Merge tag 'vfs-6.11-rc4.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "VFS:

   - Fix the name of file lease slab cache. When file leases were split
     out of file locks the name of the file lock slab cache was used for
     the file leases slab cache as well.

   - Fix a type in take_fd() helper.

   - Fix infinite directory iteration for stable offsets in tmpfs.

   - When the icache is pruned all reclaimable inodes are marked with
     I_FREEING and other processes that try to lookup such inodes will
     block.

     But some filesystems like ext4 can trigger lookups in their inode
     evict callback causing deadlocks. Ext4 does such lookups if the
     ea_inode feature is used whereby a separate inode may be used to
     store xattrs.

     Introduce I_LRU_ISOLATING which pins the inode while its pages are
     reclaimed. This avoids inode deletion during inode_lru_isolate()
     avoiding the deadlock and evict is made to wait until
     I_LRU_ISOLATING is done.

  netfs:

   - Fault in smaller chunks for non-large folio mappings for
     filesystems that haven't been converted to large folios yet.

   - Fix the CONFIG_NETFS_DEBUG config option. The config option was
     renamed a short while ago and that introduced two minor issues.
     First, it depended on CONFIG_NETFS whereas it wants to depend on
     CONFIG_NETFS_SUPPORT. The former doesn't exist, while the latter
     does. Second, the documentation for the config option wasn't fixed
     up.

   - Revert the removal of the PG_private_2 writeback flag as ceph is
     using it and fix how that flag is handled in netfs.

   - Fix DIO reads on 9p. A program watching a file on a 9p mount
     wouldn't see any changes in the size of the file being exported by
     the server if the file was changed directly in the source
     filesystem. Fix this by attempting to read the full size specified
     when a DIO read is requested.

   - Fix a NULL pointer dereference bug due to a data race where a
     cachefiles cookies was retired even though it was still in use.
     Check the cookie's n_accesses counter before discarding it.

  nsfs:

   - Fix ioctl declaration for NS_GET_MNTNS_ID from _IO() to _IOR() as
     the kernel is writing to userspace.

  pidfs:

   - Prevent the creation of pidfds for kthreads until we have a
     use-case for it and we know the semantics we want. It also confuses
     userspace why they can get pidfds for kthreads.

  squashfs:

   - Fix an unitialized value bug reported by KMSAN caused by a
     corrupted symbolic link size read from disk. Check that the
     symbolic link size is not larger than expected"

* tag 'vfs-6.11-rc4.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  Squashfs: sanity check symbolic link size
  9p: Fix DIO read through netfs
  vfs: Don't evict inode under the inode lru traversing context
  netfs: Fix handling of USE_PGPRIV2 and WRITE_TO_CACHE flags
  netfs, ceph: Revert "netfs: Remove deprecated use of PG_private_2 as a second writeback flag"
  file: fix typo in take_fd() comment
  pidfd: prevent creation of pidfds for kthreads
  netfs: clean up after renaming FSCACHE_DEBUG config
  libfs: fix infinite directory reads for offset dir
  nsfs: fix ioctl declaration
  fs/netfs/fscache_cookie: add missing "n_accesses" check
  filelock: fix name of file_lease slab cache
  netfs: Fault in smaller chunks for non-large folio mappings

2 files changed, 25 insertions, 5 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 8c16bc5250ef..c4744a02db75 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req)
 	if (err >= 0) {
 		if (sparse && err > 0)
 			err = ceph_sparse_ext_map_end(op);
-		if (err < subreq->len)
+		if (err < subreq->len &&
+		    subreq->rreq->origin != NETFS_DIO_READ)
 			__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 		if (IS_ENCRYPTED(inode) && err > 0) {
 			err = ceph_fscrypt_decrypt_extents(inode,
@@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq)
 	size_t len;
 	int mode;
 
-	__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
+	if (rreq->origin != NETFS_DIO_READ)
+		__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
 	__clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags);
 
 	if (subreq->start >= inode->i_size)
@@ -424,6 +426,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file)
 	struct ceph_netfs_request_data *priv;
 	int ret = 0;
 
+	/* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
+	__set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags);
+
 	if (rreq->origin != NETFS_READAHEAD)
 		return 0;
 
@@ -498,6 +503,11 @@ const struct netfs_request_ops ceph_netfs_ops = {
 };
 
 #ifdef CONFIG_CEPH_FSCACHE
+static void ceph_set_page_fscache(struct page *page)
+{
+	folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
+}
+
 static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
 {
 	struct inode *inode = priv;
@@ -515,6 +525,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
 			       ceph_fscache_write_terminated, inode, true, caching);
 }
 #else
+static inline void ceph_set_page_fscache(struct page *page)
+{
+}
+
 static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
 {
 }
@@ -706,6 +720,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 		len = wlen;
 
 	set_page_writeback(page);
+	if (caching)
+		ceph_set_page_fscache(page);
 	ceph_fscache_write_to_cache(inode, page_off, len, caching);
 
 	if (IS_ENCRYPTED(inode)) {
@@ -789,6 +805,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
 		return AOP_WRITEPAGE_ACTIVATE;
 	}
 
+	folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
+
 	err = writepage_nounlock(page, wbc);
 	if (err == -ERESTARTSYS) {
 		/* direct memory reclaimer was killed by SIGKILL. return 0
@@ -1062,7 +1080,8 @@ get_more_pages:
 				unlock_page(page);
 				break;
 			}
-			if (PageWriteback(page)) {
+			if (PageWriteback(page) ||
+			    PagePrivate2(page) /* [DEPRECATED] */) {
 				if (wbc->sync_mode == WB_SYNC_NONE) {
 					doutc(cl, "%p under writeback\n", page);
 					unlock_page(page);
@@ -1070,6 +1089,7 @@ get_more_pages:
 				}
 				doutc(cl, "waiting on writeback %p\n", page);
 				wait_on_page_writeback(page);
+				folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
 			}
 
 			if (!clear_page_dirty_for_io(page)) {
@@ -1254,6 +1274,8 @@ new_request:
 			}
 
 			set_page_writeback(page);
+			if (caching)
+				ceph_set_page_fscache(page);
 			len += thp_size(page);
 		}
 		ceph_fscache_write_to_cache(inode, offset, len, caching);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8f8de8f33abb..71cd70514efa 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 
 	/* Set parameters for the netfs library */
 	netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false);
-	/* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */
-	__set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags);
 
 	spin_lock_init(&ci->i_ceph_lock);