linux/fs/backing-file.c
Amir Goldstein a6293b3e28 fs: factor out backing_file_{read,write}_iter() helpers
Overlayfs submits files io to backing files on other filesystems.
Factor out some common helpers to perform io to backing files, into
fs/backing-file.c.

Suggested-by: Miklos Szeredi <miklos@szeredi.hu>
Link: https://lore.kernel.org/r/CAJfpeguhmZbjP3JLqtUy0AdWaHOkAPWeP827BBWwRFEAUgnUcQ@mail.gmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
2023-12-23 16:35:09 +02:00

259 lines
6.1 KiB
C

// 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 "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);
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);