vfs-6.17-rc6.fixes

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCaL6SyQAKCRCRxhvAZXjc
 ouTGAQDGiTnaENiOzRhzNl1XONTRv8a1uV0pxg4W3fNdiRlxgQEA/O90/+nM48KC
 pdV3WHz5eGfcnMTpqgHxK6HYgwklJAY=
 =oKnm
 -----END PGP SIGNATURE-----

Merge tag 'vfs-6.17-rc6.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:
 "fuse:

   - Prevent opening of non-regular backing files.

     Fuse doesn't support non-regular files anyway.

   - Check whether copy_file_range() returns a larger size than
     requested.

   - Prevent overflow in copy_file_range() as fuse currently only
     supports 32-bit sized copies.

   - Cache the blocksize value if the server returned a new value as
     inode->i_blkbits isn't modified directly anymore.

   - Fix i_blkbits handling for iomap partial writes.

     By default i_blkbits is set to PAGE_SIZE which causes iomap to mark
     the whole folio as uptodate even on a partial write. But fuseblk
     filesystems support choosing a blocksize smaller than PAGE_SIZE
     risking data corruption. Simply enforce PAGE_SIZE as blocksize for
     fuseblk's internal inode for now.

   - Prevent out-of-bounds acces in fuse_dev_write() when the number of
     bytes to be retrieved is truncated to the fc->max_pages limit.

  virtiofs:

   - Fix page faults for DAX page addresses.

  Misc:

   - Tighten file handle decoding from userns.

     Check that the decoded dentry itself has a valid idmapping in the
     user namespace.

   - Fix mount-notify selftests.

   - Fix some indentation errors.

   - Add an FMODE_ flag to indicate IOCB_HAS_METADATA availability.

     This will be moved to an FOP_* flag with a bit more rework needed
     for that to happen not suitable for a fix.

   - Don't silently ignore metadata for sync read/write.

   - Don't pointlessly log warning when reading coredump sysctls"

* tag 'vfs-6.17-rc6.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fuse: virtio_fs: fix page fault for DAX page address
  selftests/fs/mount-notify: Fix compilation failure.
  fhandle: use more consistent rules for decoding file handle from userns
  fuse: Block access to folio overlimit
  fuse: fix fuseblk i_blkbits for iomap partial writes
  fuse: reflect cached blocksize if blocksize was changed
  fuse: prevent overflow in copy_file_range return value
  fuse: check if copy_file_range() returns larger than requested size
  fuse: do not allow mapping a non-regular backing file
  coredump: don't pointlessly check and spew warnings
  fs: fix indentation style
  block: don't silently ignore metadata for sync read/write
  fs: add a FMODE_ flag to indicate IOCB_HAS_METADATA availability
  Please enter a commit message to explain why this merge is necessary,
  especially if it merges an updated upstream into a topic branch.

block/fops.c

@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
 #include <linux/uio.h>
@@ -54,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	struct bio bio;
 	ssize_t ret;
 
-	WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA);
 	if (nr_pages <= DIO_INLINE_BIO_VECS)
 		vecs = inline_vecs;
 	else {
@@ -131,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio)
 	if (bio->bi_status && !dio->bio.bi_status)
 		dio->bio.bi_status = bio->bi_status;
 
-	if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA))
+	if (bio_integrity(bio))
 		bio_integrity_unmap_user(bio);
 
 	if (atomic_dec_and_test(&dio->ref)) {
@@ -233,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			}
 			bio->bi_opf |= REQ_NOWAIT;
 		}
-		if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) {
+		if (iocb->ki_flags & IOCB_HAS_METADATA) {
 			ret = bio_integrity_map_iter(bio, iocb->private);
 			if (unlikely(ret))
 				goto fail;
@@ -301,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio)
 		ret = blk_status_to_errno(bio->bi_status);
 	}
 
-	if (iocb->ki_flags & IOCB_HAS_METADATA)
+	if (bio_integrity(bio))
 		bio_integrity_unmap_user(bio);
 
 	iocb->ki_complete(iocb, ret);
@@ -422,7 +422,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
-	if (likely(nr_pages <= BIO_MAX_VECS)) {
+	if (likely(nr_pages <= BIO_MAX_VECS &&
+		   !(iocb->ki_flags & IOCB_HAS_METADATA))) {
 		if (is_sync_kiocb(iocb))
 			return __blkdev_direct_IO_simple(iocb, iter, bdev,
 							nr_pages);
@@ -687,6 +688,8 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 
 	if (bdev_can_atomic_write(bdev))
 		filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+	if (blk_get_integrity(bdev->bd_disk))
+		filp->f_mode |= FMODE_HAS_METADATA;
 
 	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
 	if (ret)

fs/coredump.c

@@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write,
 	ssize_t retval;
 	char old_core_pattern[CORENAME_MAX_SIZE];
 
+	if (write)
+		return proc_dostring(table, write, buffer, lenp, ppos);
+
 	retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE);
 
 	error = proc_dostring(table, write, buffer, lenp, ppos);
 	if (error)
 		return error;
+
 	if (!check_coredump_socket()) {
 		strscpy(core_pattern, old_core_pattern, retval + 1);
 		return -EINVAL;

fs/exec.c

@@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ
 {
 	int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (!error)
+	if (!error && !write)
 		validate_coredump_safety();
 	return error;
 }

fs/fhandle.c

@@ -207,6 +207,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
 	if (!ctx->flags)
 		return 1;
 
+	/*
+	 * Verify that the decoded dentry itself has a valid id mapping.
+	 * In case the decoded dentry is the mountfd root itself, this
+	 * verifies that the mountfd inode itself has a valid id mapping.
+	 */
+	if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry)))
+		return 0;
+
 	/*
 	 * It's racy as we're not taking rename_lock but we're able to ignore
 	 * permissions and we just need an approximation whether we were able

fs/fuse/dev.c

@@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode,
 
 	index = outarg->offset >> PAGE_SHIFT;
 
-	while (num) {
+	while (num && ap->num_folios < num_pages) {
 		struct folio *folio;
 		unsigned int folio_offset;
 		unsigned int nr_bytes;

fs/fuse/dir.c

@@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode,
 	if (attr->blksize != 0)
 		blkbits = ilog2(attr->blksize);
 	else
-		blkbits = inode->i_sb->s_blocksize_bits;
+		blkbits = fc->blkbits;
 
 	stat->blksize = 1 << blkbits;
 }
@@ -1377,6 +1377,7 @@ retry:
 		generic_fillattr(idmap, request_mask, inode, stat);
 		stat->mode = fi->orig_i_mode;
 		stat->ino = fi->orig_ino;
+		stat->blksize = 1 << fi->cached_i_blkbits;
 		if (test_bit(FUSE_I_BTIME, &fi->state)) {
 			stat->btime = fi->i_btime;
 			stat->result_mask |= STATX_BTIME;

fs/fuse/file.c

@@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 		.nodeid_out = ff_out->nodeid,
 		.fh_out = ff_out->fh,
 		.off_out = pos_out,
-		.len = len,
+		.len = min_t(size_t, len, UINT_MAX & PAGE_MASK),
 		.flags = flags
 	};
 	struct fuse_write_out outarg;
@@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 		fc->no_copy_file_range = 1;
 		err = -EOPNOTSUPP;
 	}
+	if (!err && outarg.size > len)
+		err = -EIO;
+
 	if (err)
 		goto out;
 

fs/fuse/fuse_i.h

@@ -210,6 +210,12 @@ struct fuse_inode {
 	/** Reference to backing file in passthrough mode */
 	struct fuse_backing *fb;
 #endif
+
+	/*
+	 * The underlying inode->i_blkbits value will not be modified,
+	 * so preserve the blocksize specified by the server.
+	 */
+	u8 cached_i_blkbits;
 };
 
 /** FUSE inode state bits */
@@ -969,6 +975,14 @@ struct fuse_conn {
 		/* Request timeout (in jiffies). 0 = no timeout */
 		unsigned int req_timeout;
 	} timeout;
+
+	/*
+	 * This is a workaround until fuse uses iomap for reads.
+	 * For fuseblk servers, this represents the blocksize passed in at
+	 * mount time and for regular fuse servers, this is equivalent to
+	 * inode->i_blkbits.
+	 */
+	u8 blkbits;
 };
 
 /*

fs/fuse/inode.c

@@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 		}
 	}
 
+	if (attr->blksize)
+		fi->cached_i_blkbits = ilog2(attr->blksize);
+	else
+		fi->cached_i_blkbits = fc->blkbits;
+
 	/*
 	 * Don't set the sticky bit in i_mode, unless we want the VFS
 	 * to check permissions.  This prevents failures due to the
@@ -1805,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 		err = -EINVAL;
 		if (!sb_set_blocksize(sb, ctx->blksize))
 			goto err;
+		/*
+		 * This is a workaround until fuse hooks into iomap for reads.
+		 * Use PAGE_SIZE for the blocksize else if the writeback cache
+		 * is enabled, buffered writes go through iomap and a read may
+		 * overwrite partially written data if blocksize < PAGE_SIZE
+		 */
+		fc->blkbits = sb->s_blocksize_bits;
+		if (ctx->blksize != PAGE_SIZE &&
+		    !sb_set_blocksize(sb, PAGE_SIZE))
+			goto err;
 #endif
 	} else {
 		sb->s_blocksize = PAGE_SIZE;
 		sb->s_blocksize_bits = PAGE_SHIFT;
+		fc->blkbits = sb->s_blocksize_bits;
 	}
 
 	sb->s_subtype = ctx->subtype;

fs/fuse/passthrough.c

@@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
 	if (!file)
 		goto out;
 
+	/* read/write/splice/mmap passthrough only relevant for regular files */
+	res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL;
+	if (!d_is_reg(file->f_path.dentry))
+		goto out_fput;
+
 	backing_sb = file_inode(file)->i_sb;
 	res = -ELOOP;
 	if (backing_sb->s_stack_depth >= fc->max_stack_depth)

fs/fuse/virtio_fs.c

@@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (kaddr)
 		*kaddr = fs->window_kaddr + offset;
 	if (pfn)
-		*pfn = fs->window_phys_addr + offset;
+		*pfn = PHYS_PFN(fs->window_phys_addr + offset);
 	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
 }
 

fs/namespace.c

@@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 			return ERR_PTR(-EINVAL);
 	}
 
-        if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+	if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
 	if (__has_locked_children(old_mnt, path->dentry))

include/linux/fs.h

@@ -149,7 +149,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* Expect random access pattern */
 #define FMODE_RANDOM		((__force fmode_t)(1 << 12))
 
-/* FMODE_* bit 13 */
+/* Supports IOCB_HAS_METADATA */
+#define FMODE_HAS_METADATA	((__force fmode_t)(1 << 13))
 
 /* File is opened with O_PATH; almost nothing can be done with it */
 #define FMODE_PATH		((__force fmode_t)(1 << 14))

io_uring/rw.c

@@ -886,6 +886,9 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	if (req->flags & REQ_F_HAS_METADATA) {
 		struct io_async_rw *io = req->async_data;
 
+		if (!(file->f_mode & FMODE_HAS_METADATA))
+			return -EINVAL;
+
 		/*
 		 * We have a union of meta fields with wpq used for buffered-io
 		 * in io_async_rw, so fail it here.

tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c

@@ -2,6 +2,13 @@
 // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
 
 #define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
 #include <fcntl.h>
 #include <sched.h>
 #include <stdio.h>
@@ -10,20 +17,12 @@
 #include <sys/mount.h>
 #include <unistd.h>
 #include <sys/syscall.h>
+#include <sys/fanotify.h>
 
 #include "../../kselftest_harness.h"
 #include "../statmount/statmount.h"
 #include "../utils.h"
 
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
 static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
 
 static const int mark_cmds[] = {

tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c

@@ -2,6 +2,13 @@
 // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu>
 
 #define _GNU_SOURCE
+
+// Needed for linux/fanotify.h
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+#define __kernel_fsid_t __kernel_fsid_t
+
 #include <fcntl.h>
 #include <sched.h>
 #include <stdio.h>
@@ -10,21 +17,12 @@
 #include <sys/mount.h>
 #include <unistd.h>
 #include <sys/syscall.h>
+#include <sys/fanotify.h>
 
 #include "../../kselftest_harness.h"
-#include "../../pidfd/pidfd.h"
 #include "../statmount/statmount.h"
 #include "../utils.h"
 
-// Needed for linux/fanotify.h
-#ifndef __kernel_fsid_t
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-#endif
-
-#include <sys/fanotify.h>
-
 static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX";
 
 static const int mark_types[] = {