Merge tag 'xfs-6.2-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull XFS updates from Darrick Wong:
 "The highlight of this is a batch of fixes for the online metadata
  checking code as we start the loooong march towards merging online
  repair. I aim to merge that in time for the 2023 LTS.

  There are also a large number of data corruption and race condition
  fixes in this patchset. Most notably fixed are write() calls to
  unwritten extents racing with writeback, which required some late(r
  than I prefer) code changes to iomap to support the necessary
  revalidations. I don't really like iomap changes going in past -rc4,
  but Dave and I have been working on it long enough that I chose to
  push it for 6.2 anyway.

  There are also a number of other subtle problems fixed, including the
  log racing with inode writeback to write inodes with incorrect link
  count to disk; file data mapping corruptions as a result of incorrect
  lock cycling when attaching dquots; refcount metadata corruption if
  one actually manages to share a block 2^32 times; and the log
  clobbering cow staging extents if they were formerly metadata blocks.

  Summary:

   - Fix a race condition w.r.t. percpu inode free counters

   - Fix a broken error return in xfs_remove

   - Print FS UUID at mount/unmount time

   - Numerous fixes to the online fsck code

   - Fix inode locking inconsistency problems when dealing with realtime
     metadata files

   - Actually merge pull requests so that we capture the cover letter
     contents

   - Fix a race between rebuilding VFS inode state and the AIL flushing
     inodes that could cause corrupt inodes to be written to the
     filesystem

   - Fix a data corruption problem resulting from a write() to an
     unwritten extent racing with writeback started on behalf of memory
     reclaim changing the extent state

   - Add debugging knobs so that we can test iomap invalidation

   - Fix the blockdev pagecache contents being stale after unmounting
     the filesystem, leading to spurious xfs_db errors and corrupt
     metadumps

   - Fix a file mapping corruption bug due to ilock cycling when
     attaching dquots to a file during delalloc reservation

   - Fix a refcount btree corruption problem due to the refcount
     adjustment code not handling MAXREFCOUNT correctly, resulting in
     unnecessary record splits

   - Fix COW staging extent alloctions not being classified as USERDATA,
     which results in filestreams being ignored and possible data
     corruption if the allocation was filled from the AGFL and the block
     buffer is still being tracked in the AIL

   - Fix new duplicated includes

   - Fix a race between the dquot shrinker and dquot freeing that could
     cause a UAF"

* tag 'xfs-6.2-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (50 commits)
  xfs: dquot shrinker doesn't check for XFS_DQFLAG_FREEING
  xfs: Remove duplicated include in xfs_iomap.c
  xfs: invalidate xfs_bufs when allocating cow extents
  xfs: get rid of assert from xfs_btree_islastblock
  xfs: estimate post-merge refcounts correctly
  xfs: hoist refcount record merge predicates
  xfs: fix super block buf log item UAF during force shutdown
  xfs: wait iclog complete before tearing down AIL
  xfs: attach dquots to inode before reading data/cow fork mappings
  xfs: shut up -Wuninitialized in xfsaild_push
  xfs: use memcpy, not strncpy, to format the attr prefix during listxattr
  xfs: invalidate block device page cache during unmount
  xfs: add debug knob to slow down write for fun
  xfs: add debug knob to slow down writeback for fun
  xfs: drop write error injection is unfixable, remove it
  xfs: use iomap_valid method to detect stale cached iomaps
  iomap: write iomap validity checks
  xfs: xfs_bmap_punch_delalloc_range() should take a byte range
  iomap: buffered write failure should not truncate the page cache
  xfs,iomap: move delalloc punching to iomap
  ...

1 files changed, 39 insertions, 7 deletions

diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 822e6a0e9d1a..ae082808cfed 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -46,7 +46,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_REFCOUNT_FINISH_ONE,
 	XFS_RANDOM_BMAP_FINISH_ONE,
 	XFS_RANDOM_AG_RESV_CRITICAL,
-	XFS_RANDOM_DROP_WRITES,
+	0, /* XFS_RANDOM_DROP_WRITES has been removed */
 	XFS_RANDOM_LOG_BAD_CRC,
 	XFS_RANDOM_LOG_ITEM_PIN,
 	XFS_RANDOM_BUF_LRU_REF,
@@ -60,6 +60,8 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_LARP,
 	XFS_RANDOM_DA_LEAF_SPLIT,
 	XFS_RANDOM_ATTR_LEAF_TO_NODE,
+	XFS_RANDOM_WB_DELAY_MS,
+	XFS_RANDOM_WRITE_DELAY_MS,
 };
 
 struct xfs_errortag_attr {
@@ -162,7 +164,6 @@ XFS_ERRORTAG_ATTR_RW(refcount_continue_update,	XFS_ERRTAG_REFCOUNT_CONTINUE_UPDA
 XFS_ERRORTAG_ATTR_RW(refcount_finish_one,	XFS_ERRTAG_REFCOUNT_FINISH_ONE);
 XFS_ERRORTAG_ATTR_RW(bmap_finish_one,	XFS_ERRTAG_BMAP_FINISH_ONE);
 XFS_ERRORTAG_ATTR_RW(ag_resv_critical,	XFS_ERRTAG_AG_RESV_CRITICAL);
-XFS_ERRORTAG_ATTR_RW(drop_writes,	XFS_ERRTAG_DROP_WRITES);
 XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
 XFS_ERRORTAG_ATTR_RW(log_item_pin,	XFS_ERRTAG_LOG_ITEM_PIN);
 XFS_ERRORTAG_ATTR_RW(buf_lru_ref,	XFS_ERRTAG_BUF_LRU_REF);
@@ -176,6 +177,8 @@ XFS_ERRORTAG_ATTR_RW(ag_resv_fail, XFS_ERRTAG_AG_RESV_FAIL);
 XFS_ERRORTAG_ATTR_RW(larp,		XFS_ERRTAG_LARP);
 XFS_ERRORTAG_ATTR_RW(da_leaf_split,	XFS_ERRTAG_DA_LEAF_SPLIT);
 XFS_ERRORTAG_ATTR_RW(attr_leaf_to_node,	XFS_ERRTAG_ATTR_LEAF_TO_NODE);
+XFS_ERRORTAG_ATTR_RW(wb_delay_ms,	XFS_ERRTAG_WB_DELAY_MS);
+XFS_ERRORTAG_ATTR_RW(write_delay_ms,	XFS_ERRTAG_WRITE_DELAY_MS);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -206,7 +209,6 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(refcount_finish_one),
 	XFS_ERRORTAG_ATTR_LIST(bmap_finish_one),
 	XFS_ERRORTAG_ATTR_LIST(ag_resv_critical),
-	XFS_ERRORTAG_ATTR_LIST(drop_writes),
 	XFS_ERRORTAG_ATTR_LIST(log_bad_crc),
 	XFS_ERRORTAG_ATTR_LIST(log_item_pin),
 	XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
@@ -220,6 +222,8 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(larp),
 	XFS_ERRORTAG_ATTR_LIST(da_leaf_split),
 	XFS_ERRORTAG_ATTR_LIST(attr_leaf_to_node),
+	XFS_ERRORTAG_ATTR_LIST(wb_delay_ms),
+	XFS_ERRORTAG_ATTR_LIST(write_delay_ms),
 	NULL,
 };
 ATTRIBUTE_GROUPS(xfs_errortag);
@@ -256,6 +260,32 @@ xfs_errortag_del(
 	kmem_free(mp->m_errortag);
 }
 
+static bool
+xfs_errortag_valid(
+	unsigned int		error_tag)
+{
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return false;
+
+	/* Error out removed injection types */
+	if (error_tag == XFS_ERRTAG_DROP_WRITES)
+		return false;
+	return true;
+}
+
+bool
+xfs_errortag_enabled(
+	struct xfs_mount	*mp,
+	unsigned int		tag)
+{
+	if (!mp->m_errortag)
+		return false;
+	if (!xfs_errortag_valid(tag))
+		return false;
+
+	return mp->m_errortag[tag] != 0;
+}
+
 bool
 xfs_errortag_test(
 	struct xfs_mount	*mp,
@@ -277,7 +307,9 @@ xfs_errortag_test(
 	if (!mp->m_errortag)
 		return false;
 
-	ASSERT(error_tag < XFS_ERRTAG_MAX);
+	if (!xfs_errortag_valid(error_tag))
+		return false;
+
 	randfactor = mp->m_errortag[error_tag];
 	if (!randfactor || get_random_u32_below(randfactor))
 		return false;
@@ -293,7 +325,7 @@ xfs_errortag_get(
 	struct xfs_mount	*mp,
 	unsigned int		error_tag)
 {
-	if (error_tag >= XFS_ERRTAG_MAX)
+	if (!xfs_errortag_valid(error_tag))
 		return -EINVAL;
 
 	return mp->m_errortag[error_tag];
@@ -305,7 +337,7 @@ xfs_errortag_set(
 	unsigned int		error_tag,
 	unsigned int		tag_value)
 {
-	if (error_tag >= XFS_ERRTAG_MAX)
+	if (!xfs_errortag_valid(error_tag))
 		return -EINVAL;
 
 	mp->m_errortag[error_tag] = tag_value;
@@ -319,7 +351,7 @@ xfs_errortag_add(
 {
 	BUILD_BUG_ON(ARRAY_SIZE(xfs_errortag_random_default) != XFS_ERRTAG_MAX);
 
-	if (error_tag >= XFS_ERRTAG_MAX)
+	if (!xfs_errortag_valid(error_tag))
 		return -EINVAL;
 
 	return xfs_errortag_set(mp, error_tag,