summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS9
-rw-r--r--fs/Kconfig4
-rw-r--r--fs/Makefile1
-rw-r--r--fs/backing-file.c336
-rw-r--r--fs/open.c38
-rw-r--r--fs/overlayfs/Kconfig1
-rw-r--r--fs/overlayfs/file.c245
-rw-r--r--fs/overlayfs/overlayfs.h8
-rw-r--r--fs/overlayfs/super.c11
-rw-r--r--include/linux/backing-file.h42
-rw-r--r--include/linux/fs.h3
11 files changed, 435 insertions, 263 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 97f51d5ec1cf..d9ae2688f5c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8186,6 +8186,15 @@ S: Supported
F: fs/iomap/
F: include/linux/iomap.h
+FILESYSTEMS [STACKABLE]
+M: Miklos Szeredi <miklos@szeredi.hu>
+M: Amir Goldstein <amir73il@gmail.com>
+L: linux-fsdevel@vger.kernel.org
+L: linux-unionfs@vger.kernel.org
+S: Maintained
+F: fs/backing-file.c
+F: include/linux/backing-file.h
+
FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
M: Riku Voipio <riku.voipio@iki.fi>
L: linux-hwmon@vger.kernel.org
diff --git a/fs/Kconfig b/fs/Kconfig
index fd1f655b4f1f..c47fa4eb9282 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -18,6 +18,10 @@ config VALIDATE_FS_PARSER
config FS_IOMAP
bool
+# Stackable filesystems
+config FS_STACK
+ bool
+
config BUFFER_HEAD
bool
diff --git a/fs/Makefile b/fs/Makefile
index 75522f88e763..a6962c588962 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o
obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o
obj-$(CONFIG_BINFMT_FLAT) += binfmt_flat.o
+obj-$(CONFIG_FS_STACK) += backing-file.o
obj-$(CONFIG_FS_MBCACHE) += mbcache.o
obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o
obj-$(CONFIG_NFS_COMMON) += nfs_common/
diff --git a/fs/backing-file.c b/fs/backing-file.c
new file mode 100644
index 000000000000..a681f38d84d8
--- /dev/null
+++ b/fs/backing-file.c
@@ -0,0 +1,336 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Forked from fs/overlayfs/file.c.
+ *
+ * Copyright (C) 2017 Red Hat, Inc.
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#include <linux/fs.h>
+#include <linux/backing-file.h>
+#include <linux/splice.h>
+#include <linux/mm.h>
+
+#include "internal.h"
+
+/**
+ * backing_file_open - open a backing file for kernel internal use
+ * @user_path: path that the user reuqested to open
+ * @flags: open flags
+ * @real_path: path of the backing file
+ * @cred: credentials for open
+ *
+ * Open a backing file for a stackable filesystem (e.g., overlayfs).
+ * @user_path may be on the stackable filesystem and @real_path on the
+ * underlying filesystem. In this case, we want to be able to return the
+ * @user_path of the stackable filesystem. This is done by embedding the
+ * returned file into a container structure that also stores the stacked
+ * file's path, which can be retrieved using backing_file_user_path().
+ */
+struct file *backing_file_open(const struct path *user_path, int flags,
+ const struct path *real_path,
+ const struct cred *cred)
+{
+ struct file *f;
+ int error;
+
+ f = alloc_empty_backing_file(flags, cred);
+ if (IS_ERR(f))
+ return f;
+
+ path_get(user_path);
+ *backing_file_user_path(f) = *user_path;
+ error = vfs_open(real_path, f);
+ if (error) {
+ fput(f);
+ f = ERR_PTR(error);
+ }
+
+ return f;
+}
+EXPORT_SYMBOL_GPL(backing_file_open);
+
+struct backing_aio {
+ struct kiocb iocb;
+ refcount_t ref;
+ struct kiocb *orig_iocb;
+ /* used for aio completion */
+ void (*end_write)(struct file *);
+ struct work_struct work;
+ long res;
+};
+
+static struct kmem_cache *backing_aio_cachep;
+
+#define BACKING_IOCB_MASK \
+ (IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
+
+static rwf_t iocb_to_rw_flags(int flags)
+{
+ return (__force rwf_t)(flags & BACKING_IOCB_MASK);
+}
+
+static void backing_aio_put(struct backing_aio *aio)
+{
+ if (refcount_dec_and_test(&aio->ref)) {
+ fput(aio->iocb.ki_filp);
+ kmem_cache_free(backing_aio_cachep, aio);
+ }
+}
+
+static void backing_aio_cleanup(struct backing_aio *aio, long res)
+{
+ struct kiocb *iocb = &aio->iocb;
+ struct kiocb *orig_iocb = aio->orig_iocb;
+
+ if (aio->end_write)
+ aio->end_write(orig_iocb->ki_filp);
+
+ orig_iocb->ki_pos = iocb->ki_pos;
+ backing_aio_put(aio);
+}
+
+static void backing_aio_rw_complete(struct kiocb *iocb, long res)
+{
+ struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+ struct kiocb *orig_iocb = aio->orig_iocb;
+
+ if (iocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(iocb);
+
+ backing_aio_cleanup(aio, res);
+ orig_iocb->ki_complete(orig_iocb, res);
+}
+
+static void backing_aio_complete_work(struct work_struct *work)
+{
+ struct backing_aio *aio = container_of(work, struct backing_aio, work);
+
+ backing_aio_rw_complete(&aio->iocb, aio->res);
+}
+
+static void backing_aio_queue_completion(struct kiocb *iocb, long res)
+{
+ struct backing_aio *aio = container_of(iocb, struct backing_aio, iocb);
+
+ /*
+ * Punt to a work queue to serialize updates of mtime/size.
+ */
+ aio->res = res;
+ INIT_WORK(&aio->work, backing_aio_complete_work);
+ queue_work(file_inode(aio->orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
+ &aio->work);
+}
+
+static int backing_aio_init_wq(struct kiocb *iocb)
+{
+ struct super_block *sb = file_inode(iocb->ki_filp)->i_sb;
+
+ if (sb->s_dio_done_wq)
+ return 0;
+
+ return sb_init_dio_done_wq(sb);
+}
+
+
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+ struct kiocb *iocb, int flags,
+ struct backing_file_ctx *ctx)
+{
+ struct backing_aio *aio = NULL;
+ const struct cred *old_cred;
+ ssize_t ret;
+
+ if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+ return -EIO;
+
+ if (!iov_iter_count(iter))
+ return 0;
+
+ if (iocb->ki_flags & IOCB_DIRECT &&
+ !(file->f_mode & FMODE_CAN_ODIRECT))
+ return -EINVAL;
+
+ old_cred = override_creds(ctx->cred);
+ if (is_sync_kiocb(iocb)) {
+ rwf_t rwf = iocb_to_rw_flags(flags);
+
+ ret = vfs_iter_read(file, iter, &iocb->ki_pos, rwf);
+ } else {
+ ret = -ENOMEM;
+ aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+ if (!aio)
+ goto out;
+
+ aio->orig_iocb = iocb;
+ kiocb_clone(&aio->iocb, iocb, get_file(file));
+ aio->iocb.ki_complete = backing_aio_rw_complete;
+ refcount_set(&aio->ref, 2);
+ ret = vfs_iocb_iter_read(file, &aio->iocb, iter);
+ backing_aio_put(aio);
+ if (ret != -EIOCBQUEUED)
+ backing_aio_cleanup(aio, ret);
+ }
+out:
+ revert_creds(old_cred);
+
+ if (ctx->accessed)
+ ctx->accessed(ctx->user_file);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_read_iter);
+
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+ struct kiocb *iocb, int flags,
+ struct backing_file_ctx *ctx)
+{
+ const struct cred *old_cred;
+ ssize_t ret;
+
+ if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
+ return -EIO;
+
+ if (!iov_iter_count(iter))
+ return 0;
+
+ ret = file_remove_privs(ctx->user_file);
+ if (ret)
+ return ret;
+
+ if (iocb->ki_flags & IOCB_DIRECT &&
+ !(file->f_mode & FMODE_CAN_ODIRECT))
+ return -EINVAL;
+
+ /*
+ * Stacked filesystems don't support deferred completions, don't copy
+ * this property in case it is set by the issuer.
+ */
+ flags &= ~IOCB_DIO_CALLER_COMP;
+
+ old_cred = override_creds(ctx->cred);
+ if (is_sync_kiocb(iocb)) {
+ rwf_t rwf = iocb_to_rw_flags(flags);
+
+ ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf);
+ if (ctx->end_write)
+ ctx->end_write(ctx->user_file);
+ } else {
+ struct backing_aio *aio;
+
+ ret = backing_aio_init_wq(iocb);
+ if (ret)
+ goto out;
+
+ ret = -ENOMEM;
+ aio = kmem_cache_zalloc(backing_aio_cachep, GFP_KERNEL);
+ if (!aio)
+ goto out;
+
+ aio->orig_iocb = iocb;
+ aio->end_write = ctx->end_write;
+ kiocb_clone(&aio->iocb, iocb, get_file(file));
+ aio->iocb.ki_flags = flags;
+ aio->iocb.ki_complete = backing_aio_queue_completion;
+ refcount_set(&aio->ref, 2);
+ ret = vfs_iocb_iter_write(file, &aio->iocb, iter);
+ backing_aio_put(aio);
+ if (ret != -EIOCBQUEUED)
+ backing_aio_cleanup(aio, ret);
+ }
+out:
+ revert_creds(old_cred);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_write_iter);
+
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags,
+ struct backing_file_ctx *ctx)
+{
+ const struct cred *old_cred;
+ ssize_t ret;
+
+ if (WARN_ON_ONCE(!(in->f_mode & FMODE_BACKING)))
+ return -EIO;
+
+ old_cred = override_creds(ctx->cred);
+ ret = vfs_splice_read(in, ppos, pipe, len, flags);
+ revert_creds(old_cred);
+
+ if (ctx->accessed)
+ ctx->accessed(ctx->user_file);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_read);
+
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos, size_t len,
+ unsigned int flags,
+ struct backing_file_ctx *ctx)
+{
+ const struct cred *old_cred;
+ ssize_t ret;
+
+ if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
+ return -EIO;
+
+ ret = file_remove_privs(ctx->user_file);
+ if (ret)
+ return ret;
+
+ old_cred = override_creds(ctx->cred);
+ file_start_write(out);
+ ret = iter_file_splice_write(pipe, out, ppos, len, flags);
+ file_end_write(out);
+ revert_creds(old_cred);
+
+ if (ctx->end_write)
+ ctx->end_write(ctx->user_file);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_splice_write);
+
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+ struct backing_file_ctx *ctx)
+{
+ const struct cred *old_cred;
+ int ret;
+
+ if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)) ||
+ WARN_ON_ONCE(ctx->user_file != vma->vm_file))
+ return -EIO;
+
+ if (!file->f_op->mmap)
+ return -ENODEV;
+
+ vma_set_file(vma, file);
+
+ old_cred = override_creds(ctx->cred);
+ ret = call_mmap(vma->vm_file, vma);
+ revert_creds(old_cred);
+
+ if (ctx->accessed)
+ ctx->accessed(ctx->user_file);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(backing_file_mmap);
+
+static int __init backing_aio_init(void)
+{
+ backing_aio_cachep = kmem_cache_create("backing_aio",
+ sizeof(struct backing_aio),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!backing_aio_cachep)
+ return -ENOMEM;
+
+ return 0;
+}
+fs_initcall(backing_aio_init);
diff --git a/fs/open.c b/fs/open.c
index d877228d5939..a75054237437 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1184,44 +1184,6 @@ struct file *kernel_file_open(const struct path *path, int flags,
}
EXPORT_SYMBOL_GPL(kernel_file_open);
-/**
- * backing_file_open - open a backing file for kernel internal use
- * @user_path: path that the user reuqested to open
- * @flags: open flags
- * @real_path: path of the backing file
- * @cred: credentials for open
- *
- * Open a backing file for a stackable filesystem (e.g., overlayfs).
- * @user_path may be on the stackable filesystem and @real_path on the
- * underlying filesystem. In this case, we want to be able to return the
- * @user_path of the stackable filesystem. This is done by embedding the
- * returned file into a container structure that also stores the stacked
- * file's path, which can be retrieved using backing_file_user_path().
- */
-struct file *backing_file_open(const struct path *user_path, int flags,
- const struct path *real_path,
- const struct cred *cred)
-{
- struct file *f;
- int error;
-
- f = alloc_empty_backing_file(flags, cred);
- if (IS_ERR(f))
- return f;
-
- path_get(user_path);
- *backing_file_user_path(f) = *user_path;
- f->f_path = *real_path;
- error = do_dentry_open(f, d_inode(real_path->dentry), NULL);
- if (error) {
- fput(f);
- f = ERR_PTR(error);
- }
-
- return f;
-}
-EXPORT_SYMBOL_GPL(backing_file_open);
-
#define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE))
#define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC)
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index fec5020c3495..2ac67e04a6fb 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
config OVERLAY_FS
tristate "Overlay filesystem support"
+ select FS_STACK
select EXPORTFS
help
An overlay filesystem combines two filesystems - an 'upper' filesystem
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4e46420c8fdd..05536964d37f 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -9,25 +9,11 @@
#include <linux/xattr.h>
#include <linux/uio.h>
#include <linux/uaccess.h>
-#include <linux/splice.h>
#include <linux/security.h>
-#include <linux/mm.h>
#include <linux/fs.h>
+#include <linux/backing-file.h>
#include "overlayfs.h"
-#include "../internal.h" /* for sb_init_dio_done_wq */
-
-struct ovl_aio_req {
- struct kiocb iocb;
- refcount_t ref;
- struct kiocb *orig_iocb;
- /* used for aio completion */
- struct work_struct work;
- long res;
-};
-
-static struct kmem_cache *ovl_aio_request_cachep;
-
static char ovl_whatisit(struct inode *inode, struct inode *realinode)
{
if (realinode != ovl_inode_upper(inode))
@@ -274,84 +260,16 @@ static void ovl_file_accessed(struct file *file)
touch_atime(&file->f_path);
}
-#define OVL_IOCB_MASK \
- (IOCB_NOWAIT | IOCB_HIPRI | IOCB_DSYNC | IOCB_SYNC | IOCB_APPEND)
-
-static rwf_t iocb_to_rw_flags(int flags)
-{
- return (__force rwf_t)(flags & OVL_IOCB_MASK);
-}
-
-static inline void ovl_aio_put(struct ovl_aio_req *aio_req)
-{
- if (refcount_dec_and_test(&aio_req->ref)) {
- fput(aio_req->iocb.ki_filp);
- kmem_cache_free(ovl_aio_request_cachep, aio_req);
- }
-}
-
-static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
-{
- struct kiocb *iocb = &aio_req->iocb;
- struct kiocb *orig_iocb = aio_req->orig_iocb;
-
- if (iocb->ki_flags & IOCB_WRITE)
- ovl_file_modified(orig_iocb->ki_filp);
-
- orig_iocb->ki_pos = iocb->ki_pos;
- ovl_aio_put(aio_req);
-}
-
-static void ovl_aio_rw_complete(struct kiocb *iocb, long res)
-{
- struct ovl_aio_req *aio_req = container_of(iocb,
- struct ovl_aio_req, iocb);
- struct kiocb *orig_iocb = aio_req->orig_iocb;
-
- if (iocb->ki_flags & IOCB_WRITE)
- kiocb_end_write(iocb);
-
- ovl_aio_cleanup_handler(aio_req);
- orig_iocb->ki_complete(orig_iocb, res);
-}
-
-static void ovl_aio_complete_work(struct work_struct *work)
-{
- struct ovl_aio_req *aio_req = container_of(work,
- struct ovl_aio_req, work);
-
- ovl_aio_rw_complete(&aio_req->iocb, aio_req->res);
-}
-
-static void ovl_aio_queue_completion(struct kiocb *iocb, long res)
-{
- struct ovl_aio_req *aio_req = container_of(iocb,
- struct ovl_aio_req, iocb);
- struct kiocb *orig_iocb = aio_req->orig_iocb;
-
- /*
- * Punt to a work queue to serialize updates of mtime/size.
- */
- aio_req->res = res;
- INIT_WORK(&aio_req->work, ovl_aio_complete_work);
- queue_work(file_inode(orig_iocb->ki_filp)->i_sb->s_dio_done_wq,
- &aio_req->work);
-}
-
-static int ovl_init_aio_done_wq(struct super_block *sb)
-{
- if (sb->s_dio_done_wq)
- return 0;
-
- return sb_init_dio_done_wq(sb);
-}
-
static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct fd real;
- const struct cred *old_cred;
ssize_t ret;
+ struct backing_file_ctx ctx = {
+ .cred = ovl_creds(file_inode(file)->i_sb),
+ .user_file = file,
+ .accessed = ovl_file_accessed,
+ };
if (!iov_iter_count(iter))
return 0;
@@ -360,37 +278,8 @@ static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
if (ret)
return ret;
- ret = -EINVAL;
- if (iocb->ki_flags & IOCB_DIRECT &&
- !(real.file->f_mode & FMODE_CAN_ODIRECT))
- goto out_fdput;
-
- old_cred = ovl_override_creds(file_inode(file)->i_sb);
- if (is_sync_kiocb(iocb)) {
- rwf_t rwf = iocb_to_rw_flags(iocb->ki_flags);
-
- ret = vfs_iter_read(real.file, iter, &iocb->ki_pos, rwf);
- } else {
- struct ovl_aio_req *aio_req;
-
- ret = -ENOMEM;
- aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
- if (!aio_req)
- goto out;
-
- aio_req->orig_iocb = iocb;
- kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
- aio_req->iocb.ki_complete = ovl_aio_rw_complete;
- refcount_set(&aio_req->ref, 2);
- ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);
- ovl_aio_put(aio_req);
- if (ret != -EIOCBQUEUED)
- ovl_aio_cleanup_handler(aio_req);
- }
-out:
- revert_creds(old_cred);
- ovl_file_accessed(file);
-out_fdput:
+ ret = backing_file_read_iter(real.file, iter, iocb, iocb->ki_flags,
+ &ctx);
fdput(real);
return ret;
@@ -401,9 +290,13 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct fd real;
- const struct cred *old_cred;
ssize_t ret;
int ifl = iocb->ki_flags;
+ struct backing_file_ctx ctx = {
+ .cred = ovl_creds(inode->i_sb),
+ .user_file = file,
+ .end_write = ovl_file_modified,
+ };
if (!iov_iter_count(iter))
return 0;
@@ -411,19 +304,11 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
inode_lock(inode);
/* Update mode */
ovl_copyattr(inode);
- ret = file_remove_privs(file);
- if (ret)
- goto out_unlock;
ret = ovl_real_fdget(file, &real);
if (ret)
goto out_unlock;
- ret = -EINVAL;
- if (iocb->ki_flags & IOCB_DIRECT &&
- !(real.file->f_mode & FMODE_CAN_ODIRECT))
- goto out_fdput;
-
if (!ovl_should_sync(OVL_FS(inode->i_sb)))
ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
@@ -432,39 +317,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
* this property in case it is set by the issuer.
*/
ifl &= ~IOCB_DIO_CALLER_COMP;
-
- old_cred = ovl_override_creds(file_inode(file)->i_sb);
- if (is_sync_kiocb(iocb)) {
- rwf_t rwf = iocb_to_rw_flags(ifl);
-
- ret = vfs_iter_write(real.file, iter, &iocb->ki_pos, rwf);
- /* Update size */
- ovl_file_modified(file);
- } else {
- struct ovl_aio_req *aio_req;
-
- ret = ovl_init_aio_done_wq(inode->i_sb);
- if (ret)
- goto out;
-
- ret = -ENOMEM;
- aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
- if (!aio_req)
- goto out;
-
- aio_req->orig_iocb = iocb;
- kiocb_clone(&aio_req->iocb, iocb, get_file(real.file));
- aio_req->iocb.ki_flags = ifl;
- aio_req->iocb.ki_complete = ovl_aio_queue_completion;
- refcount_set(&aio_req->ref, 2);
- ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter);
- ovl_aio_put(aio_req);
- if (ret != -EIOCBQUEUED)
- ovl_aio_cleanup_handler(aio_req);
- }
-out:
- revert_creds(old_cred);
-out_fdput:
+ ret = backing_file_write_iter(real.file, iter, iocb, ifl, &ctx);
fdput(real);
out_unlock:
@@ -477,20 +330,21 @@ static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
- const struct cred *old_cred;
struct fd real;
ssize_t ret;
+ struct backing_file_ctx ctx = {
+ .cred = ovl_creds(file_inode(in)->i_sb),
+ .user_file = in,
+ .accessed = ovl_file_accessed,
+ };
ret = ovl_real_fdget(in, &real);
if (ret)
return ret;
- old_cred = ovl_override_creds(file_inode(in)->i_sb);
- ret = vfs_splice_read(real.file, ppos, pipe, len, flags);
- revert_creds(old_cred);
- ovl_file_accessed(in);
-
+ ret = backing_file_splice_read(real.file, ppos, pipe, len, flags, &ctx);
fdput(real);
+
return ret;
}
@@ -506,30 +360,23 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
loff_t *ppos, size_t len, unsigned int flags)
{
struct fd real;
- const struct cred *old_cred;
struct inode *inode = file_inode(out);
ssize_t ret;
+ struct backing_file_ctx ctx = {
+ .cred = ovl_creds(inode->i_sb),
+ .user_file = out,
+ .end_write = ovl_file_modified,
+ };
inode_lock(inode);
/* Update mode */
ovl_copyattr(inode);
- ret = file_remove_privs(out);
- if (ret)
- goto out_unlock;
ret = ovl_real_fdget(out, &real);
if (ret)
goto out_unlock;
- old_cred = ovl_override_creds(inode->i_sb);
- file_start_write(real.file);
-
- ret = iter_file_splice_write(pipe, real.file, ppos, len, flags);
-
- file_end_write(real.file);
- /* Update size */
- ovl_file_modified(out);
- revert_creds(old_cred);
+ ret = backing_file_splice_write(pipe, real.file, ppos, len, flags, &ctx);
fdput(real);
out_unlock:
@@ -567,23 +414,13 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
{
struct file *realfile = file->private_data;
- const struct cred *old_cred;
- int ret;
-
- if (!realfile->f_op->mmap)
- return -ENODEV;
+ struct backing_file_ctx ctx = {
+ .cred = ovl_creds(file_inode(file)->i_sb),
+ .user_file = file,
+ .accessed = ovl_file_accessed,
+ };
- if (WARN_ON(file != vma->vm_file))
- return -EIO;
-
- vma_set_file(vma, realfile);
-
- old_cred = ovl_override_creds(file_inode(file)->i_sb);
- ret = call_mmap(vma->vm_file, vma);
- revert_creds(old_cred);
- ovl_file_accessed(file);
-
- return ret;
+ return backing_file_mmap(realfile, vma, &ctx);
}
static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
@@ -776,19 +613,3 @@ const struct file_operations ovl_file_operations = {
.copy_file_range = ovl_copy_file_range,
.remap_file_range = ovl_remap_file_range,
};
-
-int __init ovl_aio_request_cache_init(void)
-{
- ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req",
- sizeof(struct ovl_aio_req),
- 0, SLAB_HWCACHE_ALIGN, NULL);
- if (!ovl_aio_request_cachep)
- return -ENOMEM;
-
- return 0;
-}
-
-void ovl_aio_request_cache_destroy(void)
-{
- kmem_cache_destroy(ovl_aio_request_cachep);
-}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index ca88b2636a57..509a57c85fae 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -417,6 +417,12 @@ int ovl_want_write(struct dentry *dentry);
void ovl_drop_write(struct dentry *dentry);
struct dentry *ovl_workdir(struct dentry *dentry);
const struct cred *ovl_override_creds(struct super_block *sb);
+
+static inline const struct cred *ovl_creds(struct super_block *sb)
+{
+ return OVL_FS(sb)->creator_cred;
+}
+
int ovl_can_decode_fh(struct super_block *sb);
struct dentry *ovl_indexdir(struct super_block *sb);
bool ovl_index_all(struct super_block *sb);
@@ -829,8 +835,6 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
/* file.c */
extern const struct file_operations ovl_file_operations;
-int __init ovl_aio_request_cache_init(void);
-void ovl_aio_request_cache_destroy(void);
int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa);
int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa);
int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index a0967bb25003..bcd4c314a7eb 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1501,14 +1501,10 @@ static int __init ovl_init(void)
if (ovl_inode_cachep == NULL)
return -ENOMEM;
- err = ovl_aio_request_cache_init();
- if (!err) {
- err = register_filesystem(&ovl_fs_type);
- if (!err)
- return 0;
+ err = register_filesystem(&ovl_fs_type);
+ if (!err)
+ return 0;
- ovl_aio_request_cache_destroy();
- }
kmem_cache_destroy(ovl_inode_cachep);
return err;
@@ -1524,7 +1520,6 @@ static void __exit ovl_exit(void)
*/
rcu_barrier();
kmem_cache_destroy(ovl_inode_cachep);
- ovl_aio_request_cache_destroy();
}
module_init(ovl_init);
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
new file mode 100644
index 000000000000..3f1fe1774f1b
--- /dev/null
+++ b/include/linux/backing-file.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#ifndef _LINUX_BACKING_FILE_H
+#define _LINUX_BACKING_FILE_H
+
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fs.h>
+
+struct backing_file_ctx {
+ const struct cred *cred;
+ struct file *user_file;
+ void (*accessed)(struct file *);
+ void (*end_write)(struct file *);
+};
+
+struct file *backing_file_open(const struct path *user_path, int flags,
+ const struct path *real_path,
+ const struct cred *cred);
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+ struct kiocb *iocb, int flags,
+ struct backing_file_ctx *ctx);
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+ struct kiocb *iocb, int flags,
+ struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags,
+ struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos, size_t len,
+ unsigned int flags,
+ struct backing_file_ctx *ctx);
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+ struct backing_file_ctx *ctx);
+
+#endif /* _LINUX_BACKING_FILE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 900d0cd55b50..db5d07e6e02e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2575,9 +2575,6 @@ struct file *dentry_open(const struct path *path, int flags,
const struct cred *creds);
struct file *dentry_create(const struct path *path, int flags, umode_t mode,
const struct cred *cred);
-struct file *backing_file_open(const struct path *user_path, int flags,
- const struct path *real_path,
- const struct cred *cred);
struct path *backing_file_user_path(struct file *f);
/*
generated by cgit v1.2.3 (git 2.39.0) at 2025-07-24 22:00:37 +0300