When multiple processes write data to the same block group on a compressed
zoned filesystem, the underlying device could report I/O errors and data
corruption is possible.

This happens because on a zoned file system, compressed data writes where
sent to the device via a REQ_OP_WRITE instead of a REQ_OP_ZONE_APPEND
operation. But with REQ_OP_WRITE and parallel submission it cannot be
guaranteed that the data is always submitted aligned to the underlying
zone's write pointer.

The change to using REQ_OP_ZONE_APPEND instead of REQ_OP_WRITE on a zoned
filesystem is non intrusive on a regular file system or when submitting to
a conventional zone on a zoned filesystem, as it is guarded by
btrfs_use_zone_append.

Reported-by: David Sterba <dsterba@suse.com>
Signed-off-by: Johannes Thumshirn <redacted>
---
 fs/btrfs/compression.c | 44 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 40 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 2bea01d23a5b..d27205791483 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c

@@ -28,6 +28,7 @@
 #include "compression.h"
 #include "extent_io.h"
 #include "extent_map.h"
+#include "zoned.h"
 
 static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" };
 

@@ -349,6 +350,7 @@ static void end_compressed_bio_write(struct bio *bio)
 	 */
 	inode = cb->inode;
 	cb->compressed_pages[0]->mapping = cb->inode->i_mapping;
+	btrfs_record_physical_zoned(inode, cb->start, bio);
 	btrfs_writepage_endio_finish_ordered(cb->compressed_pages[0],
 			cb->start, cb->start + cb->len - 1,
 			bio->bi_status == BLK_STS_OK);

@@ -401,6 +403,10 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	u64 first_byte = disk_start;
 	blk_status_t ret;
 	int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
+	struct block_device *bdev;
+	const bool use_append = btrfs_use_zone_append(inode, disk_start);
+	const unsigned int bio_op =
+		use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE;
 
 	WARN_ON(!PAGE_ALIGNED(start));
 	cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);

@@ -418,10 +424,31 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	cb->nr_pages = nr_pages;
 
 	bio = btrfs_bio_alloc(first_byte);
-	bio->bi_opf = REQ_OP_WRITE | write_flags;
+	bio->bi_opf = bio_op | write_flags;
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
 
+	if (use_append) {
+		struct extent_map *em;
+		struct map_lookup *map;
+
+		em = btrfs_get_chunk_map(fs_info, disk_start, PAGE_SIZE);