linux/fs/ceph/cache.c
David Howells b4fa966f03 mm, netfs, fscache: stop read optimisation when folio removed from pagecache
Fscache has an optimisation by which reads from the cache are skipped
until we know that (a) there's data there to be read and (b) that data
isn't entirely covered by pages resident in the netfs pagecache.  This is
done with two flags manipulated by fscache_note_page_release():

	if (...
	    test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) &&
	    test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags))
		clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags);

where the NO_DATA_TO_READ flag causes cachefiles_prepare_read() to
indicate that netfslib should download from the server or clear the page
instead.

The fscache_note_page_release() function is intended to be called from
->releasepage() - but that only gets called if PG_private or PG_private_2
is set - and currently the former is at the discretion of the network
filesystem and the latter is only set whilst a page is being written to
the cache, so sometimes we miss clearing the optimisation.

Fix this by following Willy's suggestion[1] and adding an address_space
flag, AS_RELEASE_ALWAYS, that causes filemap_release_folio() to always call
->release_folio() if it's set, even if PG_private or PG_private_2 aren't
set.

Note that this would require folio_test_private() and page_has_private() to
become more complicated.  To avoid that, in the places[*] where these are
used to conditionalise calls to filemap_release_folio() and
try_to_release_page(), the tests are removed the those functions just
jumped to unconditionally and the test is performed there.

[*] There are some exceptions in vmscan.c where the check guards more than
just a call to the releaser.  I've added a function, folio_needs_release()
to wrap all the checks for that.

AS_RELEASE_ALWAYS should be set if a non-NULL cookie is obtained from
fscache and cleared in ->evict_inode() before truncate_inode_pages_final()
is called.

Additionally, the FSCACHE_COOKIE_NO_DATA_TO_READ flag needs to be cleared
and the optimisation cancelled if a cachefiles object already contains data
when we open it.

[dwysocha@redhat.com: call folio_mapping() inside folio_needs_release()]
  Link: 902c990e31
Link: https://lkml.kernel.org/r/20230628104852.3391651-3-dhowells@redhat.com
Fixes: 1f67e6d0b1 ("fscache: Provide a function to note the release of a page")
Fixes: 047487c947 ("cachefiles: Implement the I/O routines")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Reported-by: Rohith Surabattula <rohiths.msft@gmail.com>
Suggested-by: Matthew Wilcox <willy@infradead.org>
Tested-by: SeongJae Park <sj@kernel.org>
Cc: Daire Byrne <daire.byrne@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Steve French <sfrench@samba.org>
Cc: Shyam Prasad N <nspmangalore@gmail.com>
Cc: Rohith Surabattula <rohiths.msft@gmail.com>
Cc: Dave Wysochanski <dwysocha@redhat.com>
Cc: Dominique Martinet <asmadeus@codewreck.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Jingbo Xu <jefflexu@linux.alibaba.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-18 10:12:13 -07:00

113 lines
2.8 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* Ceph cache definitions.
*
* Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved.
* Written by Milosz Tanski (milosz@adfin.com)
*/
#include <linux/ceph/ceph_debug.h>
#include <linux/fs_context.h>
#include "super.h"
#include "cache.h"
void ceph_fscache_register_inode_cookie(struct inode *inode)
{
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;
/* Regular files only */
if (!S_ISREG(inode->i_mode))
return;
/* Only new inodes! */
if (!(inode->i_state & I_NEW))
return;
WARN_ON_ONCE(ci->netfs.cache);
ci->netfs.cache =
fscache_acquire_cookie(fsc->fscache, 0,
&ci->i_vino, sizeof(ci->i_vino),
&ci->i_version, sizeof(ci->i_version),
i_size_read(inode));
if (ci->netfs.cache)
mapping_set_release_always(inode->i_mapping);
}
void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci)
{
fscache_relinquish_cookie(ceph_fscache_cookie(ci), false);
}
void ceph_fscache_use_cookie(struct inode *inode, bool will_modify)
{
struct ceph_inode_info *ci = ceph_inode(inode);
fscache_use_cookie(ceph_fscache_cookie(ci), will_modify);
}
void ceph_fscache_unuse_cookie(struct inode *inode, bool update)
{
struct ceph_inode_info *ci = ceph_inode(inode);
if (update) {
loff_t i_size = i_size_read(inode);
fscache_unuse_cookie(ceph_fscache_cookie(ci),
&ci->i_version, &i_size);
} else {
fscache_unuse_cookie(ceph_fscache_cookie(ci), NULL, NULL);
}
}
void ceph_fscache_update(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
loff_t i_size = i_size_read(inode);
fscache_update_cookie(ceph_fscache_cookie(ci), &ci->i_version, &i_size);
}
void ceph_fscache_invalidate(struct inode *inode, bool dio_write)
{
struct ceph_inode_info *ci = ceph_inode(inode);
fscache_invalidate(ceph_fscache_cookie(ci),
&ci->i_version, i_size_read(inode),
dio_write ? FSCACHE_INVAL_DIO_WRITE : 0);
}
int ceph_fscache_register_fs(struct ceph_fs_client* fsc, struct fs_context *fc)
{
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;
name = kasprintf(GFP_KERNEL, "ceph,%pU%s%s", fsid, uniq_len ? "," : "",
uniq_len ? fscache_uniq : "");
if (!name)
return -ENOMEM;
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)
{
fscache_relinquish_volume(fsc->fscache, NULL, false);
}