summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--block/fops.c13
-rw-r--r--fs/coredump.c4
-rw-r--r--fs/exec.c2
-rw-r--r--fs/fhandle.c8
-rw-r--r--fs/fuse/dev.c2
-rw-r--r--fs/fuse/dir.c3
-rw-r--r--fs/fuse/file.c5
-rw-r--r--fs/fuse/fuse_i.h14
-rw-r--r--fs/fuse/inode.c16
-rw-r--r--fs/fuse/passthrough.c5
-rw-r--r--fs/fuse/virtio_fs.c2
-rw-r--r--fs/namespace.c2
-rw-r--r--include/linux/fs.h3
-rw-r--r--io_uring/rw.c3
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c17
-rw-r--r--tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c18
16 files changed, 86 insertions, 31 deletions
diff --git a/block/fops.c b/block/fops.c
index 82451ac8ff25..ddbc69c0922b 100644
--- a/block/fops.c
+++ b/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)
diff --git a/fs/coredump.c b/fs/coredump.c
index 5dce257c67fc..60bc9685e149 100644
--- a/fs/coredump.c
+++ b/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;
diff --git a/fs/exec.c b/fs/exec.c
index 2a1e5e4042a1..e861a4b7ffda 100644
--- a/fs/exec.c
+++ b/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;
}
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 68a7d2861c58..a907ddfac4d5 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -208,6 +208,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
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
* to follow a path to the file.
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index e80cd8f2c049..5150aa25e64b 100644
--- a/fs/fuse/dev.c
+++ b/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;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 2d817d7cab26..5c569c3cb53f 100644
--- a/fs/fuse/dir.c
+++ b/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;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5525a4520b0f..4adcf09d4b01 100644
--- a/fs/fuse/file.c
+++ b/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;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index ec248d13c8bf..cc428d04be3e 100644
--- a/fs/fuse/fuse_i.h
+++ b/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;
};
/*
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 67c2318bfc42..7ddfd2b3cc9c 100644
--- a/fs/fuse/inode.c
+++ b/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;
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 607ef735ad4a..eb97ac009e75 100644
--- a/fs/fuse/passthrough.c
+++ b/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)
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index c826e7ca49f5..76c8fd0bfc75 100644
--- a/fs/fuse/virtio_fs.c
+++ b/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;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index ae6d1312b184..51f77c65c0c6 100644
--- a/fs/namespace.c
+++ b/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))
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d7ab4f96d705..601d036a6c78 100644
--- a/include/linux/fs.h
+++ b/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))
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 52a5b950b2e5..af5a54b5db12 100644
--- a/io_uring/rw.c
+++ b/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.
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
index 63ce708d93ed..e4b7c2b457ee 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c
+++ b/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[] = {
diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
index 090a5ca65004..9f57ca46e3af 100644
--- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c
+++ b/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[] = {
generated by cgit v1.2.3 (git 2.39.1) at 2025-09-10 20:54:57 +0000