leak in btrfs_get_dev_args_from_path()
  btrfs: check if root is readonly while setting security xattr

11 files changed, 79 insertions, 70 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 993aca2f1e18..e0375ba9d0fe 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -440,39 +440,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 	btrfs_put_caching_control(caching_ctl);
 }
 
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
+static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache,
+				       struct btrfs_caching_control *caching_ctl)
+{
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
+	return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0;
+}
+
+static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *caching_ctl;
-	int ret = 0;
+	int ret;
 
 	caching_ctl = btrfs_get_caching_control(cache);
 	if (!caching_ctl)
 		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
-
-	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
-	if (cache->cached == BTRFS_CACHE_ERROR)
-		ret = -EIO;
+	ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	btrfs_put_caching_control(caching_ctl);
 	return ret;
 }
 
-static bool space_cache_v1_done(struct btrfs_block_group *cache)
-{
-	bool ret;
-
-	spin_lock(&cache->lock);
-	ret = cache->cached != BTRFS_CACHE_FAST;
-	spin_unlock(&cache->lock);
-
-	return ret;
-}
-
-void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
-				struct btrfs_caching_control *caching_ctl)
-{
-	wait_event(caching_ctl->wait, space_cache_v1_done(cache));
-}
-
 #ifdef CONFIG_BTRFS_DEBUG
 static void fragment_free_space(struct btrfs_block_group *block_group)
 {
@@ -750,9 +737,8 @@ done:
 	btrfs_put_block_group(block_group);
 }
 
-int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
 {
-	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_caching_control *caching_ctl = NULL;
 	int ret = 0;
@@ -785,10 +771,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 	}
 	WARN_ON(cache->caching_ctl);
 	cache->caching_ctl = caching_ctl;
-	if (btrfs_test_opt(fs_info, SPACE_CACHE))
-		cache->cached = BTRFS_CACHE_FAST;
-	else
-		cache->cached = BTRFS_CACHE_STARTED;
+	cache->cached = BTRFS_CACHE_STARTED;
 	cache->has_caching_ctl = 1;
 	spin_unlock(&cache->lock);
 
@@ -801,8 +784,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 
 	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
 out:
-	if (load_cache_only && caching_ctl)
-		btrfs_wait_space_cache_v1_finished(cache, caching_ctl);
+	if (wait && caching_ctl)
+		ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	if (caching_ctl)
 		btrfs_put_caching_control(caching_ctl);
 
@@ -3312,7 +3295,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * space back to the block group, otherwise we will leak space.
 		 */
 		if (!alloc && !btrfs_block_group_done(cache))
-			btrfs_cache_block_group(cache, 1);
+			btrfs_cache_block_group(cache, true);
 
 		byte_in_group = bytenr - cache->start;
 		WARN_ON(byte_in_group > cache->length);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 35e0e860cc0b..6b3cdc4cbc41 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -263,9 +263,7 @@ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
-int btrfs_cache_block_group(struct btrfs_block_group *cache,
-			    int load_cache_only);
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4edb4bfb2166..9ef162dbd4bc 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -505,7 +505,6 @@ struct btrfs_free_cluster {
 enum btrfs_caching_type {
 	BTRFS_CACHE_NO,
 	BTRFS_CACHE_STARTED,
-	BTRFS_CACHE_FAST,
 	BTRFS_CACHE_FINISHED,
 	BTRFS_CACHE_ERROR,
 };
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f43196a893ca..41cddd3ff059 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found:
 		 */
 		if (btrfs_find_device(fs_info->fs_devices, &args)) {
 			btrfs_err(fs_info,
-			"replace devid present without an active replace item");
+"replace without active item, run 'device scan --forget' on the target device");
 			ret = -EUCLEAN;
 		} else {
 			dev_replace->srcdev = NULL;
@@ -1129,8 +1129,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		up_write(&dev_replace->rwsem);
 
 		/* Scrub for replace must not be running in suspended state */
-		ret = btrfs_scrub_cancel(fs_info);
-		ASSERT(ret != -ENOTCONN);
+		btrfs_scrub_cancel(fs_info);
 
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ab944d1f94ef..6914cd8024ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2551,17 +2551,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 
 	/*
-	 * pull in the free space cache (if any) so that our pin
-	 * removes the free space from the cache.  We have load_only set
-	 * to one because the slow code to read in the free extents does check
-	 * the pinned extents.
+	 * Fully cache the free space first so that our pin removes the free space
+	 * from the cache.
 	 */
-	btrfs_cache_block_group(cache, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(cache);
+	ret = btrfs_cache_block_group(cache, true);
 	if (ret)
 		goto out;
 
@@ -2584,12 +2577,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 	if (!block_group)
 		return -EINVAL;
 
-	btrfs_cache_block_group(block_group, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(block_group);
+	ret = btrfs_cache_block_group(block_group, true);
 	if (ret)
 		goto out;
 
@@ -4399,7 +4387,7 @@ have_block_group:
 		ffe_ctl->cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl->cached)) {
 			ffe_ctl->have_caching_bg = true;
-			ret = btrfs_cache_block_group(block_group, 0);
+			ret = btrfs_cache_block_group(block_group, false);
 
 			/*
 			 * If we get ENOMEM here or something else we want to
@@ -6169,13 +6157,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 		if (end - start >= range->minlen) {
 			if (!btrfs_block_group_done(cache)) {
-				ret = btrfs_cache_block_group(cache, 0);
-				if (ret) {
-					bg_failed++;
-					bg_ret = ret;
-					continue;
-				}
-				ret = btrfs_wait_block_group_cache_done(cache);
+				ret = btrfs_cache_block_group(cache, true);
 				if (ret) {
 					bg_failed++;
 					bg_ret = ret;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index eed81a7e36a4..cf4f19e80e2f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3233,7 +3233,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	u32 bio_size = bio->bi_iter.bi_size;
 	u32 real_size;
 	const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
-	bool contig;
+	bool contig = false;
 	int ret;
 
 	ASSERT(bio);
@@ -3242,10 +3242,35 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (bio_ctrl->compress_type != compress_type)
 		return 0;
 
-	if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
+
+	if (bio->bi_iter.bi_size == 0) {
+		/* We can always add a page into an empty bio. */
+		contig = true;
+	} else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) {
+		struct bio_vec *bvec = bio_last_bvec_all(bio);
+
+		/*
+		 * The contig check requires the following conditions to be met:
+		 * 1) The pages are belonging to the same inode
+		 *    This is implied by the call chain.
+		 *
+		 * 2) The range has adjacent logical bytenr
+		 *
+		 * 3) The range has adjacent file offset
+		 *    This is required for the usage of btrfs_bio->file_offset.
+		 */
+		if (bio_end_sector(bio) == sector &&
+		    page_offset(bvec->bv_page) + bvec->bv_offset +
+		    bvec->bv_len == page_offset(page) + pg_offset)
+			contig = true;
+	} else {
+		/*
+		 * For compression, all IO should have its logical bytenr
+		 * set to the starting bytenr of the compressed extent.
+		 */
 		contig = bio->bi_iter.bi_sector == sector;
-	else
-		contig = bio_end_sector(bio) == sector;
+	}
+
 	if (!contig)
 		return 0;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 66c822182ecc..5a3f6e0d9688 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2482,6 +2482,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
+		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_mark_buffer_dirty(leaf);
 		goto out;
 	}
@@ -2498,6 +2499,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
+		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_mark_buffer_dirty(leaf);
 		goto out;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f0c97d25b4a0..ad250892028d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7694,6 +7694,20 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	bool unlock_extents = false;
 
 	/*
+	 * We could potentially fault if we have a buffer > PAGE_SIZE, and if
+	 * we're NOWAIT we may submit a bio for a partial range and return
+	 * EIOCBQUEUED, which would result in an errant short read.
+	 *
+	 * The best way to handle this would be to allow for partial completions
+	 * of iocb's, so we could submit the partial bio, return and fault in
+	 * the rest of the pages, and then submit the io for the rest of the
+	 * range.  However we don't have that currently, so simply return
+	 * -EAGAIN at this point so that the normal path is used.
+	 */
+	if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE)
+		return -EAGAIN;
+
+	/*
 	 * Cap the size of reads to that usually seen in buffered I/O as we need
 	 * to allocate a contiguous array for the checksums.
 	 */
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index a64b26b16904..d647cb2938c0 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -349,9 +349,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 	key.offset = ref_id;
 again:
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	if (ret < 0) {
+		err = ret;
 		goto out;
-	if (ret == 0) {
+	} else if (ret == 0) {
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 272901514b0c..064ab2a79c80 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2345,8 +2345,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
 				    &bdev, &disk_super);
-	if (ret)
+	if (ret) {
+		btrfs_put_dev_args_from_path(args);
 		return ret;
+	}
+
 	args->devid = btrfs_stack_device_id(&disk_super->dev_item);
 	memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE);
 	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 7421abcf325a..5bb8d8c86311 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -371,6 +371,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
 				   const char *name, const void *buffer,
 				   size_t size, int flags)
 {
+	if (btrfs_root_readonly(BTRFS_I(inode)->root))
+		return -EROFS;
+
 	name = xattr_full_name(handler, name);
 	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
 }