linux-stable/fs/cachefiles/namei.c

866 lines
22 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* CacheFiles path walking and related routines
*
* Copyright (C) 2021 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/fs.h>
#include <linux/namei.h>
#include "internal.h"
/*
* Mark the backing file as being a cache file if it's not already in use. The
* mark tells the culling request command that it's not allowed to cull the
* file or directory. The caller must hold the inode lock.
*/
static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object,
struct inode *inode)
{
bool can_use = false;
if (!(inode->i_flags & S_KERNEL_FILE)) {
inode->i_flags |= S_KERNEL_FILE;
trace_cachefiles_mark_active(object, inode);
can_use = true;
} else {
trace_cachefiles_mark_failed(object, inode);
}
return can_use;
}
static bool cachefiles_mark_inode_in_use(struct cachefiles_object *object,
struct inode *inode)
{
bool can_use;
inode_lock(inode);
can_use = __cachefiles_mark_inode_in_use(object, inode);
inode_unlock(inode);
return can_use;
}
/*
* Unmark a backing inode. The caller must hold the inode lock.
*/
static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object,
struct inode *inode)
{
inode->i_flags &= ~S_KERNEL_FILE;
trace_cachefiles_mark_inactive(object, inode);
}
static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object,
struct inode *inode)
{
inode_lock(inode);
__cachefiles_unmark_inode_in_use(object, inode);
inode_unlock(inode);
}
/*
* Unmark a backing inode and tell cachefilesd that there's something that can
* be culled.
*/
void cachefiles_unmark_inode_in_use(struct cachefiles_object *object,
struct file *file)
{
struct cachefiles_cache *cache = object->volume->cache;
struct inode *inode = file_inode(file);
cachefiles_do_unmark_inode_in_use(object, inode);
if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) {
atomic_long_add(inode->i_blocks, &cache->b_released);
if (atomic_inc_return(&cache->f_released))
cachefiles_state_changed(cache);
}
}
/*
* get a subdirectory
*/
struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
struct dentry *dir,
const char *dirname,
bool *_is_new)
{
struct dentry *subdir;
struct path path;
int ret;
_enter(",,%s", dirname);
/* search the current directory for the element name */
inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
retry:
ret = cachefiles_inject_read_error();
if (ret == 0)
subdir = lookup_one_len(dirname, dir, strlen(dirname));
else
subdir = ERR_PTR(ret);
trace_cachefiles_lookup(NULL, dir, subdir);
if (IS_ERR(subdir)) {
trace_cachefiles_vfs_error(NULL, d_backing_inode(dir),
PTR_ERR(subdir),
cachefiles_trace_lookup_error);
if (PTR_ERR(subdir) == -ENOMEM)
goto nomem_d_alloc;
goto lookup_error;
}
_debug("subdir -> %pd %s",
subdir, d_backing_inode(subdir) ? "positive" : "negative");
/* we need to create the subdir if it doesn't exist yet */
if (d_is_negative(subdir)) {
ret = cachefiles_has_space(cache, 1, 0,
cachefiles_has_space_for_create);
if (ret < 0)
goto mkdir_error;
_debug("attempt mkdir");
path.mnt = cache->mnt;
path.dentry = dir;
ret = security_path_mkdir(&path, subdir, 0700);
if (ret < 0)
goto mkdir_error;
ret = cachefiles_inject_write_error();
if (ret == 0)
ret = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700);
if (ret < 0) {
trace_cachefiles_vfs_error(NULL, d_inode(dir), ret,
cachefiles_trace_mkdir_error);
goto mkdir_error;
}
trace_cachefiles_mkdir(dir, subdir);
if (unlikely(d_unhashed(subdir))) {
cachefiles_put_directory(subdir);
goto retry;
}
ASSERT(d_backing_inode(subdir));
_debug("mkdir -> %pd{ino=%lu}",
subdir, d_backing_inode(subdir)->i_ino);
if (_is_new)
*_is_new = true;
}
/* Tell rmdir() it's not allowed to delete the subdir */
inode_lock(d_inode(subdir));
inode_unlock(d_inode(dir));
if (!__cachefiles_mark_inode_in_use(NULL, d_inode(subdir))) {
pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n",
subdir, d_inode(subdir)->i_ino);
goto mark_error;
}
inode_unlock(d_inode(subdir));
/* we need to make sure the subdir is a directory */
ASSERT(d_backing_inode(subdir));
if (!d_can_lookup(subdir)) {
pr_err("%s is not a directory\n", dirname);
ret = -EIO;
goto check_error;
}
ret = -EPERM;
if (!(d_backing_inode(subdir)->i_opflags & IOP_XATTR) ||
!d_backing_inode(subdir)->i_op->lookup ||
!d_backing_inode(subdir)->i_op->mkdir ||
!d_backing_inode(subdir)->i_op->rename ||
!d_backing_inode(subdir)->i_op->rmdir ||
!d_backing_inode(subdir)->i_op->unlink)
goto check_error;
_leave(" = [%lu]", d_backing_inode(subdir)->i_ino);
return subdir;
check_error:
cachefiles_put_directory(subdir);
_leave(" = %d [check]", ret);
return ERR_PTR(ret);
mark_error:
inode_unlock(d_inode(subdir));
dput(subdir);
return ERR_PTR(-EBUSY);
mkdir_error:
inode_unlock(d_inode(dir));
dput(subdir);
pr_err("mkdir %s failed with error %d\n", dirname, ret);
return ERR_PTR(ret);
lookup_error:
inode_unlock(d_inode(dir));
ret = PTR_ERR(subdir);
pr_err("Lookup %s failed with error %d\n", dirname, ret);
return ERR_PTR(ret);
nomem_d_alloc:
inode_unlock(d_inode(dir));
_leave(" = -ENOMEM");
return ERR_PTR(-ENOMEM);
}
/*
* Put a subdirectory.
*/
void cachefiles_put_directory(struct dentry *dir)
{
if (dir) {
cachefiles_do_unmark_inode_in_use(NULL, d_inode(dir));
dput(dir);
}
}
/*
* Remove a regular file from the cache.
*/
static int cachefiles_unlink(struct cachefiles_cache *cache,
struct cachefiles_object *object,
struct dentry *dir, struct dentry *dentry,
enum fscache_why_object_killed why)
{
struct path path = {
.mnt = cache->mnt,
.dentry = dir,
};
int ret;
trace_cachefiles_unlink(object, d_inode(dentry)->i_ino, why);
ret = security_path_unlink(&path, dentry);
if (ret < 0) {
cachefiles_io_error(cache, "Unlink security error");
return ret;
}
ret = cachefiles_inject_remove_error();
if (ret == 0) {
ret = vfs_unlink(&nop_mnt_idmap, d_backing_inode(dir), dentry, NULL);
if (ret == -EIO)
cachefiles_io_error(cache, "Unlink failed");
}
if (ret != 0)
trace_cachefiles_vfs_error(object, d_backing_inode(dir), ret,
cachefiles_trace_unlink_error);
return ret;
}
/*
* Delete an object representation from the cache
* - File backed objects are unlinked
* - Directory backed objects are stuffed into the graveyard for userspace to
* delete
*/
int cachefiles_bury_object(struct cachefiles_cache *cache,
struct cachefiles_object *object,
struct dentry *dir,
struct dentry *rep,
enum fscache_why_object_killed why)
{
struct dentry *grave, *trap;
struct path path, path_to_graveyard;
char nbuffer[8 + 8 + 1];
int ret;
_enter(",'%pd','%pd'", dir, rep);
if (rep->d_parent != dir) {
inode_unlock(d_inode(dir));
_leave(" = -ESTALE");
return -ESTALE;
}
/* non-directories can just be unlinked */
if (!d_is_dir(rep)) {
dget(rep); /* Stop the dentry being negated if it's only pinned
* by a file struct.
*/
ret = cachefiles_unlink(cache, object, dir, rep, why);
dput(rep);
inode_unlock(d_inode(dir));
_leave(" = %d", ret);
return ret;
}
/* directories have to be moved to the graveyard */
_debug("move stale object to graveyard");
inode_unlock(d_inode(dir));
try_again:
/* first step is to make up a grave dentry in the graveyard */
sprintf(nbuffer, "%08x%08x",
(uint32_t) ktime_get_real_seconds(),
(uint32_t) atomic_inc_return(&cache->gravecounter));
/* do the multiway lock magic */
trap = lock_rename(cache->graveyard, dir);
if (IS_ERR(trap))
return PTR_ERR(trap);
/* do some checks before getting the grave dentry */
if (rep->d_parent != dir || IS_DEADDIR(d_inode(rep))) {
/* the entry was probably culled when we dropped the parent dir
* lock */
unlock_rename(cache->graveyard, dir);
_leave(" = 0 [culled?]");
return 0;
}
if (!d_can_lookup(cache->graveyard)) {
unlock_rename(cache->graveyard, dir);
cachefiles_io_error(cache, "Graveyard no longer a directory");
return -EIO;
}
if (trap == rep) {
unlock_rename(cache->graveyard, dir);
cachefiles_io_error(cache, "May not make directory loop");
return -EIO;
}
if (d_mountpoint(rep)) {
unlock_rename(cache->graveyard, dir);
cachefiles_io_error(cache, "Mountpoint in cache");
return -EIO;
}
grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer));
if (IS_ERR(grave)) {
unlock_rename(cache->graveyard, dir);
trace_cachefiles_vfs_error(object, d_inode(cache->graveyard),
PTR_ERR(grave),
cachefiles_trace_lookup_error);
if (PTR_ERR(grave) == -ENOMEM) {
_leave(" = -ENOMEM");
return -ENOMEM;
}
cachefiles_io_error(cache, "Lookup error %ld", PTR_ERR(grave));
return -EIO;
}
if (d_is_positive(grave)) {
unlock_rename(cache->graveyard, dir);
dput(grave);
grave = NULL;
cond_resched();
goto try_again;
}
if (d_mountpoint(grave)) {
unlock_rename(cache->graveyard, dir);
dput(grave);
cachefiles_io_error(cache, "Mountpoint in graveyard");
return -EIO;
}
/* target should not be an ancestor of source */
if (trap == grave) {
unlock_rename(cache->graveyard, dir);
dput(grave);
cachefiles_io_error(cache, "May not make directory loop");
return -EIO;
}
/* attempt the rename */
path.mnt = cache->mnt;
path.dentry = dir;
path_to_graveyard.mnt = cache->mnt;
path_to_graveyard.dentry = cache->graveyard;
ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
if (ret < 0) {
cachefiles_io_error(cache, "Rename security error %d", ret);
} else {
struct renamedata rd = {
.old_mnt_idmap = &nop_mnt_idmap,
.old_dir = d_inode(dir),
.old_dentry = rep,
.new_mnt_idmap = &nop_mnt_idmap,
.new_dir = d_inode(cache->graveyard),
.new_dentry = grave,
};
trace_cachefiles_rename(object, d_inode(rep)->i_ino, why);
ret = cachefiles_inject_read_error();
if (ret == 0)
ret = vfs_rename(&rd);
if (ret != 0)
trace_cachefiles_vfs_error(object, d_inode(dir), ret,
cachefiles_trace_rename_error);
if (ret != 0 && ret != -ENOMEM)
cachefiles_io_error(cache,
"Rename failed with error %d", ret);
}
__cachefiles_unmark_inode_in_use(object, d_inode(rep));
unlock_rename(cache->graveyard, dir);
dput(grave);
_leave(" = 0");
return 0;
}
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
/*
* Delete a cache file.
*/
int cachefiles_delete_object(struct cachefiles_object *object,
enum fscache_why_object_killed why)
{
struct cachefiles_volume *volume = object->volume;
struct dentry *dentry = object->file->f_path.dentry;
struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash];
int ret;
_enter(",OBJ%x{%pD}", object->debug_id, object->file);
/* Stop the dentry being negated if it's only pinned by a file struct. */
dget(dentry);
inode_lock_nested(d_backing_inode(fan), I_MUTEX_PARENT);
ret = cachefiles_unlink(volume->cache, object, fan, dentry, why);
inode_unlock(d_backing_inode(fan));
dput(dentry);
return ret;
}
/*
* Create a temporary file and leave it unattached and un-xattr'd until the
* time comes to discard the object from memory.
*/
struct file *cachefiles_create_tmpfile(struct cachefiles_object *object)
{
struct cachefiles_volume *volume = object->volume;
struct cachefiles_cache *cache = volume->cache;
const struct cred *saved_cred;
struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash];
struct file *file;
const struct path parentpath = { .mnt = cache->mnt, .dentry = fan };
cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2022-04-25 12:21:24 +00:00
uint64_t ni_size;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
long ret;
cachefiles_begin_secure(cache, &saved_cred);
ret = cachefiles_inject_write_error();
if (ret == 0) {
v6.5/vfs.file -----BEGIN PGP SIGNATURE----- iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCZJU4WgAKCRCRxhvAZXjc oofvAQDs9RJwQUyWHJmQA+tWz5cUE5DviVWCwwul5dQRRCqgaQEA2OIO0gPFaVoq 1OYOeLyUjl/cpS8e3u4uJtw34jttdQA= =AwcR -----END PGP SIGNATURE----- Merge tag 'v6.5/vfs.file' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs Pull vfs file handling updates from Christian Brauner: "This contains Amir's work to fix a long-standing problem where an unprivileged overlayfs mount can be used to avoid fanotify permission events that were requested for an inode or superblock on the underlying filesystem. Some background about files opened in overlayfs. If a file is opened in overlayfs @file->f_path will refer to a "fake" path. What this means is that while @file->f_inode will refer to inode of the underlying layer, @file->f_path refers to an overlayfs {dentry,vfsmount} pair. The reasons for doing this are out of scope here but it is the reason why the vfs has been providing the open_with_fake_path() helper for overlayfs for very long time now. So nothing new here. This is for sure not very elegant and everyone including the overlayfs maintainers agree. Improving this significantly would involve more fragile and potentially rather invasive changes. In various codepaths access to the path of the underlying filesystem is needed for such hybrid file. The best example is fsnotify where this becomes security relevant. Passing the overlayfs @file->f_path->dentry will cause fsnotify to skip generating fsnotify events registered on the underlying inode or superblock. To fix this we extend the vfs provided open_with_fake_path() concept for overlayfs to create a backing file container that holds the real path and to expose a helper that can be used by relevant callers to get access to the path of the underlying filesystem through the new file_real_path() helper. This pattern is similar to what we do in d_real() and d_real_inode(). The first beneficiary is fsnotify and fixes the security sensitive problem mentioned above. There's a couple of nice cleanups included as well. Over time, the old open_with_fake_path() helper added specifically for overlayfs a long time ago started to get used in other places such as cachefiles. Even though cachefiles have nothing to do with hybrid files. The only reason cachefiles used that concept was that files opened with open_with_fake_path() aren't charged against the caller's open file limit by raising FMODE_NOACCOUNT. It's just mere coincidence that both overlayfs and cachefiles need to ensure to not overcharge the caller for their internal open calls. So this work disentangles FMODE_NOACCOUNT use cases and backing file use-cases by adding the FMODE_BACKING flag which indicates that the file can be used to retrieve the backing file of another filesystem. (Fyi, Jens will be sending you a really nice cleanup from Christoph that gets rid of 3 FMODE_* flags otherwise this would be the last fmode_t bit we'd be using.) So now overlayfs becomes the sole user of the renamed open_with_fake_path() helper which is now named backing_file_open(). For internal kernel users such as cachefiles that are only interested in FMODE_NOACCOUNT but not in FMODE_BACKING we add a new kernel_file_open() helper which opens a file without being charged against the caller's open file limit. All new helpers are properly documented and clearly annotated to mention their special uses. We also rename vfs_tmpfile_open() to kernel_tmpfile_open() to clearly distinguish it from vfs_tmpfile() and align it the other kernel_*() internal helpers" * tag 'v6.5/vfs.file' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: ovl: enable fsnotify events on underlying real files fs: use backing_file container for internal files with "fake" f_path fs: move kmem_cache_zalloc() into alloc_empty_file*() helpers fs: use a helper for opening kernel internal files fs: rename {vfs,kernel}_tmpfile_open()
2023-06-26 17:14:36 +00:00
file = kernel_tmpfile_open(&nop_mnt_idmap, &parentpath,
S_IFREG | 0600,
O_RDWR | O_LARGEFILE | O_DIRECT,
cache->cache_cred);
ret = PTR_ERR_OR_ZERO(file);
}
if (ret) {
trace_cachefiles_vfs_error(object, d_inode(fan), ret,
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
cachefiles_trace_tmpfile_error);
if (ret == -EIO)
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
cachefiles_io_error_obj(object, "Failed to create tmpfile");
goto err;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
}
trace_cachefiles_tmpfile(object, file_inode(file));
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
/* This is a newly created file with no other possible user */
if (!cachefiles_mark_inode_in_use(object, file_inode(file)))
WARN_ON(1);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2022-04-25 12:21:24 +00:00
ret = cachefiles_ondemand_init_object(object);
if (ret < 0)
goto err_unuse;
cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2022-04-25 12:21:24 +00:00
ni_size = object->cookie->object_size;
ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
if (ni_size > 0) {
trace_cachefiles_trunc(object, file_inode(file), 0, ni_size,
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
cachefiles_trunc_expand_tmpfile);
ret = cachefiles_inject_write_error();
if (ret == 0)
ret = vfs_truncate(&file->f_path, ni_size);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
if (ret < 0) {
trace_cachefiles_vfs_error(
object, file_inode(file), ret,
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
cachefiles_trace_trunc_error);
goto err_unuse;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
}
}
ret = -EINVAL;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
if (unlikely(!file->f_op->read_iter) ||
unlikely(!file->f_op->write_iter)) {
fput(file);
pr_notice("Cache does not support read_iter and write_iter\n");
goto err_unuse;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
}
out:
cachefiles_end_secure(cache, saved_cred);
return file;
err_unuse:
cachefiles_do_unmark_inode_in_use(object, file_inode(file));
fput(file);
err:
file = ERR_PTR(ret);
goto out;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
}
/*
* Create a new file.
*/
static bool cachefiles_create_file(struct cachefiles_object *object)
{
struct file *file;
int ret;
ret = cachefiles_has_space(object->volume->cache, 1, 0,
cachefiles_has_space_for_create);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
if (ret < 0)
return false;
file = cachefiles_create_tmpfile(object);
if (IS_ERR(file))
return false;
set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags);
set_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags);
_debug("create -> %pD{ino=%lu}", file, file_inode(file)->i_ino);
object->file = file;
return true;
}
/*
* Open an existing file, checking its attributes and replacing it if it is
* stale.
*/
static bool cachefiles_open_file(struct cachefiles_object *object,
struct dentry *dentry)
{
struct cachefiles_cache *cache = object->volume->cache;
struct file *file;
struct path path;
int ret;
_enter("%pd", dentry);
if (!cachefiles_mark_inode_in_use(object, d_inode(dentry))) {
pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n",
dentry, d_inode(dentry)->i_ino);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
return false;
}
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
/* We need to open a file interface onto a data file now as we can't do
* it on demand because writeback called from do_exit() sees
* current->fs == NULL - which breaks d_path() called from ext4 open.
*/
path.mnt = cache->mnt;
path.dentry = dentry;
file = kernel_file_open(&path, O_RDWR | O_LARGEFILE | O_DIRECT,
d_backing_inode(dentry), cache->cache_cred);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
if (IS_ERR(file)) {
trace_cachefiles_vfs_error(object, d_backing_inode(dentry),
PTR_ERR(file),
cachefiles_trace_open_error);
goto error;
}
if (unlikely(!file->f_op->read_iter) ||
unlikely(!file->f_op->write_iter)) {
pr_notice("Cache does not support read_iter and write_iter\n");
goto error_fput;
}
_debug("file -> %pd positive", dentry);
cachefiles: notify the user daemon when looking up cookie Fscache/CacheFiles used to serve as a local cache for a remote networking fs. A new on-demand read mode will be introduced for CacheFiles, which can boost the scenario where on-demand read semantics are needed, e.g. container image distribution. The essential difference between these two modes is seen when a cache miss occurs: In the original mode, the netfs will fetch the data from the remote server and then write it to the cache file; in on-demand read mode, fetching the data and writing it into the cache is delegated to a user daemon. As the first step, notify the user daemon when looking up cookie. In this case, an anonymous fd is sent to the user daemon, through which the user daemon can write the fetched data to the cache file. Since the user daemon may move the anonymous fd around, e.g. through dup(), an object ID uniquely identifying the cache file is also attached. Also add one advisory flag (FSCACHE_ADV_WANT_CACHE_SIZE) suggesting that the cache file size shall be retrieved at runtime. This helps the scenario where one cache file contains multiple netfs files, e.g. for the purpose of deduplication. In this case, netfs itself has no idea the size of the cache file, whilst the user daemon should give the hint on it. Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Link: https://lore.kernel.org/r/20220509074028.74954-3-jefflexu@linux.alibaba.com Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
2022-04-25 12:21:24 +00:00
ret = cachefiles_ondemand_init_object(object);
if (ret < 0)
goto error_fput;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
ret = cachefiles_check_auxdata(object, file);
if (ret < 0)
goto check_failed;
mm, netfs, fscache: stop read optimisation when folio removed from pagecache Fscache has an optimisation by which reads from the cache are skipped until we know that (a) there's data there to be read and (b) that data isn't entirely covered by pages resident in the netfs pagecache. This is done with two flags manipulated by fscache_note_page_release(): if (... test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); where the NO_DATA_TO_READ flag causes cachefiles_prepare_read() to indicate that netfslib should download from the server or clear the page instead. The fscache_note_page_release() function is intended to be called from ->releasepage() - but that only gets called if PG_private or PG_private_2 is set - and currently the former is at the discretion of the network filesystem and the latter is only set whilst a page is being written to the cache, so sometimes we miss clearing the optimisation. Fix this by following Willy's suggestion[1] and adding an address_space flag, AS_RELEASE_ALWAYS, that causes filemap_release_folio() to always call ->release_folio() if it's set, even if PG_private or PG_private_2 aren't set. Note that this would require folio_test_private() and page_has_private() to become more complicated. To avoid that, in the places[*] where these are used to conditionalise calls to filemap_release_folio() and try_to_release_page(), the tests are removed the those functions just jumped to unconditionally and the test is performed there. [*] There are some exceptions in vmscan.c where the check guards more than just a call to the releaser. I've added a function, folio_needs_release() to wrap all the checks for that. AS_RELEASE_ALWAYS should be set if a non-NULL cookie is obtained from fscache and cleared in ->evict_inode() before truncate_inode_pages_final() is called. Additionally, the FSCACHE_COOKIE_NO_DATA_TO_READ flag needs to be cleared and the optimisation cancelled if a cachefiles object already contains data when we open it. [dwysocha@redhat.com: call folio_mapping() inside folio_needs_release()] Link: https://github.com/DaveWysochanskiRH/kernel/commit/902c990e311120179fa5de99d68364b2947b79ec Link: https://lkml.kernel.org/r/20230628104852.3391651-3-dhowells@redhat.com Fixes: 1f67e6d0b188 ("fscache: Provide a function to note the release of a page") Fixes: 047487c947e8 ("cachefiles: Implement the I/O routines") Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Reported-by: Rohith Surabattula <rohiths.msft@gmail.com> Suggested-by: Matthew Wilcox <willy@infradead.org> Tested-by: SeongJae Park <sj@kernel.org> Cc: Daire Byrne <daire.byrne@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steve French <sfrench@samba.org> Cc: Shyam Prasad N <nspmangalore@gmail.com> Cc: Rohith Surabattula <rohiths.msft@gmail.com> Cc: Dave Wysochanski <dwysocha@redhat.com> Cc: Dominique Martinet <asmadeus@codewreck.org> Cc: Ilya Dryomov <idryomov@gmail.com> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jingbo Xu <jefflexu@linux.alibaba.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Xiubo Li <xiubli@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-28 10:48:52 +00:00
clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &object->cookie->flags);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
object->file = file;
/* Always update the atime on an object we've just looked up (this is
* used to keep track of culling, and atimes are only updated by read,
* write and readdir but not lookup or open).
*/
touch_atime(&file->f_path);
dput(dentry);
return true;
check_failed:
fscache_cookie_lookup_negative(object->cookie);
cachefiles_unmark_inode_in_use(object, file);
fput(file);
dput(dentry);
if (ret == -ESTALE)
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
return cachefiles_create_file(object);
return false;
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
error_fput:
fput(file);
error:
cachefiles_do_unmark_inode_in_use(object, d_inode(dentry));
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
dput(dentry);
return false;
}
/*
* walk from the parent object to the child object through the backing
* filesystem, creating directories as we go
*/
bool cachefiles_look_up_object(struct cachefiles_object *object)
{
struct cachefiles_volume *volume = object->volume;
struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash];
int ret;
_enter("OBJ%x,%s,", object->debug_id, object->d_name);
/* Look up path "cache/vol/fanout/file". */
ret = cachefiles_inject_read_error();
if (ret == 0)
dentry = lookup_positive_unlocked(object->d_name, fan,
object->d_name_len);
else
dentry = ERR_PTR(ret);
trace_cachefiles_lookup(object, fan, dentry);
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
if (IS_ERR(dentry)) {
if (dentry == ERR_PTR(-ENOENT))
goto new_file;
if (dentry == ERR_PTR(-EIO))
cachefiles_io_error_obj(object, "Lookup failed");
return false;
}
if (!d_is_reg(dentry)) {
pr_err("%pd is not a file\n", dentry);
inode_lock_nested(d_inode(fan), I_MUTEX_PARENT);
ret = cachefiles_bury_object(volume->cache, object, fan, dentry,
FSCACHE_OBJECT_IS_WEIRD);
dput(dentry);
if (ret < 0)
return false;
goto new_file;
}
if (!cachefiles_open_file(object, dentry))
return false;
_leave(" = t [%lu]", file_inode(object->file)->i_ino);
return true;
new_file:
fscache_cookie_lookup_negative(object->cookie);
return cachefiles_create_file(object);
}
/*
* Attempt to link a temporary file into its rightful place in the cache.
*/
bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache,
struct cachefiles_object *object)
{
struct cachefiles_volume *volume = object->volume;
struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash];
bool success = false;
int ret;
_enter(",%pD", object->file);
inode_lock_nested(d_inode(fan), I_MUTEX_PARENT);
ret = cachefiles_inject_read_error();
if (ret == 0)
dentry = lookup_one_len(object->d_name, fan, object->d_name_len);
else
dentry = ERR_PTR(ret);
if (IS_ERR(dentry)) {
trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry),
cachefiles_trace_lookup_error);
_debug("lookup fail %ld", PTR_ERR(dentry));
goto out_unlock;
}
if (!d_is_negative(dentry)) {
if (d_backing_inode(dentry) == file_inode(object->file)) {
success = true;
goto out_dput;
}
ret = cachefiles_unlink(volume->cache, object, fan, dentry,
FSCACHE_OBJECT_IS_STALE);
if (ret < 0)
goto out_dput;
dput(dentry);
ret = cachefiles_inject_read_error();
if (ret == 0)
dentry = lookup_one_len(object->d_name, fan, object->d_name_len);
else
dentry = ERR_PTR(ret);
if (IS_ERR(dentry)) {
trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry),
cachefiles_trace_lookup_error);
_debug("lookup fail %ld", PTR_ERR(dentry));
goto out_unlock;
}
}
ret = cachefiles_inject_read_error();
if (ret == 0)
ret = vfs_link(object->file->f_path.dentry, &nop_mnt_idmap,
cachefiles: Implement backing file wrangling Implement the wrangling of backing files, including the following pieces: (1) Lookup and creation of a file on disk, using a tmpfile if the file isn't yet present. The file is then opened, sized for DIO and the file handle is attached to the cachefiles_object struct. The inode is marked to indicate that it's in use by a kernel service. (2) Invalidation of an object, creating a tmpfile and switching the file pointer in the cachefiles object. (3) Committing a file to disk, including setting the coherency xattr on it and, if necessary, creating a hard link to it. Note that this would be a good place to use Omar Sandoval's vfs_link() with AT_LINK_REPLACE[1] as I may have to unlink an old file before I can link a tmpfile into place. (4) Withdrawal of open objects when a cache is being withdrawn or a cookie is relinquished. This involves committing or discarding the file. Changes ======= ver #2: - Fix logging of wrong error[1]. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203094950.GA2480@kili/ [1] Link: https://lore.kernel.org/r/163819644097.215744.4505389616742411239.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906949512.143852.14222856795032602080.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967158526.1823006.17482695321424642675.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021557060.640689.16373541458119269871.stgit@warthog.procyon.org.uk/ # v4
2021-10-21 07:50:10 +00:00
d_inode(fan), dentry, NULL);
if (ret < 0) {
trace_cachefiles_vfs_error(object, d_inode(fan), ret,
cachefiles_trace_link_error);
_debug("link fail %d", ret);
} else {
trace_cachefiles_link(object, file_inode(object->file));
spin_lock(&object->lock);
/* TODO: Do we want to switch the file pointer to the new dentry? */
clear_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags);
spin_unlock(&object->lock);
success = true;
}
out_dput:
dput(dentry);
out_unlock:
inode_unlock(d_inode(fan));
_leave(" = %u", success);
return success;
}
/*
* Look up an inode to be checked or culled. Return -EBUSY if the inode is
* marked in use.
*/
static struct dentry *cachefiles_lookup_for_cull(struct cachefiles_cache *cache,
struct dentry *dir,
char *filename)
{
struct dentry *victim;
int ret = -ENOENT;
inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
victim = lookup_one_len(filename, dir, strlen(filename));
if (IS_ERR(victim))
goto lookup_error;
if (d_is_negative(victim))
goto lookup_put;
if (d_inode(victim)->i_flags & S_KERNEL_FILE)
goto lookup_busy;
return victim;
lookup_busy:
ret = -EBUSY;
lookup_put:
inode_unlock(d_inode(dir));
dput(victim);
return ERR_PTR(ret);
lookup_error:
inode_unlock(d_inode(dir));
ret = PTR_ERR(victim);
if (ret == -ENOENT)
return ERR_PTR(-ESTALE); /* Probably got retired by the netfs */
if (ret == -EIO) {
cachefiles_io_error(cache, "Lookup failed");
} else if (ret != -ENOMEM) {
pr_err("Internal error: %d\n", ret);
ret = -EIO;
}
return ERR_PTR(ret);
}
/*
* Cull an object if it's not in use
* - called only by cache manager daemon
*/
int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
char *filename)
{
struct dentry *victim;
struct inode *inode;
int ret;
_enter(",%pd/,%s", dir, filename);
victim = cachefiles_lookup_for_cull(cache, dir, filename);
if (IS_ERR(victim))
return PTR_ERR(victim);
/* check to see if someone is using this object */
inode = d_inode(victim);
inode_lock(inode);
if (inode->i_flags & S_KERNEL_FILE) {
ret = -EBUSY;
} else {
/* Stop the cache from picking it back up */
inode->i_flags |= S_KERNEL_FILE;
ret = 0;
}
inode_unlock(inode);
if (ret < 0)
goto error_unlock;
ret = cachefiles_bury_object(cache, NULL, dir, victim,
FSCACHE_OBJECT_WAS_CULLED);
if (ret < 0)
goto error;
fscache_count_culled();
dput(victim);
_leave(" = 0");
return 0;
error_unlock:
inode_unlock(d_inode(dir));
error:
dput(victim);
if (ret == -ENOENT)
return -ESTALE; /* Probably got retired by the netfs */
if (ret != -ENOMEM) {
pr_err("Internal error: %d\n", ret);
ret = -EIO;
}
_leave(" = %d", ret);
return ret;
}
/*
* Find out if an object is in use or not
* - called only by cache manager daemon
* - returns -EBUSY or 0 to indicate whether an object is in use or not
*/
int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
char *filename)
{
struct dentry *victim;
int ret = 0;
victim = cachefiles_lookup_for_cull(cache, dir, filename);
if (IS_ERR(victim))
return PTR_ERR(victim);
inode_unlock(d_inode(dir));
dput(victim);
return ret;
}