diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-12 13:45:12 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-01-12 13:45:12 -0800 |
commit | 8834147f9505661859ce44549bf601e2a06bba7c (patch) | |
tree | d8f1086c626c77fceb100bd2fc5ea011e1212070 /fs | |
parent | 8975f8974888b3cd25aa8cf9eba24edbb9230bb2 (diff) | |
parent | d7bdba1c81f7e7bad12c7c7ce55afa3c7b0821ef (diff) | |
download | linux-8834147f9505661859ce44549bf601e2a06bba7c.tar.gz linux-8834147f9505661859ce44549bf601e2a06bba7c.tar.bz2 linux-8834147f9505661859ce44549bf601e2a06bba7c.zip |
Merge tag 'fscache-rewrite-20220111' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
Pull fscache rewrite from David Howells:
"This is a set of patches that rewrites the fscache driver and the
cachefiles driver, significantly simplifying the code compared to
what's upstream, removing the complex operation scheduling and object
state machine in favour of something much smaller and simpler.
The series is structured such that the first few patches disable
fscache use by the network filesystems using it, remove the cachefiles
driver entirely and as much of the fscache driver as can be got away
with without causing build failures in the network filesystems.
The patches after that recreate fscache and then cachefiles,
attempting to add the pieces in a logical order. Finally, the
filesystems are reenabled and then the very last patch changes the
documentation.
[!] Note: I have dropped the cifs patch for the moment, leaving local
caching in cifs disabled. I've been having trouble getting that
working. I think I have it done, but it needs more testing (there
seem to be some test failures occurring with v5.16 also from
xfstests), so I propose deferring that patch to the end of the
merge window.
WHY REWRITE?
============
Fscache's operation scheduling API was intended to handle sequencing
of cache operations, which were all required (where possible) to run
asynchronously in parallel with the operations being done by the
network filesystem, whilst allowing the cache to be brought online and
offline and to interrupt service for invalidation.
With the advent of the tmpfile capacity in the VFS, however, an
opportunity arises to do invalidation much more simply, without having
to wait for I/O that's actually in progress: Cachefiles can simply
create a tmpfile, cut over the file pointer for the backing object
attached to a cookie and abandon the in-progress I/O, dismissing it
upon completion.
Future work here would involve using Omar Sandoval's vfs_link() with
AT_LINK_REPLACE[1] to allow an extant file to be displaced by a new
hard link from a tmpfile as currently I have to unlink the old file
first.
These patches can also simplify the object state handling as I/O
operations to the cache don't all have to be brought to a stop in
order to invalidate a file. To that end, and with an eye on to writing
a new backing cache model in the future, I've taken the opportunity to
simplify the indexing structure.
I've separated the index cookie concept from the file cookie concept
by C type now. The former is now called a "volume cookie" (struct
fscache_volume) and there is a container of file cookies. There are
then just the two levels. All the index cookie levels are collapsed
into a single volume cookie, and this has a single printable string as
a key. For instance, an AFS volume would have a key of something like
"afs,example.com,1000555", combining the filesystem name, cell name
and volume ID. This is freeform, but must not have '/' chars in it.
I've also eliminated all pointers back from fscache into the network
filesystem. This required the duplication of a little bit of data in
the cookie (cookie key, coherency data and file size), but it's not
actually that much. This gets rid of problems with making sure we keep
netfs data structures around so that the cache can access them.
These patches mean that most of the code that was in the drivers
before is simply gone and those drivers are now almost entirely new
code. That being the case, there doesn't seem any particular reason to
try and maintain bisectability across it. Further, there has to be a
point in the middle where things are cut over as there's a single
point everything has to go through (ie. /dev/cachefiles) and it can't
be in use by two drivers at once.
ISSUES YET OUTSTANDING
======================
There are some issues still outstanding, unaddressed by this patchset,
that will need fixing in future patchsets, but that don't stop this
series from being usable:
(1) The cachefiles driver needs to stop using the backing filesystem's
metadata to store information about what parts of the cache are
populated. This is not reliable with modern extent-based
filesystems.
Fixing this is deferred to a separate patchset as it involves
negotiation with the network filesystem and the VM as to how much
data to download to fulfil a read - which brings me on to (2)...
(2) NFS (and CIFS with the dropped patch) do not take account of how
the cache would like I/O to be structured to meet its granularity
requirements. Previously, the cache used page granularity, which
was fine as the network filesystems also dealt in page
granularity, and the backing filesystem (ext4, xfs or whatever)
did whatever it did out of sight. However, we now have folios to
deal with and the cache will now have to store its own metadata to
track its contents.
The change I'm looking at making for cachefiles is to store
content bitmaps in one or more xattrs and making a bit in the map
correspond to something like a 256KiB block. However, the size of
an xattr and the fact that they have to be read/updated in one go
means that I'm looking at covering 1GiB of data per 512-byte map
and storing each map in an xattr. Cachefiles has the potential to
grow into a fully fledged filesystem of its very own if I'm not
careful.
However, I'm also looking at changing things even more radically
and going to a different model of how the cache is arranged and
managed - one that's more akin to the way, say, openafs does
things - which brings me on to (3)...
(3) The way cachefilesd does culling is very inefficient for large
caches and it would be better to move it into the kernel if I can
as cachefilesd has to keep asking the kernel if it can cull a
file. Changing the way the backend works would allow this to be
addressed.
BITS THAT MAY BE CONTROVERSIAL
==============================
There are some bits I've added that may be controversial:
(1) I've provided a flag, S_KERNEL_FILE, that cachefiles uses to check
if a files is already being used by some other kernel service
(e.g. a duplicate cachefiles cache in the same directory) and
reject it if it is. This isn't entirely necessary, but it helps
prevent accidental data corruption.
I don't want to use S_SWAPFILE as that has other effects, but
quite possibly swapon() should set S_KERNEL_FILE too.
Note that it doesn't prevent userspace from interfering, though
perhaps it should. (I have made it prevent a marked directory from
being rmdir-able).
(2) Cachefiles wants to keep the backing file for a cookie open whilst
we might need to write to it from network filesystem writeback.
The problem is that the network filesystem unuses its cookie when
its file is closed, and so we have nothing pinning the cachefiles
file open and it will get closed automatically after a short time
to avoid EMFILE/ENFILE problems.
Reopening the cache file, however, is a problem if this is being
done due to writeback triggered by exit(). Some filesystems will
oops if we try to open a file in that context because they want to
access current->fs or suchlike.
To get around this, I added the following:
(A) An inode flag, I_PINNING_FSCACHE_WB, to be set on a network
filesystem inode to indicate that we have a usage count on the
cookie caching that inode.
(B) A flag in struct writeback_control, unpinned_fscache_wb, that
is set when __writeback_single_inode() clears the last dirty
page from i_pages - at which point it clears
I_PINNING_FSCACHE_WB and sets this flag.
This has to be done here so that clearing I_PINNING_FSCACHE_WB
can be done atomically with the check of PAGECACHE_TAG_DIRTY
that clears I_DIRTY_PAGES.
(C) A function, fscache_set_page_dirty(), which if it is not set,
sets I_PINNING_FSCACHE_WB and calls fscache_use_cookie() to
pin the cache resources.
(D) A function, fscache_unpin_writeback(), to be called by
->write_inode() to unuse the cookie.
(E) A function, fscache_clear_inode_writeback(), to be called when
the inode is evicted, before clear_inode() is called. This
cleans up any lingering I_PINNING_FSCACHE_WB.
The network filesystem can then use these tools to make sure that
fscache_write_to_cache() can write locally modified data to the
cache as well as to the server.
For the future, I'm working on write helpers for netfs lib that
should allow this facility to be removed by keeping track of the
dirty regions separately - but that's incomplete at the moment and
is also going to be affected by folios, one way or another, since
it deals with pages"
Link: https://lore.kernel.org/all/510611.1641942444@warthog.procyon.org.uk/
Tested-by: Dominique Martinet <asmadeus@codewreck.org> # 9p
Tested-by: kafs-testing@auristor.com # afs
Tested-by: Jeff Layton <jlayton@kernel.org> # ceph
Tested-by: Dave Wysochanski <dwysocha@redhat.com> # nfs
Tested-by: Daire Byrne <daire@dneg.com> # nfs
* tag 'fscache-rewrite-20220111' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: (67 commits)
9p, afs, ceph, nfs: Use current_is_kswapd() rather than gfpflags_allow_blocking()
fscache: Add a tracepoint for cookie use/unuse
fscache: Rewrite documentation
ceph: add fscache writeback support
ceph: conversion to new fscache API
nfs: Implement cache I/O by accessing the cache directly
nfs: Convert to new fscache volume/cookie API
9p: Copy local writes to the cache when writing to the server
9p: Use fscache indexing rewrite and reenable caching
afs: Skip truncation on the server of data we haven't written yet
afs: Copy local writes to the cache when writing to the server
afs: Convert afs to use the new fscache API
fscache, cachefiles: Display stat of culling events
fscache, cachefiles: Display stats of no-space events
cachefiles: Allow cachefiles to actually function
fscache, cachefiles: Store the volume coherency data
cachefiles: Implement the I/O routines
cachefiles: Implement cookie resize for truncate
cachefiles: Implement begin and end I/O operation
cachefiles: Implement backing file wrangling
...
Diffstat (limited to 'fs')
75 files changed, 5100 insertions, 9207 deletions
diff --git a/fs/9p/cache.c b/fs/9p/cache.c index f2ba131cede1..55e108e5e133 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -16,186 +16,61 @@ #include "v9fs.h" #include "cache.h" -#define CACHETAG_LEN 11 - -struct fscache_netfs v9fs_cache_netfs = { - .name = "9p", - .version = 0, -}; - -/* - * v9fs_random_cachetag - Generate a random tag to be associated - * with a new cache session. - * - * The value of jiffies is used for a fairly randomly cache tag. - */ - -static -int v9fs_random_cachetag(struct v9fs_session_info *v9ses) +int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, + const char *dev_name) { - v9ses->cachetag = kmalloc(CACHETAG_LEN, GFP_KERNEL); - if (!v9ses->cachetag) - return -ENOMEM; + struct fscache_volume *vcookie; + char *name, *p; - return scnprintf(v9ses->cachetag, CACHETAG_LEN, "%lu", jiffies); -} - -const struct fscache_cookie_def v9fs_cache_session_index_def = { - .name = "9P.session", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; + name = kasprintf(GFP_KERNEL, "9p,%s,%s", + dev_name, v9ses->cachetag ?: v9ses->aname); + if (!name) + return -ENOMEM; -void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses) -{ - /* If no cache session tag was specified, we generate a random one. */ - if (!v9ses->cachetag) { - if (v9fs_random_cachetag(v9ses) < 0) { - v9ses->fscache = NULL; - kfree(v9ses->cachetag); - v9ses->cachetag = NULL; - return; + for (p = name; *p; p++) + if (*p == '/') + *p = ';'; + + vcookie = fscache_acquire_volume(name, NULL, NULL, 0); + p9_debug(P9_DEBUG_FSC, "session %p get volume %p (%s)\n", + v9ses, vcookie, name); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(name); + return PTR_ERR(vcookie); } + pr_err("Cache volume key already in use (%s)\n", name); + vcookie = NULL; } - - v9ses->fscache = fscache_acquire_cookie(v9fs_cache_netfs.primary_index, - &v9fs_cache_session_index_def, - v9ses->cachetag, - strlen(v9ses->cachetag), - NULL, 0, - v9ses, 0, true); - p9_debug(P9_DEBUG_FSC, "session %p get cookie %p\n", - v9ses, v9ses->fscache); -} - -void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses) -{ - p9_debug(P9_DEBUG_FSC, "session %p put cookie %p\n", - v9ses, v9ses->fscache); - fscache_relinquish_cookie(v9ses->fscache, NULL, false); - v9ses->fscache = NULL; -} - -static enum -fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data, - const void *buffer, - uint16_t buflen, - loff_t object_size) -{ - const struct v9fs_inode *v9inode = cookie_netfs_data; - - if (buflen != sizeof(v9inode->qid.version)) - return FSCACHE_CHECKAUX_OBSOLETE; - - if (memcmp(buffer, &v9inode->qid.version, - sizeof(v9inode->qid.version))) - return FSCACHE_CHECKAUX_OBSOLETE; - - return FSCACHE_CHECKAUX_OKAY; + v9ses->fscache = vcookie; + kfree(name); + return 0; } -const struct fscache_cookie_def v9fs_cache_inode_index_def = { - .name = "9p.inode", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = v9fs_cache_inode_check_aux, -}; - void v9fs_cache_inode_get_cookie(struct inode *inode) { struct v9fs_inode *v9inode; struct v9fs_session_info *v9ses; + __le32 version; + __le64 path; if (!S_ISREG(inode->i_mode)) return; v9inode = V9FS_I(inode); - if (v9inode->fscache) + if (WARN_ON(v9inode->fscache)) return; + version = cpu_to_le32(v9inode->qid.version); + path = cpu_to_le64(v9inode->qid.path); v9ses = v9fs_inode2v9ses(inode); - v9inode->fscache = fscache_acquire_cookie(v9ses->fscache, - &v9fs_cache_inode_index_def, - &v9inode->qid.path, - sizeof(v9inode->qid.path), - &v9inode->qid.version, - sizeof(v9inode->qid.version), - v9inode, - i_size_read(&v9inode->vfs_inode), - true); + v9inode->fscache = + fscache_acquire_cookie(v9fs_session_cache(v9ses), + 0, + &path, sizeof(path), + &version, sizeof(version), + i_size_read(&v9inode->vfs_inode)); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", inode, v9inode->fscache); } - -void v9fs_cache_inode_put_cookie(struct inode *inode) -{ - struct v9fs_inode *v9inode = V9FS_I(inode); - - if (!v9inode->fscache) - return; - p9_debug(P9_DEBUG_FSC, "inode %p put cookie %p\n", - inode, v9inode->fscache); - - fscache_relinquish_cookie(v9inode->fscache, &v9inode->qid.version, - false); - v9inode->fscache = NULL; -} - -void v9fs_cache_inode_flush_cookie(struct inode *inode) -{ - struct v9fs_inode *v9inode = V9FS_I(inode); - - if (!v9inode->fscache) - return; - p9_debug(P9_DEBUG_FSC, "inode %p flush cookie %p\n", - inode, v9inode->fscache); - - fscache_relinquish_cookie(v9inode->fscache, NULL, true); - v9inode->fscache = NULL; -} - -void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp) -{ - struct v9fs_inode *v9inode = V9FS_I(inode); - - if (!v9inode->fscache) - return; - - mutex_lock(&v9inode->fscache_lock); - - if ((filp->f_flags & O_ACCMODE) != O_RDONLY) - v9fs_cache_inode_flush_cookie(inode); - else - v9fs_cache_inode_get_cookie(inode); - - mutex_unlock(&v9inode->fscache_lock); -} - -void v9fs_cache_inode_reset_cookie(struct inode *inode) -{ - struct v9fs_inode *v9inode = V9FS_I(inode); - struct v9fs_session_info *v9ses; - struct fscache_cookie *old; - - if (!v9inode->fscache) - return; - - old = v9inode->fscache; - - mutex_lock(&v9inode->fscache_lock); - fscache_relinquish_cookie(v9inode->fscache, NULL, true); - - v9ses = v9fs_inode2v9ses(inode); - v9inode->fscache = fscache_acquire_cookie(v9ses->fscache, - &v9fs_cache_inode_index_def, - &v9inode->qid.path, - sizeof(v9inode->qid.path), - &v9inode->qid.version, - sizeof(v9inode->qid.version), - v9inode, - i_size_read(&v9inode->vfs_inode), - true); - p9_debug(P9_DEBUG_FSC, "inode %p revalidating cookie old %p new %p\n", - inode, old, v9inode->fscache); - - mutex_unlock(&v9inode->fscache_lock); -} diff --git a/fs/9p/cache.h b/fs/9p/cache.h index 7480b4b49fea..1923affcdc62 100644 --- a/fs/9p/cache.h +++ b/fs/9p/cache.h @@ -7,26 +7,15 @@ #ifndef _9P_CACHE_H #define _9P_CACHE_H -#define FSCACHE_USE_NEW_IO_API + #include <linux/fscache.h> #ifdef CONFIG_9P_FSCACHE -extern struct fscache_netfs v9fs_cache_netfs; -extern const struct fscache_cookie_def v9fs_cache_session_index_def; -extern const struct fscache_cookie_def v9fs_cache_inode_index_def; - -extern void v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses); -extern void v9fs_cache_session_put_cookie(struct v9fs_session_info *v9ses); +extern int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, + const char *dev_name); extern void v9fs_cache_inode_get_cookie(struct inode *inode); -extern void v9fs_cache_inode_put_cookie(struct inode *inode); -extern void v9fs_cache_inode_flush_cookie(struct inode *inode); -extern void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *filp); -extern void v9fs_cache_inode_reset_cookie(struct inode *inode); - -extern int __v9fs_cache_register(void); -extern void __v9fs_cache_unregister(void); #else /* CONFIG_9P_FSCACHE */ @@ -34,13 +23,5 @@ static inline void v9fs_cache_inode_get_cookie(struct inode *inode) { } -static inline void v9fs_cache_inode_put_cookie(struct inode *inode) -{ -} - -static inline void v9fs_cache_inode_set_cookie(struct inode *inode, struct file *file) -{ -} - #endif /* CONFIG_9P_FSCACHE */ #endif /* _9P_CACHE_H */ diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index e32dd5f7721b..08f65c40af4f 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -469,7 +469,11 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, #ifdef CONFIG_9P_FSCACHE /* register the session for caching */ - v9fs_cache_session_get_cookie(v9ses); + if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) { + rc = v9fs_cache_session_get_cookie(v9ses, dev_name); + if (rc < 0) + goto err_clnt; + } #endif spin_lock(&v9fs_sessionlist_lock); list_add(&v9ses->slist, &v9fs_sessionlist); @@ -502,8 +506,7 @@ void v9fs_session_close(struct v9fs_session_info *v9ses) } #ifdef CONFIG_9P_FSCACHE - if (v9ses->fscache) - v9fs_cache_session_put_cookie(v9ses); + fscache_relinquish_volume(v9fs_session_cache(v9ses), NULL, false); kfree(v9ses->cachetag); #endif kfree(v9ses->uname); @@ -665,20 +668,12 @@ static int v9fs_cache_register(void) ret = v9fs_init_inode_cache(); if (ret < 0) return ret; -#ifdef CONFIG_9P_FSCACHE - ret = fscache_register_netfs(&v9fs_cache_netfs); - if (ret < 0) - v9fs_destroy_inode_cache(); -#endif return ret; } static void v9fs_cache_unregister(void) { v9fs_destroy_inode_cache(); -#ifdef CONFIG_9P_FSCACHE - fscache_unregister_netfs(&v9fs_cache_netfs); -#endif } /** diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 1647a8e63671..bc8b30205d36 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -89,7 +89,7 @@ struct v9fs_session_info { unsigned int cache; #ifdef CONFIG_9P_FSCACHE char *cachetag; - struct fscache_cookie *fscache; + struct fscache_volume *fscache; #endif char *uname; /* user name to mount as */ @@ -109,7 +109,6 @@ struct v9fs_session_info { struct v9fs_inode { #ifdef CONFIG_9P_FSCACHE - struct mutex fscache_lock; struct fscache_cookie *fscache; #endif struct p9_qid qid; @@ -133,6 +132,16 @@ static inline struct fscache_cookie *v9fs_inode_cookie(struct v9fs_inode *v9inod #endif } +static inline struct fscache_volume *v9fs_session_cache(struct v9fs_session_info *v9ses) +{ +#ifdef CONFIG_9P_FSCACHE + return v9ses->fscache; +#else + return NULL; +#endif +} + + extern int v9fs_show_options(struct seq_file *m, struct dentry *root); struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses, diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index fac918ccb305..c72e9f8f5f32 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -16,6 +16,7 @@ #include <linux/pagemap.h> #include <linux/idr.h> #include <linux/sched.h> +#include <linux/swap.h> #include <linux/uio.h> #include <linux/netfs.h> #include <net/9p/9p.h> @@ -78,7 +79,7 @@ static bool v9fs_is_cache_enabled(struct inode *inode) { struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(inode)); - return fscache_cookie_enabled(cookie) && !hlist_empty(&cookie->backing_objects); + return fscache_cookie_enabled(cookie) && cookie->cache_priv; } /** @@ -87,9 +88,13 @@ static bool v9fs_is_cache_enabled(struct inode *inode) */ static int v9fs_begin_cache_operation(struct netfs_read_request *rreq) { +#ifdef CONFIG_9P_FSCACHE struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode)); - return fscache_begin_read_operation(rreq, cookie); + return fscache_begin_read_operation(&rreq->cache_resources, cookie); +#else + return -ENOBUFS; +#endif } static const struct netfs_read_request_ops v9fs_req_ops = { @@ -133,16 +138,18 @@ static void v9fs_vfs_readahead(struct readahead_control *ractl) static int v9fs_release_page(struct page *page, gfp_t gfp) { struct folio *folio = page_folio(page); + struct inode *inode = folio_inode(folio); if (folio_test_private(folio)) return 0; #ifdef CONFIG_9P_FSCACHE if (folio_test_fscache(folio)) { - if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) + if (current_is_kswapd() || !(gfp & __GFP_FS)) return 0; folio_wait_fscache(folio); } #endif + fscache_note_page_release(v9fs_inode_cookie(V9FS_I(inode))); return 1; } @@ -161,10 +168,25 @@ static void v9fs_invalidate_page(struct page *page, unsigned int offset, folio_wait_fscache(folio); } +static void v9fs_write_to_cache_done(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct v9fs_inode *v9inode = priv; + __le32 version; + + if (IS_ERR_VALUE(transferred_or_error) && + transferred_or_error != -ENOBUFS) { + version = cpu_to_le32(v9inode->qid.version); + fscache_invalidate(v9fs_inode_cookie(v9inode), &version, + i_size_read(&v9inode->vfs_inode), 0); + } +} + static int v9fs_vfs_write_folio_locked(struct folio *folio) { struct inode *inode = folio_inode(folio); struct v9fs_inode *v9inode = V9FS_I(inode); + struct fscache_cookie *cookie = v9fs_inode_cookie(v9inode); loff_t start = folio_pos(folio); loff_t i_size = i_size_read(inode); struct iov_iter from; @@ -181,10 +203,21 @@ static int v9fs_vfs_write_folio_locked(struct folio *folio) /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); + folio_wait_fscache(folio); folio_start_writeback(folio); p9_client_write(v9inode->writeback_fid, start, &from, &err); + if (err == 0 && + fscache_cookie_enabled(cookie) && + test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) { + folio_start_fscache(folio); + fscache_write_to_cache(v9fs_inode_cookie(v9inode), + folio_mapping(folio), start, len, i_size, + v9fs_write_to_cache_done, v9inode, + true); + } + folio_end_writeback(folio); return err; } @@ -303,6 +336,7 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, loff_t last_pos = pos + copied; struct folio *folio = page_folio(subpage); struct inode *inode = mapping->host; + struct v9fs_inode *v9inode = V9FS_I(inode); p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); @@ -322,6 +356,7 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, if (last_pos > inode->i_size) { inode_add_bytes(inode, last_pos - inode->i_size); i_size_write(inode, last_pos); + fscache_update_cookie(v9fs_inode_cookie(v9inode), NULL, &last_pos); } folio_mark_dirty(folio); out: @@ -331,11 +366,25 @@ out: return copied; } +#ifdef CONFIG_9P_FSCACHE +/* + * Mark a page as having been made dirty and thus needing writeback. We also + * need to pin the cache object to write back to. + */ +static int v9fs_set_page_dirty(struct page *page) +{ + struct v9fs_inode *v9inode = V9FS_I(page->mapping->host); + + return fscache_set_page_dirty(page, v9fs_inode_cookie(v9inode)); +} +#else +#define v9fs_set_page_dirty __set_page_dirty_nobuffers +#endif const struct address_space_operations v9fs_addr_operations = { .readpage = v9fs_vfs_readpage, .readahead = v9fs_vfs_readahead, - .set_page_dirty = __set_page_dirty_nobuffers, + .set_page_dirty = v9fs_set_page_dirty, .writepage = v9fs_vfs_writepage, .write_begin = v9fs_write_begin, .write_end = v9fs_write_end, diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 8c854d8cb0cd..958680f7f23e 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -17,6 +17,7 @@ #include <linux/idr.h> #include <linux/slab.h> #include <linux/uio.h> +#include <linux/fscache.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -205,7 +206,10 @@ static int v9fs_dir_readdir_dotl(struct file *file, struct dir_context *ctx) int v9fs_dir_release(struct inode *inode, struct file *filp) { + struct v9fs_inode *v9inode = V9FS_I(inode); struct p9_fid *fid; + __le32 version; + loff_t i_size; fid = filp->private_data; p9_debug(P9_DEBUG_VFS, "inode: %p filp: %p fid: %d\n", @@ -216,6 +220,15 @@ int v9fs_dir_release(struct inode *inode, struct file *filp) spin_unlock(&inode->i_lock); p9_client_clunk(fid); } + + if ((filp->f_mode & FMODE_WRITE)) { + version = cpu_to_le32(v9inode->qid.version); + i_size = i_size_read(inode); + fscache_unuse_cookie(v9fs_inode_cookie(v9inode), + &version, &i_size); + } else { + fscache_unuse_cookie(v9fs_inode_cookie(v9inode), NULL, NULL); + } return 0; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 612e297f3763..be72ad9edb3e 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -93,7 +93,8 @@ int v9fs_file_open(struct inode *inode, struct file *file) } mutex_unlock(&v9inode->v_mutex); if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - v9fs_cache_inode_set_cookie(inode, file); + fscache_use_cookie(v9fs_inode_cookie(v9inode), + file->f_mode & FMODE_WRITE); v9fs_open_fid_add(inode, fid); return 0; out_error: diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 328c338ff304..2a10242c79c7 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -233,7 +233,6 @@ struct inode *v9fs_alloc_inode(struct super_block *sb) return NULL; #ifdef CONFIG_9P_FSCACHE v9inode->fscache = NULL; - mutex_init(&v9inode->fscache_lock); #endif v9inode->writeback_fid = NULL; v9inode->cache_validity = 0; @@ -381,12 +380,16 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) void v9fs_evict_inode(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); + __le32 version; truncate_inode_pages_final(&inode->i_data); + version = cpu_to_le32(v9inode->qid.version); + fscache_clear_inode_writeback(v9fs_inode_cookie(v9inode), inode, + &version); clear_inode(inode); filemap_fdatawrite(&inode->i_data); - v9fs_cache_inode_put_cookie(inode); + fscache_relinquish_cookie(v9fs_inode_cookie(v9inode), false); /* clunk the fid stashed in writeback_fid */ if (v9inode->writeback_fid) { p9_client_clunk(v9inode->writeback_fid); @@ -869,7 +872,8 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry, file->private_data = fid; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - v9fs_cache_inode_set_cookie(d_inode(dentry), file); + fscache_use_cookie(v9fs_inode_cookie(v9inode), + file->f_mode & FMODE_WRITE); v9fs_open_fid_add(inode, fid); file->f_mode |= FMODE_CREATED; @@ -1072,6 +1076,8 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *iattr) { int retval, use_dentry = 0; + struct inode *inode = d_inode(dentry); + struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses; struct p9_fid *fid = NULL; struct p9_wstat wstat; @@ -1117,7 +1123,7 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, /* Write all dirty data */ if (d_is_reg(dentry)) - filemap_write_and_wait(d_inode(dentry)->i_mapping); + filemap_write_and_wait(inode->i_mapping); retval = p9_client_wstat(fid, &wstat); @@ -1128,13 +1134,15 @@ static int v9fs_vfs_setattr(struct user_namespace *mnt_userns, return retval; if ((iattr->ia_valid & ATTR_SIZE) && - iattr->ia_size != i_size_read(d_inode(dentry))) - truncate_setsize(d_inode(dentry), iattr->ia_size); + iattr->ia_size != i_size_read(inode)) { + truncate_setsize(inode, iattr->ia_size); + fscache_resize_cookie(v9fs_inode_cookie(v9inode), iattr->ia_size); + } - v9fs_invalidate_inode_attr(d_inode(dentry)); + v9fs_invalidate_inode_attr(inode); - setattr_copy(&init_user_ns, d_inode(dentry), iattr); - mark_inode_dirty(d_inode(dentry)); + setattr_copy(&init_user_ns, inode, iattr); + mark_inode_dirty(inode); return 0; } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 7dee89ba32e7..cae301d09cd3 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -344,7 +344,8 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry, goto err_clunk_old_fid; file->private_data = ofid; if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - v9fs_cache_inode_set_cookie(inode, file); + fscache_use_cookie(v9fs_inode_cookie(v9inode), + file->f_mode & FMODE_WRITE); v9fs_open_fid_add(inode, ofid); file->f_mode |= FMODE_CREATED; out: diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index b739e02f5ef7..97e23b4e6982 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -20,6 +20,7 @@ #include <linux/slab.h> #include <linux/statfs.h> #include <linux/magic.h> +#include <linux/fscache.h> #include <net/9p/9p.h> #include <net/9p/client.h> @@ -309,6 +310,7 @@ static int v9fs_write_inode(struct inode *inode, __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return ret; } + fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); return 0; } @@ -332,6 +334,7 @@ static int v9fs_write_inode_dotl(struct inode *inode, __mark_inode_dirty(inode, I_DIRTY_DATASYNC); return ret; } + fscache_unpin_writeback(wbc, v9fs_inode_cookie(v9inode)); return 0; } diff --git a/fs/afs/Makefile b/fs/afs/Makefile index 75c4e4043d1d..e8956b65d7ff 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -3,10 +3,7 @@ # Makefile for Red Hat Linux AFS client. # -afs-cache-$(CONFIG_AFS_FSCACHE) := cache.o - kafs-y := \ - $(afs-cache-y) \ addr_list.o \ callback.o \ cell.o \ diff --git a/fs/afs/cache.c b/fs/afs/cache.c deleted file mode 100644 index 037af93e3aba..000000000000 --- a/fs/afs/cache.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* AFS caching stuff - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/sched.h> -#include "internal.h" - -static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, - const void *buffer, - uint16_t buflen, - loff_t object_size); - -struct fscache_netfs afs_cache_netfs = { - .name = "afs", - .version = 2, -}; - -struct fscache_cookie_def afs_cell_cache_index_def = { - .name = "AFS.cell", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -struct fscache_cookie_def afs_volume_cache_index_def = { - .name = "AFS.volume", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -struct fscache_cookie_def afs_vnode_cache_index_def = { - .name = "AFS.vnode", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = afs_vnode_cache_check_aux, -}; - -/* - * check that the auxiliary data indicates that the entry is still valid - */ -static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, - const void *buffer, - uint16_t buflen, - loff_t object_size) -{ - struct afs_vnode *vnode = cookie_netfs_data; - struct afs_vnode_cache_aux aux; - - _enter("{%llx,%x,%llx},%p,%u", - vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version, - buffer, buflen); - - memcpy(&aux, buffer, sizeof(aux)); - - /* check the size of the data is what we're expecting */ - if (buflen != sizeof(aux)) { - _leave(" = OBSOLETE [len %hx != %zx]", buflen, sizeof(aux)); - return FSCACHE_CHECKAUX_OBSOLETE; - } - - if (vnode->status.data_version != aux.data_version) { - _leave(" = OBSOLETE [vers %llx != %llx]", - aux.data_version, vnode->status.data_version); - return FSCACHE_CHECKAUX_OBSOLETE; - } - - _leave(" = SUCCESS"); - return FSCACHE_CHECKAUX_OKAY; -} diff --git a/fs/afs/cell.c b/fs/afs/cell.c index d88407fb9bc0..07ad744eef77 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -680,13 +680,6 @@ static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell) return ret; } -#ifdef CONFIG_AFS_FSCACHE - cell->cache = fscache_acquire_cookie(afs_cache_netfs.primary_index, - &afs_cell_cache_index_def, - cell->name, strlen(cell->name), - NULL, 0, - cell, 0, true); -#endif ret = afs_proc_cell_setup(cell); if (ret < 0) return ret; @@ -723,11 +716,6 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell) afs_dynroot_rmdir(net, cell); mutex_unlock(&net->proc_cells_lock); -#ifdef CONFIG_AFS_FSCACHE - fscache_relinquish_cookie(cell->cache, NULL, false); - cell->cache = NULL; -#endif - _leave(""); } diff --git a/fs/afs/file.c b/fs/afs/file.c index afe4b803f84b..720818a7c166 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -14,6 +14,7 @@ #include <linux/gfp.h> #include <linux/task_io_accounting_ops.h> #include <linux/mm.h> +#include <linux/swap.h> #include <linux/netfs.h> #include "internal.h" @@ -158,7 +159,9 @@ int afs_open(struct inode *inode, struct file *file) if (file->f_flags & O_TRUNC) set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - + + fscache_use_cookie(afs_vnode_cache(vnode), file->f_mode & FMODE_WRITE); + file->private_data = af; _leave(" = 0"); return 0; @@ -177,8 +180,10 @@ error: */ int afs_release(struct inode *inode, struct file *file) { + struct afs_vnode_cache_aux aux; struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_file *af = file->private_data; + loff_t i_size; int ret = 0; _enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode); @@ -189,6 +194,15 @@ int afs_release(struct inode *inode, struct file *file) file->private_data = NULL; if (af->wb) afs_put_wb_key(af->wb); + + if ((file->f_mode & FMODE_WRITE)) { + i_size = i_size_read(&vnode->vfs_inode); + afs_set_cache_aux(vnode, &aux); + fscache_unuse_cookie(afs_vnode_cache(vnode), &aux, &i_size); + } else { + fscache_unuse_cookie(afs_vnode_cache(vnode), NULL, NULL); + } + key_put(af->key); kfree(af); afs_prune_wb_keys(vnode); @@ -354,14 +368,19 @@ static bool afs_is_cache_enabled(struct inode *inode) { struct fscache_cookie *cookie = afs_vnode_cache(AFS_FS_I(inode)); - return fscache_cookie_enabled(cookie) && !hlist_empty(&cookie->backing_objects); + return fscache_cookie_enabled(cookie) && cookie->cache_priv; } static int afs_begin_cache_operation(struct netfs_read_request *rreq) { +#ifdef CONFIG_AFS_FSCACHE struct afs_vnode *vnode = AFS_FS_I(rreq->inode); - return fscache_begin_read_operation(rreq, afs_vnode_cache(vnode)); + return fscache_begin_read_operation(&rreq->cache_resources, + afs_vnode_cache(vnode)); +#else + return -ENOBUFS; +#endif } static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, @@ -398,6 +417,12 @@ static void afs_readahead(struct readahead_control *ractl) netfs_readahead(ractl, &afs_req_ops, NULL); } +int afs_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + fscache_unpin_writeback(wbc, afs_vnode_cache(AFS_FS_I(inode))); + return 0; +} + /* * Adjust the dirty region of the page on truncation or full invalidation, * getting rid of the markers altogether if the region is entirely invalidated. @@ -480,23 +505,24 @@ static void afs_invalidatepage(struct page *page, unsigned int offset, * release a page and clean up its private state if it's not busy * - return true if the page can now be released, false if not */ -static int afs_releasepage(struct page *page, gfp_t gfp_flags) +static int afs_releasepage(struct page *page, gfp_t gfp) { struct folio *folio = page_folio(page); struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); _enter("{{%llx:%llu}[%lu],%lx},%x", vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags, - gfp_flags); + gfp); /* deny if page is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE if (folio_test_fscache(folio)) { - if (!(gfp_flags & __GFP_DIRECT_RECLAIM) || !(gfp_flags & __GFP_FS)) + if (current_is_kswapd() || !(gfp & __GFP_FS)) return false; folio_wait_fscache(folio); } + fscache_note_page_release(afs_vnode_cache(vnode)); #endif if (folio_test_private(folio)) { diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 16906eb592d9..5964f8aee090 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -413,9 +413,9 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) { #ifdef CONFIG_AFS_FSCACHE struct { - u32 vnode_id; - u32 unique; - u32 vnode_id_ext[2]; /* Allow for a 96-bit key */ + __be32 vnode_id; + __be32 unique; + __be32 vnode_id_ext[2]; /* Allow for a 96-bit key */ } __packed key; struct afs_vnode_cache_aux aux; @@ -424,17 +424,18 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) return; } - key.vnode_id = vnode->fid.vnode; - key.unique = vnode->fid.unique; - key.vnode_id_ext[0] = vnode->fid.vnode >> 32; - key.vnode_id_ext[1] = vnode->fid.vnode_hi; - aux.data_version = vnode->status.data_version; - - vnode->cache = fscache_acquire_cookie(vnode->volume->cache, - &afs_vnode_cache_index_def, - &key, sizeof(key), - &aux, sizeof(aux), - vnode, vnode->status.size, true); + key.vnode_id = htonl(vnode->fid.vnode); + key.unique = htonl(vnode->fid.unique); + key.vnode_id_ext[0] = htonl(vnode->fid.vnode >> 32); + key.vnode_id_ext[1] = htonl(vnode->fid.vnode_hi); + afs_set_cache_aux(vnode, &aux); + + vnode->cache = fscache_acquire_cookie( + vnode->volume->cache, + vnode->status.type == AFS_FTYPE_FILE ? 0 : FSCACHE_ADV_SINGLE_CHUNK, + &key, sizeof(key), + &aux, sizeof(aux), + vnode->status.size); #endif } @@ -563,9 +564,7 @@ static void afs_zap_data(struct afs_vnode *vnode) { _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); -#ifdef CONFIG_AFS_FSCACHE - fscache_invalidate(vnode->cache); -#endif + afs_invalidate_cache(vnode, 0); /* nuke all the non-dirty pages that aren't locked, mapped or being * written back in a regular file and completely discard the pages in a @@ -762,9 +761,8 @@ int afs_drop_inode(struct inode *inode) */ void afs_evict_inode(struct inode *inode) { - struct afs_vnode *vnode; - - vnode = AFS_FS_I(inode); + struct afs_vnode_cache_aux aux; + struct afs_vnode *vnode = AFS_FS_I(inode); _enter("{%llx:%llu.%d}", vnode->fid.vid, @@ -776,6 +774,9 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); truncate_inode_pages_final(&inode->i_data); + + afs_set_cache_aux(vnode, &aux); + fscache_clear_inode_writeback(afs_vnode_cache(vnode), inode, &aux); clear_inode(inode); while (!list_empty(&vnode->wb_keys)) { @@ -786,14 +787,9 @@ void afs_evict_inode(struct inode *inode) } #ifdef CONFIG_AFS_FSCACHE - { - struct afs_vnode_cache_aux aux; - - aux.data_version = vnode->status.data_version; - fscache_relinquish_cookie(vnode->cache, &aux, - test_bit(AFS_VNODE_DELETED, &vnode->flags)); - vnode->cache = NULL; - } + fscache_relinquish_cookie(vnode->cache, + test_bit(AFS_VNODE_DELETED, &vnode->flags)); + vnode->cache = NULL; #endif afs_prune_wb_keys(vnode); @@ -833,6 +829,9 @@ static void afs_setattr_edit_file(struct afs_operation *op) if (size < i_size) truncate_pagecache(inode, size); + if (size != i_size) + fscache_resize_cookie(afs_vnode_cache(vp->vnode), + vp->scb.status.size); } } @@ -849,40 +848,67 @@ static const struct afs_operation_ops afs_setattr_operation = { int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) { + const unsigned int supported = + ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID | + ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | ATTR_TOUCH; struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); + struct inode *inode = &vnode->vfs_inode; + loff_t i_size; int ret; _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, attr->ia_valid); - if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID | - ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | - ATTR_TOUCH))) { + if (!(attr->ia_valid & supported)) { _leave(" = 0 [unsupported]"); return 0; } + i_size = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { - if (!S_ISREG(vnode->vfs_inode.i_mode)) + if (!S_ISREG(inode->i_mode)) return -EISDIR; - ret = inode_newsize_ok(&vnode->vfs_inode, attr->ia_size); + ret = inode_newsize_ok(inode, attr->ia_size); if (ret) return ret; - if (attr->ia_size == i_size_read(&vnode->vfs_inode)) + if (attr->ia_size == i_size) attr->ia_valid &= ~ATTR_SIZE; } - /* flush any dirty data outstanding on a regular file */ - if (S_ISREG(vnode->vfs_inode.i_mode)) - filemap_write_and_wait(vnode->vfs_inode.i_mapping); + fscache_use_cookie(afs_vnode_cache(vnode), true); /* Prevent any new writebacks from starting whilst we do this. */ down_write(&vnode->validate_lock); + if ((attr->ia_valid & ATTR_SIZE) && S_ISREG(inode->i_mode)) { + loff_t size = attr->ia_size; + + /* Wait for any outstanding writes to the server to complete */ + loff_t from = min(size, i_size); + loff_t to = max(size, i_size); + ret = filemap_fdatawait_range(inode->i_mapping, from, to); + if (ret < 0) + goto out_unlock; + + /* Don't talk to the server if we're just shortening in-memory + * writes that haven't gone to the server yet. + */ + if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) && + attr->ia_size < i_size && + attr->ia_size > vnode->status.size) { + truncate_pagecache(inode, attr->ia_size); + fscache_resize_cookie(afs_vnode_cache(vnode), + attr->ia_size); + i_size_write(inode, attr->ia_size); + ret = 0; + goto out_unlock; + } + } + op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ? afs_file_key(attr->ia_file) : NULL), vnode->volume); @@ -907,6 +933,7 @@ int afs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, out_unlock: up_write(&vnode->validate_lock); + fscache_unuse_cookie(afs_vnode_cache(vnode), NULL, NULL); _leave(" = %d", ret); return ret; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index aa4c0d6c9780..b6f02321fc09 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -14,7 +14,6 @@ #include <linux/key.h> #include <linux/workqueue.h> #include <linux/sched.h> -#define FSCACHE_USE_NEW_IO_API #include <linux/fscache.h> #include <linux/backing-dev.h> #include <linux/uuid.h> @@ -364,9 +363,6 @@ struct afs_cell { struct key *anonymous_key; /* anonymous user key for this cell */ struct work_struct manager; /* Manager for init/deinit/dns */ struct hlist_node proc_link; /* /proc cell list link */ -#ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ -#endif time64_t dns_expiry; /* Time AFSDB/SRV record expires */ time64_t last_inactive; /* Time of last drop of usage count */ atomic_t ref; /* Struct refcount */ @@ -590,7 +586,7 @@ struct afs_volume { #define AFS_VOLUME_BUSY 5 /* - T if volume busy notice given */ #define AFS_VOLUME_MAYBE_NO_IBULK 6 /* - T if some servers don't have InlineBulkStatus */ #ifdef CONFIG_AFS_FSCACHE - struct fscache_cookie *cache; /* caching cookie */ + struct fscache_volume *cache; /* Caching cookie */ #endif struct afs_server_list __rcu *servers; /* List of servers on which volume resides */ rwlock_t servers_lock; /* Lock for ->servers */ @@ -872,9 +868,24 @@ struct afs_operation { * Cache auxiliary data. */ struct afs_vnode_cache_aux { - u64 data_version; + __be64 data_version; } __packed; +static inline void afs_set_cache_aux(struct afs_vnode *vnode, + struct afs_vnode_cache_aux *aux) +{ + aux->data_version = cpu_to_be64(vnode->status.data_version); +} + +static inline void afs_invalidate_cache(struct afs_vnode *vnode, unsigned int flags) +{ + struct afs_vnode_cache_aux aux; + + afs_set_cache_aux(vnode, &aux); + fscache_invalidate(afs_vnode_cache(vnode), &aux, + i_size_read(&vnode->vfs_inode), flags); +} + /* * We use folio->private to hold the amount of the folio that we've written to, * splitting the field into two parts. However, we need to represent a range @@ -962,13 +973,6 @@ extern void afs_merge_fs_addr6(struct afs_addr_list *, __be32 *, u16); */ #ifdef CONFIG_AFS_FSCACHE extern struct fscache_netfs afs_cache_netfs; -extern struct fscache_cookie_def afs_cell_cache_index_def; -extern struct fscache_cookie_def afs_volume_cache_index_def; -extern struct fscache_cookie_def afs_vnode_cache_index_def; -#else -#define afs_cell_cache_index_def (*(struct fscache_cookie_def *) NULL) -#define afs_volume_cache_index_def (*(struct fscache_cookie_def *) NULL) -#define afs_vnode_cache_index_def (*(struct fscache_cookie_def *) NULL) #endif /* @@ -1068,6 +1072,7 @@ extern int afs_release(struct inode *, struct file *); extern int afs_fetch_data(struct afs_vnode *, struct afs_read *); extern struct afs_read *afs_alloc_read(gfp_t); extern void afs_put_read(struct afs_read *); +extern int afs_write_inode(struct inode *, struct writeback_control *); static inline struct afs_read *afs_get_read(struct afs_read *req) { @@ -1506,7 +1511,7 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, * volume.c */ extern struct afs_volume *afs_create_volume(struct afs_fs_context *); -extern void afs_activate_volume(struct afs_volume *); +extern int afs_activate_volume(struct afs_volume *); extern void afs_deactivate_volume(struct afs_volume *); extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace); extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace); @@ -1515,7 +1520,11 @@ extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); /* * write.c */ +#ifdef CONFIG_AFS_FSCACHE extern int afs_set_page_dirty(struct page *); +#else +#define afs_set_page_dirty __set_page_dirty_nobuffers +#endif extern int afs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); diff --git a/fs/afs/main.c b/fs/afs/main.c index 179004b15566..eae288c8d40a 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -186,13 +186,6 @@ static int __init afs_init(void) if (!afs_lock_manager) goto error_lockmgr; -#ifdef CONFIG_AFS_FSCACHE - /* we want to be able to cache */ - ret = fscache_register_netfs(&afs_cache_netfs); - if (ret < 0) - goto error_cache; -#endif - ret = register_pernet_device(&afs_net_ops); if (ret < 0) goto error_net; @@ -215,10 +208,6 @@ error_proc: error_fs: unregister_pernet_device(&afs_net_ops); error_net: -#ifdef CONFIG_AFS_FSCACHE - fscache_unregister_netfs(&afs_cache_netfs); -error_cache: -#endif destroy_workqueue(afs_lock_manager); error_lockmgr: destroy_workqueue(afs_async_calls); @@ -245,9 +234,6 @@ static void __exit afs_exit(void) proc_remove(afs_proc_symlink); afs_fs_exit(); unregister_pernet_device(&afs_net_ops); -#ifdef CONFIG_AFS_FSCACHE - fscache_unregister_netfs(&afs_cache_netfs); -#endif destroy_workqueue(afs_lock_manager); destroy_workqueue(afs_async_calls); destroy_workqueue(afs_wq); diff --git a/fs/afs/super.c b/fs/afs/super.c index 34c68724c98b..5ec9fd97eccc 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -55,6 +55,7 @@ int afs_net_id; static const struct super_operations afs_super_ops = { .statfs = afs_statfs, .alloc_inode = afs_alloc_inode, + .write_inode = afs_write_inode, .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .free_inode = afs_free_inode, diff --git a/fs/afs/volume.c b/fs/afs/volume.c index f84194b791d3..94a3d247924b 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -268,15 +268,30 @@ void afs_put_volume(struct afs_net *net, struct afs_volume *volume, /* * Activate a volume. */ -void afs_activate_volume(struct afs_volume *volume) +int afs_activate_volume(struct afs_volume *volume) { #ifdef CONFIG_AFS_FSCACHE - volume->cache = fscache_acquire_cookie(volume->cell->cache, - &afs_volume_cache_index_def, - &volume->vid, sizeof(volume->vid), - NULL, 0, - volume, 0, true); + struct fscache_volume *vcookie; + char *name; + + name = kasprintf(GFP_KERNEL, "afs,%s,%llx", + volume->cell->name, volume->vid); + if (!name) + return -ENOMEM; + + vcookie = fscache_acquire_volume(name, NULL, NULL, 0); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(name); + return PTR_ERR(vcookie); + } + pr_err("AFS: Cache volume key already in use (%s)\n", name); + vcookie = NULL; + } + volume->cache = vcookie; + kfree(name); #endif + return 0; } /* @@ -287,7 +302,7 @@ void afs_deactivate_volume(struct afs_volume *volume) _enter("%s", volume->name); #ifdef CONFIG_AFS_FSCACHE - fscache_relinquish_cookie(volume->cache, NULL, + fscache_relinquish_volume(volume->cache, NULL, test_bit(AFS_VOLUME_DELETED, &volume->flags)); volume->cache = NULL; #endif diff --git a/fs/afs/write.c b/fs/afs/write.c index ca4909baf5e6..5e9157d0da29 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -12,17 +12,30 @@ #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/netfs.h> -#include <linux/fscache.h> #include "internal.h" +static void afs_write_to_cache(struct afs_vnode *vnode, loff_t start, size_t len, + loff_t i_size, bool caching); + +#ifdef CONFIG_AFS_FSCACHE /* - * mark a page as having been made dirty and thus needing writeback + * Mark a page as having been made dirty and thus needing writeback. We also + * need to pin the cache object to write back to. */ int afs_set_page_dirty(struct page *page) { - _enter(""); - return __set_page_dirty_nobuffers(page); + return fscache_set_page_dirty(page, afs_vnode_cache(AFS_FS_I(page->mapping->host))); +} +static void afs_folio_start_fscache(bool caching, struct folio *folio) +{ + if (caching) + folio_start_fscache(folio); +} +#else +static void afs_folio_start_fscache(bool caching, struct folio *folio) +{ } +#endif /* * prepare to perform part of a write to a page @@ -114,7 +127,7 @@ int afs_write_end(struct file *file, struct address_space *mapping, unsigned long priv; unsigned int f, from = offset_in_folio(folio, pos); unsigned int t, to = from + copied; - loff_t i_size, maybe_i_size; + loff_t i_size, write_end_pos; _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); @@ -131,15 +144,16 @@ int afs_write_end(struct file *file, struct address_space *mapping, if (copied == 0) goto out; - maybe_i_size = pos + copied; + write_end_pos = pos + copied; i_size = i_size_read(&vnode->vfs_inode); - if (maybe_i_size > i_size) { + if (write_end_pos > i_size) { write_seqlock(&vnode->cb_lock); i_size = i_size_read(&vnode->vfs_inode); - if (maybe_i_size > i_size) - afs_set_i_size(vnode, maybe_i_size); + if (write_end_pos > i_size) + afs_set_i_size(vnode, write_end_pos); write_sequnlock(&vnode->cb_lock); + fscache_update_cookie(afs_vnode_cache(vnode), NULL, &write_end_pos); } if (folio_test_private(folio)) { @@ -418,6 +432,7 @@ static void afs_extend_writeback(struct address_space *mapping, loff_t start, loff_t max_len, bool new_content, + bool caching, unsigned int *_len) { struct pagevec pvec; @@ -464,7 +479,9 @@ static void afs_extend_writeback(struct address_space *mapping, folio_put(folio); break; } - if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { + if (!folio_test_dirty(folio) || + folio_test_writeback(folio) || + folio_test_fscache(folio)) { folio_unlock(folio); folio_put(folio); break; @@ -512,6 +529,7 @@ static void afs_extend_writeback(struct address_space *mapping, BUG(); if (folio_start_writeback(folio)) BUG(); + afs_folio_start_fscache(caching, folio); *_count -= folio_nr_pages(folio); folio_unlock(folio); @@ -539,6 +557,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, unsigned int offset, to, len, max_len; loff_t i_size = i_size_read(&vnode->vfs_inode); bool new_content = test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); + bool caching = fscache_cookie_enabled(afs_vnode_cache(vnode)); long count = wbc->nr_to_write; int ret; @@ -546,6 +565,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, if (folio_start_writeback(folio)) BUG(); + afs_folio_start_fscache(caching, folio); count -= folio_nr_pages(folio); @@ -572,7 +592,8 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, if (len < max_len && (to == folio_size(folio) || new_content)) afs_extend_writeback(mapping, vnode, &count, - start, max_len, new_content, &len); + start, max_len, new_content, + caching, &len); len = min_t(loff_t, len, max_len); } @@ -585,12 +606,19 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, if (start < i_size) { _debug("write back %x @%llx [%llx]", len, start, i_size); + /* Speculatively write to the cache. We have to fix this up + * later if the store fails. + */ + afs_write_to_cache(vnode, start, len, i_size, caching); + iov_iter_xarray(&iter, WRITE, &mapping->i_pages, start, len); ret = afs_store_data(vnode, &iter, start, false); } else { _debug("write discard %x @%llx [%llx]", len, start, i_size); /* The dirty region was entirely beyond the EOF. */ + fscache_clear_page_bits(afs_vnode_cache(vnode), + mapping, start, len, caching); afs_pages_written_back(vnode, start, len); ret = 0; } @@ -649,6 +677,10 @@ int afs_writepage(struct page *subpage, struct writeback_control *wbc) _enter("{%lx},", folio_index(folio)); +#ifdef CONFIG_AFS_FSCACHE + folio_wait_fscache(folio); +#endif + start = folio_index(folio) * PAGE_SIZE; ret = afs_write_back_from_locked_folio(folio_mapping(folio), wbc, folio, start, LLONG_MAX - start); @@ -714,10 +746,15 @@ static int afs_writepages_region(struct address_space *mapping, continue; } - if (folio_test_writeback(folio)) { + if (folio_test_writeback(folio) || + folio_test_fscache(folio)) { folio_unlock(folio); - if (wbc->sync_mode != WB_SYNC_NONE) + if (wbc->sync_mode != WB_SYNC_NONE) { folio_wait_writeback(folio); +#ifdef CONFIG_AFS_FSCACHE + folio_wait_fscache(folio); +#endif + } folio_put(folio); continue; } @@ -970,3 +1007,28 @@ int afs_launder_page(struct page *subpage) folio_wait_fscache(folio); return ret; } + +/* + * Deal with the completion of writing the data to the cache. + */ +static void afs_write_to_cache_done(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct afs_vnode *vnode = priv; + + if (IS_ERR_VALUE(transferred_or_error) && + transferred_or_error != -ENOBUFS) + afs_invalidate_cache(vnode, 0); +} + +/* + * Save the write to the cache also. + */ +static void afs_write_to_cache(struct afs_vnode *vnode, + loff_t start, size_t len, loff_t i_size, + bool caching) +{ + fscache_write_to_cache(afs_vnode_cache(vnode), + vnode->vfs_inode.i_mapping, start, len, i_size, + afs_write_to_cache_done, vnode, caching); +} diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index 6827b40f7ddc..719faeeda168 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -19,3 +19,10 @@ config CACHEFILES_DEBUG caching on files module. If this is set, the debugging output may be enabled by setting bits in /sys/modules/cachefiles/parameter/debug or by including a debugging specifier in /etc/cachefilesd.conf. + +config CACHEFILES_ERROR_INJECTION + bool "Provide error injection for cachefiles" + depends on CACHEFILES && SYSCTL + help + This permits error injection to be enabled in cachefiles whilst a + cache is in service. diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile index 02fd17731769..16d811f1a2fa 100644 --- a/fs/cachefiles/Makefile +++ b/fs/cachefiles/Makefile @@ -4,15 +4,17 @@ # cachefiles-y := \ - bind.o \ + cache.o \ daemon.o \ interface.o \ io.o \ key.o \ main.o \ namei.o \ - rdwr.o \ security.o \ + volume.o \ xattr.o +cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o + obj-$(CONFIG_CACHEFILES) := cachefiles.o diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c deleted file mode 100644 index 146291be6263..000000000000 --- a/fs/cachefiles/bind.c +++ /dev/null @@ -1,278 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Bind and unbind a cache from the filesystem backing it - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/completion.h> -#include <linux/slab.h> -#include <linux/fs.h> -#include <linux/file.h> -#include <linux/namei.h> -#include <linux/mount.h> -#include <linux/statfs.h> -#include <linux/ctype.h> -#include <linux/xattr.h> -#include "internal.h" - -static int cachefiles_daemon_add_cache(struct cachefiles_cache *caches); - -/* - * bind a directory as a cache - */ -int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args) -{ - _enter("{%u,%u,%u,%u,%u,%u},%s", - cache->frun_percent, - cache->fcull_percent, - cache->fstop_percent, - cache->brun_percent, - cache->bcull_percent, - cache->bstop_percent, - args); - - /* start by checking things over */ - ASSERT(cache->fstop_percent >= 0 && - cache->fstop_percent < cache->fcull_percent && - cache->fcull_percent < cache->frun_percent && - cache->frun_percent < 100); - - ASSERT(cache->bstop_percent >= 0 && - cache->bstop_percent < cache->bcull_percent && - cache->bcull_percent < cache->brun_percent && - cache->brun_percent < 100); - - if (*args) { - pr_err("'bind' command doesn't take an argument\n"); - return -EINVAL; - } - - if (!cache->rootdirname) { - pr_err("No cache directory specified\n"); - return -EINVAL; - } - - /* don't permit already bound caches to be re-bound */ - if (test_bit(CACHEFILES_READY, &cache->flags)) { - pr_err("Cache already bound\n"); - return -EBUSY; - } - - /* make sure we have copies of the tag and dirname strings */ - if (!cache->tag) { - /* the tag string is released by the fops->release() - * function, so we don't release it on error here */ - cache->tag = kstrdup("CacheFiles", GFP_KERNEL); - if (!cache->tag) - return -ENOMEM; - } - - /* add the cache */ - return cachefiles_daemon_add_cache(cache); -} - -/* - * add a cache - */ -static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) -{ - struct cachefiles_object *fsdef; - struct path path; - struct kstatfs stats; - struct dentry *graveyard, *cachedir, *root; - const struct cred *saved_cred; - int ret; - - _enter(""); - - /* we want to work under the module's security ID */ - ret = cachefiles_get_security_ID(cache); - if (ret < 0) - return ret; - - cachefiles_begin_secure(cache, &saved_cred); - - /* allocate the root index object */ - ret = -ENOMEM; - - fsdef = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL); - if (!fsdef) - goto error_root_object; - - ASSERTCMP(fsdef->backer, ==, NULL); - - atomic_set(&fsdef->usage, 1); - fsdef->type = FSCACHE_COOKIE_TYPE_INDEX; - - /* look up the directory at the root of the cache */ - ret = kern_path(cache->rootdirname, LOOKUP_DIRECTORY, &path); - if (ret < 0) - goto error_open_root; - - cache->mnt = path.mnt; - root = path.dentry; - - ret = -EINVAL; - if (is_idmapped_mnt(path.mnt)) { - pr_warn("File cache on idmapped mounts not supported"); - goto error_unsupported; - } - - /* check parameters */ - ret = -EOPNOTSUPP; - if (d_is_negative(root) || - !d_backing_inode(root)->i_op->lookup || - !d_backing_inode(root)->i_op->mkdir || - !(d_backing_inode(root)->i_opflags & IOP_XATTR) || - !root->d_sb->s_op->statfs || - !root->d_sb->s_op->sync_fs) - goto error_unsupported; - - ret = -EROFS; - if (sb_rdonly(root->d_sb)) - goto error_unsupported; - - /* determine the security of the on-disk cache as this governs - * security ID of files we create */ - ret = cachefiles_determine_cache_security(cache, root, &saved_cred); - if (ret < 0) - goto error_unsupported; - - /* get the cache size and blocksize */ - ret = vfs_statfs(&path, &stats); - if (ret < 0) - goto error_unsupported; - - ret = -ERANGE; - if (stats.f_bsize <= 0) - goto error_unsupported; - - ret = -EOPNOTSUPP; - if (stats.f_bsize > PAGE_SIZE) - goto error_unsupported; - - cache->bsize = stats.f_bsize; - cache->bshift = 0; - if (stats.f_bsize < PAGE_SIZE) - cache->bshift = PAGE_SHIFT - ilog2(stats.f_bsize); - - _debug("blksize %u (shift %u)", - cache->bsize, cache->bshift); - - _debug("size %llu, avail %llu", - (unsigned long long) stats.f_blocks, - (unsigned long long) stats.f_bavail); - - /* set up caching limits */ - do_div(stats.f_files, 100); - cache->fstop = stats.f_files * cache->fstop_percent; - cache->fcull = stats.f_files * cache->fcull_percent; - cache->frun = stats.f_files * cache->frun_percent; - - _debug("limits {%llu,%llu,%llu} files", - (unsigned long long) cache->frun, - (unsigned long long) cache->fcull, - (unsigned long long) cache->fstop); - - stats.f_blocks >>= cache->bshift; - do_div(stats.f_blocks, 100); - cache->bstop = stats.f_blocks * cache->bstop_percent; - cache->bcull = stats.f_blocks * cache->bcull_percent; - cache->brun = stats.f_blocks * cache->brun_percent; - - _debug("limits {%llu,%llu,%llu} blocks", - (unsigned long long) cache->brun, - (unsigned long long) cache->bcull, - (unsigned long long) cache->bstop); - - /* get the cache directory and check its type */ - cachedir = cachefiles_get_directory(cache, root, "cache"); - if (IS_ERR(cachedir)) { - ret = PTR_ERR(cachedir); - goto error_unsupported; - } - - fsdef->dentry = cachedir; - fsdef->fscache.cookie = NULL; - - ret = cachefiles_check_object_type(fsdef); - if (ret < 0) - goto error_unsupported; - - /* get the graveyard directory */ - graveyard = cachefiles_get_directory(cache, root, "graveyard"); - if (IS_ERR(graveyard)) { - ret = PTR_ERR(graveyard); - goto error_unsupported; - } - - cache->graveyard = graveyard; - - /* publish the cache */ - fscache_init_cache(&cache->cache, - &cachefiles_cache_ops, - "%s", - fsdef->dentry->d_sb->s_id); - - fscache_object_init(&fsdef->fscache, &fscache_fsdef_index, - &cache->cache); - - ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag); - if (ret < 0) - goto error_add_cache; - - /* done */ - set_bit(CACHEFILES_READY, &cache->flags); - dput(root); - - pr_info("File cache on %s registered\n", cache->cache.identifier); - - /* check how much space the cache has */ - cachefiles_has_space(cache, 0, 0); - cachefiles_end_secure(cache, saved_cred); - return 0; - -error_add_cache: - dput(cache->graveyard); - cache->graveyard = NULL; -error_unsupported: - mntput(cache->mnt); - cache->mnt = NULL; - dput(fsdef->dentry); - fsdef->dentry = NULL; - dput(root); -error_open_root: - kmem_cache_free(cachefiles_object_jar, fsdef); -error_root_object: - cachefiles_end_secure(cache, saved_cred); - pr_err("Failed to register: %d\n", ret); - return ret; -} - -/* - * unbind a cache on fd release - */ -void cachefiles_daemon_unbind(struct cachefiles_cache *cache) -{ - _enter(""); - - if (test_bit(CACHEFILES_READY, &cache->flags)) { - pr_info("File cache on %s unregistering\n", - cache->cache.identifier); - - fscache_withdraw_cache(&cache->cache); - } - - dput(cache->graveyard); - mntput(cache->mnt); - - kfree(cache->rootdirname); - kfree(cache->secctx); - kfree(cache->tag); - - _leave(""); -} diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c new file mode 100644 index 000000000000..ce4d4785003c --- /dev/null +++ b/fs/cachefiles/cache.c @@ -0,0 +1,378 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Manage high-level VFS aspects of a cache. + * + * Copyright (C) 2007, 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/slab.h> +#include <linux/statfs.h> +#include <linux/namei.h> +#include "internal.h" + +/* + * Bring a cache online. + */ +int cachefiles_add_cache(struct cachefiles_cache *cache) +{ + struct fscache_cache *cache_cookie; + struct path path; + struct kstatfs stats; + struct dentry *graveyard, *cachedir, *root; + const struct cred *saved_cred; + int ret; + + _enter(""); + + cache_cookie = fscache_acquire_cache(cache->tag); + if (IS_ERR(cache_cookie)) + return PTR_ERR(cache_cookie); + + /* we want to work under the module's security ID */ + ret = cachefiles_get_security_ID(cache); + if (ret < 0) + goto error_getsec; + + cachefiles_begin_secure(cache, &saved_cred); + + /* look up the directory at the root of the cache */ + ret = kern_path(cache->rootdirname, LOOKUP_DIRECTORY, &path); + if (ret < 0) + goto error_open_root; + + cache->mnt = path.mnt; + root = path.dentry; + + ret = -EINVAL; + if (is_idmapped_mnt(path.mnt)) { + pr_warn("File cache on idmapped mounts not supported"); + goto error_unsupported; + } + + /* check parameters */ + ret = -EOPNOTSUPP; + if (d_is_negative(root) || + !d_backing_inode(root)->i_op->lookup || + !d_backing_inode(root)->i_op->mkdir || + !(d_backing_inode(root)->i_opflags & IOP_XATTR) || + !root->d_sb->s_op->statfs || + !root->d_sb->s_op->sync_fs || + root->d_sb->s_blocksize > PAGE_SIZE) + goto error_unsupported; + + ret = -EROFS; + if (sb_rdonly(root->d_sb)) + goto error_unsupported; + + /* determine the security of the on-disk cache as this governs + * security ID of files we create */ + ret = cachefiles_determine_cache_security(cache, root, &saved_cred); + if (ret < 0) + goto error_unsupported; + + /* get the cache size and blocksize */ + ret = vfs_statfs(&path, &stats); + if (ret < 0) + goto error_unsupported; + + ret = -ERANGE; + if (stats.f_bsize <= 0) + goto error_unsupported; + + ret = -EOPNOTSUPP; + if (stats.f_bsize > PAGE_SIZE) + goto error_unsupported; + + cache->bsize = stats.f_bsize; + cache->bshift = 0; + if (stats.f_bsize < PAGE_SIZE) + cache->bshift = PAGE_SHIFT - ilog2(stats.f_bsize); + + _debug("blksize %u (shift %u)", + cache->bsize, cache->bshift); + + _debug("size %llu, avail %llu", + (unsigned long long) stats.f_blocks, + (unsigned long long) stats.f_bavail); + + /* set up caching limits */ + do_div(stats.f_files, 100); + cache->fstop = stats.f_files * cache->fstop_percent; + cache->fcull = stats.f_files * cache->fcull_percent; + cache->frun = stats.f_files * cache->frun_percent; + + _debug("limits {%llu,%llu,%llu} files", + (unsigned long long) cache->frun, + (unsigned long long) cache->fcull, + (unsigned long long) cache->fstop); + + stats.f_blocks >>= cache->bshift; + do_div(stats.f_blocks, 100); + cache->bstop = stats.f_blocks * cache->bstop_percent; + cache->bcull = stats.f_blocks * cache->bcull_percent; + cache->brun = stats.f_blocks * cache->brun_percent; + + _debug("limits {%llu,%llu,%llu} blocks", + (unsigned long long) cache->brun, + (unsigned long long) cache->bcull, + (unsigned long long) cache->bstop); + + /* get the cache directory and check its type */ + cachedir = cachefiles_get_directory(cache, root, "cache", NULL); + if (IS_ERR(cachedir)) { + ret = PTR_ERR(cachedir); + goto error_unsupported; + } + + cache->store = cachedir; + + /* get the graveyard directory */ + graveyard = cachefiles_get_directory(cache, root, "graveyard", NULL); + if (IS_ERR(graveyard)) { + ret = PTR_ERR(graveyard); + goto error_unsupported; + } + + cache->graveyard = graveyard; + cache->cache = cache_cookie; + + ret = fscache_add_cache(cache_cookie, &cachefiles_cache_ops, cache); + if (ret < 0) + goto error_add_cache; + + /* done */ + set_bit(CACHEFILES_READY, &cache->flags); + dput(root); + + pr_info("File cache on %s registered\n", cache_cookie->name); + + /* check how much space the cache has */ + cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); + cachefiles_end_secure(cache, saved_cred); + _leave(" = 0 [%px]", cache->cache); + return 0; + +error_add_cache: + cachefiles_put_directory(cache->graveyard); + cache->graveyard = NULL; +error_unsupported: + cachefiles_put_directory(cache->store); + cache->store = NULL; + mntput(cache->mnt); + cache->mnt = NULL; + dput(root); +error_open_root: + cachefiles_end_secure(cache, saved_cred); +error_getsec: + fscache_relinquish_cache(cache_cookie); + cache->cache = NULL; + pr_err("Failed to register: %d\n", ret); + return ret; +} + +/* + * See if we have space for a number of pages and/or a number of files in the + * cache + */ +int cachefiles_has_space(struct cachefiles_cache *cache, + unsigned fnr, unsigned bnr, + enum cachefiles_has_space_for reason) +{ + struct kstatfs stats; + u64 b_avail, b_writing; + int ret; + + struct path path = { + .mnt = cache->mnt, + .dentry = cache->mnt->mnt_root, + }; + + //_enter("{%llu,%llu,%llu,%llu,%llu,%llu},%u,%u", + // (unsigned long long) cache->frun, + // (unsigned long long) cache->fcull, + // (unsigned long long) cache->fstop, + // (unsigned long long) cache->brun, + // (unsigned long long) cache->bcull, + // (unsigned long long) cache->bstop, + // fnr, bnr); + + /* find out how many pages of blockdev are available */ + memset(&stats, 0, sizeof(stats)); + + ret = vfs_statfs(&path, &stats); + if (ret < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(path.dentry), ret, + cachefiles_trace_statfs_error); + if (ret == -EIO) + cachefiles_io_error(cache, "statfs failed"); + _leave(" = %d", ret); + return ret; + } + + b_avail = stats.f_bavail >> cache->bshift; + b_writing = atomic_long_read(&cache->b_writing); + if (b_avail > b_writing) + b_avail -= b_writing; + else + b_avail = 0; + + //_debug("avail %llu,%llu", + // (unsigned long long)stats.f_ffree, + // (unsigned long long)b_avail); + + /* see if there is sufficient space */ + if (stats.f_ffree > fnr) + stats.f_ffree -= fnr; + else + stats.f_ffree = 0; + + if (b_avail > bnr) + b_avail -= bnr; + else + b_avail = 0; + + ret = -ENOBUFS; + if (stats.f_ffree < cache->fstop || + b_avail < cache->bstop) + goto stop_and_begin_cull; + + ret = 0; + if (stats.f_ffree < cache->fcull || + b_avail < cache->bcull) + goto begin_cull; + + if (test_bit(CACHEFILES_CULLING, &cache->flags) && + stats.f_ffree >= cache->frun && + b_avail >= cache->brun && + test_and_clear_bit(CACHEFILES_CULLING, &cache->flags) + ) { + _debug("cease culling"); + cachefiles_state_changed(cache); + } + + //_leave(" = 0"); + return 0; + +stop_and_begin_cull: + switch (reason) { + case cachefiles_has_space_for_write: + fscache_count_no_write_space(); + break; + case cachefiles_has_space_for_create: + fscache_count_no_create_space(); + break; + default: + break; + } +begin_cull: + if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) { + _debug("### CULL CACHE ###"); + cachefiles_state_changed(cache); + } + + _leave(" = %d", ret); + return ret; +} + +/* + * Mark all the objects as being out of service and queue them all for cleanup. + */ +static void cachefiles_withdraw_objects(struct cachefiles_cache *cache) +{ + struct cachefiles_object *object; + unsigned int count = 0; + + _enter(""); + + spin_lock(&cache->object_list_lock); + + while (!list_empty(&cache->object_list)) { + object = list_first_entry(&cache->object_list, + struct cachefiles_object, cache_link); + cachefiles_see_object(object, cachefiles_obj_see_withdrawal); + list_del_init(&object->cache_link); + fscache_withdraw_cookie(object->cookie); + count++; + if ((count & 63) == 0) { + spin_unlock(&cache->object_list_lock); + cond_resched(); + spin_lock(&cache->object_list_lock); + } + } + + spin_unlock(&cache->object_list_lock); + _leave(" [%u objs]", count); +} + +/* + * Withdraw volumes. + */ +static void cachefiles_withdraw_volumes(struct cachefiles_cache *cache) +{ + _enter(""); + + for (;;) { + struct cachefiles_volume *volume = NULL; + + spin_lock(&cache->object_list_lock); + if (!list_empty(&cache->volumes)) { + volume = list_first_entry(&cache->volumes, + struct cachefiles_volume, cache_link); + list_del_init(&volume->cache_link); + } + spin_unlock(&cache->object_list_lock); + if (!volume) + break; + + cachefiles_withdraw_volume(volume); + } + + _leave(""); +} + +/* + * Sync a cache to backing disk. + */ +static void cachefiles_sync_cache(struct cachefiles_cache *cache) +{ + const struct cred *saved_cred; + int ret; + + _enter("%s", cache->cache->name); + + /* make sure all pages pinned by operations on behalf of the netfs are + * written to disc */ + cachefiles_begin_secure(cache, &saved_cred); + down_read(&cache->mnt->mnt_sb->s_umount); + ret = sync_filesystem(cache->mnt->mnt_sb); + up_read(&cache->mnt->mnt_sb->s_umount); + cachefiles_end_secure(cache, saved_cred); + + if (ret == -EIO) + cachefiles_io_error(cache, + "Attempt to sync backing fs superblock returned error %d", + ret); +} + +/* + * Withdraw cache objects. + */ +void cachefiles_withdraw_cache(struct cachefiles_cache *cache) +{ + struct fscache_cache *fscache = cache->cache; + + pr_info("File cache on %s unregistering\n", fscache->name); + + fscache_withdraw_cache(fscache); + + /* we now have to destroy all the active objects pertaining to this + * cache - which we do by passing them off to thread pool to be + * disposed of */ + cachefiles_withdraw_objects(cache); + fscache_wait_for_objects(fscache); + + cachefiles_withdraw_volumes(cache); + cachefiles_sync_cache(cache); + cache->cache = NULL; + fscache_relinquish_cache(fscache); +} diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 752c1e43416f..40a792421fc1 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* Daemon interface * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2007, 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ @@ -41,6 +41,8 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *, char *); static int cachefiles_daemon_inuse(struct cachefiles_cache *, char *); static int cachefiles_daemon_secctx(struct cachefiles_cache *, char *); static int cachefiles_daemon_tag(struct cachefiles_cache *, char *); +static int cachefiles_daemon_bind(struct cachefiles_cache *, char *); +static void cachefiles_daemon_unbind(struct cachefiles_cache *); static unsigned long cachefiles_open; @@ -78,7 +80,7 @@ static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = { /* - * do various checks + * Prepare a cache for caching. */ static int cachefiles_daemon_open(struct inode *inode, struct file *file) { @@ -102,9 +104,10 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) } mutex_init(&cache->daemon_mutex); - cache->active_nodes = RB_ROOT; - rwlock_init(&cache->active_lock); init_waitqueue_head(&cache->daemon_pollwq); + INIT_LIST_HEAD(&cache->volumes); + INIT_LIST_HEAD(&cache->object_list); + spin_lock_init(&cache->object_list_lock); /* set default caching limits * - limit at 1% free space and/or free files @@ -124,7 +127,7 @@ static int cachefiles_daemon_open(struct inode *inode, struct file *file) } /* - * release a cache + * Release a cache. */ static int cachefiles_daemon_release(struct inode *inode, struct file *file) { @@ -138,8 +141,6 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) cachefiles_daemon_unbind(cache); - ASSERT(!cache->active_nodes.rb_node); - /* clean up the control file interface */ cache->cachefilesd = NULL; file->private_data = NULL; @@ -152,7 +153,7 @@ static int cachefiles_daemon_release(struct inode *inode, struct file *file) } /* - * read the cache state + * Read the cache state. */ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, size_t buflen, loff_t *pos) @@ -169,7 +170,7 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, return 0; /* check how much space the cache has */ - cachefiles_has_space(cache, 0, 0); + cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); /* summarise */ f_released = atomic_xchg(&cache->f_released, 0); @@ -206,7 +207,7 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, } /* - * command the cache + * Take a command from cachefilesd, parse it and act on it. */ static ssize_t cachefiles_daemon_write(struct file *file, const char __user *_data, @@ -225,7 +226,7 @@ static ssize_t cachefiles_daemon_write(struct file *file, if (test_bit(CACHEFILES_DEAD, &cache->flags)) return -EIO; - if (datalen < 0 || datalen > PAGE_SIZE - 1) + if (datalen > PAGE_SIZE - 1) return -EOPNOTSUPP; /* drag the command string into the kernel so we can parse it */ @@ -284,7 +285,7 @@ found_command: } /* - * poll for culling state + * Poll for culling state * - use EPOLLOUT to indicate culling state */ static __poll_t cachefiles_daemon_poll(struct file *file, @@ -306,7 +307,7 @@ static __poll_t cachefiles_daemon_poll(struct file *file, } /* - * give a range error for cache space constraints + * Give a range error for cache space constraints * - can be tail-called */ static int cachefiles_daemon_range_error(struct cachefiles_cache *cache, @@ -318,7 +319,7 @@ static int cachefiles_daemon_range_error(struct cachefiles_cache *cache, } /* - * set the percentage of files at which to stop culling + * Set the percentage of files at which to stop culling * - command: "frun <N>%" */ static int cachefiles_daemon_frun(struct cachefiles_cache *cache, char *args) @@ -342,7 +343,7 @@ static int cachefiles_daemon_frun(struct cachefiles_cache *cache, char *args) } /* - * set the percentage of files at which to start culling + * Set the percentage of files at which to start culling * - command: "fcull <N>%" */ static int cachefiles_daemon_fcull(struct cachefiles_cache *cache, char *args) @@ -366,7 +367,7 @@ static int cachefiles_daemon_fcull(struct cachefiles_cache *cache, char *args) } /* - * set the percentage of files at which to stop allocating + * Set the percentage of files at which to stop allocating * - command: "fstop <N>%" */ static int cachefiles_daemon_fstop(struct cachefiles_cache *cache, char *args) @@ -382,7 +383,7 @@ static int cachefiles_daemon_fstop(struct cachefiles_cache *cache, char *args) if (args[0] != '%' || args[1] != '\0') return -EINVAL; - if (fstop < 0 || fstop >= cache->fcull_percent) + if (fstop >= cache->fcull_percent) return cachefiles_daemon_range_error(cache, args); cache->fstop_percent = fstop; @@ -390,7 +391,7 @@ static int cachefiles_daemon_fstop(struct cachefiles_cache *cache, char *args) } /* - * set the percentage of blocks at which to stop culling + * Set the percentage of blocks at which to stop culling * - command: "brun <N>%" */ static int cachefiles_daemon_brun(struct cachefiles_cache *cache, char *args) @@ -414,7 +415,7 @@ static int cachefiles_daemon_brun(struct cachefiles_cache *cache, char *args) } /* - * set the percentage of blocks at which to start culling + * Set the percentage of blocks at which to start culling * - command: "bcull <N>%" */ static int cachefiles_daemon_bcull(struct cachefiles_cache *cache, char *args) @@ -438,7 +439,7 @@ static int cachefiles_daemon_bcull(struct cachefiles_cache *cache, char *args) } /* - * set the percentage of blocks at which to stop allocating + * Set the percentage of blocks at which to stop allocating * - command: "bstop <N>%" */ static int cachefiles_daemon_bstop(struct cachefiles_cache *cache, char *args) @@ -454,7 +455,7 @@ static int cachefiles_daemon_bstop(struct cachefiles_cache *cache, char *args) if (args[0] != '%' || args[1] != '\0') return -EINVAL; - if (bstop < 0 || bstop >= cache->bcull_percent) + if (bstop >= cache->bcull_percent) return cachefiles_daemon_range_error(cache, args); cache->bstop_percent = bstop; @@ -462,7 +463,7 @@ static int cachefiles_daemon_bstop(struct cachefiles_cache *cache, char *args) } /* - * set the cache directory + * Set the cache directory * - command: "dir <name>" */ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) @@ -490,7 +491,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) } /* - * set the cache security context + * Set the cache security context * - command: "secctx <ctx>" */ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) @@ -518,7 +519,7 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) } /* - * set the cache tag + * Set the cache tag * - command: "tag <name>" */ static int cachefiles_daemon_tag(struct cachefiles_cache *cache, char *args) @@ -544,7 +545,7 @@ static int cachefiles_daemon_tag(struct cachefiles_cache *cache, char *args) } /* - * request a node in the cache be culled from the current working directory + * Request a node in the cache be culled from the current working directory * - command: "cull <name>" */ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args) @@ -568,7 +569,6 @@ static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args) return -EIO; } - /* extract the directory dentry from the cwd */ get_fs_pwd(current->fs, &path); if (!d_can_lookup(path.dentry)) @@ -593,7 +593,7 @@ inval: } /* - * set debugging mode + * Set debugging mode * - command: "debug <mask>" */ static int cachefiles_daemon_debug(struct cachefiles_cache *cache, char *args) @@ -616,7 +616,7 @@ inval: } /* - * find out whether an object in the current working directory is in use or not + * Find out whether an object in the current working directory is in use or not * - command: "inuse <name>" */ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args) @@ -640,7 +640,6 @@ static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args) return -EIO; } - /* extract the directory dentry from the cwd */ get_fs_pwd(current->fs, &path); if (!d_can_lookup(path.dentry)) @@ -665,84 +664,65 @@ inval: } /* - * see if we have space for a number of pages and/or a number of files in the - * cache + * Bind a directory as a cache */ -int cachefiles_has_space(struct cachefiles_cache *cache, - unsigned fnr, unsigned bnr) +static int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args) { - struct kstatfs stats; - struct path path = { - .mnt = cache->mnt, - .dentry = cache->mnt->mnt_root, - }; - int ret; + _enter("{%u,%u,%u,%u,%u,%u},%s", + cache->frun_percent, + cache->fcull_percent, + cache->fstop_percent, + cache->brun_percent, + cache->bcull_percent, + cache->bstop_percent, + args); + + if (cache->fstop_percent >= cache->fcull_percent || + cache->fcull_percent >= cache->frun_percent || + cache->frun_percent >= 100) + return -ERANGE; + + if (cache->bstop_percent >= cache->bcull_percent || + cache->bcull_percent >= cache->brun_percent || + cache->brun_percent >= 100) + return -ERANGE; - //_enter("{%llu,%llu,%llu,%llu,%llu,%llu},%u,%u", - // (unsigned long long) cache->frun, - // (unsigned long long) cache->fcull, - // (unsigned long long) cache->fstop, - // (unsigned long long) cache->brun, - // (unsigned long long) cache->bcull, - // (unsigned long long) cache->bstop, - // fnr, bnr); - - /* find out how many pages of blockdev are available */ - memset(&stats, 0, sizeof(stats)); - - ret = vfs_statfs(&path, &stats); - if (ret < 0) { - if (ret == -EIO) - cachefiles_io_error(cache, "statfs failed"); - _leave(" = %d", ret); - return ret; + if (*args) { + pr_err("'bind' command doesn't take an argument\n"); + return -EINVAL; } - stats.f_bavail >>= cache->bshift; - - //_debug("avail %llu,%llu", - // (unsigned long long) stats.f_ffree, - // (unsigned long long) stats.f_bavail); - - /* see if there is sufficient space */ - if (stats.f_ffree > fnr) - stats.f_ffree -= fnr; - else - stats.f_ffree = 0; - - if (stats.f_bavail > bnr) - stats.f_bavail -= bnr; - else - stats.f_bavail = 0; - - ret = -ENOBUFS; - if (stats.f_ffree < cache->fstop || - stats.f_bavail < cache->bstop) - goto begin_cull; - - ret = 0; - if (stats.f_ffree < cache->fcull || - stats.f_bavail < cache->bcull) - goto begin_cull; - - if (test_bit(CACHEFILES_CULLING, &cache->flags) && - stats.f_ffree >= cache->frun && - stats.f_bavail >= cache->brun && - test_and_clear_bit(CACHEFILES_CULLING, &cache->flags) - ) { - _debug("cease culling"); - cachefiles_state_changed(cache); + if (!cache->rootdirname) { + pr_err("No cache directory specified\n"); + return -EINVAL; } - //_leave(" = 0"); - return 0; - -begin_cull: - if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) { - _debug("### CULL CACHE ###"); - cachefiles_state_changed(cache); + /* Don't permit already bound caches to be re-bound */ + if (test_bit(CACHEFILES_READY, &cache->flags)) { + pr_err("Cache already bound\n"); + return -EBUSY; } - _leave(" = %d", ret); - return ret; + return cachefiles_add_cache(cache); +} + +/* + * Unbind a cache. + */ +static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) +{ + _enter(""); + + if (test_bit(CACHEFILES_READY, &cache->flags)) + cachefiles_withdraw_cache(cache); + + cachefiles_put_directory(cache->graveyard); + cachefiles_put_directory(cache->store); + mntput(cache->mnt); + + kfree(cache->rootdirname); + kfree(cache->secctx); + kfree(cache->tag); + + _leave(""); } diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c new file mode 100644 index 000000000000..58f8aec964e4 --- /dev/null +++ b/fs/cachefiles/error_inject.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Error injection handling. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/sysctl.h> +#include "internal.h" + +unsigned int cachefiles_error_injection_state; + +static struct ctl_table_header *cachefiles_sysctl; +static struct ctl_table cachefiles_sysctls[] = { + { + .procname = "error_injection", + .data = &cachefiles_error_injection_state, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec, + }, + {} +}; + +static struct ctl_table cachefiles_sysctls_root[] = { + { + .procname = "cachefiles", + .mode = 0555, + .child = cachefiles_sysctls, + }, + {} +}; + +int __init cachefiles_register_error_injection(void) +{ + cachefiles_sysctl = register_sysctl_table(cachefiles_sysctls_root); + if (!cachefiles_sysctl) + return -ENOMEM; + return 0; + +} + +void cachefiles_unregister_error_injection(void) +{ + unregister_sysctl_table(cachefiles_sysctl); +} diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index da28ac1fa225..51c968cd00a6 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -1,572 +1,445 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache interface to CacheFiles * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/slab.h> #include <linux/mount.h> +#include <linux/xattr.h> +#include <linux/file.h> +#include <linux/falloc.h> +#include <trace/events/fscache.h> #include "internal.h" -struct cachefiles_lookup_data { - struct cachefiles_xattr *auxdata; /* auxiliary data */ - char *key; /* key path */ -}; - -static int cachefiles_attr_changed(struct fscache_object *_object); +static atomic_t cachefiles_object_debug_id; /* - * allocate an object record for a cookie lookup and prepare the lookup data + * Allocate a cache object record. */ -static struct fscache_object *cachefiles_alloc_object( - struct fscache_cache *_cache, - struct fscache_cookie *cookie) +static +struct cachefiles_object *cachefiles_alloc_object(struct fscache_cookie *cookie) { - struct cachefiles_lookup_data *lookup_data; + struct fscache_volume *vcookie = cookie->volume; + struct cachefiles_volume *volume = vcookie->cache_priv; struct cachefiles_object *object; - struct cachefiles_cache *cache; - struct cachefiles_xattr *auxdata; - unsigned keylen, auxlen; - void *buffer, *p; - char *key; - cache = container_of(_cache, struct cachefiles_cache, cache); + _enter("{%s},%x,", vcookie->key, cookie->debug_id); - _enter("{%s},%x,", cache->cache.identifier, cookie->debug_id); - - lookup_data = kmalloc(sizeof(*lookup_data), cachefiles_gfp); - if (!lookup_data) - goto nomem_lookup_data; - - /* create a new object record and a temporary leaf image */ - object = kmem_cache_alloc(cachefiles_object_jar, cachefiles_gfp); + object = kmem_cache_zalloc(cachefiles_object_jar, GFP_KERNEL); if (!object) - goto nomem_object; - - ASSERTCMP(object->backer, ==, NULL); + return NULL; - BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)); - atomic_set(&object->usage, 1); + refcount_set(&object->ref, 1); - fscache_object_init(&object->fscache, cookie, &cache->cache); + spin_lock_init(&object->lock); + INIT_LIST_HEAD(&object->cache_link); + object->volume = volume; + object->debug_id = atomic_inc_return(&cachefiles_object_debug_id); + object->cookie = fscache_get_cookie(cookie, fscache_cookie_get_attach_object); - object->type = cookie->def->type; - - /* get hold of the raw key - * - stick the length on the front and leave space on the back for the - * encoder - */ - buffer = kmalloc((2 + 512) + 3, cachefiles_gfp); - if (!buffer) - goto nomem_buffer; - - keylen = cookie->key_len; - if (keylen <= sizeof(cookie->inline_key)) - p = cookie->inline_key; - else - p = cookie->key; - memcpy(buffer + 2, p, keylen); - - *(uint16_t *)buffer = keylen; - ((char *)buffer)[keylen + 2] = 0; - ((char *)buffer)[keylen + 3] = 0; - ((char *)buffer)[keylen + 4] = 0; - - /* turn the raw key into something that can work with as a filename */ - key = cachefiles_cook_key(buffer, keylen + 2, object->type); - if (!key) - goto nomem_key; - - /* get hold of the auxiliary data and prepend the object type */ - auxdata = buffer; - auxlen = cookie->aux_len; - if (auxlen) { - if (auxlen <= sizeof(cookie->inline_aux)) - p = cookie->inline_aux; - else - p = cookie->aux; - memcpy(auxdata->data, p, auxlen); - } - - auxdata->len = auxlen + 1; - auxdata->type = cookie->type; - - lookup_data->auxdata = auxdata; - lookup_data->key = key; - object->lookup_data = lookup_data; - - _leave(" = %x [%p]", object->fscache.debug_id, lookup_data); - return &object->fscache; - -nomem_key: - kfree(buffer); -nomem_buffer: - BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)); - kmem_cache_free(cachefiles_object_jar, object); - fscache_object_destroyed(&cache->cache); -nomem_object: - kfree(lookup_data); -nomem_lookup_data: - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); + fscache_count_object(vcookie->cache); + trace_cachefiles_ref(object->debug_id, cookie->debug_id, 1, + cachefiles_obj_new); + return object; } /* - * attempt to look up the nominated node in this cache - * - return -ETIMEDOUT to be scheduled again + * Note that an object has been seen. */ -static int cachefiles_lookup_object(struct fscache_object *_object) +void cachefiles_see_object(struct cachefiles_object *object, + enum cachefiles_obj_ref_trace why) { - struct cachefiles_lookup_data *lookup_data; - struct cachefiles_object *parent, *object; - struct cachefiles_cache *cache; - const struct cred *saved_cred; - int ret; - - _enter("{OBJ%x}", _object->debug_id); - - cache = container_of(_object->cache, struct cachefiles_cache, cache); - parent = container_of(_object->parent, - struct cachefiles_object, fscache); - object = container_of(_object, struct cachefiles_object, fscache); - lookup_data = object->lookup_data; - - ASSERTCMP(lookup_data, !=, NULL); - - /* look up the key, creating any missing bits */ - cachefiles_begin_secure(cache, &saved_cred); - ret = cachefiles_walk_to_object(parent, object, - lookup_data->key, - lookup_data->auxdata); - cachefiles_end_secure(cache, saved_cred); - - /* polish off by setting the attributes of non-index files */ - if (ret == 0 && - object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) - cachefiles_attr_changed(&object->fscache); - - if (ret < 0 && ret != -ETIMEDOUT) { - if (ret != -ENOBUFS) - pr_warn("Lookup failed error %d\n", ret); - fscache_object_lookup_error(&object->fscache); - } - - _leave(" [%d]", ret); - return ret; + trace_cachefiles_ref(object->debug_id, object->cookie->debug_id, + refcount_read(&object->ref), why); } /* - * indication of lookup completion + * Increment the usage count on an object; */ -static void cachefiles_lookup_complete(struct fscache_object *_object) +struct cachefiles_object *cachefiles_grab_object(struct cachefiles_object *object, + enum cachefiles_obj_ref_trace why) { - struct cachefiles_object *object; - - object = container_of(_object, struct cachefiles_object, fscache); - - _enter("{OBJ%x,%p}", object->fscache.debug_id, object->lookup_data); + int r; - if (object->lookup_data) { - kfree(object->lookup_data->key); - kfree(object->lookup_data->auxdata); - kfree(object->lookup_data); - object->lookup_data = NULL; - } + __refcount_inc(&object->ref, &r); + trace_cachefiles_ref(object->debug_id, object->cookie->debug_id, r, why); + return object; } /* - * increment the usage count on an inode object (may fail if unmounting) + * dispose of a reference to an object */ -static -struct fscache_object *cachefiles_grab_object(struct fscache_object *_object, - enum fscache_obj_ref_trace why) +void cachefiles_put_object(struct cachefiles_object *object, + enum cachefiles_obj_ref_trace why) { - struct cachefiles_object *object = - container_of(_object, struct cachefiles_object, fscache); - int u; + unsigned int object_debug_id = object->debug_id; + unsigned int cookie_debug_id = object->cookie->debug_id; + struct fscache_cache *cache; + bool done; + int r; + + done = __refcount_dec_and_test(&object->ref, &r); + trace_cachefiles_ref(object_debug_id, cookie_debug_id, r, why); + if (done) { + _debug("- kill object OBJ%x", object_debug_id); + + ASSERTCMP(object->file, ==, NULL); - _enter("{OBJ%x,%d}", _object->debug_id, atomic_read(&object->usage)); + kfree(object->d_name); -#ifdef CACHEFILES_DEBUG_SLAB - ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000); -#endif + cache = object->volume->cache->cache; + fscache_put_cookie(object->cookie, fscache_cookie_put_object); + object->cookie = NULL; + kmem_cache_free(cachefiles_object_jar, object); + fscache_uncount_object(cache); + } - u = atomic_inc_return(&object->usage); - trace_cachefiles_ref(object, _object->cookie, - (enum cachefiles_obj_ref_trace)why, u); - return &object->fscache; + _leave(""); } /* - * update the auxiliary data for an object object on disk + * Adjust the size of a cache file if necessary to match the DIO size. We keep + * the EOF marker a multiple of DIO blocks so that we don't fall back to doing + * non-DIO for a partial block straddling the EOF, but we also have to be + * careful of someone expanding the file and accidentally accreting the + * padding. */ -static void cachefiles_update_object(struct fscache_object *_object) +static int cachefiles_adjust_size(struct cachefiles_object *object) { - struct cachefiles_object *object; - struct cachefiles_xattr *auxdata; - struct cachefiles_cache *cache; - struct fscache_cookie *cookie; - const struct cred *saved_cred; - const void *aux; - unsigned auxlen; + struct iattr newattrs; + struct file *file = object->file; + uint64_t ni_size; + loff_t oi_size; + int ret; - _enter("{OBJ%x}", _object->debug_id); + ni_size = object->cookie->object_size; + ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); - object = container_of(_object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, struct cachefiles_cache, - cache); + _enter("{OBJ%x},[%llu]", + object->debug_id, (unsigned long long) ni_size); - if (!fscache_use_cookie(_object)) { - _leave(" [relinq]"); - return; - } + if (!file) + return -ENOBUFS; - cookie = object->fscache.cookie; - auxlen = cookie->aux_len; + oi_size = i_size_read(file_inode(file)); + if (oi_size == ni_size) + return 0; - if (!auxlen) { - fscache_unuse_cookie(_object); - _leave(" [no aux]"); - return; - } + inode_lock(file_inode(file)); - auxdata = kmalloc(2 + auxlen + 3, cachefiles_gfp); - if (!auxdata) { - fscache_unuse_cookie(_object); - _leave(" [nomem]"); - return; + /* if there's an extension to a partial page at the end of the backing + * file, we need to discard the partial page so that we pick up new + * data after it */ + if (oi_size & ~PAGE_MASK && ni_size > oi_size) { + _debug("discard tail %llx", oi_size); + newattrs.ia_valid = ATTR_SIZE; + newattrs.ia_size = oi_size & PAGE_MASK; + ret = cachefiles_inject_remove_error(); + if (ret == 0) + ret = notify_change(&init_user_ns, file->f_path.dentry, + &newattrs, NULL); + if (ret < 0) + goto truncate_failed; } - aux = (auxlen <= sizeof(cookie->inline_aux)) ? - cookie->inline_aux : cookie->aux; + newattrs.ia_valid = ATTR_SIZE; + newattrs.ia_size = ni_size; + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = notify_change(&init_user_ns, file->f_path.dentry, + &newattrs, NULL); - memcpy(auxdata->data, aux, auxlen); - fscache_unuse_cookie(_object); +truncate_failed: + inode_unlock(file_inode(file)); - auxdata->len = auxlen + 1; - auxdata->type = cookie->type; + if (ret < 0) + trace_cachefiles_io_error(NULL, file_inode(file), ret, + cachefiles_trace_notify_change_error); + if (ret == -EIO) { + cachefiles_io_error_obj(object, "Size set failed"); + ret = -ENOBUFS; + } - cachefiles_begin_secure(cache, &saved_cred); - cachefiles_update_object_xattr(object, auxdata); - cachefiles_end_secure(cache, saved_cred); - kfree(auxdata); - _leave(""); + _leave(" = %d", ret); + return ret; } /* - * discard the resources pinned by an object and effect retirement if - * requested + * Attempt to look up the nominated node in this cache */ -static void cachefiles_drop_object(struct fscache_object *_object) +static bool cachefiles_lookup_cookie(struct fscache_cookie *cookie) { struct cachefiles_object *object; - struct cachefiles_cache *cache; + struct cachefiles_cache *cache = cookie->volume->cache->cache_priv; const struct cred *saved_cred; - struct inode *inode; - blkcnt_t i_blocks = 0; + bool success; - ASSERT(_object); + object = cachefiles_alloc_object(cookie); + if (!object) + goto fail; - object = container_of(_object, struct cachefiles_object, fscache); + _enter("{OBJ%x}", object->debug_id); - _enter("{OBJ%x,%d}", - object->fscache.debug_id, atomic_read(&object->usage)); + if (!cachefiles_cook_key(object)) + goto fail_put; - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); + cookie->cache_priv = object; -#ifdef CACHEFILES_DEBUG_SLAB - ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000); -#endif + cachefiles_begin_secure(cache, &saved_cred); - /* We need to tidy the object up if we did in fact manage to open it. - * It's possible for us to get here before the object is fully - * initialised if the parent goes away or the object gets retired - * before we set it up. - */ - if (object->dentry) { - /* delete retired objects */ - if (test_bit(FSCACHE_OBJECT_RETIRED, &object->fscache.flags) && - _object != cache->cache.fsdef - ) { - _debug("- retire object OBJ%x", object->fscache.debug_id); - inode = d_backing_inode(object->dentry); - if (inode) - i_blocks = inode->i_blocks; - - cachefiles_begin_secure(cache, &saved_cred); - cachefiles_delete_object(cache, object); - cachefiles_end_secure(cache, saved_cred); - } + success = cachefiles_look_up_object(object); + if (!success) + goto fail_withdraw; - /* close the filesystem stuff attached to the object */ - if (object->backer != object->dentry) - dput(object->backer); - object->backer = NULL; - } + cachefiles_see_object(object, cachefiles_obj_see_lookup_cookie); + + spin_lock(&cache->object_list_lock); + list_add(&object->cache_link, &cache->object_list); + spin_unlock(&cache->object_list_lock); + cachefiles_adjust_size(object); - /* note that the object is now inactive */ - if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) - cachefiles_mark_object_inactive(cache, object, i_blocks); + cachefiles_end_secure(cache, saved_cred); + _leave(" = t"); + return true; - dput(object->dentry); - object->dentry = NULL; +fail_withdraw: + cachefiles_end_secure(cache, saved_cred); + cachefiles_see_object(object, cachefiles_obj_see_lookup_failed); + fscache_caching_failed(cookie); + _debug("failed c=%08x o=%08x", cookie->debug_id, object->debug_id); + /* The caller holds an access count on the cookie, so we need them to + * drop it before we can withdraw the object. + */ + return false; - _leave(""); +fail_put: + cachefiles_put_object(object, cachefiles_obj_put_alloc_fail); +fail: + return false; } /* - * dispose of a reference to an object + * Shorten the backing object to discard any dirty data and free up + * any unused granules. */ -void cachefiles_put_object(struct fscache_object *_object, - enum fscache_obj_ref_trace why) +static bool cachefiles_shorten_object(struct cachefiles_object *object, + struct file *file, loff_t new_size) { - struct cachefiles_object *object; - struct fscache_cache *cache; - int u; - - ASSERT(_object); - - object = container_of(_object, struct cachefiles_object, fscache); - - _enter("{OBJ%x,%d}", - object->fscache.debug_id, atomic_read(&object->usage)); - -#ifdef CACHEFILES_DEBUG_SLAB - ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000); -#endif - - ASSERTIFCMP(object->fscache.parent, - object->fscache.parent->n_children, >, 0); - - u = atomic_dec_return(&object->usage); - trace_cachefiles_ref(object, _object->cookie, - (enum cachefiles_obj_ref_trace)why, u); - ASSERTCMP(u, !=, -1); - if (u == 0) { - _debug("- kill object OBJ%x", object->fscache.debug_id); + struct cachefiles_cache *cache = object->volume->cache; + struct inode *inode = file_inode(file); + loff_t i_size, dio_size; + int ret; - ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)); - ASSERTCMP(object->fscache.parent, ==, NULL); - ASSERTCMP(object->backer, ==, NULL); - ASSERTCMP(object->dentry, ==, NULL); - ASSERTCMP(object->fscache.n_ops, ==, 0); - ASSERTCMP(object->fscache.n_children, ==, 0); + dio_size = round_up(new_size, CACHEFILES_DIO_BLOCK_SIZE); + i_size = i_size_read(inode); + + trace_cachefiles_trunc(object, inode, i_size, dio_size, + cachefiles_trunc_shrink); + ret = cachefiles_inject_remove_error(); + if (ret == 0) + ret = vfs_truncate(&file->f_path, dio_size); + if (ret < 0) { + trace_cachefiles_io_error(object, file_inode(file), ret, + cachefiles_trace_trunc_error); + cachefiles_io_error_obj(object, "Trunc-to-size failed %d", ret); + cachefiles_remove_object_xattr(cache, object, file->f_path.dentry); + return false; + } - if (object->lookup_data) { - kfree(object->lookup_data->key); - kfree(object->lookup_data->auxdata); - kfree(object->lookup_data); - object->lookup_data = NULL; + if (new_size < dio_size) { + trace_cachefiles_trunc(object, inode, dio_size, new_size, + cachefiles_trunc_dio_adjust); + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_fallocate(file, FALLOC_FL_ZERO_RANGE, + new_size, dio_size); + if (ret < 0) { + trace_cachefiles_io_error(object, file_inode(file), ret, + cachefiles_trace_fallocate_error); + cachefiles_io_error_obj(object, "Trunc-to-dio-size failed %d", ret); + cachefiles_remove_object_xattr(cache, object, file->f_path.dentry); + return false; } - - cache = object->fscache.cache; - fscache_object_destroy(&object->fscache); - kmem_cache_free(cachefiles_object_jar, object); - fscache_object_destroyed(cache); } - _leave(""); + return true; } /* - * sync a cache + * Resize the backing object. */ -static void cachefiles_sync_cache(struct fscache_cache *_cache) +static void cachefiles_resize_cookie(struct netfs_cache_resources *cres, + loff_t new_size) { - struct cachefiles_cache *cache; + struct cachefiles_object *object = cachefiles_cres_object(cres); + struct cachefiles_cache *cache = object->volume->cache; + struct fscache_cookie *cookie = object->cookie; const struct cred *saved_cred; - int ret; + struct file *file = cachefiles_cres_file(cres); + loff_t old_size = cookie->object_size; - _enter("%s", _cache->tag->name); + _enter("%llu->%llu", old_size, new_size); - cache = container_of(_cache, struct cachefiles_cache, cache); - - /* make sure all pages pinned by operations on behalf of the netfs are - * written to disc */ - cachefiles_begin_secure(cache, &saved_cred); - down_read(&cache->mnt->mnt_sb->s_umount); - ret = sync_filesystem(cache->mnt->mnt_sb); - up_read(&cache->mnt->mnt_sb->s_umount); - cachefiles_end_secure(cache, saved_cred); + if (new_size < old_size) { + cachefiles_begin_secure(cache, &saved_cred); + cachefiles_shorten_object(object, file, new_size); + cachefiles_end_secure(cache, saved_cred); + object->cookie->object_size = new_size; + return; + } - if (ret == -EIO) - cachefiles_io_error(cache, - "Attempt to sync backing fs superblock" - " returned error %d", - ret); + /* The file is being expanded. We don't need to do anything + * particularly. cookie->initial_size doesn't change and so the point + * at which we have to download before doesn't change. + */ + cookie->object_size = new_size; } /* - * check if the backing cache is updated to FS-Cache - * - called by FS-Cache when evaluates if need to invalidate the cache + * Commit changes to the object as we drop it. */ -static int cachefiles_check_consistency(struct fscache_operation *op) +static void cachefiles_commit_object(struct cachefiles_object *object, + struct cachefiles_cache *cache) { - struct cachefiles_object *object; - struct cachefiles_cache *cache; - const struct cred *saved_cred; - int ret; + bool update = false; - _enter("{OBJ%x}", op->object->debug_id); + if (test_and_clear_bit(FSCACHE_COOKIE_LOCAL_WRITE, &object->cookie->flags)) + update = true; + if (test_and_clear_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags)) + update = true; + if (update) + cachefiles_set_object_xattr(object); - object = container_of(op->object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); + if (test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) + cachefiles_commit_tmpfile(cache, object); +} - cachefiles_begin_secure(cache, &saved_cred); - ret = cachefiles_check_auxdata(object); - cachefiles_end_secure(cache, saved_cred); +/* + * Finalise and object and close the VFS structs that we have. + */ +static void cachefiles_clean_up_object(struct cachefiles_object *object, + struct cachefiles_cache *cache) +{ + if (test_bit(FSCACHE_COOKIE_RETIRED, &object->cookie->flags)) { + if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { + cachefiles_see_object(object, cachefiles_obj_see_clean_delete); + _debug("- inval object OBJ%x", object->debug_id); + cachefiles_delete_object(object, FSCACHE_OBJECT_WAS_RETIRED); + } else { + cachefiles_see_object(object, cachefiles_obj_see_clean_drop_tmp); + _debug("- inval object OBJ%x tmpfile", object->debug_id); + } + } else { + cachefiles_see_object(object, cachefiles_obj_see_clean_commit); + cachefiles_commit_object(object, cache); + } - _leave(" = %d", ret); - return ret; + cachefiles_unmark_inode_in_use(object, object->file); + if (object->file) { + fput(object->file); + object->file = NULL; + } } /* - * notification the attributes on an object have changed - * - called with reads/writes excluded by FS-Cache + * Withdraw caching for a cookie. */ -static int cachefiles_attr_changed(struct fscache_object *_object) +static void cachefiles_withdraw_cookie(struct fscache_cookie *cookie) { - struct cachefiles_object *object; - struct cachefiles_cache *cache; + struct cachefiles_object *object = cookie->cache_priv; + struct cachefiles_cache *cache = object->volume->cache; const struct cred *saved_cred; - struct iattr newattrs; - uint64_t ni_size; - loff_t oi_size; - int ret; - - ni_size = _object->store_limit_l; - - _enter("{OBJ%x},[%llu]", - _object->debug_id, (unsigned long long) ni_size); - - object = container_of(_object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - if (ni_size == object->i_size) - return 0; - - if (!object->backer) - return -ENOBUFS; - ASSERT(d_is_reg(object->backer)); + _enter("o=%x", object->debug_id); + cachefiles_see_object(object, cachefiles_obj_see_withdraw_cookie); - fscache_set_store_limit(&object->fscache, ni_size); - - oi_size = i_size_read(d_backing_inode(object->backer)); - if (oi_size == ni_size) - return 0; - - cachefiles_begin_secure(cache, &saved_cred); - inode_lock(d_inode(object->backer)); - - /* if there's an extension to a partial page at the end of the backing - * file, we need to discard the partial page so that we pick up new - * data after it */ - if (oi_size & ~PAGE_MASK && ni_size > oi_size) { - _debug("discard tail %llx", oi_size); - newattrs.ia_valid = ATTR_SIZE; - newattrs.ia_size = oi_size & PAGE_MASK; - ret = notify_change(&init_user_ns, object->backer, &newattrs, NULL); - if (ret < 0) - goto truncate_failed; + if (!list_empty(&object->cache_link)) { + spin_lock(&cache->object_list_lock); + cachefiles_see_object(object, cachefiles_obj_see_withdrawal); + list_del_init(&object->cache_link); + spin_unlock(&cache->object_list_lock); } - newattrs.ia_valid = ATTR_SIZE; - newattrs.ia_size = ni_size; - ret = notify_change(&init_user_ns, object->backer, &newattrs, NULL); - -truncate_failed: - inode_unlock(d_inode(object->backer)); - cachefiles_end_secure(cache, saved_cred); - - if (ret == -EIO) { - fscache_set_store_limit(&object->fscache, 0); - cachefiles_io_error_obj(object, "Size set failed"); - ret = -ENOBUFS; + if (object->file) { + cachefiles_begin_secure(cache, &saved_cred); + cachefiles_clean_up_object(object, cache); + cachefiles_end_secure(cache, saved_cred); } - _leave(" = %d", ret); - return ret; + cookie->cache_priv = NULL; + cachefiles_put_object(object, cachefiles_obj_put_detach); } /* - * Invalidate an object + * Invalidate the storage associated with a cookie. */ -static void cachefiles_invalidate_object(struct fscache_operation *op) +static bool cachefiles_invalidate_cookie(struct fscache_cookie *cookie) { - struct cachefiles_object *object; - struct cachefiles_cache *cache; - const struct cred *saved_cred; - struct path path; - uint64_t ni_size; - int ret; + struct cachefiles_object *object = cookie->cache_priv; + struct file *new_file, *old_file; + bool old_tmpfile; - object = container_of(op->object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); + _enter("o=%x,[%llu]", object->debug_id, object->cookie->object_size); - ni_size = op->object->store_limit_l; + old_tmpfile = test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags); - _enter("{OBJ%x},[%llu]", - op->object->debug_id, (unsigned long long)ni_size); + if (!object->file) { + fscache_resume_after_invalidation(cookie); + _leave(" = t [light]"); + return true; + } - if (object->backer) { - ASSERT(d_is_reg(object->backer)); + new_file = cachefiles_create_tmpfile(object); + if (IS_ERR(new_file)) + goto failed; - fscache_set_store_limit(&object->fscache, ni_size); + /* Substitute the VFS target */ + _debug("sub"); + spin_lock(&object->lock); - path.dentry = object->backer; - path.mnt = cache->mnt; + old_file = object->file; + object->file = new_file; + object->content_info = CACHEFILES_CONTENT_NO_DATA; + set_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags); - cachefiles_begin_secure(cache, &saved_cred); - ret = vfs_truncate(&path, 0); - if (ret == 0) - ret = vfs_truncate(&path, ni_size); - cachefiles_end_secure(cache, saved_cred); + spin_unlock(&object->lock); + _debug("subbed"); + + /* Allow I/O to take place again */ + fscache_resume_after_invalidation(cookie); + + if (old_file) { + if (!old_tmpfile) { + struct cachefiles_volume *volume = object->volume; + struct dentry *fan = volume->fanout[(u8)cookie->key_hash]; - if (ret != 0) { - fscache_set_store_limit(&object->fscache, 0); - if (ret == -EIO) - cachefiles_io_error_obj(object, - "Invalidate failed"); + inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); + cachefiles_bury_object(volume->cache, object, fan, + old_file->f_path.dentry, + FSCACHE_OBJECT_INVALIDATED); } + fput(old_file); } - fscache_op_complete(op, true); - _leave(""); -} + _leave(" = t"); + return true; -/* - * dissociate a cache from all the pages it was backing - */ -static void cachefiles_dissociate_pages(struct fscache_cache *cache) -{ - _enter(""); +failed: + _leave(" = f"); + return false; } const struct fscache_cache_ops cachefiles_cache_ops = { .name = "cachefiles", - .alloc_object = cachefiles_alloc_object, - .lookup_object = cachefiles_lookup_object, - .lookup_complete = cachefiles_lookup_complete, - .grab_object = cachefiles_grab_object, - .update_object = cachefiles_update_object, - .invalidate_object = cachefiles_invalidate_object, - .drop_object = cachefiles_drop_object, - .put_object = cachefiles_put_object, - .sync_cache = cachefiles_sync_cache, - .attr_changed = cachefiles_attr_changed, - .read_or_alloc_page = cachefiles_read_or_alloc_page, - .read_or_alloc_pages = cachefiles_read_or_alloc_pages, - .allocate_page = cachefiles_allocate_page, - .allocate_pages = cachefiles_allocate_pages, - .write_page = cachefiles_write_page, - .uncache_page = cachefiles_uncache_page, - .dissociate_pages = cachefiles_dissociate_pages, - .check_consistency = cachefiles_check_consistency, - .begin_read_operation = cachefiles_begin_read_operation, + .acquire_volume = cachefiles_acquire_volume, + .free_volume = cachefiles_free_volume, + .lookup_cookie = cachefiles_lookup_cookie, + .withdraw_cookie = cachefiles_withdraw_cookie, + .invalidate_cookie = cachefiles_invalidate_cookie, + .begin_operation = cachefiles_begin_operation, + .resize_cookie = cachefiles_resize_cookie, + .prepare_to_write = cachefiles_prepare_to_write, }; diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 0a511c36dab8..8dd54d9375b6 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General netfs cache on cache files internal defs * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ @@ -13,58 +13,72 @@ #include <linux/fscache-cache.h> -#include <linux/timer.h> -#include <linux/wait_bit.h> #include <linux/cred.h> -#include <linux/workqueue.h> #include <linux/security.h> +#define CACHEFILES_DIO_BLOCK_SIZE 4096 + struct cachefiles_cache; struct cachefiles_object; -extern unsigned cachefiles_debug; -#define CACHEFILES_DEBUG_KENTER 1 -#define CACHEFILES_DEBUG_KLEAVE 2 -#define CACHEFILES_DEBUG_KDEBUG 4 +enum cachefiles_content { + /* These values are saved on disk */ + CACHEFILES_CONTENT_NO_DATA = 0, /* No content stored */ + CACHEFILES_CONTENT_SINGLE = 1, /* Content is monolithic, all is present */ + CACHEFILES_CONTENT_ALL = 2, /* Content is all present, no map */ + CACHEFILES_CONTENT_BACKFS_MAP = 3, /* Content is piecemeal, mapped through backing fs */ + CACHEFILES_CONTENT_DIRTY = 4, /* Content is dirty (only seen on disk) */ + nr__cachefiles_content +}; -#define cachefiles_gfp (__GFP_RECLAIM | __GFP_NORETRY | __GFP_NOMEMALLOC) +/* + * Cached volume representation. + */ +struct cachefiles_volume { + struct cachefiles_cache *cache; + struct list_head cache_link; /* Link in cache->volumes */ + struct fscache_volume *vcookie; /* The netfs's representation */ + struct dentry *dentry; /* The volume dentry */ + struct dentry *fanout[256]; /* Fanout subdirs */ +}; /* - * node records + * Backing file state. */ struct cachefiles_object { - struct fscache_object fscache; /* fscache handle */ - struct cachefiles_lookup_data *lookup_data; /* cached lookup data */ - struct dentry *dentry; /* the file/dir representing this object */ - struct dentry *backer; /* backing file */ - loff_t i_size; /* object size */ + struct fscache_cookie *cookie; /* Netfs data storage object cookie */ + struct cachefiles_volume *volume; /* Cache volume that holds this object */ + struct list_head cache_link; /* Link in cache->*_list */ + struct file *file; /* The file representing this object */ + char *d_name; /* Backing file name */ + int debug_id; + spinlock_t lock; + refcount_t ref; + u8 d_name_len; /* Length of filename */ + enum cachefiles_content content_info:8; /* Info about content presence */ unsigned long flags; -#define CACHEFILES_OBJECT_ACTIVE 0 /* T if marked active */ - atomic_t usage; /* object usage count */ - uint8_t type; /* object type */ - uint8_t new; /* T if object new */ - spinlock_t work_lock; - struct rb_node active_node; /* link in active tree (dentry is key) */ +#define CACHEFILES_OBJECT_USING_TMPFILE 0 /* Have an unlinked tmpfile */ }; -extern struct kmem_cache *cachefiles_object_jar; - /* * Cache files cache definition */ struct cachefiles_cache { - struct fscache_cache cache; /* FS-Cache record */ + struct fscache_cache *cache; /* Cache cookie */ struct vfsmount *mnt; /* mountpoint holding the cache */ + struct dentry *store; /* Directory into which live objects go */ struct dentry *graveyard; /* directory into which dead objects go */ struct file *cachefilesd; /* manager daemon handle */ + struct list_head volumes; /* List of volume objects */ + struct list_head object_list; /* List of active objects */ + spinlock_t object_list_lock; /* Lock for volumes and object_list */ const struct cred *cache_cred; /* security override for accessing cache */ struct mutex daemon_mutex; /* command serialisation mutex */ wait_queue_head_t daemon_pollwq; /* poll waitqueue for daemon */ - struct rb_root active_nodes; /* active nodes (can't be culled) */ - rwlock_t active_lock; /* lock for active_nodes */ atomic_t gravecounter; /* graveyard uniquifier */ atomic_t f_released; /* number of objects released lately */ atomic_long_t b_released; /* number of blocks released lately */ + atomic_long_t b_writing; /* Number of blocks being written */ unsigned frun_percent; /* when to stop culling (% files) */ unsigned fcull_percent; /* when to start culling (% files) */ unsigned fstop_percent; /* when to stop allocating (% files) */ @@ -89,38 +103,19 @@ struct cachefiles_cache { char *tag; /* cache binding tag */ }; -/* - * backing file read tracking - */ -struct cachefiles_one_read { - wait_queue_entry_t monitor; /* link into monitored waitqueue */ - struct page *back_page; /* backing file page we're waiting for */ - struct page *netfs_page; /* netfs page we're going to fill */ - struct fscache_retrieval *op; /* retrieval op covering this */ - struct list_head op_link; /* link in op's todo list */ -}; - -/* - * backing file write tracking - */ -struct cachefiles_one_write { - struct page *netfs_page; /* netfs page to copy */ - struct cachefiles_object *object; - struct list_head obj_link; /* link in object's lists */ - fscache_rw_complete_t end_io_func; - void *context; -}; +#include <trace/events/cachefiles.h> -/* - * auxiliary data xattr buffer - */ -struct cachefiles_xattr { - uint16_t len; - uint8_t type; - uint8_t data[]; -}; +static inline +struct file *cachefiles_cres_file(struct netfs_cache_resources *cres) +{ + return cres->cache_priv2; +} -#include <trace/events/cachefiles.h> +static inline +struct cachefiles_object *cachefiles_cres_object(struct netfs_cache_resources *cres) +{ + return fscache_cres_cookie(cres)->cache_priv; +} /* * note change of state for daemon @@ -132,74 +127,118 @@ static inline void cachefiles_state_changed(struct cachefiles_cache *cache) } /* - * bind.c + * cache.c */ -extern int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args); -extern void cachefiles_daemon_unbind(struct cachefiles_cache *cache); +extern int cachefiles_add_cache(struct cachefiles_cache *cache); +extern void cachefiles_withdraw_cache(struct cachefiles_cache *cache); + +enum cachefiles_has_space_for { + cachefiles_has_space_check, + cachefiles_has_space_for_write, + cachefiles_has_space_for_create, +}; +extern int cachefiles_has_space(struct cachefiles_cache *cache, + unsigned fnr, unsigned bnr, + enum cachefiles_has_space_for reason); /* * daemon.c */ extern const struct file_operations cachefiles_daemon_fops; -extern int cachefiles_has_space(struct cachefiles_cache *cache, - unsigned fnr, unsigned bnr); +/* + * error_inject.c + */ +#ifdef CONFIG_CACHEFILES_ERROR_INJECTION +extern unsigned int cachefiles_error_injection_state; +extern int cachefiles_register_error_injection(void); +extern void cachefiles_unregister_error_injection(void); + +#else +#define cachefiles_error_injection_state 0 + +static inline int cachefiles_register_error_injection(void) +{ + return 0; +} + +static inline void cachefiles_unregister_error_injection(void) +{ +} +#endif + + +static inline int cachefiles_inject_read_error(void) +{ + return cachefiles_error_injection_state & 2 ? -EIO : 0; +} + +static inline int cachefiles_inject_write_error(void) +{ + return cachefiles_error_injection_state & 2 ? -EIO : + cachefiles_error_injection_state & 1 ? -ENOSPC : + 0; +} + +static inline int cachefiles_inject_remove_error(void) +{ + return cachefiles_error_injection_state & 2 ? -EIO : 0; +} /* * interface.c */ extern const struct fscache_cache_ops cachefiles_cache_ops; +extern void cachefiles_see_object(struct cachefiles_object *object, + enum cachefiles_obj_ref_trace why); +extern struct cachefiles_object *cachefiles_grab_object(struct cachefiles_object *object, + enum cachefiles_obj_ref_trace why); +extern void cachefiles_put_object(struct cachefiles_object *object, + enum cachefiles_obj_ref_trace why); -void cachefiles_put_object(struct fscache_object *_object, - enum fscache_obj_ref_trace why); +/* + * io.c + */ +extern bool cachefiles_begin_operation(struct netfs_cache_resources *cres, + enum fscache_want_state want_state); /* * key.c */ -extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type); +extern bool cachefiles_cook_key(struct cachefiles_object *object); + +/* + * main.c + */ +extern struct kmem_cache *cachefiles_object_jar; /* * namei.c */ -extern void cachefiles_mark_object_inactive(struct cachefiles_cache *cache, - struct cachefiles_object *object, - blkcnt_t i_blocks); -extern int cachefiles_delete_object(struct cachefiles_cache *cache, - struct cachefiles_object *object); -extern int cachefiles_walk_to_object(struct cachefiles_object *parent, - struct cachefiles_object *object, - const char *key, - struct cachefiles_xattr *auxdata); +extern void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, + struct file *file); +extern int cachefiles_bury_object(struct cachefiles_cache *cache, + struct cachefiles_object *object, + struct dentry *dir, + struct dentry *rep, + enum fscache_why_object_killed why); +extern int cachefiles_delete_object(struct cachefiles_object *object, + enum fscache_why_object_killed why); +extern bool cachefiles_look_up_object(struct cachefiles_object *object); extern struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, struct dentry *dir, - const char *name); + const char *name, + bool *_is_new); +extern void cachefiles_put_directory(struct dentry *dir); extern int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, char *filename); extern int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir, char *filename); - -/* - * rdwr.c - */ -extern int cachefiles_read_or_alloc_page(struct fscache_retrieval *, - struct page *, gfp_t); -extern int cachefiles_read_or_alloc_pages(struct fscache_retrieval *, - struct list_head *, unsigned *, - gfp_t); -extern int cachefiles_allocate_page(struct fscache_retrieval *, struct page *, - gfp_t); -extern int cachefiles_allocate_pages(struct fscache_retrieval *, - struct list_head *, unsigned *, gfp_t); -extern int cachefiles_write_page(struct fscache_storage *, struct page *); -extern void cachefiles_uncache_page(struct fscache_object *, struct page *); - -/* - * rdwr2.c - */ -extern int cachefiles_begin_read_operation(struct netfs_read_request *, - struct fscache_retrieval *); +extern struct file *cachefiles_create_tmpfile(struct cachefiles_object *object); +extern bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, + struct cachefiles_object *object); /* * security.c @@ -222,28 +261,32 @@ static inline void cachefiles_end_secure(struct cachefiles_cache *cache, } /* + * volume.c + */ +void cachefiles_acquire_volume(struct fscache_volume *volume); +void cachefiles_free_volume(struct fscache_volume *volume); +void cachefiles_withdraw_volume(struct cachefiles_volume *volume); + +/* * xattr.c */ -extern int cachefiles_check_object_type(struct cachefiles_object *object); -extern int cachefiles_set_object_xattr(struct cachefiles_object *object, - struct cachefiles_xattr *auxdata); -extern int cachefiles_update_object_xattr(struct cachefiles_object *object, - struct cachefiles_xattr *auxdata); -extern int cachefiles_check_auxdata(struct cachefiles_object *object); -extern int cachefiles_check_object_xattr(struct cachefiles_object *object, - struct cachefiles_xattr *auxdata); +extern int cachefiles_set_object_xattr(struct cachefiles_object *object); +extern int cachefiles_check_auxdata(struct cachefiles_object *object, + struct file *file); extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, + struct cachefiles_object *object, struct dentry *dentry); - +extern void cachefiles_prepare_to_write(struct fscache_cookie *cookie); +extern bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume); +extern int cachefiles_check_volume_xattr(struct cachefiles_volume *volume); /* - * error handling + * Error handling */ - #define cachefiles_io_error(___cache, FMT, ...) \ do { \ pr_err("I/O Error: " FMT"\n", ##__VA_ARGS__); \ - fscache_io_error(&(___cache)->cache); \ + fscache_io_error((___cache)->cache); \ set_bit(CACHEFILES_DEAD, &(___cache)->flags); \ } while (0) @@ -251,15 +294,20 @@ do { \ do { \ struct cachefiles_cache *___cache; \ \ - ___cache = container_of((object)->fscache.cache, \ - struct cachefiles_cache, cache); \ - cachefiles_io_error(___cache, FMT, ##__VA_ARGS__); \ + ___cache = (object)->volume->cache; \ + cachefiles_io_error(___cache, FMT " [o=%08x]", ##__VA_ARGS__, \ + (object)->debug_id); \ } while (0) /* - * debug tracing + * Debug tracing */ +extern unsigned cachefiles_debug; +#define CACHEFILES_DEBUG_KENTER 1 +#define CACHEFILES_DEBUG_KLEAVE 2 +#define CACHEFILES_DEBUG_KDEBUG 4 + #define dbgprintk(FMT, ...) \ printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index effe37ef8629..60b1eac2ce78 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -9,8 +9,9 @@ #include <linux/slab.h> #include <linux/file.h> #include <linux/uio.h> +#include <linux/falloc.h> #include <linux/sched/mm.h> -#include <linux/netfs.h> +#include <trace/events/fscache.h> #include "internal.h" struct cachefiles_kiocb { @@ -21,14 +22,18 @@ struct cachefiles_kiocb { size_t skipped; size_t len; }; + struct cachefiles_object *object; netfs_io_terminated_t term_func; void *term_func_priv; bool was_async; + unsigned int inval_counter; /* Copy of cookie->inval_counter */ + u64 b_writing; }; static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki) { if (refcount_dec_and_test(&ki->ki_refcnt)) { + cachefiles_put_object(ki->object, cachefiles_obj_put_ioreq); fput(ki->iocb.ki_filp); kfree(ki); } @@ -40,12 +45,22 @@ static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki) static void cachefiles_read_complete(struct kiocb *iocb, long ret) { struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb); + struct inode *inode = file_inode(ki->iocb.ki_filp); _enter("%ld", ret); + if (ret < 0) + trace_cachefiles_io_error(ki->object, inode, ret, + cachefiles_trace_read_error); + if (ki->term_func) { - if (ret >= 0) - ret += ki->skipped; + if (ret >= 0) { + if (ki->object->cookie->inval_counter == ki->inval_counter) + ki->skipped += ret; + else + ret = -ESTALE; + } + ki->term_func(ki->term_func_priv, ret, ki->was_async); } @@ -58,16 +73,24 @@ static void cachefiles_read_complete(struct kiocb *iocb, long ret) static int cachefiles_read(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, - bool seek_data, + enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv) { + struct cachefiles_object *object; struct cachefiles_kiocb *ki; - struct file *file = cres->cache_priv2; + struct file *file; unsigned int old_nofs; ssize_t ret = -ENOBUFS; size_t len = iov_iter_count(iter), skipped = 0; + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ)) + goto presubmission_error; + + fscache_count_read(); + object = cachefiles_cres_object(cres); + file = cachefiles_cres_file(cres); + _enter("%pD,%li,%llx,%zx/%llx", file, file_inode(file)->i_ino, start_pos, len, i_size_read(file_inode(file))); @@ -75,10 +98,12 @@ static int cachefiles_read(struct netfs_cache_resources *cres, /* If the caller asked us to seek for data before doing the read, then * we should do that now. If we find a gap, we fill it with zeros. */ - if (seek_data) { + if (read_hole != NETFS_READ_HOLE_IGNORE) { loff_t off = start_pos, off2; - off2 = vfs_llseek(file, off, SEEK_DATA); + off2 = cachefiles_inject_read_error(); + if (off2 == 0) + off2 = vfs_llseek(file, off, SEEK_DATA); if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO && off2 != -ENXIO) { skipped = 0; ret = off2; @@ -90,6 +115,10 @@ static int cachefiles_read(struct netfs_cache_resources *cres, * in the region, so clear the rest of the buffer and * return success. */ + ret = -ENODATA; + if (read_hole == NETFS_READ_HOLE_FAIL) + goto presubmission_error; + iov_iter_zero(len, iter); skipped = len; ret = 0; @@ -100,7 +129,7 @@ static int cachefiles_read(struct netfs_cache_resources *cres, iov_iter_zero(skipped, iter); } - ret = -ENOBUFS; + ret = -ENOMEM; ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL); if (!ki) goto presubmission_error; @@ -112,6 +141,8 @@ static int cachefiles_read(struct netfs_cache_resources *cres, ki->iocb.ki_hint = ki_hint_validate(file_write_hint(file)); ki->iocb.ki_ioprio = get_current_ioprio(); ki->skipped = skipped; + ki->object = object; + ki->inval_counter = cres->inval_counter; ki->term_func = term_func; ki->term_func_priv = term_func_priv; ki->was_async = true; @@ -120,9 +151,13 @@ static int cachefiles_read(struct netfs_cache_resources *cres, ki->iocb.ki_complete = cachefiles_read_complete; get_file(ki->iocb.ki_filp); + cachefiles_grab_object(object, cachefiles_obj_get_ioreq); + trace_cachefiles_read(object, file_inode(file), ki->iocb.ki_pos, len - skipped); old_nofs = memalloc_nofs_save(); - ret = vfs_iocb_iter_read(file, &ki->iocb, iter); + ret = cachefiles_inject_read_error(); + if (ret == 0) + ret = vfs_iocb_iter_read(file, &ki->iocb, iter); memalloc_nofs_restore(old_nofs); switch (ret) { case -EIOCBQUEUED: @@ -162,6 +197,7 @@ presubmission_error: static void cachefiles_write_complete(struct kiocb *iocb, long ret) { struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb); + struct cachefiles_object *object = ki->object; struct inode *inode = file_inode(ki->iocb.ki_filp); _enter("%ld", ret); @@ -170,9 +206,14 @@ static void cachefiles_write_complete(struct kiocb *iocb, long ret) __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); __sb_end_write(inode->i_sb, SB_FREEZE_WRITE); + if (ret < 0) + trace_cachefiles_io_error(object, inode, ret, + cachefiles_trace_write_error); + + atomic_long_sub(ki->b_writing, &object->volume->cache->b_writing); + set_bit(FSCACHE_COOKIE_HAVE_DATA, &object->cookie->flags); if (ki->term_func) ki->term_func(ki->term_func_priv, ret, ki->was_async); - cachefiles_put_kiocb(ki); } @@ -185,17 +226,27 @@ static int cachefiles_write(struct netfs_cache_resources *cres, netfs_io_terminated_t term_func, void *term_func_priv) { + struct cachefiles_object *object; + struct cachefiles_cache *cache; struct cachefiles_kiocb *ki; struct inode *inode; - struct file *file = cres->cache_priv2; + struct file *file; unsigned int old_nofs; ssize_t ret = -ENOBUFS; size_t len = iov_iter_count(iter); + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) + goto presubmission_error; + fscache_count_write(); + object = cachefiles_cres_object(cres); + cache = object->volume->cache; + file = cachefiles_cres_file(cres); + _enter("%pD,%li,%llx,%zx/%llx", file, file_inode(file)->i_ino, start_pos, len, i_size_read(file_inode(file))); + ret = -ENOMEM; ki = kzalloc(sizeof(struct cachefiles_kiocb), GFP_KERNEL); if (!ki) goto presubmission_error; @@ -206,14 +257,18 @@ static int cachefiles_write(struct netfs_cache_resources *cres, ki->iocb.ki_flags = IOCB_DIRECT | IOCB_WRITE; ki->iocb.ki_hint = ki_hint_validate(file_write_hint(file)); ki->iocb.ki_ioprio = get_current_ioprio(); + ki->object = object; + ki->inval_counter = cres->inval_counter; ki->start = start_pos; ki->len = len; ki->term_func = term_func; ki->term_func_priv = term_func_priv; ki->was_async = true; + ki->b_writing = (len + (1 << cache->bshift)) >> cache->bshift; if (ki->term_func) ki->iocb.ki_complete = cachefiles_write_complete; + atomic_long_add(ki->b_writing, &cache->b_writing); /* Open-code file_start_write here to grab freeze protection, which * will be released by another thread in aio_complete_rw(). Fool @@ -225,9 +280,13 @@ static int cachefiles_write(struct netfs_cache_resources *cres, __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); get_file(ki->iocb.ki_filp); + cachefiles_grab_object(object, cachefiles_obj_get_ioreq); + trace_cachefiles_write(object, inode, ki->iocb.ki_pos, len); old_nofs = memalloc_nofs_save(); - ret = vfs_iocb_iter_write(file, &ki->iocb, iter); + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_iocb_iter_write(file, &ki->iocb, iter); memalloc_nofs_restore(old_nofs); switch (ret) { case -EIOCBQUEUED: @@ -257,8 +316,8 @@ in_progress: presubmission_error: if (term_func) - term_func(term_func_priv, -ENOMEM, false); - return -ENOMEM; + term_func(term_func_priv, ret, false); + return ret; } /* @@ -268,47 +327,82 @@ presubmission_error: static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subrequest *subreq, loff_t i_size) { - struct fscache_retrieval *op = subreq->rreq->cache_resources.cache_priv; + enum cachefiles_prepare_read_trace why; + struct netfs_read_request *rreq = subreq->rreq; + struct netfs_cache_resources *cres = &rreq->cache_resources; struct cachefiles_object *object; struct cachefiles_cache *cache; + struct fscache_cookie *cookie = fscache_cres_cookie(cres); const struct cred *saved_cred; - struct file *file = subreq->rreq->cache_resources.cache_priv2; + struct file *file = cachefiles_cres_file(cres); + enum netfs_read_source ret = NETFS_DOWNLOAD_FROM_SERVER; loff_t off, to; + ino_t ino = file ? file_inode(file)->i_ino : 0; _enter("%zx @%llx/%llx", subreq->len, subreq->start, i_size); - object = container_of(op->op.object, - struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); + if (subreq->start >= i_size) { + ret = NETFS_FILL_WITH_ZEROES; + why = cachefiles_trace_read_after_eof; + goto out_no_object; + } - if (!file) - goto cache_fail_nosec; + if (test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) { + __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + why = cachefiles_trace_read_no_data; + goto out_no_object; + } - if (subreq->start >= i_size) - return NETFS_FILL_WITH_ZEROES; + /* The object and the file may be being created in the background. */ + if (!file) { + why = cachefiles_trace_read_no_file; + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ)) + goto out_no_object; + file = cachefiles_cres_file(cres); + if (!file) + goto out_no_object; + ino = file_inode(file)->i_ino; + } + object = cachefiles_cres_object(cres); + cache = object->volume->cache; cachefiles_begin_secure(cache, &saved_cred); - off = vfs_llseek(file, subreq->start, SEEK_DATA); + off = cachefiles_inject_read_error(); + if (off == 0) + off = vfs_llseek(file, subreq->start, SEEK_DATA); if (off < 0 && off >= (loff_t)-MAX_ERRNO) { - if (off == (loff_t)-ENXIO) + if (off == (loff_t)-ENXIO) { + why = cachefiles_trace_read_seek_nxio; goto download_and_store; - goto cache_fail; + } + trace_cachefiles_io_error(object, file_inode(file), off, + cachefiles_trace_seek_error); + why = cachefiles_trace_read_seek_error; + goto out; } - if (off >= subreq->start + subreq->len) + if (off >= subreq->start + subreq->len) { + why = cachefiles_trace_read_found_hole; goto download_and_store; + } if (off > subreq->start) { off = round_up(off, cache->bsize); subreq->len = off - subreq->start; + why = cachefiles_trace_read_found_part; goto download_and_store; } - to = vfs_llseek(file, subreq->start, SEEK_HOLE); - if (to < 0 && to >= (loff_t)-MAX_ERRNO) - goto cache_fail; + to = cachefiles_inject_read_error(); + if (to == 0) + to = vfs_llseek(file, subreq->start, SEEK_HOLE); + if (to < 0 && to >= (loff_t)-MAX_ERRNO) { + trace_cachefiles_io_error(object, file_inode(file), to, + cachefiles_trace_seek_error); + why = cachefiles_trace_read_seek_error; + goto out; + } if (to < subreq->start + subreq->len) { if (subreq->start + subreq->len >= i_size) @@ -318,32 +412,119 @@ static enum netfs_read_source cachefiles_prepare_read(struct netfs_read_subreque subreq->len = to - subreq->start; } - cachefiles_end_secure(cache, saved_cred); - return NETFS_READ_FROM_CACHE; + why = cachefiles_trace_read_have_data; + ret = NETFS_READ_FROM_CACHE; + goto out; download_and_store: - if (cachefiles_has_space(cache, 0, (subreq->len + PAGE_SIZE - 1) / PAGE_SIZE) == 0) - __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); -cache_fail: + __set_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); +out: cachefiles_end_secure(cache, saved_cred); -cache_fail_nosec: - return NETFS_DOWNLOAD_FROM_SERVER; +out_no_object: + trace_cachefiles_prep_read(subreq, ret, why, ino); + return ret; } /* * Prepare for a write to occur. */ -static int cachefiles_prepare_write(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size) +static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, + loff_t *_start, size_t *_len, loff_t i_size, + bool no_space_allocated_yet) { - loff_t start = *_start; + struct cachefiles_object *object = cachefiles_cres_object(cres); + struct cachefiles_cache *cache = object->volume->cache; + struct file *file = cachefiles_cres_file(cres); + loff_t start = *_start, pos; size_t len = *_len, down; + int ret; /* Round to DIO size */ down = start - round_down(start, PAGE_SIZE); *_start = start - down; *_len = round_up(down + len, PAGE_SIZE); - return 0; + + /* We need to work out whether there's sufficient disk space to perform + * the write - but we can skip that check if we have space already + * allocated. + */ + if (no_space_allocated_yet) + goto check_space; + + pos = cachefiles_inject_read_error(); + if (pos == 0) + pos = vfs_llseek(file, *_start, SEEK_DATA); + if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) { + if (pos == -ENXIO) + goto check_space; /* Unallocated tail */ + trace_cachefiles_io_error(object, file_inode(file), pos, + cachefiles_trace_seek_error); + return pos; + } + if ((u64)pos >= (u64)*_start + *_len) + goto check_space; /* Unallocated region */ + + /* We have a block that's at least partially filled - if we're low on + * space, we need to see if it's fully allocated. If it's not, we may + * want to cull it. + */ + if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE, + cachefiles_has_space_check) == 0) + return 0; /* Enough space to simply overwrite the whole block */ + + pos = cachefiles_inject_read_error(); + if (pos == 0) + pos = vfs_llseek(file, *_start, SEEK_HOLE); + if (pos < 0 && pos >= (loff_t)-MAX_ERRNO) { + trace_cachefiles_io_error(object, file_inode(file), pos, + cachefiles_trace_seek_error); + return pos; + } + if ((u64)pos >= (u64)*_start + *_len) + return 0; /* Fully allocated */ + + /* Partially allocated, but insufficient space: cull. */ + fscache_count_no_write_space(); + ret = cachefiles_inject_remove_error(); + if (ret == 0) + ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + *_start, *_len); + if (ret < 0) { + trace_cachefiles_io_error(object, file_inode(file), ret, + cachefiles_trace_fallocate_error); + cachefiles_io_error_obj(object, + "CacheFiles: fallocate failed (%d)\n", ret); + ret = -EIO; + } + + return ret; + +check_space: + return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE, + cachefiles_has_space_for_write); +} + +static int cachefiles_prepare_write(struct netfs_cache_resources *cres, + loff_t *_start, size_t *_len, loff_t i_size, + bool no_space_allocated_yet) +{ + struct cachefiles_object *object = cachefiles_cres_object(cres); + struct cachefiles_cache *cache = object->volume->cache; + const struct cred *saved_cred; + int ret; + + if (!cachefiles_cres_file(cres)) { + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_WRITE)) + return -ENOBUFS; + if (!cachefiles_cres_file(cres)) + return -ENOBUFS; + } + + cachefiles_begin_secure(cache, &saved_cred); + ret = __cachefiles_prepare_write(cres, _start, _len, i_size, + no_space_allocated_yet); + cachefiles_end_secure(cache, saved_cred); + return ret; } /* @@ -351,19 +532,11 @@ static int cachefiles_prepare_write(struct netfs_cache_resources *cres, */ static void cachefiles_end_operation(struct netfs_cache_resources *cres) { - struct fscache_retrieval *op = cres->cache_priv; - struct file *file = cres->cache_priv2; - - _enter(""); + struct file *file = cachefiles_cres_file(cres); if (file) fput(file); - if (op) { - fscache_op_complete(&op->op, false); - fscache_put_retrieval(op); - } - - _leave(""); + fscache_end_cookie_access(fscache_cres_cookie(cres), fscache_access_io_end); } static const struct netfs_cache_ops cachefiles_netfs_cache_ops = { @@ -377,44 +550,25 @@ static const struct netfs_cache_ops cachefiles_netfs_cache_ops = { /* * Open the cache file when beginning a cache operation. */ -int cachefiles_begin_read_operation(struct netfs_read_request *rreq, - struct fscache_retrieval *op) +bool cachefiles_begin_operation(struct netfs_cache_resources *cres, + enum fscache_want_state want_state) { - struct cachefiles_object *object; - struct cachefiles_cache *cache; - struct path path; - struct file *file; + struct cachefiles_object *object = cachefiles_cres_object(cres); + + if (!cachefiles_cres_file(cres)) { + cres->ops = &cachefiles_netfs_cache_ops; + if (object->file) { + spin_lock(&object->lock); + if (!cres->cache_priv2 && object->file) + cres->cache_priv2 = get_file(object->file); + spin_unlock(&object->lock); + } + } - _enter(""); - - object = container_of(op->op.object, - struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - path.mnt = cache->mnt; - path.dentry = object->backer; - file = open_with_fake_path(&path, O_RDWR | O_LARGEFILE | O_DIRECT, - d_inode(object->backer), cache->cache_cred); - if (IS_ERR(file)) - return PTR_ERR(file); - if (!S_ISREG(file_inode(file)->i_mode)) - goto error_file; - 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_file; + if (!cachefiles_cres_file(cres) && want_state != FSCACHE_WANT_PARAMS) { + pr_err("failed to get cres->file\n"); + return false; } - fscache_get_retrieval(op); - rreq->cache_resources.cache_priv = op; - rreq->cache_resources.cache_priv2 = file; - rreq->cache_resources.ops = &cachefiles_netfs_cache_ops; - rreq->cache_resources.debug_id = object->fscache.debug_id; - _leave(""); - return 0; - -error_file: - fput(file); - return -EIO; + return true; } diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c index 7f94efc97e23..bf935e25bdbe 100644 --- a/fs/cachefiles/key.c +++ b/fs/cachefiles/key.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* Key to pathname encoder * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ @@ -22,134 +22,117 @@ static const char cachefiles_filecharmap[256] = { [48 ... 127] = 1, /* '0' -> '~' */ }; +static inline unsigned int how_many_hex_digits(unsigned int x) +{ + return x ? round_up(ilog2(x) + 1, 4) / 4 : 0; +} + /* * turn the raw key into something cooked - * - the raw key should include the length in the two bytes at the front - * - the key may be up to 514 bytes in length (including the length word) + * - the key may be up to NAME_MAX in length (including the length word) * - "base64" encode the strange keys, mapping 3 bytes of raw to four of * cooked * - need to cut the cooked key into 252 char lengths (189 raw bytes) */ -char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type) +bool cachefiles_cook_key(struct cachefiles_object *object) { - unsigned char csum, ch; - unsigned int acc; - char *key; - int loop, len, max, seg, mark, print; + const u8 *key = fscache_get_key(object->cookie), *kend; + unsigned char ch; + unsigned int acc, i, n, nle, nbe, keylen = object->cookie->key_len; + unsigned int b64len, len, print, pad; + char *name, sep; - _enter(",%d", keylen); + _enter(",%u,%*phN", keylen, keylen, key); - BUG_ON(keylen < 2 || keylen > 514); + BUG_ON(keylen > NAME_MAX - 3); - csum = raw[0] + raw[1]; print = 1; - for (loop = 2; loop < keylen; loop++) { - ch = raw[loop]; - csum += ch; + for (i = 0; i < keylen; i++) { + ch = key[i]; print &= cachefiles_filecharmap[ch]; } + /* If the path is usable ASCII, then we render it directly */ if (print) { - /* if the path is usable ASCII, then we render it directly */ - max = keylen - 2; - max += 2; /* two base64'd length chars on the front */ - max += 5; /* @checksum/M */ - max += 3 * 2; /* maximum number of segment dividers (".../M") - * is ((514 + 251) / 252) = 3 - */ - max += 1; /* NUL on end */ - } else { - /* calculate the maximum length of the cooked key */ - keylen = (keylen + 2) / 3; - - max = keylen * 4; - max += 5; /* @checksum/M */ - max += 3 * 2; /* maximum number of segment dividers (".../M") - * is ((514 + 188) / 189) = 3 - */ - max += 1; /* NUL on end */ + len = 1 + keylen; + name = kmalloc(len + 1, GFP_KERNEL); + if (!name) + return false; + + name[0] = 'D'; /* Data object type, string encoding */ + memcpy(name + 1, key, keylen); + goto success; } - max += 1; /* 2nd NUL on end */ - - _debug("max: %d", max); - - key = kmalloc(max, cachefiles_gfp); - if (!key) - return NULL; - - len = 0; - - /* build the cooked key */ - sprintf(key, "@%02x%c+", (unsigned) csum, 0); - len = 5; - mark = len - 1; - - if (print) { - acc = *(uint16_t *) raw; - raw += 2; - - key[len + 1] = cachefiles_charmap[acc & 63]; - acc >>= 6; - key[len] = cachefiles_charmap[acc & 63]; - len += 2; - - seg = 250; - for (loop = keylen; loop > 0; loop--) { - if (seg <= 0) { - key[len++] = '\0'; - mark = len; - key[len++] = '+'; - seg = 252; - } - - key[len++] = *raw++; - ASSERT(len < max); - } - - switch (type) { - case FSCACHE_COOKIE_TYPE_INDEX: type = 'I'; break; - case FSCACHE_COOKIE_TYPE_DATAFILE: type = 'D'; break; - default: type = 'S'; break; - } - } else { - seg = 252; - for (loop = keylen; loop > 0; loop--) { - if (seg <= 0) { - key[len++] = '\0'; - mark = len; - key[len++] = '+'; - seg = 252; - } - - acc = *raw++; - acc |= *raw++ << 8; - acc |= *raw++ << 16; - - _debug("acc: %06x", acc); - - key[len++] = cachefiles_charmap[acc & 63]; - acc >>= 6; - key[len++] = cachefiles_charmap[acc & 63]; - acc >>= 6; - key[len++] = cachefiles_charmap[acc & 63]; - acc >>= 6; - key[len++] = cachefiles_charmap[acc & 63]; - - ASSERT(len < max); - } + /* See if it makes sense to encode it as "hex,hex,hex" for each 32-bit + * chunk. We rely on the key having been padded out to a whole number + * of 32-bit words. + */ + n = round_up(keylen, 4); + nbe = nle = 0; + for (i = 0; i < n; i += 4) { + u32 be = be32_to_cpu(*(__be32 *)(key + i)); + u32 le = le32_to_cpu(*(__le32 *)(key + i)); + + nbe += 1 + how_many_hex_digits(be); + nle += 1 + how_many_hex_digits(le); + } - switch (type) { - case FSCACHE_COOKIE_TYPE_INDEX: type = 'J'; break; - case FSCACHE_COOKIE_TYPE_DATAFILE: type = 'E'; break; - default: type = 'T'; break; + b64len = DIV_ROUND_UP(keylen, 3); + pad = b64len * 3 - keylen; + b64len = 2 + b64len * 4; /* Length if we base64-encode it */ + _debug("len=%u nbe=%u nle=%u b64=%u", keylen, nbe, nle, b64len); + if (nbe < b64len || nle < b64len) { + unsigned int nlen = min(nbe, nle) + 1; + name = kmalloc(nlen, GFP_KERNEL); + if (!name) + return false; + sep = (nbe <= nle) ? 'S' : 'T'; /* Encoding indicator */ + len = 0; + for (i = 0; i < n; i += 4) { + u32 x; + if (nbe <= nle) + x = be32_to_cpu(*(__be32 *)(key + i)); + else + x = le32_to_cpu(*(__le32 *)(key + i)); + name[len++] = sep; + if (x != 0) + len += snprintf(name + len, nlen - len, "%x", x); + sep = ','; } + goto success; } - key[mark] = type; - key[len++] = 0; - key[len] = 0; + /* We need to base64-encode it */ + name = kmalloc(b64len + 1, GFP_KERNEL); + if (!name) + return false; + + name[0] = 'E'; + name[1] = '0' + pad; + len = 2; + kend = key + keylen; + do { + acc = *key++; + if (key < kend) { + acc |= *key++ << 8; + if (key < kend) + acc |= *key++ << 16; + } - _leave(" = %s %d", key, len); - return key; + name[len++] = cachefiles_charmap[acc & 63]; + acc >>= 6; + name[len++] = cachefiles_charmap[acc & 63]; + acc >>= 6; + name[len++] = cachefiles_charmap[acc & 63]; + acc >>= 6; + name[len++] = cachefiles_charmap[acc & 63]; + } while (key < kend); + +success: + name[len] = 0; + object->d_name = name; + object->d_name_len = len; + _leave(" = %s", object->d_name); + return true; } diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c index 9c8d34c49b12..3f369c6f816d 100644 --- a/fs/cachefiles/main.c +++ b/fs/cachefiles/main.c @@ -2,7 +2,7 @@ /* Network filesystem caching backend to use cache files on a premounted * filesystem * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ @@ -18,6 +18,8 @@ #include <linux/statfs.h> #include <linux/sysctl.h> #include <linux/miscdevice.h> +#include <linux/netfs.h> +#include <trace/events/netfs.h> #define CREATE_TRACE_POINTS #include "internal.h" @@ -37,14 +39,6 @@ static struct miscdevice cachefiles_dev = { .fops = &cachefiles_daemon_fops, }; -static void cachefiles_object_init_once(void *_object) -{ - struct cachefiles_object *object = _object; - - memset(object, 0, sizeof(*object)); - spin_lock_init(&object->work_lock); -} - /* * initialise the fs caching module */ @@ -52,6 +46,9 @@ static int __init cachefiles_init(void) { int ret; + ret = cachefiles_register_error_injection(); + if (ret < 0) + goto error_einj; ret = misc_register(&cachefiles_dev); if (ret < 0) goto error_dev; @@ -61,9 +58,7 @@ static int __init cachefiles_init(void) cachefiles_object_jar = kmem_cache_create("cachefiles_object_jar", sizeof(struct cachefiles_object), - 0, - SLAB_HWCACHE_ALIGN, - cachefiles_object_init_once); + 0, SLAB_HWCACHE_ALIGN, NULL); if (!cachefiles_object_jar) { pr_notice("Failed to allocate an object jar\n"); goto error_object_jar; @@ -75,6 +70,8 @@ static int __init cachefiles_init(void) error_object_jar: misc_deregister(&cachefiles_dev); error_dev: + cachefiles_unregister_error_injection(); +error_einj: pr_err("failed to register: %d\n", ret); return ret; } @@ -90,6 +87,7 @@ static void __exit cachefiles_exit(void) kmem_cache_destroy(cachefiles_object_jar); misc_deregister(&cachefiles_dev); + cachefiles_unregister_error_injection(); } module_exit(cachefiles_exit); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index a9aca5ab5970..9bd692870617 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -1,295 +1,268 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles path walking and related routines * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/file.h> #include <linux/fs.h> -#include <linux/fsnotify.h> -#include <linux/quotaops.h> -#include <linux/xattr.h> -#include <linux/mount.h> #include <linux/namei.h> -#include <linux/security.h> -#include <linux/slab.h> #include "internal.h" -#define CACHEFILES_KEYBUF_SIZE 512 - /* - * dump debugging info about an object + * 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 noinline -void __cachefiles_printk_object(struct cachefiles_object *object, - const char *prefix) +static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) { - struct fscache_cookie *cookie; - const u8 *k; - unsigned loop; - - pr_err("%sobject: OBJ%x\n", prefix, object->fscache.debug_id); - pr_err("%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n", - prefix, object->fscache.state->name, - object->fscache.flags, work_busy(&object->fscache.work), - object->fscache.events, object->fscache.event_mask); - pr_err("%sops=%u inp=%u exc=%u\n", - prefix, object->fscache.n_ops, object->fscache.n_in_progress, - object->fscache.n_exclusive); - pr_err("%sparent=%x\n", - prefix, object->fscache.parent ? object->fscache.parent->debug_id : 0); - - spin_lock(&object->fscache.lock); - cookie = object->fscache.cookie; - if (cookie) { - pr_err("%scookie=%x [pr=%x nd=%p fl=%lx]\n", - prefix, - cookie->debug_id, - cookie->parent ? cookie->parent->debug_id : 0, - cookie->netfs_data, - cookie->flags); - pr_err("%skey=[%u] '", prefix, cookie->key_len); - k = (cookie->key_len <= sizeof(cookie->inline_key)) ? - cookie->inline_key : cookie->key; - for (loop = 0; loop < cookie->key_len; loop++) - pr_cont("%02x", k[loop]); - pr_cont("'\n"); + struct inode *inode = d_backing_inode(dentry); + 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 { - pr_err("%scookie=NULL\n", prefix); + pr_notice("cachefiles: Inode already in use: %pd\n", dentry); } - spin_unlock(&object->fscache.lock); + + return can_use; } -/* - * dump debugging info about a pair of objects - */ -static noinline void cachefiles_printk_object(struct cachefiles_object *object, - struct cachefiles_object *xobject) +static bool cachefiles_mark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) { - if (object) - __cachefiles_printk_object(object, ""); - if (xobject) - __cachefiles_printk_object(xobject, "x"); + struct inode *inode = d_backing_inode(dentry); + bool can_use; + + inode_lock(inode); + can_use = __cachefiles_mark_inode_in_use(object, dentry); + inode_unlock(inode); + return can_use; } /* - * mark the owner of a dentry, if there is one, to indicate that that dentry - * has been preemptively deleted - * - the caller must hold the i_mutex on the dentry's parent as required to - * call vfs_unlink(), vfs_rmdir() or vfs_rename() + * Unmark a backing inode. The caller must hold the inode lock. */ -static void cachefiles_mark_object_buried(struct cachefiles_cache *cache, - struct dentry *dentry, - enum fscache_why_object_killed why) +static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) { - struct cachefiles_object *object; - struct rb_node *p; - - _enter(",'%pd'", dentry); + struct inode *inode = d_backing_inode(dentry); - write_lock(&cache->active_lock); + inode->i_flags &= ~S_KERNEL_FILE; + trace_cachefiles_mark_inactive(object, inode); +} - p = cache->active_nodes.rb_node; - while (p) { - object = rb_entry(p, struct cachefiles_object, active_node); - if (object->dentry > dentry) - p = p->rb_left; - else if (object->dentry < dentry) - p = p->rb_right; - else - goto found_dentry; +/* + * 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); + + if (inode) { + inode_lock(inode); + __cachefiles_unmark_inode_in_use(object, file->f_path.dentry); + inode_unlock(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); + } } +} - write_unlock(&cache->active_lock); - trace_cachefiles_mark_buried(NULL, dentry, why); - _leave(" [no owner]"); - return; +/* + * 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; - /* found the dentry for */ -found_dentry: - kdebug("preemptive burial: OBJ%x [%s] %pd", - object->fscache.debug_id, - object->fscache.state->name, - dentry); + _enter(",,%s", dirname); - trace_cachefiles_mark_buried(object, dentry, why); + /* search the current directory for the element name */ + inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - if (fscache_object_is_live(&object->fscache)) { - pr_err("\n"); - pr_err("Error: Can't preemptively bury live object\n"); - cachefiles_printk_object(object, NULL); - } else { - if (why != FSCACHE_OBJECT_IS_STALE) - fscache_object_mark_killed(&object->fscache, why); +retry: + ret = cachefiles_inject_read_error(); + if (ret == 0) + subdir = lookup_one_len(dirname, dir, strlen(dirname)); + else + subdir = ERR_PTR(ret); + 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; } - write_unlock(&cache->active_lock); - _leave(" [owner marked]"); -} + _debug("subdir -> %pd %s", + subdir, d_backing_inode(subdir) ? "positive" : "negative"); -/* - * record the fact that an object is now active - */ -static int cachefiles_mark_object_active(struct cachefiles_cache *cache, - struct cachefiles_object *object) -{ - struct cachefiles_object *xobject; - struct rb_node **_p, *_parent = NULL; - struct dentry *dentry; + /* 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; - _enter(",%x", object->fscache.debug_id); + _debug("attempt mkdir"); -try_again: - write_lock(&cache->active_lock); + 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(&init_user_ns, d_inode(dir), subdir, 0700); + if (ret < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dir), ret, + cachefiles_trace_mkdir_error); + goto mkdir_error; + } - dentry = object->dentry; - trace_cachefiles_mark_active(object, dentry); + if (unlikely(d_unhashed(subdir))) { + cachefiles_put_directory(subdir); + goto retry; + } + ASSERT(d_backing_inode(subdir)); - if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) { - pr_err("Error: Object already active\n"); - cachefiles_printk_object(object, NULL); - BUG(); + _debug("mkdir -> %pd{ino=%lu}", + subdir, d_backing_inode(subdir)->i_ino); + if (_is_new) + *_is_new = true; } - _p = &cache->active_nodes.rb_node; - while (*_p) { - _parent = *_p; - xobject = rb_entry(_parent, - struct cachefiles_object, active_node); + /* Tell rmdir() it's not allowed to delete the subdir */ + inode_lock(d_inode(subdir)); + inode_unlock(d_inode(dir)); - ASSERT(xobject != object); + if (!__cachefiles_mark_inode_in_use(NULL, subdir)) + goto mark_error; - if (xobject->dentry > dentry) - _p = &(*_p)->rb_left; - else if (xobject->dentry < dentry) - _p = &(*_p)->rb_right; - else - goto wait_for_old_object; - } + inode_unlock(d_inode(subdir)); - rb_link_node(&object->active_node, _parent, _p); - rb_insert_color(&object->active_node, &cache->active_nodes); + /* we need to make sure the subdir is a directory */ + ASSERT(d_backing_inode(subdir)); - write_unlock(&cache->active_lock); - _leave(" = 0"); - return 0; + if (!d_can_lookup(subdir)) { + pr_err("%s is not a directory\n", dirname); + ret = -EIO; + goto check_error; + } - /* an old object from a previous incarnation is hogging the slot - we - * need to wait for it to be destroyed */ -wait_for_old_object: - trace_cachefiles_wait_active(object, dentry, xobject); - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); - - if (fscache_object_is_live(&xobject->fscache)) { - pr_err("\n"); - pr_err("Error: Unexpected object collision\n"); - cachefiles_printk_object(object, xobject); - } - atomic_inc(&xobject->usage); - write_unlock(&cache->active_lock); - - if (test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) { - wait_queue_head_t *wq; - - signed long timeout = 60 * HZ; - wait_queue_entry_t wait; - bool requeue; - - /* if the object we're waiting for is queued for processing, - * then just put ourselves on the queue behind it */ - if (work_pending(&xobject->fscache.work)) { - _debug("queue OBJ%x behind OBJ%x immediately", - object->fscache.debug_id, - xobject->fscache.debug_id); - goto requeue; - } + 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; - /* otherwise we sleep until either the object we're waiting for - * is done, or the fscache_object is congested */ - wq = bit_waitqueue(&xobject->flags, CACHEFILES_OBJECT_ACTIVE); - init_wait(&wait); - requeue = false; - do { - prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); - if (!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) - break; - - requeue = fscache_object_sleep_till_congested(&timeout); - } while (timeout > 0 && !requeue); - finish_wait(wq, &wait); - - if (requeue && - test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)) { - _debug("queue OBJ%x behind OBJ%x after wait", - object->fscache.debug_id, - xobject->fscache.debug_id); - goto requeue; - } + _leave(" = [%lu]", d_backing_inode(subdir)->i_ino); + return subdir; - if (timeout <= 0) { - pr_err("\n"); - pr_err("Error: Overlong wait for old active object to go away\n"); - cachefiles_printk_object(object, xobject); - goto requeue; - } - } +check_error: + cachefiles_put_directory(subdir); + _leave(" = %d [check]", ret); + return ERR_PTR(ret); - ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)); +mark_error: + inode_unlock(d_inode(subdir)); + dput(subdir); + return ERR_PTR(-EBUSY); - cache->cache.ops->put_object(&xobject->fscache, - (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_retry); - goto try_again; +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); -requeue: - cache->cache.ops->put_object(&xobject->fscache, - (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_timeo); - _leave(" = -ETIMEDOUT"); - return -ETIMEDOUT; +nomem_d_alloc: + inode_unlock(d_inode(dir)); + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); } /* - * Mark an object as being inactive. + * Put a subdirectory. */ -void cachefiles_mark_object_inactive(struct cachefiles_cache *cache, - struct cachefiles_object *object, - blkcnt_t i_blocks) +void cachefiles_put_directory(struct dentry *dir) { - struct dentry *dentry = object->dentry; - struct inode *inode = d_backing_inode(dentry); - - trace_cachefiles_mark_inactive(object, dentry, inode); + if (dir) { + inode_lock(dir->d_inode); + __cachefiles_unmark_inode_in_use(NULL, dir); + inode_unlock(dir->d_inode); + dput(dir); + } +} - write_lock(&cache->active_lock); - rb_erase(&object->active_node, &cache->active_nodes); - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); - write_unlock(&cache->active_lock); +/* + * 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; - wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE); + trace_cachefiles_unlink(object, dentry, why); + ret = security_path_unlink(&path, dentry); + if (ret < 0) { + cachefiles_io_error(cache, "Unlink security error"); + return ret; + } - /* This object can now be culled, so we need to let the daemon know - * that there is something it can remove if it needs to. - */ - atomic_long_add(i_blocks, &cache->b_released); - if (atomic_inc_return(&cache->f_released)) - cachefiles_state_changed(cache); + ret = cachefiles_inject_remove_error(); + if (ret == 0) { + ret = vfs_unlink(&init_user_ns, 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 an object representation from the cache + * - File backed objects are unlinked + * - Directory backed objects are stuffed into the graveyard for userspace to * delete - * - unlocks the directory mutex */ -static int cachefiles_bury_object(struct cachefiles_cache *cache, - struct cachefiles_object *object, - struct dentry *dir, - struct dentry *rep, - bool preemptive, - enum fscache_why_object_killed why) +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; @@ -298,29 +271,21 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache, _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)) { - _debug("unlink stale object"); - - path.mnt = cache->mnt; - path.dentry = dir; - ret = security_path_unlink(&path, rep); - if (ret < 0) { - cachefiles_io_error(cache, "Unlink security error"); - } else { - trace_cachefiles_unlink(object, rep, why); - ret = vfs_unlink(&init_user_ns, d_inode(dir), rep, - NULL); - - if (preemptive) - cachefiles_mark_object_buried(cache, rep, why); - } + 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)); - - if (ret == -EIO) - cachefiles_io_error(cache, "Unlink failed"); - _leave(" = %d", ret); return ret; } @@ -368,14 +333,16 @@ try_again: 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)); + cachefiles_io_error(cache, "Lookup error %ld", PTR_ERR(grave)); return -EIO; } @@ -420,15 +387,18 @@ try_again: .new_dentry = grave, }; trace_cachefiles_rename(object, rep, grave, why); - ret = vfs_rename(&rd); + 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); - - if (preemptive) - cachefiles_mark_object_buried(cache, rep, why); } + __cachefiles_unmark_inode_in_use(object, rep); unlock_rename(cache->graveyard, dir); dput(grave); _leave(" = 0"); @@ -436,493 +406,358 @@ try_again: } /* - * delete an object representation from the cache + * Delete a cache file. */ -int cachefiles_delete_object(struct cachefiles_cache *cache, - struct cachefiles_object *object) +int cachefiles_delete_object(struct cachefiles_object *object, + enum fscache_why_object_killed why) { - struct dentry *dir; + 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->fscache.debug_id, object->dentry); - - ASSERT(object->dentry); - ASSERT(d_backing_inode(object->dentry)); - ASSERT(object->dentry->d_parent); + _enter(",OBJ%x{%pD}", object->debug_id, object->file); - dir = dget_parent(object->dentry); + /* Stop the dentry being negated if it's only pinned by a file struct. */ + dget(dentry); - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); - - if (test_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->fscache.flags)) { - /* object allocation for the same key preemptively deleted this - * object's file so that it could create its own file */ - _debug("object preemptively buried"); - inode_unlock(d_inode(dir)); - ret = 0; - } else { - /* we need to check that our parent is _still_ our parent - it - * may have been renamed */ - if (dir == object->dentry->d_parent) { - ret = cachefiles_bury_object(cache, object, dir, - object->dentry, false, - FSCACHE_OBJECT_WAS_RETIRED); - } else { - /* it got moved, presumably by cachefilesd culling it, - * so it's no longer in the key path and we can ignore - * it */ - inode_unlock(d_inode(dir)); - ret = 0; - } - } - - dput(dir); - _leave(" = %d", ret); + 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; } /* - * walk from the parent object to the child object through the backing - * filesystem, creating directories as we go + * Create a temporary file and leave it unattached and un-xattr'd until the + * time comes to discard the object from memory. */ -int cachefiles_walk_to_object(struct cachefiles_object *parent, - struct cachefiles_object *object, - const char *key, - struct cachefiles_xattr *auxdata) +struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) { - struct cachefiles_cache *cache; - struct dentry *dir, *next = NULL; - struct inode *inode; + 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; struct path path; - const char *name; - int ret, nlen; - - _enter("OBJ%x{%pd},OBJ%x,%s,", - parent->fscache.debug_id, parent->dentry, - object->fscache.debug_id, key); - - cache = container_of(parent->fscache.cache, - struct cachefiles_cache, cache); - path.mnt = cache->mnt; - - ASSERT(parent->dentry); - ASSERT(d_backing_inode(parent->dentry)); - - if (!(d_is_dir(parent->dentry))) { - // TODO: convert file to dir - _leave("looking up in none directory"); - return -ENOBUFS; - } - - dir = dget(parent->dentry); - -advance: - /* attempt to transit the first directory component */ - name = key; - nlen = strlen(key); - - /* key ends in a double NUL */ - key = key + nlen + 1; - if (!*key) - key = NULL; - -lookup_again: - /* search the current directory for the element name */ - _debug("lookup '%s'", name); - - inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); + uint64_t ni_size = object->cookie->object_size; + long ret; - next = lookup_one_len(name, dir, nlen); - if (IS_ERR(next)) { - trace_cachefiles_lookup(object, next, NULL); - goto lookup_error; - } + ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); - inode = d_backing_inode(next); - trace_cachefiles_lookup(object, next, inode); - _debug("next -> %pd %s", next, inode ? "positive" : "negative"); - - if (!key) - object->new = !inode; - - /* if this element of the path doesn't exist, then the lookup phase - * failed, and we can release any readers in the certain knowledge that - * there's nothing for them to actually read */ - if (d_is_negative(next)) - fscache_object_lookup_negative(&object->fscache); - - /* we need to create the object if it's negative */ - if (key || object->type == FSCACHE_COOKIE_TYPE_INDEX) { - /* index objects and intervening tree levels must be subdirs */ - if (d_is_negative(next)) { - ret = cachefiles_has_space(cache, 1, 0); - if (ret < 0) - goto no_space_error; - - path.dentry = dir; - ret = security_path_mkdir(&path, next, 0); - if (ret < 0) - goto create_error; - ret = vfs_mkdir(&init_user_ns, d_inode(dir), next, 0); - if (!key) - trace_cachefiles_mkdir(object, next, ret); - if (ret < 0) - goto create_error; - - if (unlikely(d_unhashed(next))) { - dput(next); - inode_unlock(d_inode(dir)); - goto lookup_again; - } - ASSERT(d_backing_inode(next)); - - _debug("mkdir -> %pd{ino=%lu}", - next, d_backing_inode(next)->i_ino); - - } else if (!d_can_lookup(next)) { - pr_err("inode %lu is not a directory\n", - d_backing_inode(next)->i_ino); - ret = -ENOBUFS; - goto error; - } + cachefiles_begin_secure(cache, &saved_cred); - } else { - /* non-index objects start out life as files */ - if (d_is_negative(next)) { - ret = cachefiles_has_space(cache, 1, 0); - if (ret < 0) - goto no_space_error; - - path.dentry = dir; - ret = security_path_mknod(&path, next, S_IFREG, 0); - if (ret < 0) - goto create_error; - ret = vfs_create(&init_user_ns, d_inode(dir), next, - S_IFREG, true); - trace_cachefiles_create(object, next, ret); - if (ret < 0) - goto create_error; - - ASSERT(d_backing_inode(next)); - - _debug("create -> %pd{ino=%lu}", - next, d_backing_inode(next)->i_ino); - - } else if (!d_can_lookup(next) && - !d_is_reg(next) - ) { - pr_err("inode %lu is not a file or directory\n", - d_backing_inode(next)->i_ino); - ret = -ENOBUFS; - goto error; + path.mnt = cache->mnt; + ret = cachefiles_inject_write_error(); + if (ret == 0) + path.dentry = vfs_tmpfile(&init_user_ns, fan, S_IFREG, O_RDWR); + else + path.dentry = ERR_PTR(ret); + if (IS_ERR(path.dentry)) { + trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(path.dentry), + cachefiles_trace_tmpfile_error); + if (PTR_ERR(path.dentry) == -EIO) + cachefiles_io_error_obj(object, "Failed to create tmpfile"); + file = ERR_CAST(path.dentry); + goto out; + } + + trace_cachefiles_tmpfile(object, d_backing_inode(path.dentry)); + + if (!cachefiles_mark_inode_in_use(object, path.dentry)) { + file = ERR_PTR(-EBUSY); + goto out_dput; + } + + if (ni_size > 0) { + trace_cachefiles_trunc(object, d_backing_inode(path.dentry), 0, ni_size, + cachefiles_trunc_expand_tmpfile); + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_truncate(&path, ni_size); + if (ret < 0) { + trace_cachefiles_vfs_error( + object, d_backing_inode(path.dentry), ret, + cachefiles_trace_trunc_error); + file = ERR_PTR(ret); + goto out_dput; } } - /* process the next component */ - if (key) { - _debug("advance"); - inode_unlock(d_inode(dir)); - dput(dir); - dir = next; - next = NULL; - goto advance; + file = open_with_fake_path(&path, O_RDWR | O_LARGEFILE | O_DIRECT, + d_backing_inode(path.dentry), cache->cache_cred); + if (IS_ERR(file)) { + trace_cachefiles_vfs_error(object, d_backing_inode(path.dentry), + PTR_ERR(file), + cachefiles_trace_open_error); + goto out_dput; + } + 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"); + file = ERR_PTR(-EINVAL); } - /* we've found the object we were looking for */ - object->dentry = next; - - /* if we've found that the terminal object exists, then we need to - * check its attributes and delete it if it's out of date */ - if (!object->new) { - _debug("validate '%pd'", next); - - ret = cachefiles_check_object_xattr(object, auxdata); - if (ret == -ESTALE) { - /* delete the object (the deleter drops the directory - * mutex) */ - object->dentry = NULL; +out_dput: + dput(path.dentry); +out: + cachefiles_end_secure(cache, saved_cred); + return file; +} - ret = cachefiles_bury_object(cache, object, dir, next, - true, - FSCACHE_OBJECT_IS_STALE); - dput(next); - next = NULL; +/* + * Create a new file. + */ +static bool cachefiles_create_file(struct cachefiles_object *object) +{ + struct file *file; + int ret; - if (ret < 0) - goto delete_error; + ret = cachefiles_has_space(object->volume->cache, 1, 0, + cachefiles_has_space_for_create); + if (ret < 0) + return false; - _debug("redo lookup"); - fscache_object_retrying_stale(&object->fscache); - goto lookup_again; - } - } + file = cachefiles_create_tmpfile(object); + if (IS_ERR(file)) + return false; - /* note that we're now using this object */ - ret = cachefiles_mark_object_active(cache, object); + 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; +} - inode_unlock(d_inode(dir)); - dput(dir); - dir = NULL; +/* + * 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; - if (ret == -ETIMEDOUT) - goto mark_active_timed_out; + _enter("%pd", dentry); - _debug("=== OBTAINED_OBJECT ==="); + if (!cachefiles_mark_inode_in_use(object, dentry)) + return false; - if (object->new) { - /* attach data to a newly constructed terminal object */ - ret = cachefiles_set_object_xattr(object, auxdata); - if (ret < 0) - goto check_error; - } else { - /* 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) */ - path.dentry = next; - touch_atime(&path); - } - - /* open a file interface onto a data file */ - if (object->type != FSCACHE_COOKIE_TYPE_INDEX) { - if (d_is_reg(object->dentry)) { - const struct address_space_operations *aops; - - ret = -EPERM; - aops = d_backing_inode(object->dentry)->i_mapping->a_ops; - if (!aops->bmap) - goto check_error; - if (object->dentry->d_sb->s_blocksize > PAGE_SIZE) - goto check_error; - - object->backer = object->dentry; - } else { - BUG(); // TODO: open file in data-class subdir - } + /* 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 = open_with_fake_path(&path, O_RDWR | O_LARGEFILE | O_DIRECT, + d_backing_inode(dentry), cache->cache_cred); + if (IS_ERR(file)) { + trace_cachefiles_vfs_error(object, d_backing_inode(dentry), + PTR_ERR(file), + cachefiles_trace_open_error); + goto error; } - object->new = 0; - fscache_obtained_object(&object->fscache); - - _leave(" = 0 [%lu]", d_backing_inode(object->dentry)->i_ino); - return 0; - -no_space_error: - fscache_object_mark_killed(&object->fscache, FSCACHE_OBJECT_NO_SPACE); -create_error: - _debug("create error %d", ret); - if (ret == -EIO) - cachefiles_io_error(cache, "Create/mkdir failed"); - 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); -mark_active_timed_out: - _debug("mark active timed out"); - goto release_dentry; + ret = cachefiles_check_auxdata(object, file); + if (ret < 0) + goto check_failed; -check_error: - _debug("check error %d", ret); - cachefiles_mark_object_inactive( - cache, object, d_backing_inode(object->dentry)->i_blocks); -release_dentry: - dput(object->dentry); - object->dentry = NULL; - goto error_out; - -delete_error: - _debug("delete error %d", ret); - goto error_out2; + object->file = file; -lookup_error: - _debug("lookup error %ld", PTR_ERR(next)); - ret = PTR_ERR(next); - if (ret == -EIO) - cachefiles_io_error(cache, "Lookup failed"); - next = NULL; + /* 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); + if (ret == -ESTALE) { + fput(file); + dput(dentry); + return cachefiles_create_file(object); + } +error_fput: + fput(file); error: - inode_unlock(d_inode(dir)); - dput(next); -error_out2: - dput(dir); -error_out: - _leave(" = error %d", -ret); - return ret; + dput(dentry); + return false; } /* - * get a subdirectory + * walk from the parent object to the child object through the backing + * filesystem, creating directories as we go */ -struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, - struct dentry *dir, - const char *dirname) +bool cachefiles_look_up_object(struct cachefiles_object *object) { - struct dentry *subdir; - struct path path; + struct cachefiles_volume *volume = object->volume; + struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash]; int ret; - _enter(",,%s", dirname); - - /* search the current directory for the element name */ - inode_lock(d_inode(dir)); - -retry: - subdir = lookup_one_len(dirname, dir, strlen(dirname)); - if (IS_ERR(subdir)) { - if (PTR_ERR(subdir) == -ENOMEM) - goto nomem_d_alloc; - goto lookup_error; + _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, dentry); + 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; } - _debug("subdir -> %pd %s", - subdir, d_backing_inode(subdir) ? "positive" : "negative"); + if (!cachefiles_open_file(object, dentry)) + return false; - /* we need to create the subdir if it doesn't exist yet */ - if (d_is_negative(subdir)) { - ret = cachefiles_has_space(cache, 1, 0); - if (ret < 0) - goto mkdir_error; + _leave(" = t [%lu]", file_inode(object->file)->i_ino); + return true; - _debug("attempt mkdir"); +new_file: + fscache_cookie_lookup_negative(object->cookie); + return cachefiles_create_file(object); +} - path.mnt = cache->mnt; - path.dentry = dir; - ret = security_path_mkdir(&path, subdir, 0700); - if (ret < 0) - goto mkdir_error; - ret = vfs_mkdir(&init_user_ns, d_inode(dir), subdir, 0700); - if (ret < 0) - goto mkdir_error; +/* + * 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; - if (unlikely(d_unhashed(subdir))) { - dput(subdir); - goto retry; + _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; } - ASSERT(d_backing_inode(subdir)); - _debug("mkdir -> %pd{ino=%lu}", - subdir, d_backing_inode(subdir)->i_ino); - } - - inode_unlock(d_inode(dir)); - - /* we need to make sure the subdir is a directory */ - ASSERT(d_backing_inode(subdir)); + ret = cachefiles_unlink(volume->cache, object, fan, dentry, + FSCACHE_OBJECT_IS_STALE); + if (ret < 0) + goto out_dput; - if (!d_can_lookup(subdir)) { - pr_err("%s is not a directory\n", dirname); - ret = -EIO; - goto check_error; + 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 = -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->create || - !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: - dput(subdir); - _leave(" = %d [check]", ret); - return ERR_PTR(ret); - -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); + ret = cachefiles_inject_read_error(); + if (ret == 0) + ret = vfs_link(object->file->f_path.dentry, &init_user_ns, + 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; } /* - * find out if an object is in use or not - * - if finds object and it's not in use: - * - returns a pointer to the object and a reference on it - * - returns with the directory locked + * Look up an inode to be checked or culled. Return -EBUSY if the inode is + * marked in use. */ -static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache, - struct dentry *dir, - char *filename) +static struct dentry *cachefiles_lookup_for_cull(struct cachefiles_cache *cache, + struct dentry *dir, + char *filename) { - struct cachefiles_object *object; - struct rb_node *_n; struct dentry *victim; - int ret; - - //_enter(",%pd/,%s", - // dir, filename); + int ret = -ENOENT; - /* look up the victim */ inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); victim = lookup_one_len(filename, dir, strlen(filename)); if (IS_ERR(victim)) goto lookup_error; - - //_debug("victim -> %pd %s", - // victim, d_backing_inode(victim) ? "positive" : "negative"); - - /* if the object is no longer there then we probably retired the object - * at the netfs's request whilst the cull was in progress - */ - if (d_is_negative(victim)) { - inode_unlock(d_inode(dir)); - dput(victim); - _leave(" = -ENOENT [absent]"); - return ERR_PTR(-ENOENT); - } - - /* check to see if we're using this object */ - read_lock(&cache->active_lock); - - _n = cache->active_nodes.rb_node; - - while (_n) { - object = rb_entry(_n, struct cachefiles_object, active_node); - - if (object->dentry > victim) - _n = _n->rb_left; - else if (object->dentry < victim) - _n = _n->rb_right; - else - goto object_in_use; - } - - read_unlock(&cache->active_lock); - - //_leave(" = %pd", victim); + if (d_is_negative(victim)) + goto lookup_put; + if (d_inode(victim)->i_flags & S_KERNEL_FILE) + goto lookup_busy; return victim; -object_in_use: - read_unlock(&cache->active_lock); +lookup_busy: + ret = -EBUSY; +lookup_put: inode_unlock(d_inode(dir)); dput(victim); - //_leave(" = -EBUSY [in use]"); - return ERR_PTR(-EBUSY); + return ERR_PTR(ret); lookup_error: inode_unlock(d_inode(dir)); ret = PTR_ERR(victim); - if (ret == -ENOENT) { - /* file or dir now absent - probably retired by netfs */ - _leave(" = -ESTALE [absent]"); - return ERR_PTR(-ESTALE); - } + if (ret == -ENOENT) + return ERR_PTR(-ESTALE); /* Probably got retired by the netfs */ if (ret == -EIO) { cachefiles_io_error(cache, "Lookup failed"); @@ -931,46 +766,46 @@ lookup_error: ret = -EIO; } - _leave(" = %d", ret); return ERR_PTR(ret); } /* - * cull an object if it's not in use + * 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_check_active(cache, dir, filename); + victim = cachefiles_lookup_for_cull(cache, dir, filename); if (IS_ERR(victim)) return PTR_ERR(victim); - _debug("victim -> %pd %s", - victim, d_backing_inode(victim) ? "positive" : "negative"); - - /* okay... the victim is not being used so we can cull it - * - start by marking it as stale - */ - _debug("victim is cullable"); - - ret = cachefiles_remove_object_xattr(cache, 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; - /* actually remove the victim (drops the dir mutex) */ - _debug("bury"); - - ret = cachefiles_bury_object(cache, NULL, dir, victim, false, + 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; @@ -979,11 +814,8 @@ error_unlock: inode_unlock(d_inode(dir)); error: dput(victim); - if (ret == -ENOENT) { - /* file or dir now absent - probably retired by netfs */ - _leave(" = -ESTALE [absent]"); - return -ESTALE; - } + if (ret == -ENOENT) + return -ESTALE; /* Probably got retired by the netfs */ if (ret != -ENOMEM) { pr_err("Internal error: %d\n", ret); @@ -995,7 +827,7 @@ error: } /* - * find out if an object is in use or not + * 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 */ @@ -1003,16 +835,13 @@ int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir, char *filename) { struct dentry *victim; + int ret = 0; - //_enter(",%pd/,%s", - // dir, filename); - - victim = cachefiles_check_active(cache, dir, filename); + victim = cachefiles_lookup_for_cull(cache, dir, filename); if (IS_ERR(victim)) return PTR_ERR(victim); inode_unlock(d_inode(dir)); dput(victim); - //_leave(" = 0"); - return 0; + return ret; } diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c deleted file mode 100644 index fcf4f3b72923..000000000000 --- a/fs/cachefiles/rdwr.c +++ /dev/null @@ -1,972 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Storage object read/write - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/mount.h> -#include <linux/slab.h> -#include <linux/file.h> -#include <linux/swap.h> -#include "internal.h" - -/* - * detect wake up events generated by the unlocking of pages in which we're - * interested - * - we use this to detect read completion of backing pages - * - the caller holds the waitqueue lock - */ -static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, - int sync, void *_key) -{ - struct cachefiles_one_read *monitor = - container_of(wait, struct cachefiles_one_read, monitor); - struct cachefiles_object *object; - struct fscache_retrieval *op = monitor->op; - struct wait_page_key *key = _key; - struct folio *folio = wait->private; - - ASSERT(key); - - _enter("{%lu},%u,%d,{%p,%u}", - monitor->netfs_page->index, mode, sync, - key->folio, key->bit_nr); - - if (key->folio != folio || key->bit_nr != PG_locked) - return 0; - - _debug("--- monitor %p %lx ---", folio, folio->flags); - - if (!folio_test_uptodate(folio) && !folio_test_error(folio)) { - /* unlocked, not uptodate and not erronous? */ - _debug("page probably truncated"); - } - - /* remove from the waitqueue */ - list_del(&wait->entry); - - /* move onto the action list and queue for FS-Cache thread pool */ - ASSERT(op); - - /* We need to temporarily bump the usage count as we don't own a ref - * here otherwise cachefiles_read_copier() may free the op between the - * monitor being enqueued on the op->to_do list and the op getting - * enqueued on the work queue. - */ - fscache_get_retrieval(op); - - object = container_of(op->op.object, struct cachefiles_object, fscache); - spin_lock(&object->work_lock); - list_add_tail(&monitor->op_link, &op->to_do); - fscache_enqueue_retrieval(op); - spin_unlock(&object->work_lock); - - fscache_put_retrieval(op); - return 0; -} - -/* - * handle a probably truncated page - * - check to see if the page is still relevant and reissue the read if - * possible - * - return -EIO on error, -ENODATA if the page is gone, -EINPROGRESS if we - * must wait again and 0 if successful - */ -static int cachefiles_read_reissue(struct cachefiles_object *object, - struct cachefiles_one_read *monitor) -{ - struct address_space *bmapping = d_backing_inode(object->backer)->i_mapping; - struct page *backpage = monitor->back_page, *backpage2; - int ret; - - _enter("{ino=%lx},{%lx,%lx}", - d_backing_inode(object->backer)->i_ino, - backpage->index, backpage->flags); - - /* skip if the page was truncated away completely */ - if (backpage->mapping != bmapping) { - _leave(" = -ENODATA [mapping]"); - return -ENODATA; - } - - backpage2 = find_get_page(bmapping, backpage->index); - if (!backpage2) { - _leave(" = -ENODATA [gone]"); - return -ENODATA; - } - - if (backpage != backpage2) { - put_page(backpage2); - _leave(" = -ENODATA [different]"); - return -ENODATA; - } - - /* the page is still there and we already have a ref on it, so we don't - * need a second */ - put_page(backpage2); - - INIT_LIST_HEAD(&monitor->op_link); - folio_add_wait_queue(page_folio(backpage), &monitor->monitor); - - if (trylock_page(backpage)) { - ret = -EIO; - if (PageError(backpage)) - goto unlock_discard; - ret = 0; - if (PageUptodate(backpage)) - goto unlock_discard; - - _debug("reissue read"); - ret = bmapping->a_ops->readpage(NULL, backpage); - if (ret < 0) - goto discard; - } - - /* but the page may have been read before the monitor was installed, so - * the monitor may miss the event - so we have to ensure that we do get - * one in such a case */ - if (trylock_page(backpage)) { - _debug("jumpstart %p {%lx}", backpage, backpage->flags); - unlock_page(backpage); - } - - /* it'll reappear on the todo list */ - _leave(" = -EINPROGRESS"); - return -EINPROGRESS; - -unlock_discard: - unlock_page(backpage); -discard: - spin_lock_irq(&object->work_lock); - list_del(&monitor->op_link); - spin_unlock_irq(&object->work_lock); - _leave(" = %d", ret); - return ret; -} - -/* - * copy data from backing pages to netfs pages to complete a read operation - * - driven by FS-Cache's thread pool - */ -static void cachefiles_read_copier(struct fscache_operation *_op) -{ - struct cachefiles_one_read *monitor; - struct cachefiles_object *object; - struct fscache_retrieval *op; - int error, max; - - op = container_of(_op, struct fscache_retrieval, op); - object = container_of(op->op.object, - struct cachefiles_object, fscache); - - _enter("{ino=%lu}", d_backing_inode(object->backer)->i_ino); - - max = 8; - spin_lock_irq(&object->work_lock); - - while (!list_empty(&op->to_do)) { - monitor = list_entry(op->to_do.next, - struct cachefiles_one_read, op_link); - list_del(&monitor->op_link); - - spin_unlock_irq(&object->work_lock); - - _debug("- copy {%lu}", monitor->back_page->index); - - recheck: - if (test_bit(FSCACHE_COOKIE_INVALIDATING, - &object->fscache.cookie->flags)) { - error = -ESTALE; - } else if (PageUptodate(monitor->back_page)) { - copy_highpage(monitor->netfs_page, monitor->back_page); - fscache_mark_page_cached(monitor->op, - monitor->netfs_page); - error = 0; - } else if (!PageError(monitor->back_page)) { - /* the page has probably been truncated */ - error = cachefiles_read_reissue(object, monitor); - if (error == -EINPROGRESS) - goto next; - goto recheck; - } else { - cachefiles_io_error_obj( - object, - "Readpage failed on backing file %lx", - (unsigned long) monitor->back_page->flags); - error = -EIO; - } - - put_page(monitor->back_page); - - fscache_end_io(op, monitor->netfs_page, error); - put_page(monitor->netfs_page); - fscache_retrieval_complete(op, 1); - fscache_put_retrieval(op); - kfree(monitor); - - next: - /* let the thread pool have some air occasionally */ - max--; - if (max < 0 || need_resched()) { - if (!list_empty(&op->to_do)) - fscache_enqueue_retrieval(op); - _leave(" [maxed out]"); - return; - } - - spin_lock_irq(&object->work_lock); - } - - spin_unlock_irq(&object->work_lock); - _leave(""); -} - -/* - * read the corresponding page to the given set from the backing file - * - an uncertain page is simply discarded, to be tried again another time - */ -static int cachefiles_read_backing_file_one(struct cachefiles_object *object, - struct fscache_retrieval *op, - struct page *netpage) -{ - struct cachefiles_one_read *monitor; - struct address_space *bmapping; - struct page *newpage, *backpage; - int ret; - - _enter(""); - - _debug("read back %p{%lu,%d}", - netpage, netpage->index, page_count(netpage)); - - monitor = kzalloc(sizeof(*monitor), cachefiles_gfp); - if (!monitor) - goto nomem; - - monitor->netfs_page = netpage; - monitor->op = fscache_get_retrieval(op); - - init_waitqueue_func_entry(&monitor->monitor, cachefiles_read_waiter); - - /* attempt to get hold of the backing page */ - bmapping = d_backing_inode(object->backer)->i_mapping; - newpage = NULL; - - for (;;) { - backpage = find_get_page(bmapping, netpage->index); - if (backpage) - goto backing_page_already_present; - - if (!newpage) { - newpage = __page_cache_alloc(cachefiles_gfp); - if (!newpage) - goto nomem_monitor; - } - - ret = add_to_page_cache_lru(newpage, bmapping, - netpage->index, cachefiles_gfp); - if (ret == 0) - goto installed_new_backing_page; - if (ret != -EEXIST) - goto nomem_page; - } - - /* we've installed a new backing page, so now we need to start - * it reading */ -installed_new_backing_page: - _debug("- new %p", newpage); - - backpage = newpage; - newpage = NULL; - -read_backing_page: - ret = bmapping->a_ops->readpage(NULL, backpage); - if (ret < 0) - goto read_error; - - /* set the monitor to transfer the data across */ -monitor_backing_page: - _debug("- monitor add"); - - /* install the monitor */ - get_page(monitor->netfs_page); - get_page(backpage); - monitor->back_page = backpage; - monitor->monitor.private = backpage; - folio_add_wait_queue(page_folio(backpage), &monitor->monitor); - monitor = NULL; - - /* but the page may have been read before the monitor was installed, so - * the monitor may miss the event - so we have to ensure that we do get - * one in such a case */ - if (trylock_page(backpage)) { - _debug("jumpstart %p {%lx}", backpage, backpage->flags); - unlock_page(backpage); - } - goto success; - - /* if the backing page is already present, it can be in one of - * three states: read in progress, read failed or read okay */ -backing_page_already_present: - _debug("- present"); - - if (newpage) { - put_page(newpage); - newpage = NULL; - } - - if (PageError(backpage)) - goto io_error; - - if (PageUptodate(backpage)) - goto backing_page_already_uptodate; - - if (!trylock_page(backpage)) - goto monitor_backing_page; - _debug("read %p {%lx}", backpage, backpage->flags); - goto read_backing_page; - - /* the backing page is already up to date, attach the netfs - * page to the pagecache and LRU and copy the data across */ -backing_page_already_uptodate: - _debug("- uptodate"); - - fscache_mark_page_cached(op, netpage); - - copy_highpage(netpage, backpage); - fscache_end_io(op, netpage, 0); - fscache_retrieval_complete(op, 1); - -success: - _debug("success"); - ret = 0; - -out: - if (backpage) - put_page(backpage); - if (monitor) { - fscache_put_retrieval(monitor->op); - kfree(monitor); - } - _leave(" = %d", ret); - return ret; - -read_error: - _debug("read error %d", ret); - if (ret == -ENOMEM) { - fscache_retrieval_complete(op, 1); - goto out; - } -io_error: - cachefiles_io_error_obj(object, "Page read error on backing file"); - fscache_retrieval_complete(op, 1); - ret = -ENOBUFS; - goto out; - -nomem_page: - put_page(newpage); -nomem_monitor: - fscache_put_retrieval(monitor->op); - kfree(monitor); -nomem: - fscache_retrieval_complete(op, 1); - _leave(" = -ENOMEM"); - return -ENOMEM; -} - -/* - * read a page from the cache or allocate a block in which to store it - * - cache withdrawal is prevented by the caller - * - returns -EINTR if interrupted - * - returns -ENOMEM if ran out of memory - * - returns -ENOBUFS if no buffers can be made available - * - returns -ENOBUFS if page is beyond EOF - * - if the page is backed by a block in the cache: - * - a read will be started which will call the callback on completion - * - 0 will be returned - * - else if the page is unbacked: - * - the metadata will be retained - * - -ENODATA will be returned - */ -int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, - struct page *page, - gfp_t gfp) -{ - struct cachefiles_object *object; - struct cachefiles_cache *cache; - struct inode *inode; - sector_t block; - unsigned shift; - int ret, ret2; - - object = container_of(op->op.object, - struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - _enter("{%p},{%lx},,,", object, page->index); - - if (!object->backer) - goto enobufs; - - inode = d_backing_inode(object->backer); - ASSERT(S_ISREG(inode->i_mode)); - - /* calculate the shift required to use bmap */ - shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; - - op->op.flags &= FSCACHE_OP_KEEP_FLAGS; - op->op.flags |= FSCACHE_OP_ASYNC; - op->op.processor = cachefiles_read_copier; - - /* we assume the absence or presence of the first block is a good - * enough indication for the page as a whole - * - TODO: don't use bmap() for this as it is _not_ actually good - * enough for this as it doesn't indicate errors, but it's all we've - * got for the moment - */ - block = page->index; - block <<= shift; - - ret2 = bmap(inode, &block); - ASSERT(ret2 == 0); - - _debug("%llx -> %llx", - (unsigned long long) (page->index << shift), - (unsigned long long) block); - - if (block) { - /* submit the apparently valid page to the backing fs to be - * read from disk */ - ret = cachefiles_read_backing_file_one(object, op, page); - } else if (cachefiles_has_space(cache, 0, 1) == 0) { - /* there's space in the cache we can use */ - fscache_mark_page_cached(op, page); - fscache_retrieval_complete(op, 1); - ret = -ENODATA; - } else { - goto enobufs; - } - - _leave(" = %d", ret); - return ret; - -enobufs: - fscache_retrieval_complete(op, 1); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} - -/* - * read the corresponding pages to the given set from the backing file - * - any uncertain pages are simply discarded, to be tried again another time - */ -static int cachefiles_read_backing_file(struct cachefiles_object *object, - struct fscache_retrieval *op, - struct list_head *list) -{ - struct cachefiles_one_read *monitor = NULL; - struct address_space *bmapping = d_backing_inode(object->backer)->i_mapping; - struct page *newpage = NULL, *netpage, *_n, *backpage = NULL; - int ret = 0; - - _enter(""); - - list_for_each_entry_safe(netpage, _n, list, lru) { - list_del(&netpage->lru); - - _debug("read back %p{%lu,%d}", - netpage, netpage->index, page_count(netpage)); - - if (!monitor) { - monitor = kzalloc(sizeof(*monitor), cachefiles_gfp); - if (!monitor) - goto nomem; - - monitor->op = fscache_get_retrieval(op); - init_waitqueue_func_entry(&monitor->monitor, - cachefiles_read_waiter); - } - - for (;;) { - backpage = find_get_page(bmapping, netpage->index); - if (backpage) - goto backing_page_already_present; - - if (!newpage) { - newpage = __page_cache_alloc(cachefiles_gfp); - if (!newpage) - goto nomem; - } - - ret = add_to_page_cache_lru(newpage, bmapping, - netpage->index, - cachefiles_gfp); - if (ret == 0) - goto installed_new_backing_page; - if (ret != -EEXIST) - goto nomem; - } - - /* we've installed a new backing page, so now we need - * to start it reading */ - installed_new_backing_page: - _debug("- new %p", newpage); - - backpage = newpage; - newpage = NULL; - - reread_backing_page: - ret = bmapping->a_ops->readpage(NULL, backpage); - if (ret < 0) - goto read_error; - - /* add the netfs page to the pagecache and LRU, and set the - * monitor to transfer the data across */ - monitor_backing_page: - _debug("- monitor add"); - - ret = add_to_page_cache_lru(netpage, op->mapping, - netpage->index, cachefiles_gfp); - if (ret < 0) { - if (ret == -EEXIST) { - put_page(backpage); - backpage = NULL; - put_page(netpage); - netpage = NULL; - fscache_retrieval_complete(op, 1); - continue; - } - goto nomem; - } - - /* install a monitor */ - get_page(netpage); - monitor->netfs_page = netpage; - - get_page(backpage); - monitor->back_page = backpage; - monitor->monitor.private = backpage; - folio_add_wait_queue(page_folio(backpage), &monitor->monitor); - monitor = NULL; - - /* but the page may have been read before the monitor was - * installed, so the monitor may miss the event - so we have to - * ensure that we do get one in such a case */ - if (trylock_page(backpage)) { - _debug("2unlock %p {%lx}", backpage, backpage->flags); - unlock_page(backpage); - } - - put_page(backpage); - backpage = NULL; - - put_page(netpage); - netpage = NULL; - continue; - - /* if the backing page is already present, it can be in one of - * three states: read in progress, read failed or read okay */ - backing_page_already_present: - _debug("- present %p", backpage); - - if (PageError(backpage)) - goto io_error; - - if (PageUptodate(backpage)) - goto backing_page_already_uptodate; - - _debug("- not ready %p{%lx}", backpage, backpage->flags); - - if (!trylock_page(backpage)) - goto monitor_backing_page; - - if (PageError(backpage)) { - _debug("error %lx", backpage->flags); - unlock_page(backpage); - goto io_error; - } - - if (PageUptodate(backpage)) - goto backing_page_already_uptodate_unlock; - - /* we've locked a page that's neither up to date nor erroneous, - * so we need to attempt to read it again */ - goto reread_backing_page; - - /* the backing page is already up to date, attach the netfs - * page to the pagecache and LRU and copy the data across */ - backing_page_already_uptodate_unlock: - _debug("uptodate %lx", backpage->flags); - unlock_page(backpage); - backing_page_already_uptodate: - _debug("- uptodate"); - - ret = add_to_page_cache_lru(netpage, op->mapping, - netpage->index, cachefiles_gfp); - if (ret < 0) { - if (ret == -EEXIST) { - put_page(backpage); - backpage = NULL; - put_page(netpage); - netpage = NULL; - fscache_retrieval_complete(op, 1); - continue; - } - goto nomem; - } - - copy_highpage(netpage, backpage); - - put_page(backpage); - backpage = NULL; - - fscache_mark_page_cached(op, netpage); - - /* the netpage is unlocked and marked up to date here */ - fscache_end_io(op, netpage, 0); - put_page(netpage); - netpage = NULL; - fscache_retrieval_complete(op, 1); - continue; - } - - netpage = NULL; - - _debug("out"); - -out: - /* tidy up */ - if (newpage) - put_page(newpage); - if (netpage) - put_page(netpage); - if (backpage) - put_page(backpage); - if (monitor) { - fscache_put_retrieval(op); - kfree(monitor); - } - - list_for_each_entry_safe(netpage, _n, list, lru) { - list_del(&netpage->lru); - put_page(netpage); - fscache_retrieval_complete(op, 1); - } - - _leave(" = %d", ret); - return ret; - -nomem: - _debug("nomem"); - ret = -ENOMEM; - goto record_page_complete; - -read_error: - _debug("read error %d", ret); - if (ret == -ENOMEM) - goto record_page_complete; -io_error: - cachefiles_io_error_obj(object, "Page read error on backing file"); - ret = -ENOBUFS; -record_page_complete: - fscache_retrieval_complete(op, 1); - goto out; -} - -/* - * read a list of pages from the cache or allocate blocks in which to store - * them - */ -int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, - struct list_head *pages, - unsigned *nr_pages, - gfp_t gfp) -{ - struct cachefiles_object *object; - struct cachefiles_cache *cache; - struct list_head backpages; - struct pagevec pagevec; - struct inode *inode; - struct page *page, *_n; - unsigned shift, nrbackpages; - int ret, ret2, space; - - object = container_of(op->op.object, - struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - _enter("{OBJ%x,%d},,%d,,", - object->fscache.debug_id, atomic_read(&op->op.usage), - *nr_pages); - - if (!object->backer) - goto all_enobufs; - - space = 1; - if (cachefiles_has_space(cache, 0, *nr_pages) < 0) - space = 0; - - inode = d_backing_inode(object->backer); - ASSERT(S_ISREG(inode->i_mode)); - - /* calculate the shift required to use bmap */ - shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; - - pagevec_init(&pagevec); - - op->op.flags &= FSCACHE_OP_KEEP_FLAGS; - op->op.flags |= FSCACHE_OP_ASYNC; - op->op.processor = cachefiles_read_copier; - - INIT_LIST_HEAD(&backpages); - nrbackpages = 0; - - ret = space ? -ENODATA : -ENOBUFS; - list_for_each_entry_safe(page, _n, pages, lru) { - sector_t block; - - /* we assume the absence or presence of the first block is a - * good enough indication for the page as a whole - * - TODO: don't use bmap() for this as it is _not_ actually - * good enough for this as it doesn't indicate errors, but - * it's all we've got for the moment - */ - block = page->index; - block <<= shift; - - ret2 = bmap(inode, &block); - ASSERT(ret2 == 0); - - _debug("%llx -> %llx", - (unsigned long long) (page->index << shift), - (unsigned long long) block); - - if (block) { - /* we have data - add it to the list to give to the - * backing fs */ - list_move(&page->lru, &backpages); - (*nr_pages)--; - nrbackpages++; - } else if (space && pagevec_add(&pagevec, page) == 0) { - fscache_mark_pages_cached(op, &pagevec); - fscache_retrieval_complete(op, 1); - ret = -ENODATA; - } else { - fscache_retrieval_complete(op, 1); - } - } - - if (pagevec_count(&pagevec) > 0) - fscache_mark_pages_cached(op, &pagevec); - - if (list_empty(pages)) - ret = 0; - - /* submit the apparently valid pages to the backing fs to be read from - * disk */ - if (nrbackpages > 0) { - ret2 = cachefiles_read_backing_file(object, op, &backpages); - if (ret2 == -ENOMEM || ret2 == -EINTR) - ret = ret2; - } - - _leave(" = %d [nr=%u%s]", - ret, *nr_pages, list_empty(pages) ? " empty" : ""); - return ret; - -all_enobufs: - fscache_retrieval_complete(op, *nr_pages); - return -ENOBUFS; -} - -/* - * allocate a block in the cache in which to store a page - * - cache withdrawal is prevented by the caller - * - returns -EINTR if interrupted - * - returns -ENOMEM if ran out of memory - * - returns -ENOBUFS if no buffers can be made available - * - returns -ENOBUFS if page is beyond EOF - * - otherwise: - * - the metadata will be retained - * - 0 will be returned - */ -int cachefiles_allocate_page(struct fscache_retrieval *op, - struct page *page, - gfp_t gfp) -{ - struct cachefiles_object *object; - struct cachefiles_cache *cache; - int ret; - - object = container_of(op->op.object, - struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - _enter("%p,{%lx},", object, page->index); - - ret = cachefiles_has_space(cache, 0, 1); - if (ret == 0) - fscache_mark_page_cached(op, page); - else - ret = -ENOBUFS; - - fscache_retrieval_complete(op, 1); - _leave(" = %d", ret); - return ret; -} - -/* - * allocate blocks in the cache in which to store a set of pages - * - cache withdrawal is prevented by the caller - * - returns -EINTR if interrupted - * - returns -ENOMEM if ran out of memory - * - returns -ENOBUFS if some buffers couldn't be made available - * - returns -ENOBUFS if some pages are beyond EOF - * - otherwise: - * - -ENODATA will be returned - * - metadata will be retained for any page marked - */ -int cachefiles_allocate_pages(struct fscache_retrieval *op, - struct list_head *pages, - unsigned *nr_pages, - gfp_t gfp) -{ - struct cachefiles_object *object; - struct cachefiles_cache *cache; - struct pagevec pagevec; - struct page *page; - int ret; - - object = container_of(op->op.object, - struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - _enter("%p,,,%d,", object, *nr_pages); - - ret = cachefiles_has_space(cache, 0, *nr_pages); - if (ret == 0) { - pagevec_init(&pagevec); - - list_for_each_entry(page, pages, lru) { - if (pagevec_add(&pagevec, page) == 0) - fscache_mark_pages_cached(op, &pagevec); - } - - if (pagevec_count(&pagevec) > 0) - fscache_mark_pages_cached(op, &pagevec); - ret = -ENODATA; - } else { - ret = -ENOBUFS; - } - - fscache_retrieval_complete(op, *nr_pages); - _leave(" = %d", ret); - return ret; -} - -/* - * request a page be stored in the cache - * - cache withdrawal is prevented by the caller - * - this request may be ignored if there's no cache block available, in which - * case -ENOBUFS will be returned - * - if the op is in progress, 0 will be returned - */ -int cachefiles_write_page(struct fscache_storage *op, struct page *page) -{ - struct cachefiles_object *object; - struct cachefiles_cache *cache; - struct file *file; - struct path path; - loff_t pos, eof; - size_t len; - void *data; - int ret = -ENOBUFS; - - ASSERT(op != NULL); - ASSERT(page != NULL); - - object = container_of(op->op.object, - struct cachefiles_object, fscache); - - _enter("%p,%p{%lx},,,", object, page, page->index); - - if (!object->backer) { - _leave(" = -ENOBUFS"); - return -ENOBUFS; - } - - ASSERT(d_is_reg(object->backer)); - - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); - - pos = (loff_t)page->index << PAGE_SHIFT; - - /* We mustn't write more data than we have, so we have to beware of a - * partial page at EOF. - */ - eof = object->fscache.store_limit_l; - if (pos >= eof) - goto error; - - /* write the page to the backing filesystem and let it store it in its - * own time */ - path.mnt = cache->mnt; - path.dentry = object->backer; - file = dentry_open(&path, O_RDWR | O_LARGEFILE, cache->cache_cred); - if (IS_ERR(file)) { - ret = PTR_ERR(file); - goto error_2; - } - - len = PAGE_SIZE; - if (eof & ~PAGE_MASK) { - if (eof - pos < PAGE_SIZE) { - _debug("cut short %llx to %llx", - pos, eof); - len = eof - pos; - ASSERTCMP(pos + len, ==, eof); - } - } - - data = kmap(page); - ret = kernel_write(file, data, len, &pos); - kunmap(page); - fput(file); - if (ret != len) - goto error_eio; - - _leave(" = 0"); - return 0; - -error_eio: - ret = -EIO; -error_2: - if (ret == -EIO) - cachefiles_io_error_obj(object, - "Write page to backing file failed"); -error: - _leave(" = -ENOBUFS [%d]", ret); - return -ENOBUFS; -} - -/* - * detach a backing block from a page - * - cache withdrawal is prevented by the caller - */ -void cachefiles_uncache_page(struct fscache_object *_object, struct page *page) - __releases(&object->fscache.cookie->lock) -{ - struct cachefiles_object *object; - - object = container_of(_object, struct cachefiles_object, fscache); - - _enter("%p,{%lu}", object, page->index); - - spin_unlock(&object->fscache.cookie->lock); -} diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index aec13fd94692..fe777164f1d8 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles security management * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2007, 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ diff --git a/fs/cachefiles/volume.c b/fs/cachefiles/volume.c new file mode 100644 index 000000000000..89df0ba8ba5e --- /dev/null +++ b/fs/cachefiles/volume.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Volume handling. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include "internal.h" +#include <trace/events/fscache.h> + +/* + * Allocate and set up a volume representation. We make sure all the fanout + * directories are created and pinned. + */ +void cachefiles_acquire_volume(struct fscache_volume *vcookie) +{ + struct cachefiles_volume *volume; + struct cachefiles_cache *cache = vcookie->cache->cache_priv; + const struct cred *saved_cred; + struct dentry *vdentry, *fan; + size_t len; + char *name; + bool is_new = false; + int ret, n_accesses, i; + + _enter(""); + + volume = kzalloc(sizeof(struct cachefiles_volume), GFP_KERNEL); + if (!volume) + return; + volume->vcookie = vcookie; + volume->cache = cache; + INIT_LIST_HEAD(&volume->cache_link); + + cachefiles_begin_secure(cache, &saved_cred); + + len = vcookie->key[0]; + name = kmalloc(len + 3, GFP_NOFS); + if (!name) + goto error_vol; + name[0] = 'I'; + memcpy(name + 1, vcookie->key + 1, len); + name[len + 1] = 0; + +retry: + vdentry = cachefiles_get_directory(cache, cache->store, name, &is_new); + if (IS_ERR(vdentry)) + goto error_name; + volume->dentry = vdentry; + + if (is_new) { + if (!cachefiles_set_volume_xattr(volume)) + goto error_dir; + } else { + ret = cachefiles_check_volume_xattr(volume); + if (ret < 0) { + if (ret != -ESTALE) + goto error_dir; + inode_lock_nested(d_inode(cache->store), I_MUTEX_PARENT); + cachefiles_bury_object(cache, NULL, cache->store, vdentry, + FSCACHE_VOLUME_IS_WEIRD); + cachefiles_put_directory(volume->dentry); + cond_resched(); + goto retry; + } + } + + for (i = 0; i < 256; i++) { + sprintf(name, "@%02x", i); + fan = cachefiles_get_directory(cache, vdentry, name, NULL); + if (IS_ERR(fan)) + goto error_fan; + volume->fanout[i] = fan; + } + + cachefiles_end_secure(cache, saved_cred); + + vcookie->cache_priv = volume; + n_accesses = atomic_inc_return(&vcookie->n_accesses); /* Stop wakeups on dec-to-0 */ + trace_fscache_access_volume(vcookie->debug_id, 0, + refcount_read(&vcookie->ref), + n_accesses, fscache_access_cache_pin); + + spin_lock(&cache->object_list_lock); + list_add(&volume->cache_link, &volume->cache->volumes); + spin_unlock(&cache->object_list_lock); + + kfree(name); + return; + +error_fan: + for (i = 0; i < 256; i++) + cachefiles_put_directory(volume->fanout[i]); +error_dir: + cachefiles_put_directory(volume->dentry); +error_name: + kfree(name); +error_vol: + kfree(volume); + cachefiles_end_secure(cache, saved_cred); +} + +/* + * Release a volume representation. + */ +static void __cachefiles_free_volume(struct cachefiles_volume *volume) +{ + int i; + + _enter(""); + + volume->vcookie->cache_priv = NULL; + + for (i = 0; i < 256; i++) + cachefiles_put_directory(volume->fanout[i]); + cachefiles_put_directory(volume->dentry); + kfree(volume); +} + +void cachefiles_free_volume(struct fscache_volume *vcookie) +{ + struct cachefiles_volume *volume = vcookie->cache_priv; + + if (volume) { + spin_lock(&volume->cache->object_list_lock); + list_del_init(&volume->cache_link); + spin_unlock(&volume->cache->object_list_lock); + __cachefiles_free_volume(volume); + } +} + +void cachefiles_withdraw_volume(struct cachefiles_volume *volume) +{ + fscache_withdraw_volume(volume->vcookie); + cachefiles_set_volume_xattr(volume); + __cachefiles_free_volume(volume); +} diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 9e82de668595..83f41bd0c3a9 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles extended attribute management * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ @@ -15,310 +15,245 @@ #include <linux/slab.h> #include "internal.h" +#define CACHEFILES_COOKIE_TYPE_DATA 1 + +struct cachefiles_xattr { + __be64 object_size; /* Actual size of the object */ + __be64 zero_point; /* Size after which server has no data not written by us */ + __u8 type; /* Type of object */ + __u8 content; /* Content presence (enum cachefiles_content) */ + __u8 data[]; /* netfs coherency data */ +} __packed; + static const char cachefiles_xattr_cache[] = XATTR_USER_PREFIX "CacheFiles.cache"; /* - * check the type label on an object - * - done using xattrs + * set the state xattr on a cache file */ -int cachefiles_check_object_type(struct cachefiles_object *object) +int cachefiles_set_object_xattr(struct cachefiles_object *object) { - struct dentry *dentry = object->dentry; - char type[3], xtype[3]; + struct cachefiles_xattr *buf; + struct dentry *dentry; + struct file *file = object->file; + unsigned int len = object->cookie->aux_len; int ret; - ASSERT(dentry); - ASSERT(d_backing_inode(dentry)); - - if (!object->fscache.cookie) - strcpy(type, "C3"); - else - snprintf(type, 3, "%02x", object->fscache.cookie->def->type); - - _enter("%x{%s}", object->fscache.debug_id, type); + if (!file) + return -ESTALE; + dentry = file->f_path.dentry; - /* attempt to install a type label directly */ - ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, type, - 2, XATTR_CREATE); - if (ret == 0) { - _debug("SET"); /* we succeeded */ - goto error; - } + _enter("%x,#%d", object->debug_id, len); - if (ret != -EEXIST) { - pr_err("Can't set xattr on %pd [%lu] (err %d)\n", - dentry, d_backing_inode(dentry)->i_ino, - -ret); - goto error; - } + buf = kmalloc(sizeof(struct cachefiles_xattr) + len, GFP_KERNEL); + if (!buf) + return -ENOMEM; - /* read the current type label */ - ret = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, xtype, - 3); + buf->object_size = cpu_to_be64(object->cookie->object_size); + buf->zero_point = 0; + buf->type = CACHEFILES_COOKIE_TYPE_DATA; + buf->content = object->content_info; + if (test_bit(FSCACHE_COOKIE_LOCAL_WRITE, &object->cookie->flags)) + buf->content = CACHEFILES_CONTENT_DIRTY; + if (len > 0) + memcpy(buf->data, fscache_get_aux(object->cookie), len); + + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + buf, sizeof(struct cachefiles_xattr) + len, 0); if (ret < 0) { - if (ret == -ERANGE) - goto bad_type_length; - - pr_err("Can't read xattr on %pd [%lu] (err %d)\n", - dentry, d_backing_inode(dentry)->i_ino, - -ret); - goto error; + trace_cachefiles_vfs_error(object, file_inode(file), ret, + cachefiles_trace_setxattr_error); + trace_cachefiles_coherency(object, file_inode(file)->i_ino, + buf->content, + cachefiles_coherency_set_fail); + if (ret != -ENOMEM) + cachefiles_io_error_obj( + object, + "Failed to set xattr with error %d", ret); + } else { + trace_cachefiles_coherency(object, file_inode(file)->i_ino, + buf->content, + cachefiles_coherency_set_ok); } - /* check the type is what we're expecting */ - if (ret != 2) - goto bad_type_length; - - if (xtype[0] != type[0] || xtype[1] != type[1]) - goto bad_type; - - ret = 0; - -error: + kfree(buf); _leave(" = %d", ret); return ret; - -bad_type_length: - pr_err("Cache object %lu type xattr length incorrect\n", - d_backing_inode(dentry)->i_ino); - ret = -EIO; - goto error; - -bad_type: - xtype[2] = 0; - pr_err("Cache object %pd [%lu] type %s not %s\n", - dentry, d_backing_inode(dentry)->i_ino, - xtype, type); - ret = -EIO; - goto error; } /* - * set the state xattr on a cache file + * check the consistency between the backing cache and the FS-Cache cookie */ -int cachefiles_set_object_xattr(struct cachefiles_object *object, - struct cachefiles_xattr *auxdata) +int cachefiles_check_auxdata(struct cachefiles_object *object, struct file *file) { - struct dentry *dentry = object->dentry; - int ret; - - ASSERT(dentry); - - _enter("%p,#%d", object, auxdata->len); + struct cachefiles_xattr *buf; + struct dentry *dentry = file->f_path.dentry; + unsigned int len = object->cookie->aux_len, tlen; + const void *p = fscache_get_aux(object->cookie); + enum cachefiles_coherency_trace why; + ssize_t xlen; + int ret = -ESTALE; - /* attempt to install the cache metadata directly */ - _debug("SET #%u", auxdata->len); + tlen = sizeof(struct cachefiles_xattr) + len; + buf = kmalloc(tlen, GFP_KERNEL); + if (!buf) + return -ENOMEM; - clear_bit(FSCACHE_COOKIE_AUX_UPDATED, &object->fscache.cookie->flags); - ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, - &auxdata->type, auxdata->len, XATTR_CREATE); - if (ret < 0 && ret != -ENOMEM) - cachefiles_io_error_obj( - object, - "Failed to set xattr with error %d", ret); + xlen = cachefiles_inject_read_error(); + if (xlen == 0) + xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, buf, tlen); + if (xlen != tlen) { + if (xlen < 0) + trace_cachefiles_vfs_error(object, file_inode(file), xlen, + cachefiles_trace_getxattr_error); + if (xlen == -EIO) + cachefiles_io_error_obj( + object, + "Failed to read aux with error %zd", xlen); + why = cachefiles_coherency_check_xattr; + } else if (buf->type != CACHEFILES_COOKIE_TYPE_DATA) { + why = cachefiles_coherency_check_type; + } else if (memcmp(buf->data, p, len) != 0) { + why = cachefiles_coherency_check_aux; + } else if (be64_to_cpu(buf->object_size) != object->cookie->object_size) { + why = cachefiles_coherency_check_objsize; + } else if (buf->content == CACHEFILES_CONTENT_DIRTY) { + // TODO: Begin conflict resolution + pr_warn("Dirty object in cache\n"); + why = cachefiles_coherency_check_dirty; + } else { + why = cachefiles_coherency_check_ok; + ret = 0; + } - _leave(" = %d", ret); + trace_cachefiles_coherency(object, file_inode(file)->i_ino, + buf->content, why); + kfree(buf); return ret; } /* - * update the state xattr on a cache file + * remove the object's xattr to mark it stale */ -int cachefiles_update_object_xattr(struct cachefiles_object *object, - struct cachefiles_xattr *auxdata) +int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, + struct cachefiles_object *object, + struct dentry *dentry) { - struct dentry *dentry = object->dentry; int ret; - if (!dentry) - return -ESTALE; - - _enter("%x,#%d", object->fscache.debug_id, auxdata->len); - - /* attempt to install the cache metadata directly */ - _debug("SET #%u", auxdata->len); - - clear_bit(FSCACHE_COOKIE_AUX_UPDATED, &object->fscache.cookie->flags); - ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, - &auxdata->type, auxdata->len, XATTR_REPLACE); - if (ret < 0 && ret != -ENOMEM) - cachefiles_io_error_obj( - object, - "Failed to update xattr with error %d", ret); + ret = cachefiles_inject_remove_error(); + if (ret == 0) + ret = vfs_removexattr(&init_user_ns, dentry, cachefiles_xattr_cache); + if (ret < 0) { + trace_cachefiles_vfs_error(object, d_inode(dentry), ret, + cachefiles_trace_remxattr_error); + if (ret == -ENOENT || ret == -ENODATA) + ret = 0; + else if (ret != -ENOMEM) + cachefiles_io_error(cache, + "Can't remove xattr from %lu" + " (error %d)", + d_backing_inode(dentry)->i_ino, -ret); + } _leave(" = %d", ret); return ret; } /* - * check the consistency between the backing cache and the FS-Cache cookie + * Stick a marker on the cache object to indicate that it's dirty. */ -int cachefiles_check_auxdata(struct cachefiles_object *object) +void cachefiles_prepare_to_write(struct fscache_cookie *cookie) { - struct cachefiles_xattr *auxbuf; - enum fscache_checkaux validity; - struct dentry *dentry = object->dentry; - ssize_t xlen; - int ret; - - ASSERT(dentry); - ASSERT(d_backing_inode(dentry)); - ASSERT(object->fscache.cookie->def->check_aux); - - auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL); - if (!auxbuf) - return -ENOMEM; + const struct cred *saved_cred; + struct cachefiles_object *object = cookie->cache_priv; + struct cachefiles_cache *cache = object->volume->cache; - xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, - &auxbuf->type, 512 + 1); - ret = -ESTALE; - if (xlen < 1 || - auxbuf->type != object->fscache.cookie->def->type) - goto error; + _enter("c=%08x", object->cookie->debug_id); - xlen--; - validity = fscache_check_aux(&object->fscache, &auxbuf->data, xlen, - i_size_read(d_backing_inode(dentry))); - if (validity != FSCACHE_CHECKAUX_OKAY) - goto error; - - ret = 0; -error: - kfree(auxbuf); - return ret; + if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { + cachefiles_begin_secure(cache, &saved_cred); + cachefiles_set_object_xattr(object); + cachefiles_end_secure(cache, saved_cred); + } } /* - * check the state xattr on a cache file - * - return -ESTALE if the object should be deleted + * Set the state xattr on a volume directory. */ -int cachefiles_check_object_xattr(struct cachefiles_object *object, - struct cachefiles_xattr *auxdata) +bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) { - struct cachefiles_xattr *auxbuf; - struct dentry *dentry = object->dentry; + unsigned int len = volume->vcookie->coherency_len; + const void *p = volume->vcookie->coherency; + struct dentry *dentry = volume->dentry; int ret; - _enter("%p,#%d", object, auxdata->len); - - ASSERT(dentry); - ASSERT(d_backing_inode(dentry)); - - auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, cachefiles_gfp); - if (!auxbuf) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } + _enter("%x,#%d", volume->vcookie->debug_id, len); - /* read the current type label */ - ret = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, - &auxbuf->type, 512 + 1); + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + p, len, 0); if (ret < 0) { - if (ret == -ENODATA) - goto stale; /* no attribute - power went off - * mid-cull? */ - - if (ret == -ERANGE) - goto bad_type_length; - - cachefiles_io_error_obj(object, - "Can't read xattr on %lu (err %d)", - d_backing_inode(dentry)->i_ino, -ret); - goto error; + trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, + cachefiles_trace_setxattr_error); + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, + cachefiles_coherency_vol_set_fail); + if (ret != -ENOMEM) + cachefiles_io_error( + volume->cache, "Failed to set xattr with error %d", ret); + } else { + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, + cachefiles_coherency_vol_set_ok); } - /* check the on-disk object */ - if (ret < 1) - goto bad_type_length; - - if (auxbuf->type != auxdata->type) - goto stale; - - auxbuf->len = ret; - - /* consult the netfs */ - if (object->fscache.cookie->def->check_aux) { - enum fscache_checkaux result; - unsigned int dlen; - - dlen = auxbuf->len - 1; - - _debug("checkaux %s #%u", - object->fscache.cookie->def->name, dlen); - - result = fscache_check_aux(&object->fscache, - &auxbuf->data, dlen, - i_size_read(d_backing_inode(dentry))); - - switch (result) { - /* entry okay as is */ - case FSCACHE_CHECKAUX_OKAY: - goto okay; - - /* entry requires update */ - case FSCACHE_CHECKAUX_NEEDS_UPDATE: - break; - - /* entry requires deletion */ - case FSCACHE_CHECKAUX_OBSOLETE: - goto stale; - - default: - BUG(); - } - - /* update the current label */ - ret = vfs_setxattr(&init_user_ns, dentry, - cachefiles_xattr_cache, &auxdata->type, - auxdata->len, XATTR_REPLACE); - if (ret < 0) { - cachefiles_io_error_obj(object, - "Can't update xattr on %lu" - " (error %d)", - d_backing_inode(dentry)->i_ino, -ret); - goto error; - } - } - -okay: - ret = 0; - -error: - kfree(auxbuf); _leave(" = %d", ret); - return ret; - -bad_type_length: - pr_err("Cache object %lu xattr length incorrect\n", - d_backing_inode(dentry)->i_ino); - ret = -EIO; - goto error; - -stale: - ret = -ESTALE; - goto error; + return ret == 0; } /* - * remove the object's xattr to mark it stale + * Check the consistency between the backing cache and the volume cookie. */ -int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, - struct dentry *dentry) +int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) { - int ret; + struct cachefiles_xattr *buf; + struct dentry *dentry = volume->dentry; + unsigned int len = volume->vcookie->coherency_len; + const void *p = volume->vcookie->coherency; + enum cachefiles_coherency_trace why; + ssize_t xlen; + int ret = -ESTALE; - ret = vfs_removexattr(&init_user_ns, dentry, cachefiles_xattr_cache); - if (ret < 0) { - if (ret == -ENOENT || ret == -ENODATA) - ret = 0; - else if (ret != -ENOMEM) - cachefiles_io_error(cache, - "Can't remove xattr from %lu" - " (error %d)", - d_backing_inode(dentry)->i_ino, -ret); + _enter(""); + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + xlen = cachefiles_inject_read_error(); + if (xlen == 0) + xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, buf, len); + if (xlen != len) { + if (xlen < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dentry), xlen, + cachefiles_trace_getxattr_error); + if (xlen == -EIO) + cachefiles_io_error( + volume->cache, + "Failed to read xattr with error %zd", xlen); + } + why = cachefiles_coherency_vol_check_xattr; + } else if (memcmp(buf->data, p, len) != 0) { + why = cachefiles_coherency_vol_check_cmp; + } else { + why = cachefiles_coherency_vol_check_ok; + ret = 0; } + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, why); + kfree(buf); _leave(" = %d", ret); return ret; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index e53c8541f5b2..b3d9459c9bbd 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -4,8 +4,8 @@ #include <linux/backing-dev.h> #include <linux/fs.h> #include <linux/mm.h> +#include <linux/swap.h> #include <linux/pagemap.h> -#include <linux/writeback.h> /* generic_writepages */ #include <linux/slab.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> @@ -126,7 +126,7 @@ static int ceph_set_page_dirty(struct page *page) BUG_ON(PagePrivate(page)); attach_page_private(page, snapc); - return __set_page_dirty_nobuffers(page); + return ceph_fscache_set_page_dirty(page); } /* @@ -141,8 +141,6 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, struct ceph_inode_info *ci; struct ceph_snap_context *snapc; - wait_on_page_fscache(page); - inode = page->mapping->host; ci = ceph_inode(inode); @@ -153,28 +151,36 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, } WARN_ON(!PageLocked(page)); - if (!PagePrivate(page)) - return; + if (PagePrivate(page)) { + dout("%p invalidatepage %p idx %lu full dirty page\n", + inode, page, page->index); - dout("%p invalidatepage %p idx %lu full dirty page\n", - inode, page, page->index); + snapc = detach_page_private(page); + ceph_put_wrbuffer_cap_refs(ci, 1, snapc); + ceph_put_snap_context(snapc); + } - snapc = detach_page_private(page); - ceph_put_wrbuffer_cap_refs(ci, 1, snapc); - ceph_put_snap_context(snapc); + wait_on_page_fscache(page); } static int ceph_releasepage(struct page *page, gfp_t gfp) { - dout("%p releasepage %p idx %lu (%sdirty)\n", page->mapping->host, - page, page->index, PageDirty(page) ? "" : "not "); + struct inode *inode = page->mapping->host; + + dout("%llx:%llx releasepage %p idx %lu (%sdirty)\n", + ceph_vinop(inode), page, + page->index, PageDirty(page) ? "" : "not "); + + if (PagePrivate(page)) + return 0; if (PageFsCache(page)) { - if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) + if (current_is_kswapd() || !(gfp & __GFP_FS)) return 0; wait_on_page_fscache(page); } - return !PagePrivate(page); + ceph_fscache_note_page_release(inode); + return 1; } static void ceph_netfs_expand_readahead(struct netfs_read_request *rreq) @@ -378,6 +384,38 @@ static void ceph_readahead(struct readahead_control *ractl) netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got); } +#ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + set_page_fscache(page); +} + +static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) +{ + struct inode *inode = priv; + + if (IS_ERR_VALUE(error) && error != -ENOBUFS) + ceph_fscache_invalidate(inode, false); +} + +static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct fscache_cookie *cookie = ceph_fscache_cookie(ci); + + fscache_write_to_cache(cookie, inode->i_mapping, off, len, i_size_read(inode), + ceph_fscache_write_terminated, inode, caching); +} +#else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + +static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) +{ +} +#endif /* CONFIG_CEPH_FSCACHE */ + struct ceph_writeback_ctl { loff_t i_size; @@ -493,6 +531,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) struct ceph_writeback_ctl ceph_wbc; struct ceph_osd_client *osdc = &fsc->client->osdc; struct ceph_osd_request *req; + bool caching = ceph_is_cache_enabled(inode); dout("writepage %p idx %lu\n", page, page->index); @@ -531,16 +570,17 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); - set_page_writeback(page); req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1, CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc, ceph_wbc.truncate_seq, ceph_wbc.truncate_size, true); - if (IS_ERR(req)) { - redirty_page_for_writepage(wbc, page); - end_page_writeback(page); + if (IS_ERR(req)) return PTR_ERR(req); - } + + set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); + ceph_fscache_write_to_cache(inode, page_off, len, caching); /* it may be a short write due to an object boundary */ WARN_ON_ONCE(len > thp_size(page)); @@ -599,6 +639,9 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = page->mapping->host; BUG_ON(!inode); ihold(inode); + + wait_on_page_fscache(page); + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -720,6 +763,7 @@ static int ceph_writepages_start(struct address_space *mapping, struct ceph_writeback_ctl ceph_wbc; bool should_loop, range_whole = false; bool done = false; + bool caching = ceph_is_cache_enabled(inode); dout("writepages_start %p (mode=%s)\n", inode, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : @@ -843,7 +887,7 @@ get_more_pages: unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || PageFsCache(page)) { if (wbc->sync_mode == WB_SYNC_NONE) { dout("%p under writeback\n", page); unlock_page(page); @@ -851,6 +895,7 @@ get_more_pages: } dout("waiting on writeback %p\n", page); wait_on_page_writeback(page); + wait_on_page_fscache(page); } if (!clear_page_dirty_for_io(page)) { @@ -983,9 +1028,19 @@ new_request: op_idx = 0; for (i = 0; i < locked_pages; i++) { u64 cur_offset = page_offset(pages[i]); + /* + * Discontinuity in page range? Ceph can handle that by just passing + * multiple extents in the write op. + */ if (offset + len != cur_offset) { + /* If it's full, stop here */ if (op_idx + 1 == req->r_num_ops) break; + + /* Kick off an fscache write with what we have so far. */ + ceph_fscache_write_to_cache(inode, offset, len, caching); + + /* Start a new extent */ osd_req_op_extent_dup_last(req, op_idx, cur_offset - offset); dout("writepages got pages at %llu~%llu\n", @@ -996,14 +1051,17 @@ new_request: osd_req_op_extent_update(req, op_idx, len); len = 0; - offset = cur_offset; + offset = cur_offset; data_pages = pages + i; op_idx++; } set_page_writeback(pages[i]); + if (caching) + ceph_set_page_fscache(pages[i]); len += thp_size(page); } + ceph_fscache_write_to_cache(inode, offset, len, caching); if (ceph_wbc.size_stable) { len = min(len, ceph_wbc.i_size - offset); diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 457afda5498a..7d22850623ef 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -12,199 +12,99 @@ #include "super.h" #include "cache.h" -struct fscache_netfs ceph_cache_netfs = { - .name = "ceph", - .version = 0, -}; - -static DEFINE_MUTEX(ceph_fscache_lock); -static LIST_HEAD(ceph_fscache_list); - -struct ceph_fscache_entry { - struct list_head list; - struct fscache_cookie *fscache; - size_t uniq_len; - /* The following members must be last */ - struct ceph_fsid fsid; - char uniquifier[]; -}; - -static const struct fscache_cookie_def ceph_fscache_fsid_object_def = { - .name = "CEPH.fsid", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -int __init ceph_fscache_register(void) -{ - return fscache_register_netfs(&ceph_cache_netfs); -} - -void ceph_fscache_unregister(void) -{ - fscache_unregister_netfs(&ceph_cache_netfs); -} - -int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) +void ceph_fscache_register_inode_cookie(struct inode *inode) { - const struct ceph_fsid *fsid = &fsc->client->fsid; - const char *fscache_uniq = fsc->mount_options->fscache_uniq; - size_t uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0; - struct ceph_fscache_entry *ent; - int err = 0; + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - mutex_lock(&ceph_fscache_lock); - list_for_each_entry(ent, &ceph_fscache_list, list) { - if (memcmp(&ent->fsid, fsid, sizeof(*fsid))) - continue; - if (ent->uniq_len != uniq_len) - continue; - if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len)) - continue; - - errorfc(fc, "fscache cookie already registered for fsid %pU, use fsc=<uniquifier> option", - fsid); - err = -EBUSY; - goto out_unlock; - } + /* No caching for filesystem? */ + if (!fsc->fscache) + return; - ent = kzalloc(sizeof(*ent) + uniq_len, GFP_KERNEL); - if (!ent) { - err = -ENOMEM; - goto out_unlock; - } + /* Regular files only */ + if (!S_ISREG(inode->i_mode)) + return; - memcpy(&ent->fsid, fsid, sizeof(*fsid)); - if (uniq_len > 0) { - memcpy(&ent->uniquifier, fscache_uniq, uniq_len); - ent->uniq_len = uniq_len; - } + /* Only new inodes! */ + if (!(inode->i_state & I_NEW)) + return; - fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index, - &ceph_fscache_fsid_object_def, - &ent->fsid, sizeof(ent->fsid) + uniq_len, - NULL, 0, - fsc, 0, true); + WARN_ON_ONCE(ci->fscache); - if (fsc->fscache) { - ent->fscache = fsc->fscache; - list_add_tail(&ent->list, &ceph_fscache_list); - } else { - kfree(ent); - errorfc(fc, "unable to register fscache cookie for fsid %pU", - fsid); - /* all other fs ignore this error */ - } -out_unlock: - mutex_unlock(&ceph_fscache_lock); - return err; + ci->fscache = fscache_acquire_cookie(fsc->fscache, 0, + &ci->i_vino, sizeof(ci->i_vino), + &ci->i_version, sizeof(ci->i_version), + i_size_read(inode)); } -static enum fscache_checkaux ceph_fscache_inode_check_aux( - void *cookie_netfs_data, const void *data, uint16_t dlen, - loff_t object_size) +void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) { - struct ceph_inode_info* ci = cookie_netfs_data; - struct inode* inode = &ci->vfs_inode; + struct fscache_cookie *cookie = ci->fscache; - if (dlen != sizeof(ci->i_version) || - i_size_read(inode) != object_size) - return FSCACHE_CHECKAUX_OBSOLETE; + fscache_relinquish_cookie(cookie, false); +} - if (*(u64 *)data != ci->i_version) - return FSCACHE_CHECKAUX_OBSOLETE; +void ceph_fscache_use_cookie(struct inode *inode, bool will_modify) +{ + struct ceph_inode_info *ci = ceph_inode(inode); - dout("ceph inode 0x%p cached okay\n", ci); - return FSCACHE_CHECKAUX_OKAY; + fscache_use_cookie(ci->fscache, will_modify); } -static const struct fscache_cookie_def ceph_fscache_inode_object_def = { - .name = "CEPH.inode", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = ceph_fscache_inode_check_aux, -}; - -void ceph_fscache_register_inode_cookie(struct inode *inode) +void ceph_fscache_unuse_cookie(struct inode *inode, bool update) { struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - - /* No caching for filesystem */ - if (!fsc->fscache) - return; - /* Only cache for regular files that are read only */ - if (!S_ISREG(inode->i_mode)) - return; + if (update) { + loff_t i_size = i_size_read(inode); - inode_lock_nested(inode, I_MUTEX_CHILD); - if (!ci->fscache) { - ci->fscache = fscache_acquire_cookie(fsc->fscache, - &ceph_fscache_inode_object_def, - &ci->i_vino, sizeof(ci->i_vino), - &ci->i_version, sizeof(ci->i_version), - ci, i_size_read(inode), false); + fscache_unuse_cookie(ci->fscache, &ci->i_version, &i_size); + } else { + fscache_unuse_cookie(ci->fscache, NULL, NULL); } - inode_unlock(inode); } -void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +void ceph_fscache_update(struct inode *inode) { - struct fscache_cookie* cookie; - - if ((cookie = ci->fscache) == NULL) - return; - - ci->fscache = NULL; + struct ceph_inode_info *ci = ceph_inode(inode); + loff_t i_size = i_size_read(inode); - fscache_relinquish_cookie(cookie, &ci->i_vino, false); + fscache_update_cookie(ci->fscache, &ci->i_version, &i_size); } -static bool ceph_fscache_can_enable(void *data) +void ceph_fscache_invalidate(struct inode *inode, bool dio_write) { - struct inode *inode = data; - return !inode_is_open_for_write(inode); + struct ceph_inode_info *ci = ceph_inode(inode); + + fscache_invalidate(ceph_inode(inode)->fscache, + &ci->i_version, i_size_read(inode), + dio_write ? FSCACHE_INVAL_DIO_WRITE : 0); } -void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp) +int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) { - struct ceph_inode_info *ci = ceph_inode(inode); + const struct ceph_fsid *fsid = &fsc->client->fsid; + const char *fscache_uniq = fsc->mount_options->fscache_uniq; + size_t uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0; + char *name; + int err = 0; - if (!fscache_cookie_valid(ci->fscache)) - return; + name = kasprintf(GFP_KERNEL, "ceph,%pU%s%s", fsid, uniq_len ? "," : "", + uniq_len ? fscache_uniq : ""); + if (!name) + return -ENOMEM; - if (inode_is_open_for_write(inode)) { - dout("fscache_file_set_cookie %p %p disabling cache\n", - inode, filp); - fscache_disable_cookie(ci->fscache, &ci->i_vino, false); - } else { - fscache_enable_cookie(ci->fscache, &ci->i_vino, i_size_read(inode), - ceph_fscache_can_enable, inode); - if (fscache_cookie_enabled(ci->fscache)) { - dout("fscache_file_set_cookie %p %p enabling cache\n", - inode, filp); - } + fsc->fscache = fscache_acquire_volume(name, NULL, NULL, 0); + if (IS_ERR_OR_NULL(fsc->fscache)) { + errorfc(fc, "Unable to register fscache cookie for %s", name); + err = fsc->fscache ? PTR_ERR(fsc->fscache) : -EOPNOTSUPP; + fsc->fscache = NULL; } + kfree(name); + return err; } void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) { - if (fscache_cookie_valid(fsc->fscache)) { - struct ceph_fscache_entry *ent; - bool found = false; - - mutex_lock(&ceph_fscache_lock); - list_for_each_entry(ent, &ceph_fscache_list, list) { - if (ent->fscache == fsc->fscache) { - list_del(&ent->list); - kfree(ent); - found = true; - break; - } - } - WARN_ON_ONCE(!found); - mutex_unlock(&ceph_fscache_lock); - - __fscache_relinquish_cookie(fsc->fscache, NULL, false); - } - fsc->fscache = NULL; + fscache_relinquish_volume(fsc->fscache, NULL, false); } diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index 058ea2a04376..09164389fa66 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -12,19 +12,19 @@ #include <linux/netfs.h> #ifdef CONFIG_CEPH_FSCACHE - -extern struct fscache_netfs ceph_cache_netfs; - -int ceph_fscache_register(void); -void ceph_fscache_unregister(void); +#include <linux/fscache.h> int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc); void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc); void ceph_fscache_register_inode_cookie(struct inode *inode); void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci); -void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp); -void ceph_fscache_revalidate_cookie(struct ceph_inode_info *ci); + +void ceph_fscache_use_cookie(struct inode *inode, bool will_modify); +void ceph_fscache_unuse_cookie(struct inode *inode, bool update); + +void ceph_fscache_update(struct inode *inode); +void ceph_fscache_invalidate(struct inode *inode, bool dio_write); static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) { @@ -36,37 +36,51 @@ static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info return ci->fscache; } -static inline void ceph_fscache_invalidate(struct inode *inode) +static inline void ceph_fscache_resize(struct inode *inode, loff_t to) { - fscache_invalidate(ceph_inode(inode)->fscache); + struct ceph_inode_info *ci = ceph_inode(inode); + struct fscache_cookie *cookie = ceph_fscache_cookie(ci); + + if (cookie) { + ceph_fscache_use_cookie(inode, true); + fscache_resize_cookie(cookie, to); + ceph_fscache_unuse_cookie(inode, true); + } } -static inline bool ceph_is_cache_enabled(struct inode *inode) +static inline void ceph_fscache_unpin_writeback(struct inode *inode, + struct writeback_control *wbc) { - struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(inode)); + fscache_unpin_writeback(wbc, ceph_fscache_cookie(ceph_inode(inode))); +} + +static inline int ceph_fscache_set_page_dirty(struct page *page) +{ + struct inode *inode = page->mapping->host; + struct ceph_inode_info *ci = ceph_inode(inode); - if (!cookie) - return false; - return fscache_cookie_enabled(cookie); + return fscache_set_page_dirty(page, ceph_fscache_cookie(ci)); } static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq) { struct fscache_cookie *cookie = ceph_fscache_cookie(ceph_inode(rreq->inode)); - return fscache_begin_read_operation(rreq, cookie); + return fscache_begin_read_operation(&rreq->cache_resources, cookie); } -#else -static inline int ceph_fscache_register(void) +static inline bool ceph_is_cache_enabled(struct inode *inode) { - return 0; + return fscache_cookie_enabled(ceph_fscache_cookie(ceph_inode(inode))); } -static inline void ceph_fscache_unregister(void) +static inline void ceph_fscache_note_page_release(struct inode *inode) { -} + struct ceph_inode_info *ci = ceph_inode(inode); + fscache_note_page_release(ceph_fscache_cookie(ci)); +} +#else /* CONFIG_CEPH_FSCACHE */ static inline int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc) { @@ -81,28 +95,49 @@ static inline void ceph_fscache_inode_init(struct ceph_inode_info *ci) { } -static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci) +static inline void ceph_fscache_register_inode_cookie(struct inode *inode) { - return NULL; } -static inline void ceph_fscache_register_inode_cookie(struct inode *inode) +static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) { } -static inline void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info* ci) +static inline void ceph_fscache_use_cookie(struct inode *inode, bool will_modify) { } -static inline void ceph_fscache_file_set_cookie(struct inode *inode, - struct file *filp) +static inline void ceph_fscache_unuse_cookie(struct inode *inode, bool update) { } -static inline void ceph_fscache_invalidate(struct inode *inode) +static inline void ceph_fscache_update(struct inode *inode) { } +static inline void ceph_fscache_invalidate(struct inode *inode, bool dio_write) +{ +} + +static inline struct fscache_cookie *ceph_fscache_cookie(struct ceph_inode_info *ci) +{ + return NULL; +} + +static inline void ceph_fscache_resize(struct inode *inode, loff_t to) +{ +} + +static inline void ceph_fscache_unpin_writeback(struct inode *inode, + struct writeback_control *wbc) +{ +} + +static inline int ceph_fscache_set_page_dirty(struct page *page) +{ + return __set_page_dirty_nobuffers(page); +} + static inline bool ceph_is_cache_enabled(struct inode *inode) { return false; @@ -112,6 +147,10 @@ static inline int ceph_begin_cache_operation(struct netfs_read_request *rreq) { return -ENOBUFS; } -#endif -#endif /* _CEPH_CACHE_H */ +static inline void ceph_fscache_note_page_release(struct inode *inode) +{ +} +#endif /* CONFIG_CEPH_FSCACHE */ + +#endif diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index c447fa2e2d1f..7d2c33cdbac6 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1856,7 +1856,7 @@ static int try_nonblocking_invalidate(struct inode *inode) u32 invalidating_gen = ci->i_rdcache_gen; spin_unlock(&ci->i_ceph_lock); - ceph_fscache_invalidate(inode); + ceph_fscache_invalidate(inode, false); invalidate_mapping_pages(&inode->i_data, 0, -1); spin_lock(&ci->i_ceph_lock); @@ -2388,6 +2388,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc) int wait = (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync); dout("write_inode %p wait=%d\n", inode, wait); + ceph_fscache_unpin_writeback(inode, wbc); if (wait) { dirty = try_flush_caps(inode, &flush_tid); if (dirty) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index c138e8126286..9d9304e712d9 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -248,8 +248,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) switch (inode->i_mode & S_IFMT) { case S_IFREG: - ceph_fscache_register_inode_cookie(inode); - ceph_fscache_file_set_cookie(inode, file); + ceph_fscache_use_cookie(inode, file->f_mode & FMODE_WRITE); fallthrough; case S_IFDIR: ret = ceph_init_file_info(inode, file, fmode, @@ -822,6 +821,7 @@ int ceph_release(struct inode *inode, struct file *file) dout("release inode %p regular file %p\n", inode, file); WARN_ON(!list_empty(&fi->rw_contexts)); + ceph_fscache_unuse_cookie(inode, file->f_mode & FMODE_WRITE); ceph_put_fmode(ci, fi->fmode, 1); kmem_cache_free(ceph_file_cachep, fi); @@ -1218,7 +1218,11 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, snapc, snapc ? snapc->seq : 0); if (write) { - int ret2 = invalidate_inode_pages2_range(inode->i_mapping, + int ret2; + + ceph_fscache_invalidate(inode, true); + + ret2 = invalidate_inode_pages2_range(inode->i_mapping, pos >> PAGE_SHIFT, (pos + count - 1) >> PAGE_SHIFT); if (ret2 < 0) @@ -1429,6 +1433,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, if (ret < 0) return ret; + ceph_fscache_invalidate(inode, false); ret = invalidate_inode_pages2_range(inode->i_mapping, pos >> PAGE_SHIFT, (pos + count - 1) >> PAGE_SHIFT); @@ -2113,6 +2118,7 @@ static long ceph_fallocate(struct file *file, int mode, goto unlock; filemap_invalidate_lock(inode->i_mapping); + ceph_fscache_invalidate(inode, false); ceph_zero_pagecache_range(inode, offset, length); ret = ceph_zero_objects(inode, offset, length); @@ -2437,6 +2443,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, goto out_caps; /* Drop dst file cached pages */ + ceph_fscache_invalidate(dst_inode, false); ret = invalidate_inode_pages2_range(dst_inode->i_mapping, dst_off >> PAGE_SHIFT, (dst_off + len) >> PAGE_SHIFT); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e3322fcb2e8d..ef4a980a7bf3 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -564,6 +564,8 @@ void ceph_evict_inode(struct inode *inode) percpu_counter_dec(&mdsc->metric.total_inodes); truncate_inode_pages_final(&inode->i_data); + if (inode->i_state & I_PINNING_FSCACHE_WB) + ceph_fscache_unuse_cookie(inode, true); clear_inode(inode); ceph_fscache_unregister_inode_cookie(ci); @@ -634,6 +636,12 @@ int ceph_fill_file_size(struct inode *inode, int issued, } i_size_write(inode, size); inode->i_blocks = calc_inode_blocks(size); + /* + * If we're expanding, then we should be able to just update + * the existing cookie. + */ + if (size > isize) + ceph_fscache_update(inode); ci->i_reported_size = size; if (truncate_seq != ci->i_truncate_seq) { dout("truncate_seq %u -> %u\n", @@ -666,10 +674,6 @@ int ceph_fill_file_size(struct inode *inode, int issued, truncate_size); ci->i_truncate_size = truncate_size; } - - if (queue_trunc) - ceph_fscache_invalidate(inode); - return queue_trunc; } @@ -1053,6 +1057,8 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, spin_unlock(&ci->i_ceph_lock); + ceph_fscache_register_inode_cookie(inode); + if (fill_inline) ceph_fill_inline_data(inode, locked_page, iinfo->inline_data, iinfo->inline_len); @@ -1814,11 +1820,13 @@ bool ceph_inode_set_size(struct inode *inode, loff_t size) spin_lock(&ci->i_ceph_lock); dout("set_size %p %llu -> %llu\n", inode, i_size_read(inode), size); i_size_write(inode, size); + ceph_fscache_update(inode); inode->i_blocks = calc_inode_blocks(size); ret = __ceph_should_report_size(ci); spin_unlock(&ci->i_ceph_lock); + return ret; } @@ -1844,6 +1852,8 @@ static void ceph_do_invalidate_pages(struct inode *inode) u32 orig_gen; int check = 0; + ceph_fscache_invalidate(inode, false); + mutex_lock(&ci->i_truncate_mutex); if (ceph_inode_is_shutdown(inode)) { @@ -1868,7 +1878,7 @@ static void ceph_do_invalidate_pages(struct inode *inode) orig_gen = ci->i_rdcache_gen; spin_unlock(&ci->i_ceph_lock); - ceph_fscache_invalidate(inode); + ceph_fscache_invalidate(inode, false); if (invalidate_inode_pages2(inode->i_mapping) < 0) { pr_err("invalidate_inode_pages2 %llx.%llx failed\n", ceph_vinop(inode)); @@ -1937,6 +1947,7 @@ retry: ci->i_truncate_pending, to); spin_unlock(&ci->i_ceph_lock); + ceph_fscache_resize(inode, to); truncate_pagecache(inode, to); spin_lock(&ci->i_ceph_lock); @@ -2184,7 +2195,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) if (inode_dirty_flags) __mark_inode_dirty(inode, inode_dirty_flags); - if (mask) { req->r_inode = inode; ihold(inode); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index bab61232dc5a..bea89bdb534a 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -787,16 +787,10 @@ static int __init init_caches(void) if (!ceph_wb_pagevec_pool) goto bad_pagevec_pool; - error = ceph_fscache_register(); - if (error) - goto bad_fscache; - return 0; -bad_fscache: - kmem_cache_destroy(ceph_mds_request_cachep); bad_pagevec_pool: - mempool_destroy(ceph_wb_pagevec_pool); + kmem_cache_destroy(ceph_mds_request_cachep); bad_mds_req: kmem_cache_destroy(ceph_dir_file_cachep); bad_dir_file: @@ -828,8 +822,6 @@ static void destroy_caches(void) kmem_cache_destroy(ceph_dir_file_cachep); kmem_cache_destroy(ceph_mds_request_cachep); mempool_destroy(ceph_wb_pagevec_pool); - - ceph_fscache_unregister(); } static void __ceph_umount_begin(struct ceph_fs_client *fsc) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index ac331aa07cfa..d0142cc5c41b 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -21,7 +21,6 @@ #include <linux/ceph/libceph.h> #ifdef CONFIG_CEPH_FSCACHE -#define FSCACHE_USE_NEW_IO_API #include <linux/fscache.h> #endif @@ -135,7 +134,7 @@ struct ceph_fs_client { #endif #ifdef CONFIG_CEPH_FSCACHE - struct fscache_cookie *fscache; + struct fscache_volume *fscache; #endif }; diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 3b7e3b9e4fd2..346ae8716deb 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -188,7 +188,7 @@ config CIFS_SMB_DIRECT config CIFS_FSCACHE bool "Provide CIFS client caching support" - depends on CIFS=m && FSCACHE || CIFS=y && FSCACHE=y + depends on CIFS=m && FSCACHE_OLD_API || CIFS=y && FSCACHE_OLD_API=y help Makes CIFS FS-Cache capable. Say Y here if you want your CIFS data to be cached locally on disk through the general filesystem cache diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4f680f848c8b..f8d7fe6db989 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1668,6 +1668,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; + else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) { + if (!(inode->i_state & I_DIRTY_PAGES)) { + inode->i_state &= ~I_PINNING_FSCACHE_WB; + wbc->unpinned_fscache_wb = true; + dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */ + } + } spin_unlock(&inode->i_lock); @@ -1677,6 +1684,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (ret == 0) ret = err; } + wbc->unpinned_fscache_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index b313a978ae0a..76316c4a3fb7 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -38,3 +38,6 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_OLD_API + bool diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index 03a871d689bb..afb090ea16c4 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -6,13 +6,9 @@ fscache-y := \ cache.o \ cookie.o \ - fsdef.o \ io.o \ main.o \ - netfs.o \ - object.o \ - operation.o \ - page.o + volume.o fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index bd4f44c1cce0..2749933852a9 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -1,209 +1,229 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache cache handling * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define FSCACHE_DEBUG_LEVEL CACHE -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> #include "internal.h" -LIST_HEAD(fscache_cache_list); +static LIST_HEAD(fscache_caches); DECLARE_RWSEM(fscache_addremove_sem); -DECLARE_WAIT_QUEUE_HEAD(fscache_cache_cleared_wq); -EXPORT_SYMBOL(fscache_cache_cleared_wq); +EXPORT_SYMBOL(fscache_addremove_sem); +DECLARE_WAIT_QUEUE_HEAD(fscache_clearance_waiters); +EXPORT_SYMBOL(fscache_clearance_waiters); -static LIST_HEAD(fscache_cache_tag_list); +static atomic_t fscache_cache_debug_id; /* - * look up a cache tag + * Allocate a cache cookie. */ -struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *name) +static struct fscache_cache *fscache_alloc_cache(const char *name) { - struct fscache_cache_tag *tag, *xtag; - - /* firstly check for the existence of the tag under read lock */ - down_read(&fscache_addremove_sem); - - list_for_each_entry(tag, &fscache_cache_tag_list, link) { - if (strcmp(tag->name, name) == 0) { - atomic_inc(&tag->usage); - up_read(&fscache_addremove_sem); - return tag; - } - } - - up_read(&fscache_addremove_sem); - - /* the tag does not exist - create a candidate */ - xtag = kzalloc(sizeof(*xtag) + strlen(name) + 1, GFP_KERNEL); - if (!xtag) - /* return a dummy tag if out of memory */ - return ERR_PTR(-ENOMEM); - - atomic_set(&xtag->usage, 1); - strcpy(xtag->name, name); - - /* write lock, search again and add if still not present */ - down_write(&fscache_addremove_sem); + struct fscache_cache *cache; - list_for_each_entry(tag, &fscache_cache_tag_list, link) { - if (strcmp(tag->name, name) == 0) { - atomic_inc(&tag->usage); - up_write(&fscache_addremove_sem); - kfree(xtag); - return tag; + cache = kzalloc(sizeof(*cache), GFP_KERNEL); + if (cache) { + if (name) { + cache->name = kstrdup(name, GFP_KERNEL); + if (!cache->name) { + kfree(cache); + return NULL; + } } + refcount_set(&cache->ref, 1); + INIT_LIST_HEAD(&cache->cache_link); + cache->debug_id = atomic_inc_return(&fscache_cache_debug_id); } - - list_add_tail(&xtag->link, &fscache_cache_tag_list); - up_write(&fscache_addremove_sem); - return xtag; + return cache; } -/* - * release a reference to a cache tag - */ -void __fscache_release_cache_tag(struct fscache_cache_tag *tag) +static bool fscache_get_cache_maybe(struct fscache_cache *cache, + enum fscache_cache_trace where) { - if (tag != ERR_PTR(-ENOMEM)) { - down_write(&fscache_addremove_sem); + bool success; + int ref; - if (atomic_dec_and_test(&tag->usage)) - list_del_init(&tag->link); - else - tag = NULL; - - up_write(&fscache_addremove_sem); - - kfree(tag); - } + success = __refcount_inc_not_zero(&cache->ref, &ref); + if (success) + trace_fscache_cache(cache->debug_id, ref + 1, where); + return success; } /* - * select a cache in which to store an object - * - the cache addremove semaphore must be at least read-locked by the caller - * - the object will never be an index + * Look up a cache cookie. */ -struct fscache_cache *fscache_select_cache_for_object( - struct fscache_cookie *cookie) +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache) { - struct fscache_cache_tag *tag; - struct fscache_object *object; - struct fscache_cache *cache; + struct fscache_cache *candidate, *cache, *unnamed = NULL; - _enter(""); + /* firstly check for the existence of the cache under read lock */ + down_read(&fscache_addremove_sem); - if (list_empty(&fscache_cache_list)) { - _leave(" = NULL [no cache]"); - return NULL; + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && name && strcmp(cache->name, name) == 0 && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + if (!cache->name && !name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; } - /* we check the parent to determine the cache to use */ - spin_lock(&cookie->lock); + if (!name) { + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + } + } - /* the first in the parent's backing list should be the preferred - * cache */ - if (!hlist_empty(&cookie->backing_objects)) { - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); + up_read(&fscache_addremove_sem); - cache = object->cache; - if (fscache_object_is_dying(object) || - test_bit(FSCACHE_IOERROR, &cache->flags)) - cache = NULL; + /* the cache does not exist - create a candidate */ + candidate = fscache_alloc_cache(name); + if (!candidate) + return ERR_PTR(-ENOMEM); - spin_unlock(&cookie->lock); - _leave(" = %s [parent]", cache ? cache->tag->name : "NULL"); - return cache; - } + /* write lock, search again and add if still not present */ + down_write(&fscache_addremove_sem); - /* the parent is unbacked */ - if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) { - /* cookie not an index and is unbacked */ - spin_unlock(&cookie->lock); - _leave(" = NULL [cookie ub,ni]"); - return NULL; + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && name && strcmp(cache->name, name) == 0 && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + if (!cache->name) { + unnamed = cache; + if (!name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + } } - spin_unlock(&cookie->lock); + if (unnamed && is_cache && + fscache_get_cache_maybe(unnamed, fscache_cache_get_acquire)) + goto use_unnamed_cache; - if (!cookie->def->select_cache) - goto no_preference; + if (!name) { + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + } + } - /* ask the netfs for its preference */ - tag = cookie->def->select_cache(cookie->parent->netfs_data, - cookie->netfs_data); - if (!tag) - goto no_preference; + list_add_tail(&candidate->cache_link, &fscache_caches); + trace_fscache_cache(candidate->debug_id, + refcount_read(&candidate->ref), + fscache_cache_new_acquire); + up_write(&fscache_addremove_sem); + return candidate; - if (tag == ERR_PTR(-ENOMEM)) { - _leave(" = NULL [nomem tag]"); - return NULL; - } +got_cache_r: + up_read(&fscache_addremove_sem); + return cache; +use_unnamed_cache: + cache = unnamed; + cache->name = candidate->name; + candidate->name = NULL; +got_cache_w: + up_write(&fscache_addremove_sem); + kfree(candidate->name); + kfree(candidate); + return cache; +} - if (!tag->cache) { - _leave(" = NULL [unbacked tag]"); - return NULL; - } +/** + * fscache_acquire_cache - Acquire a cache-level cookie. + * @name: The name of the cache. + * + * Get a cookie to represent an actual cache. If a name is given and there is + * a nameless cache record available, this will acquire that and set its name, + * directing all the volumes using it to this cache. + * + * The cache will be switched over to the preparing state if not currently in + * use, otherwise -EBUSY will be returned. + */ +struct fscache_cache *fscache_acquire_cache(const char *name) +{ + struct fscache_cache *cache; - if (test_bit(FSCACHE_IOERROR, &tag->cache->flags)) - return NULL; + ASSERT(name); + cache = fscache_lookup_cache(name, true); + if (IS_ERR(cache)) + return cache; - _leave(" = %s [specific]", tag->name); - return tag->cache; + if (!fscache_set_cache_state_maybe(cache, + FSCACHE_CACHE_IS_NOT_PRESENT, + FSCACHE_CACHE_IS_PREPARING)) { + pr_warn("Cache tag %s in use\n", name); + fscache_put_cache(cache, fscache_cache_put_cache); + return ERR_PTR(-EBUSY); + } -no_preference: - /* netfs has no preference - just select first cache */ - cache = list_entry(fscache_cache_list.next, - struct fscache_cache, link); - _leave(" = %s [first]", cache->tag->name); return cache; } +EXPORT_SYMBOL(fscache_acquire_cache); /** - * fscache_init_cache - Initialise a cache record - * @cache: The cache record to be initialised - * @ops: The cache operations to be installed in that record - * @idfmt: Format string to define identifier - * @...: sprintf-style arguments + * fscache_put_cache - Release a cache-level cookie. + * @cache: The cache cookie to be released + * @where: An indication of where the release happened * - * Initialise a record of a cache and fill in the name. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. + * Release the caller's reference on a cache-level cookie. The @where + * indication should give information about the circumstances in which the call + * occurs and will be logged through a tracepoint. */ -void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, - ...) +void fscache_put_cache(struct fscache_cache *cache, + enum fscache_cache_trace where) { - va_list va; + unsigned int debug_id = cache->debug_id; + bool zero; + int ref; - memset(cache, 0, sizeof(*cache)); + if (IS_ERR_OR_NULL(cache)) + return; - cache->ops = ops; + zero = __refcount_dec_and_test(&cache->ref, &ref); + trace_fscache_cache(debug_id, ref - 1, where); - va_start(va, idfmt); - vsnprintf(cache->identifier, sizeof(cache->identifier), idfmt, va); - va_end(va); + if (zero) { + down_write(&fscache_addremove_sem); + list_del_init(&cache->cache_link); + up_write(&fscache_addremove_sem); + kfree(cache->name); + kfree(cache); + } +} - INIT_WORK(&cache->op_gc, fscache_operation_gc); - INIT_LIST_HEAD(&cache->link); - INIT_LIST_HEAD(&cache->object_list); - INIT_LIST_HEAD(&cache->op_gc_list); - spin_lock_init(&cache->object_list_lock); - spin_lock_init(&cache->op_gc_list_lock); +/** + * fscache_relinquish_cache - Reset cache state and release cookie + * @cache: The cache cookie to be released + * + * Reset the state of a cache and release the caller's reference on a cache + * cookie. + */ +void fscache_relinquish_cache(struct fscache_cache *cache) +{ + enum fscache_cache_trace where = + (cache->state == FSCACHE_CACHE_IS_PREPARING) ? + fscache_cache_put_prep_failed : + fscache_cache_put_relinquish; + + cache->ops = NULL; + cache->cache_priv = NULL; + smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_put_cache(cache, where); } -EXPORT_SYMBOL(fscache_init_cache); +EXPORT_SYMBOL(fscache_relinquish_cache); /** * fscache_add_cache - Declare a cache as being open for business - * @cache: The record describing the cache - * @ifsdef: The record of the cache object describing the top-level index - * @tagname: The tag describing this cache + * @cache: The cache-level cookie representing the cache + * @ops: Table of cache operations to use + * @cache_priv: Private data for the cache record * * Add a cache to the system, making it available for netfs's to use. * @@ -211,93 +231,97 @@ EXPORT_SYMBOL(fscache_init_cache); * description. */ int fscache_add_cache(struct fscache_cache *cache, - struct fscache_object *ifsdef, - const char *tagname) + const struct fscache_cache_ops *ops, + void *cache_priv) { - struct fscache_cache_tag *tag; - - ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index); - BUG_ON(!cache->ops); - BUG_ON(!ifsdef); + int n_accesses; - cache->flags = 0; - ifsdef->event_mask = - ((1 << NR_FSCACHE_OBJECT_EVENTS) - 1) & - ~(1 << FSCACHE_OBJECT_EV_CLEARED); - __set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &ifsdef->flags); + _enter("{%s,%s}", ops->name, cache->name); - if (!tagname) - tagname = cache->identifier; + BUG_ON(fscache_cache_state(cache) != FSCACHE_CACHE_IS_PREPARING); - BUG_ON(!tagname[0]); - - _enter("{%s.%s},,%s", cache->ops->name, cache->identifier, tagname); - - /* we use the cache tag to uniquely identify caches */ - tag = __fscache_lookup_cache_tag(tagname); - if (IS_ERR(tag)) - goto nomem; - - if (test_and_set_bit(FSCACHE_TAG_RESERVED, &tag->flags)) - goto tag_in_use; - - cache->kobj = kobject_create_and_add(tagname, fscache_root); - if (!cache->kobj) - goto error; - - ifsdef->cache = cache; - cache->fsdef = ifsdef; + /* Get a ref on the cache cookie and keep its n_accesses counter raised + * by 1 to prevent wakeups from transitioning it to 0 until we're + * withdrawing caching services from it. + */ + n_accesses = atomic_inc_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, fscache_access_cache_pin); down_write(&fscache_addremove_sem); - tag->cache = cache; - cache->tag = tag; - - /* add the cache to the list */ - list_add(&cache->link, &fscache_cache_list); - - /* add the cache's netfs definition index object to the cache's - * list */ - spin_lock(&cache->object_list_lock); - list_add_tail(&ifsdef->cache_link, &cache->object_list); - spin_unlock(&cache->object_list_lock); - - /* add the cache's netfs definition index object to the top level index - * cookie as a known backing object */ - spin_lock(&fscache_fsdef_index.lock); - - hlist_add_head(&ifsdef->cookie_link, - &fscache_fsdef_index.backing_objects); - - refcount_inc(&fscache_fsdef_index.ref); + cache->ops = ops; + cache->cache_priv = cache_priv; + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_ACTIVE); - /* done */ - spin_unlock(&fscache_fsdef_index.lock); up_write(&fscache_addremove_sem); - - pr_notice("Cache \"%s\" added (type %s)\n", - cache->tag->name, cache->ops->name); - kobject_uevent(cache->kobj, KOBJ_ADD); - - _leave(" = 0 [%s]", cache->identifier); + pr_notice("Cache \"%s\" added (type %s)\n", cache->name, ops->name); + _leave(" = 0 [%s]", cache->name); return 0; +} +EXPORT_SYMBOL(fscache_add_cache); -tag_in_use: - pr_err("Cache tag '%s' already in use\n", tagname); - __fscache_release_cache_tag(tag); - _leave(" = -EXIST"); - return -EEXIST; - -error: - __fscache_release_cache_tag(tag); - _leave(" = -EINVAL"); - return -EINVAL; +/** + * fscache_begin_cache_access - Pin a cache so it can be accessed + * @cache: The cache-level cookie + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing it and returns true if successful. This works as follows: + * + * (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), + * then we return false to indicate access was not permitted. + * + * (2) If the cache tests as live, then we increment the n_accesses count and + * then recheck the liveness, ending the access if it ceased to be live. + * + * (3) When we end the access, we decrement n_accesses and wake up the any + * waiters if it reaches 0. + * + * (4) Whilst the cache is caching, n_accesses is kept artificially + * incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline, the state is changed to prevent new + * accesses, n_accesses is decremented and we wait for n_accesses to + * become 0. + */ +bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why) +{ + int n_accesses; + + if (!fscache_cache_is_live(cache)) + return false; + + n_accesses = atomic_inc_return(&cache->n_accesses); + smp_mb__after_atomic(); /* Reread live flag after n_accesses */ + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, why); + if (!fscache_cache_is_live(cache)) { + fscache_end_cache_access(cache, fscache_access_unlive); + return false; + } + return true; +} -nomem: - _leave(" = -ENOMEM"); - return -ENOMEM; +/** + * fscache_end_cache_access - Unpin a cache at the end of an access. + * @cache: The cache-level cookie + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache after we've accessed it. The @why indicator is merely + * provided for tracing purposes. + */ +void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, why); + if (n_accesses == 0) + wake_up_var(&cache->n_accesses); } -EXPORT_SYMBOL(fscache_add_cache); /** * fscache_io_error - Note a cache I/O error @@ -311,106 +335,94 @@ EXPORT_SYMBOL(fscache_add_cache); */ void fscache_io_error(struct fscache_cache *cache) { - if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags)) + if (fscache_set_cache_state_maybe(cache, + FSCACHE_CACHE_IS_ACTIVE, + FSCACHE_CACHE_GOT_IOERROR)) pr_err("Cache '%s' stopped due to I/O error\n", - cache->ops->name); + cache->name); } EXPORT_SYMBOL(fscache_io_error); -/* - * request withdrawal of all the objects in a cache - * - all the objects being withdrawn are moved onto the supplied list +/** + * fscache_withdraw_cache - Withdraw a cache from the active service + * @cache: The cache cookie + * + * Begin the process of withdrawing a cache from service. This stops new + * cache-level and volume-level accesses from taking place and waits for + * currently ongoing cache-level accesses to end. */ -static void fscache_withdraw_all_objects(struct fscache_cache *cache, - struct list_head *dying_objects) +void fscache_withdraw_cache(struct fscache_cache *cache) { - struct fscache_object *object; + int n_accesses; - while (!list_empty(&cache->object_list)) { - spin_lock(&cache->object_list_lock); + pr_notice("Withdrawing cache \"%s\" (%u objs)\n", + cache->name, atomic_read(&cache->object_count)); - if (!list_empty(&cache->object_list)) { - object = list_entry(cache->object_list.next, - struct fscache_object, cache_link); - list_move_tail(&object->cache_link, dying_objects); + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_WITHDRAWN); - _debug("withdraw %x", object->cookie->debug_id); + /* Allow wakeups on dec-to-0 */ + n_accesses = atomic_dec_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, fscache_access_cache_unpin); - /* This must be done under object_list_lock to prevent - * a race with fscache_drop_object(). - */ - fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL); - } - - spin_unlock(&cache->object_list_lock); - cond_resched(); - } + wait_var_event(&cache->n_accesses, + atomic_read(&cache->n_accesses) == 0); } +EXPORT_SYMBOL(fscache_withdraw_cache); -/** - * fscache_withdraw_cache - Withdraw a cache from the active service - * @cache: The record describing the cache - * - * Withdraw a cache from service, unbinding all its cache objects from the - * netfs cookies they're currently representing. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. +#ifdef CONFIG_PROC_FS +static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; + +/* + * Generate a list of caches in /proc/fs/fscache/caches */ -void fscache_withdraw_cache(struct fscache_cache *cache) +static int fscache_caches_seq_show(struct seq_file *m, void *v) { - LIST_HEAD(dying_objects); + struct fscache_cache *cache; - _enter(""); + if (v == &fscache_caches) { + seq_puts(m, + "CACHE REF VOLS OBJS ACCES S NAME\n" + "======== ===== ===== ===== ===== = ===============\n" + ); + return 0; + } - pr_notice("Withdrawing cache \"%s\"\n", - cache->tag->name); + cache = list_entry(v, struct fscache_cache, cache_link); + seq_printf(m, + "%08x %5d %5d %5d %5d %c %s\n", + cache->debug_id, + refcount_read(&cache->ref), + atomic_read(&cache->n_volumes), + atomic_read(&cache->object_count), + atomic_read(&cache->n_accesses), + fscache_cache_states[cache->state], + cache->name ?: "-"); + return 0; +} - /* make the cache unavailable for cookie acquisition */ - if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags)) - BUG(); +static void *fscache_caches_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(fscache_addremove_sem) +{ + down_read(&fscache_addremove_sem); + return seq_list_start_head(&fscache_caches, *_pos); +} - down_write(&fscache_addremove_sem); - list_del_init(&cache->link); - cache->tag->cache = NULL; - up_write(&fscache_addremove_sem); +static void *fscache_caches_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_caches, _pos); +} - /* make sure all pages pinned by operations on behalf of the netfs are - * written to disk */ - fscache_stat(&fscache_n_cop_sync_cache); - cache->ops->sync_cache(cache); - fscache_stat_d(&fscache_n_cop_sync_cache); - - /* dissociate all the netfs pages backed by this cache from the block - * mappings in the cache */ - fscache_stat(&fscache_n_cop_dissociate_pages); - cache->ops->dissociate_pages(cache); - fscache_stat_d(&fscache_n_cop_dissociate_pages); - - /* we now have to destroy all the active objects pertaining to this - * cache - which we do by passing them off to thread pool to be - * disposed of */ - _debug("destroy"); - - fscache_withdraw_all_objects(cache, &dying_objects); - - /* wait for all extant objects to finish their outstanding operations - * and go away */ - _debug("wait for finish"); - wait_event(fscache_cache_cleared_wq, - atomic_read(&cache->object_count) == 0); - _debug("wait for clearance"); - wait_event(fscache_cache_cleared_wq, - list_empty(&cache->object_list)); - _debug("cleared"); - ASSERT(list_empty(&dying_objects)); - - kobject_put(cache->kobj); - - clear_bit(FSCACHE_TAG_RESERVED, &cache->tag->flags); - fscache_release_cache_tag(cache->tag); - cache->tag = NULL; - - _leave(""); +static void fscache_caches_seq_stop(struct seq_file *m, void *v) + __releases(fscache_addremove_sem) +{ + up_read(&fscache_addremove_sem); } -EXPORT_SYMBOL(fscache_withdraw_cache); + +const struct seq_operations fscache_caches_seq_ops = { + .start = fscache_caches_seq_start, + .next = fscache_caches_seq_next, + .stop = fscache_caches_seq_stop, + .show = fscache_caches_seq_show, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index cd42be646ed3..9bb1ab5fe5ed 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* netfs cookie management * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/filesystems/caching/netfs-api.rst for more information on @@ -15,70 +15,258 @@ struct kmem_cache *fscache_cookie_jar; -static atomic_t fscache_object_debug_id = ATOMIC_INIT(0); +static void fscache_cookie_lru_timed_out(struct timer_list *timer); +static void fscache_cookie_lru_worker(struct work_struct *work); +static void fscache_cookie_worker(struct work_struct *work); +static void fscache_unhash_cookie(struct fscache_cookie *cookie); +static void fscache_perform_invalidation(struct fscache_cookie *cookie); #define fscache_cookie_hash_shift 15 static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; static LIST_HEAD(fscache_cookies); static DEFINE_RWLOCK(fscache_cookies_lock); - -static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie, - loff_t object_size); -static int fscache_alloc_object(struct fscache_cache *cache, - struct fscache_cookie *cookie); -static int fscache_attach_object(struct fscache_cookie *cookie, - struct fscache_object *object); - -static void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) +static LIST_HEAD(fscache_cookie_lru); +static DEFINE_SPINLOCK(fscache_cookie_lru_lock); +DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); +static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; +unsigned int fscache_lru_cookie_timeout = 10 * HZ; + +void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { - struct fscache_object *object; - struct hlist_node *o; const u8 *k; - unsigned loop; - pr_err("%c-cookie c=%08x [p=%08x fl=%lx nc=%u na=%u]\n", + pr_err("%c-cookie c=%08x [fl=%lx na=%u nA=%u s=%c]\n", prefix, cookie->debug_id, - cookie->parent ? cookie->parent->debug_id : 0, cookie->flags, - atomic_read(&cookie->n_children), - atomic_read(&cookie->n_active)); - pr_err("%c-cookie d=%p{%s} n=%p\n", + atomic_read(&cookie->n_active), + atomic_read(&cookie->n_accesses), + fscache_cookie_states[cookie->state]); + pr_err("%c-cookie V=%08x [%s]\n", prefix, - cookie->def, - cookie->def ? cookie->def->name : "?", - cookie->netfs_data); - - o = READ_ONCE(cookie->backing_objects.first); - if (o) { - object = hlist_entry(o, struct fscache_object, cookie_link); - pr_err("%c-cookie o=%u\n", prefix, object->debug_id); - } + cookie->volume->debug_id, + cookie->volume->key); - pr_err("%c-key=[%u] '", prefix, cookie->key_len); k = (cookie->key_len <= sizeof(cookie->inline_key)) ? cookie->inline_key : cookie->key; - for (loop = 0; loop < cookie->key_len; loop++) - pr_cont("%02x", k[loop]); - pr_cont("'\n"); + pr_err("%c-key=[%u] '%*phN'\n", prefix, cookie->key_len, cookie->key_len, k); } -void fscache_free_cookie(struct fscache_cookie *cookie) +static void fscache_free_cookie(struct fscache_cookie *cookie) { - if (cookie) { - BUG_ON(!hlist_empty(&cookie->backing_objects)); - write_lock(&fscache_cookies_lock); - list_del(&cookie->proc_link); - write_unlock(&fscache_cookies_lock); - if (cookie->aux_len > sizeof(cookie->inline_aux)) - kfree(cookie->aux); - if (cookie->key_len > sizeof(cookie->inline_key)) - kfree(cookie->key); - kmem_cache_free(fscache_cookie_jar, cookie); + if (WARN_ON_ONCE(!list_empty(&cookie->commit_link))) { + spin_lock(&fscache_cookie_lru_lock); + list_del_init(&cookie->commit_link); + spin_unlock(&fscache_cookie_lru_lock); + fscache_stat_d(&fscache_n_cookies_lru); + fscache_stat(&fscache_n_cookies_lru_removed); + } + + if (WARN_ON_ONCE(test_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags))) { + fscache_print_cookie(cookie, 'F'); + return; } + + write_lock(&fscache_cookies_lock); + list_del(&cookie->proc_link); + write_unlock(&fscache_cookies_lock); + if (cookie->aux_len > sizeof(cookie->inline_aux)) + kfree(cookie->aux); + if (cookie->key_len > sizeof(cookie->inline_key)) + kfree(cookie->key); + fscache_stat_d(&fscache_n_cookies); + kmem_cache_free(fscache_cookie_jar, cookie); +} + +static void __fscache_queue_cookie(struct fscache_cookie *cookie) +{ + if (!queue_work(fscache_wq, &cookie->work)) + fscache_put_cookie(cookie, fscache_cookie_put_over_queued); +} + +static void fscache_queue_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + fscache_get_cookie(cookie, where); + __fscache_queue_cookie(cookie); } /* + * Initialise the access gate on a cookie by setting a flag to prevent the + * state machine from being queued when the access counter transitions to 0. + * We're only interested in this when we withdraw caching services from the + * cookie. + */ +static void fscache_init_access_gate(struct fscache_cookie *cookie) +{ + int n_accesses; + + n_accesses = atomic_read(&cookie->n_accesses); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, fscache_access_cache_pin); + set_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags); +} + +/** + * fscache_end_cookie_access - Unpin a cache at the end of an access. + * @cookie: A data file cookie + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache cookie after we've accessed it and bring a deferred + * relinquishment or withdrawal state into effect. + * + * The @why indicator is provided for tracing purposes. + */ +void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&cookie->n_accesses); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, why); + if (n_accesses == 0 && + !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) + fscache_queue_cookie(cookie, fscache_cookie_get_end_access); +} +EXPORT_SYMBOL(fscache_end_cookie_access); + +/* + * Pin the cache behind a cookie so that we can access it. + */ +static void __fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + n_accesses = atomic_inc_return(&cookie->n_accesses); + smp_mb__after_atomic(); /* (Future) read state after is-caching. + * Reread n_accesses after is-caching + */ + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, why); +} + +/** + * fscache_begin_cookie_access - Pin a cache so data can be accessed + * @cookie: A data file cookie + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing data and returns true if successful. This works as follows: + * + * (1) If the cookie is not being cached (ie. FSCACHE_COOKIE_IS_CACHING is not + * set), we return false to indicate access was not permitted. + * + * (2) If the cookie is being cached, we increment its n_accesses count and + * then recheck the IS_CACHING flag, ending the access if it got cleared. + * + * (3) When we end the access, we decrement the cookie's n_accesses and wake + * up the any waiters if it reaches 0. + * + * (4) Whilst the cookie is actively being cached, its n_accesses is kept + * artificially incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline or if the cookie is culled, the flag is + * cleared to prevent new accesses, the cookie's n_accesses is decremented + * and we wait for it to become 0. + * + * The @why indicator are merely provided for tracing purposes. + */ +bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) + return false; + __fscache_begin_cookie_access(cookie, why); + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags) || + !fscache_cache_is_live(cookie->volume->cache)) { + fscache_end_cookie_access(cookie, fscache_access_unlive); + return false; + } + return true; +} + +static inline void wake_up_cookie_state(struct fscache_cookie *cookie) +{ + /* Use a barrier to ensure that waiters see the state variable + * change, as spin_unlock doesn't guarantee a barrier. + * + * See comments over wake_up_bit() and waitqueue_active(). + */ + smp_mb(); + wake_up_var(&cookie->state); +} + +/* + * Change the state a cookie is at and wake up anyone waiting for that. Impose + * an ordering between the stuff stored in the cookie and the state member. + * Paired with fscache_cookie_state(). + */ +static void __fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) +{ + smp_store_release(&cookie->state, state); +} + +static void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) +{ + spin_lock(&cookie->lock); + __fscache_set_cookie_state(cookie, state); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); +} + +/** + * fscache_cookie_lookup_negative - Note negative lookup + * @cookie: The cookie that was being looked up + * + * Note that some part of the metadata path in the cache doesn't exist and so + * we can release any waiting readers in the certain knowledge that there's + * nothing for them to actually read. + * + * This function uses no locking and must only be called from the state machine. + */ +void fscache_cookie_lookup_negative(struct fscache_cookie *cookie) +{ + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_CREATING); +} +EXPORT_SYMBOL(fscache_cookie_lookup_negative); + +/** + * fscache_resume_after_invalidation - Allow I/O to resume after invalidation + * @cookie: The cookie that was invalidated + * + * Tell fscache that invalidation is sufficiently complete that I/O can be + * allowed again. + */ +void fscache_resume_after_invalidation(struct fscache_cookie *cookie) +{ + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); +} +EXPORT_SYMBOL(fscache_resume_after_invalidation); + +/** + * fscache_caching_failed - Report that a failure stopped caching on a cookie + * @cookie: The cookie that was affected + * + * Tell fscache that caching on a cookie needs to be stopped due to some sort + * of failure. + * + * This function uses no locking and must only be called from the state machine. + */ +void fscache_caching_failed(struct fscache_cookie *cookie) +{ + clear_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_FAILED); +} +EXPORT_SYMBOL(fscache_caching_failed); + +/* * Set the index key in a cookie. The cookie struct has space for a 16-byte * key plus length and hash, but if that's not big enough, it's instead a * pointer to a buffer containing 3 bytes of hash, 1 byte of length and then @@ -87,38 +275,35 @@ void fscache_free_cookie(struct fscache_cookie *cookie) static int fscache_set_key(struct fscache_cookie *cookie, const void *index_key, size_t index_key_len) { - u32 *buf; - int bufs; + void *buf; + size_t buf_size; - bufs = DIV_ROUND_UP(index_key_len, sizeof(*buf)); + buf_size = round_up(index_key_len, sizeof(__le32)); if (index_key_len > sizeof(cookie->inline_key)) { - buf = kcalloc(bufs, sizeof(*buf), GFP_KERNEL); + buf = kzalloc(buf_size, GFP_KERNEL); if (!buf) return -ENOMEM; cookie->key = buf; } else { - buf = (u32 *)cookie->inline_key; + buf = cookie->inline_key; } memcpy(buf, index_key, index_key_len); - cookie->key_hash = fscache_hash(0, buf, bufs); + cookie->key_hash = fscache_hash(cookie->volume->key_hash, + buf, buf_size); return 0; } -static long fscache_compare_cookie(const struct fscache_cookie *a, - const struct fscache_cookie *b) +static bool fscache_cookie_same(const struct fscache_cookie *a, + const struct fscache_cookie *b) { const void *ka, *kb; - if (a->key_hash != b->key_hash) - return (long)a->key_hash - (long)b->key_hash; - if (a->parent != b->parent) - return (long)a->parent - (long)b->parent; - if (a->key_len != b->key_len) - return (long)a->key_len - (long)b->key_len; - if (a->type != b->type) - return (long)a->type - (long)b->type; + if (a->key_hash != b->key_hash || + a->volume != b->volume || + a->key_len != b->key_len) + return false; if (a->key_len <= sizeof(a->inline_key)) { ka = &a->inline_key; @@ -127,7 +312,7 @@ static long fscache_compare_cookie(const struct fscache_cookie *a, ka = a->key; kb = b->key; } - return memcmp(ka, kb, a->key_len); + return memcmp(ka, kb, a->key_len) == 0; } static atomic_t fscache_cookie_debug_id = ATOMIC_INIT(1); @@ -135,12 +320,11 @@ static atomic_t fscache_cookie_debug_id = ATOMIC_INIT(1); /* * Allocate a cookie. */ -struct fscache_cookie *fscache_alloc_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, +static struct fscache_cookie *fscache_alloc_cookie( + struct fscache_volume *volume, + u8 advice, const void *index_key, size_t index_key_len, const void *aux_data, size_t aux_data_len, - void *netfs_data, loff_t object_size) { struct fscache_cookie *cookie; @@ -149,9 +333,15 @@ struct fscache_cookie *fscache_alloc_cookie( cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); if (!cookie) return NULL; + fscache_stat(&fscache_n_cookies); - cookie->key_len = index_key_len; - cookie->aux_len = aux_data_len; + cookie->volume = volume; + cookie->advice = advice; + cookie->key_len = index_key_len; + cookie->aux_len = aux_data_len; + cookie->object_size = object_size; + if (object_size == 0) + __set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); if (fscache_set_key(cookie, index_key, index_key_len) < 0) goto nomem; @@ -165,30 +355,16 @@ struct fscache_cookie *fscache_alloc_cookie( } refcount_set(&cookie->ref, 1); - atomic_set(&cookie->n_children, 0); cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); - - /* We keep the active count elevated until relinquishment to prevent an - * attempt to wake up every time the object operations queue quiesces. - */ - atomic_set(&cookie->n_active, 1); - - cookie->def = def; - cookie->parent = parent; - cookie->netfs_data = netfs_data; - cookie->flags = (1 << FSCACHE_COOKIE_NO_DATA_YET); - cookie->type = def->type; spin_lock_init(&cookie->lock); - spin_lock_init(&cookie->stores_lock); - INIT_HLIST_HEAD(&cookie->backing_objects); - - /* radix tree insertion won't use the preallocation pool unless it's - * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); + INIT_LIST_HEAD(&cookie->commit_link); + INIT_WORK(&cookie->work, fscache_cookie_worker); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); write_lock(&fscache_cookies_lock); list_add_tail(&cookie->proc_link, &fscache_cookies); write_unlock(&fscache_cookies_lock); + fscache_see_cookie(cookie, fscache_cookie_new_acquire); return cookie; nomem: @@ -196,13 +372,28 @@ nomem: return NULL; } +static void fscache_wait_on_collision(struct fscache_cookie *candidate, + struct fscache_cookie *wait_for) +{ + enum fscache_cookie_state *statep = &wait_for->state; + + wait_var_event_timeout(statep, READ_ONCE(*statep) == FSCACHE_COOKIE_STATE_DROPPED, + 20 * HZ); + if (READ_ONCE(*statep) != FSCACHE_COOKIE_STATE_DROPPED) { + pr_notice("Potential collision c=%08x old: c=%08x", + candidate->debug_id, wait_for->debug_id); + wait_var_event(statep, READ_ONCE(*statep) == FSCACHE_COOKIE_STATE_DROPPED); + } +} + /* * Attempt to insert the new cookie into the hash. If there's a collision, we - * return the old cookie if it's not in use and an error otherwise. + * wait for the old cookie to complete if it's being relinquished and an error + * otherwise. */ -struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *candidate) +static bool fscache_hash_cookie(struct fscache_cookie *candidate) { - struct fscache_cookie *cursor; + struct fscache_cookie *cursor, *wait_for = NULL; struct hlist_bl_head *h; struct hlist_bl_node *p; unsigned int bucket; @@ -212,64 +403,53 @@ struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *candidate) hlist_bl_lock(h); hlist_bl_for_each_entry(cursor, p, h, hash_link) { - if (fscache_compare_cookie(candidate, cursor) == 0) - goto collision; + if (fscache_cookie_same(candidate, cursor)) { + if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cursor->flags)) + goto collision; + wait_for = fscache_get_cookie(cursor, + fscache_cookie_get_hash_collision); + break; + } } - __set_bit(FSCACHE_COOKIE_ACQUIRED, &candidate->flags); - fscache_cookie_get(candidate->parent, fscache_cookie_get_acquire_parent); - atomic_inc(&candidate->parent->n_children); + fscache_get_volume(candidate->volume, fscache_volume_get_cookie); + atomic_inc(&candidate->volume->n_cookies); hlist_bl_add_head(&candidate->hash_link, h); + set_bit(FSCACHE_COOKIE_IS_HASHED, &candidate->flags); hlist_bl_unlock(h); - return candidate; -collision: - if (test_and_set_bit(FSCACHE_COOKIE_ACQUIRED, &cursor->flags)) { - trace_fscache_cookie(cursor->debug_id, refcount_read(&cursor->ref), - fscache_cookie_collision); - pr_err("Duplicate cookie detected\n"); - fscache_print_cookie(cursor, 'O'); - fscache_print_cookie(candidate, 'N'); - hlist_bl_unlock(h); - return NULL; + if (wait_for) { + fscache_wait_on_collision(candidate, wait_for); + fscache_put_cookie(wait_for, fscache_cookie_put_hash_collision); } + return true; - fscache_cookie_get(cursor, fscache_cookie_get_reacquire); +collision: + trace_fscache_cookie(cursor->debug_id, refcount_read(&cursor->ref), + fscache_cookie_collision); + pr_err("Duplicate cookie detected\n"); + fscache_print_cookie(cursor, 'O'); + fscache_print_cookie(candidate, 'N'); hlist_bl_unlock(h); - return cursor; + return false; } /* - * request a cookie to represent an object (index, datafile, xattr, etc) - * - parent specifies the parent object - * - the top level index cookie for each netfs is stored in the fscache_netfs - * struct upon registration - * - def points to the definition - * - the netfs_data will be passed to the functions pointed to in *def - * - all attached caches will be searched to see if they contain this object - * - index objects aren't stored on disk until there's a dependent file that - * needs storing - * - other objects are stored in a selected cache immediately, and all the - * indices forming the path to it are instantiated if necessary - * - we never let on to the netfs about errors - * - we may set a negative cookie pointer, but that's okay + * Request a cookie to represent a data storage object within a volume. + * + * We never let on to the netfs about errors. We may set a negative cookie + * pointer, but that's okay */ struct fscache_cookie *__fscache_acquire_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, + struct fscache_volume *volume, + u8 advice, const void *index_key, size_t index_key_len, const void *aux_data, size_t aux_data_len, - void *netfs_data, - loff_t object_size, - bool enable) + loff_t object_size) { - struct fscache_cookie *candidate, *cookie; - - BUG_ON(!def); + struct fscache_cookie *cookie; - _enter("{%s},{%s},%p,%u", - parent ? (char *) parent->def->name : "<no-parent>", - def->name, netfs_data, enable); + _enter("V=%x", volume->debug_id); if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255) return NULL; @@ -280,563 +460,440 @@ struct fscache_cookie *__fscache_acquire_cookie( fscache_stat(&fscache_n_acquires); - /* if there's no parent cookie, then we don't create one here either */ - if (!parent) { - fscache_stat(&fscache_n_acquires_null); - _leave(" [no parent]"); - return NULL; - } - - /* validate the definition */ - BUG_ON(!def->name[0]); - - BUG_ON(def->type == FSCACHE_COOKIE_TYPE_INDEX && - parent->type != FSCACHE_COOKIE_TYPE_INDEX); - - candidate = fscache_alloc_cookie(parent, def, - index_key, index_key_len, - aux_data, aux_data_len, - netfs_data, object_size); - if (!candidate) { + cookie = fscache_alloc_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); + if (!cookie) { fscache_stat(&fscache_n_acquires_oom); - _leave(" [ENOMEM]"); return NULL; } - cookie = fscache_hash_cookie(candidate); - if (!cookie) { - trace_fscache_cookie(candidate->debug_id, 1, - fscache_cookie_discard); - goto out; - } - - if (cookie == candidate) - candidate = NULL; - - switch (cookie->type) { - case FSCACHE_COOKIE_TYPE_INDEX: - fscache_stat(&fscache_n_cookie_index); - break; - case FSCACHE_COOKIE_TYPE_DATAFILE: - fscache_stat(&fscache_n_cookie_data); - break; - default: - fscache_stat(&fscache_n_cookie_special); - break; + if (!fscache_hash_cookie(cookie)) { + fscache_see_cookie(cookie, fscache_cookie_discard); + fscache_free_cookie(cookie); + return NULL; } trace_fscache_acquire(cookie); - - if (enable) { - /* if the object is an index then we need do nothing more here - * - we create indices on disk when we need them as an index - * may exist in multiple caches */ - if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) { - if (fscache_acquire_non_index_cookie(cookie, object_size) == 0) { - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } else { - atomic_dec(&parent->n_children); - fscache_cookie_put(cookie, - fscache_cookie_put_acquire_nobufs); - fscache_stat(&fscache_n_acquires_nobufs); - _leave(" = NULL"); - return NULL; - } - } else { - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } - } - fscache_stat(&fscache_n_acquires_ok); - -out: - fscache_free_cookie(candidate); + _leave(" = c=%08x", cookie->debug_id); return cookie; } EXPORT_SYMBOL(__fscache_acquire_cookie); /* - * Enable a cookie to permit it to accept new operations. + * Prepare a cache object to be written to. */ -void __fscache_enable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - loff_t object_size, - bool (*can_enable)(void *data), - void *data) +static void fscache_prepare_to_write(struct fscache_cookie *cookie) { - _enter("%x", cookie->debug_id); - - trace_fscache_enable(cookie); - - wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - TASK_UNINTERRUPTIBLE); - - fscache_update_aux(cookie, aux_data); - - if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) - goto out_unlock; - - if (can_enable && !can_enable(data)) { - /* The netfs decided it didn't want to enable after all */ - } else if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) { - /* Wait for outstanding disablement to complete */ - __fscache_wait_on_invalidate(cookie); - - if (fscache_acquire_non_index_cookie(cookie, object_size) == 0) - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } else { - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } - -out_unlock: - clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK); + cookie->volume->cache->ops->prepare_to_write(cookie); } -EXPORT_SYMBOL(__fscache_enable_cookie); /* - * acquire a non-index cookie - * - this must make sure the index chain is instantiated and instantiate the - * object representation too + * Look up a cookie in the cache. */ -static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie, - loff_t object_size) +static void fscache_perform_lookup(struct fscache_cookie *cookie) { - struct fscache_object *object; - struct fscache_cache *cache; - int ret; + enum fscache_access_trace trace = fscache_access_lookup_cookie_end_failed; + bool need_withdraw = false; _enter(""); - set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - - /* now we need to see whether the backing objects for this cookie yet - * exist, if not there'll be nothing to search */ - down_read(&fscache_addremove_sem); - - if (list_empty(&fscache_cache_list)) { - up_read(&fscache_addremove_sem); - _leave(" = 0 [no caches]"); - return 0; - } - - /* select a cache in which to store the object */ - cache = fscache_select_cache_for_object(cookie->parent); - if (!cache) { - up_read(&fscache_addremove_sem); - fscache_stat(&fscache_n_acquires_no_cache); - _leave(" = -ENOMEDIUM [no cache]"); - return -ENOMEDIUM; - } - - _debug("cache %s", cache->tag->name); - - set_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags); - - /* ask the cache to allocate objects for this cookie and its parent - * chain */ - ret = fscache_alloc_object(cache, cookie); - if (ret < 0) { - up_read(&fscache_addremove_sem); - _leave(" = %d", ret); - return ret; - } - - spin_lock(&cookie->lock); - if (hlist_empty(&cookie->backing_objects)) { - spin_unlock(&cookie->lock); - goto unavailable; + if (!cookie->volume->cache_priv) { + fscache_create_volume(cookie->volume, true); + if (!cookie->volume->cache_priv) { + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + goto out; + } } - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - fscache_set_store_limit(object, object_size); - - /* initiate the process of looking up all the objects in the chain - * (done by fscache_initialise_object()) */ - fscache_raise_event(object, FSCACHE_OBJECT_EV_NEW_CHILD); - - spin_unlock(&cookie->lock); - - /* we may be required to wait for lookup to complete at this point */ - if (!fscache_defer_lookup) { - wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - TASK_UNINTERRUPTIBLE); - if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags)) - goto unavailable; + if (!cookie->volume->cache->ops->lookup_cookie(cookie)) { + if (cookie->state != FSCACHE_COOKIE_STATE_FAILED) + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + need_withdraw = true; + _leave(" [fail]"); + goto out; } - up_read(&fscache_addremove_sem); - _leave(" = 0 [deferred]"); - return 0; + fscache_see_cookie(cookie, fscache_cookie_see_active); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); + trace = fscache_access_lookup_cookie_end; -unavailable: - up_read(&fscache_addremove_sem); - _leave(" = -ENOBUFS"); - return -ENOBUFS; +out: + fscache_end_cookie_access(cookie, trace); + if (need_withdraw) + fscache_withdraw_cookie(cookie); + fscache_end_volume_access(cookie->volume, cookie, trace); } /* - * recursively allocate cache object records for a cookie/cache combination - * - caller must be holding the addremove sem + * Begin the process of looking up a cookie. We offload the actual process to + * a worker thread. */ -static int fscache_alloc_object(struct fscache_cache *cache, - struct fscache_cookie *cookie) +static bool fscache_begin_lookup(struct fscache_cookie *cookie, bool will_modify) { - struct fscache_object *object; - int ret; - - _enter("%s,%x{%s}", cache->tag->name, cookie->debug_id, cookie->def->name); - - spin_lock(&cookie->lock); - hlist_for_each_entry(object, &cookie->backing_objects, - cookie_link) { - if (object->cache == cache) - goto object_already_extant; + if (will_modify) { + set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); + set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); } - spin_unlock(&cookie->lock); - - /* ask the cache to allocate an object (we may end up with duplicate - * objects at this stage, but we sort that out later) */ - fscache_stat(&fscache_n_cop_alloc_object); - object = cache->ops->alloc_object(cache, cookie); - fscache_stat_d(&fscache_n_cop_alloc_object); - if (IS_ERR(object)) { - fscache_stat(&fscache_n_object_no_alloc); - ret = PTR_ERR(object); - goto error; - } - - ASSERTCMP(object->cookie, ==, cookie); - fscache_stat(&fscache_n_object_alloc); - - object->debug_id = atomic_inc_return(&fscache_object_debug_id); - - _debug("ALLOC OBJ%x: %s {%lx}", - object->debug_id, cookie->def->name, object->events); - - ret = fscache_alloc_object(cache, cookie->parent); - if (ret < 0) - goto error_put; - - /* only attach if we managed to allocate all we needed, otherwise - * discard the object we just allocated and instead use the one - * attached to the cookie */ - if (fscache_attach_object(cookie, object) < 0) { - fscache_stat(&fscache_n_cop_put_object); - cache->ops->put_object(object, fscache_obj_put_attach_fail); - fscache_stat_d(&fscache_n_cop_put_object); - } - - _leave(" = 0"); - return 0; - -object_already_extant: - ret = -ENOBUFS; - if (fscache_object_is_dying(object) || - fscache_cache_is_broken(object)) { - spin_unlock(&cookie->lock); - goto error; - } - spin_unlock(&cookie->lock); - _leave(" = 0 [found]"); - return 0; - -error_put: - fscache_stat(&fscache_n_cop_put_object); - cache->ops->put_object(object, fscache_obj_put_alloc_fail); - fscache_stat_d(&fscache_n_cop_put_object); -error: - _leave(" = %d", ret); - return ret; + if (!fscache_begin_volume_access(cookie->volume, cookie, + fscache_access_lookup_cookie)) + return false; + + __fscache_begin_cookie_access(cookie, fscache_access_lookup_cookie); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LOOKING_UP); + set_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); + set_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags); + return true; } /* - * attach a cache object to a cookie + * Start using the cookie for I/O. This prevents the backing object from being + * reaped by VM pressure. */ -static int fscache_attach_object(struct fscache_cookie *cookie, - struct fscache_object *object) +void __fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify) { - struct fscache_object *p; - struct fscache_cache *cache = object->cache; - int ret; + enum fscache_cookie_state state; + bool queue = false; + int n_active; - _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); + _enter("c=%08x", cookie->debug_id); - ASSERTCMP(object->cookie, ==, cookie); + if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Trying to use relinquished cookie\n")) + return; spin_lock(&cookie->lock); - /* there may be multiple initial creations of this object, but we only - * want one */ - ret = -EEXIST; - hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) { - if (p->cache == object->cache) { - if (fscache_object_is_dying(p)) - ret = -ENOBUFS; - goto cant_attach_object; - } - } + n_active = atomic_inc_return(&cookie->n_active); + trace_fscache_active(cookie->debug_id, refcount_read(&cookie->ref), + n_active, atomic_read(&cookie->n_accesses), + will_modify ? + fscache_active_use_modify : fscache_active_use); + +again: + state = fscache_cookie_state(cookie); + switch (state) { + case FSCACHE_COOKIE_STATE_QUIESCENT: + queue = fscache_begin_lookup(cookie, will_modify); + break; - /* pin the parent object */ - spin_lock_nested(&cookie->parent->lock, 1); - hlist_for_each_entry(p, &cookie->parent->backing_objects, - cookie_link) { - if (p->cache == object->cache) { - if (fscache_object_is_dying(p)) { - ret = -ENOBUFS; - spin_unlock(&cookie->parent->lock); - goto cant_attach_object; - } - object->parent = p; - spin_lock(&p->lock); - p->n_children++; - spin_unlock(&p->lock); - break; + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_CREATING: + if (will_modify) + set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); + break; + case FSCACHE_COOKIE_STATE_ACTIVE: + case FSCACHE_COOKIE_STATE_INVALIDATING: + if (will_modify && + !test_and_set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags)) { + set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + queue = true; } - } - spin_unlock(&cookie->parent->lock); - - /* attach to the cache's object list */ - if (list_empty(&object->cache_link)) { - spin_lock(&cache->object_list_lock); - list_add(&object->cache_link, &cache->object_list); - spin_unlock(&cache->object_list_lock); - } - - /* Attach to the cookie. The object already has a ref on it. */ - hlist_add_head(&object->cookie_link, &cookie->backing_objects); - ret = 0; - -cant_attach_object: - spin_unlock(&cookie->lock); - _leave(" = %d", ret); - return ret; -} - -/* - * Invalidate an object. Callable with spinlocks held. - */ -void __fscache_invalidate(struct fscache_cookie *cookie) -{ - struct fscache_object *object; - - _enter("{%s}", cookie->def->name); - - fscache_stat(&fscache_n_invalidates); + break; - /* Only permit invalidation of data files. Invalidating an index will - * require the caller to release all its attachments to the tree rooted - * there, and if it's doing that, it may as well just retire the - * cookie. - */ - ASSERTCMP(cookie->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE); + case FSCACHE_COOKIE_STATE_FAILED: + case FSCACHE_COOKIE_STATE_WITHDRAWING: + break; - /* If there's an object, we tell the object state machine to handle the - * invalidation on our behalf, otherwise there's nothing to do. - */ - if (!hlist_empty(&cookie->backing_objects)) { + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + spin_unlock(&cookie->lock); + wait_var_event(&cookie->state, + fscache_cookie_state(cookie) != + FSCACHE_COOKIE_STATE_LRU_DISCARDING); spin_lock(&cookie->lock); + goto again; - if (fscache_cookie_enabled(cookie) && - !hlist_empty(&cookie->backing_objects) && - !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING, - &cookie->flags)) { - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, - cookie_link); - if (fscache_object_is_live(object)) - fscache_raise_event( - object, FSCACHE_OBJECT_EV_INVALIDATE); - } - - spin_unlock(&cookie->lock); + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + WARN(1, "Can't use cookie in state %u\n", state); + break; } + spin_unlock(&cookie->lock); + if (queue) + fscache_queue_cookie(cookie, fscache_cookie_get_use_work); _leave(""); } -EXPORT_SYMBOL(__fscache_invalidate); +EXPORT_SYMBOL(__fscache_use_cookie); -/* - * Wait for object invalidation to complete. - */ -void __fscache_wait_on_invalidate(struct fscache_cookie *cookie) +static void fscache_unuse_cookie_locked(struct fscache_cookie *cookie) { - _enter("%x", cookie->debug_id); + clear_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags); + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) + return; - wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING, - TASK_UNINTERRUPTIBLE); + cookie->unused_at = jiffies; + spin_lock(&fscache_cookie_lru_lock); + if (list_empty(&cookie->commit_link)) { + fscache_get_cookie(cookie, fscache_cookie_get_lru); + fscache_stat(&fscache_n_cookies_lru); + } + list_move_tail(&cookie->commit_link, &fscache_cookie_lru); - _leave(""); + spin_unlock(&fscache_cookie_lru_lock); + timer_reduce(&fscache_cookie_lru_timer, + jiffies + fscache_lru_cookie_timeout); } -EXPORT_SYMBOL(__fscache_wait_on_invalidate); /* - * update the index entries backing a cookie + * Stop using the cookie for I/O. */ -void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) +void __fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) { - struct fscache_object *object; - - fscache_stat(&fscache_n_updates); - - if (!cookie) { - fscache_stat(&fscache_n_updates_null); - _leave(" [no cookie]"); + unsigned int debug_id = cookie->debug_id; + unsigned int r = refcount_read(&cookie->ref); + unsigned int a = atomic_read(&cookie->n_accesses); + unsigned int c; + + if (aux_data || object_size) + __fscache_update_cookie(cookie, aux_data, object_size); + + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + c = atomic_fetch_add_unless(&cookie->n_active, -1, 1); + if (c != 1) { + trace_fscache_active(debug_id, r, c - 1, a, fscache_active_unuse); return; } - _enter("{%s}", cookie->def->name); - spin_lock(&cookie->lock); - - fscache_update_aux(cookie, aux_data); - - if (fscache_cookie_enabled(cookie)) { - /* update the index entry on disk in each cache backing this - * cookie. - */ - hlist_for_each_entry(object, - &cookie->backing_objects, cookie_link) { - fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE); - } - } - + r = refcount_read(&cookie->ref); + a = atomic_read(&cookie->n_accesses); + c = atomic_dec_return(&cookie->n_active); + trace_fscache_active(debug_id, r, c, a, fscache_active_unuse); + if (c == 0) + fscache_unuse_cookie_locked(cookie); spin_unlock(&cookie->lock); - _leave(""); } -EXPORT_SYMBOL(__fscache_update_cookie); +EXPORT_SYMBOL(__fscache_unuse_cookie); /* - * Disable a cookie to stop it from accepting new requests from the netfs. + * Perform work upon the cookie, such as committing its cache state, + * relinquishing it or withdrawing the backing cache. We're protected from the + * cache going away under us as object withdrawal must come through this + * non-reentrant work item. */ -void __fscache_disable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool invalidate) +static void fscache_cookie_state_machine(struct fscache_cookie *cookie) { - struct fscache_object *object; - bool awaken = false; + enum fscache_cookie_state state; + bool wake = false; - _enter("%x,%u", cookie->debug_id, invalidate); + _enter("c=%x", cookie->debug_id); - trace_fscache_disable(cookie); - - ASSERTCMP(atomic_read(&cookie->n_active), >, 0); - - if (atomic_read(&cookie->n_children) != 0) { - pr_err("Cookie '%s' still has children\n", - cookie->def->name); - BUG(); - } +again: + spin_lock(&cookie->lock); +again_locked: + state = cookie->state; + switch (state) { + case FSCACHE_COOKIE_STATE_QUIESCENT: + /* The QUIESCENT state is jumped to the LOOKING_UP state by + * fscache_use_cookie(). + */ - wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - TASK_UNINTERRUPTIBLE); + if (atomic_read(&cookie->n_accesses) == 0 && + test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_RELINQUISHING); + wake = true; + goto again_locked; + } + break; - fscache_update_aux(cookie, aux_data); + case FSCACHE_COOKIE_STATE_LOOKING_UP: + spin_unlock(&cookie->lock); + fscache_init_access_gate(cookie); + fscache_perform_lookup(cookie); + goto again; - if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) - goto out_unlock_enable; + case FSCACHE_COOKIE_STATE_INVALIDATING: + spin_unlock(&cookie->lock); + fscache_perform_invalidation(cookie); + goto again; + + case FSCACHE_COOKIE_STATE_ACTIVE: + if (test_and_clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags)) { + spin_unlock(&cookie->lock); + fscache_prepare_to_write(cookie); + spin_lock(&cookie->lock); + } + if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_LRU_DISCARDING); + wake = true; + goto again_locked; + } + fallthrough; - /* If the cookie is being invalidated, wait for that to complete first - * so that we can reuse the flag. - */ - __fscache_wait_on_invalidate(cookie); + case FSCACHE_COOKIE_STATE_FAILED: + if (atomic_read(&cookie->n_accesses) != 0) + break; + if (test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_RELINQUISHING); + wake = true; + goto again_locked; + } + if (test_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_WITHDRAWING); + wake = true; + goto again_locked; + } + break; - /* Dispose of the backing objects */ - set_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags); + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + case FSCACHE_COOKIE_STATE_WITHDRAWING: + if (cookie->cache_priv) { + spin_unlock(&cookie->lock); + cookie->volume->cache->ops->withdraw_cookie(cookie); + spin_lock(&cookie->lock); + } - spin_lock(&cookie->lock); - if (!hlist_empty(&cookie->backing_objects)) { - hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { - if (invalidate) - set_bit(FSCACHE_OBJECT_RETIRED, &object->flags); - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL); + switch (state) { + case FSCACHE_COOKIE_STATE_RELINQUISHING: + fscache_see_cookie(cookie, fscache_cookie_see_relinquish); + fscache_unhash_cookie(cookie); + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_DROPPED); + wake = true; + goto out; + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + fscache_see_cookie(cookie, fscache_cookie_see_lru_discard); + break; + case FSCACHE_COOKIE_STATE_WITHDRAWING: + fscache_see_cookie(cookie, fscache_cookie_see_withdraw); + break; + default: + BUG(); } - } else { - if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) - awaken = true; - } - spin_unlock(&cookie->lock); - if (awaken) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); - /* Wait for cessation of activity requiring access to the netfs (when - * n_active reaches 0). This makes sure outstanding reads and writes - * have completed. - */ - if (!atomic_dec_and_test(&cookie->n_active)) { - wait_var_event(&cookie->n_active, - !atomic_read(&cookie->n_active)); - } + clear_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + wake = true; + goto again_locked; - /* Make sure any pending writes are cancelled. */ - if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) - fscache_invalidate_writes(cookie); + case FSCACHE_COOKIE_STATE_DROPPED: + break; - /* Reset the cookie state if it wasn't relinquished */ - if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) { - atomic_inc(&cookie->n_active); - set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); + default: + WARN_ONCE(1, "Cookie %x in unexpected state %u\n", + cookie->debug_id, state); + break; } -out_unlock_enable: - clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK); +out: + spin_unlock(&cookie->lock); + if (wake) + wake_up_cookie_state(cookie); _leave(""); } -EXPORT_SYMBOL(__fscache_disable_cookie); + +static void fscache_cookie_worker(struct work_struct *work) +{ + struct fscache_cookie *cookie = container_of(work, struct fscache_cookie, work); + + fscache_see_cookie(cookie, fscache_cookie_see_work); + fscache_cookie_state_machine(cookie); + fscache_put_cookie(cookie, fscache_cookie_put_work); +} /* - * release a cookie back to the cache - * - the object will be marked as recyclable on disk if retire is true - * - all dependents of this cookie must have already been unregistered - * (indices/files/pages) + * Wait for the object to become inactive. The cookie's work item will be + * scheduled when someone transitions n_accesses to 0 - but if someone's + * already done that, schedule it anyway. */ -void __fscache_relinquish_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool retire) +static void __fscache_withdraw_cookie(struct fscache_cookie *cookie) { - fscache_stat(&fscache_n_relinquishes); - if (retire) - fscache_stat(&fscache_n_relinquishes_retire); + int n_accesses; + bool unpinned; + + unpinned = test_and_clear_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags); + + /* Need to read the access count after unpinning */ + n_accesses = atomic_read(&cookie->n_accesses); + if (unpinned) + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, fscache_access_cache_unpin); + if (n_accesses == 0) + fscache_queue_cookie(cookie, fscache_cookie_get_end_access); +} - if (!cookie) { - fscache_stat(&fscache_n_relinquishes_null); - _leave(" [no cookie]"); - return; - } +static void fscache_cookie_lru_do_one(struct fscache_cookie *cookie) +{ + fscache_see_cookie(cookie, fscache_cookie_see_lru_do_one); - _enter("%x{%s,%d},%d", - cookie->debug_id, cookie->def->name, - atomic_read(&cookie->n_active), retire); + spin_lock(&cookie->lock); + if (cookie->state != FSCACHE_COOKIE_STATE_ACTIVE || + time_before(jiffies, cookie->unused_at + fscache_lru_cookie_timeout) || + atomic_read(&cookie->n_active) > 0) { + spin_unlock(&cookie->lock); + fscache_stat(&fscache_n_cookies_lru_removed); + } else { + set_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags); + spin_unlock(&cookie->lock); + fscache_stat(&fscache_n_cookies_lru_expired); + _debug("lru c=%x", cookie->debug_id); + __fscache_withdraw_cookie(cookie); + } - trace_fscache_relinquish(cookie, retire); + fscache_put_cookie(cookie, fscache_cookie_put_lru); +} - /* No further netfs-accessing operations on this cookie permitted */ - if (test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) - BUG(); +static void fscache_cookie_lru_worker(struct work_struct *work) +{ + struct fscache_cookie *cookie; + unsigned long unused_at; - __fscache_disable_cookie(cookie, aux_data, retire); + spin_lock(&fscache_cookie_lru_lock); - /* Clear pointers back to the netfs */ - cookie->netfs_data = NULL; - cookie->def = NULL; - BUG_ON(!radix_tree_empty(&cookie->stores)); + while (!list_empty(&fscache_cookie_lru)) { + cookie = list_first_entry(&fscache_cookie_lru, + struct fscache_cookie, commit_link); + unused_at = cookie->unused_at + fscache_lru_cookie_timeout; + if (time_before(jiffies, unused_at)) { + timer_reduce(&fscache_cookie_lru_timer, unused_at); + break; + } - if (cookie->parent) { - ASSERTCMP(refcount_read(&cookie->parent->ref), >, 0); - ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0); - atomic_dec(&cookie->parent->n_children); + list_del_init(&cookie->commit_link); + fscache_stat_d(&fscache_n_cookies_lru); + spin_unlock(&fscache_cookie_lru_lock); + fscache_cookie_lru_do_one(cookie); + spin_lock(&fscache_cookie_lru_lock); } - /* Dispose of the netfs's link to the cookie */ - fscache_cookie_put(cookie, fscache_cookie_put_relinquish); + spin_unlock(&fscache_cookie_lru_lock); +} - _leave(""); +static void fscache_cookie_lru_timed_out(struct timer_list *timer) +{ + queue_work(fscache_wq, &fscache_cookie_lru_work); +} + +static void fscache_cookie_drop_from_lru(struct fscache_cookie *cookie) +{ + bool need_put = false; + + if (!list_empty(&cookie->commit_link)) { + spin_lock(&fscache_cookie_lru_lock); + if (!list_empty(&cookie->commit_link)) { + list_del_init(&cookie->commit_link); + fscache_stat_d(&fscache_n_cookies_lru); + fscache_stat(&fscache_n_cookies_lru_dropped); + need_put = true; + } + spin_unlock(&fscache_cookie_lru_lock); + if (need_put) + fscache_put_cookie(cookie, fscache_cookie_put_lru); + } } -EXPORT_SYMBOL(__fscache_relinquish_cookie); /* * Remove a cookie from the hash table. @@ -851,43 +908,91 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie) hlist_bl_lock(h); hlist_bl_del(&cookie->hash_link); + clear_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags); hlist_bl_unlock(h); + fscache_stat(&fscache_n_relinquishes_dropped); } +static void fscache_drop_withdraw_cookie(struct fscache_cookie *cookie) +{ + fscache_cookie_drop_from_lru(cookie); + __fscache_withdraw_cookie(cookie); +} + +/** + * fscache_withdraw_cookie - Mark a cookie for withdrawal + * @cookie: The cookie to be withdrawn. + * + * Allow the cache backend to withdraw the backing for a cookie for its own + * reasons, even if that cookie is in active use. + */ +void fscache_withdraw_cookie(struct fscache_cookie *cookie) +{ + set_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags); + fscache_drop_withdraw_cookie(cookie); +} +EXPORT_SYMBOL(fscache_withdraw_cookie); + /* - * Drop a reference to a cookie. + * Allow the netfs to release a cookie back to the cache. + * - the object will be marked as recyclable on disk if retire is true */ -void fscache_cookie_put(struct fscache_cookie *cookie, - enum fscache_cookie_trace where) +void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) { - struct fscache_cookie *parent; - int ref; + fscache_stat(&fscache_n_relinquishes); + if (retire) + fscache_stat(&fscache_n_relinquishes_retire); + + _enter("c=%08x{%d},%d", + cookie->debug_id, atomic_read(&cookie->n_active), retire); - _enter("%x", cookie->debug_id); + if (WARN(test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Cookie c=%x already relinquished\n", cookie->debug_id)) + return; - do { - unsigned int cookie_debug_id = cookie->debug_id; - bool zero = __refcount_dec_and_test(&cookie->ref, &ref); + if (retire) + set_bit(FSCACHE_COOKIE_RETIRED, &cookie->flags); + trace_fscache_relinquish(cookie, retire); - trace_fscache_cookie(cookie_debug_id, ref - 1, where); - if (!zero) - return; + ASSERTCMP(atomic_read(&cookie->n_active), ==, 0); + ASSERTCMP(atomic_read(&cookie->volume->n_cookies), >, 0); + atomic_dec(&cookie->volume->n_cookies); - parent = cookie->parent; + if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) { + set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); + fscache_drop_withdraw_cookie(cookie); + } else { + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); fscache_unhash_cookie(cookie); - fscache_free_cookie(cookie); + } + fscache_put_cookie(cookie, fscache_cookie_put_relinquish); +} +EXPORT_SYMBOL(__fscache_relinquish_cookie); - cookie = parent; - where = fscache_cookie_put_parent; - } while (cookie); +/* + * Drop a reference to a cookie. + */ +void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + struct fscache_volume *volume = cookie->volume; + unsigned int cookie_debug_id = cookie->debug_id; + bool zero; + int ref; - _leave(""); + zero = __refcount_dec_and_test(&cookie->ref, &ref); + trace_fscache_cookie(cookie_debug_id, ref - 1, where); + if (zero) { + fscache_free_cookie(cookie); + fscache_put_volume(volume, fscache_volume_put_cookie); + } } +EXPORT_SYMBOL(fscache_put_cookie); /* * Get a reference to a cookie. */ -struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *cookie, +struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where) { int ref; @@ -896,85 +1001,73 @@ struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *cookie, trace_fscache_cookie(cookie->debug_id, ref + 1, where); return cookie; } +EXPORT_SYMBOL(fscache_get_cookie); /* - * check the consistency between the netfs inode and the backing cache - * - * NOTE: it only serves no-index type + * Ask the cache to effect invalidation of a cookie. */ -int __fscache_check_consistency(struct fscache_cookie *cookie, - const void *aux_data) +static void fscache_perform_invalidation(struct fscache_cookie *cookie) { - struct fscache_operation *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,", cookie); + if (!cookie->volume->cache->ops->invalidate_cookie(cookie)) + fscache_caching_failed(cookie); + fscache_end_cookie_access(cookie, fscache_access_invalidate_cookie_end); +} - ASSERTCMP(cookie->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE); +/* + * Invalidate an object. + */ +void __fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t new_size, + unsigned int flags) +{ + bool is_caching; - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; + _enter("c=%x", cookie->debug_id); - if (hlist_empty(&cookie->backing_objects)) - return 0; + fscache_stat(&fscache_n_invalidates); - op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!op) - return -ENOMEM; + if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Trying to invalidate relinquished cookie\n")) + return; - fscache_operation_init(cookie, op, NULL, NULL, NULL); - op->flags = FSCACHE_OP_MYTHREAD | - (1 << FSCACHE_OP_WAITING) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - trace_fscache_page_op(cookie, NULL, op, fscache_page_op_check_consistency); + if ((flags & FSCACHE_INVAL_DIO_WRITE) && + test_and_set_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) + return; spin_lock(&cookie->lock); + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + fscache_update_aux(cookie, aux_data, &new_size); + cookie->inval_counter++; + trace_fscache_invalidate(cookie, new_size); - fscache_update_aux(cookie, aux_data); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto inconsistent; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - if (test_bit(FSCACHE_IOERROR, &object->cache->flags)) - goto inconsistent; - - op->debug_id = atomic_inc_return(&fscache_op_debug_id); + switch (cookie->state) { + case FSCACHE_COOKIE_STATE_INVALIDATING: /* is_still_valid will catch it */ + default: + spin_unlock(&cookie->lock); + _leave(" [no %u]", cookie->state); + return; - __fscache_use_cookie(cookie); - if (fscache_submit_op(object, op) < 0) - goto submit_failed; + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_CREATING: + spin_unlock(&cookie->lock); + _leave(" [look %x]", cookie->inval_counter); + return; - /* the work queue now carries its own ref on the object */ - spin_unlock(&cookie->lock); + case FSCACHE_COOKIE_STATE_ACTIVE: + is_caching = fscache_begin_cookie_access( + cookie, fscache_access_invalidate_cookie); + if (is_caching) + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_INVALIDATING); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); - ret = fscache_wait_for_operation_activation(object, op, NULL, NULL); - if (ret == 0) { - /* ask the cache to honour the operation */ - ret = object->cache->ops->check_consistency(op); - fscache_op_complete(op, false); - } else if (ret == -ENOBUFS) { - ret = 0; + if (is_caching) + fscache_queue_cookie(cookie, fscache_cookie_get_inval_work); + _leave(" [inv]"); + return; } - - fscache_put_operation(op); - _leave(" = %d", ret); - return ret; - -submit_failed: - wake_cookie = __fscache_unuse_cookie(cookie); -inconsistent: - spin_unlock(&cookie->lock); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - kfree(op); - _leave(" = -ESTALE"); - return -ESTALE; } -EXPORT_SYMBOL(__fscache_check_consistency); +EXPORT_SYMBOL(__fscache_invalidate); /* * Generate a list of extant cookies in /proc/fs/fscache/cookies @@ -983,44 +1076,27 @@ static int fscache_cookies_seq_show(struct seq_file *m, void *v) { struct fscache_cookie *cookie; unsigned int keylen = 0, auxlen = 0; - char _type[3], *type; u8 *p; if (v == &fscache_cookies) { seq_puts(m, - "COOKIE PARENT USAGE CHILD ACT TY FL DEF NETFS_DATA\n" - "======== ======== ===== ===== === == === ================ ==========\n" + "COOKIE VOLUME REF ACT ACC S FL DEF \n" + "======== ======== === === === = == ================\n" ); return 0; } cookie = list_entry(v, struct fscache_cookie, proc_link); - switch (cookie->type) { - case 0: - type = "IX"; - break; - case 1: - type = "DT"; - break; - default: - snprintf(_type, sizeof(_type), "%02u", - cookie->type); - type = _type; - break; - } - seq_printf(m, - "%08x %08x %5u %5u %3u %s %03lx %-16s %px", + "%08x %08x %3d %3d %3d %c %02lx", cookie->debug_id, - cookie->parent ? cookie->parent->debug_id : 0, + cookie->volume->debug_id, refcount_read(&cookie->ref), - atomic_read(&cookie->n_children), atomic_read(&cookie->n_active), - type, - cookie->flags, - cookie->def->name, - cookie->netfs_data); + atomic_read(&cookie->n_accesses), + fscache_cookie_states[cookie->state], + cookie->flags); keylen = cookie->key_len; auxlen = cookie->aux_len; diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c deleted file mode 100644 index 0402673c680e..000000000000 --- a/fs/fscache/fsdef.c +++ /dev/null @@ -1,98 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Filesystem index definition - * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL CACHE -#include <linux/module.h> -#include "internal.h" - -static -enum fscache_checkaux fscache_fsdef_netfs_check_aux(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size); - -/* - * The root index is owned by FS-Cache itself. - * - * When a netfs requests caching facilities, FS-Cache will, if one doesn't - * already exist, create an entry in the root index with the key being the name - * of the netfs ("AFS" for example), and the auxiliary data holding the index - * structure version supplied by the netfs: - * - * FSDEF - * | - * +-----------+ - * | | - * NFS AFS - * [v=1] [v=1] - * - * If an entry with the appropriate name does already exist, the version is - * compared. If the version is different, the entire subtree from that entry - * will be discarded and a new entry created. - * - * The new entry will be an index, and a cookie referring to it will be passed - * to the netfs. This is then the root handle by which the netfs accesses the - * cache. It can create whatever objects it likes in that index, including - * further indices. - */ -static struct fscache_cookie_def fscache_fsdef_index_def = { - .name = ".FS-Cache", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -struct fscache_cookie fscache_fsdef_index = { - .debug_id = 1, - .ref = REFCOUNT_INIT(1), - .n_active = ATOMIC_INIT(1), - .lock = __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock), - .backing_objects = HLIST_HEAD_INIT, - .def = &fscache_fsdef_index_def, - .flags = 1 << FSCACHE_COOKIE_ENABLED, - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; -EXPORT_SYMBOL(fscache_fsdef_index); - -/* - * Definition of an entry in the root index. Each entry is an index, keyed to - * a specific netfs and only applicable to a particular version of the index - * structure used by that netfs. - */ -struct fscache_cookie_def fscache_fsdef_netfs_def = { - .name = "FSDEF.netfs", - .type = FSCACHE_COOKIE_TYPE_INDEX, - .check_aux = fscache_fsdef_netfs_check_aux, -}; - -/* - * check that the index structure version number stored in the auxiliary data - * matches the one the netfs gave us - */ -static enum fscache_checkaux fscache_fsdef_netfs_check_aux( - void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size) -{ - struct fscache_netfs *netfs = cookie_netfs_data; - uint32_t version; - - _enter("{%s},,%hu", netfs->name, datalen); - - if (datalen != sizeof(version)) { - _leave(" = OBSOLETE [dl=%d v=%zu]", datalen, sizeof(version)); - return FSCACHE_CHECKAUX_OBSOLETE; - } - - memcpy(&version, data, sizeof(version)); - if (version != netfs->version) { - _leave(" = OBSOLETE [ver=%x net=%x]", version, netfs->version); - return FSCACHE_CHECKAUX_OBSOLETE; - } - - _leave(" = OKAY"); - return FSCACHE_CHECKAUX_OKAY; -} diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index c3e4804b8fcb..f121c21590dc 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -1,65 +1,69 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Internal definitions for FS-Cache * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ -/* - * Lock order, in the order in which multiple locks should be obtained: - * - fscache_addremove_sem - * - cookie->lock - * - cookie->parent->lock - * - cache->object_list_lock - * - object->lock - * - object->parent->lock - * - cookie->stores_lock - * - fscache_thread_lock - * - */ - #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) "FS-Cache: " fmt +#include <linux/slab.h> #include <linux/fscache-cache.h> #include <trace/events/fscache.h> #include <linux/sched.h> #include <linux/seq_file.h> -#define FSCACHE_MIN_THREADS 4 -#define FSCACHE_MAX_THREADS 32 - /* * cache.c */ -extern struct list_head fscache_cache_list; -extern struct rw_semaphore fscache_addremove_sem; +#ifdef CONFIG_PROC_FS +extern const struct seq_operations fscache_caches_seq_ops; +#endif +bool fscache_begin_cache_access(struct fscache_cache *cache, enum fscache_access_trace why); +void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_trace why); +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache); +void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where); + +static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache) +{ + return smp_load_acquire(&cache->state); +} + +static inline bool fscache_cache_is_live(const struct fscache_cache *cache) +{ + return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE; +} -extern struct fscache_cache *fscache_select_cache_for_object( - struct fscache_cookie *); +static inline void fscache_set_cache_state(struct fscache_cache *cache, + enum fscache_cache_state new_state) +{ + smp_store_release(&cache->state, new_state); + +} + +static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, + enum fscache_cache_state old_state, + enum fscache_cache_state new_state) +{ + return try_cmpxchg_release(&cache->state, &old_state, new_state); +} /* * cookie.c */ extern struct kmem_cache *fscache_cookie_jar; extern const struct seq_operations fscache_cookies_seq_ops; +extern struct timer_list fscache_cookie_lru_timer; + +extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); +extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); -extern void fscache_free_cookie(struct fscache_cookie *); -extern struct fscache_cookie *fscache_alloc_cookie(struct fscache_cookie *, - const struct fscache_cookie_def *, - const void *, size_t, - const void *, size_t, - void *, loff_t); -extern struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *); -extern struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *, - enum fscache_cookie_trace); -extern void fscache_cookie_put(struct fscache_cookie *, - enum fscache_cookie_trace); - -static inline void fscache_cookie_see(struct fscache_cookie *cookie, +static inline void fscache_see_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where) { trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), @@ -67,60 +71,22 @@ static inline void fscache_cookie_see(struct fscache_cookie *cookie, } /* - * fsdef.c + * io.c */ -extern struct fscache_cookie fscache_fsdef_index; -extern struct fscache_cookie_def fscache_fsdef_netfs_def; - -/* - * main.c - */ -extern unsigned fscache_defer_lookup; -extern unsigned fscache_defer_create; -extern unsigned fscache_debug; -extern struct kobject *fscache_root; -extern struct workqueue_struct *fscache_object_wq; -extern struct workqueue_struct *fscache_op_wq; -DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); - -extern unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n); - -static inline bool fscache_object_congested(void) +static inline void fscache_end_operation(struct netfs_cache_resources *cres) { - return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); } /* - * object.c + * main.c */ -extern void fscache_enqueue_object(struct fscache_object *); +extern unsigned fscache_debug; -/* - * operation.c - */ -extern int fscache_submit_exclusive_op(struct fscache_object *, - struct fscache_operation *); -extern int fscache_submit_op(struct fscache_object *, - struct fscache_operation *); -extern int fscache_cancel_op(struct fscache_operation *, bool); -extern void fscache_cancel_all_ops(struct fscache_object *); -extern void fscache_abort_object(struct fscache_object *); -extern void fscache_start_operations(struct fscache_object *); -extern void fscache_operation_gc(struct work_struct *); - -/* - * page.c - */ -extern int fscache_wait_for_deferred_lookup(struct fscache_cookie *); -extern int fscache_wait_for_operation_activation(struct fscache_object *, - struct fscache_operation *, - atomic_t *, - atomic_t *); -extern void fscache_invalidate_writes(struct fscache_cookie *); -struct fscache_retrieval *fscache_alloc_retrieval(struct fscache_cookie *cookie, - struct address_space *mapping, - fscache_rw_complete_t end_io_func, - void *context); +extern unsigned int fscache_hash(unsigned int salt, const void *data, size_t len); /* * proc.c @@ -137,125 +103,27 @@ extern void fscache_proc_cleanup(void); * stats.c */ #ifdef CONFIG_FSCACHE_STATS -extern atomic_t fscache_n_ops_processed[FSCACHE_MAX_THREADS]; -extern atomic_t fscache_n_objs_processed[FSCACHE_MAX_THREADS]; - -extern atomic_t fscache_n_op_pend; -extern atomic_t fscache_n_op_run; -extern atomic_t fscache_n_op_enqueue; -extern atomic_t fscache_n_op_deferred_release; -extern atomic_t fscache_n_op_initialised; -extern atomic_t fscache_n_op_release; -extern atomic_t fscache_n_op_gc; -extern atomic_t fscache_n_op_cancelled; -extern atomic_t fscache_n_op_rejected; - -extern atomic_t fscache_n_attr_changed; -extern atomic_t fscache_n_attr_changed_ok; -extern atomic_t fscache_n_attr_changed_nobufs; -extern atomic_t fscache_n_attr_changed_nomem; -extern atomic_t fscache_n_attr_changed_calls; - -extern atomic_t fscache_n_allocs; -extern atomic_t fscache_n_allocs_ok; -extern atomic_t fscache_n_allocs_wait; -extern atomic_t fscache_n_allocs_nobufs; -extern atomic_t fscache_n_allocs_intr; -extern atomic_t fscache_n_allocs_object_dead; -extern atomic_t fscache_n_alloc_ops; -extern atomic_t fscache_n_alloc_op_waits; - -extern atomic_t fscache_n_retrievals; -extern atomic_t fscache_n_retrievals_ok; -extern atomic_t fscache_n_retrievals_wait; -extern atomic_t fscache_n_retrievals_nodata; -extern atomic_t fscache_n_retrievals_nobufs; -extern atomic_t fscache_n_retrievals_intr; -extern atomic_t fscache_n_retrievals_nomem; -extern atomic_t fscache_n_retrievals_object_dead; -extern atomic_t fscache_n_retrieval_ops; -extern atomic_t fscache_n_retrieval_op_waits; - -extern atomic_t fscache_n_stores; -extern atomic_t fscache_n_stores_ok; -extern atomic_t fscache_n_stores_again; -extern atomic_t fscache_n_stores_nobufs; -extern atomic_t fscache_n_stores_oom; -extern atomic_t fscache_n_store_ops; -extern atomic_t fscache_n_store_calls; -extern atomic_t fscache_n_store_pages; -extern atomic_t fscache_n_store_radix_deletes; -extern atomic_t fscache_n_store_pages_over_limit; - -extern atomic_t fscache_n_store_vmscan_not_storing; -extern atomic_t fscache_n_store_vmscan_gone; -extern atomic_t fscache_n_store_vmscan_busy; -extern atomic_t fscache_n_store_vmscan_cancelled; -extern atomic_t fscache_n_store_vmscan_wait; - -extern atomic_t fscache_n_marks; -extern atomic_t fscache_n_uncaches; +extern atomic_t fscache_n_volumes; +extern atomic_t fscache_n_volumes_collision; +extern atomic_t fscache_n_volumes_nomem; +extern atomic_t fscache_n_cookies; +extern atomic_t fscache_n_cookies_lru; +extern atomic_t fscache_n_cookies_lru_expired; +extern atomic_t fscache_n_cookies_lru_removed; +extern atomic_t fscache_n_cookies_lru_dropped; extern atomic_t fscache_n_acquires; -extern atomic_t fscache_n_acquires_null; -extern atomic_t fscache_n_acquires_no_cache; extern atomic_t fscache_n_acquires_ok; -extern atomic_t fscache_n_acquires_nobufs; extern atomic_t fscache_n_acquires_oom; extern atomic_t fscache_n_invalidates; -extern atomic_t fscache_n_invalidates_run; - -extern atomic_t fscache_n_updates; -extern atomic_t fscache_n_updates_null; -extern atomic_t fscache_n_updates_run; extern atomic_t fscache_n_relinquishes; -extern atomic_t fscache_n_relinquishes_null; -extern atomic_t fscache_n_relinquishes_waitcrt; extern atomic_t fscache_n_relinquishes_retire; +extern atomic_t fscache_n_relinquishes_dropped; -extern atomic_t fscache_n_cookie_index; -extern atomic_t fscache_n_cookie_data; -extern atomic_t fscache_n_cookie_special; - -extern atomic_t fscache_n_object_alloc; -extern atomic_t fscache_n_object_no_alloc; -extern atomic_t fscache_n_object_lookups; -extern atomic_t fscache_n_object_lookups_negative; -extern atomic_t fscache_n_object_lookups_positive; -extern atomic_t fscache_n_object_lookups_timed_out; -extern atomic_t fscache_n_object_created; -extern atomic_t fscache_n_object_avail; -extern atomic_t fscache_n_object_dead; - -extern atomic_t fscache_n_checkaux_none; -extern atomic_t fscache_n_checkaux_okay; -extern atomic_t fscache_n_checkaux_update; -extern atomic_t fscache_n_checkaux_obsolete; - -extern atomic_t fscache_n_cop_alloc_object; -extern atomic_t fscache_n_cop_lookup_object; -extern atomic_t fscache_n_cop_lookup_complete; -extern atomic_t fscache_n_cop_grab_object; -extern atomic_t fscache_n_cop_invalidate_object; -extern atomic_t fscache_n_cop_update_object; -extern atomic_t fscache_n_cop_drop_object; -extern atomic_t fscache_n_cop_put_object; -extern atomic_t fscache_n_cop_sync_cache; -extern atomic_t fscache_n_cop_attr_changed; -extern atomic_t fscache_n_cop_read_or_alloc_page; -extern atomic_t fscache_n_cop_read_or_alloc_pages; -extern atomic_t fscache_n_cop_allocate_page; -extern atomic_t fscache_n_cop_allocate_pages; -extern atomic_t fscache_n_cop_write_page; -extern atomic_t fscache_n_cop_uncache_page; -extern atomic_t fscache_n_cop_dissociate_pages; - -extern atomic_t fscache_n_cache_no_space_reject; -extern atomic_t fscache_n_cache_stale_objects; -extern atomic_t fscache_n_cache_retired_objects; -extern atomic_t fscache_n_cache_culled_objects; +extern atomic_t fscache_n_resizes; +extern atomic_t fscache_n_resizes_null; static inline void fscache_stat(atomic_t *stat) { @@ -278,71 +146,26 @@ int fscache_stats_show(struct seq_file *m, void *v); #endif /* - * raise an event on an object - * - if the event is not masked for that object, then the object is - * queued for attention by the thread pool. - */ -static inline void fscache_raise_event(struct fscache_object *object, - unsigned event) -{ - BUG_ON(event >= NR_FSCACHE_OBJECT_EVENTS); -#if 0 - printk("*** fscache_raise_event(OBJ%d{%lx},%x)\n", - object->debug_id, object->event_mask, (1 << event)); -#endif - if (!test_and_set_bit(event, &object->events) && - test_bit(event, &object->event_mask)) - fscache_enqueue_object(object); -} - -/* - * get an extra reference to a netfs retrieval context + * volume.c */ -static inline -void *fscache_get_context(struct fscache_cookie *cookie, void *context) -{ - if (cookie->def->get_context) - cookie->def->get_context(cookie->netfs_data, context); - return context; -} +extern const struct seq_operations fscache_volumes_seq_ops; -/* - * release a reference to a netfs retrieval context - */ -static inline -void fscache_put_context(struct fscache_cookie *cookie, void *context) -{ - if (cookie->def->put_context) - cookie->def->put_context(cookie->netfs_data, context); -} +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); +void fscache_create_volume(struct fscache_volume *volume, bool wait); -/* - * Update the auxiliary data on a cookie. - */ -static inline -void fscache_update_aux(struct fscache_cookie *cookie, const void *aux_data) -{ - void *p; - - if (!aux_data) - return; - if (cookie->aux_len <= sizeof(cookie->inline_aux)) - p = cookie->inline_aux; - else - p = cookie->aux; - - if (memcmp(p, aux_data, cookie->aux_len) != 0) { - memcpy(p, aux_data, cookie->aux_len); - set_bit(FSCACHE_COOKIE_AUX_UPDATED, &cookie->flags); - } -} /*****************************************************************************/ /* * debug tracing */ #define dbgprintk(FMT, ...) \ - printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) + printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) #define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__) #define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__) @@ -395,7 +218,7 @@ do { \ #define FSCACHE_DEBUG_CACHE 0 #define FSCACHE_DEBUG_COOKIE 1 -#define FSCACHE_DEBUG_PAGE 2 +#define FSCACHE_DEBUG_OBJECT 2 #define FSCACHE_DEBUG_OPERATION 3 #define FSCACHE_POINT_ENTER 1 diff --git a/fs/fscache/io.c b/fs/fscache/io.c index 8ecc1141802f..7a769ea57720 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -4,113 +4,323 @@ * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ - -#define FSCACHE_DEBUG_LEVEL PAGE -#include <linux/module.h> -#define FSCACHE_USE_NEW_IO_API +#define FSCACHE_DEBUG_LEVEL OPERATION #include <linux/fscache-cache.h> +#include <linux/uio.h> +#include <linux/bvec.h> #include <linux/slab.h> -#include <linux/netfs.h> +#include <linux/uio.h> #include "internal.h" -/* - * Start a cache read operation. - * - we return: - * -ENOMEM - out of memory, some pages may be being read - * -ERESTARTSYS - interrupted, some pages may be being read - * -ENOBUFS - no backing object or space available in which to cache any - * pages not being read - * -ENODATA - no data available in the backing object for some or all of - * the pages - * 0 - dispatched a read on all pages +/** + * fscache_wait_for_operation - Wait for an object become accessible + * @cres: The cache resources for the operation being performed + * @want_state: The minimum state the object must be at + * + * See if the target cache object is at the specified minimum state of + * accessibility yet, and if not, wait for it. */ -int __fscache_begin_read_operation(struct netfs_read_request *rreq, - struct fscache_cookie *cookie) +bool fscache_wait_for_operation(struct netfs_cache_resources *cres, + enum fscache_want_state want_state) { - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; + struct fscache_cookie *cookie = fscache_cres_cookie(cres); + enum fscache_cookie_state state; - _enter("rr=%08x", rreq->debug_id); +again: + if (!fscache_cache_is_live(cookie->volume->cache)) { + _leave(" [broken]"); + return false; + } - fscache_stat(&fscache_n_retrievals); + state = fscache_cookie_state(cookie); + _enter("c=%08x{%u},%x", cookie->debug_id, state, want_state); - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; + switch (state) { + case FSCACHE_COOKIE_STATE_CREATING: + case FSCACHE_COOKIE_STATE_INVALIDATING: + if (want_state == FSCACHE_WANT_PARAMS) + goto ready; /* There can be no content */ + fallthrough; + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + wait_var_event(&cookie->state, + fscache_cookie_state(cookie) != state); + goto again; - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; + case FSCACHE_COOKIE_STATE_ACTIVE: + goto ready; + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + default: + _leave(" [not live]"); + return false; } - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); +ready: + if (!cres->cache_priv2) + return cookie->volume->cache->ops->begin_operation(cres, want_state); + return true; +} +EXPORT_SYMBOL(fscache_wait_for_operation); + +/* + * Begin an I/O operation on the cache, waiting till we reach the right state. + * + * Attaches the resources required to the operation resources record. + */ +static int fscache_begin_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie, + enum fscache_want_state want_state, + enum fscache_access_trace why) +{ + enum fscache_cookie_state state; + long timeo; + bool once_only = false; - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; + cres->ops = NULL; + cres->cache_priv = cookie; + cres->cache_priv2 = NULL; + cres->debug_id = cookie->debug_id; + cres->inval_counter = cookie->inval_counter; - op = fscache_alloc_retrieval(cookie, NULL, NULL, NULL); - if (!op) - return -ENOMEM; - trace_fscache_page_op(cookie, NULL, &op->op, fscache_page_op_retr_multi); + if (!fscache_begin_cookie_access(cookie, why)) + return -ENOBUFS; +again: spin_lock(&cookie->lock); - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); + state = fscache_cookie_state(cookie); + _enter("c=%08x{%u},%x", cookie->debug_id, state, want_state); - __fscache_use_cookie(cookie); - atomic_inc(&object->n_reads); - __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); + switch (state) { + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + case FSCACHE_COOKIE_STATE_INVALIDATING: + goto wait_for_file_wrangling; + case FSCACHE_COOKIE_STATE_CREATING: + if (want_state == FSCACHE_WANT_PARAMS) + goto ready; /* There can be no content */ + goto wait_for_file_wrangling; + case FSCACHE_COOKIE_STATE_ACTIVE: + goto ready; + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + WARN(1, "Can't use cookie in state %u\n", cookie->state); + goto not_live; + default: + goto not_live; + } - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; +ready: spin_unlock(&cookie->lock); + if (!cookie->volume->cache->ops->begin_operation(cres, want_state)) + goto failed; + return 0; - fscache_stat(&fscache_n_retrieval_ops); +wait_for_file_wrangling: + spin_unlock(&cookie->lock); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + atomic_read(&cookie->n_accesses), + fscache_access_io_wait); + timeo = wait_var_event_timeout(&cookie->state, + fscache_cookie_state(cookie) != state, 20 * HZ); + if (timeo <= 1 && !once_only) { + pr_warn("%s: cookie state change wait timed out: cookie->state=%u state=%u", + __func__, fscache_cookie_state(cookie), state); + fscache_print_cookie(cookie, 'O'); + once_only = true; + } + goto again; - /* we wait for the operation to become active, and then process it - * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - ret = object->cache->ops->begin_read_operation(rreq, op); - -error: - if (ret == -ENOMEM) - fscache_stat(&fscache_n_retrievals_nomem); - else if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_retrievals_intr); - else if (ret == -ENODATA) - fscache_stat(&fscache_n_retrievals_nodata); - else if (ret < 0) - fscache_stat(&fscache_n_retrievals_nobufs); - else - fscache_stat(&fscache_n_retrievals_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - atomic_dec(&object->n_reads); - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: +not_live: spin_unlock(&cookie->lock); - fscache_put_retrieval(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); -nobufs: - fscache_stat(&fscache_n_retrievals_nobufs); +failed: + cres->cache_priv = NULL; + cres->ops = NULL; + fscache_end_cookie_access(cookie, fscache_access_io_not_live); _leave(" = -ENOBUFS"); return -ENOBUFS; } + +int __fscache_begin_read_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS, + fscache_access_io_read); +} EXPORT_SYMBOL(__fscache_begin_read_operation); + +int __fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS, + fscache_access_io_write); +} +EXPORT_SYMBOL(__fscache_begin_write_operation); + +/** + * fscache_set_page_dirty - Mark page dirty and pin a cache object for writeback + * @page: The page being dirtied + * @cookie: The cookie referring to the cache object + * + * Set the dirty flag on a page and pin an in-use cache object in memory when + * dirtying a page so that writeback can later write to it. This is intended + * to be called from the filesystem's ->set_page_dirty() method. + * + * Returns 1 if PG_dirty was set on the page, 0 otherwise. + */ +int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie) +{ + struct inode *inode = page->mapping->host; + bool need_use = false; + + _enter(""); + + if (!__set_page_dirty_nobuffers(page)) + return 0; + if (!fscache_cookie_valid(cookie)) + return 1; + + if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { + inode->i_state |= I_PINNING_FSCACHE_WB; + need_use = true; + } + spin_unlock(&inode->i_lock); + + if (need_use) + fscache_use_cookie(cookie, true); + } + return 1; +} +EXPORT_SYMBOL(fscache_set_page_dirty); + +struct fscache_write_request { + struct netfs_cache_resources cache_resources; + struct address_space *mapping; + loff_t start; + size_t len; + bool set_bits; + netfs_io_terminated_t term_func; + void *term_func_priv; +}; + +void __fscache_clear_page_bits(struct address_space *mapping, + loff_t start, size_t len) +{ + pgoff_t first = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE; + struct page *page; + + if (len) { + XA_STATE(xas, &mapping->i_pages, first); + + rcu_read_lock(); + xas_for_each(&xas, page, last) { + end_page_fscache(page); + } + rcu_read_unlock(); + } +} +EXPORT_SYMBOL(__fscache_clear_page_bits); + +/* + * Deal with the completion of writing the data to the cache. + */ +static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct fscache_write_request *wreq = priv; + + fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), + wreq->mapping, wreq->start, wreq->len, + wreq->set_bits); + + if (wreq->term_func) + wreq->term_func(wreq->term_func_priv, transferred_or_error, + was_async); + fscache_end_operation(&wreq->cache_resources); + kfree(wreq); +} + +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool cond) +{ + struct fscache_write_request *wreq; + struct netfs_cache_resources *cres; + struct iov_iter iter; + int ret = -ENOBUFS; + + if (len == 0) + goto abandon; + + _enter("%llx,%zx", start, len); + + wreq = kzalloc(sizeof(struct fscache_write_request), GFP_NOFS); + if (!wreq) + goto abandon; + wreq->mapping = mapping; + wreq->start = start; + wreq->len = len; + wreq->set_bits = cond; + wreq->term_func = term_func; + wreq->term_func_priv = term_func_priv; + + cres = &wreq->cache_resources; + if (fscache_begin_operation(cres, cookie, FSCACHE_WANT_WRITE, + fscache_access_io_write) < 0) + goto abandon_free; + + ret = cres->ops->prepare_write(cres, &start, &len, i_size, false); + if (ret < 0) + goto abandon_end; + + /* TODO: Consider clearing page bits now for space the write isn't + * covering. This is more complicated than it appears when THPs are + * taken into account. + */ + + iov_iter_xarray(&iter, WRITE, &mapping->i_pages, start, len); + fscache_write(cres, start, &iter, fscache_wreq_done, wreq); + return; + +abandon_end: + return fscache_wreq_done(wreq, ret, false); +abandon_free: + kfree(wreq); +abandon: + fscache_clear_page_bits(cookie, mapping, start, len, cond); + if (term_func) + term_func(term_func_priv, ret, false); +} +EXPORT_SYMBOL(__fscache_write_to_cache); + +/* + * Change the size of a backing object. + */ +void __fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) +{ + struct netfs_cache_resources cres; + + trace_fscache_resize(cookie, new_size); + if (fscache_begin_operation(&cres, cookie, FSCACHE_WANT_WRITE, + fscache_access_io_resize) == 0) { + fscache_stat(&fscache_n_resizes); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); + + /* We cannot defer a resize as we need to do it inside the + * netfs's inode lock so that we're serialised with respect to + * writes. + */ + cookie->volume->cache->ops->resize_cookie(&cres, new_size); + fscache_end_operation(&cres); + } else { + fscache_stat(&fscache_n_resizes_null); + } +} +EXPORT_SYMBOL(__fscache_resize_cookie); diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 4207f98e405f..dad85fd84f6f 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -1,17 +1,13 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* General filesystem local caching manager * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define FSCACHE_DEBUG_LEVEL CACHE #include <linux/module.h> #include <linux/init.h> -#include <linux/sched.h> -#include <linux/completion.h> -#include <linux/slab.h> -#include <linux/seq_file.h> #define CREATE_TRACE_POINTS #include "internal.h" @@ -19,79 +15,18 @@ MODULE_DESCRIPTION("FS Cache Manager"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); -unsigned fscache_defer_lookup = 1; -module_param_named(defer_lookup, fscache_defer_lookup, uint, - S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(fscache_defer_lookup, - "Defer cookie lookup to background thread"); - -unsigned fscache_defer_create = 1; -module_param_named(defer_create, fscache_defer_create, uint, - S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(fscache_defer_create, - "Defer cookie creation to background thread"); - unsigned fscache_debug; module_param_named(debug, fscache_debug, uint, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(fscache_debug, "FS-Cache debugging mask"); -struct kobject *fscache_root; -struct workqueue_struct *fscache_object_wq; -struct workqueue_struct *fscache_op_wq; - -DEFINE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); +EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache); +EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume); +EXPORT_TRACEPOINT_SYMBOL(fscache_access); -/* these values serve as lower bounds, will be adjusted in fscache_init() */ -static unsigned fscache_object_max_active = 4; -static unsigned fscache_op_max_active = 2; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *fscache_sysctl_header; - -static int fscache_max_active_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - struct workqueue_struct **wqp = table->extra1; - unsigned int *datap = table->data; - int ret; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret == 0) - workqueue_set_max_active(*wqp, *datap); - return ret; -} - -static struct ctl_table fscache_sysctls[] = { - { - .procname = "object_max_active", - .data = &fscache_object_max_active, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = fscache_max_active_sysctl, - .extra1 = &fscache_object_wq, - }, - { - .procname = "operation_max_active", - .data = &fscache_op_max_active, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = fscache_max_active_sysctl, - .extra1 = &fscache_op_wq, - }, - {} -}; - -static struct ctl_table fscache_sysctls_root[] = { - { - .procname = "fscache", - .mode = 0555, - .child = fscache_sysctls, - }, - {} -}; -#endif +struct workqueue_struct *fscache_wq; +EXPORT_SYMBOL(fscache_wq); /* * Mixing scores (in bits) for (7,20): @@ -118,15 +53,16 @@ static inline unsigned int fold_hash(unsigned long x, unsigned long y) /* * Generate a hash. This is derived from full_name_hash(), but we want to be * sure it is arch independent and that it doesn't change as bits of the - * computed hash value might appear on disk. The caller also guarantees that - * the hashed data will be a series of aligned 32-bit words. + * computed hash value might appear on disk. The caller must guarantee that + * the source data is a multiple of four bytes in size. */ -unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n) +unsigned int fscache_hash(unsigned int salt, const void *data, size_t len) { - unsigned int a, x = 0, y = salt; + const __le32 *p = data; + unsigned int a, x = 0, y = salt, n = len / sizeof(__le32); for (; n; n--) { - a = *data++; + a = le32_to_cpu(*p++); HASH_MIX(x, y, a); } return fold_hash(x, y); @@ -137,44 +73,16 @@ unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n) */ static int __init fscache_init(void) { - unsigned int nr_cpus = num_possible_cpus(); - unsigned int cpu; - int ret; - - fscache_object_max_active = - clamp_val(nr_cpus, - fscache_object_max_active, WQ_UNBOUND_MAX_ACTIVE); - - ret = -ENOMEM; - fscache_object_wq = alloc_workqueue("fscache_object", WQ_UNBOUND, - fscache_object_max_active); - if (!fscache_object_wq) - goto error_object_wq; - - fscache_op_max_active = - clamp_val(fscache_object_max_active / 2, - fscache_op_max_active, WQ_UNBOUND_MAX_ACTIVE); + int ret = -ENOMEM; - ret = -ENOMEM; - fscache_op_wq = alloc_workqueue("fscache_operation", WQ_UNBOUND, - fscache_op_max_active); - if (!fscache_op_wq) - goto error_op_wq; - - for_each_possible_cpu(cpu) - init_waitqueue_head(&per_cpu(fscache_object_cong_wait, cpu)); + fscache_wq = alloc_workqueue("fscache", WQ_UNBOUND | WQ_FREEZABLE, 0); + if (!fscache_wq) + goto error_wq; ret = fscache_proc_init(); if (ret < 0) goto error_proc; -#ifdef CONFIG_SYSCTL - ret = -ENOMEM; - fscache_sysctl_header = register_sysctl_table(fscache_sysctls_root); - if (!fscache_sysctl_header) - goto error_sysctl; -#endif - fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar", sizeof(struct fscache_cookie), 0, 0, NULL); @@ -184,26 +92,14 @@ static int __init fscache_init(void) goto error_cookie_jar; } - fscache_root = kobject_create_and_add("fscache", kernel_kobj); - if (!fscache_root) - goto error_kobj; - pr_notice("Loaded\n"); return 0; -error_kobj: - kmem_cache_destroy(fscache_cookie_jar); error_cookie_jar: -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(fscache_sysctl_header); -error_sysctl: -#endif fscache_proc_cleanup(); error_proc: - destroy_workqueue(fscache_op_wq); -error_op_wq: - destroy_workqueue(fscache_object_wq); -error_object_wq: + destroy_workqueue(fscache_wq); +error_wq: return ret; } @@ -216,14 +112,9 @@ static void __exit fscache_exit(void) { _enter(""); - kobject_put(fscache_root); kmem_cache_destroy(fscache_cookie_jar); -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(fscache_sysctl_header); -#endif fscache_proc_cleanup(); - destroy_workqueue(fscache_op_wq); - destroy_workqueue(fscache_object_wq); + destroy_workqueue(fscache_wq); pr_notice("Unloaded\n"); } diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c deleted file mode 100644 index d6bdb7b5e723..000000000000 --- a/fs/fscache/netfs.c +++ /dev/null @@ -1,74 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache netfs (client) registration - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL COOKIE -#include <linux/module.h> -#include <linux/slab.h> -#include "internal.h" - -/* - * register a network filesystem for caching - */ -int __fscache_register_netfs(struct fscache_netfs *netfs) -{ - struct fscache_cookie *candidate, *cookie; - - _enter("{%s}", netfs->name); - - /* allocate a cookie for the primary index */ - candidate = fscache_alloc_cookie(&fscache_fsdef_index, - &fscache_fsdef_netfs_def, - netfs->name, strlen(netfs->name), - &netfs->version, sizeof(netfs->version), - netfs, 0); - if (!candidate) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - candidate->flags = 1 << FSCACHE_COOKIE_ENABLED; - - /* check the netfs type is not already present */ - cookie = fscache_hash_cookie(candidate); - if (!cookie) - goto already_registered; - if (cookie != candidate) { - trace_fscache_cookie(candidate->debug_id, 1, fscache_cookie_discard); - fscache_free_cookie(candidate); - } - - fscache_cookie_get(cookie->parent, fscache_cookie_get_register_netfs); - atomic_inc(&cookie->parent->n_children); - - netfs->primary_index = cookie; - - pr_notice("Netfs '%s' registered for caching\n", netfs->name); - trace_fscache_netfs(netfs); - _leave(" = 0"); - return 0; - -already_registered: - fscache_cookie_put(candidate, fscache_cookie_put_dup_netfs); - _leave(" = -EEXIST"); - return -EEXIST; -} -EXPORT_SYMBOL(__fscache_register_netfs); - -/* - * unregister a network filesystem from the cache - * - all cookies must have been released first - */ -void __fscache_unregister_netfs(struct fscache_netfs *netfs) -{ - _enter("{%s.%u}", netfs->name, netfs->version); - - fscache_relinquish_cookie(netfs->primary_index, NULL, false); - pr_notice("Netfs '%s' unregistered from caching\n", netfs->name); - - _leave(""); -} -EXPORT_SYMBOL(__fscache_unregister_netfs); diff --git a/fs/fscache/object.c b/fs/fscache/object.c deleted file mode 100644 index 6a675652129b..000000000000 --- a/fs/fscache/object.c +++ /dev/null @@ -1,1125 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache object state machine handler - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * See Documentation/filesystems/caching/object.rst for a description of the - * object state machine and the in-kernel representations. - */ - -#define FSCACHE_DEBUG_LEVEL COOKIE -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/prefetch.h> -#include "internal.h" - -static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *, int); -static const struct fscache_state *fscache_kill_dependents(struct fscache_object *, int); -static const struct fscache_state *fscache_drop_object(struct fscache_object *, int); -static const struct fscache_state *fscache_initialise_object(struct fscache_object *, int); -static const struct fscache_state *fscache_invalidate_object(struct fscache_object *, int); -static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *, int); -static const struct fscache_state *fscache_kill_object(struct fscache_object *, int); -static const struct fscache_state *fscache_lookup_failure(struct fscache_object *, int); -static const struct fscache_state *fscache_look_up_object(struct fscache_object *, int); -static const struct fscache_state *fscache_object_available(struct fscache_object *, int); -static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int); -static const struct fscache_state *fscache_update_object(struct fscache_object *, int); -static const struct fscache_state *fscache_object_dead(struct fscache_object *, int); - -#define __STATE_NAME(n) fscache_osm_##n -#define STATE(n) (&__STATE_NAME(n)) - -/* - * Define a work state. Work states are execution states. No event processing - * is performed by them. The function attached to a work state returns a - * pointer indicating the next state to which the state machine should - * transition. Returning NO_TRANSIT repeats the current state, but goes back - * to the scheduler first. - */ -#define WORK_STATE(n, sn, f) \ - const struct fscache_state __STATE_NAME(n) = { \ - .name = #n, \ - .short_name = sn, \ - .work = f \ - } - -/* - * Returns from work states. - */ -#define transit_to(state) ({ prefetch(&STATE(state)->work); STATE(state); }) - -#define NO_TRANSIT ((struct fscache_state *)NULL) - -/* - * Define a wait state. Wait states are event processing states. No execution - * is performed by them. Wait states are just tables of "if event X occurs, - * clear it and transition to state Y". The dispatcher returns to the - * scheduler if none of the events in which the wait state has an interest are - * currently pending. - */ -#define WAIT_STATE(n, sn, ...) \ - const struct fscache_state __STATE_NAME(n) = { \ - .name = #n, \ - .short_name = sn, \ - .work = NULL, \ - .transitions = { __VA_ARGS__, { 0, NULL } } \ - } - -#define TRANSIT_TO(state, emask) \ - { .events = (emask), .transit_to = STATE(state) } - -/* - * The object state machine. - */ -static WORK_STATE(INIT_OBJECT, "INIT", fscache_initialise_object); -static WORK_STATE(PARENT_READY, "PRDY", fscache_parent_ready); -static WORK_STATE(ABORT_INIT, "ABRT", fscache_abort_initialisation); -static WORK_STATE(LOOK_UP_OBJECT, "LOOK", fscache_look_up_object); -static WORK_STATE(OBJECT_AVAILABLE, "AVBL", fscache_object_available); -static WORK_STATE(JUMPSTART_DEPS, "JUMP", fscache_jumpstart_dependents); - -static WORK_STATE(INVALIDATE_OBJECT, "INVL", fscache_invalidate_object); -static WORK_STATE(UPDATE_OBJECT, "UPDT", fscache_update_object); - -static WORK_STATE(LOOKUP_FAILURE, "LCFL", fscache_lookup_failure); -static WORK_STATE(KILL_OBJECT, "KILL", fscache_kill_object); -static WORK_STATE(KILL_DEPENDENTS, "KDEP", fscache_kill_dependents); -static WORK_STATE(DROP_OBJECT, "DROP", fscache_drop_object); -static WORK_STATE(OBJECT_DEAD, "DEAD", fscache_object_dead); - -static WAIT_STATE(WAIT_FOR_INIT, "?INI", - TRANSIT_TO(INIT_OBJECT, 1 << FSCACHE_OBJECT_EV_NEW_CHILD)); - -static WAIT_STATE(WAIT_FOR_PARENT, "?PRN", - TRANSIT_TO(PARENT_READY, 1 << FSCACHE_OBJECT_EV_PARENT_READY)); - -static WAIT_STATE(WAIT_FOR_CMD, "?CMD", - TRANSIT_TO(INVALIDATE_OBJECT, 1 << FSCACHE_OBJECT_EV_INVALIDATE), - TRANSIT_TO(UPDATE_OBJECT, 1 << FSCACHE_OBJECT_EV_UPDATE), - TRANSIT_TO(JUMPSTART_DEPS, 1 << FSCACHE_OBJECT_EV_NEW_CHILD)); - -static WAIT_STATE(WAIT_FOR_CLEARANCE, "?CLR", - TRANSIT_TO(KILL_OBJECT, 1 << FSCACHE_OBJECT_EV_CLEARED)); - -/* - * Out-of-band event transition tables. These are for handling unexpected - * events, such as an I/O error. If an OOB event occurs, the state machine - * clears and disables the event and forces a transition to the nominated work - * state (acurrently executing work states will complete first). - * - * In such a situation, object->state remembers the state the machine should - * have been in/gone to and returning NO_TRANSIT returns to that. - */ -static const struct fscache_transition fscache_osm_init_oob[] = { - TRANSIT_TO(ABORT_INIT, - (1 << FSCACHE_OBJECT_EV_ERROR) | - (1 << FSCACHE_OBJECT_EV_KILL)), - { 0, NULL } -}; - -static const struct fscache_transition fscache_osm_lookup_oob[] = { - TRANSIT_TO(LOOKUP_FAILURE, - (1 << FSCACHE_OBJECT_EV_ERROR) | - (1 << FSCACHE_OBJECT_EV_KILL)), - { 0, NULL } -}; - -static const struct fscache_transition fscache_osm_run_oob[] = { - TRANSIT_TO(KILL_OBJECT, - (1 << FSCACHE_OBJECT_EV_ERROR) | - (1 << FSCACHE_OBJECT_EV_KILL)), - { 0, NULL } -}; - -static int fscache_get_object(struct fscache_object *, - enum fscache_obj_ref_trace); -static void fscache_put_object(struct fscache_object *, - enum fscache_obj_ref_trace); -static bool fscache_enqueue_dependents(struct fscache_object *, int); -static void fscache_dequeue_object(struct fscache_object *); -static void fscache_update_aux_data(struct fscache_object *); - -/* - * we need to notify the parent when an op completes that we had outstanding - * upon it - */ -static inline void fscache_done_parent_op(struct fscache_object *object) -{ - struct fscache_object *parent = object->parent; - - _enter("OBJ%x {OBJ%x,%x}", - object->debug_id, parent->debug_id, parent->n_ops); - - spin_lock_nested(&parent->lock, 1); - parent->n_obj_ops--; - parent->n_ops--; - if (parent->n_ops == 0) - fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED); - spin_unlock(&parent->lock); -} - -/* - * Object state machine dispatcher. - */ -static void fscache_object_sm_dispatcher(struct fscache_object *object) -{ - const struct fscache_transition *t; - const struct fscache_state *state, *new_state; - unsigned long events, event_mask; - bool oob; - int event = -1; - - ASSERT(object != NULL); - - _enter("{OBJ%x,%s,%lx}", - object->debug_id, object->state->name, object->events); - - event_mask = object->event_mask; -restart: - object->event_mask = 0; /* Mask normal event handling */ - state = object->state; -restart_masked: - events = object->events; - - /* Handle any out-of-band events (typically an error) */ - if (events & object->oob_event_mask) { - _debug("{OBJ%x} oob %lx", - object->debug_id, events & object->oob_event_mask); - oob = true; - for (t = object->oob_table; t->events; t++) { - if (events & t->events) { - state = t->transit_to; - ASSERT(state->work != NULL); - event = fls(events & t->events) - 1; - __clear_bit(event, &object->oob_event_mask); - clear_bit(event, &object->events); - goto execute_work_state; - } - } - } - oob = false; - - /* Wait states are just transition tables */ - if (!state->work) { - if (events & event_mask) { - for (t = state->transitions; t->events; t++) { - if (events & t->events) { - new_state = t->transit_to; - event = fls(events & t->events) - 1; - trace_fscache_osm(object, state, - true, false, event); - clear_bit(event, &object->events); - _debug("{OBJ%x} ev %d: %s -> %s", - object->debug_id, event, - state->name, new_state->name); - object->state = state = new_state; - goto execute_work_state; - } - } - - /* The event mask didn't include all the tabled bits */ - BUG(); - } - /* Randomly woke up */ - goto unmask_events; - } - -execute_work_state: - _debug("{OBJ%x} exec %s", object->debug_id, state->name); - - trace_fscache_osm(object, state, false, oob, event); - new_state = state->work(object, event); - event = -1; - if (new_state == NO_TRANSIT) { - _debug("{OBJ%x} %s notrans", object->debug_id, state->name); - if (unlikely(state == STATE(OBJECT_DEAD))) { - _leave(" [dead]"); - return; - } - fscache_enqueue_object(object); - event_mask = object->oob_event_mask; - goto unmask_events; - } - - _debug("{OBJ%x} %s -> %s", - object->debug_id, state->name, new_state->name); - object->state = state = new_state; - - if (state->work) { - if (unlikely(state == STATE(OBJECT_DEAD))) { - _leave(" [dead]"); - return; - } - goto restart_masked; - } - - /* Transited to wait state */ - event_mask = object->oob_event_mask; - for (t = state->transitions; t->events; t++) - event_mask |= t->events; - -unmask_events: - object->event_mask = event_mask; - smp_mb(); - events = object->events; - if (events & event_mask) - goto restart; - _leave(" [msk %lx]", event_mask); -} - -/* - * execute an object - */ -static void fscache_object_work_func(struct work_struct *work) -{ - struct fscache_object *object = - container_of(work, struct fscache_object, work); - - _enter("{OBJ%x}", object->debug_id); - - fscache_object_sm_dispatcher(object); - fscache_put_object(object, fscache_obj_put_work); -} - -/** - * fscache_object_init - Initialise a cache object description - * @object: Object description - * @cookie: Cookie object will be attached to - * @cache: Cache in which backing object will be found - * - * Initialise a cache object description to its basic values. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -void fscache_object_init(struct fscache_object *object, - struct fscache_cookie *cookie, - struct fscache_cache *cache) -{ - const struct fscache_transition *t; - - atomic_inc(&cache->object_count); - - object->state = STATE(WAIT_FOR_INIT); - object->oob_table = fscache_osm_init_oob; - object->flags = 1 << FSCACHE_OBJECT_IS_LIVE; - spin_lock_init(&object->lock); - INIT_LIST_HEAD(&object->cache_link); - INIT_HLIST_NODE(&object->cookie_link); - INIT_WORK(&object->work, fscache_object_work_func); - INIT_LIST_HEAD(&object->dependents); - INIT_LIST_HEAD(&object->dep_link); - INIT_LIST_HEAD(&object->pending_ops); - object->n_children = 0; - object->n_ops = object->n_in_progress = object->n_exclusive = 0; - object->events = 0; - object->store_limit = 0; - object->store_limit_l = 0; - object->cache = cache; - object->cookie = cookie; - fscache_cookie_get(cookie, fscache_cookie_get_attach_object); - object->parent = NULL; -#ifdef CONFIG_FSCACHE_OBJECT_LIST - RB_CLEAR_NODE(&object->objlist_link); -#endif - - object->oob_event_mask = 0; - for (t = object->oob_table; t->events; t++) - object->oob_event_mask |= t->events; - object->event_mask = object->oob_event_mask; - for (t = object->state->transitions; t->events; t++) - object->event_mask |= t->events; -} -EXPORT_SYMBOL(fscache_object_init); - -/* - * Mark the object as no longer being live, making sure that we synchronise - * against op submission. - */ -static inline void fscache_mark_object_dead(struct fscache_object *object) -{ - spin_lock(&object->lock); - clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); - spin_unlock(&object->lock); -} - -/* - * Abort object initialisation before we start it. - */ -static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_event_mask = 0; - fscache_dequeue_object(object); - return transit_to(KILL_OBJECT); -} - -/* - * initialise an object - * - check the specified object's parent to see if we can make use of it - * immediately to do a creation - * - we may need to start the process of creating a parent and we need to wait - * for the parent's lookup and creation to complete if it's not there yet - */ -static const struct fscache_state *fscache_initialise_object(struct fscache_object *object, - int event) -{ - struct fscache_object *parent; - bool success; - - _enter("{OBJ%x},%d", object->debug_id, event); - - ASSERT(list_empty(&object->dep_link)); - - parent = object->parent; - if (!parent) { - _leave(" [no parent]"); - return transit_to(DROP_OBJECT); - } - - _debug("parent: %s of:%lx", parent->state->name, parent->flags); - - if (fscache_object_is_dying(parent)) { - _leave(" [bad parent]"); - return transit_to(DROP_OBJECT); - } - - if (fscache_object_is_available(parent)) { - _leave(" [ready]"); - return transit_to(PARENT_READY); - } - - _debug("wait"); - - spin_lock(&parent->lock); - fscache_stat(&fscache_n_cop_grab_object); - success = false; - if (fscache_object_is_live(parent) && - object->cache->ops->grab_object(object, fscache_obj_get_add_to_deps)) { - list_add(&object->dep_link, &parent->dependents); - success = true; - } - fscache_stat_d(&fscache_n_cop_grab_object); - spin_unlock(&parent->lock); - if (!success) { - _leave(" [grab failed]"); - return transit_to(DROP_OBJECT); - } - - /* fscache_acquire_non_index_cookie() uses this - * to wake the chain up */ - fscache_raise_event(parent, FSCACHE_OBJECT_EV_NEW_CHILD); - _leave(" [wait]"); - return transit_to(WAIT_FOR_PARENT); -} - -/* - * Once the parent object is ready, we should kick off our lookup op. - */ -static const struct fscache_state *fscache_parent_ready(struct fscache_object *object, - int event) -{ - struct fscache_object *parent = object->parent; - - _enter("{OBJ%x},%d", object->debug_id, event); - - ASSERT(parent != NULL); - - spin_lock(&parent->lock); - parent->n_ops++; - parent->n_obj_ops++; - spin_unlock(&parent->lock); - - _leave(""); - return transit_to(LOOK_UP_OBJECT); -} - -/* - * look an object up in the cache from which it was allocated - * - we hold an "access lock" on the parent object, so the parent object cannot - * be withdrawn by either party till we've finished - */ -static const struct fscache_state *fscache_look_up_object(struct fscache_object *object, - int event) -{ - struct fscache_cookie *cookie = object->cookie; - struct fscache_object *parent = object->parent; - int ret; - - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_table = fscache_osm_lookup_oob; - - ASSERT(parent != NULL); - ASSERTCMP(parent->n_ops, >, 0); - ASSERTCMP(parent->n_obj_ops, >, 0); - - /* make sure the parent is still available */ - ASSERT(fscache_object_is_available(parent)); - - if (fscache_object_is_dying(parent) || - test_bit(FSCACHE_IOERROR, &object->cache->flags) || - !fscache_use_cookie(object)) { - _leave(" [unavailable]"); - return transit_to(LOOKUP_FAILURE); - } - - _debug("LOOKUP \"%s\" in \"%s\"", - cookie->def->name, object->cache->tag->name); - - fscache_stat(&fscache_n_object_lookups); - fscache_stat(&fscache_n_cop_lookup_object); - ret = object->cache->ops->lookup_object(object); - fscache_stat_d(&fscache_n_cop_lookup_object); - - fscache_unuse_cookie(object); - - if (ret == -ETIMEDOUT) { - /* probably stuck behind another object, so move this one to - * the back of the queue */ - fscache_stat(&fscache_n_object_lookups_timed_out); - _leave(" [timeout]"); - return NO_TRANSIT; - } - - if (ret < 0) { - _leave(" [error]"); - return transit_to(LOOKUP_FAILURE); - } - - _leave(" [ok]"); - return transit_to(OBJECT_AVAILABLE); -} - -/** - * fscache_object_lookup_negative - Note negative cookie lookup - * @object: Object pointing to cookie to mark - * - * Note negative lookup, permitting those waiting to read data from an already - * existing backing object to continue as there's no data for them to read. - */ -void fscache_object_lookup_negative(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - - _enter("{OBJ%x,%s}", object->debug_id, object->state->name); - - if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) { - fscache_stat(&fscache_n_object_lookups_negative); - - /* Allow write requests to begin stacking up and read requests to begin - * returning ENODATA. - */ - set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - - clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - } - _leave(""); -} -EXPORT_SYMBOL(fscache_object_lookup_negative); - -/** - * fscache_obtained_object - Note successful object lookup or creation - * @object: Object pointing to cookie to mark - * - * Note successful lookup and/or creation, permitting those waiting to write - * data to a backing object to continue. - * - * Note that after calling this, an object's cookie may be relinquished by the - * netfs, and so must be accessed with object lock held. - */ -void fscache_obtained_object(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - - _enter("{OBJ%x,%s}", object->debug_id, object->state->name); - - /* if we were still looking up, then we must have a positive lookup - * result, in which case there may be data available */ - if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) { - fscache_stat(&fscache_n_object_lookups_positive); - - /* We do (presumably) have data */ - clear_bit_unlock(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - - /* Allow write requests to begin stacking up and read requests - * to begin shovelling data. - */ - clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - } else { - fscache_stat(&fscache_n_object_created); - } - - set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); - _leave(""); -} -EXPORT_SYMBOL(fscache_obtained_object); - -/* - * handle an object that has just become available - */ -static const struct fscache_state *fscache_object_available(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_table = fscache_osm_run_oob; - - spin_lock(&object->lock); - - fscache_done_parent_op(object); - if (object->n_in_progress == 0) { - if (object->n_ops > 0) { - ASSERTCMP(object->n_ops, >=, object->n_obj_ops); - fscache_start_operations(object); - } else { - ASSERT(list_empty(&object->pending_ops)); - } - } - spin_unlock(&object->lock); - - fscache_stat(&fscache_n_cop_lookup_complete); - object->cache->ops->lookup_complete(object); - fscache_stat_d(&fscache_n_cop_lookup_complete); - - fscache_stat(&fscache_n_object_avail); - - _leave(""); - return transit_to(JUMPSTART_DEPS); -} - -/* - * Wake up this object's dependent objects now that we've become available. - */ -static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_PARENT_READY)) - return NO_TRANSIT; /* Not finished; requeue */ - return transit_to(WAIT_FOR_CMD); -} - -/* - * Handle lookup or creation failute. - */ -static const struct fscache_state *fscache_lookup_failure(struct fscache_object *object, - int event) -{ - struct fscache_cookie *cookie; - - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_event_mask = 0; - - fscache_stat(&fscache_n_cop_lookup_complete); - object->cache->ops->lookup_complete(object); - fscache_stat_d(&fscache_n_cop_lookup_complete); - - set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags); - - cookie = object->cookie; - set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - - fscache_done_parent_op(object); - return transit_to(KILL_OBJECT); -} - -/* - * Wait for completion of all active operations on this object and the death of - * all child objects of this object. - */ -static const struct fscache_state *fscache_kill_object(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x,%d,%d},%d", - object->debug_id, object->n_ops, object->n_children, event); - - fscache_mark_object_dead(object); - object->oob_event_mask = 0; - - if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) { - /* Reject any new read/write ops and abort any that are pending. */ - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - fscache_cancel_all_ops(object); - } - - if (list_empty(&object->dependents) && - object->n_ops == 0 && - object->n_children == 0) - return transit_to(DROP_OBJECT); - - if (object->n_in_progress == 0) { - spin_lock(&object->lock); - if (object->n_ops > 0 && object->n_in_progress == 0) - fscache_start_operations(object); - spin_unlock(&object->lock); - } - - if (!list_empty(&object->dependents)) - return transit_to(KILL_DEPENDENTS); - - return transit_to(WAIT_FOR_CLEARANCE); -} - -/* - * Kill dependent objects. - */ -static const struct fscache_state *fscache_kill_dependents(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_KILL)) - return NO_TRANSIT; /* Not finished */ - return transit_to(WAIT_FOR_CLEARANCE); -} - -/* - * Drop an object's attachments - */ -static const struct fscache_state *fscache_drop_object(struct fscache_object *object, - int event) -{ - struct fscache_object *parent = object->parent; - struct fscache_cookie *cookie = object->cookie; - struct fscache_cache *cache = object->cache; - bool awaken = false; - - _enter("{OBJ%x,%d},%d", object->debug_id, object->n_children, event); - - ASSERT(cookie != NULL); - ASSERT(!hlist_unhashed(&object->cookie_link)); - - if (test_bit(FSCACHE_COOKIE_AUX_UPDATED, &cookie->flags)) { - _debug("final update"); - fscache_update_aux_data(object); - } - - /* Make sure the cookie no longer points here and that the netfs isn't - * waiting for us. - */ - spin_lock(&cookie->lock); - hlist_del_init(&object->cookie_link); - if (hlist_empty(&cookie->backing_objects) && - test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) - awaken = true; - spin_unlock(&cookie->lock); - - if (awaken) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); - if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - - - /* Prevent a race with our last child, which has to signal EV_CLEARED - * before dropping our spinlock. - */ - spin_lock(&object->lock); - spin_unlock(&object->lock); - - /* Discard from the cache's collection of objects */ - spin_lock(&cache->object_list_lock); - list_del_init(&object->cache_link); - spin_unlock(&cache->object_list_lock); - - fscache_stat(&fscache_n_cop_drop_object); - cache->ops->drop_object(object); - fscache_stat_d(&fscache_n_cop_drop_object); - - /* The parent object wants to know when all it dependents have gone */ - if (parent) { - _debug("release parent OBJ%x {%d}", - parent->debug_id, parent->n_children); - - spin_lock(&parent->lock); - parent->n_children--; - if (parent->n_children == 0) - fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED); - spin_unlock(&parent->lock); - object->parent = NULL; - } - - /* this just shifts the object release to the work processor */ - fscache_put_object(object, fscache_obj_put_drop_obj); - fscache_stat(&fscache_n_object_dead); - - _leave(""); - return transit_to(OBJECT_DEAD); -} - -/* - * get a ref on an object - */ -static int fscache_get_object(struct fscache_object *object, - enum fscache_obj_ref_trace why) -{ - int ret; - - fscache_stat(&fscache_n_cop_grab_object); - ret = object->cache->ops->grab_object(object, why) ? 0 : -EAGAIN; - fscache_stat_d(&fscache_n_cop_grab_object); - return ret; -} - -/* - * Discard a ref on an object - */ -static void fscache_put_object(struct fscache_object *object, - enum fscache_obj_ref_trace why) -{ - fscache_stat(&fscache_n_cop_put_object); - object->cache->ops->put_object(object, why); - fscache_stat_d(&fscache_n_cop_put_object); -} - -/** - * fscache_object_destroy - Note that a cache object is about to be destroyed - * @object: The object to be destroyed - * - * Note the imminent destruction and deallocation of a cache object record. - */ -void fscache_object_destroy(struct fscache_object *object) -{ - /* We can get rid of the cookie now */ - fscache_cookie_put(object->cookie, fscache_cookie_put_object); - object->cookie = NULL; -} -EXPORT_SYMBOL(fscache_object_destroy); - -/* - * enqueue an object for metadata-type processing - */ -void fscache_enqueue_object(struct fscache_object *object) -{ - _enter("{OBJ%x}", object->debug_id); - - if (fscache_get_object(object, fscache_obj_get_queue) >= 0) { - wait_queue_head_t *cong_wq = - &get_cpu_var(fscache_object_cong_wait); - - if (queue_work(fscache_object_wq, &object->work)) { - if (fscache_object_congested()) - wake_up(cong_wq); - } else - fscache_put_object(object, fscache_obj_put_queue); - - put_cpu_var(fscache_object_cong_wait); - } -} - -/** - * fscache_object_sleep_till_congested - Sleep until object wq is congested - * @timeoutp: Scheduler sleep timeout - * - * Allow an object handler to sleep until the object workqueue is congested. - * - * The caller must set up a wake up event before calling this and must have set - * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own - * condition before calling this function as no test is made here. - * - * %true is returned if the object wq is congested, %false otherwise. - */ -bool fscache_object_sleep_till_congested(signed long *timeoutp) -{ - wait_queue_head_t *cong_wq = this_cpu_ptr(&fscache_object_cong_wait); - DEFINE_WAIT(wait); - - if (fscache_object_congested()) - return true; - - add_wait_queue_exclusive(cong_wq, &wait); - if (!fscache_object_congested()) - *timeoutp = schedule_timeout(*timeoutp); - finish_wait(cong_wq, &wait); - - return fscache_object_congested(); -} -EXPORT_SYMBOL_GPL(fscache_object_sleep_till_congested); - -/* - * Enqueue the dependents of an object for metadata-type processing. - * - * If we don't manage to finish the list before the scheduler wants to run - * again then return false immediately. We return true if the list was - * cleared. - */ -static bool fscache_enqueue_dependents(struct fscache_object *object, int event) -{ - struct fscache_object *dep; - bool ret = true; - - _enter("{OBJ%x}", object->debug_id); - - if (list_empty(&object->dependents)) - return true; - - spin_lock(&object->lock); - - while (!list_empty(&object->dependents)) { - dep = list_entry(object->dependents.next, - struct fscache_object, dep_link); - list_del_init(&dep->dep_link); - - fscache_raise_event(dep, event); - fscache_put_object(dep, fscache_obj_put_enq_dep); - - if (!list_empty(&object->dependents) && need_resched()) { - ret = false; - break; - } - } - - spin_unlock(&object->lock); - return ret; -} - -/* - * remove an object from whatever queue it's waiting on - */ -static void fscache_dequeue_object(struct fscache_object *object) -{ - _enter("{OBJ%x}", object->debug_id); - - if (!list_empty(&object->dep_link)) { - spin_lock(&object->parent->lock); - list_del_init(&object->dep_link); - spin_unlock(&object->parent->lock); - } - - _leave(""); -} - -/** - * fscache_check_aux - Ask the netfs whether an object on disk is still valid - * @object: The object to ask about - * @data: The auxiliary data for the object - * @datalen: The size of the auxiliary data - * @object_size: The size of the object according to the server. - * - * This function consults the netfs about the coherency state of an object. - * The caller must be holding a ref on cookie->n_active (held by - * fscache_look_up_object() on behalf of the cache backend during object lookup - * and creation). - */ -enum fscache_checkaux fscache_check_aux(struct fscache_object *object, - const void *data, uint16_t datalen, - loff_t object_size) -{ - enum fscache_checkaux result; - - if (!object->cookie->def->check_aux) { - fscache_stat(&fscache_n_checkaux_none); - return FSCACHE_CHECKAUX_OKAY; - } - - result = object->cookie->def->check_aux(object->cookie->netfs_data, - data, datalen, object_size); - switch (result) { - /* entry okay as is */ - case FSCACHE_CHECKAUX_OKAY: - fscache_stat(&fscache_n_checkaux_okay); - break; - - /* entry requires update */ - case FSCACHE_CHECKAUX_NEEDS_UPDATE: - fscache_stat(&fscache_n_checkaux_update); - break; - - /* entry requires deletion */ - case FSCACHE_CHECKAUX_OBSOLETE: - fscache_stat(&fscache_n_checkaux_obsolete); - break; - - default: - BUG(); - } - - return result; -} -EXPORT_SYMBOL(fscache_check_aux); - -/* - * Asynchronously invalidate an object. - */ -static const struct fscache_state *_fscache_invalidate_object(struct fscache_object *object, - int event) -{ - struct fscache_operation *op; - struct fscache_cookie *cookie = object->cookie; - - _enter("{OBJ%x},%d", object->debug_id, event); - - /* We're going to need the cookie. If the cookie is not available then - * retire the object instead. - */ - if (!fscache_use_cookie(object)) { - ASSERT(radix_tree_empty(&object->cookie->stores)); - set_bit(FSCACHE_OBJECT_RETIRED, &object->flags); - _leave(" [no cookie]"); - return transit_to(KILL_OBJECT); - } - - /* Reject any new read/write ops and abort any that are pending. */ - fscache_invalidate_writes(cookie); - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - fscache_cancel_all_ops(object); - - /* Now we have to wait for in-progress reads and writes */ - op = kzalloc(sizeof(*op), GFP_KERNEL); - if (!op) - goto nomem; - - fscache_operation_init(cookie, op, object->cache->ops->invalidate_object, - NULL, NULL); - op->flags = FSCACHE_OP_ASYNC | - (1 << FSCACHE_OP_EXCLUSIVE) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - trace_fscache_page_op(cookie, NULL, op, fscache_page_op_invalidate); - - spin_lock(&cookie->lock); - if (fscache_submit_exclusive_op(object, op) < 0) - goto submit_op_failed; - spin_unlock(&cookie->lock); - fscache_put_operation(op); - - /* Once we've completed the invalidation, we know there will be no data - * stored in the cache and thus we can reinstate the data-check-skip - * optimisation. - */ - set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - - /* We can allow read and write requests to come in once again. They'll - * queue up behind our exclusive invalidation operation. - */ - if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); - _leave(" [ok]"); - return transit_to(UPDATE_OBJECT); - -nomem: - fscache_mark_object_dead(object); - fscache_unuse_cookie(object); - _leave(" [ENOMEM]"); - return transit_to(KILL_OBJECT); - -submit_op_failed: - fscache_mark_object_dead(object); - spin_unlock(&cookie->lock); - fscache_unuse_cookie(object); - kfree(op); - _leave(" [EIO]"); - return transit_to(KILL_OBJECT); -} - -static const struct fscache_state *fscache_invalidate_object(struct fscache_object *object, - int event) -{ - const struct fscache_state *s; - - fscache_stat(&fscache_n_invalidates_run); - fscache_stat(&fscache_n_cop_invalidate_object); - s = _fscache_invalidate_object(object, event); - fscache_stat_d(&fscache_n_cop_invalidate_object); - return s; -} - -/* - * Update auxiliary data. - */ -static void fscache_update_aux_data(struct fscache_object *object) -{ - fscache_stat(&fscache_n_updates_run); - fscache_stat(&fscache_n_cop_update_object); - object->cache->ops->update_object(object); - fscache_stat_d(&fscache_n_cop_update_object); -} - -/* - * Asynchronously update an object. - */ -static const struct fscache_state *fscache_update_object(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - fscache_update_aux_data(object); - - _leave(""); - return transit_to(WAIT_FOR_CMD); -} - -/** - * fscache_object_retrying_stale - Note retrying stale object - * @object: The object that will be retried - * - * Note that an object lookup found an on-disk object that was adjudged to be - * stale and has been deleted. The lookup will be retried. - */ -void fscache_object_retrying_stale(struct fscache_object *object) -{ - fscache_stat(&fscache_n_cache_no_space_reject); -} -EXPORT_SYMBOL(fscache_object_retrying_stale); - -/** - * fscache_object_mark_killed - Note that an object was killed - * @object: The object that was culled - * @why: The reason the object was killed. - * - * Note that an object was killed. Returns true if the object was - * already marked killed, false if it wasn't. - */ -void fscache_object_mark_killed(struct fscache_object *object, - enum fscache_why_object_killed why) -{ - if (test_and_set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags)) { - pr_err("Error: Object already killed by cache [%s]\n", - object->cache->identifier); - return; - } - - switch (why) { - case FSCACHE_OBJECT_NO_SPACE: - fscache_stat(&fscache_n_cache_no_space_reject); - break; - case FSCACHE_OBJECT_IS_STALE: - fscache_stat(&fscache_n_cache_stale_objects); - break; - case FSCACHE_OBJECT_WAS_RETIRED: - fscache_stat(&fscache_n_cache_retired_objects); - break; - case FSCACHE_OBJECT_WAS_CULLED: - fscache_stat(&fscache_n_cache_culled_objects); - break; - } -} -EXPORT_SYMBOL(fscache_object_mark_killed); - -/* - * The object is dead. We can get here if an object gets queued by an event - * that would lead to its death (such as EV_KILL) when the dispatcher is - * already running (and so can be requeued) but hasn't yet cleared the event - * mask. - */ -static const struct fscache_state *fscache_object_dead(struct fscache_object *object, - int event) -{ - if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD, - &object->flags)) - return NO_TRANSIT; - - WARN(true, "FS-Cache object redispatched after death"); - return NO_TRANSIT; -} diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c deleted file mode 100644 index e002cdfaf3cc..000000000000 --- a/fs/fscache/operation.c +++ /dev/null @@ -1,633 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache worker operation management routines - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * See Documentation/filesystems/caching/operations.rst - */ - -#define FSCACHE_DEBUG_LEVEL OPERATION -#include <linux/module.h> -#include <linux/seq_file.h> -#include <linux/slab.h> -#include "internal.h" - -atomic_t fscache_op_debug_id; -EXPORT_SYMBOL(fscache_op_debug_id); - -static void fscache_operation_dummy_cancel(struct fscache_operation *op) -{ -} - -/** - * fscache_operation_init - Do basic initialisation of an operation - * @cookie: The cookie to operate on - * @op: The operation to initialise - * @processor: The function to perform the operation - * @cancel: A function to handle operation cancellation - * @release: The release function to assign - * - * Do basic initialisation of an operation. The caller must still set flags, - * object and processor if needed. - */ -void fscache_operation_init(struct fscache_cookie *cookie, - struct fscache_operation *op, - fscache_operation_processor_t processor, - fscache_operation_cancel_t cancel, - fscache_operation_release_t release) -{ - INIT_WORK(&op->work, fscache_op_work_func); - atomic_set(&op->usage, 1); - op->state = FSCACHE_OP_ST_INITIALISED; - op->debug_id = atomic_inc_return(&fscache_op_debug_id); - op->processor = processor; - op->cancel = cancel ?: fscache_operation_dummy_cancel; - op->release = release; - INIT_LIST_HEAD(&op->pend_link); - fscache_stat(&fscache_n_op_initialised); - trace_fscache_op(cookie, op, fscache_op_init); -} -EXPORT_SYMBOL(fscache_operation_init); - -/** - * fscache_enqueue_operation - Enqueue an operation for processing - * @op: The operation to enqueue - * - * Enqueue an operation for processing by the FS-Cache thread pool. - * - * This will get its own ref on the object. - */ -void fscache_enqueue_operation(struct fscache_operation *op) -{ - struct fscache_cookie *cookie = op->object->cookie; - - _enter("{OBJ%x OP%x,%u}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); - - ASSERT(list_empty(&op->pend_link)); - ASSERT(op->processor != NULL); - ASSERT(fscache_object_is_available(op->object)); - ASSERTCMP(atomic_read(&op->usage), >, 0); - ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS, - op->state, ==, FSCACHE_OP_ST_CANCELLED); - - fscache_stat(&fscache_n_op_enqueue); - switch (op->flags & FSCACHE_OP_TYPE) { - case FSCACHE_OP_ASYNC: - trace_fscache_op(cookie, op, fscache_op_enqueue_async); - _debug("queue async"); - atomic_inc(&op->usage); - if (!queue_work(fscache_op_wq, &op->work)) - fscache_put_operation(op); - break; - case FSCACHE_OP_MYTHREAD: - trace_fscache_op(cookie, op, fscache_op_enqueue_mythread); - _debug("queue for caller's attention"); - break; - default: - pr_err("Unexpected op type %lx", op->flags); - BUG(); - break; - } -} -EXPORT_SYMBOL(fscache_enqueue_operation); - -/* - * start an op running - */ -static void fscache_run_op(struct fscache_object *object, - struct fscache_operation *op) -{ - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING); - - op->state = FSCACHE_OP_ST_IN_PROGRESS; - object->n_in_progress++; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - if (op->processor) - fscache_enqueue_operation(op); - else - trace_fscache_op(object->cookie, op, fscache_op_run); - fscache_stat(&fscache_n_op_run); -} - -/* - * report an unexpected submission - */ -static void fscache_report_unexpected_submission(struct fscache_object *object, - struct fscache_operation *op, - const struct fscache_state *ostate) -{ - static bool once_only; - struct fscache_operation *p; - unsigned n; - - if (once_only) - return; - once_only = true; - - kdebug("unexpected submission OP%x [OBJ%x %s]", - op->debug_id, object->debug_id, object->state->name); - kdebug("objstate=%s [%s]", object->state->name, ostate->name); - kdebug("objflags=%lx", object->flags); - kdebug("objevent=%lx [%lx]", object->events, object->event_mask); - kdebug("ops=%u inp=%u exc=%u", - object->n_ops, object->n_in_progress, object->n_exclusive); - - if (!list_empty(&object->pending_ops)) { - n = 0; - list_for_each_entry(p, &object->pending_ops, pend_link) { - ASSERTCMP(p->object, ==, object); - kdebug("%p %p", op->processor, op->release); - n++; - } - - kdebug("n=%u", n); - } - - dump_stack(); -} - -/* - * submit an exclusive operation for an object - * - other ops are excluded from running simultaneously with this one - * - this gets any extra refs it needs on an op - */ -int fscache_submit_exclusive_op(struct fscache_object *object, - struct fscache_operation *op) -{ - const struct fscache_state *ostate; - unsigned long flags; - int ret; - - _enter("{OBJ%x OP%x},", object->debug_id, op->debug_id); - - trace_fscache_op(object->cookie, op, fscache_op_submit_ex); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED); - ASSERTCMP(atomic_read(&op->usage), >, 0); - - spin_lock(&object->lock); - ASSERTCMP(object->n_ops, >=, object->n_in_progress); - ASSERTCMP(object->n_ops, >=, object->n_exclusive); - ASSERT(list_empty(&op->pend_link)); - - ostate = object->state; - smp_rmb(); - - op->state = FSCACHE_OP_ST_PENDING; - flags = READ_ONCE(object->flags); - if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) { - fscache_stat(&fscache_n_op_rejected); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else if (unlikely(fscache_cache_is_broken(object))) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -EIO; - } else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) { - op->object = object; - object->n_ops++; - object->n_exclusive++; /* reads and writes must wait */ - - if (object->n_in_progress > 0) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - } else if (!list_empty(&object->pending_ops)) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - fscache_start_operations(object); - } else { - ASSERTCMP(object->n_in_progress, ==, 0); - fscache_run_op(object, op); - } - - /* need to issue a new write op after this */ - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) { - op->object = object; - object->n_ops++; - object->n_exclusive++; /* reads and writes must wait */ - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else { - fscache_report_unexpected_submission(object, op, ostate); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } - - spin_unlock(&object->lock); - return ret; -} - -/* - * submit an operation for an object - * - objects may be submitted only in the following states: - * - during object creation (write ops may be submitted) - * - whilst the object is active - * - after an I/O error incurred in one of the two above states (op rejected) - * - this gets any extra refs it needs on an op - */ -int fscache_submit_op(struct fscache_object *object, - struct fscache_operation *op) -{ - const struct fscache_state *ostate; - unsigned long flags; - int ret; - - _enter("{OBJ%x OP%x},{%u}", - object->debug_id, op->debug_id, atomic_read(&op->usage)); - - trace_fscache_op(object->cookie, op, fscache_op_submit); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED); - ASSERTCMP(atomic_read(&op->usage), >, 0); - - spin_lock(&object->lock); - ASSERTCMP(object->n_ops, >=, object->n_in_progress); - ASSERTCMP(object->n_ops, >=, object->n_exclusive); - ASSERT(list_empty(&op->pend_link)); - - ostate = object->state; - smp_rmb(); - - op->state = FSCACHE_OP_ST_PENDING; - flags = READ_ONCE(object->flags); - if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) { - fscache_stat(&fscache_n_op_rejected); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else if (unlikely(fscache_cache_is_broken(object))) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -EIO; - } else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) { - op->object = object; - object->n_ops++; - - if (object->n_exclusive > 0) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - } else if (!list_empty(&object->pending_ops)) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - fscache_start_operations(object); - } else { - ASSERTCMP(object->n_exclusive, ==, 0); - fscache_run_op(object, op); - } - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) { - op->object = object; - object->n_ops++; - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else { - fscache_report_unexpected_submission(object, op, ostate); - ASSERT(!fscache_object_is_active(object)); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } - - spin_unlock(&object->lock); - return ret; -} - -/* - * queue an object for withdrawal on error, aborting all following asynchronous - * operations - */ -void fscache_abort_object(struct fscache_object *object) -{ - _enter("{OBJ%x}", object->debug_id); - - fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR); -} - -/* - * Jump start the operation processing on an object. The caller must hold - * object->lock. - */ -void fscache_start_operations(struct fscache_object *object) -{ - struct fscache_operation *op; - bool stop = false; - - while (!list_empty(&object->pending_ops) && !stop) { - op = list_entry(object->pending_ops.next, - struct fscache_operation, pend_link); - - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) { - if (object->n_in_progress > 0) - break; - stop = true; - } - list_del_init(&op->pend_link); - fscache_run_op(object, op); - - /* the pending queue was holding a ref on the object */ - fscache_put_operation(op); - } - - ASSERTCMP(object->n_in_progress, <=, object->n_ops); - - _debug("woke %d ops on OBJ%x", - object->n_in_progress, object->debug_id); -} - -/* - * cancel an operation that's pending on an object - */ -int fscache_cancel_op(struct fscache_operation *op, - bool cancel_in_progress_op) -{ - struct fscache_object *object = op->object; - bool put = false; - int ret; - - _enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id); - - trace_fscache_op(object->cookie, op, fscache_op_cancel); - - ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING); - ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED); - ASSERTCMP(atomic_read(&op->usage), >, 0); - - spin_lock(&object->lock); - - ret = -EBUSY; - if (op->state == FSCACHE_OP_ST_PENDING) { - ASSERT(!list_empty(&op->pend_link)); - list_del_init(&op->pend_link); - put = true; - - fscache_stat(&fscache_n_op_cancelled); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - ret = 0; - } else if (op->state == FSCACHE_OP_ST_IN_PROGRESS && cancel_in_progress_op) { - ASSERTCMP(object->n_in_progress, >, 0); - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - object->n_in_progress--; - if (object->n_in_progress == 0) - fscache_start_operations(object); - - fscache_stat(&fscache_n_op_cancelled); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - ret = 0; - } - - if (put) - fscache_put_operation(op); - spin_unlock(&object->lock); - _leave(" = %d", ret); - return ret; -} - -/* - * Cancel all pending operations on an object - */ -void fscache_cancel_all_ops(struct fscache_object *object) -{ - struct fscache_operation *op; - - _enter("OBJ%x", object->debug_id); - - spin_lock(&object->lock); - - while (!list_empty(&object->pending_ops)) { - op = list_entry(object->pending_ops.next, - struct fscache_operation, pend_link); - fscache_stat(&fscache_n_op_cancelled); - list_del_init(&op->pend_link); - - trace_fscache_op(object->cookie, op, fscache_op_cancel_all); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - fscache_put_operation(op); - cond_resched_lock(&object->lock); - } - - spin_unlock(&object->lock); - _leave(""); -} - -/* - * Record the completion or cancellation of an in-progress operation. - */ -void fscache_op_complete(struct fscache_operation *op, bool cancelled) -{ - struct fscache_object *object = op->object; - - _enter("OBJ%x", object->debug_id); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS); - ASSERTCMP(object->n_in_progress, >, 0); - ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags), - object->n_exclusive, >, 0); - ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags), - object->n_in_progress, ==, 1); - - spin_lock(&object->lock); - - if (!cancelled) { - trace_fscache_op(object->cookie, op, fscache_op_completed); - op->state = FSCACHE_OP_ST_COMPLETE; - } else { - op->cancel(op); - trace_fscache_op(object->cookie, op, fscache_op_cancelled); - op->state = FSCACHE_OP_ST_CANCELLED; - } - - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - object->n_in_progress--; - if (object->n_in_progress == 0) - fscache_start_operations(object); - - spin_unlock(&object->lock); - _leave(""); -} -EXPORT_SYMBOL(fscache_op_complete); - -/* - * release an operation - * - queues pending ops if this is the last in-progress op - */ -void fscache_put_operation(struct fscache_operation *op) -{ - struct fscache_object *object; - struct fscache_cache *cache; - - _enter("{OBJ%x OP%x,%d}", - op->object ? op->object->debug_id : 0, - op->debug_id, atomic_read(&op->usage)); - - ASSERTCMP(atomic_read(&op->usage), >, 0); - - if (!atomic_dec_and_test(&op->usage)) - return; - - trace_fscache_op(op->object ? op->object->cookie : NULL, op, fscache_op_put); - - _debug("PUT OP"); - ASSERTIFCMP(op->state != FSCACHE_OP_ST_INITIALISED && - op->state != FSCACHE_OP_ST_COMPLETE, - op->state, ==, FSCACHE_OP_ST_CANCELLED); - - fscache_stat(&fscache_n_op_release); - - if (op->release) { - op->release(op); - op->release = NULL; - } - op->state = FSCACHE_OP_ST_DEAD; - - object = op->object; - if (likely(object)) { - if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) - atomic_dec(&object->n_reads); - if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags)) - fscache_unuse_cookie(object); - - /* now... we may get called with the object spinlock held, so we - * complete the cleanup here only if we can immediately acquire the - * lock, and defer it otherwise */ - if (!spin_trylock(&object->lock)) { - _debug("defer put"); - fscache_stat(&fscache_n_op_deferred_release); - - cache = object->cache; - spin_lock(&cache->op_gc_list_lock); - list_add_tail(&op->pend_link, &cache->op_gc_list); - spin_unlock(&cache->op_gc_list_lock); - schedule_work(&cache->op_gc); - _leave(" [defer]"); - return; - } - - ASSERTCMP(object->n_ops, >, 0); - object->n_ops--; - if (object->n_ops == 0) - fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED); - - spin_unlock(&object->lock); - } - - kfree(op); - _leave(" [done]"); -} -EXPORT_SYMBOL(fscache_put_operation); - -/* - * garbage collect operations that have had their release deferred - */ -void fscache_operation_gc(struct work_struct *work) -{ - struct fscache_operation *op; - struct fscache_object *object; - struct fscache_cache *cache = - container_of(work, struct fscache_cache, op_gc); - int count = 0; - - _enter(""); - - do { - spin_lock(&cache->op_gc_list_lock); - if (list_empty(&cache->op_gc_list)) { - spin_unlock(&cache->op_gc_list_lock); - break; - } - - op = list_entry(cache->op_gc_list.next, - struct fscache_operation, pend_link); - list_del(&op->pend_link); - spin_unlock(&cache->op_gc_list_lock); - - object = op->object; - trace_fscache_op(object->cookie, op, fscache_op_gc); - - spin_lock(&object->lock); - - _debug("GC DEFERRED REL OBJ%x OP%x", - object->debug_id, op->debug_id); - fscache_stat(&fscache_n_op_gc); - - ASSERTCMP(atomic_read(&op->usage), ==, 0); - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD); - - ASSERTCMP(object->n_ops, >, 0); - object->n_ops--; - if (object->n_ops == 0) - fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED); - - spin_unlock(&object->lock); - kfree(op); - - } while (count++ < 20); - - if (!list_empty(&cache->op_gc_list)) - schedule_work(&cache->op_gc); - - _leave(""); -} - -/* - * execute an operation using fs_op_wq to provide processing context - - * the caller holds a ref to this object, so we don't need to hold one - */ -void fscache_op_work_func(struct work_struct *work) -{ - struct fscache_operation *op = - container_of(work, struct fscache_operation, work); - - _enter("{OBJ%x OP%x,%d}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); - - trace_fscache_op(op->object->cookie, op, fscache_op_work); - - ASSERT(op->processor != NULL); - op->processor(op); - fscache_put_operation(op); - - _leave(""); -} diff --git a/fs/fscache/page.c b/fs/fscache/page.c deleted file mode 100644 index 27df94ef0e0b..000000000000 --- a/fs/fscache/page.c +++ /dev/null @@ -1,1242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Cache page management and data I/O routines - * - * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL PAGE -#include <linux/module.h> -#include <linux/fscache-cache.h> -#include <linux/buffer_head.h> -#include <linux/pagevec.h> -#include <linux/slab.h> -#include "internal.h" - -/* - * check to see if a page is being written to the cache - */ -bool __fscache_check_page_write(struct fscache_cookie *cookie, struct page *page) -{ - void *val; - - rcu_read_lock(); - val = radix_tree_lookup(&cookie->stores, page->index); - rcu_read_unlock(); - trace_fscache_check_page(cookie, page, val, 0); - - return val != NULL; -} -EXPORT_SYMBOL(__fscache_check_page_write); - -/* - * wait for a page to finish being written to the cache - */ -void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page) -{ - wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0); - - trace_fscache_page(cookie, page, fscache_page_write_wait); - - wait_event(*wq, !__fscache_check_page_write(cookie, page)); -} -EXPORT_SYMBOL(__fscache_wait_on_page_write); - -/* - * wait for a page to finish being written to the cache. Put a timeout here - * since we might be called recursively via parent fs. - */ -static -bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) -{ - wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0); - - return wait_event_timeout(*wq, !__fscache_check_page_write(cookie, page), - HZ); -} - -/* - * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged - */ -bool __fscache_maybe_release_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - struct page *xpage; - void *val; - - _enter("%p,%p,%x", cookie, page, gfp); - - trace_fscache_page(cookie, page, fscache_page_maybe_release); - -try_again: - rcu_read_lock(); - val = radix_tree_lookup(&cookie->stores, page->index); - if (!val) { - rcu_read_unlock(); - fscache_stat(&fscache_n_store_vmscan_not_storing); - __fscache_uncache_page(cookie, page); - return true; - } - - /* see if the page is actually undergoing storage - if so we can't get - * rid of it till the cache has finished with it */ - if (radix_tree_tag_get(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG)) { - rcu_read_unlock(); - goto page_busy; - } - - /* the page is pending storage, so we attempt to cancel the store and - * discard the store request so that the page can be reclaimed */ - spin_lock(&cookie->stores_lock); - rcu_read_unlock(); - - if (radix_tree_tag_get(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG)) { - /* the page started to undergo storage whilst we were looking, - * so now we can only wait or return */ - spin_unlock(&cookie->stores_lock); - goto page_busy; - } - - xpage = radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - spin_unlock(&cookie->stores_lock); - - if (xpage) { - fscache_stat(&fscache_n_store_vmscan_cancelled); - fscache_stat(&fscache_n_store_radix_deletes); - ASSERTCMP(xpage, ==, page); - } else { - fscache_stat(&fscache_n_store_vmscan_gone); - } - - wake_up_bit(&cookie->flags, 0); - trace_fscache_wake_cookie(cookie); - if (xpage) - put_page(xpage); - __fscache_uncache_page(cookie, page); - return true; - -page_busy: - /* We will wait here if we're allowed to, but that could deadlock the - * allocator as the work threads writing to the cache may all end up - * sleeping on memory allocation, so we may need to impose a timeout - * too. */ - if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { - fscache_stat(&fscache_n_store_vmscan_busy); - return false; - } - - fscache_stat(&fscache_n_store_vmscan_wait); - if (!release_page_wait_timeout(cookie, page)) - _debug("fscache writeout timeout page: %p{%lx}", - page, page->index); - - gfp &= ~__GFP_DIRECT_RECLAIM; - goto try_again; -} -EXPORT_SYMBOL(__fscache_maybe_release_page); - -/* - * note that a page has finished being written to the cache - */ -static void fscache_end_page_write(struct fscache_object *object, - struct page *page) -{ - struct fscache_cookie *cookie; - struct page *xpage = NULL, *val; - - spin_lock(&object->lock); - cookie = object->cookie; - if (cookie) { - /* delete the page from the tree if it is now no longer - * pending */ - spin_lock(&cookie->stores_lock); - radix_tree_tag_clear(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG); - trace_fscache_page(cookie, page, fscache_page_radix_clear_store); - if (!radix_tree_tag_get(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG)) { - fscache_stat(&fscache_n_store_radix_deletes); - xpage = radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - trace_fscache_page(cookie, page, fscache_page_write_end); - - val = radix_tree_lookup(&cookie->stores, page->index); - trace_fscache_check_page(cookie, page, val, 1); - } else { - trace_fscache_page(cookie, page, fscache_page_write_end_pend); - } - spin_unlock(&cookie->stores_lock); - wake_up_bit(&cookie->flags, 0); - trace_fscache_wake_cookie(cookie); - } else { - trace_fscache_page(cookie, page, fscache_page_write_end_noc); - } - spin_unlock(&object->lock); - if (xpage) - put_page(xpage); -} - -/* - * actually apply the changed attributes to a cache object - */ -static void fscache_attr_changed_op(struct fscache_operation *op) -{ - struct fscache_object *object = op->object; - int ret; - - _enter("{OBJ%x OP%x}", object->debug_id, op->debug_id); - - fscache_stat(&fscache_n_attr_changed_calls); - - if (fscache_object_is_active(object)) { - fscache_stat(&fscache_n_cop_attr_changed); - ret = object->cache->ops->attr_changed(object); - fscache_stat_d(&fscache_n_cop_attr_changed); - if (ret < 0) - fscache_abort_object(object); - fscache_op_complete(op, ret < 0); - } else { - fscache_op_complete(op, true); - } - - _leave(""); -} - -/* - * notification that the attributes on an object have changed - */ -int __fscache_attr_changed(struct fscache_cookie *cookie) -{ - struct fscache_operation *op; - struct fscache_object *object; - bool wake_cookie = false; - - _enter("%p", cookie); - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - - fscache_stat(&fscache_n_attr_changed); - - op = kzalloc(sizeof(*op), GFP_KERNEL); - if (!op) { - fscache_stat(&fscache_n_attr_changed_nomem); - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - fscache_operation_init(cookie, op, fscache_attr_changed_op, NULL, NULL); - trace_fscache_page_op(cookie, NULL, op, fscache_page_op_attr_changed); - op->flags = FSCACHE_OP_ASYNC | - (1 << FSCACHE_OP_EXCLUSIVE) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - if (fscache_submit_exclusive_op(object, op) < 0) - goto nobufs_dec; - spin_unlock(&cookie->lock); - fscache_stat(&fscache_n_attr_changed_ok); - fscache_put_operation(op); - _leave(" = 0"); - return 0; - -nobufs_dec: - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs: - spin_unlock(&cookie->lock); - fscache_put_operation(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - fscache_stat(&fscache_n_attr_changed_nobufs); - _leave(" = %d", -ENOBUFS); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_attr_changed); - -/* - * Handle cancellation of a pending retrieval op - */ -static void fscache_do_cancel_retrieval(struct fscache_operation *_op) -{ - struct fscache_retrieval *op = - container_of(_op, struct fscache_retrieval, op); - - atomic_set(&op->n_pages, 0); -} - -/* - * release a retrieval op reference - */ -static void fscache_release_retrieval_op(struct fscache_operation *_op) -{ - struct fscache_retrieval *op = - container_of(_op, struct fscache_retrieval, op); - - _enter("{OP%x}", op->op.debug_id); - - ASSERTIFCMP(op->op.state != FSCACHE_OP_ST_INITIALISED, - atomic_read(&op->n_pages), ==, 0); - - if (op->context) - fscache_put_context(op->cookie, op->context); - - _leave(""); -} - -/* - * allocate a retrieval op - */ -struct fscache_retrieval *fscache_alloc_retrieval( - struct fscache_cookie *cookie, - struct address_space *mapping, - fscache_rw_complete_t end_io_func, - void *context) -{ - struct fscache_retrieval *op; - - /* allocate a retrieval operation and attempt to submit it */ - op = kzalloc(sizeof(*op), GFP_NOIO); - if (!op) { - fscache_stat(&fscache_n_retrievals_nomem); - return NULL; - } - - fscache_operation_init(cookie, &op->op, NULL, - fscache_do_cancel_retrieval, - fscache_release_retrieval_op); - op->op.flags = FSCACHE_OP_MYTHREAD | - (1UL << FSCACHE_OP_WAITING) | - (1UL << FSCACHE_OP_UNUSE_COOKIE); - op->cookie = cookie; - op->mapping = mapping; - op->end_io_func = end_io_func; - op->context = context; - INIT_LIST_HEAD(&op->to_do); - - /* Pin the netfs read context in case we need to do the actual netfs - * read because we've encountered a cache read failure. - */ - if (context) - fscache_get_context(op->cookie, context); - return op; -} - -/* - * wait for a deferred lookup to complete - */ -int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) -{ - _enter(""); - - if (!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) { - _leave(" = 0 [imm]"); - return 0; - } - - fscache_stat(&fscache_n_retrievals_wait); - - if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - TASK_INTERRUPTIBLE) != 0) { - fscache_stat(&fscache_n_retrievals_intr); - _leave(" = -ERESTARTSYS"); - return -ERESTARTSYS; - } - - ASSERT(!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)); - - smp_rmb(); - _leave(" = 0 [dly]"); - return 0; -} - -/* - * wait for an object to become active (or dead) - */ -int fscache_wait_for_operation_activation(struct fscache_object *object, - struct fscache_operation *op, - atomic_t *stat_op_waits, - atomic_t *stat_object_dead) -{ - int ret; - - if (!test_bit(FSCACHE_OP_WAITING, &op->flags)) - goto check_if_dead; - - _debug(">>> WT"); - if (stat_op_waits) - fscache_stat(stat_op_waits); - if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - TASK_INTERRUPTIBLE) != 0) { - trace_fscache_op(object->cookie, op, fscache_op_signal); - ret = fscache_cancel_op(op, false); - if (ret == 0) - return -ERESTARTSYS; - - /* it's been removed from the pending queue by another party, - * so we should get to run shortly */ - wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - TASK_UNINTERRUPTIBLE); - } - _debug("<<< GO"); - -check_if_dead: - if (op->state == FSCACHE_OP_ST_CANCELLED) { - if (stat_object_dead) - fscache_stat(stat_object_dead); - _leave(" = -ENOBUFS [cancelled]"); - return -ENOBUFS; - } - if (unlikely(fscache_object_is_dying(object) || - fscache_cache_is_broken(object))) { - enum fscache_operation_state state = op->state; - trace_fscache_op(object->cookie, op, fscache_op_signal); - fscache_cancel_op(op, true); - if (stat_object_dead) - fscache_stat(stat_object_dead); - _leave(" = -ENOBUFS [obj dead %d]", state); - return -ENOBUFS; - } - return 0; -} - -/* - * read a page from the cache or allocate a block in which to store it - * - we return: - * -ENOMEM - out of memory, nothing done - * -ERESTARTSYS - interrupted - * -ENOBUFS - no backing object available in which to cache the block - * -ENODATA - no data available in the backing object for this block - * 0 - dispatched a read - it'll call end_io_func() when finished - */ -int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, - struct page *page, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,%p,,,", cookie, page); - - fscache_stat(&fscache_n_retrievals); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(page, !=, NULL); - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, page->mapping, - end_io_func, context); - if (!op) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - atomic_set(&op->n_pages, 1); - trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_retr_one); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - ASSERT(test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)); - - __fscache_use_cookie(cookie); - atomic_inc(&object->n_reads); - __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); - - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_retrieval_ops); - - /* we wait for the operation to become active, and then process it - * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { - fscache_stat(&fscache_n_cop_allocate_page); - ret = object->cache->ops->allocate_page(op, page, gfp); - fscache_stat_d(&fscache_n_cop_allocate_page); - if (ret == 0) - ret = -ENODATA; - } else { - fscache_stat(&fscache_n_cop_read_or_alloc_page); - ret = object->cache->ops->read_or_alloc_page(op, page, gfp); - fscache_stat_d(&fscache_n_cop_read_or_alloc_page); - } - -error: - if (ret == -ENOMEM) - fscache_stat(&fscache_n_retrievals_nomem); - else if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_retrievals_intr); - else if (ret == -ENODATA) - fscache_stat(&fscache_n_retrievals_nodata); - else if (ret < 0) - fscache_stat(&fscache_n_retrievals_nobufs); - else - fscache_stat(&fscache_n_retrievals_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - atomic_dec(&object->n_reads); - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - fscache_put_retrieval(op); -nobufs: - fscache_stat(&fscache_n_retrievals_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_read_or_alloc_page); - -/* - * read a list of page from the cache or allocate a block in which to store - * them - * - we return: - * -ENOMEM - out of memory, some pages may be being read - * -ERESTARTSYS - interrupted, some pages may be being read - * -ENOBUFS - no backing object or space available in which to cache any - * pages not being read - * -ENODATA - no data available in the backing object for some or all of - * the pages - * 0 - dispatched a read on all pages - * - * end_io_func() will be called for each page read from the cache as it is - * finishes being read - * - * any pages for which a read is dispatched will be removed from pages and - * nr_pages - */ -int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,,%d,,,", cookie, *nr_pages); - - fscache_stat(&fscache_n_retrievals); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(*nr_pages, >, 0); - ASSERT(!list_empty(pages)); - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, mapping, end_io_func, context); - if (!op) - return -ENOMEM; - atomic_set(&op->n_pages, *nr_pages); - trace_fscache_page_op(cookie, NULL, &op->op, fscache_page_op_retr_multi); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - atomic_inc(&object->n_reads); - __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); - - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_retrieval_ops); - - /* we wait for the operation to become active, and then process it - * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { - fscache_stat(&fscache_n_cop_allocate_pages); - ret = object->cache->ops->allocate_pages( - op, pages, nr_pages, gfp); - fscache_stat_d(&fscache_n_cop_allocate_pages); - } else { - fscache_stat(&fscache_n_cop_read_or_alloc_pages); - ret = object->cache->ops->read_or_alloc_pages( - op, pages, nr_pages, gfp); - fscache_stat_d(&fscache_n_cop_read_or_alloc_pages); - } - -error: - if (ret == -ENOMEM) - fscache_stat(&fscache_n_retrievals_nomem); - else if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_retrievals_intr); - else if (ret == -ENODATA) - fscache_stat(&fscache_n_retrievals_nodata); - else if (ret < 0) - fscache_stat(&fscache_n_retrievals_nobufs); - else - fscache_stat(&fscache_n_retrievals_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - atomic_dec(&object->n_reads); - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - fscache_put_retrieval(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); -nobufs: - fscache_stat(&fscache_n_retrievals_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_read_or_alloc_pages); - -/* - * allocate a block in the cache on which to store a page - * - we return: - * -ENOMEM - out of memory, nothing done - * -ERESTARTSYS - interrupted - * -ENOBUFS - no backing object available in which to cache the block - * 0 - block allocated - */ -int __fscache_alloc_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,%p,,,", cookie, page); - - fscache_stat(&fscache_n_allocs); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(page, !=, NULL); - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, page->mapping, NULL, NULL); - if (!op) - return -ENOMEM; - atomic_set(&op->n_pages, 1); - trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_alloc_one); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_alloc_ops); - - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_alloc_op_waits), - __fscache_stat(&fscache_n_allocs_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - fscache_stat(&fscache_n_cop_allocate_page); - ret = object->cache->ops->allocate_page(op, page, gfp); - fscache_stat_d(&fscache_n_cop_allocate_page); - -error: - if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_allocs_intr); - else if (ret < 0) - fscache_stat(&fscache_n_allocs_nobufs); - else - fscache_stat(&fscache_n_allocs_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - fscache_put_retrieval(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); -nobufs: - fscache_stat(&fscache_n_allocs_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_alloc_page); - -/* - * Unmark pages allocate in the readahead code path (via: - * fscache_readpages_or_alloc) after delegating to the base filesystem - */ -void __fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages) -{ - struct page *page; - - list_for_each_entry(page, pages, lru) { - if (PageFsCache(page)) - __fscache_uncache_page(cookie, page); - } -} -EXPORT_SYMBOL(__fscache_readpages_cancel); - -/* - * release a write op reference - */ -static void fscache_release_write_op(struct fscache_operation *_op) -{ - _enter("{OP%x}", _op->debug_id); -} - -/* - * perform the background storage of a page into the cache - */ -static void fscache_write_op(struct fscache_operation *_op) -{ - struct fscache_storage *op = - container_of(_op, struct fscache_storage, op); - struct fscache_object *object = op->op.object; - struct fscache_cookie *cookie; - struct page *page; - unsigned n; - void *results[1]; - int ret; - - _enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage)); - -again: - spin_lock(&object->lock); - cookie = object->cookie; - - if (!fscache_object_is_active(object)) { - /* If we get here, then the on-disk cache object likely no - * longer exists, so we should just cancel this write - * operation. - */ - spin_unlock(&object->lock); - fscache_op_complete(&op->op, true); - _leave(" [inactive]"); - return; - } - - if (!cookie) { - /* If we get here, then the cookie belonging to the object was - * detached, probably by the cookie being withdrawn due to - * memory pressure, which means that the pages we might write - * to the cache from no longer exist - therefore, we can just - * cancel this write operation. - */ - spin_unlock(&object->lock); - fscache_op_complete(&op->op, true); - _leave(" [cancel] op{f=%lx s=%u} obj{s=%s f=%lx}", - _op->flags, _op->state, object->state->short_name, - object->flags); - return; - } - - spin_lock(&cookie->stores_lock); - - fscache_stat(&fscache_n_store_calls); - - /* find a page to store */ - results[0] = NULL; - page = NULL; - n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, 1, - FSCACHE_COOKIE_PENDING_TAG); - trace_fscache_gang_lookup(cookie, &op->op, results, n, op->store_limit); - if (n != 1) - goto superseded; - page = results[0]; - _debug("gang %d [%lx]", n, page->index); - - radix_tree_tag_set(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG); - radix_tree_tag_clear(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG); - trace_fscache_page(cookie, page, fscache_page_radix_pend2store); - - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); - - if (page->index >= op->store_limit) - goto discard_page; - - fscache_stat(&fscache_n_store_pages); - fscache_stat(&fscache_n_cop_write_page); - ret = object->cache->ops->write_page(op, page); - fscache_stat_d(&fscache_n_cop_write_page); - trace_fscache_wrote_page(cookie, page, &op->op, ret); - fscache_end_page_write(object, page); - if (ret < 0) { - fscache_abort_object(object); - fscache_op_complete(&op->op, true); - } else { - fscache_enqueue_operation(&op->op); - } - - _leave(""); - return; - -discard_page: - fscache_stat(&fscache_n_store_pages_over_limit); - trace_fscache_wrote_page(cookie, page, &op->op, -ENOBUFS); - fscache_end_page_write(object, page); - goto again; - -superseded: - /* this writer is going away and there aren't any more things to - * write */ - _debug("cease"); - spin_unlock(&cookie->stores_lock); - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - spin_unlock(&object->lock); - fscache_op_complete(&op->op, false); - _leave(""); -} - -/* - * Clear the pages pending writing for invalidation - */ -void fscache_invalidate_writes(struct fscache_cookie *cookie) -{ - struct page *page; - void *results[16]; - int n, i; - - _enter(""); - - for (;;) { - spin_lock(&cookie->stores_lock); - n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, - ARRAY_SIZE(results), - FSCACHE_COOKIE_PENDING_TAG); - if (n == 0) { - spin_unlock(&cookie->stores_lock); - break; - } - - for (i = n - 1; i >= 0; i--) { - page = results[i]; - radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - trace_fscache_page(cookie, page, fscache_page_inval); - } - - spin_unlock(&cookie->stores_lock); - - for (i = n - 1; i >= 0; i--) - put_page(results[i]); - } - - wake_up_bit(&cookie->flags, 0); - trace_fscache_wake_cookie(cookie); - - _leave(""); -} - -/* - * request a page be stored in the cache - * - returns: - * -ENOMEM - out of memory, nothing done - * -ENOBUFS - no backing object available in which to cache the page - * 0 - dispatched a write - it'll call end_io_func() when finished - * - * if the cookie still has a backing object at this point, that object can be - * in one of a few states with respect to storage processing: - * - * (1) negative lookup, object not yet created (FSCACHE_COOKIE_CREATING is - * set) - * - * (a) no writes yet - * - * (b) writes deferred till post-creation (mark page for writing and - * return immediately) - * - * (2) negative lookup, object created, initial fill being made from netfs - * - * (a) fill point not yet reached this page (mark page for writing and - * return) - * - * (b) fill point passed this page (queue op to store this page) - * - * (3) object extant (queue op to store this page) - * - * any other state is invalid - */ -int __fscache_write_page(struct fscache_cookie *cookie, - struct page *page, - loff_t object_size, - gfp_t gfp) -{ - struct fscache_storage *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,%x,", cookie, (u32) page->flags); - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERT(PageFsCache(page)); - - fscache_stat(&fscache_n_stores); - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!op) - goto nomem; - - fscache_operation_init(cookie, &op->op, fscache_write_op, NULL, - fscache_release_write_op); - op->op.flags = FSCACHE_OP_ASYNC | - (1 << FSCACHE_OP_WAITING) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - - ret = radix_tree_maybe_preload(gfp & ~__GFP_HIGHMEM); - if (ret < 0) - goto nomem_free; - - trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_write_one); - - ret = -ENOBUFS; - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - if (test_bit(FSCACHE_IOERROR, &object->cache->flags)) - goto nobufs; - - trace_fscache_page(cookie, page, fscache_page_write); - - /* add the page to the pending-storage radix tree on the backing - * object */ - spin_lock(&object->lock); - - if (object->store_limit_l != object_size) - fscache_set_store_limit(object, object_size); - - spin_lock(&cookie->stores_lock); - - _debug("store limit %llx", (unsigned long long) object->store_limit); - - ret = radix_tree_insert(&cookie->stores, page->index, page); - if (ret < 0) { - if (ret == -EEXIST) - goto already_queued; - _debug("insert failed %d", ret); - goto nobufs_unlock_obj; - } - - trace_fscache_page(cookie, page, fscache_page_radix_insert); - radix_tree_tag_set(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG); - trace_fscache_page(cookie, page, fscache_page_radix_set_pend); - get_page(page); - - /* we only want one writer at a time, but we do need to queue new - * writers after exclusive ops */ - if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags)) - goto already_pending; - - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); - - op->op.debug_id = atomic_inc_return(&fscache_op_debug_id); - op->store_limit = object->store_limit; - - __fscache_use_cookie(cookie); - if (fscache_submit_op(object, &op->op) < 0) - goto submit_failed; - - spin_unlock(&cookie->lock); - radix_tree_preload_end(); - fscache_stat(&fscache_n_store_ops); - fscache_stat(&fscache_n_stores_ok); - - /* the work queue now carries its own ref on the object */ - fscache_put_operation(&op->op); - _leave(" = 0"); - return 0; - -already_queued: - fscache_stat(&fscache_n_stores_again); -already_pending: - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); - spin_unlock(&cookie->lock); - radix_tree_preload_end(); - fscache_put_operation(&op->op); - fscache_stat(&fscache_n_stores_ok); - _leave(" = 0"); - return 0; - -submit_failed: - spin_lock(&cookie->stores_lock); - radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - spin_unlock(&cookie->stores_lock); - wake_cookie = __fscache_unuse_cookie(cookie); - put_page(page); - ret = -ENOBUFS; - goto nobufs; - -nobufs_unlock_obj: - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); -nobufs: - spin_unlock(&cookie->lock); - radix_tree_preload_end(); - fscache_put_operation(&op->op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - fscache_stat(&fscache_n_stores_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; - -nomem_free: - fscache_put_operation(&op->op); -nomem: - fscache_stat(&fscache_n_stores_oom); - _leave(" = -ENOMEM"); - return -ENOMEM; -} -EXPORT_SYMBOL(__fscache_write_page); - -/* - * remove a page from the cache - */ -void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page) -{ - struct fscache_object *object; - - _enter(",%p", page); - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(page, !=, NULL); - - fscache_stat(&fscache_n_uncaches); - - /* cache withdrawal may beat us to it */ - if (!PageFsCache(page)) - goto done; - - trace_fscache_page(cookie, page, fscache_page_uncache); - - /* get the object */ - spin_lock(&cookie->lock); - - if (hlist_empty(&cookie->backing_objects)) { - ClearPageFsCache(page); - goto done_unlock; - } - - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - /* there might now be stuff on disk we could read */ - clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - - /* only invoke the cache backend if we managed to mark the page - * uncached here; this deals with synchronisation vs withdrawal */ - if (TestClearPageFsCache(page) && - object->cache->ops->uncache_page) { - /* the cache backend releases the cookie lock */ - fscache_stat(&fscache_n_cop_uncache_page); - object->cache->ops->uncache_page(object, page); - fscache_stat_d(&fscache_n_cop_uncache_page); - goto done; - } - -done_unlock: - spin_unlock(&cookie->lock); -done: - _leave(""); -} -EXPORT_SYMBOL(__fscache_uncache_page); - -/** - * fscache_mark_page_cached - Mark a page as being cached - * @op: The retrieval op pages are being marked for - * @page: The page to be marked - * - * Mark a netfs page as being cached. After this is called, the netfs - * must call fscache_uncache_page() to remove the mark. - */ -void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page) -{ - struct fscache_cookie *cookie = op->op.object->cookie; - -#ifdef CONFIG_FSCACHE_STATS - atomic_inc(&fscache_n_marks); -#endif - - trace_fscache_page(cookie, page, fscache_page_cached); - - _debug("- mark %p{%lx}", page, page->index); - if (TestSetPageFsCache(page)) { - static bool once_only; - if (!once_only) { - once_only = true; - pr_warn("Cookie type %s marked page %lx multiple times\n", - cookie->def->name, page->index); - } - } - - if (cookie->def->mark_page_cached) - cookie->def->mark_page_cached(cookie->netfs_data, - op->mapping, page); -} -EXPORT_SYMBOL(fscache_mark_page_cached); - -/** - * fscache_mark_pages_cached - Mark pages as being cached - * @op: The retrieval op pages are being marked for - * @pagevec: The pages to be marked - * - * Mark a bunch of netfs pages as being cached. After this is called, - * the netfs must call fscache_uncache_page() to remove the mark. - */ -void fscache_mark_pages_cached(struct fscache_retrieval *op, - struct pagevec *pagevec) -{ - unsigned long loop; - - for (loop = 0; loop < pagevec->nr; loop++) - fscache_mark_page_cached(op, pagevec->pages[loop]); - - pagevec_reinit(pagevec); -} -EXPORT_SYMBOL(fscache_mark_pages_cached); - -/* - * Uncache all the pages in an inode that are marked PG_fscache, assuming them - * to be associated with the given cookie. - */ -void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, - struct inode *inode) -{ - struct address_space *mapping = inode->i_mapping; - struct pagevec pvec; - pgoff_t next; - int i; - - _enter("%p,%p", cookie, inode); - - if (!mapping || mapping->nrpages == 0) { - _leave(" [no pages]"); - return; - } - - pagevec_init(&pvec); - next = 0; - do { - if (!pagevec_lookup(&pvec, mapping, &next)) - break; - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - if (PageFsCache(page)) { - __fscache_wait_on_page_write(cookie, page); - __fscache_uncache_page(cookie, page); - } - } - pagevec_release(&pvec); - cond_resched(); - } while (next); - - _leave(""); -} -EXPORT_SYMBOL(__fscache_uncache_all_inode_pages); diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 061df8f61ffc..dc3b0e9c8cce 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache statistics viewing interface * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ -#define FSCACHE_DEBUG_LEVEL OPERATION +#define FSCACHE_DEBUG_LEVEL CACHE #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -16,42 +16,32 @@ */ int __init fscache_proc_init(void) { - _enter(""); - if (!proc_mkdir("fs/fscache", NULL)) goto error_dir; + if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL, + &fscache_caches_seq_ops)) + goto error; + + if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL, + &fscache_volumes_seq_ops)) + goto error; + if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL, &fscache_cookies_seq_ops)) - goto error_cookies; + goto error; #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, - fscache_stats_show)) - goto error_stats; + fscache_stats_show)) + goto error; #endif -#ifdef CONFIG_FSCACHE_OBJECT_LIST - if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, - &fscache_objlist_proc_ops)) - goto error_objects; -#endif - - _leave(" = 0"); return 0; -#ifdef CONFIG_FSCACHE_OBJECT_LIST -error_objects: -#endif -#ifdef CONFIG_FSCACHE_STATS - remove_proc_entry("fs/fscache/stats", NULL); -error_stats: -#endif - remove_proc_entry("fs/fscache/cookies", NULL); -error_cookies: +error: remove_proc_entry("fs/fscache", NULL); error_dir: - _leave(" = -ENOMEM"); return -ENOMEM; } @@ -60,12 +50,5 @@ error_dir: */ void fscache_proc_cleanup(void) { -#ifdef CONFIG_FSCACHE_OBJECT_LIST - remove_proc_entry("fs/fscache/objects", NULL); -#endif -#ifdef CONFIG_FSCACHE_STATS - remove_proc_entry("fs/fscache/stats", NULL); -#endif - remove_proc_entry("fs/fscache/cookies", NULL); - remove_proc_entry("fs/fscache", NULL); + remove_proc_subtree("fs/fscache", NULL); } diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index a7c3ed89a3e0..fc94e5e79f1c 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -1,12 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache statistics * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ -#define FSCACHE_DEBUG_LEVEL THREAD -#include <linux/module.h> +#define FSCACHE_DEBUG_LEVEL CACHE #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "internal.h" @@ -14,122 +13,41 @@ /* * operation counters */ -atomic_t fscache_n_op_pend; -atomic_t fscache_n_op_run; -atomic_t fscache_n_op_enqueue; -atomic_t fscache_n_op_deferred_release; -atomic_t fscache_n_op_initialised; -atomic_t fscache_n_op_release; -atomic_t fscache_n_op_gc; -atomic_t fscache_n_op_cancelled; -atomic_t fscache_n_op_rejected; - -atomic_t fscache_n_attr_changed; -atomic_t fscache_n_attr_changed_ok; -atomic_t fscache_n_attr_changed_nobufs; -atomic_t fscache_n_attr_changed_nomem; -atomic_t fscache_n_attr_changed_calls; - -atomic_t fscache_n_allocs; -atomic_t fscache_n_allocs_ok; -atomic_t fscache_n_allocs_wait; -atomic_t fscache_n_allocs_nobufs; -atomic_t fscache_n_allocs_intr; -atomic_t fscache_n_allocs_object_dead; -atomic_t fscache_n_alloc_ops; -atomic_t fscache_n_alloc_op_waits; - -atomic_t fscache_n_retrievals; -atomic_t fscache_n_retrievals_ok; -atomic_t fscache_n_retrievals_wait; -atomic_t fscache_n_retrievals_nodata; -atomic_t fscache_n_retrievals_nobufs; -atomic_t fscache_n_retrievals_intr; -atomic_t fscache_n_retrievals_nomem; -atomic_t fscache_n_retrievals_object_dead; -atomic_t fscache_n_retrieval_ops; -atomic_t fscache_n_retrieval_op_waits; - -atomic_t fscache_n_stores; -atomic_t fscache_n_stores_ok; -atomic_t fscache_n_stores_again; -atomic_t fscache_n_stores_nobufs; -atomic_t fscache_n_stores_oom; -atomic_t fscache_n_store_ops; -atomic_t fscache_n_store_calls; -atomic_t fscache_n_store_pages; -atomic_t fscache_n_store_radix_deletes; -atomic_t fscache_n_store_pages_over_limit; - -atomic_t fscache_n_store_vmscan_not_storing; -atomic_t fscache_n_store_vmscan_gone; -atomic_t fscache_n_store_vmscan_busy; -atomic_t fscache_n_store_vmscan_cancelled; -atomic_t fscache_n_store_vmscan_wait; - -atomic_t fscache_n_marks; -atomic_t fscache_n_uncaches; +atomic_t fscache_n_volumes; +atomic_t fscache_n_volumes_collision; +atomic_t fscache_n_volumes_nomem; +atomic_t fscache_n_cookies; +atomic_t fscache_n_cookies_lru; +atomic_t fscache_n_cookies_lru_expired; +atomic_t fscache_n_cookies_lru_removed; +atomic_t fscache_n_cookies_lru_dropped; atomic_t fscache_n_acquires; -atomic_t fscache_n_acquires_null; -atomic_t fscache_n_acquires_no_cache; atomic_t fscache_n_acquires_ok; -atomic_t fscache_n_acquires_nobufs; atomic_t fscache_n_acquires_oom; atomic_t fscache_n_invalidates; -atomic_t fscache_n_invalidates_run; atomic_t fscache_n_updates; -atomic_t fscache_n_updates_null; -atomic_t fscache_n_updates_run; +EXPORT_SYMBOL(fscache_n_updates); atomic_t fscache_n_relinquishes; -atomic_t fscache_n_relinquishes_null; -atomic_t fscache_n_relinquishes_waitcrt; atomic_t fscache_n_relinquishes_retire; - -atomic_t fscache_n_cookie_index; -atomic_t fscache_n_cookie_data; -atomic_t fscache_n_cookie_special; - -atomic_t fscache_n_object_alloc; -atomic_t fscache_n_object_no_alloc; -atomic_t fscache_n_object_lookups; -atomic_t fscache_n_object_lookups_negative; -atomic_t fscache_n_object_lookups_positive; -atomic_t fscache_n_object_lookups_timed_out; -atomic_t fscache_n_object_created; -atomic_t fscache_n_object_avail; -atomic_t fscache_n_object_dead; - -atomic_t fscache_n_checkaux_none; -atomic_t fscache_n_checkaux_okay; -atomic_t fscache_n_checkaux_update; -atomic_t fscache_n_checkaux_obsolete; - -atomic_t fscache_n_cop_alloc_object; -atomic_t fscache_n_cop_lookup_object; -atomic_t fscache_n_cop_lookup_complete; -atomic_t fscache_n_cop_grab_object; -atomic_t fscache_n_cop_invalidate_object; -atomic_t fscache_n_cop_update_object; -atomic_t fscache_n_cop_drop_object; -atomic_t fscache_n_cop_put_object; -atomic_t fscache_n_cop_sync_cache; -atomic_t fscache_n_cop_attr_changed; -atomic_t fscache_n_cop_read_or_alloc_page; -atomic_t fscache_n_cop_read_or_alloc_pages; -atomic_t fscache_n_cop_allocate_page; -atomic_t fscache_n_cop_allocate_pages; -atomic_t fscache_n_cop_write_page; -atomic_t fscache_n_cop_uncache_page; -atomic_t fscache_n_cop_dissociate_pages; - -atomic_t fscache_n_cache_no_space_reject; -atomic_t fscache_n_cache_stale_objects; -atomic_t fscache_n_cache_retired_objects; -atomic_t fscache_n_cache_culled_objects; +atomic_t fscache_n_relinquishes_dropped; + +atomic_t fscache_n_resizes; +atomic_t fscache_n_resizes_null; + +atomic_t fscache_n_read; +EXPORT_SYMBOL(fscache_n_read); +atomic_t fscache_n_write; +EXPORT_SYMBOL(fscache_n_write); +atomic_t fscache_n_no_write_space; +EXPORT_SYMBOL(fscache_n_no_write_space); +atomic_t fscache_n_no_create_space; +EXPORT_SYMBOL(fscache_n_no_create_space); +atomic_t fscache_n_culled; +EXPORT_SYMBOL(fscache_n_culled); /* * display the general statistics @@ -137,147 +55,48 @@ atomic_t fscache_n_cache_culled_objects; int fscache_stats_show(struct seq_file *m, void *v) { seq_puts(m, "FS-Cache statistics\n"); - - seq_printf(m, "Cookies: idx=%u dat=%u spc=%u\n", - atomic_read(&fscache_n_cookie_index), - atomic_read(&fscache_n_cookie_data), - atomic_read(&fscache_n_cookie_special)); - - seq_printf(m, "Objects: alc=%u nal=%u avl=%u ded=%u\n", - atomic_read(&fscache_n_object_alloc), - atomic_read(&fscache_n_object_no_alloc), - atomic_read(&fscache_n_object_avail), - atomic_read(&fscache_n_object_dead)); - seq_printf(m, "ChkAux : non=%u ok=%u upd=%u obs=%u\n", - atomic_read(&fscache_n_checkaux_none), - atomic_read(&fscache_n_checkaux_okay), - atomic_read(&fscache_n_checkaux_update), - atomic_read(&fscache_n_checkaux_obsolete)); - - seq_printf(m, "Pages : mrk=%u unc=%u\n", - atomic_read(&fscache_n_marks), - atomic_read(&fscache_n_uncaches)); - - seq_printf(m, "Acquire: n=%u nul=%u noc=%u ok=%u nbf=%u" - " oom=%u\n", + seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n", + atomic_read(&fscache_n_cookies), + atomic_read(&fscache_n_volumes), + atomic_read(&fscache_n_volumes_collision), + atomic_read(&fscache_n_volumes_nomem) + ); + + seq_printf(m, "Acquire: n=%u ok=%u oom=%u\n", atomic_read(&fscache_n_acquires), - atomic_read(&fscache_n_acquires_null), - atomic_read(&fscache_n_acquires_no_cache), atomic_read(&fscache_n_acquires_ok), - atomic_read(&fscache_n_acquires_nobufs), atomic_read(&fscache_n_acquires_oom)); - seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u tmo=%u\n", - atomic_read(&fscache_n_object_lookups), - atomic_read(&fscache_n_object_lookups_negative), - atomic_read(&fscache_n_object_lookups_positive), - atomic_read(&fscache_n_object_created), - atomic_read(&fscache_n_object_lookups_timed_out)); + seq_printf(m, "LRU : n=%u exp=%u rmv=%u drp=%u at=%ld\n", + atomic_read(&fscache_n_cookies_lru), + atomic_read(&fscache_n_cookies_lru_expired), + atomic_read(&fscache_n_cookies_lru_removed), + atomic_read(&fscache_n_cookies_lru_dropped), + timer_pending(&fscache_cookie_lru_timer) ? + fscache_cookie_lru_timer.expires - jiffies : 0); - seq_printf(m, "Invals : n=%u run=%u\n", - atomic_read(&fscache_n_invalidates), - atomic_read(&fscache_n_invalidates_run)); + seq_printf(m, "Invals : n=%u\n", + atomic_read(&fscache_n_invalidates)); - seq_printf(m, "Updates: n=%u nul=%u run=%u\n", + seq_printf(m, "Updates: n=%u rsz=%u rsn=%u\n", atomic_read(&fscache_n_updates), - atomic_read(&fscache_n_updates_null), - atomic_read(&fscache_n_updates_run)); + atomic_read(&fscache_n_resizes), + atomic_read(&fscache_n_resizes_null)); - seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u rtr=%u\n", + seq_printf(m, "Relinqs: n=%u rtr=%u drop=%u\n", atomic_read(&fscache_n_relinquishes), - atomic_read(&fscache_n_relinquishes_null), - atomic_read(&fscache_n_relinquishes_waitcrt), - atomic_read(&fscache_n_relinquishes_retire)); - - seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n", - atomic_read(&fscache_n_attr_changed), - atomic_read(&fscache_n_attr_changed_ok), - atomic_read(&fscache_n_attr_changed_nobufs), - atomic_read(&fscache_n_attr_changed_nomem), - atomic_read(&fscache_n_attr_changed_calls)); - - seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n", - atomic_read(&fscache_n_allocs), - atomic_read(&fscache_n_allocs_ok), - atomic_read(&fscache_n_allocs_wait), - atomic_read(&fscache_n_allocs_nobufs), - atomic_read(&fscache_n_allocs_intr)); - seq_printf(m, "Allocs : ops=%u owt=%u abt=%u\n", - atomic_read(&fscache_n_alloc_ops), - atomic_read(&fscache_n_alloc_op_waits), - atomic_read(&fscache_n_allocs_object_dead)); - - seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u" - " int=%u oom=%u\n", - atomic_read(&fscache_n_retrievals), - atomic_read(&fscache_n_retrievals_ok), - atomic_read(&fscache_n_retrievals_wait), - atomic_read(&fscache_n_retrievals_nodata), - atomic_read(&fscache_n_retrievals_nobufs), - atomic_read(&fscache_n_retrievals_intr), - atomic_read(&fscache_n_retrievals_nomem)); - seq_printf(m, "Retrvls: ops=%u owt=%u abt=%u\n", - atomic_read(&fscache_n_retrieval_ops), - atomic_read(&fscache_n_retrieval_op_waits), - atomic_read(&fscache_n_retrievals_object_dead)); - - seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n", - atomic_read(&fscache_n_stores), - atomic_read(&fscache_n_stores_ok), - atomic_read(&fscache_n_stores_again), - atomic_read(&fscache_n_stores_nobufs), - atomic_read(&fscache_n_stores_oom)); - seq_printf(m, "Stores : ops=%u run=%u pgs=%u rxd=%u olm=%u\n", - atomic_read(&fscache_n_store_ops), - atomic_read(&fscache_n_store_calls), - atomic_read(&fscache_n_store_pages), - atomic_read(&fscache_n_store_radix_deletes), - atomic_read(&fscache_n_store_pages_over_limit)); + atomic_read(&fscache_n_relinquishes_retire), + atomic_read(&fscache_n_relinquishes_dropped)); - seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u wt=%u\n", - atomic_read(&fscache_n_store_vmscan_not_storing), - atomic_read(&fscache_n_store_vmscan_gone), - atomic_read(&fscache_n_store_vmscan_busy), - atomic_read(&fscache_n_store_vmscan_cancelled), - atomic_read(&fscache_n_store_vmscan_wait)); + seq_printf(m, "NoSpace: nwr=%u ncr=%u cull=%u\n", + atomic_read(&fscache_n_no_write_space), + atomic_read(&fscache_n_no_create_space), + atomic_read(&fscache_n_culled)); - seq_printf(m, "Ops : pend=%u run=%u enq=%u can=%u rej=%u\n", - atomic_read(&fscache_n_op_pend), - atomic_read(&fscache_n_op_run), - atomic_read(&fscache_n_op_enqueue), - atomic_read(&fscache_n_op_cancelled), - atomic_read(&fscache_n_op_rejected)); - seq_printf(m, "Ops : ini=%u dfr=%u rel=%u gc=%u\n", - atomic_read(&fscache_n_op_initialised), - atomic_read(&fscache_n_op_deferred_release), - atomic_read(&fscache_n_op_release), - atomic_read(&fscache_n_op_gc)); + seq_printf(m, "IO : rd=%u wr=%u\n", + atomic_read(&fscache_n_read), + atomic_read(&fscache_n_write)); - seq_printf(m, "CacheOp: alo=%d luo=%d luc=%d gro=%d\n", - atomic_read(&fscache_n_cop_alloc_object), - atomic_read(&fscache_n_cop_lookup_object), - atomic_read(&fscache_n_cop_lookup_complete), - atomic_read(&fscache_n_cop_grab_object)); - seq_printf(m, "CacheOp: inv=%d upo=%d dro=%d pto=%d atc=%d syn=%d\n", - atomic_read(&fscache_n_cop_invalidate_object), - atomic_read(&fscache_n_cop_update_object), - atomic_read(&fscache_n_cop_drop_object), - atomic_read(&fscache_n_cop_put_object), - atomic_read(&fscache_n_cop_attr_changed), - atomic_read(&fscache_n_cop_sync_cache)); - seq_printf(m, "CacheOp: rap=%d ras=%d alp=%d als=%d wrp=%d ucp=%d dsp=%d\n", - atomic_read(&fscache_n_cop_read_or_alloc_page), - atomic_read(&fscache_n_cop_read_or_alloc_pages), - atomic_read(&fscache_n_cop_allocate_page), - atomic_read(&fscache_n_cop_allocate_pages), - atomic_read(&fscache_n_cop_write_page), - atomic_read(&fscache_n_cop_uncache_page), - atomic_read(&fscache_n_cop_dissociate_pages)); - seq_printf(m, "CacheEv: nsp=%d stl=%d rtr=%d cul=%d\n", - atomic_read(&fscache_n_cache_no_space_reject), - atomic_read(&fscache_n_cache_stale_objects), - atomic_read(&fscache_n_cache_retired_objects), - atomic_read(&fscache_n_cache_culled_objects)); netfs_stats_show(m); return 0; } diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c new file mode 100644 index 000000000000..a57c6cbee858 --- /dev/null +++ b/fs/fscache/volume.c @@ -0,0 +1,517 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Volume-level cache cookie handling. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include <linux/export.h> +#include <linux/slab.h> +#include "internal.h" + +#define fscache_volume_hash_shift 10 +static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift]; +static atomic_t fscache_volume_debug_id; +static LIST_HEAD(fscache_volumes); + +static void fscache_create_volume_work(struct work_struct *work); + +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + int ref; + + __refcount_inc(&volume->ref, &ref); + trace_fscache_volume(volume->debug_id, ref + 1, where); + return volume; +} + +static void fscache_see_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + int ref = refcount_read(&volume->ref); + + trace_fscache_volume(volume->debug_id, ref, where); +} + +/* + * Pin the cache behind a volume so that we can access it. + */ +static void __fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + n_accesses = atomic_inc_return(&volume->n_accesses); + smp_mb__after_atomic(); + trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, + refcount_read(&volume->ref), + n_accesses, why); +} + +/** + * fscache_begin_volume_access - Pin a cache so a volume can be accessed + * @volume: The volume cookie + * @cookie: A datafile cookie for a tracing reference (or NULL) + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing a volume and returns true if successful. This works as follows: + * + * (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), + * then we return false to indicate access was not permitted. + * + * (2) If the cache tests as live, then we increment the volume's n_accesses + * count and then recheck the cache liveness, ending the access if it + * ceased to be live. + * + * (3) When we end the access, we decrement the volume's n_accesses and wake + * up the any waiters if it reaches 0. + * + * (4) Whilst the cache is caching, the volume's n_accesses is kept + * artificially incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline, the state is changed to prevent new + * accesses, the volume's n_accesses is decremented and we wait for it to + * become 0. + * + * The datafile @cookie and the @why indicator are merely provided for tracing + * purposes. + */ +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + if (!fscache_cache_is_live(volume->cache)) + return false; + __fscache_begin_volume_access(volume, cookie, why); + if (!fscache_cache_is_live(volume->cache)) { + fscache_end_volume_access(volume, cookie, fscache_access_unlive); + return false; + } + return true; +} + +/** + * fscache_end_volume_access - Unpin a cache at the end of an access. + * @volume: The volume cookie + * @cookie: A datafile cookie for a tracing reference (or NULL) + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache volume after we've accessed it. The datafile @cookie and the + * @why indicator are merely provided for tracing purposes. + */ +void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&volume->n_accesses); + trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, + refcount_read(&volume->ref), + n_accesses, why); + if (n_accesses == 0) + wake_up_var(&volume->n_accesses); +} +EXPORT_SYMBOL(fscache_end_volume_access); + +static bool fscache_volume_same(const struct fscache_volume *a, + const struct fscache_volume *b) +{ + size_t klen; + + if (a->key_hash != b->key_hash || + a->cache != b->cache || + a->key[0] != b->key[0]) + return false; + + klen = round_up(a->key[0] + 1, sizeof(__le32)); + return memcmp(a->key, b->key, klen) == 0; +} + +static bool fscache_is_acquire_pending(struct fscache_volume *volume) +{ + return test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &volume->flags); +} + +static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, + unsigned int collidee_debug_id) +{ + wait_var_event_timeout(&candidate->flags, + fscache_is_acquire_pending(candidate), 20 * HZ); + if (!fscache_is_acquire_pending(candidate)) { + pr_notice("Potential volume collision new=%08x old=%08x", + candidate->debug_id, collidee_debug_id); + fscache_stat(&fscache_n_volumes_collision); + wait_var_event(&candidate->flags, fscache_is_acquire_pending(candidate)); + } +} + +/* + * Attempt to insert the new volume into the hash. If there's a collision, we + * wait for the old volume to complete if it's being relinquished and an error + * otherwise. + */ +static bool fscache_hash_volume(struct fscache_volume *candidate) +{ + struct fscache_volume *cursor; + struct hlist_bl_head *h; + struct hlist_bl_node *p; + unsigned int bucket, collidee_debug_id = 0; + + bucket = candidate->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); + h = &fscache_volume_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_volume_same(candidate, cursor)) { + if (!test_bit(FSCACHE_VOLUME_RELINQUISHED, &cursor->flags)) + goto collision; + fscache_see_volume(cursor, fscache_volume_get_hash_collision); + set_bit(FSCACHE_VOLUME_COLLIDED_WITH, &cursor->flags); + set_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags); + collidee_debug_id = cursor->debug_id; + break; + } + } + + hlist_bl_add_head(&candidate->hash_link, h); + hlist_bl_unlock(h); + + if (test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags)) + fscache_wait_on_volume_collision(candidate, collidee_debug_id); + return true; + +collision: + fscache_see_volume(cursor, fscache_volume_collision); + hlist_bl_unlock(h); + return false; +} + +/* + * Allocate and initialise a volume representation cookie. + */ +static struct fscache_volume *fscache_alloc_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + struct fscache_volume *volume; + struct fscache_cache *cache; + size_t klen, hlen; + char *key; + + if (!coherency_data) + coherency_len = 0; + + cache = fscache_lookup_cache(cache_name, false); + if (IS_ERR(cache)) + return NULL; + + volume = kzalloc(struct_size(volume, coherency, coherency_len), + GFP_KERNEL); + if (!volume) + goto err_cache; + + volume->cache = cache; + volume->coherency_len = coherency_len; + if (coherency_data) + memcpy(volume->coherency, coherency_data, coherency_len); + INIT_LIST_HEAD(&volume->proc_link); + INIT_WORK(&volume->work, fscache_create_volume_work); + refcount_set(&volume->ref, 1); + spin_lock_init(&volume->lock); + + /* Stick the length on the front of the key and pad it out to make + * hashing easier. + */ + klen = strlen(volume_key); + hlen = round_up(1 + klen + 1, sizeof(__le32)); + key = kzalloc(hlen, GFP_KERNEL); + if (!key) + goto err_vol; + key[0] = klen; + memcpy(key + 1, volume_key, klen); + + volume->key = key; + volume->key_hash = fscache_hash(0, key, hlen); + + volume->debug_id = atomic_inc_return(&fscache_volume_debug_id); + down_write(&fscache_addremove_sem); + atomic_inc(&cache->n_volumes); + list_add_tail(&volume->proc_link, &fscache_volumes); + fscache_see_volume(volume, fscache_volume_new_acquire); + fscache_stat(&fscache_n_volumes); + up_write(&fscache_addremove_sem); + _leave(" = v=%x", volume->debug_id); + return volume; + +err_vol: + kfree(volume); +err_cache: + fscache_put_cache(cache, fscache_cache_put_alloc_volume); + fscache_stat(&fscache_n_volumes_nomem); + return NULL; +} + +/* + * Create a volume's representation on disk. Have a volume ref and a cache + * access we have to release. + */ +static void fscache_create_volume_work(struct work_struct *work) +{ + const struct fscache_cache_ops *ops; + struct fscache_volume *volume = + container_of(work, struct fscache_volume, work); + + fscache_see_volume(volume, fscache_volume_see_create_work); + + ops = volume->cache->ops; + if (ops->acquire_volume) + ops->acquire_volume(volume); + fscache_end_cache_access(volume->cache, + fscache_access_acquire_volume_end); + + clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); + wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); + fscache_put_volume(volume, fscache_volume_put_create_work); +} + +/* + * Dispatch a worker thread to create a volume's representation on disk. + */ +void fscache_create_volume(struct fscache_volume *volume, bool wait) +{ + if (test_and_set_bit(FSCACHE_VOLUME_CREATING, &volume->flags)) + goto maybe_wait; + if (volume->cache_priv) + goto no_wait; /* We raced */ + if (!fscache_begin_cache_access(volume->cache, + fscache_access_acquire_volume)) + goto no_wait; + + fscache_get_volume(volume, fscache_volume_get_create_work); + if (!schedule_work(&volume->work)) + fscache_put_volume(volume, fscache_volume_put_create_work); + +maybe_wait: + if (wait) { + fscache_see_volume(volume, fscache_volume_wait_create_work); + wait_on_bit(&volume->flags, FSCACHE_VOLUME_CREATING, + TASK_UNINTERRUPTIBLE); + } + return; +no_wait: + clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); + wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); +} + +/* + * Acquire a volume representation cookie and link it to a (proposed) cache. + */ +struct fscache_volume *__fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + struct fscache_volume *volume; + + volume = fscache_alloc_volume(volume_key, cache_name, + coherency_data, coherency_len); + if (!volume) + return ERR_PTR(-ENOMEM); + + if (!fscache_hash_volume(volume)) { + fscache_put_volume(volume, fscache_volume_put_hash_collision); + return ERR_PTR(-EBUSY); + } + + fscache_create_volume(volume, false); + return volume; +} +EXPORT_SYMBOL(__fscache_acquire_volume); + +static void fscache_wake_pending_volume(struct fscache_volume *volume, + struct hlist_bl_head *h) +{ + struct fscache_volume *cursor; + struct hlist_bl_node *p; + + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_volume_same(cursor, volume)) { + fscache_see_volume(cursor, fscache_volume_see_hash_wake); + clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); + wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING); + return; + } + } +} + +/* + * Remove a volume cookie from the hash table. + */ +static void fscache_unhash_volume(struct fscache_volume *volume) +{ + struct hlist_bl_head *h; + unsigned int bucket; + + bucket = volume->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); + h = &fscache_volume_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_del(&volume->hash_link); + if (test_bit(FSCACHE_VOLUME_COLLIDED_WITH, &volume->flags)) + fscache_wake_pending_volume(volume, h); + hlist_bl_unlock(h); +} + +/* + * Drop a cache's volume attachments. + */ +static void fscache_free_volume(struct fscache_volume *volume) +{ + struct fscache_cache *cache = volume->cache; + + if (volume->cache_priv) { + __fscache_begin_volume_access(volume, NULL, + fscache_access_relinquish_volume); + if (volume->cache_priv) + cache->ops->free_volume(volume); + fscache_end_volume_access(volume, NULL, + fscache_access_relinquish_volume_end); + } + + down_write(&fscache_addremove_sem); + list_del_init(&volume->proc_link); + atomic_dec(&volume->cache->n_volumes); + up_write(&fscache_addremove_sem); + + if (!hlist_bl_unhashed(&volume->hash_link)) + fscache_unhash_volume(volume); + + trace_fscache_volume(volume->debug_id, 0, fscache_volume_free); + kfree(volume->key); + kfree(volume); + fscache_stat_d(&fscache_n_volumes); + fscache_put_cache(cache, fscache_cache_put_volume); +} + +/* + * Drop a reference to a volume cookie. + */ +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + if (volume) { + unsigned int debug_id = volume->debug_id; + bool zero; + int ref; + + zero = __refcount_dec_and_test(&volume->ref, &ref); + trace_fscache_volume(debug_id, ref - 1, where); + if (zero) + fscache_free_volume(volume); + } +} + +/* + * Relinquish a volume representation cookie. + */ +void __fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) +{ + if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags))) + return; + + if (invalidate) { + set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags); + } else if (coherency_data) { + memcpy(volume->coherency, coherency_data, volume->coherency_len); + } + + fscache_put_volume(volume, fscache_volume_put_relinquish); +} +EXPORT_SYMBOL(__fscache_relinquish_volume); + +/** + * fscache_withdraw_volume - Withdraw a volume from being cached + * @volume: Volume cookie + * + * Withdraw a cache volume from service, waiting for all accesses to complete + * before returning. + */ +void fscache_withdraw_volume(struct fscache_volume *volume) +{ + int n_accesses; + + _debug("withdraw V=%x", volume->debug_id); + + /* Allow wakeups on dec-to-0 */ + n_accesses = atomic_dec_return(&volume->n_accesses); + trace_fscache_access_volume(volume->debug_id, 0, + refcount_read(&volume->ref), + n_accesses, fscache_access_cache_unpin); + + wait_var_event(&volume->n_accesses, + atomic_read(&volume->n_accesses) == 0); +} +EXPORT_SYMBOL(fscache_withdraw_volume); + +#ifdef CONFIG_PROC_FS +/* + * Generate a list of volumes in /proc/fs/fscache/volumes + */ +static int fscache_volumes_seq_show(struct seq_file *m, void *v) +{ + struct fscache_volume *volume; + + if (v == &fscache_volumes) { + seq_puts(m, + "VOLUME REF nCOOK ACC FL CACHE KEY\n" + "======== ===== ===== === == =============== ================\n"); + return 0; + } + + volume = list_entry(v, struct fscache_volume, proc_link); + seq_printf(m, + "%08x %5d %5d %3d %02lx %-15.15s %s\n", + volume->debug_id, + refcount_read(&volume->ref), + atomic_read(&volume->n_cookies), + atomic_read(&volume->n_accesses), + volume->flags, + volume->cache->name ?: "-", + volume->key + 1); + return 0; +} + +static void *fscache_volumes_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(&fscache_addremove_sem) +{ + down_read(&fscache_addremove_sem); + return seq_list_start_head(&fscache_volumes, *_pos); +} + +static void *fscache_volumes_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_volumes, _pos); +} + +static void fscache_volumes_seq_stop(struct seq_file *m, void *v) + __releases(&fscache_addremove_sem) +{ + up_read(&fscache_addremove_sem); +} + +const struct seq_operations fscache_volumes_seq_ops = { + .start = fscache_volumes_seq_start, + .next = fscache_volumes_seq_next, + .stop = fscache_volumes_seq_stop, + .show = fscache_volumes_seq_show, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/fs/namei.c b/fs/namei.c index 1f9d2187c765..d81f04f8d818 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3958,7 +3958,8 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, inode_lock(dentry->d_inode); error = -EBUSY; - if (is_local_mountpoint(dentry)) + if (is_local_mountpoint(dentry) || + (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 75c76cbb27cc..6169659857b3 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -170,7 +170,7 @@ static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error */ static void netfs_read_from_cache(struct netfs_read_request *rreq, struct netfs_read_subrequest *subreq, - bool seek_data) + enum netfs_read_from_hole read_hole) { struct netfs_cache_resources *cres = &rreq->cache_resources; struct iov_iter iter; @@ -180,7 +180,7 @@ static void netfs_read_from_cache(struct netfs_read_request *rreq, subreq->start + subreq->transferred, subreq->len - subreq->transferred); - cres->ops->read(cres, subreq->start, &iter, seek_data, + cres->ops->read(cres, subreq->start, &iter, read_hole, netfs_cache_read_terminated, subreq); } @@ -323,7 +323,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq) } ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size); + rreq->i_size, true); if (ret < 0) { trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); @@ -461,7 +461,7 @@ static void netfs_rreq_short_read(struct netfs_read_request *rreq, netfs_get_read_subrequest(subreq); atomic_inc(&rreq->nr_rd_ops); if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, true); + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); else netfs_read_from_server(rreq, subreq); } @@ -789,7 +789,7 @@ static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq, netfs_read_from_server(rreq, subreq); break; case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, false); + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); break; default: BUG(); diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 22d11fdc6deb..5f6db37f461e 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,7 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ export.o sysfs.o fs_context.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o -nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +nfs-$(CONFIG_NFS_FSCACHE) += fscache.o obj-$(CONFIG_NFS_V2) += nfsv2.o nfsv2-y := nfs2super.o proc.o nfs2xdr.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 1e4dc1ab9312..8d8b85b5a641 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -183,8 +183,6 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_net = get_net(cl_init->net); clp->cl_principal = "*"; - nfs_fscache_get_client_cookie(clp); - return clp; error_cleanup: @@ -238,8 +236,6 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { - nfs_fscache_release_client_cookie(clp); - /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 9cff8709c80a..eabfdab543c8 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -59,6 +59,7 @@ #include "internal.h" #include "iostat.h" #include "pnfs.h" +#include "fscache.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -959,6 +960,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) } else { result = requested; } + nfs_fscache_invalidate(inode, FSCACHE_INVAL_DIO_WRITE); out_release: nfs_direct_req_release(dreq); out: diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 24e7dccce355..76d76acbc594 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -84,6 +84,7 @@ nfs_file_release(struct inode *inode, struct file *filp) nfs_inc_stats(inode, NFSIOS_VFSRELEASE); nfs_file_clear_open_context(filp); + nfs_fscache_release_file(inode, filp); return 0; } EXPORT_SYMBOL_GPL(nfs_file_release); @@ -415,8 +416,7 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset, return; /* Cancel any unstarted writes on this page */ nfs_wb_page_cancel(page_file_mapping(page)->host, page); - - nfs_fscache_invalidate_page(page, page->mapping->host); + wait_on_page_fscache(page); } /* @@ -475,12 +475,11 @@ static void nfs_check_dirty_writeback(struct page *page, static int nfs_launder_page(struct page *page) { struct inode *inode = page_file_mapping(page)->host; - struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n", inode->i_ino, (long long)page_offset(page)); - nfs_fscache_wait_on_page_write(nfsi, page); + wait_on_page_fscache(page); return nfs_wb_page(inode, page); } @@ -555,7 +554,11 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); /* make sure the cache has finished storing the page */ - nfs_fscache_wait_on_page_write(NFS_I(inode), page); + if (PageFsCache(page) && + wait_on_page_fscache_killable(vmf->page) < 0) { + ret = VM_FAULT_RETRY; + goto out; + } wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c deleted file mode 100644 index 573b1da9342c..000000000000 --- a/fs/nfs/fscache-index.c +++ /dev/null @@ -1,140 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* NFS FS-Cache index structure definition - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/nfs_fs.h> -#include <linux/nfs_fs_sb.h> -#include <linux/in6.h> -#include <linux/iversion.h> - -#include "internal.h" -#include "fscache.h" - -#define NFSDBG_FACILITY NFSDBG_FSCACHE - -/* - * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks - * the cookie for the top-level index object for NFS into here. The top-level - * index can than have other cache objects inserted into it. - */ -struct fscache_netfs nfs_fscache_netfs = { - .name = "nfs", - .version = 0, -}; - -/* - * Register NFS for caching - */ -int nfs_fscache_register(void) -{ - return fscache_register_netfs(&nfs_fscache_netfs); -} - -/* - * Unregister NFS for caching - */ -void nfs_fscache_unregister(void) -{ - fscache_unregister_netfs(&nfs_fscache_netfs); -} - -/* - * Define the server object for FS-Cache. This is used to describe a server - * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and - * server address parameters. - */ -const struct fscache_cookie_def nfs_fscache_server_index_def = { - .name = "NFS.server", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Define the superblock object for FS-Cache. This is used to describe a - * superblock object to fscache_acquire_cookie(). It is keyed by all the NFS - * parameters that might cause a separate superblock. - */ -const struct fscache_cookie_def nfs_fscache_super_index_def = { - .name = "NFS.super", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Consult the netfs about the state of an object - * - This function can be absent if the index carries no state data - * - The netfs data from the cookie being used as the target is - * presented, as is the auxiliary data - */ -static -enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size) -{ - struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = cookie_netfs_data; - - if (datalen != sizeof(auxdata)) - return FSCACHE_CHECKAUX_OBSOLETE; - - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); - - if (memcmp(data, &auxdata, datalen) != 0) - return FSCACHE_CHECKAUX_OBSOLETE; - - return FSCACHE_CHECKAUX_OKAY; -} - -/* - * Get an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - * - The read context is passed back to NFS in the event that a data read on the - * cache fails with EIO - in which case the server must be contacted to - * retrieve the data, which requires the read context for security. - */ -static void nfs_fh_get_context(void *cookie_netfs_data, void *context) -{ - get_nfs_open_context(context); -} - -/* - * Release an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - */ -static void nfs_fh_put_context(void *cookie_netfs_data, void *context) -{ - if (context) - put_nfs_open_context(context); -} - -/* - * Define the inode object for FS-Cache. This is used to describe an inode - * object to fscache_acquire_cookie(). It is keyed by the NFS file handle for - * an inode. - * - * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime - * held in the cache auxiliary data for the data storage object with those in - * the inode struct in memory. - */ -const struct fscache_cookie_def nfs_fscache_inode_object_def = { - .name = "NFS.fh", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = nfs_fscache_inode_check_aux, - .get_context = nfs_fh_get_context, - .put_context = nfs_fh_put_context, -}; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index d743629e05e1..cfe901650ab0 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -22,24 +22,18 @@ #define NFSDBG_FACILITY NFSDBG_FSCACHE -static struct rb_root nfs_fscache_keys = RB_ROOT; -static DEFINE_SPINLOCK(nfs_fscache_keys_lock); +#define NFS_MAX_KEY_LEN 1000 -/* - * Layout of the key for an NFS server cache object. - */ -struct nfs_server_key { - struct { - uint16_t nfsversion; /* NFS protocol version */ - uint32_t minorversion; /* NFSv4 minor version */ - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; /* IPv4 address */ - struct in6_addr ipv6_addr; /* IPv6 address */ - }; -} __packed; +static bool nfs_append_int(char *key, int *_len, unsigned long long x) +{ + if (*_len > NFS_MAX_KEY_LEN) + return false; + if (x == 0) + key[(*_len)++] = ','; + else + *_len += sprintf(key + *_len, ",%llx", x); + return true; +} /* * Get the per-client index cookie for an NFS client if the appropriate mount @@ -47,160 +41,108 @@ struct nfs_server_key { * - We always try and get an index cookie for the client, but get filehandle * cookies on a per-superblock basis, depending on the mount flags */ -void nfs_fscache_get_client_cookie(struct nfs_client *clp) +static bool nfs_fscache_get_client_key(struct nfs_client *clp, + char *key, int *_len) { const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr; const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr; - struct nfs_server_key key; - uint16_t len = sizeof(key.hdr); - memset(&key, 0, sizeof(key)); - key.hdr.nfsversion = clp->rpc_ops->version; - key.hdr.minorversion = clp->cl_minorversion; - key.hdr.family = clp->cl_addr.ss_family; + *_len += snprintf(key + *_len, NFS_MAX_KEY_LEN - *_len, + ",%u.%u,%x", + clp->rpc_ops->version, + clp->cl_minorversion, + clp->cl_addr.ss_family); switch (clp->cl_addr.ss_family) { case AF_INET: - key.hdr.port = sin->sin_port; - key.ipv4_addr = sin->sin_addr; - len += sizeof(key.ipv4_addr); - break; + if (!nfs_append_int(key, _len, sin->sin_port) || + !nfs_append_int(key, _len, sin->sin_addr.s_addr)) + return false; + return true; case AF_INET6: - key.hdr.port = sin6->sin6_port; - key.ipv6_addr = sin6->sin6_addr; - len += sizeof(key.ipv6_addr); - break; + if (!nfs_append_int(key, _len, sin6->sin6_port) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[0]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[1]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[2]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[3])) + return false; + return true; default: printk(KERN_WARNING "NFS: Unknown network family '%d'\n", clp->cl_addr.ss_family); - clp->fscache = NULL; - return; + return false; } - - /* create a cache index for looking up filehandles */ - clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index, - &nfs_fscache_server_index_def, - &key, len, - NULL, 0, - clp, 0, true); - dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n", - clp, clp->fscache); -} - -/* - * Dispose of a per-client cookie - */ -void nfs_fscache_release_client_cookie(struct nfs_client *clp) -{ - dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n", - clp, clp->fscache); - - fscache_relinquish_cookie(clp->fscache, NULL, false); - clp->fscache = NULL; } /* - * Get the cache cookie for an NFS superblock. We have to handle - * uniquification here because the cache doesn't do it for us. + * Get the cache cookie for an NFS superblock. * * The default uniquifier is just an empty string, but it may be overridden * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent * superblock across an automount point of some nature. */ -void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) +int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) { - struct nfs_fscache_key *key, *xkey; + struct fscache_volume *vcookie; struct nfs_server *nfss = NFS_SB(sb); - struct rb_node **p, *parent; - int diff; + unsigned int len = 3; + char *key; - nfss->fscache_key = NULL; - nfss->fscache = NULL; - if (!uniq) { - uniq = ""; - ulen = 1; + if (uniq) { + nfss->fscache_uniq = kmemdup_nul(uniq, ulen, GFP_KERNEL); + if (!nfss->fscache_uniq) + return -ENOMEM; } - key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL); + key = kmalloc(NFS_MAX_KEY_LEN + 24, GFP_KERNEL); if (!key) - return; - - key->nfs_client = nfss->nfs_client; - key->key.super.s_flags = sb->s_flags & NFS_SB_MASK; - key->key.nfs_server.flags = nfss->flags; - key->key.nfs_server.rsize = nfss->rsize; - key->key.nfs_server.wsize = nfss->wsize; - key->key.nfs_server.acregmin = nfss->acregmin; - key->key.nfs_server.acregmax = nfss->acregmax; - key->key.nfs_server.acdirmin = nfss->acdirmin; - key->key.nfs_server.acdirmax = nfss->acdirmax; - key->key.nfs_server.fsid = nfss->fsid; - key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor; - - key->key.uniq_len = ulen; - memcpy(key->key.uniquifier, uniq, ulen); - - spin_lock(&nfs_fscache_keys_lock); - p = &nfs_fscache_keys.rb_node; - parent = NULL; - while (*p) { - parent = *p; - xkey = rb_entry(parent, struct nfs_fscache_key, node); - - if (key->nfs_client < xkey->nfs_client) - goto go_left; - if (key->nfs_client > xkey->nfs_client) - goto go_right; - - diff = memcmp(&key->key, &xkey->key, sizeof(key->key)); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - - if (key->key.uniq_len == 0) - goto non_unique; - diff = memcmp(key->key.uniquifier, - xkey->key.uniquifier, - key->key.uniq_len); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - goto non_unique; - - go_left: - p = &(*p)->rb_left; - continue; - go_right: - p = &(*p)->rb_right; + return -ENOMEM; + + memcpy(key, "nfs", 3); + if (!nfs_fscache_get_client_key(nfss->nfs_client, key, &len) || + !nfs_append_int(key, &len, nfss->fsid.major) || + !nfs_append_int(key, &len, nfss->fsid.minor) || + !nfs_append_int(key, &len, sb->s_flags & NFS_SB_MASK) || + !nfs_append_int(key, &len, nfss->flags) || + !nfs_append_int(key, &len, nfss->rsize) || + !nfs_append_int(key, &len, nfss->wsize) || + !nfs_append_int(key, &len, nfss->acregmin) || + !nfs_append_int(key, &len, nfss->acregmax) || + !nfs_append_int(key, &len, nfss->acdirmin) || + !nfs_append_int(key, &len, nfss->acdirmax) || + !nfs_append_int(key, &len, nfss->client->cl_auth->au_flavor)) + goto out; + + if (ulen > 0) { + if (ulen > NFS_MAX_KEY_LEN - len) + goto out; + key[len++] = ','; + memcpy(key + len, uniq, ulen); + len += ulen; } - - rb_link_node(&key->node, parent, p); - rb_insert_color(&key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - nfss->fscache_key = key; + key[len] = 0; /* create a cache index for looking up filehandles */ - nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache, - &nfs_fscache_super_index_def, - &key->key, - sizeof(key->key) + ulen, - NULL, 0, - nfss, 0, true); + vcookie = fscache_acquire_volume(key, + NULL, /* preferred_cache */ + NULL, 0 /* coherency_data */); dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", - nfss, nfss->fscache); - return; + nfss, vcookie); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(key); + return PTR_ERR(vcookie); + } + pr_err("NFS: Cache volume key already in use (%s)\n", key); + vcookie = NULL; + } + nfss->fscache = vcookie; -non_unique: - spin_unlock(&nfs_fscache_keys_lock); +out: kfree(key); - nfss->fscache_key = NULL; - nfss->fscache = NULL; - printk(KERN_WARNING "NFS:" - " Cache request denied due to non-unique superblock keys\n"); + return 0; } /* @@ -213,29 +155,9 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n", nfss, nfss->fscache); - fscache_relinquish_cookie(nfss->fscache, NULL, false); + fscache_relinquish_volume(nfss->fscache, NULL, false); nfss->fscache = NULL; - - if (nfss->fscache_key) { - spin_lock(&nfs_fscache_keys_lock); - rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - kfree(nfss->fscache_key); - nfss->fscache_key = NULL; - } -} - -static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, - struct nfs_inode *nfsi) -{ - memset(auxdata, 0, sizeof(*auxdata)); - auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); + kfree(nfss->fscache_uniq); } /* @@ -254,10 +176,12 @@ void nfs_fscache_init_inode(struct inode *inode) nfs_fscache_update_auxdata(&auxdata, nfsi); nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, - &nfs_fscache_inode_object_def, - nfsi->fh.data, nfsi->fh.size, - &auxdata, sizeof(auxdata), - nfsi, nfsi->vfs_inode.i_size, false); + 0, + nfsi->fh.data, /* index_key */ + nfsi->fh.size, + &auxdata, /* aux_data */ + sizeof(auxdata), + i_size_read(&nfsi->vfs_inode)); } /* @@ -265,24 +189,15 @@ void nfs_fscache_init_inode(struct inode *inode) */ void nfs_fscache_clear_inode(struct inode *inode) { - struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); - nfs_fscache_update_auxdata(&auxdata, nfsi); - fscache_relinquish_cookie(cookie, &auxdata, false); + fscache_relinquish_cookie(cookie, false); nfsi->fscache = NULL; } -static bool nfs_fscache_can_enable(void *data) -{ - struct inode *inode = data; - - return !inode_is_open_for_write(inode); -} - /* * Enable or disable caching for a file that is being opened as appropriate. * The cookie is allocated when the inode is initialised, but is not enabled at @@ -307,100 +222,104 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp) struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); + bool open_for_write = inode_is_open_for_write(inode); if (!fscache_cookie_valid(cookie)) return; - nfs_fscache_update_auxdata(&auxdata, nfsi); - - if (inode_is_open_for_write(inode)) { + fscache_use_cookie(cookie, open_for_write); + if (open_for_write) { dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); - clear_bit(NFS_INO_FSCACHE, &nfsi->flags); - fscache_disable_cookie(cookie, &auxdata, true); - fscache_uncache_all_inode_pages(cookie, inode); - } else { - dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi); - fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size, - nfs_fscache_can_enable, inode); - if (fscache_cookie_enabled(cookie)) - set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_invalidate(cookie, &auxdata, i_size_read(inode), + FSCACHE_INVAL_DIO_WRITE); } } EXPORT_SYMBOL_GPL(nfs_fscache_open_file); -/* - * Release the caching state associated with a page, if the page isn't busy - * interacting with the cache. - * - Returns true (can release page) or false (page busy). - */ -int nfs_fscache_release_page(struct page *page, gfp_t gfp) +void nfs_fscache_release_file(struct inode *inode, struct file *filp) { - if (PageFsCache(page)) { - struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host); - - BUG_ON(!cookie); - dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(page->mapping->host)); - - if (!fscache_maybe_release_page(cookie, page, gfp)) - return 0; + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); + struct fscache_cookie *cookie = nfs_i_fscache(inode); - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); + if (fscache_cookie_valid(cookie)) { + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_unuse_cookie(cookie, &auxdata, NULL); } +} - return 1; +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); } /* - * Release the caching state associated with a page if undergoing complete page - * invalidation. + * Fallback page reading interface. */ -void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) +static int fscache_fallback_read_page(struct inode *inode, struct page *page) { + struct netfs_cache_resources cres; struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + int ret; - BUG_ON(!cookie); - - dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(inode)); + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); - fscache_wait_on_page_write(cookie, page); + ret = fscache_begin_read_operation(&cres, cookie); + if (ret < 0) + return ret; - BUG_ON(!PageLocked(page)); - fscache_uncache_page(cookie, page); - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); + ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, + NULL, NULL); + fscache_end_operation(&cres); + return ret; } /* - * Handle completion of a page being read from the cache. - * - Called in process (keventd) context. + * Fallback page writing interface. */ -static void nfs_readpage_from_fscache_complete(struct page *page, - void *context, - int error) +static int fscache_fallback_write_page(struct inode *inode, struct page *page, + bool no_space_allocated_yet) { - dfprintk(FSCACHE, - "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n", - page, context, error); - - /* - * If the read completes with an error, mark the page with PG_checked, - * unlock the page, and let the VM reissue the readpage. - */ - if (!error) - SetPageUptodate(page); - else - SetPageChecked(page); - unlock_page(page); + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + loff_t start = page_offset(page); + size_t len = PAGE_SIZE; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_write_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), + no_space_allocated_yet); + if (ret == 0) + ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL); + fscache_end_operation(&cres); + return ret; } /* * Retrieve a page from fscache */ -int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, struct page *page) +int __nfs_readpage_from_fscache(struct inode *inode, struct page *page) { int ret; @@ -409,112 +328,49 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, nfs_i_fscache(inode), page, page->index, page->flags, inode); if (PageChecked(page)) { + dfprintk(FSCACHE, "NFS: readpage_from_fscache: PageChecked\n"); ClearPageChecked(page); return 1; } - ret = fscache_read_or_alloc_page(nfs_i_fscache(inode), - page, - nfs_readpage_from_fscache_complete, - ctx, - GFP_KERNEL); - - switch (ret) { - case 0: /* read BIO submitted (page in fscache) */ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache: BIO submitted\n"); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); - return ret; - - case -ENOBUFS: /* inode not in cache */ - case -ENODATA: /* page not in cache */ + ret = fscache_fallback_read_page(inode, page); + if (ret < 0) { nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); dfprintk(FSCACHE, - "NFS: readpage_from_fscache %d\n", ret); - return 1; - - default: - dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - } - return ret; -} - -/* - * Retrieve a set of pages from fscache - */ -int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - unsigned npages = *nr_pages; - int ret; - - dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", - nfs_i_fscache(inode), npages, inode); - - ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode), - mapping, pages, nr_pages, - nfs_readpage_from_fscache_complete, - ctx, - mapping_gfp_mask(mapping)); - if (*nr_pages < npages) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, - npages); - if (*nr_pages > 0) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, - *nr_pages); - - switch (ret) { - case 0: /* read submitted to the cache for all pages */ - BUG_ON(!list_empty(pages)); - BUG_ON(*nr_pages != 0); - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: submitted\n"); - + "NFS: readpage_from_fscache failed %d\n", ret); + SetPageChecked(page); return ret; - - case -ENOBUFS: /* some pages aren't cached and can't be */ - case -ENODATA: /* some pages aren't cached */ - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: no page: %d\n", ret); - return 1; - - default: - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: ret %d\n", ret); } - return ret; + /* Read completed synchronously */ + dfprintk(FSCACHE, "NFS: readpage_from_fscache: read successful\n"); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); + SetPageUptodate(page); + return 0; } /* - * Store a newly fetched page in fscache - * - PG_fscache must be set on the page + * Store a newly fetched page in fscache. We can be certain there's no page + * stored in the cache as yet otherwise we would've read it from there. */ -void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) +void __nfs_readpage_to_fscache(struct inode *inode, struct page *page) { int ret; dfprintk(FSCACHE, - "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", - nfs_i_fscache(inode), page, page->index, page->flags, sync); + "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx))\n", + nfs_i_fscache(inode), page, page->index, page->flags); + + ret = fscache_fallback_write_page(inode, page, true); - ret = fscache_write_page(nfs_i_fscache(inode), page, - inode->i_size, GFP_KERNEL); dfprintk(FSCACHE, "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", page, page->index, page->flags, ret); if (ret != 0) { - fscache_uncache_page(nfs_i_fscache(inode), page); - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); } else { - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK); } } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 6754c8607230..25a5c0f82392 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -8,51 +8,16 @@ #ifndef _NFS_FSCACHE_H #define _NFS_FSCACHE_H +#include <linux/swap.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/fscache.h> +#include <linux/iversion.h> #ifdef CONFIG_NFS_FSCACHE /* - * set of NFS FS-Cache objects that form a superblock key - */ -struct nfs_fscache_key { - struct rb_node node; - struct nfs_client *nfs_client; /* the server */ - - /* the elements of the unique key - as used by nfs_compare_super() and - * nfs_compare_mount_options() to distinguish superblocks */ - struct { - struct { - unsigned long s_flags; /* various flags - * (& NFS_MS_MASK) */ - } super; - - struct { - struct nfs_fsid fsid; - int flags; - unsigned int rsize; /* read size */ - unsigned int wsize; /* write size */ - unsigned int acregmin; /* attr cache timeouts */ - unsigned int acregmax; - unsigned int acdirmin; - unsigned int acdirmax; - } nfs_server; - - struct { - rpc_authflavor_t au_flavor; - } rpc_auth; - - /* uniquifier - can be used if nfs_server.flags includes - * NFS_MOUNT_UNSHARED */ - u8 uniq_len; - char uniquifier[0]; - } key; -}; - -/* * Definition of the auxiliary data attached to NFS inode storage objects * within the cache. * @@ -70,84 +35,42 @@ struct nfs_fscache_inode_auxdata { }; /* - * fscache-index.c - */ -extern struct fscache_netfs nfs_fscache_netfs; -extern const struct fscache_cookie_def nfs_fscache_server_index_def; -extern const struct fscache_cookie_def nfs_fscache_super_index_def; -extern const struct fscache_cookie_def nfs_fscache_inode_object_def; - -extern int nfs_fscache_register(void); -extern void nfs_fscache_unregister(void); - -/* * fscache.c */ -extern void nfs_fscache_get_client_cookie(struct nfs_client *); -extern void nfs_fscache_release_client_cookie(struct nfs_client *); - -extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int); +extern int nfs_fscache_get_super_cookie(struct super_block *, const char *, int); extern void nfs_fscache_release_super_cookie(struct super_block *); extern void nfs_fscache_init_inode(struct inode *); extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); +extern void nfs_fscache_release_file(struct inode *, struct file *); -extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); -extern int nfs_fscache_release_page(struct page *, gfp_t); +extern int __nfs_readpage_from_fscache(struct inode *, struct page *); +extern void __nfs_read_completion_to_fscache(struct nfs_pgio_header *hdr, + unsigned long bytes); +extern void __nfs_readpage_to_fscache(struct inode *, struct page *); -extern int __nfs_readpage_from_fscache(struct nfs_open_context *, - struct inode *, struct page *); -extern int __nfs_readpages_from_fscache(struct nfs_open_context *, - struct inode *, struct address_space *, - struct list_head *, unsigned *); -extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); - -/* - * wait for a page to complete writing to the cache - */ -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) -{ - if (PageFsCache(page)) - fscache_wait_on_page_write(nfsi->fscache, page); -} - -/* - * release the caching state associated with a page if undergoing complete page - * invalidation - */ -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) +static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { - if (PageFsCache(page)) - __nfs_fscache_invalidate_page(page, inode); + if (PageFsCache(page)) { + if (current_is_kswapd() || !(gfp & __GFP_FS)) + return false; + wait_on_page_fscache(page); + fscache_note_page_release(nfs_i_fscache(page->mapping->host)); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); + } + return true; } /* * Retrieve a page from an inode data storage object. */ -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, +static inline int nfs_readpage_from_fscache(struct inode *inode, struct page *page) { if (NFS_I(inode)->fscache) - return __nfs_readpage_from_fscache(ctx, inode, page); - return -ENOBUFS; -} - -/* - * Retrieve a set of pages from an inode data storage object. - */ -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - if (NFS_I(inode)->fscache) - return __nfs_readpages_from_fscache(ctx, inode, mapping, pages, - nr_pages); + return __nfs_readpage_from_fscache(inode, page); return -ENOBUFS; } @@ -156,27 +79,38 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, * in the cache. */ static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, - int sync) + struct page *page) { - if (PageFsCache(page)) - __nfs_readpage_to_fscache(inode, page, sync); + if (NFS_I(inode)->fscache) + __nfs_readpage_to_fscache(inode, page); } -/* - * Invalidate the contents of fscache for this inode. This will not sleep. - */ -static inline void nfs_fscache_invalidate(struct inode *inode) +static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, + struct nfs_inode *nfsi) { - fscache_invalidate(NFS_I(inode)->fscache); + memset(auxdata, 0, sizeof(*auxdata)); + auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; + auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; + auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; + auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + + if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) + auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); } /* - * Wait for an object to finish being invalidated. + * Invalidate the contents of fscache for this inode. This will not sleep. */ -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) { - fscache_wait_on_invalidate(NFS_I(inode)->fscache); + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); + + if (nfsi->fscache) { + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_invalidate(nfsi->fscache, &auxdata, + i_size_read(&nfsi->vfs_inode), flags); + } } /* @@ -190,48 +124,28 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server) } #else /* CONFIG_NFS_FSCACHE */ -static inline int nfs_fscache_register(void) { return 0; } -static inline void nfs_fscache_unregister(void) {} - -static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {} -static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {} - static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} static inline void nfs_fscache_init_inode(struct inode *inode) {} static inline void nfs_fscache_clear_inode(struct inode *inode) {} static inline void nfs_fscache_open_file(struct inode *inode, struct file *filp) {} +static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {} static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { return 1; /* True: may release page */ } -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) {} -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) {} - -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, +static inline int nfs_readpage_from_fscache(struct inode *inode, struct page *page) { return -ENOBUFS; } -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - return -ENOBUFS; -} static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, int sync) {} + struct page *page) {} -static inline void nfs_fscache_invalidate(struct inode *inode) {} -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {} +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} static inline const char *nfs_server_fscache_state(struct nfs_server *server) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index fda530d5e764..a918c3a834b6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -209,7 +209,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) - nfs_fscache_invalidate(inode); + nfs_fscache_invalidate(inode, 0); flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); nfsi->cache_validity |= flags; @@ -1289,6 +1289,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map { int ret; + nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); @@ -1300,7 +1301,6 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); - nfs_fscache_wait_on_invalidate(inode); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, @@ -2374,10 +2374,6 @@ static int __init init_nfs_fs(void) if (err < 0) goto out9; - err = nfs_fscache_register(); - if (err < 0) - goto out8; - err = nfsiod_start(); if (err) goto out7; @@ -2429,8 +2425,6 @@ out5: out6: nfsiod_stop(); out7: - nfs_fscache_unregister(); -out8: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); @@ -2445,7 +2439,6 @@ static void __exit exit_nfs_fs(void) nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); - nfs_fscache_unregister(); unregister_pernet_subsys(&nfs_net_ops); rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index b3aee261801e..317ce27bdc4b 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -42,7 +42,6 @@ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ { BIT(NFS_INO_FSCACHE), "FSCACHE" }, \ - { BIT(NFS_INO_FSCACHE_LOCK), "FSCACHE_LOCK" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ diff --git a/fs/nfs/read.c b/fs/nfs/read.c index d11af2a9299c..eb00229c1a50 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -123,7 +123,7 @@ static void nfs_readpage_release(struct nfs_page *req, int error) struct address_space *mapping = page_file_mapping(page); if (PageUptodate(page)) - nfs_readpage_to_fscache(inode, page, 0); + nfs_readpage_to_fscache(inode, page); else if (!PageError(page) && !PagePrivate(page)) generic_error_remove_page(mapping, page); unlock_page(page); @@ -305,6 +305,12 @@ readpage_async_filler(void *data, struct page *page) aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE); + if (!IS_SYNC(page->mapping->host)) { + error = nfs_readpage_from_fscache(page->mapping->host, page); + if (error == 0) + goto out_unlock; + } + new = nfs_create_request(desc->ctx, page, 0, aligned_len); if (IS_ERR(new)) goto out_error; @@ -320,6 +326,7 @@ readpage_async_filler(void *data, struct page *page) return 0; out_error: error = PTR_ERR(new); +out_unlock: unlock_page(page); out: return error; @@ -366,12 +373,6 @@ int nfs_readpage(struct file *file, struct page *page) desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); xchg(&desc.ctx->error, 0); - if (!IS_SYNC(inode)) { - ret = nfs_readpage_from_fscache(desc.ctx, inode, page); - if (ret == 0) - goto out_wait; - } - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -381,7 +382,6 @@ int nfs_readpage(struct file *file, struct page *page) nfs_pageio_complete_read(&desc.pgio); ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; -out_wait: if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) @@ -419,14 +419,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping, } else desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); - /* attempt to read as many of the pages as possible from the cache - * - this returns -ENOBUFS immediately if the cookie is negative - */ - ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping, - pages, &nr_pages); - if (ret == 0) - goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -434,7 +426,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping, nfs_pageio_complete_read(&desc.pgio); -read_complete: put_nfs_open_context(desc.ctx); out: trace_nfs_aop_readahead_done(inode, nr_pages, ret); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3aced401735c..6ab5eeb000dc 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1204,42 +1204,42 @@ static int nfs_compare_super(struct super_block *sb, struct fs_context *fc) } #ifdef CONFIG_NFS_FSCACHE -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { struct nfs_server *nfss = NFS_SB(sb); char *uniq = NULL; int ulen = 0; - nfss->fscache_key = NULL; nfss->fscache = NULL; if (!ctx) - return; + return 0; if (ctx->clone_data.sb) { struct nfs_server *mnt_s = NFS_SB(ctx->clone_data.sb); if (!(mnt_s->options & NFS_OPTION_FSCACHE)) - return; - if (mnt_s->fscache_key) { - uniq = mnt_s->fscache_key->key.uniquifier; - ulen = mnt_s->fscache_key->key.uniq_len; + return 0; + if (mnt_s->fscache_uniq) { + uniq = mnt_s->fscache_uniq; + ulen = strlen(uniq); } } else { if (!(ctx->options & NFS_OPTION_FSCACHE)) - return; + return 0; if (ctx->fscache_uniq) { uniq = ctx->fscache_uniq; ulen = strlen(ctx->fscache_uniq); } } - nfs_fscache_get_super_cookie(sb, uniq, ulen); + return nfs_fscache_get_super_cookie(sb, uniq, ulen); } #else -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { + return 0; } #endif @@ -1299,7 +1299,9 @@ int nfs_get_tree_common(struct fs_context *fc) s->s_blocksize_bits = bsize; s->s_blocksize = 1U << bsize; } - nfs_get_cache_cookie(s, ctx); + error = nfs_get_cache_cookie(s, ctx); + if (error < 0) + goto error_splat_super; } error = nfs_get_root(s, fc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9b7619ce17a7..987a187bd39a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -294,6 +294,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); out: spin_unlock(&inode->i_lock); + nfs_fscache_invalidate(inode, 0); } /* A writeback failed: mark the page as bad, and invalidate the page cache */ @@ -2125,8 +2126,11 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, if (PagePrivate(page)) return -EBUSY; - if (!nfs_fscache_release_page(page, GFP_KERNEL)) - return -EBUSY; + if (PageFsCache(page)) { + if (mode == MIGRATE_ASYNC) + return -EBUSY; + wait_on_page_fscache(page); + } return migrate_page(mapping, newpage, page, mode); } |