mirror of
https://github.com/torvalds/linux
synced 2024-09-06 09:51:23 +00:00
![Dave Wysochanski](/assets/img/avatar_default.png)
The loop inside nfs_netfs_issue_read() currently does not disable
interrupts while iterating through pages in the xarray to submit
for NFS read. This is not safe though since after taking xa_lock,
another page in the mapping could be processed for writeback inside
an interrupt, and deadlock can occur. The fix is simple and clean
if we use xa_for_each_range(), which handles the iteration with RCU
while reducing code complexity.
The problem is easily reproduced with the following test:
mount -o vers=3,fsc 127.0.0.1:/export /mnt/nfs
dd if=/dev/zero of=/mnt/nfs/file1.bin bs=4096 count=1
echo 3 > /proc/sys/vm/drop_caches
dd if=/mnt/nfs/file1.bin of=/dev/null
umount /mnt/nfs
On the console with a lockdep-enabled kernel a message similar to
the following will be seen:
================================
WARNING: inconsistent lock state
6.7.0-lockdbg+ #10 Not tainted
--------------------------------
inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage.
test5/1708 [HC0[0]:SC0[0]:HE1:SE1] takes:
ffff888127baa598 (&xa->xa_lock#4){+.?.}-{3:3}, at:
nfs_netfs_issue_read+0x1b2/0x4b0 [nfs]
{IN-SOFTIRQ-W} state was registered at:
lock_acquire+0x144/0x380
_raw_spin_lock_irqsave+0x4e/0xa0
__folio_end_writeback+0x17e/0x5c0
folio_end_writeback+0x93/0x1b0
iomap_finish_ioend+0xeb/0x6a0
blk_update_request+0x204/0x7f0
blk_mq_end_request+0x30/0x1c0
blk_complete_reqs+0x7e/0xa0
__do_softirq+0x113/0x544
__irq_exit_rcu+0xfe/0x120
irq_exit_rcu+0xe/0x20
sysvec_call_function_single+0x6f/0x90
asm_sysvec_call_function_single+0x1a/0x20
pv_native_safe_halt+0xf/0x20
default_idle+0x9/0x20
default_idle_call+0x67/0xa0
do_idle+0x2b5/0x300
cpu_startup_entry+0x34/0x40
start_secondary+0x19d/0x1c0
secondary_startup_64_no_verify+0x18f/0x19b
irq event stamp: 176891
hardirqs last enabled at (176891): [<ffffffffa67a0be4>]
_raw_spin_unlock_irqrestore+0x44/0x60
hardirqs last disabled at (176890): [<ffffffffa67a0899>]
_raw_spin_lock_irqsave+0x79/0xa0
softirqs last enabled at (176646): [<ffffffffa515d91e>]
__irq_exit_rcu+0xfe/0x120
softirqs last disabled at (176633): [<ffffffffa515d91e>]
__irq_exit_rcu+0xfe/0x120
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&xa->xa_lock#4);
<Interrupt>
lock(&xa->xa_lock#4);
*** DEADLOCK ***
2 locks held by test5/1708:
#0: ffff888127baa498 (&sb->s_type->i_mutex_key#22){++++}-{4:4}, at:
nfs_start_io_read+0x28/0x90 [nfs]
#1: ffff888127baa650 (mapping.invalidate_lock#3){.+.+}-{4:4}, at:
page_cache_ra_unbounded+0xa4/0x280
stack backtrace:
CPU: 6 PID: 1708 Comm: test5 Kdump: loaded Not tainted 6.7.0-lockdbg+
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-1.fc39
04/01/2014
Call Trace:
dump_stack_lvl+0x5b/0x90
mark_lock+0xb3f/0xd20
__lock_acquire+0x77b/0x3360
_raw_spin_lock+0x34/0x80
nfs_netfs_issue_read+0x1b2/0x4b0 [nfs]
netfs_begin_read+0x77f/0x980 [netfs]
nfs_netfs_readahead+0x45/0x60 [nfs]
nfs_readahead+0x323/0x5a0 [nfs]
read_pages+0xf3/0x5c0
page_cache_ra_unbounded+0x1c8/0x280
filemap_get_pages+0x38c/0xae0
filemap_read+0x206/0x5e0
nfs_file_read+0xb7/0x140 [nfs]
vfs_read+0x2a9/0x460
ksys_read+0xb7/0x140
Fixes: 000dbe0bec
("NFS: Convert buffered read paths to use netfs when fscache is enabled")
Suggested-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: David Howells <dhowells@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
382 lines
10 KiB
C
382 lines
10 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 <linux/xarray.h>
|
|
#include <linux/fscache.h>
|
|
#include <linux/netfs.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);
|
|
|
|
netfs_inode(inode)->cache = NULL;
|
|
if (!(nfss->fscache && S_ISREG(inode->i_mode)))
|
|
return;
|
|
|
|
nfs_fscache_update_auxdata(&auxdata, inode);
|
|
|
|
netfs_inode(inode)->cache = fscache_acquire_cookie(
|
|
nfss->fscache,
|
|
0,
|
|
nfsi->fh.data, /* index_key */
|
|
nfsi->fh.size,
|
|
&auxdata, /* aux_data */
|
|
sizeof(auxdata),
|
|
i_size_read(inode));
|
|
|
|
if (netfs_inode(inode)->cache)
|
|
mapping_set_release_always(inode->i_mapping);
|
|
}
|
|
|
|
/*
|
|
* Release a per-inode cookie.
|
|
*/
|
|
void nfs_fscache_clear_inode(struct inode *inode)
|
|
{
|
|
fscache_relinquish_cookie(netfs_i_cookie(netfs_inode(inode)), false);
|
|
netfs_inode(inode)->cache = 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 = netfs_i_cookie(netfs_inode(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 = netfs_i_cookie(netfs_inode(inode));
|
|
loff_t i_size = i_size_read(inode);
|
|
|
|
nfs_fscache_update_auxdata(&auxdata, inode);
|
|
fscache_unuse_cookie(cookie, &auxdata, &i_size);
|
|
}
|
|
|
|
int nfs_netfs_read_folio(struct file *file, struct folio *folio)
|
|
{
|
|
if (!netfs_inode(folio_inode(folio))->cache)
|
|
return -ENOBUFS;
|
|
|
|
return netfs_read_folio(file, folio);
|
|
}
|
|
|
|
int nfs_netfs_readahead(struct readahead_control *ractl)
|
|
{
|
|
struct inode *inode = ractl->mapping->host;
|
|
|
|
if (!netfs_inode(inode)->cache)
|
|
return -ENOBUFS;
|
|
|
|
netfs_readahead(ractl);
|
|
return 0;
|
|
}
|
|
|
|
static atomic_t nfs_netfs_debug_id;
|
|
static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file)
|
|
{
|
|
rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file));
|
|
rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void nfs_netfs_free_request(struct netfs_io_request *rreq)
|
|
{
|
|
put_nfs_open_context(rreq->netfs_priv);
|
|
}
|
|
|
|
static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq)
|
|
{
|
|
struct nfs_netfs_io_data *netfs;
|
|
|
|
netfs = kzalloc(sizeof(*netfs), GFP_KERNEL_ACCOUNT);
|
|
if (!netfs)
|
|
return NULL;
|
|
netfs->sreq = sreq;
|
|
refcount_set(&netfs->refcount, 1);
|
|
return netfs;
|
|
}
|
|
|
|
static bool nfs_netfs_clamp_length(struct netfs_io_subrequest *sreq)
|
|
{
|
|
size_t rsize = NFS_SB(sreq->rreq->inode->i_sb)->rsize;
|
|
|
|
sreq->len = min(sreq->len, rsize);
|
|
return true;
|
|
}
|
|
|
|
static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq)
|
|
{
|
|
struct nfs_netfs_io_data *netfs;
|
|
struct nfs_pageio_descriptor pgio;
|
|
struct inode *inode = sreq->rreq->inode;
|
|
struct nfs_open_context *ctx = sreq->rreq->netfs_priv;
|
|
struct page *page;
|
|
unsigned long idx;
|
|
int err;
|
|
pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT;
|
|
pgoff_t last = ((sreq->start + sreq->len -
|
|
sreq->transferred - 1) >> PAGE_SHIFT);
|
|
|
|
nfs_pageio_init_read(&pgio, inode, false,
|
|
&nfs_async_read_completion_ops);
|
|
|
|
netfs = nfs_netfs_alloc(sreq);
|
|
if (!netfs)
|
|
return netfs_subreq_terminated(sreq, -ENOMEM, false);
|
|
|
|
pgio.pg_netfs = netfs; /* used in completion */
|
|
|
|
xa_for_each_range(&sreq->rreq->mapping->i_pages, idx, page, start, last) {
|
|
/* nfs_read_add_folio() may schedule() due to pNFS layout and other RPCs */
|
|
err = nfs_read_add_folio(&pgio, ctx, page_folio(page));
|
|
if (err < 0) {
|
|
netfs->error = err;
|
|
goto out;
|
|
}
|
|
}
|
|
out:
|
|
nfs_pageio_complete_read(&pgio);
|
|
nfs_netfs_put(netfs);
|
|
}
|
|
|
|
void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr)
|
|
{
|
|
struct nfs_netfs_io_data *netfs = hdr->netfs;
|
|
|
|
if (!netfs)
|
|
return;
|
|
|
|
nfs_netfs_get(netfs);
|
|
}
|
|
|
|
int nfs_netfs_folio_unlock(struct folio *folio)
|
|
{
|
|
struct inode *inode = folio_file_mapping(folio)->host;
|
|
|
|
/*
|
|
* If fscache is enabled, netfs will unlock pages.
|
|
*/
|
|
if (netfs_inode(inode)->cache)
|
|
return 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
void nfs_netfs_read_completion(struct nfs_pgio_header *hdr)
|
|
{
|
|
struct nfs_netfs_io_data *netfs = hdr->netfs;
|
|
struct netfs_io_subrequest *sreq;
|
|
|
|
if (!netfs)
|
|
return;
|
|
|
|
sreq = netfs->sreq;
|
|
if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
|
|
__set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags);
|
|
|
|
if (hdr->error)
|
|
netfs->error = hdr->error;
|
|
else
|
|
atomic64_add(hdr->res.count, &netfs->transferred);
|
|
|
|
nfs_netfs_put(netfs);
|
|
hdr->netfs = NULL;
|
|
}
|
|
|
|
const struct netfs_request_ops nfs_netfs_ops = {
|
|
.init_request = nfs_netfs_init_request,
|
|
.free_request = nfs_netfs_free_request,
|
|
.issue_read = nfs_netfs_issue_read,
|
|
.clamp_length = nfs_netfs_clamp_length
|
|
};
|