9c4a5c75a6
Pass updated i_size in fscache_unuse_cookie() when called
from nfs_fscache_release_file(), which ensures the size of
an fscache object gets written to the cache storage. Failing
to do so results in unnessary reads from the NFS server, even
when the data is cached, due to a cachefiles object coherency
check failing with a trace similar to the following:
cachefiles_coherency: o=0000000e BAD osiz B=afbb3 c=0
This problem can be reproduced as follows:
#!/bin/bash
v=4.2; NFS_SERVER=127.0.0.1
set -e; trap cleanup EXIT; rc=1
function cleanup {
umount /mnt/nfs > /dev/null 2>&1
RC_STR="TEST PASS"
[ $rc -eq 1 ] && RC_STR="TEST FAIL"
echo "$RC_STR on $(uname -r) with NFSv$v and server $NFS_SERVER"
}
mount -o vers=$v,fsc $NFS_SERVER:/export /mnt/nfs
rm -f /mnt/nfs/file1.bin > /dev/null 2>&1
dd if=/dev/zero of=/mnt/nfs/file1.bin bs=4096 count=1 > /dev/null 2>&1
echo 3 > /proc/sys/vm/drop_caches
echo Read file 1st time from NFS server into fscache
dd if=/mnt/nfs/file1.bin of=/dev/null > /dev/null 2>&1
umount /mnt/nfs && mount -o vers=$v,fsc $NFS_SERVER:/export /mnt/nfs
echo 3 > /proc/sys/vm/drop_caches
echo Read file 2nd time from fscache
dd if=/mnt/nfs/file1.bin of=/dev/null > /dev/null 2>&1
echo Check mountstats for NFS read
grep -q "READ: 0" /proc/self/mountstats # (1st number) == 0
[ $? -eq 0 ] && rc=0
Fixes: a6b5a28eb5
"nfs: Convert to new fscache volume/cookie API"
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Tested-by: Daire Byrne <daire@dneg.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
349 lines
9.4 KiB
C
349 lines
9.4 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/* NFS filesystem cache interface
|
|
*
|
|
* 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/seq_file.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/iversion.h>
|
|
|
|
#include "internal.h"
|
|
#include "iostat.h"
|
|
#include "fscache.h"
|
|
#include "nfstrace.h"
|
|
|
|
#define NFS_MAX_KEY_LEN 1000
|
|
|
|
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
|
|
* flag was set
|
|
* - 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
|
|
*/
|
|
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;
|
|
|
|
*_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:
|
|
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:
|
|
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);
|
|
return false;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen)
|
|
{
|
|
struct fscache_volume *vcookie;
|
|
struct nfs_server *nfss = NFS_SB(sb);
|
|
unsigned int len = 3;
|
|
char *key;
|
|
|
|
if (uniq) {
|
|
nfss->fscache_uniq = kmemdup_nul(uniq, ulen, GFP_KERNEL);
|
|
if (!nfss->fscache_uniq)
|
|
return -ENOMEM;
|
|
}
|
|
|
|
key = kmalloc(NFS_MAX_KEY_LEN + 24, GFP_KERNEL);
|
|
if (!key)
|
|
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;
|
|
}
|
|
key[len] = 0;
|
|
|
|
/* create a cache index for looking up filehandles */
|
|
vcookie = fscache_acquire_volume(key,
|
|
NULL, /* preferred_cache */
|
|
NULL, 0 /* coherency_data */);
|
|
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;
|
|
|
|
out:
|
|
kfree(key);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* release a per-superblock cookie
|
|
*/
|
|
void nfs_fscache_release_super_cookie(struct super_block *sb)
|
|
{
|
|
struct nfs_server *nfss = NFS_SB(sb);
|
|
|
|
fscache_relinquish_volume(nfss->fscache, NULL, false);
|
|
nfss->fscache = NULL;
|
|
kfree(nfss->fscache_uniq);
|
|
}
|
|
|
|
/*
|
|
* Initialise the per-inode cache cookie pointer for an NFS inode.
|
|
*/
|
|
void nfs_fscache_init_inode(struct inode *inode)
|
|
{
|
|
struct nfs_fscache_inode_auxdata auxdata;
|
|
struct nfs_server *nfss = NFS_SERVER(inode);
|
|
struct nfs_inode *nfsi = NFS_I(inode);
|
|
|
|
nfsi->fscache = NULL;
|
|
if (!(nfss->fscache && S_ISREG(inode->i_mode)))
|
|
return;
|
|
|
|
nfs_fscache_update_auxdata(&auxdata, inode);
|
|
|
|
nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
|
|
0,
|
|
nfsi->fh.data, /* index_key */
|
|
nfsi->fh.size,
|
|
&auxdata, /* aux_data */
|
|
sizeof(auxdata),
|
|
i_size_read(inode));
|
|
}
|
|
|
|
/*
|
|
* Release a per-inode cookie.
|
|
*/
|
|
void nfs_fscache_clear_inode(struct inode *inode)
|
|
{
|
|
struct nfs_inode *nfsi = NFS_I(inode);
|
|
struct fscache_cookie *cookie = nfs_i_fscache(inode);
|
|
|
|
fscache_relinquish_cookie(cookie, false);
|
|
nfsi->fscache = NULL;
|
|
}
|
|
|
|
/*
|
|
* 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
|
|
* that time. Enablement is deferred to file-open time to avoid stat() and
|
|
* access() thrashing the cache.
|
|
*
|
|
* For now, with NFS, only regular files that are open read-only will be able
|
|
* to use the cache.
|
|
*
|
|
* We enable the cache for an inode if we open it read-only and it isn't
|
|
* currently open for writing. We disable the cache if the inode is open
|
|
* write-only.
|
|
*
|
|
* The caller uses the file struct to pin i_writecount on the inode before
|
|
* calling us when a file is opened for writing, so we can make use of that.
|
|
*
|
|
* Note that this may be invoked multiple times in parallel by parallel
|
|
* nfs_open() functions.
|
|
*/
|
|
void nfs_fscache_open_file(struct inode *inode, struct file *filp)
|
|
{
|
|
struct nfs_fscache_inode_auxdata auxdata;
|
|
struct fscache_cookie *cookie = nfs_i_fscache(inode);
|
|
bool open_for_write = inode_is_open_for_write(inode);
|
|
|
|
if (!fscache_cookie_valid(cookie))
|
|
return;
|
|
|
|
fscache_use_cookie(cookie, open_for_write);
|
|
if (open_for_write) {
|
|
nfs_fscache_update_auxdata(&auxdata, inode);
|
|
fscache_invalidate(cookie, &auxdata, i_size_read(inode),
|
|
FSCACHE_INVAL_DIO_WRITE);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(nfs_fscache_open_file);
|
|
|
|
void nfs_fscache_release_file(struct inode *inode, struct file *filp)
|
|
{
|
|
struct nfs_fscache_inode_auxdata auxdata;
|
|
struct fscache_cookie *cookie = nfs_i_fscache(inode);
|
|
loff_t i_size = i_size_read(inode);
|
|
|
|
nfs_fscache_update_auxdata(&auxdata, inode);
|
|
fscache_unuse_cookie(cookie, &auxdata, &i_size);
|
|
}
|
|
|
|
/*
|
|
* Fallback page reading interface.
|
|
*/
|
|
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;
|
|
|
|
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);
|
|
|
|
ret = fscache_begin_read_operation(&cres, cookie);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL,
|
|
NULL, NULL);
|
|
fscache_end_operation(&cres);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Fallback page writing interface.
|
|
*/
|
|
static int fscache_fallback_write_page(struct inode *inode, struct page *page,
|
|
bool no_space_allocated_yet)
|
|
{
|
|
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_fscache_read_page(struct inode *inode, struct page *page)
|
|
{
|
|
int ret;
|
|
|
|
trace_nfs_fscache_read_page(inode, page);
|
|
if (PageChecked(page)) {
|
|
ClearPageChecked(page);
|
|
ret = 1;
|
|
goto out;
|
|
}
|
|
|
|
ret = fscache_fallback_read_page(inode, page);
|
|
if (ret < 0) {
|
|
nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL);
|
|
SetPageChecked(page);
|
|
goto out;
|
|
}
|
|
|
|
/* Read completed synchronously */
|
|
nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK);
|
|
SetPageUptodate(page);
|
|
ret = 0;
|
|
out:
|
|
trace_nfs_fscache_read_page_exit(inode, page, ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* 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_fscache_write_page(struct inode *inode, struct page *page)
|
|
{
|
|
int ret;
|
|
|
|
trace_nfs_fscache_write_page(inode, page);
|
|
|
|
ret = fscache_fallback_write_page(inode, page, true);
|
|
|
|
if (ret != 0) {
|
|
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);
|
|
}
|
|
trace_nfs_fscache_write_page_exit(inode, page, ret);
|
|
}
|