aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2008-12-31 15:57:56 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2008-12-31 15:57:56 -0800
commitb58602a4bac012b5f4fc12fe6b46ab237b610d5d (patch)
tree38929e210a723f67fe2b945f37264bf3aae3c2c4 /fs
parentdb200df0b3530f673d8e9f5bd535e9e10305842a (diff)
parent1f3403fa640f9f7b135dee79f2d39d01c8ad4a08 (diff)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (34 commits) nfsd race fixes: jfs nfsd race fixes: reiserfs nfsd race fixes: ext4 nfsd race fixes: ext3 nfsd race fixes: ext2 nfsd/create race fixes, infrastructure filesystem notification: create fs/notify to contain all fs notification fs/block_dev.c: __read_mostly improvement and sb_is_blkdev_sb utilization kill ->dir_notify() filp_cachep can be static in fs/file_table.c fix f_count description in Documentation/filesystems/files.txt make INIT_FS use the __RW_LOCK_UNLOCKED initialization take init_fs to saner place kill vfs_permission pass a struct path * to may_open kill walk_init_root remove incorrect comment in inode_permission expand some comments (d_path / seq_path) correct wrong function name of d_put in kernel document and source comment fix switch_names() breakage in short-to-short case ...
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig39
-rw-r--r--fs/Makefile5
-rw-r--r--fs/bad_inode.c6
-rw-r--r--fs/befs/linuxvfs.c5
-rw-r--r--fs/block_dev.c9
-rw-r--r--fs/cifs/Makefile2
-rw-r--r--fs/cifs/cifsfs.c7
-rw-r--r--fs/cifs/cifsfs.h1
-rw-r--r--fs/cifs/fcntl.c118
-rw-r--r--fs/dcache.c25
-rw-r--r--fs/dcookies.c28
-rw-r--r--fs/ecryptfs/inode.c3
-rw-r--r--fs/exec.c5
-rw-r--r--fs/ext2/ialloc.c6
-rw-r--r--fs/ext2/inode.c7
-rw-r--r--fs/ext2/namei.c15
-rw-r--r--fs/ext3/ialloc.c6
-rw-r--r--fs/ext3/inode.c7
-rw-r--r--fs/ext3/namei.c15
-rw-r--r--fs/ext4/ialloc.c6
-rw-r--r--fs/ext4/inode.c7
-rw-r--r--fs/ext4/namei.c14
-rw-r--r--fs/file_table.c10
-rw-r--r--fs/freevxfs/vxfs_inode.c4
-rw-r--r--fs/inode.c59
-rw-r--r--fs/jfs/jfs_inode.c29
-rw-r--r--fs/jfs/namei.c24
-rw-r--r--fs/namei.c115
-rw-r--r--fs/namespace.c2
-rw-r--r--fs/nfsctl.c5
-rw-r--r--fs/notify/Kconfig2
-rw-r--r--fs/notify/Makefile2
-rw-r--r--fs/notify/dnotify/Kconfig10
-rw-r--r--fs/notify/dnotify/Makefile1
-rw-r--r--fs/notify/dnotify/dnotify.c (renamed from fs/dnotify.c)3
-rw-r--r--fs/notify/inotify/Kconfig27
-rw-r--r--fs/notify/inotify/Makefile2
-rw-r--r--fs/notify/inotify/inotify.c (renamed from fs/inotify.c)0
-rw-r--r--fs/notify/inotify/inotify_user.c (renamed from fs/inotify_user.c)2
-rw-r--r--fs/open.c5
-rw-r--r--fs/reiserfs/inode.c15
-rw-r--r--fs/reiserfs/namei.c8
-rw-r--r--fs/seq_file.c10
-rw-r--r--fs/sysv/inode.c6
44 files changed, 385 insertions, 292 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index 522469a7eca..ff0e8198020 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -270,44 +270,7 @@ config OCFS2_COMPAT_JBD
endif # BLOCK
-config DNOTIFY
- bool "Dnotify support"
- default y
- help
- Dnotify is a directory-based per-fd file change notification system
- that uses signals to communicate events to user-space. There exist
- superior alternatives, but some applications may still rely on
- dnotify.
-
- If unsure, say Y.
-
-config INOTIFY
- bool "Inotify file change notification support"
- default y
- ---help---
- Say Y here to enable inotify support. Inotify is a file change
- notification system and a replacement for dnotify. Inotify fixes
- numerous shortcomings in dnotify and introduces several new features
- including multiple file events, one-shot support, and unmount
- notification.
-
- For more information, see <file:Documentation/filesystems/inotify.txt>
-
- If unsure, say Y.
-
-config INOTIFY_USER
- bool "Inotify support for userspace"
- depends on INOTIFY
- default y
- ---help---
- Say Y here to enable inotify support for userspace, including the
- associated system calls. Inotify allows monitoring of both files and
- directories via a single open fd. Events are read from the file
- descriptor, which is also select()- and poll()-able.
-
- For more information, see <file:Documentation/filesystems/inotify.txt>
-
- If unsure, say Y.
+source "fs/notify/Kconfig"
config QUOTA
bool "Quota support"
diff --git a/fs/Makefile b/fs/Makefile
index d9f8afe6f0c..e6f423d1d22 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -20,8 +20,7 @@ obj-y += no-block.o
endif
obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
-obj-$(CONFIG_INOTIFY) += inotify.o
-obj-$(CONFIG_INOTIFY_USER) += inotify_user.o
+obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
obj-$(CONFIG_ANON_INODES) += anon_inodes.o
obj-$(CONFIG_SIGNALFD) += signalfd.o
@@ -57,8 +56,6 @@ obj-$(CONFIG_QFMT_V1) += quota_v1.o
obj-$(CONFIG_QFMT_V2) += quota_v2.o
obj-$(CONFIG_QUOTACTL) += quota.o
-obj-$(CONFIG_DNOTIFY) += dnotify.o
-
obj-$(CONFIG_PROC_FS) += proc/
obj-y += partitions/
obj-$(CONFIG_SYSFS) += sysfs/
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 5f1538c03b1..a05287a23f6 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -132,11 +132,6 @@ static int bad_file_check_flags(int flags)
return -EIO;
}
-static int bad_file_dir_notify(struct file *file, unsigned long arg)
-{
- return -EIO;
-}
-
static int bad_file_flock(struct file *filp, int cmd, struct file_lock *fl)
{
return -EIO;
@@ -179,7 +174,6 @@ static const struct file_operations bad_file_ops =
.sendpage = bad_file_sendpage,
.get_unmapped_area = bad_file_get_unmapped_area,
.check_flags = bad_file_check_flags,
- .dir_notify = bad_file_dir_notify,
.flock = bad_file_flock,
.splice_write = bad_file_splice_write,
.splice_read = bad_file_splice_read,
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index b6dfee37c7b..d06cb023ad0 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -378,7 +378,8 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino)
inode->i_size = 0;
inode->i_blocks = befs_sb->block_size / VFS_BLOCK_SIZE;
strncpy(befs_ino->i_data.symlink, raw_inode->data.symlink,
- BEFS_SYMLINK_LEN);
+ BEFS_SYMLINK_LEN - 1);
+ befs_ino->i_data.symlink[BEFS_SYMLINK_LEN - 1] = '\0';
} else {
int num_blks;
@@ -477,6 +478,8 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd)
kfree(link);
befs_error(sb, "Failed to read entire long symlink");
link = ERR_PTR(-EIO);
+ } else {
+ link[len - 1] = '\0';
}
} else {
link = befs_ino->i_data.symlink;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 99e0ae1a4c7..349a26c1000 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -326,12 +326,13 @@ static struct file_system_type bd_type = {
.kill_sb = kill_anon_super,
};
-static struct vfsmount *bd_mnt __read_mostly;
-struct super_block *blockdev_superblock;
+struct super_block *blockdev_superblock __read_mostly;
void __init bdev_cache_init(void)
{
int err;
+ struct vfsmount *bd_mnt;
+
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD|SLAB_PANIC),
@@ -373,7 +374,7 @@ struct block_device *bdget(dev_t dev)
struct block_device *bdev;
struct inode *inode;
- inode = iget5_locked(bd_mnt->mnt_sb, hash(dev),
+ inode = iget5_locked(blockdev_superblock, hash(dev),
bdev_test, bdev_set, &dev);
if (!inode)
@@ -463,7 +464,7 @@ void bd_forget(struct inode *inode)
spin_lock(&bdev_lock);
if (inode->i_bdev) {
- if (inode->i_sb != blockdev_superblock)
+ if (!sb_is_blkdev_sb(inode->i_sb))
bdev = inode->i_bdev;
__bd_forget(inode);
}
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index 6ba43fb346f..9948c0030e8 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -5,7 +5,7 @@ obj-$(CONFIG_CIFS) += cifs.o
cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
link.o misc.o netmisc.o smbdes.o smbencrypt.o transport.o asn1.o \
- md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o fcntl.o \
+ md4.o md5.o cifs_unicode.o nterr.o xattr.o cifsencrypt.o \
readdir.o ioctl.o sess.o export.o cifsacl.o
cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 0005a194a75..13ea53251dc 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -747,7 +747,6 @@ const struct file_operations cifs_file_ops = {
#endif /* CONFIG_CIFS_POSIX */
#ifdef CONFIG_CIFS_EXPERIMENTAL
- .dir_notify = cifs_dir_notify,
.setlease = cifs_setlease,
#endif /* CONFIG_CIFS_EXPERIMENTAL */
};
@@ -768,7 +767,6 @@ const struct file_operations cifs_file_direct_ops = {
#endif /* CONFIG_CIFS_POSIX */
.llseek = cifs_llseek,
#ifdef CONFIG_CIFS_EXPERIMENTAL
- .dir_notify = cifs_dir_notify,
.setlease = cifs_setlease,
#endif /* CONFIG_CIFS_EXPERIMENTAL */
};
@@ -789,7 +787,6 @@ const struct file_operations cifs_file_nobrl_ops = {
#endif /* CONFIG_CIFS_POSIX */
#ifdef CONFIG_CIFS_EXPERIMENTAL
- .dir_notify = cifs_dir_notify,
.setlease = cifs_setlease,
#endif /* CONFIG_CIFS_EXPERIMENTAL */
};
@@ -809,7 +806,6 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
#endif /* CONFIG_CIFS_POSIX */
.llseek = cifs_llseek,
#ifdef CONFIG_CIFS_EXPERIMENTAL
- .dir_notify = cifs_dir_notify,
.setlease = cifs_setlease,
#endif /* CONFIG_CIFS_EXPERIMENTAL */
};
@@ -818,9 +814,6 @@ const struct file_operations cifs_dir_ops = {
.readdir = cifs_readdir,
.release = cifs_closedir,
.read = generic_read_dir,
-#ifdef CONFIG_CIFS_EXPERIMENTAL
- .dir_notify = cifs_dir_notify,
-#endif /* CONFIG_CIFS_EXPERIMENTAL */
.unlocked_ioctl = cifs_ioctl,
.llseek = generic_file_llseek,
};
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 2ce04c73d74..7ac481841f8 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -76,7 +76,6 @@ extern int cifs_file_mmap(struct file * , struct vm_area_struct *);
extern const struct file_operations cifs_dir_ops;
extern int cifs_dir_open(struct inode *inode, struct file *file);
extern int cifs_readdir(struct file *file, void *direntry, filldir_t filldir);
-extern int cifs_dir_notify(struct file *, unsigned long arg);
/* Functions related to dir entries */
extern struct dentry_operations cifs_dentry_ops;
diff --git a/fs/cifs/fcntl.c b/fs/cifs/fcntl.c
deleted file mode 100644
index 5a57581eb4b..00000000000
--- a/fs/cifs/fcntl.c
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- * fs/cifs/fcntl.c
- *
- * vfs operations that deal with the file control API
- *
- * Copyright (C) International Business Machines Corp., 2003,2004
- * 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 <linux/fcntl.h>
-#include "cifsglob.h"
-#include "cifsproto.h"
-#include "cifs_unicode.h"
-#include "cifs_debug.h"
-#include "cifsfs.h"
-
-static __u32 convert_to_cifs_notify_flags(unsigned long fcntl_notify_flags)
-{
- __u32 cifs_ntfy_flags = 0;
-
- /* No way on Linux VFS to ask to monitor xattr
- changes (and no stream support either */
- if (fcntl_notify_flags & DN_ACCESS)
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_LAST_ACCESS;
- if (fcntl_notify_flags & DN_MODIFY) {
- /* What does this mean on directories? */
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_LAST_WRITE |
- FILE_NOTIFY_CHANGE_SIZE;
- }
- if (fcntl_notify_flags & DN_CREATE) {
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_CREATION |
- FILE_NOTIFY_CHANGE_LAST_WRITE;
- }
- if (fcntl_notify_flags & DN_DELETE)
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_LAST_WRITE;
- if (fcntl_notify_flags & DN_RENAME) {
- /* BB review this - checking various server behaviors */
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_DIR_NAME |
- FILE_NOTIFY_CHANGE_FILE_NAME;
- }
- if (fcntl_notify_flags & DN_ATTRIB) {
- cifs_ntfy_flags |= FILE_NOTIFY_CHANGE_SECURITY |
- FILE_NOTIFY_CHANGE_ATTRIBUTES;
- }
-/* if (fcntl_notify_flags & DN_MULTISHOT) {
- cifs_ntfy_flags |= ;
- } */ /* BB fixme - not sure how to handle this with CIFS yet */
-
- return cifs_ntfy_flags;
-}
-
-int cifs_dir_notify(struct file *file, unsigned long arg)
-{
- int xid;
- int rc = -EINVAL;
- int oplock = 0;
- struct cifs_sb_info *cifs_sb;
- struct cifsTconInfo *pTcon;
- char *full_path = NULL;
- __u32 filter = FILE_NOTIFY_CHANGE_NAME | FILE_NOTIFY_CHANGE_ATTRIBUTES;
- __u16 netfid;
-
- if (experimEnabled == 0)
- return 0;
-
- xid = GetXid();
- cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
- pTcon = cifs_sb->tcon;
-
- full_path = build_path_from_dentry(file->f_path.dentry);
-
- if (full_path == NULL) {
- rc = -ENOMEM;
- } else {
- cFYI(1, ("dir notify on file %s Arg 0x%lx", full_path, arg));
- rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_OPEN,
- GENERIC_READ | SYNCHRONIZE, 0 /* create options */,
- &netfid, &oplock, NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
- /* BB fixme - add this handle to a notify handle list */
- if (rc) {
- cFYI(1, ("Could not open directory for notify"));
- } else {
- filter = convert_to_cifs_notify_flags(arg);
- if (filter != 0) {
- rc = CIFSSMBNotify(xid, pTcon,
- 0 /* no subdirs */, netfid,
- filter, file, arg & DN_MULTISHOT,
- cifs_sb->local_nls);
- } else {
- rc = -EINVAL;
- }
- /* BB add code to close file eventually (at unmount
- it would close automatically but may be a way
- to do it easily when inode freed or when
- notify info is cleared/changed */
- cFYI(1, ("notify rc %d", rc));
- }
- }
-
- FreeXid(xid);
- return rc;
-}
diff --git a/fs/dcache.c b/fs/dcache.c
index a1d86c7f3e6..e88c23b85a3 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -34,7 +34,6 @@
#include <linux/bootmem.h>
#include "internal.h"
-
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
@@ -948,9 +947,6 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
dentry->d_op = NULL;
dentry->d_fsdata = NULL;
dentry->d_mounted = 0;
-#ifdef CONFIG_PROFILING
- dentry->d_cookie = NULL;
-#endif
INIT_HLIST_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
@@ -1336,7 +1332,7 @@ err_out:
*
* Searches the children of the parent dentry for the name in question. If
* the dentry is found its reference count is incremented and the dentry
- * is returned. The caller must use d_put to free the entry when it has
+ * is returned. The caller must use dput to free the entry when it has
* finished using it. %NULL is returned on failure.
*
* __d_lookup is dcache_lock free. The hash list is protected using RCU.
@@ -1620,8 +1616,11 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
*/
memcpy(dentry->d_iname, target->d_name.name,
target->d_name.len + 1);
+ dentry->d_name.len = target->d_name.len;
+ return;
}
}
+ do_switch(dentry->d_name.len, target->d_name.len);
}
/*
@@ -1681,7 +1680,6 @@ already_unhashed:
/* Switch the names.. */
switch_names(dentry, target);
- do_switch(dentry->d_name.len, target->d_name.len);
do_switch(dentry->d_name.hash, target->d_name.hash);
/* ... and switch the parents */
@@ -1791,7 +1789,6 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
struct dentry *dparent, *aparent;
switch_names(dentry, anon);
- do_switch(dentry->d_name.len, anon->d_name.len);
do_switch(dentry->d_name.hash, anon->d_name.hash);
dparent = dentry->d_parent;
@@ -1911,7 +1908,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
* Convert a dentry into an ASCII path name. If the entry has been deleted
* the string " (deleted)" is appended. Note that this is ambiguous.
*
- * Returns the buffer or an error code if the path was too long.
+ * Returns a pointer into the buffer or an error code if the
+ * path was too long.
*
* "buflen" should be positive. Caller holds the dcache_lock.
*
@@ -1987,7 +1985,10 @@ Elong:
* Convert a dentry into an ASCII path name. If the entry has been deleted
* the string " (deleted)" is appended. Note that this is ambiguous.
*
- * Returns the buffer or an error code if the path was too long.
+ * Returns a pointer into the buffer or an error code if the path was
+ * too long. Note: Callers should use the returned pointer, not the passed
+ * in buffer, to use the name! The implementation often starts at an offset
+ * into the buffer, and may leave 0 bytes at the start.
*
* "buflen" should be positive.
*/
@@ -2313,9 +2314,6 @@ static void __init dcache_init(void)
/* SLAB cache for __getname() consumers */
struct kmem_cache *names_cachep __read_mostly;
-/* SLAB cache for file structures */
-struct kmem_cache *filp_cachep __read_mostly;
-
EXPORT_SYMBOL(d_genocide);
void __init vfs_caches_init_early(void)
@@ -2337,9 +2335,6 @@ void __init vfs_caches_init(unsigned long mempages)
names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
- filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-
dcache_init();
inode_init();
files_init(mempages);
diff --git a/fs/dcookies.c b/fs/dcookies.c
index 855d4b1d619..180e9fec4ad 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -93,10 +93,15 @@ static struct dcookie_struct *alloc_dcookie(struct path *path)
{
struct dcookie_struct *dcs = kmem_cache_alloc(dcookie_cache,
GFP_KERNEL);
+ struct dentry *d;
if (!dcs)
return NULL;
- path->dentry->d_cookie = dcs;
+ d = path->dentry;
+ spin_lock(&d->d_lock);
+ d->d_flags |= DCACHE_COOKIE;
+ spin_unlock(&d->d_lock);
+
dcs->path = *path;
path_get(path);
hash_dcookie(dcs);
@@ -119,14 +124,14 @@ int get_dcookie(struct path *path, unsigned long *cookie)
goto out;
}
- dcs = path->dentry->d_cookie;
-
- if (!dcs)
+ if (path->dentry->d_flags & DCACHE_COOKIE) {
+ dcs = find_dcookie((unsigned long)path->dentry);
+ } else {
dcs = alloc_dcookie(path);
-
- if (!dcs) {
- err = -ENOMEM;
- goto out;
+ if (!dcs) {
+ err = -ENOMEM;
+ goto out;
+ }
}
*cookie = dcookie_value(dcs);
@@ -251,7 +256,12 @@ out_kmem:
static void free_dcookie(struct dcookie_struct * dcs)
{
- dcs->path.dentry->d_cookie = NULL;
+ struct dentry *d = dcs->path.dentry;
+
+ spin_lock(&d->d_lock);
+ d->d_flags &= ~DCACHE_COOKIE;
+ spin_unlock(&d->d_lock);
+
path_put(&dcs->path);
kmem_cache_free(dcookie_cache, dcs);
}
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 89209f00f9c..5e78fc17988 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -673,10 +673,11 @@ static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd)
ecryptfs_printk(KERN_DEBUG, "Calling readlink w/ "
"dentry->d_name.name = [%s]\n", dentry->d_name.name);
rc = dentry->d_inode->i_op->readlink(dentry, (char __user *)buf, len);
- buf[rc] = '\0';
set_fs(old_fs);
if (rc < 0)
goto out_free;
+ else
+ buf[rc] = '\0';
rc = 0;
nd_set_link(nd, buf);
goto out;
diff --git a/fs/exec.c b/fs/exec.c
index 02d2e120542..dfbf7009fbe 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -127,7 +127,8 @@ asmlinkage long sys_uselib(const char __user * library)
if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
goto exit;
- error = vfs_permission(&nd, MAY_READ | MAY_EXEC | MAY_OPEN);
+ error = inode_permission(nd.path.dentry->d_inode,
+ MAY_READ | MAY_EXEC | MAY_OPEN);
if (error)
goto exit;
@@ -680,7 +681,7 @@ struct file *open_exec(const char *name)
if (nd.path.mnt->mnt_flags & MNT_NOEXEC)
goto out_path_put;
- err = vfs_permission(&nd, MAY_EXEC | MAY_OPEN);
+ err = inode_permission(nd.path.dentry->d_inode, MAY_EXEC | MAY_OPEN);
if (err)
goto out_path_put;
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 8d0add62587..c454d5db28a 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -585,7 +585,10 @@ got:
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
- insert_inode_hash(inode);
+ if (insert_inode_locked(inode) < 0) {
+ err = -EINVAL;
+ goto fail_drop;
+ }
if (DQUOT_ALLOC_INODE(inode)) {
err = -EDQUOT;
@@ -612,6 +615,7 @@ fail_drop:
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
+ unlock_new_inode(inode);
iput(inode);
return ERR_PTR(err);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 7658b33e265..02b39a5deb7 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -32,6 +32,7 @@
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/fiemap.h>
+#include <linux/namei.h>
#include "ext2.h"
#include "acl.h"
#include "xip.h"
@@ -1286,9 +1287,11 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
else
inode->i_mapping->a_ops = &ext2_aops;
} else if (S_ISLNK(inode->i_mode)) {
- if (ext2_inode_is_fast_symlink(inode))
+ if (ext2_inode_is_fast_symlink(inode)) {
inode->i_op = &ext2_fast_symlink_inode_operations;
- else {
+ nd_terminate_link(ei->i_data, inode->i_size,
+ sizeof(ei->i_data) - 1);
+ } else {
inode->i_op = &ext2_symlink_inode_operations;
if (test_opt(inode->i_sb, NOBH))
inode->i_mapping->a_ops = &ext2_nobh_aops;
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 2a747252ec1..90ea17998a7 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -41,9 +41,11 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
int err = ext2_add_link(dentry, inode);
if (!err) {
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
return 0;
}
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput(inode);
return err;
}
@@ -170,6 +172,7 @@ out:
out_fail:
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput (inode);
goto out;
}
@@ -178,6 +181,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
+ int err;
if (inode->i_nlink >= EXT2_LINK_MAX)
return -EMLINK;
@@ -186,7 +190,14 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
inode_inc_link_count(inode);
atomic_inc(&inode->i_count);
- return ext2_add_nondir(dentry, inode);
+ err = ext2_add_link(dentry, inode);
+ if (!err) {
+ d_instantiate(dentry, inode);
+ return 0;
+ }
+ inode_dec_link_count(inode);
+ iput(inode);
+ return err;
}
static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
@@ -222,12 +233,14 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, int mode)
goto out_fail;
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
out:
return err;
out_fail:
inode_dec_link_count(inode);
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput(inode);
out_dir:
inode_dec_link_count(dir);
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 490bd0ed789..5655fbcbd11 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -579,7 +579,10 @@ got:
ext3_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
- insert_inode_hash(inode);
+ if (insert_inode_locked(inode) < 0) {
+ err = -EINVAL;
+ goto fail_drop;
+ }
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
@@ -627,6 +630,7 @@ fail_drop:
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
+ unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index f8424ad8997..c4bdccf976b 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -37,6 +37,7 @@
#include <linux/uio.h>
#include <linux/bio.h>
#include <linux/fiemap.h>
+#include <linux/namei.h>
#include "xattr.h"
#include "acl.h"
@@ -2817,9 +2818,11 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino)
inode->i_op = &ext3_dir_inode_operations;
inode->i_fop = &ext3_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
- if (ext3_inode_is_fast_symlink(inode))
+ if (ext3_inode_is_fast_symlink(inode)) {
inode->i_op = &ext3_fast_symlink_inode_operations;
- else {
+ nd_terminate_link(ei->i_data, inode->i_size,
+ sizeof(ei->i_data) - 1);
+ } else {
inode->i_op = &ext3_symlink_inode_operations;
ext3_set_aops(inode);
}
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 3e5edc92aa0..297ea8dfac7 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1652,9 +1652,11 @@ static int ext3_add_nondir(handle_t *handle,
if (!err) {
ext3_mark_inode_dirty(handle, inode);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
return 0;
}
drop_nlink(inode);
+ unlock_new_inode(inode);
iput(inode);
return err;
}
@@ -1765,6 +1767,7 @@ retry:
dir_block = ext3_bread (handle, inode, 0, 1, &err);
if (!dir_block) {
drop_nlink(inode); /* is this nlink == 0? */
+ unlock_new_inode(inode);
ext3_mark_inode_dirty(handle, inode);
iput (inode);
goto out_stop;
@@ -1792,6 +1795,7 @@ retry:
err = ext3_add_entry (handle, dentry, inode);
if (err) {
inode->i_nlink = 0;
+ unlock_new_inode(inode);
ext3_mark_inode_dirty(handle, inode);
iput (inode);
goto out_stop;
@@ -1800,6 +1804,7 @@ retry:
ext3_update_dx_flag(dir);
ext3_mark_inode_dirty(handle, dir);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
out_stop:
ext3_journal_stop(handle);
if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
@@ -2174,6 +2179,7 @@ retry:
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
if (err) {
drop_nlink(inode);
+ unlock_new_inode(inode);
ext3_mark_inode_dirty(handle, inode);
iput (inode);
goto out_stop;
@@ -2221,7 +2227,14 @@ retry:
inc_nlink(inode);
atomic_inc(&inode->i_count);
- err = ext3_add_nondir(handle, dentry, inode);
+ err = ext3_add_entry(handle, dentry, inode);
+ if (!err) {
+ ext3_mark_inode_dirty(handle, inode);
+ d_instantiate(dentry, inode);
+ } else {
+ drop_nlink(inode);
+ iput(inode);
+ }
ext3_journal_stop(handle);
if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
goto retry;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 08cac9fcace..6e6052879aa 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -826,7 +826,10 @@ got:
ext4_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
- insert_inode_hash(inode);
+ if (insert_inode_locked(inode) < 0) {
+ err = -EINVAL;
+ goto fail_drop;
+ }
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
@@ -881,6 +884,7 @@ fail_drop:
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
+ unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index be21a5ae33c..7c3325e0b00 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -34,6 +34,7 @@
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/mpage.h>
+#include <linux/namei.h>
#include <linux/uio.h>
#include <linux/bio.h>
#include "ext4_jbd2.h"
@@ -4164,9 +4165,11 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
inode->i_op = &ext4_dir_inode_operations;
inode->i_fop = &ext4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
- if (ext4_inode_is_fast_symlink(inode))
+ if (ext4_inode_is_fast_symlink(inode)) {
inode->i_op = &ext4_fast_symlink_inode_operations;
- else {
+ nd_terminate_link(ei->i_data, inode->i_size,
+ sizeof(ei->i_data) - 1);
+ } else {
inode->i_op = &ext4_symlink_inode_operations;
ext4_set_aops(inode);
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 63adcb79298..da98a9012fa 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1693,9 +1693,11 @@ static int ext4_add_nondir(handle_t *handle,
if (!err) {
ext4_mark_inode_dirty(handle, inode);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
return 0;
}
drop_nlink(inode);
+ unlock_new_inode(inode);
iput(inode);
return err;
}
@@ -1830,6 +1832,7 @@ retry:
if (err) {
out_clear_inode:
clear_nlink(inode);
+ unlock_new_inode(inode);
ext4_mark_inode_dirty(handle, inode);
iput(inode);
goto out_stop;
@@ -1838,6 +1841,7 @@ out_clear_inode:
ext4_update_dx_flag(dir);
ext4_mark_inode_dirty(handle, dir);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
out_stop:
ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
@@ -2212,6 +2216,7 @@ retry:
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
if (err) {
clear_nlink(inode);
+ unlock_new_inode(inode);
ext4_mark_inode_dirty(handle, inode);
iput(inode);
goto out_stop;
@@ -2262,7 +2267,14 @@ retry:
ext4_inc_count(handle, inode);
atomic_inc(&inode->i_count);
- err = ext4_add_nondir(handle, dentry, inode);
+ err = ext4_add_entry(handle, dentry, inode);
+ if (!err) {
+ ext4_mark_inode_dirty(handle, inode);
+ d_instantiate(dentry, inode);
+ } else {
+ drop_nlink(inode);
+ iput(inode);
+ }
ext4_journal_stop(handle);
if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
goto retry;
diff --git a/fs/file_table.c b/fs/file_table.c
index 0fbcacc3ea7..bbeeac6efa1 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -32,6 +32,9 @@ struct files_stat_struct files_stat = {
/* public. Not pretty! */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock);
+/* SLAB cache for file structures */
+static struct kmem_cache *filp_cachep __read_mostly;
+
static struct percpu_counter nr_files __cacheline_aligned_in_smp;
static inline void file_free_rcu(struct rcu_head *head)
@@ -397,7 +400,12 @@ too_bad:
void __init files_init(unsigned long mempages)
{
int n;
- /* One file with associated inode and dcache is very roughly 1K.
+
+ filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+
+ /*
+ * One file with associated inode and dcache is very roughly 1K.
* Per default don't use more than 10% of our memory for files.
*/
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index 9f3f2ceb73f..03a6ea5e99f 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -325,8 +325,10 @@ vxfs_iget(struct super_block *sbp, ino_t ino)
if (!VXFS_ISIMMED(vip)) {
ip->i_op = &page_symlink_inode_operations;
ip->i_mapping->a_ops = &vxfs_aops;
- } else
+ } else {
ip->i_op = &vxfs_immed_symlink_iops;
+ vip->vii_immed.vi_immed[ip->i_size] = '\0';
+ }
} else
init_special_inode(ip, ip->i_mode, old_decode_dev(vip->vii_rdev));
diff --git a/fs/inode.c b/fs/inode.c
index 098a2443196..7de1cda9248 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1032,6 +1032,65 @@ struct inode *iget_locked(struct super_block *sb, unsigned long ino)
EXPORT_SYMBOL(iget_locked);
+int insert_inode_locked(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+ ino_t ino = inode->i_ino;
+ struct hlist_head *head = inode_hashtable + hash(sb, ino);
+ struct inode *old;
+
+ inode->i_state |= I_LOCK|I_NEW;
+ while (1) {
+ spin_lock(&inode_lock);
+ old = find_inode_fast(sb, head, ino);
+ if (likely(!old)) {
+ hlist_add_head(&inode->i_hash, head);
+ spin_unlock(&inode_lock);
+ return 0;
+ }
+ __iget(old);
+ spin_unlock(&inode_lock);
+ wait_on_inode(old);
+ if (unlikely(!hlist_unhashed(&old->i_hash))) {
+ iput(old);
+ return -EBUSY;
+ }
+ iput(old);
+ }
+}
+
+EXPORT_SYMBOL(insert_inode_locked);
+
+int insert_inode_locked4(struct inode *inode, unsigned long hashval,
+ int (*test)(struct inode *, void *), void *data)
+{
+ struct super_block *sb = inode->i_sb;
+ struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+ struct inode *old;
+
+ inode->i_state |= I_LOCK|I_NEW;
+
+ while (1) {
+ spin_lock(&inode_lock);
+ old = find_inode(sb, head, test, data);
+ if (likely(!old)) {
+ hlist_add_head(&inode->i_hash, head);
+ spin_unlock(&inode_lock);
+ return 0;
+ }
+ __iget(old);
+ spin_unlock(&inode_lock);
+ wait_on_inode(old);
+ if (unlikely(!hlist_unhashed(&old->i_hash))) {
+ iput(old);
+ return -EBUSY;
+ }
+ iput(old);
+ }
+}
+
+EXPORT_SYMBOL(insert_inode_locked4);
+
/**
* __insert_inode_hash - hash an inode
* @inode: unhashed inode
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 70022fd1c53..d4d142c2edd 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -79,7 +79,8 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
inode = new_inode(sb);
if (!inode) {
jfs_warn("ialloc: new_inode returned NULL!");
- return ERR_PTR(-ENOMEM);
+ rc = -ENOMEM;
+ goto fail;
}
jfs_inode = JFS_IP(inode);
@@ -89,8 +90,12 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
jfs_warn("ialloc: diAlloc returned %d!", rc);
if (rc == -EIO)
make_bad_inode(inode);
- iput(inode);
- return ERR_PTR(rc);
+ goto fail_put;
+ }
+
+ if (insert_inode_locked(inode) < 0) {
+ rc = -EINVAL;
+ goto fail_unlock;
}
inode->i_uid = current_fsuid();
@@ -112,11 +117,8 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
* Allocate inode to quota.
*/
if (DQUOT_ALLOC_INODE(inode)) {
- DQUOT_DROP(inode);
- inode->i_flags |= S_NOQUOTA;
- inode->i_nlink = 0;
- iput(inode);
- return ERR_PTR(-EDQUOT);
+ rc = -EDQUOT;
+ goto fail_drop;
}
inode->i_mode = mode;
@@ -158,4 +160,15 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
jfs_info("ialloc returns inode = 0x%p\n", inode);
return inode;
+
+fail_drop:
+ DQUOT_DROP(inode);
+ inode->i_flags |= S_NOQUOTA;
+fail_unlock:
+ inode->i_nlink = 0;
+ unlock_new_inode(inode);
+fail_put:
+ iput(inode);
+fail:
+ return ERR_PTR(rc);
}
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index cc3cedffbfa..b4de56b851e 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -155,7 +155,6 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, int mode,
ip->i_fop = &jfs_file_operations;
ip->i_mapping->a_ops = &jfs_aops;
- insert_inode_hash(ip);
mark_inode_dirty(ip);
dip->i_ctime = dip->i_mtime = CURRENT_TIME;
@@ -171,9 +170,12 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, int mode,
if (rc) {
free_ea_wmap(ip);
ip->i_nlink = 0;
+ unlock_new_inode(ip);
iput(ip);
- } else
+ } else {
d_instantiate(dentry, ip);
+ unlock_new_inode(ip);
+ }
out2:
free_UCSname(&dname);
@@ -289,7 +291,6 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode)
ip->i_op = &jfs_dir_inode_operations;
ip->i_fop = &jfs_dir_operations;
- insert_inode_hash(ip);
mark_inode_dirty(ip);
/* update parent directory inode */
@@ -306,9 +307,12 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode)
if (rc) {
free_ea_wmap(ip);
ip->i_nlink = 0;
+ unlock_new_inode(ip);
iput(ip);
- } else
+ } else {
d_instantiate(dentry, ip);
+ unlock_new_inode(ip);
+ }
out2:
free_UCSname(&dname);
@@ -1019,7 +1023,6 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
goto out3;
}
- insert_inode_hash(ip);
mark_inode_dirty(ip);
dip->i_ctime = dip->i_mtime = CURRENT_TIME;
@@ -1039,9 +1042,12 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
if (rc) {
free_ea_wmap(ip);
ip->i_nlink = 0;
+ unlock_new_inode(ip);
iput(ip);
- } else
+ } else {
d_instantiate(dentry, ip);
+ unlock_new_inode(ip);
+ }
out2:
free_UCSname(&dname);
@@ -1399,7 +1405,6 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
jfs_ip->dev = new_encode_dev(rdev);
init_special_inode(ip, ip->i_mode, rdev);
- insert_inode_hash(ip);
mark_inode_dirty(ip);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
@@ -1417,9 +1422,12 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
if (rc) {
free_ea_wmap(ip);
ip->i_nlink = 0;
+ unlock_new_inode(ip);
iput(ip);
- } else
+ } else {
d_instantiate(dentry, ip);
+ unlock_new_inode(ip);
+ }
out1:
free_UCSname(&dname);
diff --git a/fs/namei.c b/fs/namei.c
index af3783fff1d..dd5c9f0bf82 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -226,6 +226,16 @@ int generic_permission(struct inode *inode, int mask,
return -EACCES;
}
+/**
+ * inode_permission - check for access rights to a given inode
+ * @inode: inode to check permission on
+ * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ *
+ * Used to check for read/write/execute permissions on an inode.
+ * We use "fsuid" for this, letting us set arbitrary permissions
+ * for filesystem access without changing the "normal" uids which
+ * are used for other things.
+ */
int inode_permission(struct inode *inode, int mask)
{
int retval;
@@ -247,7 +257,6 @@ int inode_permission(struct inode *inode, int mask)
return -EACCES;
}
- /* Ordinary permission routines do not understand MAY_APPEND. */
if (inode->i_op && inode->i_op->permission)
retval = inode->i_op->permission(inode, mask);
else
@@ -265,21 +274,6 @@ int inode_permission(struct inode *inode, int mask)
}
/**
- * vfs_permission - check for access rights to a given path
- * @nd: lookup result that describes the path
- * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
- *
- * Used to check for read/write/execute permissions on a path.
- * We use "fsuid" for this, letting us set arbitrary permissions
- * for filesystem access without changing the "normal" uids which
- * are used for other things.
- */
-int vfs_permission(struct nameidata *nd, int mask)
-{
- return inode_permission(nd->path.dentry->d_inode, mask);
-}
-
-/**
* file_permission - check for additional access rights to a given file
* @file: file to check access rights for
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
@@ -289,7 +283,7 @@ int vfs_permission(struct nameidata *nd, int mask)
*
* Note:
* Do not use this function in new code. All access checks should
- * be done using vfs_permission().
+ * be done using inode_permission().
*/
int file_permission(struct file *file, int mask)
{
@@ -527,18 +521,6 @@ out_unlock:
return result;
}
-/* SMP-safe */
-static __always_inline void
-walk_init_root(const char *name, struct nameidata *nd)
-{
- struct fs_struct *fs = current->fs;
-
- read_lock(&fs->lock);
- nd->path = fs->root;
- path_get(&fs->root);
- read_unlock(&fs->lock);
-}
-
/*
* Wrapper to retry pathname resolution whenever the underlying
* file system returns an ESTALE.
@@ -576,9 +558,16 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l
goto fail;
if (*link == '/') {
+ struct fs_struct *fs = current->fs;
+
path_put(&nd->path);
- walk_init_root(link, nd);
+
+ read_lock(&fs->lock);
+ nd->path = fs->root;
+ path_get(&fs->root);
+ read_unlock(&fs->lock);
}
+
res = link_path_walk(link, nd);
if (nd->depth || res || nd->last_type!=LAST_NORM)
return res;
@@ -859,7 +848,8 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
nd->flags |= LOOKUP_CONTINUE;
err = exec_permission_lite(inode);
if (err == -EAGAIN)
- err = vfs_permission(nd, MAY_EXEC);
+ err = inode_permission(nd->path.dentry->d_inode,
+ MAY_EXEC);
if (err)
break;
@@ -1493,9 +1483,9 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
return error;
}
-int may_open(struct nameidata *nd, int acc_mode, int flag)
+int may_open(struct path *path, int acc_mode, int flag)
{
- struct dentry *dentry = nd->path.dentry;
+ struct dentry *dentry = path->dentry;
struct inode *inode = dentry->d_inode;
int error;
@@ -1516,13 +1506,13 @@ int may_open(struct nameidata *nd, int acc_mode, int flag)
if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
flag &= ~O_TRUNC;
} else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) {
- if (nd->path.mnt->mnt_flags & MNT_NODEV)
+ if (path->mnt->mnt_flags & MNT_NODEV)
return -EACCES;
flag &= ~O_TRUNC;
}
- error = vfs_permission(nd, acc_mode);
+ error = inode_permission(inode, acc_mode);
if (error)
return error;
/*
@@ -1556,6 +1546,9 @@ int may_open(struct nameidata *nd, int acc_mode, int flag)
* Refuse to truncate files with mandatory locks held on them.
*/
error = locks_verify_locked(inode);
+ if (!error)
+ error = security_path_truncate(path, 0,
+ ATTR_MTIME|ATTR_CTIME|ATTR_OPEN);
if (!error) {
DQUOT_INIT(inode);
@@ -1586,14 +1579,18 @@ static int __open_namei_create(struct nameidata *nd, struct path *path,
if (!IS_POSIXACL(dir->d_inode))
mode &= ~current->fs->umask;
+ error = security_path_mknod(&nd->path, path->dentry, mode, 0);
+ if (error)
+ goto out_unlock;
error = vfs_create(dir->d_inode, path->dentry, mode, nd);
+out_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
dput(nd->path.dentry);
nd->path.dentry = path->dentry;
if (error)
return error;
/* Don't check for write permission, don't truncate */
- return may_open(nd, 0, flag & ~O_TRUNC);
+ return may_open(&nd->path, 0, flag & ~O_TRUNC);
}
/*
@@ -1779,7 +1776,7 @@ ok:
if (error)
goto exit;
}
- error = may_open(&nd, acc_mode, flag);
+ error = may_open(&nd.path, acc_mode, flag);
if (error) {
if (will_write)
mnt_drop_write(nd.path.mnt);
@@ -1999,6 +1996,9 @@ asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
error = mnt_want_write(nd.path.mnt);
if (error)
goto out_dput;
+ error = security_path_mknod(&nd.path, dentry, mode, dev);
+ if (error)
+ goto out_drop_write;
switch (mode & S_IFMT) {
case 0: case S_IFREG:
error = vfs_create(nd.path.dentry->d_inode,dentry,mode,&nd);
@@ -2011,6 +2011,7 @@ asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,0);
break;
}
+out_drop_write:
mnt_drop_write(nd.path.mnt);
out_dput:
dput(dentry);
@@ -2070,7 +2071,11 @@ asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode)
error = mnt_want_write(nd.path.mnt);
if (error)
goto out_dput;
+ error = security_path_mkdir(&nd.path, dentry, mode);
+ if (error)
+ goto out_drop_write;
error = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
+out_drop_write:
mnt_drop_write(nd.path.mnt);
out_dput:
dput(dentry);
@@ -2180,7 +2185,11 @@ static long do_rmdir(int dfd, const char __user *pathname)
error = mnt_want_write(nd.path.mnt);
if (error)
goto exit3;
+ error = security_path_rmdir(&nd.path, dentry);
+ if (error)
+ goto exit4;
error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
+exit4:
mnt_drop_write(nd.path.mnt);
exit3:
dput(dentry);
@@ -2265,7 +2274,11 @@ static long do_unlinkat(int dfd, const char __user *pathname)
error = mnt_want_write(nd.path.mnt);
if (error)
goto exit2;
+ error = security_path_unlink(&nd.path, dentry);
+ if (error)
+ goto exit3;
error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+exit3:
mnt_drop_write(nd.path.mnt);
exit2:
dput(dentry);
@@ -2346,7 +2359,11 @@ asmlinkage long sys_symlinkat(const char __user *oldname,
error = mnt_want_write(nd.path.mnt);
if (error)
goto out_dput;
+ error = security_path_symlink(&nd.path, dentry, from);
+ if (error)
+ goto out_drop_write;
error = vfs_symlink(nd.path.dentry->d_inode, dentry, from);
+out_drop_write:
mnt_drop_write(nd.path.mnt);
out_dput:
dput(dentry);
@@ -2443,7 +2460,11 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
error = mnt_want_write(nd.path.mnt);
if (error)
goto out_dput;
+ error = security_path_link(old_path.dentry, &nd.path, new_dentry);
+ if (error)
+ goto out_drop_write;
error = vfs_link(old_path.dentry, nd.path.dentry->d_inode, new_dentry);
+out_drop_write:
mnt_drop_write(nd.path.mnt);
out_dput:
dput(new_dentry);
@@ -2679,8 +2700,13 @@ asmlinkage long sys_renameat(int olddfd, const char __user *oldname,
error = mnt_want_write(oldnd.path.mnt);
if (error)
goto exit5;
+ error = security_path_rename(&oldnd.path, old_dentry,
+ &newnd.path, new_dentry);
+ if (error)
+ goto exit6;
error = vfs_rename(old_dir->d_inode, old_dentry,
new_dir->d_inode, new_dentry);
+exit6:
mnt_drop_write(oldnd.path.mnt);
exit5:
dput(new_dentry);
@@ -2750,13 +2776,16 @@ int vfs_follow_link(struct nameidata *nd, const char *link)
/* get the link contents into pagecache */
static char *page_getlink(struct dentry * dentry, struct page **ppage)
{
- struct page * page;
+ char *kaddr;
+ struct page *page;
struct address_space *mapping = dentry->d_inode->i_mapping;
page = read_mapping_page(mapping, 0, NULL);
if (IS_ERR(page))
return (char*)page;
*ppage = page;
- return kmap(page);
+ kaddr = kmap(page);
+ nd_terminate_link(kaddr, dentry->d_inode->i_size, PAGE_SIZE - 1);
+ return kaddr;
}
int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
@@ -2849,7 +2878,6 @@ EXPORT_SYMBOL(path_lookup);
EXPORT_SYMBOL(kern_path);
EXPORT_SYMBOL(vfs_path_lookup);
EXPORT_SYMBOL(inode_permission);
-EXPORT_SYMBOL(vfs_permission);
EXPORT_SYMBOL(file_permission);
EXPORT_SYMBOL(unlock_rename);
EXPORT_SYMBOL(vfs_create);
@@ -2865,3 +2893,10 @@ EXPORT_SYMBOL(vfs_symlink);
EXPORT_SYMBOL(vfs_unlink);
EXPORT_SYMBOL(dentry_unhash);
EXPORT_SYMBOL(generic_readlink);
+
+/* to be mentioned only in INIT_TASK */
+struct fs_struct init_fs = {
+ .count = ATOMIC_INIT(1),
+ .lock = __RW_LOCK_UNLOCKED(init_fs.lock),
+ .umask = 0022,
+};
diff --git a/fs/namespace.c b/fs/namespace.c
index 1c09cab8f7c..a40685d800a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1990,7 +1990,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
if (!new_ns->root) {
up_write(&namespace_sem);
kfree(new_ns);
- return ERR_PTR(-ENOMEM);;
+ return ERR_PTR(-ENOMEM);
}
spin_lock(&vfsmount_lock);
list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
diff --git a/fs/nfsctl.c b/fs/nfsctl.c
index b1acbd6ab6f..b27451909df 100644
--- a/fs/nfsctl.c
+++ b/fs/nfsctl.c
@@ -38,9 +38,10 @@ static struct file *do_open(char *name, int flags)
return ERR_PTR(error);
if (flags == O_RDWR)
- error = may_open(&nd,MAY_READ|MAY_WRITE,FMODE_READ|FMODE_WRITE);
+ error = may_open(&nd.path, MAY_READ|MAY_WRITE,
+ FMODE_READ|FMODE_WRITE);
else
- error = may_open(&nd, MAY_WRITE, FMODE_WRITE);
+ error = may_open(&nd.path, MAY_WRITE, FMODE_WRITE);
if (!error)
return dentry_open(nd.path.dentry, nd.path.mnt, flags,
diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
new file mode 100644
index 00000000000..50914d7303c
--- /dev/null
+++ b/fs/notify/Kconfig
@@ -0,0 +1,2 @@
+source "fs/notify/dnotify/Kconfig"
+source "fs/notify/inotify/Kconfig"
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
new file mode 100644
index 00000000000..5a95b6010ce
--- /dev/null
+++ b/fs/notify/Makefile
@@ -0,0 +1,2 @@
+obj-y += dnotify/
+obj-y += inotify/
diff --git a/fs/notify/dnotify/Kconfig b/fs/notify/dnotify/Kconfig
new file mode 100644
index 00000000000..26adf5dfa64
--- /dev/null
+++ b/fs/notify/dnotify/Kconfig
@@ -0,0 +1,10 @@
+config DNOTIFY
+ bool "Dnotify support"
+ default y
+ help
+ Dnotify is a directory-based per-fd file change notification system
+ that uses signals to communicate events to user-space. There exist
+ superior alternatives, but some applications may still rely on
+ dnotify.
+
+ If unsure, say Y.
diff --git a/fs/notify/dnotify/Makefile b/fs/notify/dnotify/Makefile
new file mode 100644
index 00000000000..f145251dcad
--- /dev/null
+++ b/fs/notify/dnotify/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_DNOTIFY) += dnotify.o
diff --git a/fs/dnotify.c b/fs/notify/dnotify/dnotify.c
index 676073b8dda..b0aa2cde80b 100644
--- a/fs/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -115,9 +115,6 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
dn->dn_next = inode->i_dnotify;
inode->i_dnotify = dn;
spin_unlock(&inode->i_lock);
-
- if (filp->f_op && filp->f_op->dir_notify)
- return filp->f_op->dir_notify(filp, arg);
return 0;
out_free:
diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig
new file mode 100644
index 00000000000..44679284102
--- /dev/null
+++ b/fs/notify/inotify/Kconfig
@@ -0,0 +1,27 @@
+config INOTIFY
+ bool "Inotify file change notification support"
+ default y
+ ---help---
+ Say Y here to enable inotify support. Inotify is a file change
+ notification system and a replacement for dnotify. Inotify fixes
+ numerous shortcomings in dnotify and introduces several new features
+ including multiple file events, one-shot support, and unmount
+ notification.
+
+ For more information, see <file:Documentation/filesystems/inotify.txt>
+
+ If unsure, say Y.
+
+config INOTIFY_USER
+ bool "Inotify support for userspace"
+ depends on INOTIFY
+ default y
+ ---help---
+ Say Y here to enable inotify support for userspace, including the
+ associated system calls. Inotify allows monitoring of both files and
+ directories via a single open fd. Events are read from the file
+ descriptor, which is also select()- and poll()-able.
+
+ For more information, see <file:Documentation/filesystems/inotify.txt>
+
+ If unsure, say Y.
diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile
new file mode 100644
index 00000000000..e290f3bb9d8
--- /dev/null
+++ b/fs/notify/inotify/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_INOTIFY) += inotify.o
+obj-$(CONFIG_INOTIFY_USER) += inotify_user.o
diff --git a/fs/inotify.c b/fs/notify/inotify/inotify.c
index dae3f28f30d..dae3f28f30d 100644
--- a/fs/inotify.c
+++ b/fs/notify/inotify/inotify.c
diff --git a/fs/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e2425bbd871..400f8064a54 100644
--- a/fs/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -76,10 +76,10 @@ struct inotify_device {
struct mutex ev_mutex; /* protects event queue */
struct mutex up_mutex; /* synchronizes watch updates */
struct list_head events; /* list of queued events */
- atomic_t count; /* reference count */
struct user_struct *user; /* user who opened this dev */
struct inotify_handle *ih; /* inotify handle */
struct fasync_struct *fa; /* async notification */
+ atomic_t count; /* reference count */
unsigned int queue_size; /* size of the queue (bytes) */
unsigned int event_count; /* number of pending events */
unsigned int max_events; /* maximum number of events */
diff --git a/fs/open.c b/fs/open.c
index c0a426d5766..1cd7d40e999 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -272,6 +272,8 @@ static long do_sys_truncate(const char __user *pathname, loff_t length)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
+ if (!error)
+ error = security_path_truncate(&path, length, 0);
if (!error) {
DQUOT_INIT(inode);
error = do_truncate(path.dentry, length, 0, NULL);
@@ -329,6 +331,9 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
error = locks_verify_truncate(inode, file, length);
if (!error)
+ error = security_path_truncate(&file->f_path, length,
+ ATTR_MTIME|ATTR_CTIME);
+ if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
out_putf:
fput(file);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 6c4c2c69449..145c2d3e5e0 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -1753,6 +1753,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
struct inode *inode)
{
struct super_block *sb;
+ struct reiserfs_iget_args args;
INITIALIZE_PATH(path_to_key);
struct cpu_key key;
struct item_head ih;
@@ -1780,6 +1781,14 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
err = -ENOMEM;
goto out_bad_inode;
}
+ args.objectid = inode->i_ino = le32_to_cpu(ih.ih_key.k_objectid);
+ memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE);
+ args.dirid = le32_to_cpu(ih.ih_key.k_dir_id);
+ if (insert_inode_locked4(inode, args.objectid,
+ reiserfs_find_actor, &args) < 0) {
+ err = -EINVAL;
+ goto out_bad_inode;
+ }
if (old_format_only(sb))
/* not a perfect generation count, as object ids can be reused, but
** this is as good as reiserfs can do right now.
@@ -1859,13 +1868,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
} else {
inode2sd(&sd, inode, inode->i_size);
}
- // these do not go to on-disk stat data
- inode->i_ino = le32_to_cpu(ih.ih_key.k_objectid);
-
// store in in-core inode the key of stat data and version all
// object items will have (directory items will have old offset
// format, other new objects will consist of new items)
- memcpy(INODE_PKEY(inode), &(ih.ih_key), KEY_SIZE);
if (old_format_only(sb) || S_ISDIR(mode) || S_ISLNK(mode))
set_inode_item_key_version(inode, KEY_FORMAT_3_5);
else
@@ -1929,7 +1934,6 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
reiserfs_mark_inode_private(inode);
}
- insert_inode_hash(inode);
reiserfs_update_sd(th, inode);
reiserfs_check_path(&path_to_key);
@@ -1956,6 +1960,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
out_inserted_sd:
inode->i_nlink = 0;
th->t_trans_id = 0; /* so the caller can't use this handle later */
+ unlock_new_inode(inode); /* OK to do even if we hadn't locked it */
/* If we were inheriting an ACL, we need to release the lock so that
* iput doesn't deadlock in reiserfs_delete_xattrs. The locking
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 4f322e5ed84..738967f6c8e 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -646,6 +646,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, int mode,
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
retval = err;
+ unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
@@ -653,6 +654,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, int mode,
reiserfs_update_inode_transaction(dir);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
retval = journal_end(&th, dir->i_sb, jbegin_count);
out_failed:
@@ -727,11 +729,13 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, int mode,
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
retval = err;
+ unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
retval = journal_end(&th, dir->i_sb, jbegin_count);
out_failed:
@@ -812,6 +816,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
err = journal_end(&th, dir->i_sb, jbegin_count);
if (err)
retval = err;
+ unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
@@ -819,6 +824,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
reiserfs_update_sd(&th, dir);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
retval = journal_end(&th, dir->i_sb, jbegin_count);
out_failed:
if (locked)
@@ -1096,11 +1102,13 @@ static int reiserfs_symlink(struct inode *parent_dir,
err = journal_end(&th, parent_dir->i_sb, jbegin_count);
if (err)
retval = err;
+ unlock_new_inode(inode);
iput(inode);
goto out_failed;
}
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
retval = journal_end(&th, parent_dir->i_sb, jbegin_count);
out_failed:
reiserfs_write_unlock(parent_dir->i_sb);
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 16c211558c2..99d8b8cfc9b 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -389,8 +389,14 @@ char *mangle_path(char *s, char *p, char *esc)
}
EXPORT_SYMBOL(mangle_path);
-/*
- * return the absolute path of 'dentry' residing in mount 'mnt'.
+/**
+ * seq_path - seq_file interface to print a pathname
+ * @m: the seq_file handle
+ * @path: the struct path to print
+ * @esc: set of characters to escape in the output
+ *
+ * return the absolute path of 'path', as represented by the
+ * dentry / mnt pair in the path parameter.
*/
int seq_path(struct seq_file *m, struct path *path, char *esc)
{
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index df0d435baa4..3d81bf58dae 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -27,6 +27,7 @@
#include <linux/init.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
+#include <linux/namei.h>
#include <asm/byteorder.h>
#include "sysv.h"
@@ -163,8 +164,11 @@ void sysv_set_inode(struct inode *inode, dev_t rdev)
if (inode->i_blocks) {
inode->i_op = &sysv_symlink_inode_operations;
inode->i_mapping->a_ops = &sysv_aops;
- } else
+ } else {
inode->i_op = &sysv_fast_symlink_inode_operations;
+ nd_terminate_link(SYSV_I(inode)->i_data, inode->i_size,
+ sizeof(SYSV_I(inode)->i_data) - 1);
+ }
} else
init_special_inode(inode, inode->i_mode, rdev);
}