Merge tag 'vfs-6.13-rc7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - Relax assertions on failure to encode file handles

   The ->encode_fh() method can fail for various reasons. None of them
   warrant a WARN_ON().

 - Fix overlayfs file handle encoding by allowing encoding an fid from
   an inode without an alias

 - Make sure fuse_dir_open() handles FOPEN_KEEP_CACHE. If it's not
   specified fuse needs to invaludate the directory inode page cache

 - Fix qnx6 so it builds with gcc-15

 - Various fixes for netfslib and ceph and nfs filesystems:
     - Ignore silly rename files from afs and nfs when building header
       archives
     - Fix read result collection in netfslib with multiple subrequests
     - Handle ENOMEM for netfslib buffered reads
     - Fix oops in nfs_netfs_init_request()
     - Parse the secctx command immediately in cachefiles
     - Remove a redundant smp_rmb() in netfslib
     - Handle recursion in read retry in netfslib
     - Fix clearing of folio_queue
     - Fix missing cancellation of copy-to_cache when the cache for a
       file is temporarly disabled in netfslib

 - Sanity check the hfs root record

 - Fix zero padding data issues in concurrent write scenarios

 - Fix is_mnt_ns_file() after converting nsfs to path_from_stashed()

 - Fix missing declaration of init_files

 - Increase I/O priority when writing revoke records in jbd2

 - Flush filesystem device before updating tail sequence in jbd2

* tag 'vfs-6.13-rc7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (23 commits)
  ovl: support encoding fid from inode with no alias
  ovl: pass realinode to ovl_encode_real_fh() instead of realdentry
  fuse: respect FOPEN_KEEP_CACHE on opendir
  netfs: Fix is-caching check in read-retry
  netfs: Fix the (non-)cancellation of copy when cache is temporarily disabled
  netfs: Fix ceph copy to cache on write-begin
  netfs: Work around recursion by abandoning retry if nothing read
  netfs: Fix missing barriers by using clear_and_wake_up_bit()
  netfs: Remove redundant use of smp_rmb()
  cachefiles: Parse the "secctx" immediately
  nfs: Fix oops in nfs_netfs_init_request() when copying to cache
  netfs: Fix enomem handling in buffered reads
  netfs: Fix non-contiguous donation between completed reads
  kheaders: Ignore silly-rename files
  fs: relax assertions on failure to encode file handles
  fs: fix missing declaration of init_files
  fs: fix is_mnt_ns_file()
  iomap: fix zero padding data issue in concurrent append writes
  iomap: pass byte granular end position to iomap_add_to_ioend
  jbd2: flush filesystem device before updating tail sequence
  ...

Author: torvalds

fs/9p/vfs_addr.c

@@ -57,6 +57,8 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq)
 	int err, len;
 
 	len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err);
+	if (len > 0)
+		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
 	netfs_write_subrequest_terminated(subreq, len ?: err, false);
 }
 
@@ -80,8 +82,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq)
 	if (pos + total >= i_size_read(rreq->inode))
 		__set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags);
 
-	if (!err)
+	if (!err) {
 		subreq->transferred += total;
+		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
+	}
 
 	netfs_read_subreq_terminated(subreq, err, false);
 }

fs/afs/write.c

@@ -122,7 +122,7 @@ static void afs_issue_write_worker(struct work_struct *work)
 	if (subreq->debug_index == 3)
 		return netfs_write_subrequest_terminated(subreq, -ENOANO, false);
 
-	if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) {
+	if (!subreq->retry_count) {
 		set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
 		return netfs_write_subrequest_terminated(subreq, -EAGAIN, false);
 	}
@@ -149,6 +149,9 @@ static void afs_issue_write_worker(struct work_struct *work)
 	afs_wait_for_operation(op);
 	ret = afs_put_operation(op);
 	switch (ret) {
+	case 0:
+		__set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags);
+		break;
 	case -EACCES:
 	case -EPERM:
 	case -ENOKEY:

fs/cachefiles/daemon.c

@@ -15,6 +15,7 @@
 #include <linux/namei.h>
 #include <linux/poll.h>
 #include <linux/mount.h>
+#include <linux/security.h>
 #include <linux/statfs.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
@@ -576,7 +577,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args)
  */
 static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args)
 {
-	char *secctx;
+	int err;
 
 	_enter(",%s", args);
 
@@ -585,16 +586,16 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args)
 		return -EINVAL;
 	}
 
-	if (cache->secctx) {
+	if (cache->have_secid) {
 		pr_err("Second security context specified\n");
 		return -EINVAL;
 	}
 
-	secctx = kstrdup(args, GFP_KERNEL);
-	if (!secctx)
-		return -ENOMEM;
+	err = security_secctx_to_secid(args, strlen(args), &cache->secid);
+	if (err)
+		return err;
 
-	cache->secctx = secctx;
+	cache->have_secid = true;
 	return 0;
 }
 
@@ -820,7 +821,6 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache)
 	put_cred(cache->cache_cred);
 
 	kfree(cache->rootdirname);
-	kfree(cache->secctx);
 	kfree(cache->tag);
 
 	_leave("");

fs/cachefiles/internal.h

@@ -122,14 +122,15 @@ struct cachefiles_cache {
 #define CACHEFILES_STATE_CHANGED	3	/* T if state changed (poll trigger) */
 #define CACHEFILES_ONDEMAND_MODE	4	/* T if in on-demand read mode */
 	char				*rootdirname;	/* name of cache root directory */
-	char				*secctx;	/* LSM security context */
 	char				*tag;		/* cache binding tag */
 	refcount_t			unbind_pincount;/* refcount to do daemon unbind */
 	struct xarray			reqs;		/* xarray of pending on-demand requests */
 	unsigned long			req_id_next;
 	struct xarray			ondemand_ids;	/* xarray for ondemand_id allocation */
 	u32				ondemand_id_next;
 	u32				msg_id_next;
+	u32				secid;		/* LSM security id */
+	bool				have_secid;	/* whether "secid" was set */
 };
 
 static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache)

fs/cachefiles/security.c

@@ -18,16 +18,16 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache)
 	struct cred *new;
 	int ret;
 
-	_enter("{%s}", cache->secctx);
+	_enter("{%u}", cache->have_secid ? cache->secid : 0);
 
 	new = prepare_kernel_cred(current);
 	if (!new) {
 		ret = -ENOMEM;
 		goto error;
 	}
 
-	if (cache->secctx) {
-		ret = set_security_override_from_ctx(new, cache->secctx);
+	if (cache->have_secid) {
+		ret = set_security_override(new, cache->secid);
 		if (ret < 0) {
 			put_cred(new);
 			pr_err("Security denies permission to nominate security context: error %d\n",

fs/file.c

@@ -22,6 +22,7 @@
 #include <linux/close_range.h>
 #include <linux/file_ref.h>
 #include <net/sock.h>
+#include <linux/init_task.h>
 
 #include "internal.h"
 

fs/fuse/dir.c

@@ -1681,6 +1681,8 @@ static int fuse_dir_open(struct inode *inode, struct file *file)
 		 */
 		if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE))
 			nonseekable_open(inode, file);
+		if (!(ff->open_flags & FOPEN_KEEP_CACHE))
+			invalidate_inode_pages2(inode->i_mapping);
 	}
 
 	return err;

fs/hfs/super.c

@@ -349,11 +349,13 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto bail_no_root;
 	res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd);
 	if (!res) {
-		if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) {
+		if (fd.entrylength != sizeof(rec.dir)) {
 			res =  -EIO;
 			goto bail_hfs_find;
 		}
 		hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength);
+		if (rec.type != HFS_CDR_DIR)
+			res = -EIO;
 	}
 	if (res)
 		goto bail_hfs_find;

fs/iomap/buffered-io.c

@@ -1774,7 +1774,8 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos)
  */
 static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
 		struct writeback_control *wbc, struct folio *folio,
-		struct inode *inode, loff_t pos, unsigned len)
+		struct inode *inode, loff_t pos, loff_t end_pos,
+		unsigned len)
 {
 	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
@@ -1793,15 +1794,60 @@ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
 
 	if (ifs)
 		atomic_add(len, &ifs->write_bytes_pending);
+
+	/*
+	 * Clamp io_offset and io_size to the incore EOF so that ondisk
+	 * file size updates in the ioend completion are byte-accurate.
+	 * This avoids recovering files with zeroed tail regions when
+	 * writeback races with appending writes:
+	 *
+	 *    Thread 1:                  Thread 2:
+	 *    ------------               -----------
+	 *    write [A, A+B]
+	 *    update inode size to A+B
+	 *    submit I/O [A, A+BS]
+	 *                               write [A+B, A+B+C]
+	 *                               update inode size to A+B+C
+	 *    <I/O completes, updates disk size to min(A+B+C, A+BS)>
+	 *    <power failure>
+	 *
+	 *  After reboot:
+	 *    1) with A+B+C < A+BS, the file has zero padding in range
+	 *       [A+B, A+B+C]
+	 *
+	 *    |<     Block Size (BS)   >|
+	 *    |DDDDDDDDDDDD0000000000000|
+	 *    ^           ^        ^
+	 *    A          A+B     A+B+C
+	 *                       (EOF)
+	 *
+	 *    2) with A+B+C > A+BS, the file has zero padding in range
+	 *       [A+B, A+BS]
+	 *
+	 *    |<     Block Size (BS)   >|<     Block Size (BS)    >|
+	 *    |DDDDDDDDDDDD0000000000000|00000000000000000000000000|
+	 *    ^           ^             ^           ^
+	 *    A          A+B           A+BS       A+B+C
+	 *                             (EOF)
+	 *
+	 *    D = Valid Data
+	 *    0 = Zero Padding
+	 *
+	 * Note that this defeats the ability to chain the ioends of
+	 * appending writes.
+	 */
 	wpc->ioend->io_size += len;
+	if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos)
+		wpc->ioend->io_size = end_pos - wpc->ioend->io_offset;
+
 	wbc_account_cgroup_owner(wbc, folio, len);
 	return 0;
 }
 
 static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
 		struct writeback_control *wbc, struct folio *folio,
-		struct inode *inode, u64 pos, unsigned dirty_len,
-		unsigned *count)
+		struct inode *inode, u64 pos, u64 end_pos,
+		unsigned dirty_len, unsigned *count)
 {
 	int error;
 
@@ -1826,7 +1872,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
 			break;
 		default:
 			error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos,
-					map_len);
+					end_pos, map_len);
 			if (!error)
 				(*count)++;
 			break;
@@ -1897,11 +1943,11 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode,
 		 *    remaining memory is zeroed when mapped, and writes to that
 		 *    region are not written out to the file.
 		 *
-		 * Also adjust the writeback range to skip all blocks entirely
-		 * beyond i_size.
+		 * Also adjust the end_pos to the end of file and skip writeback
+		 * for all blocks entirely beyond i_size.
 		 */
 		folio_zero_segment(folio, poff, folio_size(folio));
-		*end_pos = round_up(isize, i_blocksize(inode));
+		*end_pos = isize;
 	}
 
 	return true;
@@ -1914,6 +1960,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	struct inode *inode = folio->mapping->host;
 	u64 pos = folio_pos(folio);
 	u64 end_pos = pos + folio_size(folio);
+	u64 end_aligned = 0;
 	unsigned count = 0;
 	int error = 0;
 	u32 rlen;
@@ -1955,9 +2002,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	/*
 	 * Walk through the folio to find dirty areas to write back.
 	 */
-	while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) {
+	end_aligned = round_up(end_pos, i_blocksize(inode));
+	while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) {
 		error = iomap_writepage_map_blocks(wpc, wbc, folio, inode,
-				pos, rlen, &count);
+				pos, end_pos, rlen, &count);
 		if (error)
 			break;
 		pos += rlen;

fs/jbd2/commit.c

@@ -772,9 +772,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	/*
 	 * If the journal is not located on the file system device,
 	 * then we must flush the file system device before we issue
-	 * the commit record
+	 * the commit record and update the journal tail sequence.
 	 */
-	if (commit_transaction->t_need_data_flush &&
+	if ((commit_transaction->t_need_data_flush || update_tail) &&
 	    (journal->j_fs_dev != journal->j_dev) &&
 	    (journal->j_flags & JBD2_BARRIER))
 		blkdev_issue_flush(journal->j_fs_dev);