WSL2-Linux-Kernel/fs/9p/vfs_inode.c

1447 строки
33 KiB
C
Исходник Обычный вид История

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/fs/9p/vfs_inode.c
*
* This file contains vfs inode ops for the 9P2000 protocol.
*
* Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
* Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pagemap.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/inet.h>
#include <linux/namei.h>
#include <linux/idr.h>
#include <linux/sched.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>
#include "v9fs.h"
#include "v9fs_vfs.h"
#include "fid.h"
#include "cache.h"
#include "xattr.h"
#include "acl.h"
static const struct inode_operations v9fs_dir_inode_operations;
static const struct inode_operations v9fs_dir_inode_operations_dotu;
static const struct inode_operations v9fs_file_inode_operations;
static const struct inode_operations v9fs_symlink_inode_operations;
/**
* unixmode2p9mode - convert unix mode bits to plan 9
* @v9ses: v9fs session information
* @mode: mode to convert
*
*/
static u32 unixmode2p9mode(struct v9fs_session_info *v9ses, umode_t mode)
{
int res;
res = mode & 0777;
if (S_ISDIR(mode))
res |= P9_DMDIR;
if (v9fs_proto_dotu(v9ses)) {
if (v9ses->nodev == 0) {
if (S_ISSOCK(mode))
res |= P9_DMSOCKET;
if (S_ISFIFO(mode))
res |= P9_DMNAMEDPIPE;
if (S_ISBLK(mode))
res |= P9_DMDEVICE;
if (S_ISCHR(mode))
res |= P9_DMDEVICE;
}
if ((mode & S_ISUID) == S_ISUID)
res |= P9_DMSETUID;
if ((mode & S_ISGID) == S_ISGID)
res |= P9_DMSETGID;
if ((mode & S_ISVTX) == S_ISVTX)
res |= P9_DMSETVTX;
}
return res;
}
/**
* p9mode2perm- convert plan9 mode bits to unix permission bits
* @v9ses: v9fs session information
* @stat: p9_wstat from which mode need to be derived
*
*/
static int p9mode2perm(struct v9fs_session_info *v9ses,
struct p9_wstat *stat)
{
int res;
int mode = stat->mode;
res = mode & S_IALLUGO;
if (v9fs_proto_dotu(v9ses)) {
if ((mode & P9_DMSETUID) == P9_DMSETUID)
res |= S_ISUID;
if ((mode & P9_DMSETGID) == P9_DMSETGID)
res |= S_ISGID;
if ((mode & P9_DMSETVTX) == P9_DMSETVTX)
res |= S_ISVTX;
}
return res;
}
/**
* p9mode2unixmode- convert plan9 mode bits to unix mode bits
* @v9ses: v9fs session information
* @stat: p9_wstat from which mode need to be derived
* @rdev: major number, minor number in case of device files.
*
*/
static umode_t p9mode2unixmode(struct v9fs_session_info *v9ses,
struct p9_wstat *stat, dev_t *rdev)
{
int res;
u32 mode = stat->mode;
*rdev = 0;
res = p9mode2perm(v9ses, stat);
if ((mode & P9_DMDIR) == P9_DMDIR)
res |= S_IFDIR;
else if ((mode & P9_DMSYMLINK) && (v9fs_proto_dotu(v9ses)))
res |= S_IFLNK;
else if ((mode & P9_DMSOCKET) && (v9fs_proto_dotu(v9ses))
&& (v9ses->nodev == 0))
res |= S_IFSOCK;
else if ((mode & P9_DMNAMEDPIPE) && (v9fs_proto_dotu(v9ses))
&& (v9ses->nodev == 0))
res |= S_IFIFO;
else if ((mode & P9_DMDEVICE) && (v9fs_proto_dotu(v9ses))
&& (v9ses->nodev == 0)) {
char type = 0, ext[32];
int major = -1, minor = -1;
strlcpy(ext, stat->extension, sizeof(ext));
sscanf(ext, "%c %i %i", &type, &major, &minor);
switch (type) {
case 'c':
res |= S_IFCHR;
break;
case 'b':
res |= S_IFBLK;
break;
default:
p9_debug(P9_DEBUG_ERROR, "Unknown special type %c %s\n",
type, stat->extension);
}
*rdev = MKDEV(major, minor);
} else
res |= S_IFREG;
return res;
}
/**
* v9fs_uflags2omode- convert posix open flags to plan 9 mode bits
* @uflags: flags to convert
* @extended: if .u extensions are active
*/
int v9fs_uflags2omode(int uflags, int extended)
{
int ret;
ret = 0;
switch (uflags&3) {
default:
case O_RDONLY:
ret = P9_OREAD;
break;
case O_WRONLY:
ret = P9_OWRITE;
break;
case O_RDWR:
ret = P9_ORDWR;
break;
}
if (extended) {
if (uflags & O_EXCL)
ret |= P9_OEXCL;
if (uflags & O_APPEND)
ret |= P9_OAPPEND;
}
return ret;
}
/**
* v9fs_blank_wstat - helper function to setup a 9P stat structure
* @wstat: structure to initialize
*
*/
void
v9fs_blank_wstat(struct p9_wstat *wstat)
{
wstat->type = ~0;
wstat->dev = ~0;
wstat->qid.type = ~0;
wstat->qid.version = ~0;
*((long long *)&wstat->qid.path) = ~0;
wstat->mode = ~0;
wstat->atime = ~0;
wstat->mtime = ~0;
wstat->length = ~0;
wstat->name = NULL;
wstat->uid = NULL;
wstat->gid = NULL;
wstat->muid = NULL;
wstat->n_uid = INVALID_UID;
wstat->n_gid = INVALID_GID;
wstat->n_muid = INVALID_UID;
wstat->extension = NULL;
}
/**
* v9fs_alloc_inode - helper function to allocate an inode
*
*/
struct inode *v9fs_alloc_inode(struct super_block *sb)
{
struct v9fs_inode *v9inode;
v9inode = kmem_cache_alloc(v9fs_inode_cache, GFP_KERNEL);
if (!v9inode)
return NULL;
#ifdef CONFIG_9P_FSCACHE
v9inode->fscache = NULL;
mutex_init(&v9inode->fscache_lock);
#endif
v9inode->writeback_fid = NULL;
v9inode->cache_validity = 0;
mutex_init(&v9inode->v_mutex);
return &v9inode->vfs_inode;
}
/**
* v9fs_free_inode - destroy an inode
*
*/
void v9fs_free_inode(struct inode *inode)
{
kmem_cache_free(v9fs_inode_cache, V9FS_I(inode));
}
2011-01-07 09:49:49 +03:00
int v9fs_init_inode(struct v9fs_session_info *v9ses,
struct inode *inode, umode_t mode, dev_t rdev)
{
int err = 0;
inode_init_owner(inode, NULL, mode);
inode->i_blocks = 0;
inode->i_rdev = rdev;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_mapping->a_ops = &v9fs_addr_operations;
inode->i_private = NULL;
switch (mode & S_IFMT) {
case S_IFIFO:
case S_IFBLK:
case S_IFCHR:
case S_IFSOCK:
if (v9fs_proto_dotl(v9ses)) {
inode->i_op = &v9fs_file_inode_operations_dotl;
} else if (v9fs_proto_dotu(v9ses)) {
inode->i_op = &v9fs_file_inode_operations;
} else {
p9_debug(P9_DEBUG_ERROR,
"special files without extended mode\n");
err = -EINVAL;
goto error;
}
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
case S_IFREG:
if (v9fs_proto_dotl(v9ses)) {
inode->i_op = &v9fs_file_inode_operations_dotl;
if (v9ses->cache == CACHE_LOOSE ||
v9ses->cache == CACHE_FSCACHE)
inode->i_fop =
&v9fs_cached_file_operations_dotl;
else if (v9ses->cache == CACHE_MMAP)
inode->i_fop = &v9fs_mmap_file_operations_dotl;
else
inode->i_fop = &v9fs_file_operations_dotl;
} else {
inode->i_op = &v9fs_file_inode_operations;
if (v9ses->cache == CACHE_LOOSE ||
v9ses->cache == CACHE_FSCACHE)
inode->i_fop =
&v9fs_cached_file_operations;
else if (v9ses->cache == CACHE_MMAP)
inode->i_fop = &v9fs_mmap_file_operations;
else
inode->i_fop = &v9fs_file_operations;
}
break;
case S_IFLNK:
if (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)) {
p9_debug(P9_DEBUG_ERROR,
"extended modes used with legacy protocol\n");
err = -EINVAL;
goto error;
}
if (v9fs_proto_dotl(v9ses))
inode->i_op = &v9fs_symlink_inode_operations_dotl;
else
inode->i_op = &v9fs_symlink_inode_operations;
break;
case S_IFDIR:
inc_nlink(inode);
if (v9fs_proto_dotl(v9ses))
inode->i_op = &v9fs_dir_inode_operations_dotl;
else if (v9fs_proto_dotu(v9ses))
inode->i_op = &v9fs_dir_inode_operations_dotu;
else
inode->i_op = &v9fs_dir_inode_operations;
if (v9fs_proto_dotl(v9ses))
inode->i_fop = &v9fs_dir_operations_dotl;
else
inode->i_fop = &v9fs_dir_operations;
break;
default:
p9_debug(P9_DEBUG_ERROR, "BAD mode 0x%hx S_IFMT 0x%x\n",
mode, mode & S_IFMT);
err = -EINVAL;
goto error;
}
error:
return err;
}
/**
* v9fs_get_inode - helper function to setup an inode
* @sb: superblock
* @mode: mode to setup inode with
*
*/
struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev)
{
int err;
struct inode *inode;
struct v9fs_session_info *v9ses = sb->s_fs_info;
p9_debug(P9_DEBUG_VFS, "super block: %p mode: %ho\n", sb, mode);
inode = new_inode(sb);
if (!inode) {
pr_warn("%s (%d): Problem allocating inode\n",
__func__, task_pid_nr(current));
return ERR_PTR(-ENOMEM);
}
err = v9fs_init_inode(v9ses, inode, mode, rdev);
if (err) {
iput(inode);
return ERR_PTR(err);
}
return inode;
}
/**
* v9fs_clear_inode - release an inode
* @inode: inode to release
*
*/
void v9fs_evict_inode(struct inode *inode)
{
struct v9fs_inode *v9inode = V9FS_I(inode);
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
filemap_fdatawrite(&inode->i_data);
v9fs_cache_inode_put_cookie(inode);
/* clunk the fid stashed in writeback_fid */
if (v9inode->writeback_fid) {
p9_client_clunk(v9inode->writeback_fid);
v9inode->writeback_fid = NULL;
}
}
static int v9fs_test_inode(struct inode *inode, void *data)
{
int umode;
dev_t rdev;
struct v9fs_inode *v9inode = V9FS_I(inode);
struct p9_wstat *st = (struct p9_wstat *)data;
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode);
umode = p9mode2unixmode(v9ses, st, &rdev);
/* don't match inode of different type */
if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
return 0;
/* compare qid details */
if (memcmp(&v9inode->qid.version,
&st->qid.version, sizeof(v9inode->qid.version)))
return 0;
if (v9inode->qid.type != st->qid.type)
return 0;
if (v9inode->qid.path != st->qid.path)
return 0;
return 1;
}
static int v9fs_test_new_inode(struct inode *inode, void *data)
{
return 0;
}
static int v9fs_set_inode(struct inode *inode, void *data)
{
struct v9fs_inode *v9inode = V9FS_I(inode);
struct p9_wstat *st = (struct p9_wstat *)data;
memcpy(&v9inode->qid, &st->qid, sizeof(st->qid));
return 0;
}
static struct inode *v9fs_qid_iget(struct super_block *sb,
struct p9_qid *qid,
struct p9_wstat *st,
int new)
{
dev_t rdev;
int retval;
umode_t umode;
unsigned long i_ino;
struct inode *inode;
struct v9fs_session_info *v9ses = sb->s_fs_info;
int (*test)(struct inode *, void *);
if (new)
test = v9fs_test_new_inode;
else
test = v9fs_test_inode;
i_ino = v9fs_qid2ino(qid);
inode = iget5_locked(sb, i_ino, test, v9fs_set_inode, st);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
/*
* initialize the inode with the stat info
* FIXME!! we may need support for stale inodes
* later.
*/
inode->i_ino = i_ino;
umode = p9mode2unixmode(v9ses, st, &rdev);
retval = v9fs_init_inode(v9ses, inode, umode, rdev);
if (retval)
goto error;
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
v9fs_stat2inode(st, inode, sb, 0);
v9fs_cache_inode_get_cookie(inode);
unlock_new_inode(inode);
return inode;
error:
iget_failed(inode);
return ERR_PTR(retval);
}
struct inode *
v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
struct super_block *sb, int new)
{
struct p9_wstat *st;
struct inode *inode = NULL;
st = p9_client_stat(fid);
if (IS_ERR(st))
return ERR_CAST(st);
inode = v9fs_qid_iget(sb, &st->qid, st, new);
p9stat_free(st);
kfree(st);
return inode;
}
/**
* v9fs_at_to_dotl_flags- convert Linux specific AT flags to
* plan 9 AT flag.
* @flags: flags to convert
*/
static int v9fs_at_to_dotl_flags(int flags)
{
int rflags = 0;
if (flags & AT_REMOVEDIR)
rflags |= P9_DOTL_AT_REMOVEDIR;
return rflags;
}
9p: don't maintain dir i_nlink if the exported fs doesn't either If the exported filesystem dir on 9p server doesn't maintain accurate i_nlink count, e.g. always reports i_nlink as 1, then 9p should not maintain nlink count either, otherwise drop_link would report warning with i_nlink being zero. For example: - overlayfs sets nlink to 1 for merged dir - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more than EXT4_LINK_MAX (65000) links. In this case, everytime a stat(2) call (getattr) on such exported dirs on 9p client side, the i_nlink gets reset to 1, then operations like rmdir(2), unlink(2) and rename(2) would cause the dir nlink to go to zero (then negative), which results in warnings in drop_nlink() and/or inc_nlink() calls. This can be reproduced easily as the following steps: - export a merged overlayfs dir via qemu virtfs to guest - mount the exported virtfs in guest - create two sub-directories in the root dir of the mounted 9pfs - stat the root dir of 9pfs, this resets nlink to 1 - remove all subdirs, the second unlink/rmdir would trigger warning ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1284 at fs/inode.c:282 drop_nlink+0x3e/0x50 ... Call Trace: dump_stack+0x63/0x81 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 drop_nlink+0x3e/0x50 v9fs_remove+0xaa/0x130 [9p] v9fs_vfs_rmdir+0x13/0x20 [9p] vfs_rmdir+0xb7/0x130 do_rmdir+0x1b8/0x230 SyS_unlinkat+0x22/0x30 do_syscall_64+0x67/0x180 ---[ end trace 43758d8ba91e603b ]--- Fix it by leaving i_nlink to be 1 and don't drop nlink if a directory has nlink <= 2, which indicates that the underlying exported fs doesn't maintain nlink count accurately. This follows what ext4 does in ext4_dec_count(). Link: http://lkml.kernel.org/r/20180312053829.4367-1-eguan@linux.alibaba.com Signed-off-by: Eryu Guan <eguan@linux.alibaba.com> Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com> Tested-by: Roman Kapl <code@rkapl.cz> Cc: Caspar Zhang <caspar@linux.alibaba.com> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Cc: <v9fs-developer@lists.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-06 02:19:49 +03:00
/**
* v9fs_dec_count - helper functon to drop i_nlink.
*
* If a directory had nlink <= 2 (including . and ..), then we should not drop
* the link count, which indicates the underlying exported fs doesn't maintain
* nlink accurately. e.g.
* - overlayfs sets nlink to 1 for merged dir
* - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more
* than EXT4_LINK_MAX (65000) links.
*
* @inode: inode whose nlink is being dropped
*/
static void v9fs_dec_count(struct inode *inode)
{
if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
drop_nlink(inode);
}
/**
* v9fs_remove - helper function to remove files and directories
* @dir: directory inode that is being deleted
* @dentry: dentry that is being deleted
* @flags: removing a directory
*
*/
static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
{
struct inode *inode;
int retval = -EOPNOTSUPP;
struct p9_fid *v9fid, *dfid;
struct v9fs_session_info *v9ses;
p9_debug(P9_DEBUG_VFS, "inode: %p dentry: %p rmdir: %x\n",
dir, dentry, flags);
v9ses = v9fs_inode2v9ses(dir);
inode = d_inode(dentry);
dfid = v9fs_parent_fid(dentry);
if (IS_ERR(dfid)) {
retval = PTR_ERR(dfid);
p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", retval);
return retval;
}
if (v9fs_proto_dotl(v9ses))
retval = p9_client_unlinkat(dfid, dentry->d_name.name,
v9fs_at_to_dotl_flags(flags));
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
if (retval == -EOPNOTSUPP) {
/* Try the one based on path */
v9fid = v9fs_fid_clone(dentry);
if (IS_ERR(v9fid))
return PTR_ERR(v9fid);
retval = p9_client_remove(v9fid);
}
if (!retval) {
/*
* directories on unlink should have zero
* link count
*/
if (flags & AT_REMOVEDIR) {
clear_nlink(inode);
9p: don't maintain dir i_nlink if the exported fs doesn't either If the exported filesystem dir on 9p server doesn't maintain accurate i_nlink count, e.g. always reports i_nlink as 1, then 9p should not maintain nlink count either, otherwise drop_link would report warning with i_nlink being zero. For example: - overlayfs sets nlink to 1 for merged dir - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more than EXT4_LINK_MAX (65000) links. In this case, everytime a stat(2) call (getattr) on such exported dirs on 9p client side, the i_nlink gets reset to 1, then operations like rmdir(2), unlink(2) and rename(2) would cause the dir nlink to go to zero (then negative), which results in warnings in drop_nlink() and/or inc_nlink() calls. This can be reproduced easily as the following steps: - export a merged overlayfs dir via qemu virtfs to guest - mount the exported virtfs in guest - create two sub-directories in the root dir of the mounted 9pfs - stat the root dir of 9pfs, this resets nlink to 1 - remove all subdirs, the second unlink/rmdir would trigger warning ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1284 at fs/inode.c:282 drop_nlink+0x3e/0x50 ... Call Trace: dump_stack+0x63/0x81 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 drop_nlink+0x3e/0x50 v9fs_remove+0xaa/0x130 [9p] v9fs_vfs_rmdir+0x13/0x20 [9p] vfs_rmdir+0xb7/0x130 do_rmdir+0x1b8/0x230 SyS_unlinkat+0x22/0x30 do_syscall_64+0x67/0x180 ---[ end trace 43758d8ba91e603b ]--- Fix it by leaving i_nlink to be 1 and don't drop nlink if a directory has nlink <= 2, which indicates that the underlying exported fs doesn't maintain nlink count accurately. This follows what ext4 does in ext4_dec_count(). Link: http://lkml.kernel.org/r/20180312053829.4367-1-eguan@linux.alibaba.com Signed-off-by: Eryu Guan <eguan@linux.alibaba.com> Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com> Tested-by: Roman Kapl <code@rkapl.cz> Cc: Caspar Zhang <caspar@linux.alibaba.com> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Cc: <v9fs-developer@lists.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-06 02:19:49 +03:00
v9fs_dec_count(dir);
} else
9p: don't maintain dir i_nlink if the exported fs doesn't either If the exported filesystem dir on 9p server doesn't maintain accurate i_nlink count, e.g. always reports i_nlink as 1, then 9p should not maintain nlink count either, otherwise drop_link would report warning with i_nlink being zero. For example: - overlayfs sets nlink to 1 for merged dir - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more than EXT4_LINK_MAX (65000) links. In this case, everytime a stat(2) call (getattr) on such exported dirs on 9p client side, the i_nlink gets reset to 1, then operations like rmdir(2), unlink(2) and rename(2) would cause the dir nlink to go to zero (then negative), which results in warnings in drop_nlink() and/or inc_nlink() calls. This can be reproduced easily as the following steps: - export a merged overlayfs dir via qemu virtfs to guest - mount the exported virtfs in guest - create two sub-directories in the root dir of the mounted 9pfs - stat the root dir of 9pfs, this resets nlink to 1 - remove all subdirs, the second unlink/rmdir would trigger warning ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1284 at fs/inode.c:282 drop_nlink+0x3e/0x50 ... Call Trace: dump_stack+0x63/0x81 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 drop_nlink+0x3e/0x50 v9fs_remove+0xaa/0x130 [9p] v9fs_vfs_rmdir+0x13/0x20 [9p] vfs_rmdir+0xb7/0x130 do_rmdir+0x1b8/0x230 SyS_unlinkat+0x22/0x30 do_syscall_64+0x67/0x180 ---[ end trace 43758d8ba91e603b ]--- Fix it by leaving i_nlink to be 1 and don't drop nlink if a directory has nlink <= 2, which indicates that the underlying exported fs doesn't maintain nlink count accurately. This follows what ext4 does in ext4_dec_count(). Link: http://lkml.kernel.org/r/20180312053829.4367-1-eguan@linux.alibaba.com Signed-off-by: Eryu Guan <eguan@linux.alibaba.com> Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com> Tested-by: Roman Kapl <code@rkapl.cz> Cc: Caspar Zhang <caspar@linux.alibaba.com> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Cc: <v9fs-developer@lists.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-06 02:19:49 +03:00
v9fs_dec_count(inode);
v9fs_invalidate_inode_attr(inode);
v9fs_invalidate_inode_attr(dir);
/* invalidate all fids associated with dentry */
/* NOTE: This will not include open fids */
dentry->d_op->d_release(dentry);
}
return retval;
}
/**
* v9fs_create - Create a file
* @v9ses: session information
* @dir: directory that dentry is being created in
* @dentry: dentry that is being created
* @extension: 9p2000.u extension string to support devices, etc.
* @perm: create permissions
* @mode: open mode
*
*/
static struct p9_fid *
v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
struct dentry *dentry, char *extension, u32 perm, u8 mode)
{
int err;
const unsigned char *name;
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
struct p9_fid *dfid, *ofid = NULL, *fid = NULL;
struct inode *inode;
p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
err = 0;
name = dentry->d_name.name;
dfid = v9fs_parent_fid(dentry);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
if (IS_ERR(dfid)) {
err = PTR_ERR(dfid);
p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
return ERR_PTR(err);
}
/* clone a fid to use for creation */
ofid = clone_fid(dfid);
if (IS_ERR(ofid)) {
err = PTR_ERR(ofid);
p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
return ERR_PTR(err);
}
err = p9_client_fcreate(ofid, name, perm, mode, extension);
if (err < 0) {
p9_debug(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
goto error;
}
if (!(perm & P9_DMLINK)) {
/* now walk from the parent so we can get unopened fid */
fid = p9_client_walk(dfid, 1, &name, 1);
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
p9_debug(P9_DEBUG_VFS,
"p9_client_walk failed %d\n", err);
fid = NULL;
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
goto error;
}
/*
* instantiate inode and assign the unopened fid to the dentry
*/
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
p9_debug(P9_DEBUG_VFS,
"inode creation failed %d\n", err);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
goto error;
}
v9fs_fid_add(dentry, fid);
d_instantiate(dentry, inode);
}
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
return ofid;
error:
if (ofid)
p9_client_clunk(ofid);
if (fid)
p9_client_clunk(fid);
return ERR_PTR(err);
}
/**
* v9fs_vfs_create - VFS hook to create a regular file
*
* open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called
* for mknod(2).
*
* @dir: directory inode that is being created
* @dentry: dentry that is being deleted
* @mode: create permissions
*
*/
static int
v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool excl)
{
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
u32 perm = unixmode2p9mode(v9ses, mode);
struct p9_fid *fid;
/* P9_OEXCL? */
fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR);
if (IS_ERR(fid))
return PTR_ERR(fid);
v9fs_invalidate_inode_attr(dir);
p9_client_clunk(fid);
return 0;
}
/**
* v9fs_vfs_mkdir - VFS mkdir hook to create a directory
* @dir: inode that is being unlinked
* @dentry: dentry that is being unlinked
* @mode: mode for new directory
*
*/
static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int err;
u32 perm;
struct p9_fid *fid;
struct v9fs_session_info *v9ses;
p9_debug(P9_DEBUG_VFS, "name %pd\n", dentry);
err = 0;
v9ses = v9fs_inode2v9ses(dir);
perm = unixmode2p9mode(v9ses, mode | S_IFDIR);
fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_OREAD);
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
fid = NULL;
} else {
inc_nlink(dir);
v9fs_invalidate_inode_attr(dir);
}
if (fid)
p9_client_clunk(fid);
return err;
}
/**
* v9fs_vfs_lookup - VFS lookup hook to "walk" to a new inode
* @dir: inode that is being walked from
* @dentry: dentry that is being walked to?
* @flags: lookup flags (unused)
*
*/
struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct dentry *res;
struct v9fs_session_info *v9ses;
struct p9_fid *dfid, *fid;
struct inode *inode;
const unsigned char *name;
p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n",
dir, dentry, dentry, flags);
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
v9ses = v9fs_inode2v9ses(dir);
/* We can walk d_parent because we hold the dir->i_mutex */
dfid = v9fs_parent_fid(dentry);
if (IS_ERR(dfid))
return ERR_CAST(dfid);
/*
* Make sure we don't use a wrong inode due to parallel
* unlink. For cached mode create calls request for new
* inode. But with cache disabled, lookup should do this.
*/
name = dentry->d_name.name;
fid = p9_client_walk(dfid, 1, &name, 1);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(dfid);
if (fid == ERR_PTR(-ENOENT))
inode = NULL;
else if (IS_ERR(fid))
inode = ERR_CAST(fid);
else if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
else
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
/*
* If we had a rename on the server and a parallel lookup
* for the new name, then make sure we instantiate with
* the new name. ie look up for a/b, while on server somebody
* moved b under k and client parallely did a lookup for
* k/b.
*/
res = d_splice_alias(inode, dentry);
if (!IS_ERR(fid)) {
if (!res)
v9fs_fid_add(dentry, fid);
else if (!IS_ERR(res))
v9fs_fid_add(res, fid);
else
p9_client_clunk(fid);
}
return res;
}
static int
v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned flags, umode_t mode)
{
int err;
u32 perm;
struct v9fs_inode *v9inode;
struct v9fs_session_info *v9ses;
struct p9_fid *fid, *inode_fid;
struct dentry *res = NULL;
struct inode *inode;
if (d_in_lookup(dentry)) {
res = v9fs_vfs_lookup(dir, dentry, 0);
if (IS_ERR(res))
return PTR_ERR(res);
if (res)
dentry = res;
}
/* Only creates */
if (!(flags & O_CREAT) || d_really_is_positive(dentry))
return finish_no_open(file, res);
err = 0;
v9ses = v9fs_inode2v9ses(dir);
perm = unixmode2p9mode(v9ses, mode);
fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
v9fs_uflags2omode(flags,
v9fs_proto_dotu(v9ses)));
if (IS_ERR(fid)) {
err = PTR_ERR(fid);
fid = NULL;
goto error;
}
v9fs_invalidate_inode_attr(dir);
inode = d_inode(dentry);
v9inode = V9FS_I(inode);
mutex_lock(&v9inode->v_mutex);
if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) &&
!v9inode->writeback_fid &&
((flags & O_ACCMODE) != O_RDONLY)) {
/*
* clone a fid and add it to writeback_fid
* we do it during open time instead of
* page dirty time via write_begin/page_mkwrite
* because we want write after unlink usecase
* to work.
*/
inode_fid = v9fs_writeback_fid(dentry);
if (IS_ERR(inode_fid)) {
err = PTR_ERR(inode_fid);
mutex_unlock(&v9inode->v_mutex);
goto error;
}
v9inode->writeback_fid = (void *) inode_fid;
}
mutex_unlock(&v9inode->v_mutex);
err = finish_open(file, dentry, generic_file_open);
if (err)
goto error;
file->private_data = fid;
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
v9fs_cache_inode_set_cookie(d_inode(dentry), file);
v9fs_open_fid_add(inode, fid);
file->f_mode |= FMODE_CREATED;
out:
dput(res);
return err;
error:
if (fid)
p9_client_clunk(fid);
goto out;
}
/**
* v9fs_vfs_unlink - VFS unlink hook to delete an inode
* @i: inode that is being unlinked
* @d: dentry that is being unlinked
*
*/
int v9fs_vfs_unlink(struct inode *i, struct dentry *d)
{
return v9fs_remove(i, d, 0);
}
/**
* v9fs_vfs_rmdir - VFS unlink hook to delete a directory
* @i: inode that is being unlinked
* @d: dentry that is being unlinked
*
*/
int v9fs_vfs_rmdir(struct inode *i, struct dentry *d)
{
return v9fs_remove(i, d, AT_REMOVEDIR);
}
/**
* v9fs_vfs_rename - VFS hook to rename an inode
* @old_dir: old dir inode
* @old_dentry: old dentry
* @new_dir: new dir inode
* @new_dentry: new dentry
*
*/
int
v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
int retval;
struct inode *old_inode;
struct inode *new_inode;
struct v9fs_session_info *v9ses;
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
struct p9_fid *oldfid, *dfid;
struct p9_fid *olddirfid;
struct p9_fid *newdirfid;
struct p9_wstat wstat;
if (flags)
return -EINVAL;
p9_debug(P9_DEBUG_VFS, "\n");
retval = 0;
old_inode = d_inode(old_dentry);
new_inode = d_inode(new_dentry);
v9ses = v9fs_inode2v9ses(old_inode);
oldfid = v9fs_fid_lookup(old_dentry);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
if (IS_ERR(oldfid))
return PTR_ERR(oldfid);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
dfid = v9fs_parent_fid(old_dentry);
olddirfid = clone_fid(dfid);
if (dfid && !IS_ERR(dfid))
p9_client_clunk(dfid);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
if (IS_ERR(olddirfid)) {
retval = PTR_ERR(olddirfid);
goto done;
}
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
dfid = v9fs_parent_fid(new_dentry);
newdirfid = clone_fid(dfid);
p9_client_clunk(dfid);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
if (IS_ERR(newdirfid)) {
retval = PTR_ERR(newdirfid);
goto clunk_olddir;
}
down_write(&v9ses->rename_sem);
if (v9fs_proto_dotl(v9ses)) {
retval = p9_client_renameat(olddirfid, old_dentry->d_name.name,
newdirfid, new_dentry->d_name.name);
if (retval == -EOPNOTSUPP)
retval = p9_client_rename(oldfid, newdirfid,
new_dentry->d_name.name);
if (retval != -EOPNOTSUPP)
goto clunk_newdir;
}
if (old_dentry->d_parent != new_dentry->d_parent) {
/*
* 9P .u can only handle file rename in the same directory
*/
p9_debug(P9_DEBUG_ERROR, "old dir and new dir are different\n");
retval = -EXDEV;
goto clunk_newdir;
}
v9fs_blank_wstat(&wstat);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
wstat.muid = v9ses->uname;
wstat.name = new_dentry->d_name.name;
retval = p9_client_wstat(oldfid, &wstat);
clunk_newdir:
if (!retval) {
if (new_inode) {
if (S_ISDIR(new_inode->i_mode))
clear_nlink(new_inode);
else
9p: don't maintain dir i_nlink if the exported fs doesn't either If the exported filesystem dir on 9p server doesn't maintain accurate i_nlink count, e.g. always reports i_nlink as 1, then 9p should not maintain nlink count either, otherwise drop_link would report warning with i_nlink being zero. For example: - overlayfs sets nlink to 1 for merged dir - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more than EXT4_LINK_MAX (65000) links. In this case, everytime a stat(2) call (getattr) on such exported dirs on 9p client side, the i_nlink gets reset to 1, then operations like rmdir(2), unlink(2) and rename(2) would cause the dir nlink to go to zero (then negative), which results in warnings in drop_nlink() and/or inc_nlink() calls. This can be reproduced easily as the following steps: - export a merged overlayfs dir via qemu virtfs to guest - mount the exported virtfs in guest - create two sub-directories in the root dir of the mounted 9pfs - stat the root dir of 9pfs, this resets nlink to 1 - remove all subdirs, the second unlink/rmdir would trigger warning ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1284 at fs/inode.c:282 drop_nlink+0x3e/0x50 ... Call Trace: dump_stack+0x63/0x81 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 drop_nlink+0x3e/0x50 v9fs_remove+0xaa/0x130 [9p] v9fs_vfs_rmdir+0x13/0x20 [9p] vfs_rmdir+0xb7/0x130 do_rmdir+0x1b8/0x230 SyS_unlinkat+0x22/0x30 do_syscall_64+0x67/0x180 ---[ end trace 43758d8ba91e603b ]--- Fix it by leaving i_nlink to be 1 and don't drop nlink if a directory has nlink <= 2, which indicates that the underlying exported fs doesn't maintain nlink count accurately. This follows what ext4 does in ext4_dec_count(). Link: http://lkml.kernel.org/r/20180312053829.4367-1-eguan@linux.alibaba.com Signed-off-by: Eryu Guan <eguan@linux.alibaba.com> Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com> Tested-by: Roman Kapl <code@rkapl.cz> Cc: Caspar Zhang <caspar@linux.alibaba.com> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Cc: <v9fs-developer@lists.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-06 02:19:49 +03:00
v9fs_dec_count(new_inode);
}
if (S_ISDIR(old_inode->i_mode)) {
if (!new_inode)
inc_nlink(new_dir);
9p: don't maintain dir i_nlink if the exported fs doesn't either If the exported filesystem dir on 9p server doesn't maintain accurate i_nlink count, e.g. always reports i_nlink as 1, then 9p should not maintain nlink count either, otherwise drop_link would report warning with i_nlink being zero. For example: - overlayfs sets nlink to 1 for merged dir - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more than EXT4_LINK_MAX (65000) links. In this case, everytime a stat(2) call (getattr) on such exported dirs on 9p client side, the i_nlink gets reset to 1, then operations like rmdir(2), unlink(2) and rename(2) would cause the dir nlink to go to zero (then negative), which results in warnings in drop_nlink() and/or inc_nlink() calls. This can be reproduced easily as the following steps: - export a merged overlayfs dir via qemu virtfs to guest - mount the exported virtfs in guest - create two sub-directories in the root dir of the mounted 9pfs - stat the root dir of 9pfs, this resets nlink to 1 - remove all subdirs, the second unlink/rmdir would trigger warning ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1284 at fs/inode.c:282 drop_nlink+0x3e/0x50 ... Call Trace: dump_stack+0x63/0x81 __warn+0xcb/0xf0 warn_slowpath_null+0x1d/0x20 drop_nlink+0x3e/0x50 v9fs_remove+0xaa/0x130 [9p] v9fs_vfs_rmdir+0x13/0x20 [9p] vfs_rmdir+0xb7/0x130 do_rmdir+0x1b8/0x230 SyS_unlinkat+0x22/0x30 do_syscall_64+0x67/0x180 ---[ end trace 43758d8ba91e603b ]--- Fix it by leaving i_nlink to be 1 and don't drop nlink if a directory has nlink <= 2, which indicates that the underlying exported fs doesn't maintain nlink count accurately. This follows what ext4 does in ext4_dec_count(). Link: http://lkml.kernel.org/r/20180312053829.4367-1-eguan@linux.alibaba.com Signed-off-by: Eryu Guan <eguan@linux.alibaba.com> Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com> Tested-by: Roman Kapl <code@rkapl.cz> Cc: Caspar Zhang <caspar@linux.alibaba.com> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Cc: <v9fs-developer@lists.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-04-06 02:19:49 +03:00
v9fs_dec_count(old_dir);
}
v9fs_invalidate_inode_attr(old_inode);
v9fs_invalidate_inode_attr(old_dir);
v9fs_invalidate_inode_attr(new_dir);
/* successful rename */
d_move(old_dentry, new_dentry);
}
up_write(&v9ses->rename_sem);
p9_client_clunk(newdirfid);
clunk_olddir:
p9_client_clunk(olddirfid);
done:
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(oldfid);
return retval;
}
/**
* v9fs_vfs_getattr - retrieve file metadata
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 19:46:22 +03:00
* @path: Object to query
* @stat: metadata structure to populate
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 19:46:22 +03:00
* @request_mask: Mask of STATX_xxx flags indicating the caller's interests
* @flags: AT_STATX_xxx setting
*
*/
static int
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 19:46:22 +03:00
v9fs_vfs_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-01-31 19:46:22 +03:00
struct dentry *dentry = path->dentry;
struct v9fs_session_info *v9ses;
struct p9_fid *fid;
struct p9_wstat *st;
p9_debug(P9_DEBUG_VFS, "dentry: %p\n", dentry);
v9ses = v9fs_dentry2v9ses(dentry);
if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
generic_fillattr(d_inode(dentry), stat);
return 0;
}
fid = v9fs_fid_lookup(dentry);
if (IS_ERR(fid))
return PTR_ERR(fid);
st = p9_client_stat(fid);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(fid);
if (IS_ERR(st))
return PTR_ERR(st);
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0);
generic_fillattr(d_inode(dentry), stat);
p9stat_free(st);
kfree(st);
return 0;
}
/**
* v9fs_vfs_setattr - set file metadata
* @dentry: file whose metadata to set
* @iattr: metadata assignment structure
*
*/
static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
int retval, use_dentry = 0;
struct v9fs_session_info *v9ses;
struct p9_fid *fid = NULL;
struct p9_wstat wstat;
p9_debug(P9_DEBUG_VFS, "\n");
retval = setattr_prepare(dentry, iattr);
if (retval)
return retval;
retval = -EPERM;
v9ses = v9fs_dentry2v9ses(dentry);
if (iattr->ia_valid & ATTR_FILE) {
fid = iattr->ia_file->private_data;
WARN_ON(!fid);
}
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
if (!fid) {
fid = v9fs_fid_lookup(dentry);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
use_dentry = 1;
}
if(IS_ERR(fid))
return PTR_ERR(fid);
v9fs_blank_wstat(&wstat);
if (iattr->ia_valid & ATTR_MODE)
wstat.mode = unixmode2p9mode(v9ses, iattr->ia_mode);
if (iattr->ia_valid & ATTR_MTIME)
wstat.mtime = iattr->ia_mtime.tv_sec;
if (iattr->ia_valid & ATTR_ATIME)
wstat.atime = iattr->ia_atime.tv_sec;
if (iattr->ia_valid & ATTR_SIZE)
wstat.length = iattr->ia_size;
if (v9fs_proto_dotu(v9ses)) {
if (iattr->ia_valid & ATTR_UID)
wstat.n_uid = iattr->ia_uid;
if (iattr->ia_valid & ATTR_GID)
wstat.n_gid = iattr->ia_gid;
}
/* Write all dirty data */
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 15:02:35 +03:00
if (d_is_reg(dentry))
filemap_write_and_wait(d_inode(dentry)->i_mapping);
retval = p9_client_wstat(fid, &wstat);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
if (use_dentry)
p9_client_clunk(fid);
if (retval < 0)
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);
v9fs_invalidate_inode_attr(d_inode(dentry));
setattr_copy(d_inode(dentry), iattr);
mark_inode_dirty(d_inode(dentry));
return 0;
}
/**
* v9fs_stat2inode - populate an inode structure with mistat info
* @stat: Plan 9 metadata (mistat) structure
* @inode: inode to populate
* @sb: superblock of filesystem
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
* @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE)
*
*/
void
v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
struct super_block *sb, unsigned int flags)
{
umode_t mode;
char ext[32];
char tag_name[14];
unsigned int i_nlink;
struct v9fs_session_info *v9ses = sb->s_fs_info;
struct v9fs_inode *v9inode = V9FS_I(inode);
set_nlink(inode, 1);
inode->i_atime.tv_sec = stat->atime;
inode->i_mtime.tv_sec = stat->mtime;
inode->i_ctime.tv_sec = stat->mtime;
inode->i_uid = v9ses->dfltuid;
inode->i_gid = v9ses->dfltgid;
if (v9fs_proto_dotu(v9ses)) {
inode->i_uid = stat->n_uid;
inode->i_gid = stat->n_gid;
}
if ((S_ISREG(inode->i_mode)) || (S_ISDIR(inode->i_mode))) {
if (v9fs_proto_dotu(v9ses) && (stat->extension[0] != '\0')) {
/*
* Hadlink support got added later to
* to the .u extension. So there can be
* server out there that doesn't support
* this even with .u extension. So check
* for non NULL stat->extension
*/
strlcpy(ext, stat->extension, sizeof(ext));
/* HARDLINKCOUNT %u */
sscanf(ext, "%13s %u", tag_name, &i_nlink);
if (!strncmp(tag_name, "HARDLINKCOUNT", 13))
set_nlink(inode, i_nlink);
}
}
mode = p9mode2perm(v9ses, stat);
mode |= inode->i_mode & ~S_IALLUGO;
inode->i_mode = mode;
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE))
v9fs_i_size_write(inode, stat->length);
/* not real number of blocks, but 512 byte ones ... */
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
inode->i_blocks = (stat->length + 512 - 1) >> 9;
v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR;
}
/**
* v9fs_qid2ino - convert qid into inode number
* @qid: qid to hash
*
* BUG: potential for inode number collisions?
*/
ino_t v9fs_qid2ino(struct p9_qid *qid)
{
u64 path = qid->path + 2;
ino_t i = 0;
if (sizeof(ino_t) == sizeof(path))
memcpy(&i, &path, sizeof(ino_t));
else
i = (ino_t) (path ^ (path >> 32));
return i;
}
/**
* v9fs_vfs_get_link - follow a symlink path
* @dentry: dentry for symlink
* @inode: inode for symlink
* @done: delayed call for when we are done with the return value
*/
static const char *v9fs_vfs_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
struct v9fs_session_info *v9ses;
struct p9_fid *fid;
struct p9_wstat *st;
char *res;
if (!dentry)
return ERR_PTR(-ECHILD);
v9ses = v9fs_dentry2v9ses(dentry);
fid = v9fs_fid_lookup(dentry);
p9_debug(P9_DEBUG_VFS, "%pd\n", dentry);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
if (IS_ERR(fid))
return ERR_CAST(fid);
if (!v9fs_proto_dotu(v9ses))
return ERR_PTR(-EBADF);
st = p9_client_stat(fid);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 17:11:46 +03:00
p9_client_clunk(fid);
if (IS_ERR(st))
return ERR_CAST(st);
if (!(st->mode & P9_DMSYMLINK)) {
p9stat_free(st);
kfree(st);
return ERR_PTR(-EINVAL);
}
res = st->extension;
st->extension = NULL;
if (strlen(res) >= PATH_MAX)
res[PATH_MAX - 1] = '\0';
p9stat_free(st);
kfree(st);
set_delayed_call(done, kfree_link, res);
return res;
}
/**
* v9fs_vfs_mkspecial - create a special file
* @dir: inode to create special file in
* @dentry: dentry to create
* @perm: mode to create special file
* @extension: 9p2000.u format extension string representing special file
*
*/
static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry,
u32 perm, const char *extension)
{
struct p9_fid *fid;
struct v9fs_session_info *v9ses;
v9ses = v9fs_inode2v9ses(dir);
if (!v9fs_proto_dotu(v9ses)) {
p9_debug(P9_DEBUG_ERROR, "not extended\n");
return -EPERM;
}
fid = v9fs_create(v9ses, dir, dentry, (char *) extension, perm,
P9_OREAD);
if (IS_ERR(fid))
return PTR_ERR(fid);
v9fs_invalidate_inode_attr(dir);
p9_client_clunk(fid);
return 0;
}
/**
* v9fs_vfs_symlink - helper function to create symlinks
* @dir: directory inode containing symlink
* @dentry: dentry for symlink
* @symname: symlink data
*
* See Also: 9P2000.u RFC for more information
*
*/
static int
v9fs_vfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
{
p9_debug(P9_DEBUG_VFS, " %lu,%pd,%s\n",
dir->i_ino, dentry, symname);
return v9fs_vfs_mkspecial(dir, dentry, P9_DMSYMLINK, symname);
}
#define U32_MAX_DIGITS 10
/**
* v9fs_vfs_link - create a hardlink
* @old_dentry: dentry for file to link to
* @dir: inode destination for new link
* @dentry: dentry for link
*
*/
static int
v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
int retval;
char name[1 + U32_MAX_DIGITS + 2]; /* sign + number + \n + \0 */
struct p9_fid *oldfid;
p9_debug(P9_DEBUG_VFS, " %lu,%pd,%pd\n",
dir->i_ino, dentry, old_dentry);
oldfid = v9fs_fid_clone(old_dentry);
9p: attach-per-user The 9P2000 protocol requires the authentication and permission checks to be done in the file server. For that reason every user that accesses the file server tree has to authenticate and attach to the server separately. Multiple users can share the same connection to the server. Currently v9fs does a single attach and executes all I/O operations as a single user. This makes using v9fs in multiuser environment unsafe as it depends on the client doing the permission checking. This patch improves the 9P2000 support by allowing every user to attach separately. The patch defines three modes of access (new mount option 'access'): - attach-per-user (access=user) (default mode for 9P2000.u) If a user tries to access a file served by v9fs for the first time, v9fs sends an attach command to the server (Tattach) specifying the user. If the attach succeeds, the user can access the v9fs tree. As there is no uname->uid (string->integer) mapping yet, this mode works only with the 9P2000.u dialect. - allow only one user to access the tree (access=<uid>) Only the user with uid can access the v9fs tree. Other users that attempt to access it will get EPERM error. - do all operations as a single user (access=any) (default for 9P2000) V9fs does a single attach and all operations are done as a single user. If this mode is selected, the v9fs behavior is identical with the current one. Signed-off-by: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
2007-10-17 23:31:07 +04:00
if (IS_ERR(oldfid))
return PTR_ERR(oldfid);
sprintf(name, "%d\n", oldfid->fid);
retval = v9fs_vfs_mkspecial(dir, dentry, P9_DMLINK, name);
if (!retval) {
v9fs_refresh_inode(oldfid, d_inode(old_dentry));
v9fs_invalidate_inode_attr(dir);
}
p9_client_clunk(oldfid);
return retval;
}
/**
* v9fs_vfs_mknod - create a special file
* @dir: inode destination for new link
* @dentry: dentry for file
* @mode: mode for creation
* @rdev: device associated with special file
*
*/
static int
v9fs_vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
int retval;
char name[2 + U32_MAX_DIGITS + 1 + U32_MAX_DIGITS + 1];
u32 perm;
p9_debug(P9_DEBUG_VFS, " %lu,%pd mode: %hx MAJOR: %u MINOR: %u\n",
dir->i_ino, dentry, mode,
MAJOR(rdev), MINOR(rdev));
/* build extension */
if (S_ISBLK(mode))
sprintf(name, "b %u %u", MAJOR(rdev), MINOR(rdev));
else if (S_ISCHR(mode))
sprintf(name, "c %u %u", MAJOR(rdev), MINOR(rdev));
else
*name = 0;
perm = unixmode2p9mode(v9ses, mode);
retval = v9fs_vfs_mkspecial(dir, dentry, perm, name);
return retval;
}
int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
{
int umode;
dev_t rdev;
struct p9_wstat *st;
struct v9fs_session_info *v9ses;
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
unsigned int flags;
v9ses = v9fs_inode2v9ses(inode);
st = p9_client_stat(fid);
if (IS_ERR(st))
return PTR_ERR(st);
/*
* Don't update inode if the file type is different
*/
umode = p9mode2unixmode(v9ses, st, &rdev);
if ((inode->i_mode & S_IFMT) != (umode & S_IFMT))
goto out;
/*
* We don't want to refresh inode->i_size,
* because we may have cached data
*/
9p: use inode->i_lock to protect i_size_write() under 32-bit Use inode->i_lock to protect i_size_write(), else i_size_read() in generic_fillattr() may loop infinitely in read_seqcount_begin() when multiple processes invoke v9fs_vfs_getattr() or v9fs_vfs_getattr_dotl() simultaneously under 32-bit SMP environment, and a soft lockup will be triggered as show below: watchdog: BUG: soft lockup - CPU#5 stuck for 22s! [stat:2217] Modules linked in: CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system PC is at generic_fillattr+0x104/0x108 LR is at 0xec497f00 pc : [<802b8898>] lr : [<ec497f00>] psr: 200c0013 sp : ec497e20 ip : ed608030 fp : ec497e3c r10: 00000000 r9 : ec497f00 r8 : ed608030 r7 : ec497ebc r6 : ec497f00 r5 : ee5c1550 r4 : ee005780 r3 : 0000052d r2 : 00000000 r1 : ec497f00 r0 : ed608030 Flags: nzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 10c5387d Table: ac48006a DAC: 00000051 CPU: 5 PID: 2217 Comm: stat Not tainted 5.0.0-rc1-00005-g7f702faf5a9e #4 Hardware name: Generic DT based system Backtrace: [<8010d974>] (dump_backtrace) from [<8010dc88>] (show_stack+0x20/0x24) [<8010dc68>] (show_stack) from [<80a1d194>] (dump_stack+0xb0/0xdc) [<80a1d0e4>] (dump_stack) from [<80109f34>] (show_regs+0x1c/0x20) [<80109f18>] (show_regs) from [<801d0a80>] (watchdog_timer_fn+0x280/0x2f8) [<801d0800>] (watchdog_timer_fn) from [<80198658>] (__hrtimer_run_queues+0x18c/0x380) [<801984cc>] (__hrtimer_run_queues) from [<80198e60>] (hrtimer_run_queues+0xb8/0xf0) [<80198da8>] (hrtimer_run_queues) from [<801973e8>] (run_local_timers+0x28/0x64) [<801973c0>] (run_local_timers) from [<80197460>] (update_process_times+0x3c/0x6c) [<80197424>] (update_process_times) from [<801ab2b8>] (tick_nohz_handler+0xe0/0x1bc) [<801ab1d8>] (tick_nohz_handler) from [<80843050>] (arch_timer_handler_virt+0x38/0x48) [<80843018>] (arch_timer_handler_virt) from [<80180a64>] (handle_percpu_devid_irq+0x8c/0x240) [<801809d8>] (handle_percpu_devid_irq) from [<8017ac20>] (generic_handle_irq+0x34/0x44) [<8017abec>] (generic_handle_irq) from [<8017b344>] (__handle_domain_irq+0x6c/0xc4) [<8017b2d8>] (__handle_domain_irq) from [<801022e0>] (gic_handle_irq+0x4c/0x88) [<80102294>] (gic_handle_irq) from [<80101a30>] (__irq_svc+0x70/0x98) [<802b8794>] (generic_fillattr) from [<8056b284>] (v9fs_vfs_getattr_dotl+0x74/0xa4) [<8056b210>] (v9fs_vfs_getattr_dotl) from [<802b8904>] (vfs_getattr_nosec+0x68/0x7c) [<802b889c>] (vfs_getattr_nosec) from [<802b895c>] (vfs_getattr+0x44/0x48) [<802b8918>] (vfs_getattr) from [<802b8a74>] (vfs_statx+0x9c/0xec) [<802b89d8>] (vfs_statx) from [<802b9428>] (sys_lstat64+0x48/0x78) [<802b93e0>] (sys_lstat64) from [<80101000>] (ret_fast_syscall+0x0/0x28) [dominique.martinet@cea.fr: updated comment to not refer to a function in another subsystem] Link: http://lkml.kernel.org/r/20190124063514.8571-2-houtao1@huawei.com Cc: stable@vger.kernel.org Fixes: 7549ae3e81cc ("9p: Use the i_size_[read, write]() macros instead of using inode->i_size directly.") Reported-by: Xing Gaopeng <xingaopeng@huawei.com> Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
2019-01-24 09:35:13 +03:00
flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ?
V9FS_STAT2INODE_KEEP_ISIZE : 0;
v9fs_stat2inode(st, inode, inode->i_sb, flags);
out:
p9stat_free(st);
kfree(st);
return 0;
}
static const struct inode_operations v9fs_dir_inode_operations_dotu = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
.atomic_open = v9fs_vfs_atomic_open,
.symlink = v9fs_vfs_symlink,
.link = v9fs_vfs_link,
.unlink = v9fs_vfs_unlink,
.mkdir = v9fs_vfs_mkdir,
.rmdir = v9fs_vfs_rmdir,
.mknod = v9fs_vfs_mknod,
.rename = v9fs_vfs_rename,
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};
static const struct inode_operations v9fs_dir_inode_operations = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
.atomic_open = v9fs_vfs_atomic_open,
.unlink = v9fs_vfs_unlink,
.mkdir = v9fs_vfs_mkdir,
.rmdir = v9fs_vfs_rmdir,
.mknod = v9fs_vfs_mknod,
.rename = v9fs_vfs_rename,
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};
static const struct inode_operations v9fs_file_inode_operations = {
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};
static const struct inode_operations v9fs_symlink_inode_operations = {
.get_link = v9fs_vfs_get_link,
.getattr = v9fs_vfs_getattr,
.setattr = v9fs_vfs_setattr,
};