WSL2-Linux-Kernel/fs/cifs/inode.c

2508 строки
65 KiB
C
Исходник Обычный вид История

/*
* fs/cifs/inode.c
*
* Copyright (C) International Business Machines Corp., 2002,2010
* Author(s): Steve French (sfrench@us.ibm.com)
*
* This library is free software; you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published
* by the Free Software Foundation; either version 2.1 of the License, or
* (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See
* the GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/fs.h>
#include <linux/stat.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/pagemap.h>
#include <linux/freezer.h>
#include <linux/sched/signal.h>
#include <linux/wait_bit.h>
#include <asm/div64.h>
#include "cifsfs.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
#include "cifs_unicode.h"
#include "fscache.h"
static void cifs_set_ops(struct inode *inode)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &cifs_file_inode_ops;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
inode->i_fop = &cifs_file_direct_nobrl_ops;
else
inode->i_fop = &cifs_file_direct_ops;
} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
inode->i_fop = &cifs_file_strict_nobrl_ops;
else
inode->i_fop = &cifs_file_strict_ops;
} else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL)
inode->i_fop = &cifs_file_nobrl_ops;
else { /* not direct, send byte range locks */
inode->i_fop = &cifs_file_ops;
}
/* check if server can support readpages */
if (cifs_sb_master_tcon(cifs_sb)->ses->server->maxBuf <
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
PAGE_SIZE + MAX_CIFS_HDR_SIZE)
inode->i_data.a_ops = &cifs_addr_ops_smallbuf;
else
inode->i_data.a_ops = &cifs_addr_ops;
break;
case S_IFDIR:
#ifdef CONFIG_CIFS_DFS_UPCALL
if (IS_AUTOMOUNT(inode)) {
inode->i_op = &cifs_dfs_referral_inode_operations;
} else {
#else /* NO DFS support, treat as a directory */
{
#endif
inode->i_op = &cifs_dir_inode_ops;
inode->i_fop = &cifs_dir_ops;
}
break;
case S_IFLNK:
inode->i_op = &cifs_symlink_inode_ops;
break;
default:
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
}
/* check inode attributes against fattr. If they don't match, tag the
* inode for cache invalidation
*/
static void
cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
cifs_dbg(FYI, "%s: revalidating inode %llu\n",
__func__, cifs_i->uniqueid);
if (inode->i_state & I_NEW) {
cifs_dbg(FYI, "%s: inode %llu is new\n",
__func__, cifs_i->uniqueid);
return;
}
/* don't bother with revalidation if we have an oplock */
if (CIFS_CACHE_READ(cifs_i)) {
cifs_dbg(FYI, "%s: inode %llu is oplocked\n",
__func__, cifs_i->uniqueid);
return;
}
/* revalidate if mtime or size have changed */
if (timespec_equal(&inode->i_mtime, &fattr->cf_mtime) &&
cifs_i->server_eof == fattr->cf_eof) {
cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
__func__, cifs_i->uniqueid);
return;
}
cifs_dbg(FYI, "%s: invalidating inode %llu mapping\n",
__func__, cifs_i->uniqueid);
set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
}
/*
* copy nlink to the inode, unless it wasn't provided. Provide
* sane values if we don't have an existing one and none was provided
*/
static void
cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
{
/*
* if we're in a situation where we can't trust what we
* got from the server (readdir, some non-unix cases)
* fake reasonable values
*/
if (fattr->cf_flags & CIFS_FATTR_UNKNOWN_NLINK) {
/* only provide fake values on a new inode */
if (inode->i_state & I_NEW) {
if (fattr->cf_cifsattrs & ATTR_DIRECTORY)
set_nlink(inode, 2);
else
set_nlink(inode, 1);
}
return;
}
/* we trust the server, so update it */
set_nlink(inode, fattr->cf_nlink);
}
/* populate an inode with info from a cifs_fattr struct */
void
cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
cifs_revalidate_cache(inode, fattr);
spin_lock(&inode->i_lock);
inode->i_atime = fattr->cf_atime;
inode->i_mtime = fattr->cf_mtime;
inode->i_ctime = fattr->cf_ctime;
inode->i_rdev = fattr->cf_rdev;
cifs_nlink_fattr_to_inode(inode, fattr);
inode->i_uid = fattr->cf_uid;
inode->i_gid = fattr->cf_gid;
/* if dynperm is set, don't clobber existing mode */
if (inode->i_state & I_NEW ||
!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM))
inode->i_mode = fattr->cf_mode;
cifs_i->cifsAttrs = fattr->cf_cifsattrs;
if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
cifs_i->time = 0;
else
cifs_i->time = jiffies;
if (fattr->cf_flags & CIFS_FATTR_DELETE_PENDING)
set_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
else
clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags);
cifs_i->server_eof = fattr->cf_eof;
/*
* Can't safely change the file size here if the client is writing to
* it due to potential races.
*/
if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) {
i_size_write(inode, fattr->cf_eof);
/*
* i_blocks is not related to (i_size / i_blksize),
* but instead 512 byte (2**9) size is required for
* calculating num blocks.
*/
inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9;
}
spin_unlock(&inode->i_lock);
if (fattr->cf_flags & CIFS_FATTR_DFS_REFERRAL)
inode->i_flags |= S_AUTOMOUNT;
if (inode->i_state & I_NEW)
cifs_set_ops(inode);
}
void
cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)
return;
fattr->cf_uniqueid = iunique(sb, ROOT_I);
}
/* Fill a cifs_fattr struct with info from FILE_UNIX_BASIC_INFO. */
void
cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info,
struct cifs_sb_info *cifs_sb)
{
memset(fattr, 0, sizeof(*fattr));
fattr->cf_uniqueid = le64_to_cpu(info->UniqueId);
fattr->cf_bytes = le64_to_cpu(info->NumOfBytes);
fattr->cf_eof = le64_to_cpu(info->EndOfFile);
fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
fattr->cf_mtime = cifs_NTtimeToUnix(info->LastModificationTime);
fattr->cf_ctime = cifs_NTtimeToUnix(info->LastStatusChange);
/* old POSIX extensions don't get create time */
fattr->cf_mode = le64_to_cpu(info->Permissions);
/*
* Since we set the inode type below we need to mask off
* to avoid strange results if bits set above.
*/
fattr->cf_mode &= ~S_IFMT;
switch (le32_to_cpu(info->Type)) {
case UNIX_FILE:
fattr->cf_mode |= S_IFREG;
fattr->cf_dtype = DT_REG;
break;
case UNIX_SYMLINK:
fattr->cf_mode |= S_IFLNK;
fattr->cf_dtype = DT_LNK;
break;
case UNIX_DIR:
fattr->cf_mode |= S_IFDIR;
fattr->cf_dtype = DT_DIR;
break;
case UNIX_CHARDEV:
fattr->cf_mode |= S_IFCHR;
fattr->cf_dtype = DT_CHR;
fattr->cf_rdev = MKDEV(le64_to_cpu(info->DevMajor),
le64_to_cpu(info->DevMinor) & MINORMASK);
break;
case UNIX_BLOCKDEV:
fattr->cf_mode |= S_IFBLK;
fattr->cf_dtype = DT_BLK;
fattr->cf_rdev = MKDEV(le64_to_cpu(info->DevMajor),
le64_to_cpu(info->DevMinor) & MINORMASK);
break;
case UNIX_FIFO:
fattr->cf_mode |= S_IFIFO;
fattr->cf_dtype = DT_FIFO;
break;
case UNIX_SOCKET:
fattr->cf_mode |= S_IFSOCK;
fattr->cf_dtype = DT_SOCK;
break;
default:
/* safest to call it a file if we do not know */
fattr->cf_mode |= S_IFREG;
fattr->cf_dtype = DT_REG;
cifs_dbg(FYI, "unknown type %d\n", le32_to_cpu(info->Type));
break;
}
fattr->cf_uid = cifs_sb->mnt_uid;
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) {
u64 id = le64_to_cpu(info->Uid);
if (id < ((uid_t)-1)) {
kuid_t uid = make_kuid(&init_user_ns, id);
if (uid_valid(uid))
fattr->cf_uid = uid;
}
}
fattr->cf_gid = cifs_sb->mnt_gid;
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) {
u64 id = le64_to_cpu(info->Gid);
if (id < ((gid_t)-1)) {
kgid_t gid = make_kgid(&init_user_ns, id);
if (gid_valid(gid))
fattr->cf_gid = gid;
}
}
fattr->cf_nlink = le64_to_cpu(info->Nlinks);
}
/*
* Fill a cifs_fattr struct with fake inode info.
*
* Needed to setup cifs_fattr data for the directory which is the
* junction to the new submount (ie to setup the fake directory
* which represents a DFS referral).
*/
static void
cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
cifs_dbg(FYI, "creating fake fattr for DFS referral\n");
memset(fattr, 0, sizeof(*fattr));
fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
fattr->cf_uid = cifs_sb->mnt_uid;
fattr->cf_gid = cifs_sb->mnt_gid;
ktime_get_real_ts(&fattr->cf_mtime);
fattr->cf_mtime = timespec_trunc(fattr->cf_mtime, sb->s_time_gran);
fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime;
fattr->cf_nlink = 2;
fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL;
}
static int
cifs_get_file_info_unix(struct file *filp)
{
int rc;
unsigned int xid;
FILE_UNIX_BASIC_INFO find_data;
struct cifs_fattr fattr;
struct inode *inode = file_inode(filp);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsFileInfo *cfile = filp->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
xid = get_xid();
rc = CIFSSMBUnixQFileInfo(xid, tcon, cfile->fid.netfid, &find_data);
if (!rc) {
cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb);
} else if (rc == -EREMOTE) {
cifs_create_dfs_fattr(&fattr, inode->i_sb);
rc = 0;
}
cifs_fattr_to_inode(inode, &fattr);
free_xid(xid);
return rc;
}
int cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *full_path,
struct super_block *sb, unsigned int xid)
{
int rc;
FILE_UNIX_BASIC_INFO find_data;
struct cifs_fattr fattr;
struct cifs_tcon *tcon;
struct tcon_link *tlink;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
cifs_dbg(FYI, "Getting info on %s\n", full_path);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
/* could have done a find first instead but this returns more info */
rc = CIFSSMBUnixQPathInfo(xid, tcon, full_path, &find_data,
cifs_sb->local_nls, cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
if (!rc) {
cifs_unix_basic_to_fattr(&fattr, &find_data, cifs_sb);
} else if (rc == -EREMOTE) {
cifs_create_dfs_fattr(&fattr, sb);
rc = 0;
} else {
return rc;
}
/* check for Minshall+French symlinks */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
int tmprc = check_mf_symlink(xid, tcon, cifs_sb, &fattr,
full_path);
if (tmprc)
cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
}
if (*pinode == NULL) {
/* get new inode */
cifs_fill_uniqueid(sb, &fattr);
*pinode = cifs_iget(sb, &fattr);
if (!*pinode)
rc = -ENOMEM;
} else {
/* we already have inode, update it */
/* if uniqueid is different, return error */
if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) {
rc = -ESTALE;
goto cgiiu_exit;
}
/* if filetype is different, return error */
if (unlikely(((*pinode)->i_mode & S_IFMT) !=
(fattr.cf_mode & S_IFMT))) {
rc = -ESTALE;
goto cgiiu_exit;
}
cifs_fattr_to_inode(*pinode, &fattr);
}
cgiiu_exit:
return rc;
}
static int
cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
struct cifs_sb_info *cifs_sb, unsigned int xid)
{
int rc;
__u32 oplock;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct cifs_fid fid;
struct cifs_open_parms oparms;
struct cifs_io_parms io_parms;
char buf[24];
unsigned int bytes_read;
char *pbuf;
int buf_type = CIFS_NO_BUFFER;
pbuf = buf;
fattr->cf_mode &= ~S_IFMT;
if (fattr->cf_eof == 0) {
fattr->cf_mode |= S_IFIFO;
fattr->cf_dtype = DT_FIFO;
return 0;
} else if (fattr->cf_eof < 8) {
fattr->cf_mode |= S_IFREG;
fattr->cf_dtype = DT_REG;
return -EINVAL; /* EOPNOTSUPP? */
}
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = GENERIC_READ;
oparms.create_options = CREATE_NOT_DIR;
oparms.disposition = FILE_OPEN;
oparms.path = path;
oparms.fid = &fid;
oparms.reconnect = false;
if (tcon->ses->server->oplocks)
oplock = REQ_OPLOCK;
else
oplock = 0;
rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, NULL);
if (rc) {
cifs_dbg(FYI, "check sfu type of %s, open rc = %d\n", path, rc);
cifs_put_tlink(tlink);
return rc;
}
/* Read header */
io_parms.netfid = fid.netfid;
io_parms.pid = current->tgid;
io_parms.tcon = tcon;
io_parms.offset = 0;
io_parms.length = 24;
rc = tcon->ses->server->ops->sync_read(xid, &fid, &io_parms,
&bytes_read, &pbuf, &buf_type);
if ((rc == 0) && (bytes_read >= 8)) {
if (memcmp("IntxBLK", pbuf, 8) == 0) {
cifs_dbg(FYI, "Block device\n");
fattr->cf_mode |= S_IFBLK;
fattr->cf_dtype = DT_BLK;
if (bytes_read == 24) {
/* we have enough to decode dev num */
__u64 mjr; /* major */
__u64 mnr; /* minor */
mjr = le64_to_cpu(*(__le64 *)(pbuf+8));
mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
fattr->cf_rdev = MKDEV(mjr, mnr);
}
} else if (memcmp("IntxCHR", pbuf, 8) == 0) {
cifs_dbg(FYI, "Char device\n");
fattr->cf_mode |= S_IFCHR;
fattr->cf_dtype = DT_CHR;
if (bytes_read == 24) {
/* we have enough to decode dev num */
__u64 mjr; /* major */
__u64 mnr; /* minor */
mjr = le64_to_cpu(*(__le64 *)(pbuf+8));
mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
fattr->cf_rdev = MKDEV(mjr, mnr);
}
} else if (memcmp("IntxLNK", pbuf, 7) == 0) {
cifs_dbg(FYI, "Symlink\n");
fattr->cf_mode |= S_IFLNK;
fattr->cf_dtype = DT_LNK;
} else {
fattr->cf_mode |= S_IFREG; /* file? */
fattr->cf_dtype = DT_REG;
rc = -EOPNOTSUPP;
}
} else {
fattr->cf_mode |= S_IFREG; /* then it is a file */
fattr->cf_dtype = DT_REG;
rc = -EOPNOTSUPP; /* or some unknown SFU type */
}
tcon->ses->server->ops->close(xid, tcon, &fid);
cifs_put_tlink(tlink);
return rc;
}
#define SFBITS_MASK (S_ISVTX | S_ISGID | S_ISUID) /* SETFILEBITS valid bits */
/*
* Fetch mode bits as provided by SFU.
*
* FIXME: Doesn't this clobber the type bit we got from cifs_sfu_type ?
*/
static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
struct cifs_sb_info *cifs_sb, unsigned int xid)
{
#ifdef CONFIG_CIFS_XATTR
ssize_t rc;
char ea_value[4];
__u32 mode;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
if (tcon->ses->server->ops->query_all_EAs == NULL) {
cifs_put_tlink(tlink);
return -EOPNOTSUPP;
}
rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
"SETFILEBITS", ea_value, 4 /* size of buf */,
cifs_sb);
cifs_put_tlink(tlink);
if (rc < 0)
return (int)rc;
else if (rc > 3) {
mode = le32_to_cpu(*((__le32 *)ea_value));
fattr->cf_mode &= ~SFBITS_MASK;
cifs_dbg(FYI, "special bits 0%o org mode 0%o\n",
mode, fattr->cf_mode);
fattr->cf_mode = (mode & SFBITS_MASK) | fattr->cf_mode;
cifs_dbg(FYI, "special mode bits 0%o\n", mode);
}
return 0;
#else
return -EOPNOTSUPP;
#endif
}
/* Fill a cifs_fattr struct with info from FILE_ALL_INFO */
static void
cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
struct super_block *sb, bool adjust_tz,
bool symlink)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
memset(fattr, 0, sizeof(*fattr));
fattr->cf_cifsattrs = le32_to_cpu(info->Attributes);
if (info->DeletePending)
fattr->cf_flags |= CIFS_FATTR_DELETE_PENDING;
if (info->LastAccessTime)
fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
else {
ktime_get_real_ts(&fattr->cf_atime);
fattr->cf_atime = timespec_trunc(fattr->cf_atime, sb->s_time_gran);
}
fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime);
if (adjust_tz) {
fattr->cf_ctime.tv_sec += tcon->ses->server->timeAdj;
fattr->cf_mtime.tv_sec += tcon->ses->server->timeAdj;
}
fattr->cf_eof = le64_to_cpu(info->EndOfFile);
fattr->cf_bytes = le64_to_cpu(info->AllocationSize);
fattr->cf_createtime = le64_to_cpu(info->CreationTime);
fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
if (symlink) {
fattr->cf_mode = S_IFLNK;
fattr->cf_dtype = DT_LNK;
} else if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
fattr->cf_mode = S_IFDIR | cifs_sb->mnt_dir_mode;
fattr->cf_dtype = DT_DIR;
/*
* Server can return wrong NumberOfLinks value for directories
* when Unix extensions are disabled - fake it.
*/
if (!tcon->unix_ext)
fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
} else {
fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode;
fattr->cf_dtype = DT_REG;
/* clear write bits if ATTR_READONLY is set */
if (fattr->cf_cifsattrs & ATTR_READONLY)
fattr->cf_mode &= ~(S_IWUGO);
/*
* Don't accept zero nlink from non-unix servers unless
* delete is pending. Instead mark it as unknown.
*/
if ((fattr->cf_nlink < 1) && !tcon->unix_ext &&
!info->DeletePending) {
cifs_dbg(1, "bogus file nlink value %u\n",
fattr->cf_nlink);
fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK;
}
}
fattr->cf_uid = cifs_sb->mnt_uid;
fattr->cf_gid = cifs_sb->mnt_gid;
}
static int
cifs_get_file_info(struct file *filp)
{
int rc;
unsigned int xid;
FILE_ALL_INFO find_data;
struct cifs_fattr fattr;
struct inode *inode = file_inode(filp);
struct cifsFileInfo *cfile = filp->private_data;
struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
struct TCP_Server_Info *server = tcon->ses->server;
if (!server->ops->query_file_info)
return -ENOSYS;
xid = get_xid();
rc = server->ops->query_file_info(xid, tcon, &cfile->fid, &find_data);
switch (rc) {
case 0:
cifs_all_info_to_fattr(&fattr, &find_data, inode->i_sb, false,
false);
break;
case -EREMOTE:
cifs_create_dfs_fattr(&fattr, inode->i_sb);
rc = 0;
break;
case -EOPNOTSUPP:
case -EINVAL:
/*
* FIXME: legacy server -- fall back to path-based call?
* for now, just skip revalidating and mark inode for
* immediate reval.
*/
rc = 0;
CIFS_I(inode)->time = 0;
default:
goto cgfi_exit;
}
/*
* don't bother with SFU junk here -- just mark inode as needing
* revalidation.
*/
fattr.cf_uniqueid = CIFS_I(inode)->uniqueid;
fattr.cf_flags |= CIFS_FATTR_NEED_REVAL;
cifs_fattr_to_inode(inode, &fattr);
cgfi_exit:
free_xid(xid);
return rc;
}
/* Simple function to return a 64 bit hash of string. Rarely called */
static __u64 simple_hashstr(const char *str)
{
const __u64 hash_mult = 1125899906842597ULL; /* a big enough prime */
__u64 hash = 0;
while (*str)
hash = (hash + (__u64) *str++) * hash_mult;
return hash;
}
int
cifs_get_inode_info(struct inode **inode, const char *full_path,
FILE_ALL_INFO *data, struct super_block *sb, int xid,
2014-02-11 00:08:16 +04:00
const struct cifs_fid *fid)
{
bool validinum = false;
__u16 srchflgs;
int rc = 0, tmprc = ENOSYS;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct tcon_link *tlink;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
char *buf = NULL;
bool adjust_tz = false;
struct cifs_fattr fattr;
struct cifs_search_info *srchinf = NULL;
bool symlink = false;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
cifs_dbg(FYI, "Getting info on %s\n", full_path);
if ((data == NULL) && (*inode != NULL)) {
if (CIFS_CACHE_READ(CIFS_I(*inode))) {
cifs_dbg(FYI, "No need to revalidate cached inode sizes\n");
goto cgii_exit;
}
}
/* if inode info is not passed, get it from server */
if (data == NULL) {
if (!server->ops->query_path_info) {
rc = -ENOSYS;
goto cgii_exit;
}
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
rc = -ENOMEM;
goto cgii_exit;
}
data = (FILE_ALL_INFO *)buf;
rc = server->ops->query_path_info(xid, tcon, cifs_sb, full_path,
data, &adjust_tz, &symlink);
}
if (!rc) {
cifs_all_info_to_fattr(&fattr, data, sb, adjust_tz,
symlink);
} else if (rc == -EREMOTE) {
cifs_create_dfs_fattr(&fattr, sb);
rc = 0;
} else if (rc == -EACCES && backup_cred(cifs_sb)) {
srchinf = kzalloc(sizeof(struct cifs_search_info),
GFP_KERNEL);
if (srchinf == NULL) {
rc = -ENOMEM;
goto cgii_exit;
}
srchinf->endOfSearch = false;
srchinf->info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO;
srchflgs = CIFS_SEARCH_CLOSE_ALWAYS |
CIFS_SEARCH_CLOSE_AT_END |
CIFS_SEARCH_BACKUP_SEARCH;
rc = CIFSFindFirst(xid, tcon, full_path,
cifs_sb, NULL, srchflgs, srchinf, false);
if (!rc) {
data =
(FILE_ALL_INFO *)srchinf->srch_entries_start;
cifs_dir_info_to_fattr(&fattr,
(FILE_DIRECTORY_INFO *)data, cifs_sb);
fattr.cf_uniqueid = le64_to_cpu(
((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId);
validinum = true;
cifs_buf_release(srchinf->ntwrk_buf_start);
}
kfree(srchinf);
if (rc)
goto cgii_exit;
} else
goto cgii_exit;
/*
* If an inode wasn't passed in, then get the inode number
*
* Is an i_ino of zero legal? Can we use that to check if the server
* supports returning inode numbers? Are there other sanity checks we
* can use to ensure that the server is really filling in that field?
*/
if (*inode == NULL) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
if (validinum == false) {
if (server->ops->get_srv_inum)
tmprc = server->ops->get_srv_inum(xid,
tcon, cifs_sb, full_path,
&fattr.cf_uniqueid, data);
if (tmprc) {
cifs_dbg(FYI, "GetSrvInodeNum rc %d\n",
tmprc);
fattr.cf_uniqueid = iunique(sb, ROOT_I);
cifs_autodisable_serverino(cifs_sb);
} else if ((fattr.cf_uniqueid == 0) &&
strlen(full_path) == 0) {
/* some servers ret bad root ino ie 0 */
cifs_dbg(FYI, "Invalid (0) inodenum\n");
fattr.cf_flags |=
CIFS_FATTR_FAKE_ROOT_INO;
fattr.cf_uniqueid =
simple_hashstr(tcon->treeName);
}
}
} else
fattr.cf_uniqueid = iunique(sb, ROOT_I);
} else {
if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
validinum == false && server->ops->get_srv_inum) {
/*
* Pass a NULL tcon to ensure we don't make a round
* trip to the server. This only works for SMB2+.
*/
tmprc = server->ops->get_srv_inum(xid,
NULL, cifs_sb, full_path,
&fattr.cf_uniqueid, data);
if (tmprc)
fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
else if ((fattr.cf_uniqueid == 0) &&
strlen(full_path) == 0) {
/*
* Reuse existing root inode num since
* inum zero for root causes ls of . and .. to
* not be returned
*/
cifs_dbg(FYI, "Srv ret 0 inode num for root\n");
fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
}
} else
fattr.cf_uniqueid = CIFS_I(*inode)->uniqueid;
}
/* query for SFU type info if supported and needed */
if (fattr.cf_cifsattrs & ATTR_SYSTEM &&
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) {
tmprc = cifs_sfu_type(&fattr, full_path, cifs_sb, xid);
if (tmprc)
cifs_dbg(FYI, "cifs_sfu_type failed: %d\n", tmprc);
}
#ifdef CONFIG_CIFS_ACL
/* fill in 0777 bits from ACL */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
rc = cifs_acl_to_fattr(cifs_sb, &fattr, *inode, full_path, fid);
if (rc) {
cifs_dbg(FYI, "%s: Getting ACL failed with error: %d\n",
__func__, rc);
goto cgii_exit;
}
}
#endif /* CONFIG_CIFS_ACL */
/* fill in remaining high mode bits e.g. SUID, VTX */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)
cifs_sfu_mode(&fattr, full_path, cifs_sb, xid);
/* check for Minshall+French symlinks */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
tmprc = check_mf_symlink(xid, tcon, cifs_sb, &fattr,
full_path);
if (tmprc)
cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
}
if (!*inode) {
*inode = cifs_iget(sb, &fattr);
if (!*inode)
rc = -ENOMEM;
} else {
/* we already have inode, update it */
/* if uniqueid is different, return error */
if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
CIFS_I(*inode)->uniqueid != fattr.cf_uniqueid)) {
rc = -ESTALE;
goto cgii_exit;
}
/* if filetype is different, return error */
if (unlikely(((*inode)->i_mode & S_IFMT) !=
(fattr.cf_mode & S_IFMT))) {
rc = -ESTALE;
goto cgii_exit;
}
cifs_fattr_to_inode(*inode, &fattr);
}
cgii_exit:
if ((*inode) && ((*inode)->i_ino == 0))
cifs_dbg(FYI, "inode number of zero returned\n");
kfree(buf);
cifs_put_tlink(tlink);
return rc;
}
static const struct inode_operations cifs_ipc_inode_ops = {
.lookup = cifs_lookup,
};
static int
cifs_find_inode(struct inode *inode, void *opaque)
{
struct cifs_fattr *fattr = (struct cifs_fattr *) opaque;
/* don't match inode with different uniqueid */
if (CIFS_I(inode)->uniqueid != fattr->cf_uniqueid)
return 0;
/* use createtime like an i_generation field */
if (CIFS_I(inode)->createtime != fattr->cf_createtime)
return 0;
/* don't match inode of different type */
if ((inode->i_mode & S_IFMT) != (fattr->cf_mode & S_IFMT))
return 0;
/* if it's not a directory or has no dentries, then flag it */
if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry))
fattr->cf_flags |= CIFS_FATTR_INO_COLLISION;
return 1;
}
static int
cifs_init_inode(struct inode *inode, void *opaque)
{
struct cifs_fattr *fattr = (struct cifs_fattr *) opaque;
CIFS_I(inode)->uniqueid = fattr->cf_uniqueid;
CIFS_I(inode)->createtime = fattr->cf_createtime;
return 0;
}
/*
* walk dentry list for an inode and report whether it has aliases that
* are hashed. We use this to determine if a directory inode can actually
* be used.
*/
static bool
inode_has_hashed_dentries(struct inode *inode)
{
struct dentry *dentry;
spin_lock(&inode->i_lock);
hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) {
if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
spin_unlock(&inode->i_lock);
return true;
}
}
spin_unlock(&inode->i_lock);
return false;
}
/* Given fattrs, get a corresponding inode */
struct inode *
cifs_iget(struct super_block *sb, struct cifs_fattr *fattr)
{
unsigned long hash;
struct inode *inode;
retry_iget5_locked:
cifs_dbg(FYI, "looking for uniqueid=%llu\n", fattr->cf_uniqueid);
/* hash down to 32-bits on 32-bit arch */
hash = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid);
inode = iget5_locked(sb, hash, cifs_find_inode, cifs_init_inode, fattr);
if (inode) {
/* was there a potentially problematic inode collision? */
if (fattr->cf_flags & CIFS_FATTR_INO_COLLISION) {
fattr->cf_flags &= ~CIFS_FATTR_INO_COLLISION;
if (inode_has_hashed_dentries(inode)) {
cifs_autodisable_serverino(CIFS_SB(sb));
iput(inode);
fattr->cf_uniqueid = iunique(sb, ROOT_I);
goto retry_iget5_locked;
}
}
cifs_fattr_to_inode(inode, fattr);
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-28 00:05:09 +03:00
if (sb->s_flags & SB_NOATIME)
inode->i_flags |= S_NOATIME | S_NOCMTIME;
if (inode->i_state & I_NEW) {
inode->i_ino = hash;
#ifdef CONFIG_CIFS_FSCACHE
/* initialize per-inode cache cookie pointer */
CIFS_I(inode)->fscache = NULL;
#endif
unlock_new_inode(inode);
}
}
return inode;
}
/* gets root inode */
struct inode *cifs_root_iget(struct super_block *sb)
{
unsigned int xid;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct inode *inode = NULL;
long rc;
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
char *path = NULL;
int len;
if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
&& cifs_sb->prepath) {
len = strlen(cifs_sb->prepath);
path = kzalloc(len + 2 /* leading sep + null */, GFP_KERNEL);
if (path == NULL)
return ERR_PTR(-ENOMEM);
path[0] = '/';
memcpy(path+1, cifs_sb->prepath, len);
} else {
path = kstrdup("", GFP_KERNEL);
if (path == NULL)
return ERR_PTR(-ENOMEM);
}
xid = get_xid();
if (tcon->unix_ext) {
rc = cifs_get_inode_info_unix(&inode, path, sb, xid);
/* some servers mistakenly claim POSIX support */
if (rc != -EOPNOTSUPP)
goto iget_no_retry;
cifs_dbg(VFS, "server does not support POSIX extensions");
tcon->unix_ext = false;
}
convert_delimiter(path, CIFS_DIR_SEP(cifs_sb));
rc = cifs_get_inode_info(&inode, path, NULL, sb, xid, NULL);
iget_no_retry:
if (!inode) {
inode = ERR_PTR(rc);
goto out;
}
#ifdef CONFIG_CIFS_FSCACHE
/* populate tcon->resource_id */
tcon->resource_id = CIFS_I(inode)->uniqueid;
#endif
if (rc && tcon->pipe) {
cifs_dbg(FYI, "ipc connection - fake read inode\n");
spin_lock(&inode->i_lock);
inode->i_mode |= S_IFDIR;
set_nlink(inode, 2);
inode->i_op = &cifs_ipc_inode_ops;
inode->i_fop = &simple_dir_operations;
inode->i_uid = cifs_sb->mnt_uid;
inode->i_gid = cifs_sb->mnt_gid;
spin_unlock(&inode->i_lock);
} else if (rc) {
iget_failed(inode);
inode = ERR_PTR(rc);
}
out:
kfree(path);
free_xid(xid);
return inode;
}
int
cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
char *full_path, __u32 dosattr)
{
bool set_time = false;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct TCP_Server_Info *server;
FILE_BASIC_INFO info_buf;
if (attrs == NULL)
return -EINVAL;
server = cifs_sb_master_tcon(cifs_sb)->ses->server;
if (!server->ops->set_file_info)
return -ENOSYS;
if (attrs->ia_valid & ATTR_ATIME) {
set_time = true;
info_buf.LastAccessTime =
cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
} else
info_buf.LastAccessTime = 0;
if (attrs->ia_valid & ATTR_MTIME) {
set_time = true;
info_buf.LastWriteTime =
cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
} else
info_buf.LastWriteTime = 0;
/*
* Samba throws this field away, but windows may actually use it.
* Do not set ctime unless other time stamps are changed explicitly
* (i.e. by utimes()) since we would then have a mix of client and
* server times.
*/
if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
cifs_dbg(FYI, "CIFS - CTIME changed\n");
info_buf.ChangeTime =
cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
} else
info_buf.ChangeTime = 0;
info_buf.CreationTime = 0; /* don't change */
info_buf.Attributes = cpu_to_le32(dosattr);
return server->ops->set_file_info(inode, full_path, &info_buf, xid);
}
/*
* Open the given file (if it isn't already), set the DELETE_ON_CLOSE bit
* and rename it to a random name that hopefully won't conflict with
* anything else.
*/
int
cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
const unsigned int xid)
{
int oplock = 0;
int rc;
struct cifs_fid fid;
struct cifs_open_parms oparms;
struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
struct cifs_tcon *tcon;
__u32 dosattr, origattr;
FILE_BASIC_INFO *info_buf = NULL;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
/*
* We cannot rename the file if the server doesn't support
* CAP_INFOLEVEL_PASSTHRU
*/
if (!(tcon->ses->capabilities & CAP_INFOLEVEL_PASSTHRU)) {
rc = -EBUSY;
goto out;
}
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = DELETE | FILE_WRITE_ATTRIBUTES;
oparms.create_options = CREATE_NOT_DIR;
oparms.disposition = FILE_OPEN;
oparms.path = full_path;
oparms.fid = &fid;
oparms.reconnect = false;
rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc != 0)
goto out;
origattr = cifsInode->cifsAttrs;
if (origattr == 0)
origattr |= ATTR_NORMAL;
dosattr = origattr & ~ATTR_READONLY;
if (dosattr == 0)
dosattr |= ATTR_NORMAL;
dosattr |= ATTR_HIDDEN;
/* set ATTR_HIDDEN and clear ATTR_READONLY, but only if needed */
if (dosattr != origattr) {
info_buf = kzalloc(sizeof(*info_buf), GFP_KERNEL);
if (info_buf == NULL) {
rc = -ENOMEM;
goto out_close;
}
info_buf->Attributes = cpu_to_le32(dosattr);
rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, fid.netfid,
current->tgid);
/* although we would like to mark the file hidden
if that fails we will still try to rename it */
if (!rc)
cifsInode->cifsAttrs = dosattr;
else
dosattr = origattr; /* since not able to change them */
}
/* rename the file */
rc = CIFSSMBRenameOpenFile(xid, tcon, fid.netfid, NULL,
cifs_sb->local_nls,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_remap(cifs_sb));
if (rc != 0) {
rc = -EBUSY;
goto undo_setattr;
}
/* try to set DELETE_ON_CLOSE */
if (!test_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags)) {
rc = CIFSSMBSetFileDisposition(xid, tcon, true, fid.netfid,
current->tgid);
/*
* some samba versions return -ENOENT when we try to set the
* file disposition here. Likely a samba bug, but work around
* it for now. This means that some cifsXXX files may hang
* around after they shouldn't.
*
* BB: remove this hack after more servers have the fix
*/
if (rc == -ENOENT)
rc = 0;
else if (rc != 0) {
rc = -EBUSY;
goto undo_rename;
}
set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags);
}
out_close:
CIFSSMBClose(xid, tcon, fid.netfid);
out:
kfree(info_buf);
cifs_put_tlink(tlink);
return rc;
/*
* reset everything back to the original state. Don't bother
* dealing with errors here since we can't do anything about
* them anyway.
*/
undo_rename:
CIFSSMBRenameOpenFile(xid, tcon, fid.netfid, dentry->d_name.name,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_sb->local_nls, cifs_remap(cifs_sb));
undo_setattr:
if (dosattr != origattr) {
info_buf->Attributes = cpu_to_le32(origattr);
if (!CIFSSMBSetFileInfo(xid, tcon, info_buf, fid.netfid,
current->tgid))
cifsInode->cifsAttrs = origattr;
}
goto out_close;
}
/* copied from fs/nfs/dir.c with small changes */
static void
cifs_drop_nlink(struct inode *inode)
{
spin_lock(&inode->i_lock);
if (inode->i_nlink > 0)
drop_nlink(inode);
spin_unlock(&inode->i_lock);
}
/*
* If d_inode(dentry) is null (usually meaning the cached dentry
* is a negative dentry) then we would attempt a standard SMB delete, but
* if that fails we can not attempt the fall back mechanisms on EACCESS
* but will return the EACCESS to the caller. Note that the VFS does not call
* unlink on negative dentries currently.
*/
int cifs_unlink(struct inode *dir, struct dentry *dentry)
{
int rc = 0;
unsigned int xid;
char *full_path = NULL;
struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifs_inode;
struct super_block *sb = dir->i_sb;
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct iattr *attrs = NULL;
__u32 dosattr = 0, origattr = 0;
cifs_dbg(FYI, "cifs_unlink, dir=0x%p, dentry=0x%p\n", dir, dentry);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
xid = get_xid();
/* Unlink can be called from rename so we can not take the
* sb->s_vfs_rename_mutex here */
full_path = build_path_from_dentry(dentry);
if (full_path == NULL) {
cifs: Fix incorrect return code being printed in cFYI messages FreeXid() along with freeing Xid does add a cifsFYI debug message that prints rc (return code) as well. In some code paths where we set/return error code after calling FreeXid(), incorrect error code is being printed when cifsFYI is enabled. This could be misleading in few cases. For eg. In cifs_open() if cifs_fill_filedata() returns a valid pointer to cifsFileInfo, FreeXid() prints rc=-13 whereas 0 is actually being returned. Fix this by setting rc before calling FreeXid(). Basically convert FreeXid(xid); rc = -ERR; return -ERR; => FreeXid(xid); return rc; [Note that Christoph would like to replace the GetXid/FreeXid calls, which are primarily used for debugging. This seems like a good longer term goal, but although there is an alternative tracing facility, there are no examples yet available that I know of that we can use (yet) to convert this cifs function entry/exit logging, and for creating an identifier that we can use to correlate all dmesg log entries for a particular vfs operation (ie identify all log entries for a particular vfs request to cifs: e.g. a particular close or read or write or byte range lock call ... and just using the thread id is harder). Eventually when a replacement for this is available (e.g. when NFS switches over and various samples to look at in other file systems) we can remove the GetXid/FreeXid macro but in the meantime multiple people use this run time configurable logging all the time for debugging, and Suresh's patch fixes a problem which made it harder to notice some low memory problems in the log so it is worthwhile to fix this problem until a better logging approach is able to be used] Acked-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
2009-06-25 16:42:34 +04:00
rc = -ENOMEM;
goto unlink_out;
}
if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = CIFSPOSIXDelFile(xid, tcon, full_path,
SMB_POSIX_UNLINK_FILE_TARGET, cifs_sb->local_nls,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_remap(cifs_sb));
cifs_dbg(FYI, "posix del rc %d\n", rc);
if ((rc == 0) || (rc == -ENOENT))
goto psx_del_no_retry;
}
retry_std_delete:
if (!server->ops->unlink) {
rc = -ENOSYS;
goto psx_del_no_retry;
}
rc = server->ops->unlink(xid, tcon, full_path, cifs_sb);
psx_del_no_retry:
if (!rc) {
if (inode)
cifs_drop_nlink(inode);
} else if (rc == -ENOENT) {
d_drop(dentry);
} else if (rc == -EBUSY) {
if (server->ops->rename_pending_delete) {
rc = server->ops->rename_pending_delete(full_path,
dentry, xid);
if (rc == 0)
cifs_drop_nlink(inode);
}
} else if ((rc == -EACCES) && (dosattr == 0) && inode) {
attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
if (attrs == NULL) {
rc = -ENOMEM;
goto out_reval;
}
/* try to reset dos attributes */
cifs_inode = CIFS_I(inode);
origattr = cifs_inode->cifsAttrs;
if (origattr == 0)
origattr |= ATTR_NORMAL;
dosattr = origattr & ~ATTR_READONLY;
if (dosattr == 0)
dosattr |= ATTR_NORMAL;
dosattr |= ATTR_HIDDEN;
rc = cifs_set_file_info(inode, attrs, xid, full_path, dosattr);
if (rc != 0)
goto out_reval;
goto retry_std_delete;
}
/* undo the setattr if we errored out and it's needed */
if (rc != 0 && dosattr != 0)
cifs_set_file_info(inode, attrs, xid, full_path, origattr);
out_reval:
if (inode) {
cifs_inode = CIFS_I(inode);
cifs_inode->time = 0; /* will force revalidate to get info
when needed */
inode->i_ctime = current_time(inode);
}
dir->i_ctime = dir->i_mtime = current_time(dir);
cifs_inode = CIFS_I(dir);
CIFS_I(dir)->time = 0; /* force revalidate of dir as well */
unlink_out:
kfree(full_path);
kfree(attrs);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
}
static int
cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode,
const char *full_path, struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon, const unsigned int xid)
{
int rc = 0;
struct inode *inode = NULL;
if (tcon->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path, parent->i_sb,
xid);
else
rc = cifs_get_inode_info(&inode, full_path, NULL, parent->i_sb,
xid, NULL);
if (rc)
return rc;
/*
* setting nlink not necessary except in cases where we failed to get it
* from the server or was set bogus. Also, since this is a brand new
* inode, no need to grab the i_lock before setting the i_nlink.
*/
if (inode->i_nlink < 2)
set_nlink(inode, 2);
mode &= ~current_umask();
/* must turn on setgid bit if parent dir has it */
if (parent->i_mode & S_ISGID)
mode |= S_ISGID;
if (tcon->unix_ext) {
struct cifs_unix_set_info_args args = {
.mode = mode,
.ctime = NO_CHANGE_64,
.atime = NO_CHANGE_64,
.mtime = NO_CHANGE_64,
.device = 0,
};
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
args.uid = current_fsuid();
if (parent->i_mode & S_ISGID)
args.gid = parent->i_gid;
else
args.gid = current_fsgid();
} else {
args.uid = INVALID_UID; /* no change */
args.gid = INVALID_GID; /* no change */
}
CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
cifs_sb->local_nls,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_remap(cifs_sb));
} else {
struct TCP_Server_Info *server = tcon->ses->server;
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
(mode & S_IWUGO) == 0 && server->ops->mkdir_setinfo)
server->ops->mkdir_setinfo(inode, full_path, cifs_sb,
tcon, xid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
inode->i_mode = (mode | S_IFDIR);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
inode->i_uid = current_fsuid();
if (inode->i_mode & S_ISGID)
inode->i_gid = parent->i_gid;
else
inode->i_gid = current_fsgid();
}
}
d_instantiate(dentry, inode);
return rc;
}
static int
cifs_posix_mkdir(struct inode *inode, struct dentry *dentry, umode_t mode,
const char *full_path, struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon, const unsigned int xid)
{
int rc = 0;
u32 oplock = 0;
FILE_UNIX_BASIC_INFO *info = NULL;
struct inode *newinode = NULL;
struct cifs_fattr fattr;
info = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL);
if (info == NULL) {
rc = -ENOMEM;
goto posix_mkdir_out;
}
mode &= ~current_umask();
rc = CIFSPOSIXCreate(xid, tcon, SMB_O_DIRECTORY | SMB_O_CREAT, mode,
NULL /* netfid */, info, &oplock, full_path,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_sb->local_nls, cifs_remap(cifs_sb));
if (rc == -EOPNOTSUPP)
goto posix_mkdir_out;
else if (rc) {
cifs_dbg(FYI, "posix mkdir returned 0x%x\n", rc);
d_drop(dentry);
goto posix_mkdir_out;
}
if (info->Type == cpu_to_le32(-1))
/* no return info, go query for it */
goto posix_mkdir_get_info;
/*
* BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if
* need to set uid/gid.
*/
cifs_unix_basic_to_fattr(&fattr, info, cifs_sb);
cifs_fill_uniqueid(inode->i_sb, &fattr);
newinode = cifs_iget(inode->i_sb, &fattr);
if (!newinode)
goto posix_mkdir_get_info;
d_instantiate(dentry, newinode);
#ifdef CONFIG_CIFS_DEBUG2
cifs_dbg(FYI, "instantiated dentry %p %pd to inode %p\n",
dentry, dentry, newinode);
if (newinode->i_nlink != 2)
cifs_dbg(FYI, "unexpected number of links %d\n",
newinode->i_nlink);
#endif
posix_mkdir_out:
kfree(info);
return rc;
posix_mkdir_get_info:
rc = cifs_mkdir_qinfo(inode, dentry, mode, full_path, cifs_sb, tcon,
xid);
goto posix_mkdir_out;
}
int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
{
int rc = 0;
unsigned int xid;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
char *full_path;
cifs_dbg(FYI, "In cifs_mkdir, mode = 0x%hx inode = 0x%p\n",
mode, inode);
cifs_sb = CIFS_SB(inode->i_sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
xid = get_xid();
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
cifs: Fix incorrect return code being printed in cFYI messages FreeXid() along with freeing Xid does add a cifsFYI debug message that prints rc (return code) as well. In some code paths where we set/return error code after calling FreeXid(), incorrect error code is being printed when cifsFYI is enabled. This could be misleading in few cases. For eg. In cifs_open() if cifs_fill_filedata() returns a valid pointer to cifsFileInfo, FreeXid() prints rc=-13 whereas 0 is actually being returned. Fix this by setting rc before calling FreeXid(). Basically convert FreeXid(xid); rc = -ERR; return -ERR; => FreeXid(xid); return rc; [Note that Christoph would like to replace the GetXid/FreeXid calls, which are primarily used for debugging. This seems like a good longer term goal, but although there is an alternative tracing facility, there are no examples yet available that I know of that we can use (yet) to convert this cifs function entry/exit logging, and for creating an identifier that we can use to correlate all dmesg log entries for a particular vfs operation (ie identify all log entries for a particular vfs request to cifs: e.g. a particular close or read or write or byte range lock call ... and just using the thread id is harder). Eventually when a replacement for this is available (e.g. when NFS switches over and various samples to look at in other file systems) we can remove the GetXid/FreeXid macro but in the meantime multiple people use this run time configurable logging all the time for debugging, and Suresh's patch fixes a problem which made it harder to notice some low memory problems in the log so it is worthwhile to fix this problem until a better logging approach is able to be used] Acked-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
2009-06-25 16:42:34 +04:00
rc = -ENOMEM;
goto mkdir_out;
}
if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_mkdir(inode, direntry, mode, full_path, cifs_sb,
tcon, xid);
if (rc != -EOPNOTSUPP)
goto mkdir_out;
}
server = tcon->ses->server;
if (!server->ops->mkdir) {
rc = -ENOSYS;
goto mkdir_out;
}
/* BB add setting the equivalent of mode via CreateX w/ACLs */
rc = server->ops->mkdir(xid, tcon, full_path, cifs_sb);
if (rc) {
cifs_dbg(FYI, "cifs_mkdir returned 0x%x\n", rc);
d_drop(direntry);
goto mkdir_out;
}
rc = cifs_mkdir_qinfo(inode, direntry, mode, full_path, cifs_sb, tcon,
xid);
mkdir_out:
/*
* Force revalidate to get parent dir info when needed since cached
* attributes are invalid now.
*/
CIFS_I(inode)->time = 0;
kfree(full_path);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
}
int cifs_rmdir(struct inode *inode, struct dentry *direntry)
{
int rc = 0;
unsigned int xid;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
char *full_path = NULL;
struct cifsInodeInfo *cifsInode;
cifs_dbg(FYI, "cifs_rmdir, inode = 0x%p\n", inode);
xid = get_xid();
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
cifs: Fix incorrect return code being printed in cFYI messages FreeXid() along with freeing Xid does add a cifsFYI debug message that prints rc (return code) as well. In some code paths where we set/return error code after calling FreeXid(), incorrect error code is being printed when cifsFYI is enabled. This could be misleading in few cases. For eg. In cifs_open() if cifs_fill_filedata() returns a valid pointer to cifsFileInfo, FreeXid() prints rc=-13 whereas 0 is actually being returned. Fix this by setting rc before calling FreeXid(). Basically convert FreeXid(xid); rc = -ERR; return -ERR; => FreeXid(xid); return rc; [Note that Christoph would like to replace the GetXid/FreeXid calls, which are primarily used for debugging. This seems like a good longer term goal, but although there is an alternative tracing facility, there are no examples yet available that I know of that we can use (yet) to convert this cifs function entry/exit logging, and for creating an identifier that we can use to correlate all dmesg log entries for a particular vfs operation (ie identify all log entries for a particular vfs request to cifs: e.g. a particular close or read or write or byte range lock call ... and just using the thread id is harder). Eventually when a replacement for this is available (e.g. when NFS switches over and various samples to look at in other file systems) we can remove the GetXid/FreeXid macro but in the meantime multiple people use this run time configurable logging all the time for debugging, and Suresh's patch fixes a problem which made it harder to notice some low memory problems in the log so it is worthwhile to fix this problem until a better logging approach is able to be used] Acked-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
2009-06-25 16:42:34 +04:00
rc = -ENOMEM;
goto rmdir_exit;
}
cifs_sb = CIFS_SB(inode->i_sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
rc = PTR_ERR(tlink);
goto rmdir_exit;
}
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
if (!server->ops->rmdir) {
rc = -ENOSYS;
cifs_put_tlink(tlink);
goto rmdir_exit;
}
rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb);
cifs_put_tlink(tlink);
if (!rc) {
spin_lock(&d_inode(direntry)->i_lock);
i_size_write(d_inode(direntry), 0);
clear_nlink(d_inode(direntry));
spin_unlock(&d_inode(direntry)->i_lock);
}
cifsInode = CIFS_I(d_inode(direntry));
/* force revalidate to go get info when needed */
cifsInode->time = 0;
cifsInode = CIFS_I(inode);
/*
* Force revalidate to get parent dir info when needed since cached
* attributes are invalid now.
*/
cifsInode->time = 0;
d_inode(direntry)->i_ctime = inode->i_ctime = inode->i_mtime =
current_time(inode);
rmdir_exit:
kfree(full_path);
free_xid(xid);
return rc;
}
static int
cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
const char *from_path, struct dentry *to_dentry,
const char *to_path)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(from_dentry->d_sb);
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
struct cifs_fid fid;
struct cifs_open_parms oparms;
int oplock, rc;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
if (!server->ops->rename)
return -ENOSYS;
/* try path-based rename first */
rc = server->ops->rename(xid, tcon, from_path, to_path, cifs_sb);
/*
* Don't bother with rename by filehandle unless file is busy and
* source. Note that cross directory moves do not work with
* rename by filehandle to various Windows servers.
*/
if (rc == 0 || rc != -EBUSY)
goto do_rename_exit;
/* open-file renames don't work across directories */
if (to_dentry->d_parent != from_dentry->d_parent)
goto do_rename_exit;
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
/* open the file to be renamed -- we need DELETE perms */
oparms.desired_access = DELETE;
oparms.create_options = CREATE_NOT_DIR;
oparms.disposition = FILE_OPEN;
oparms.path = from_path;
oparms.fid = &fid;
oparms.reconnect = false;
rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc == 0) {
rc = CIFSSMBRenameOpenFile(xid, tcon, fid.netfid,
(const char *) to_dentry->d_name.name,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_sb->local_nls, cifs_remap(cifs_sb));
CIFSSMBClose(xid, tcon, fid.netfid);
}
do_rename_exit:
cifs_put_tlink(tlink);
return rc;
}
int
cifs_rename2(struct inode *source_dir, struct dentry *source_dentry,
struct inode *target_dir, struct dentry *target_dentry,
unsigned int flags)
{
char *from_name = NULL;
char *to_name = NULL;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
FILE_UNIX_BASIC_INFO *info_buf_source = NULL;
FILE_UNIX_BASIC_INFO *info_buf_target;
unsigned int xid;
int rc, tmprc;
if (flags & ~RENAME_NOREPLACE)
return -EINVAL;
cifs_sb = CIFS_SB(source_dir->i_sb);
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
xid = get_xid();
/*
* we already have the rename sem so we do not need to
* grab it again here to protect the path integrity
*/
from_name = build_path_from_dentry(source_dentry);
if (from_name == NULL) {
rc = -ENOMEM;
goto cifs_rename_exit;
}
to_name = build_path_from_dentry(target_dentry);
if (to_name == NULL) {
rc = -ENOMEM;
goto cifs_rename_exit;
}
rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry,
to_name);
/*
* No-replace is the natural behavior for CIFS, so skip unlink hacks.
*/
if (flags & RENAME_NOREPLACE)
goto cifs_rename_exit;
if (rc == -EEXIST && tcon->unix_ext) {
/*
* Are src and dst hardlinks of same inode? We can only tell
* with unix extensions enabled.
*/
info_buf_source =
kmalloc(2 * sizeof(FILE_UNIX_BASIC_INFO),
GFP_KERNEL);
if (info_buf_source == NULL) {
rc = -ENOMEM;
goto cifs_rename_exit;
}
info_buf_target = info_buf_source + 1;
tmprc = CIFSSMBUnixQPathInfo(xid, tcon, from_name,
info_buf_source,
cifs_sb->local_nls,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_remap(cifs_sb));
if (tmprc != 0)
goto unlink_target;
tmprc = CIFSSMBUnixQPathInfo(xid, tcon, to_name,
info_buf_target,
cifs_sb->local_nls,
Remap reserved posix characters by default (part 3/3) This is a bigger patch, but its size is mostly due to a single change for how we check for remapping illegal characters in file names - a lot of repeated, small changes to the way callers request converting file names. The final patch in the series does the following: 1) changes default behavior for cifs to be more intuitive. Currently we do not map by default to seven reserved characters, ie those valid in POSIX but not in NTFS/CIFS/SMB3/Windows, unless a mount option (mapchars) is specified. Change this to by default always map and map using the SFM maping (like the Mac uses) unless the server negotiates the CIFS Unix Extensions (like Samba does when mounting with the cifs protocol) when the remapping of the characters is unnecessary. This should help SMB3 mounts in particular since Samba will likely be able to implement this mapping with its new "vfs_fruit" module as it will be doing for the Mac. 2) if the user specifies the existing "mapchars" mount option then use the "SFU" (Microsoft Services for Unix, SUA) style mapping of the seven characters instead. 3) if the user specifies "nomapposix" then disable SFM/MAC style mapping (so no character remapping would be used unless the user specifies "mapchars" on mount as well, as above). 4) change all the places in the code that check for the superblock flag on the mount which is set by mapchars and passed in on all path based operation and change it to use a small function call instead to set the mapping type properly (and check for the mapping type in the cifs unicode functions) Signed-off-by: Steve French <smfrench@gmail.com>
2014-09-27 11:19:01 +04:00
cifs_remap(cifs_sb));
if (tmprc == 0 && (info_buf_source->UniqueId ==
info_buf_target->UniqueId)) {
/* same file, POSIX says that this is a noop */
rc = 0;
goto cifs_rename_exit;
}
}
/*
* else ... BB we could add the same check for Windows by
* checking the UniqueId via FILE_INTERNAL_INFO
*/
unlink_target:
/* Try unlinking the target dentry if it's not negative */
if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) {
if (d_is_dir(target_dentry))
tmprc = cifs_rmdir(target_dir, target_dentry);
else
tmprc = cifs_unlink(target_dir, target_dentry);
if (tmprc)
goto cifs_rename_exit;
rc = cifs_do_rename(xid, source_dentry, from_name,
target_dentry, to_name);
}
/* force revalidate to go get info when needed */
CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0;
source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime =
target_dir->i_mtime = current_time(source_dir);
cifs_rename_exit:
kfree(info_buf_source);
kfree(from_name);
kfree(to_name);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
}
static bool
cifs_inode_needs_reval(struct inode *inode)
{
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
if (CIFS_CACHE_READ(cifs_i))
return false;
if (!lookupCacheEnabled)
return true;
if (cifs_i->time == 0)
return true;
if (!cifs_sb->actimeo)
return true;
if (!time_in_range(jiffies, cifs_i->time,
cifs_i->time + cifs_sb->actimeo))
return true;
/* hardlinked files w/ noserverino get "special" treatment */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) &&
S_ISREG(inode->i_mode) && inode->i_nlink != 1)
return true;
return false;
}
/*
* Zap the cache. Called when invalid_mapping flag is set.
*/
int
cifs_invalidate_mapping(struct inode *inode)
{
int rc = 0;
if (inode->i_mapping && inode->i_mapping->nrpages != 0) {
rc = invalidate_inode_pages2(inode->i_mapping);
if (rc)
cifs_dbg(VFS, "%s: could not invalidate inode %p\n",
__func__, inode);
}
cifs_fscache_reset_inode_cookie(inode);
return rc;
}
/**
* cifs_wait_bit_killable - helper for functions that are sleeping on bit locks
* @word: long word containing the bit lock
*/
static int
cifs_wait_bit_killable(struct wait_bit_key *key, int mode)
{
freezable_schedule_unsafe();
if (signal_pending_state(mode, current))
return -ERESTARTSYS;
return 0;
}
int
cifs_revalidate_mapping(struct inode *inode)
{
int rc;
unsigned long *flags = &CIFS_I(inode)->flags;
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
rc = wait_on_bit_lock_action(flags, CIFS_INO_LOCK, cifs_wait_bit_killable,
TASK_KILLABLE);
if (rc)
return rc;
if (test_and_clear_bit(CIFS_INO_INVALID_MAPPING, flags)) {
rc = cifs_invalidate_mapping(inode);
if (rc)
set_bit(CIFS_INO_INVALID_MAPPING, flags);
}
clear_bit_unlock(CIFS_INO_LOCK, flags);
smp_mb__after_atomic();
wake_up_bit(flags, CIFS_INO_LOCK);
return rc;
}
int
cifs_zap_mapping(struct inode *inode)
{
set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags);
return cifs_revalidate_mapping(inode);
}
int cifs_revalidate_file_attr(struct file *filp)
{
int rc = 0;
struct inode *inode = file_inode(filp);
struct cifsFileInfo *cfile = (struct cifsFileInfo *) filp->private_data;
if (!cifs_inode_needs_reval(inode))
return rc;
if (tlink_tcon(cfile->tlink)->unix_ext)
rc = cifs_get_file_info_unix(filp);
else
rc = cifs_get_file_info(filp);
return rc;
}
int cifs_revalidate_dentry_attr(struct dentry *dentry)
{
unsigned int xid;
int rc = 0;
struct inode *inode = d_inode(dentry);
struct super_block *sb = dentry->d_sb;
char *full_path = NULL;
if (inode == NULL)
return -ENOENT;
if (!cifs_inode_needs_reval(inode))
return rc;
xid = get_xid();
/* can not safely grab the rename sem here if rename calls revalidate
since that would deadlock */
full_path = build_path_from_dentry(dentry);
if (full_path == NULL) {
cifs: Fix incorrect return code being printed in cFYI messages FreeXid() along with freeing Xid does add a cifsFYI debug message that prints rc (return code) as well. In some code paths where we set/return error code after calling FreeXid(), incorrect error code is being printed when cifsFYI is enabled. This could be misleading in few cases. For eg. In cifs_open() if cifs_fill_filedata() returns a valid pointer to cifsFileInfo, FreeXid() prints rc=-13 whereas 0 is actually being returned. Fix this by setting rc before calling FreeXid(). Basically convert FreeXid(xid); rc = -ERR; return -ERR; => FreeXid(xid); return rc; [Note that Christoph would like to replace the GetXid/FreeXid calls, which are primarily used for debugging. This seems like a good longer term goal, but although there is an alternative tracing facility, there are no examples yet available that I know of that we can use (yet) to convert this cifs function entry/exit logging, and for creating an identifier that we can use to correlate all dmesg log entries for a particular vfs operation (ie identify all log entries for a particular vfs request to cifs: e.g. a particular close or read or write or byte range lock call ... and just using the thread id is harder). Eventually when a replacement for this is available (e.g. when NFS switches over and various samples to look at in other file systems) we can remove the GetXid/FreeXid macro but in the meantime multiple people use this run time configurable logging all the time for debugging, and Suresh's patch fixes a problem which made it harder to notice some low memory problems in the log so it is worthwhile to fix this problem until a better logging approach is able to be used] Acked-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
2009-06-25 16:42:34 +04:00
rc = -ENOMEM;
goto out;
}
cifs_dbg(FYI, "Update attributes: %s inode 0x%p count %d dentry: 0x%p d_time %ld jiffies %ld\n",
full_path, inode, inode->i_count.counter,
dentry, cifs_get_time(dentry), jiffies);
if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
rc = cifs_get_inode_info_unix(&inode, full_path, sb, xid);
else
rc = cifs_get_inode_info(&inode, full_path, NULL, sb,
xid, NULL);
out:
kfree(full_path);
free_xid(xid);
return rc;
}
int cifs_revalidate_file(struct file *filp)
{
int rc;
struct inode *inode = file_inode(filp);
rc = cifs_revalidate_file_attr(filp);
if (rc)
return rc;
return cifs_revalidate_mapping(inode);
}
/* revalidate a dentry's inode attributes */
int cifs_revalidate_dentry(struct dentry *dentry)
{
int rc;
struct inode *inode = d_inode(dentry);
rc = cifs_revalidate_dentry_attr(dentry);
if (rc)
return rc;
return cifs_revalidate_mapping(inode);
}
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
int cifs_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 cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct inode *inode = d_inode(dentry);
int rc;
/*
* We need to be sure that all dirty pages are written and the server
* has actual ctime, mtime and file length.
*/
if (!CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping &&
inode->i_mapping->nrpages != 0) {
rc = filemap_fdatawait(inode->i_mapping);
if (rc) {
mapping_set_error(inode->i_mapping, rc);
return rc;
}
}
rc = cifs_revalidate_dentry_attr(dentry);
if (rc)
return rc;
generic_fillattr(inode, stat);
stat->blksize = CIFS_MAX_MSGSIZE;
stat->ino = CIFS_I(inode)->uniqueid;
/* old CIFS Unix Extensions doesn't return create time */
if (CIFS_I(inode)->createtime) {
stat->result_mask |= STATX_BTIME;
stat->btime =
cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
}
stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_COMPRESSED)
stat->attributes |= STATX_ATTR_COMPRESSED;
if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_ENCRYPTED)
stat->attributes |= STATX_ATTR_ENCRYPTED;
/*
* If on a multiuser mount without unix extensions or cifsacl being
* enabled, and the admin hasn't overridden them, set the ownership
* to the fsuid/fsgid of the current process.
*/
if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) &&
!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) &&
!tcon->unix_ext) {
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID))
stat->uid = current_fsuid();
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID))
stat->gid = current_fsgid();
}
return rc;
}
static int cifs_truncate_page(struct address_space *mapping, loff_t from)
{
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (PAGE_SIZE - 1);
struct page *page;
int rc = 0;
page = grab_cache_page(mapping, index);
if (!page)
return -ENOMEM;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
zero_user_segment(page, offset, PAGE_SIZE);
unlock_page(page);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 15:29:47 +03:00
put_page(page);
return rc;
}
static void cifs_setsize(struct inode *inode, loff_t offset)
{
spin_lock(&inode->i_lock);
i_size_write(inode, offset);
spin_unlock(&inode->i_lock);
truncate_pagecache(inode, offset);
}
static int
cifs_set_file_size(struct inode *inode, struct iattr *attrs,
unsigned int xid, char *full_path)
{
int rc;
struct cifsFileInfo *open_file;
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = NULL;
struct cifs_tcon *tcon = NULL;
struct TCP_Server_Info *server;
/*
* To avoid spurious oplock breaks from server, in the case of
* inodes that we already have open, avoid doing path based
* setting of file size if we can do it by handle.
* This keeps our caching token (oplock) and avoids timeouts
* when the local oplock break takes longer to flush
* writebehind data than the SMB timeout for the SetPathInfo
* request would allow
*/
open_file = find_writable_file(cifsInode, true);
if (open_file) {
tcon = tlink_tcon(open_file->tlink);
server = tcon->ses->server;
if (server->ops->set_file_size)
rc = server->ops->set_file_size(xid, tcon, open_file,
attrs->ia_size, false);
else
rc = -ENOSYS;
cifsFileInfo_put(open_file);
cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc);
} else
rc = -EINVAL;
if (!rc)
goto set_size_out;
if (tcon == NULL) {
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
}
/*
* Set file size by pathname rather than by handle either because no
* valid, writeable file handle for it was found or because there was
* an error setting it by handle.
*/
if (server->ops->set_path_size)
rc = server->ops->set_path_size(xid, tcon, full_path,
attrs->ia_size, cifs_sb, false);
else
rc = -ENOSYS;
cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc);
if (tlink)
cifs_put_tlink(tlink);
set_size_out:
if (rc == 0) {
cifsInode->server_eof = attrs->ia_size;
cifs_setsize(inode, attrs->ia_size);
cifs_truncate_page(inode->i_mapping, inode->i_size);
}
return rc;
}
static int
cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
{
int rc;
unsigned int xid;
char *full_path = NULL;
struct inode *inode = d_inode(direntry);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
struct cifs_unix_set_info_args *args = NULL;
struct cifsFileInfo *open_file;
cifs_dbg(FYI, "setattr_unix on file %pd attrs->ia_valid=0x%x\n",
direntry, attrs->ia_valid);
xid = get_xid();
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
attrs->ia_valid |= ATTR_FORCE;
rc = setattr_prepare(direntry, attrs);
if (rc < 0)
goto out;
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
rc = -ENOMEM;
goto out;
}
/*
* Attempt to flush data before changing attributes. We need to do
* this for ATTR_SIZE and ATTR_MTIME for sure, and if we change the
* ownership or mode then we may also need to do this. Here, we take
* the safe way out and just do the flush on all setattr requests. If
* the flush returns error, store it to report later and continue.
*
* BB: This should be smarter. Why bother flushing pages that
* will be truncated anyway? Also, should we error out here if
* the flush returns error?
*/
rc = filemap_write_and_wait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
rc = 0;
if (attrs->ia_valid & ATTR_SIZE) {
rc = cifs_set_file_size(inode, attrs, xid, full_path);
if (rc != 0)
goto out;
}
/* skip mode change if it's just for clearing setuid/setgid */
if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
attrs->ia_valid &= ~ATTR_MODE;
args = kmalloc(sizeof(*args), GFP_KERNEL);
if (args == NULL) {
rc = -ENOMEM;
goto out;
}
/* set up the struct */
if (attrs->ia_valid & ATTR_MODE)
args->mode = attrs->ia_mode;
else
args->mode = NO_CHANGE_64;
if (attrs->ia_valid & ATTR_UID)
args->uid = attrs->ia_uid;
else
args->uid = INVALID_UID; /* no change */
if (attrs->ia_valid & ATTR_GID)
args->gid = attrs->ia_gid;
else
args->gid = INVALID_GID; /* no change */
if (attrs->ia_valid & ATTR_ATIME)
args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
else
args->atime = NO_CHANGE_64;
if (attrs->ia_valid & ATTR_MTIME)
args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime);
else
args->mtime = NO_CHANGE_64;
if (attrs->ia_valid & ATTR_CTIME)
args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime);
else
args->ctime = NO_CHANGE_64;
args->device = 0;
open_file = find_writable_file(cifsInode, true);
if (open_file) {
u16 nfid = open_file->fid.netfid;
u32 npid = open_file->pid;
pTcon = tlink_tcon(open_file->tlink);
rc = CIFSSMBUnixSetFileInfo(xid, pTcon, args, nfid, npid);
cifsFileInfo_put(open_file);
} else {
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink)) {
rc = PTR_ERR(tlink);
goto out;
}
pTcon = tlink_tcon(tlink);
rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, args,
cifs_sb->local_nls,
cifs_remap(cifs_sb));
cifs_put_tlink(tlink);
}
if (rc)
goto out;
if ((attrs->ia_valid & ATTR_SIZE) &&
attrs->ia_size != i_size_read(inode))
truncate_setsize(inode, attrs->ia_size);
setattr_copy(inode, attrs);
mark_inode_dirty(inode);
/* force revalidate when any of these times are set since some
of the fs types (eg ext3, fat) do not have fine enough
time granularity to match protocol, and we do not have a
a way (yet) to query the server fs's time granularity (and
whether it rounds times down).
*/
if (attrs->ia_valid & (ATTR_MTIME | ATTR_CTIME))
cifsInode->time = 0;
out:
kfree(args);
kfree(full_path);
free_xid(xid);
return rc;
}
static int
cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
{
unsigned int xid;
kuid_t uid = INVALID_UID;
kgid_t gid = INVALID_GID;
struct inode *inode = d_inode(direntry);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
char *full_path = NULL;
int rc = -EACCES;
__u32 dosattr = 0;
__u64 mode = NO_CHANGE_64;
xid = get_xid();
cifs_dbg(FYI, "setattr on file %pd attrs->iavalid 0x%x\n",
direntry, attrs->ia_valid);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
attrs->ia_valid |= ATTR_FORCE;
rc = setattr_prepare(direntry, attrs);
if (rc < 0) {
free_xid(xid);
return rc;
}
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
cifs: Fix incorrect return code being printed in cFYI messages FreeXid() along with freeing Xid does add a cifsFYI debug message that prints rc (return code) as well. In some code paths where we set/return error code after calling FreeXid(), incorrect error code is being printed when cifsFYI is enabled. This could be misleading in few cases. For eg. In cifs_open() if cifs_fill_filedata() returns a valid pointer to cifsFileInfo, FreeXid() prints rc=-13 whereas 0 is actually being returned. Fix this by setting rc before calling FreeXid(). Basically convert FreeXid(xid); rc = -ERR; return -ERR; => FreeXid(xid); return rc; [Note that Christoph would like to replace the GetXid/FreeXid calls, which are primarily used for debugging. This seems like a good longer term goal, but although there is an alternative tracing facility, there are no examples yet available that I know of that we can use (yet) to convert this cifs function entry/exit logging, and for creating an identifier that we can use to correlate all dmesg log entries for a particular vfs operation (ie identify all log entries for a particular vfs request to cifs: e.g. a particular close or read or write or byte range lock call ... and just using the thread id is harder). Eventually when a replacement for this is available (e.g. when NFS switches over and various samples to look at in other file systems) we can remove the GetXid/FreeXid macro but in the meantime multiple people use this run time configurable logging all the time for debugging, and Suresh's patch fixes a problem which made it harder to notice some low memory problems in the log so it is worthwhile to fix this problem until a better logging approach is able to be used] Acked-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
2009-06-25 16:42:34 +04:00
rc = -ENOMEM;
free_xid(xid);
cifs: Fix incorrect return code being printed in cFYI messages FreeXid() along with freeing Xid does add a cifsFYI debug message that prints rc (return code) as well. In some code paths where we set/return error code after calling FreeXid(), incorrect error code is being printed when cifsFYI is enabled. This could be misleading in few cases. For eg. In cifs_open() if cifs_fill_filedata() returns a valid pointer to cifsFileInfo, FreeXid() prints rc=-13 whereas 0 is actually being returned. Fix this by setting rc before calling FreeXid(). Basically convert FreeXid(xid); rc = -ERR; return -ERR; => FreeXid(xid); return rc; [Note that Christoph would like to replace the GetXid/FreeXid calls, which are primarily used for debugging. This seems like a good longer term goal, but although there is an alternative tracing facility, there are no examples yet available that I know of that we can use (yet) to convert this cifs function entry/exit logging, and for creating an identifier that we can use to correlate all dmesg log entries for a particular vfs operation (ie identify all log entries for a particular vfs request to cifs: e.g. a particular close or read or write or byte range lock call ... and just using the thread id is harder). Eventually when a replacement for this is available (e.g. when NFS switches over and various samples to look at in other file systems) we can remove the GetXid/FreeXid macro but in the meantime multiple people use this run time configurable logging all the time for debugging, and Suresh's patch fixes a problem which made it harder to notice some low memory problems in the log so it is worthwhile to fix this problem until a better logging approach is able to be used] Acked-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de> Signed-off-by: Steve French <sfrench@us.ibm.com>
2009-06-25 16:42:34 +04:00
return rc;
}
/*
* Attempt to flush data before changing attributes. We need to do
* this for ATTR_SIZE and ATTR_MTIME for sure, and if we change the
* ownership or mode then we may also need to do this. Here, we take
* the safe way out and just do the flush on all setattr requests. If
* the flush returns error, store it to report later and continue.
*
* BB: This should be smarter. Why bother flushing pages that
* will be truncated anyway? Also, should we error out here if
* the flush returns error?
*/
rc = filemap_write_and_wait(inode->i_mapping);
mapping_set_error(inode->i_mapping, rc);
rc = 0;
[CIFS] Fix potential data corruption when writing out cached dirty pages Fix RedHat bug 329431 The idea here is separate "conscious" from "unconscious" flushes. Conscious flushes are those due to a fsync() or close(). Unconscious ones are flushes that occur as a side effect of some other operation or due to memory pressure. Currently, when an error occurs during an unconscious flush (ENOSPC or EIO), we toss out the page and don't preserve that error to report to the user when a conscious flush occurs. If after the unconscious flush, there are no more dirty pages for the inode, the conscious flush will simply return success even though there were previous errors when writing out pages. This can lead to data corruption. The easiest way to reproduce this is to mount up a CIFS share that's very close to being full or where the user is very close to quota. mv a file to the share that's slightly larger than the quota allows. The writes will all succeed (since they go to pagecache). The mv will do a setattr to set the new file's attributes. This calls filemap_write_and_wait, which will return an error since all of the pages can't be written out. Then later, when the flush and release ops occur, there are no more dirty pages in pagecache for the file and those operations return 0. mv then assumes that the file was written out correctly and deletes the original. CIFS already has a write_behind_rc variable where it stores the results from earlier flushes, but that value is only reported in cifs_close. Since the VFS ignores the return value from the release operation, this isn't helpful. We should be reporting this error during the flush operation. This patch does the following: 1) changes cifs_fsync to use filemap_write_and_wait and cifs_flush and also sync to check its return code. If it returns successful, they then check the value of write_behind_rc to see if an earlier flush had reported any errors. If so, they return that error and clear write_behind_rc. 2) sets write_behind_rc in a few other places where pages are written out as a side effect of other operations and the code waits on them. 3) changes cifs_setattr to only call filemap_write_and_wait for ATTR_SIZE changes. 4) makes cifs_writepages accurately distinguish between EIO and ENOSPC errors when writing out pages. Some simple testing indicates that the patch works as expected and that it fixes the reproduceable known problem. Acked-by: Dave Kleikamp <shaggy@austin.rr.com> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Steve French <sfrench@us.ibm.com>
2007-11-21 02:19:03 +03:00
if (attrs->ia_valid & ATTR_SIZE) {
rc = cifs_set_file_size(inode, attrs, xid, full_path);
if (rc != 0)
goto cifs_setattr_exit;
}
if (attrs->ia_valid & ATTR_UID)
uid = attrs->ia_uid;
if (attrs->ia_valid & ATTR_GID)
gid = attrs->ia_gid;
#ifdef CONFIG_CIFS_ACL
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
if (uid_valid(uid) || gid_valid(gid)) {
rc = id_mode_to_cifs_acl(inode, full_path, NO_CHANGE_64,
uid, gid);
if (rc) {
cifs_dbg(FYI, "%s: Setting id failed with error: %d\n",
__func__, rc);
goto cifs_setattr_exit;
}
}
} else
#endif /* CONFIG_CIFS_ACL */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID))
attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
/* skip mode change if it's just for clearing setuid/setgid */
if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
attrs->ia_valid &= ~ATTR_MODE;
if (attrs->ia_valid & ATTR_MODE) {
mode = attrs->ia_mode;
rc = 0;
#ifdef CONFIG_CIFS_ACL
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) {
rc = id_mode_to_cifs_acl(inode, full_path, mode,
INVALID_UID, INVALID_GID);
if (rc) {
cifs_dbg(FYI, "%s: Setting ACL failed with error: %d\n",
__func__, rc);
goto cifs_setattr_exit;
}
} else
#endif /* CONFIG_CIFS_ACL */
if (((mode & S_IWUGO) == 0) &&
(cifsInode->cifsAttrs & ATTR_READONLY) == 0) {
dosattr = cifsInode->cifsAttrs | ATTR_READONLY;
/* fix up mode if we're not using dynperm */
if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0)
attrs->ia_mode = inode->i_mode & ~S_IWUGO;
} else if ((mode & S_IWUGO) &&
(cifsInode->cifsAttrs & ATTR_READONLY)) {
dosattr = cifsInode->cifsAttrs & ~ATTR_READONLY;
/* Attributes of 0 are ignored */
if (dosattr == 0)
dosattr |= ATTR_NORMAL;
/* reset local inode permissions to normal */
if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
attrs->ia_mode &= ~(S_IALLUGO);
if (S_ISDIR(inode->i_mode))
attrs->ia_mode |=
cifs_sb->mnt_dir_mode;
else
attrs->ia_mode |=
cifs_sb->mnt_file_mode;
}
} else if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) {
/* ignore mode change - ATTR_READONLY hasn't changed */
attrs->ia_valid &= ~ATTR_MODE;
}
}
if (attrs->ia_valid & (ATTR_MTIME|ATTR_ATIME|ATTR_CTIME) ||
((attrs->ia_valid & ATTR_MODE) && dosattr)) {
rc = cifs_set_file_info(inode, attrs, xid, full_path, dosattr);
/* BB: check for rc = -EOPNOTSUPP and switch to legacy mode */
/* Even if error on time set, no sense failing the call if
the server would set the time to a reasonable value anyway,
and this check ensures that we are not being called from
sys_utimes in which case we ought to fail the call back to
the user when the server rejects the call */
if ((rc) && (attrs->ia_valid &
(ATTR_MODE | ATTR_GID | ATTR_UID | ATTR_SIZE)))
rc = 0;
}
/* do not need local check to inode_check_ok since the server does
that */
if (rc)
goto cifs_setattr_exit;
if ((attrs->ia_valid & ATTR_SIZE) &&
attrs->ia_size != i_size_read(inode))
truncate_setsize(inode, attrs->ia_size);
setattr_copy(inode, attrs);
mark_inode_dirty(inode);
cifs_setattr_exit:
kfree(full_path);
free_xid(xid);
return rc;
}
int
cifs_setattr(struct dentry *direntry, struct iattr *attrs)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *pTcon = cifs_sb_master_tcon(cifs_sb);
if (pTcon->unix_ext)
return cifs_setattr_unix(direntry, attrs);
return cifs_setattr_nounix(direntry, attrs);
/* BB: add cifs_setattr_legacy for really old servers */
}
#if 0
void cifs_delete_inode(struct inode *inode)
{
cifs_dbg(FYI, "In cifs_delete_inode, inode = 0x%p\n", inode);
/* may have to add back in if and when safe distributed caching of
directories added e.g. via FindNotify */
}
#endif