Merge branch 'lineage-16.0' of https://github.com/z3ntu/android_kernel_fairphone_msm8974 into lineage-16.0
Change-Id: Ie34580e6571b5e89476b76c6d461a3b2bb0db3f7
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index d5a269a..7248c52 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -9,7 +9,7 @@
--------------------------- dentry_operations --------------------------
prototypes:
- int (*d_revalidate)(struct dentry *, struct nameidata *);
+ int (*d_revalidate)(struct dentry *, unsigned int);
int (*d_hash)(const struct dentry *, const struct inode *,
struct qstr *);
int (*d_compare)(const struct dentry *, const struct inode *,
@@ -37,9 +37,8 @@
--------------------------- inode_operations ---------------------------
prototypes:
- int (*create) (struct inode *,struct dentry *,umode_t, struct nameidata *);
- struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameid
-ata *);
+ int (*create) (struct inode *,struct dentry *,umode_t, bool);
+ struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -63,6 +62,10 @@
void (*truncate_range)(struct inode *, loff_t, loff_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
void (*update_time)(struct inode *, struct timespec *, int);
+ int (*atomic_open)(struct inode *, struct dentry *,
+ struct file *, unsigned open_flag,
+ umode_t create_mode, int *opened);
+ int (*tmpfile) (struct inode *, struct dentry *, umode_t);
locking rules:
all may block
@@ -91,6 +94,8 @@
truncate_range: yes
fiemap: no
update_time: no
+atomic_open: yes
+tmpfile: no
Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
victim.
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 74acd96..88cf1b9 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -435,3 +435,14 @@
d_alloc_root() is gone, along with a lot of bugs caused by code
misusing it. Replacement: d_make_root(inode). The difference is,
d_make_root() drops the reference to inode if dentry allocation fails.
+
+--
+[mandatory]
+ The witch is dead! Well, 2/3 of it, anyway. ->d_revalidate() and
+->lookup() do *not* take struct nameidata anymore; just the flags.
+--
+[mandatory]
+ ->create() doesn't take struct nameidata *; unlike the previous
+two, it gets "is it an O_EXCL or equivalent?" boolean argument. Note that
+local filesystems can ignore tha argument - they are guaranteed that the
+object doesn't exist. It's remote/distributed ones that might care...
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index b2aa722..8a0b032 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -341,8 +341,8 @@
filesystem. As of kernel 2.6.22, the following members are defined:
struct inode_operations {
- int (*create) (struct inode *,struct dentry *, umode_t, struct nameidata *);
- struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+ int (*create) (struct inode *,struct dentry *, umode_t, bool);
+ struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -365,6 +365,9 @@
int (*removexattr) (struct dentry *, const char *);
void (*truncate_range)(struct inode *, loff_t, loff_t);
void (*update_time)(struct inode *, struct timespec *, int);
+ int (*atomic_open)(struct inode *, struct dentry *, struct file *,
+ unsigned open_flag, umode_t create_mode, int *opened);
+ int (*tmpfile) (struct inode *, struct dentry *, umode_t);
};
Again, all methods are called without any locks being held, unless
@@ -480,6 +483,19 @@
an inode. If this is not defined the VFS will update the inode itself
and call mark_inode_dirty_sync.
+ atomic_open: called on the last component of an open. Using this optional
+ method the filesystem can look up, possibly create and open the file in
+ one atomic operation. If it cannot perform this (e.g. the file type
+ turned out to be wrong) it may signal this by returning 1 instead of
+ usual 0 or -ve . This method is only called if the last component is
+ negative or needs lookup. Cached positive dentries are still handled by
+ f_op->open(). If the file was created, the FILE_CREATED flag should be
+ set in "opened". In case of O_EXCL the method must only succeed if the
+ file didn't exist and hence FILE_CREATED shall always be set on success.
+
+ tmpfile: called in the end of O_TMPFILE open(). Optional, equivalent to
+ atomically creating, opening and unlinking a file in given directory.
+
The Address Space Object
========================
@@ -888,7 +904,7 @@
defined:
struct dentry_operations {
- int (*d_revalidate)(struct dentry *, struct nameidata *);
+ int (*d_revalidate)(struct dentry *, unsigned int);
int (*d_hash)(const struct dentry *, const struct inode *,
struct qstr *);
int (*d_compare)(const struct dentry *, const struct inode *,
@@ -907,11 +923,11 @@
dcache. Most filesystems leave this as NULL, because all their
dentries in the dcache are valid
- d_revalidate may be called in rcu-walk mode (nd->flags & LOOKUP_RCU).
+ d_revalidate may be called in rcu-walk mode (flags & LOOKUP_RCU).
If in rcu-walk mode, the filesystem must revalidate the dentry without
blocking or storing to the dentry, d_parent and d_inode should not be
- used without care (because they can go NULL), instead nd->inode should
- be used.
+ used without care (because they can change and, in d_inode case, even
+ become NULL under us).
If a situation is encountered that rcu-walk cannot handle, return
-ECHILD and it will be called again in ref-walk mode.
diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index 9330fba..7580554 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -32,6 +32,8 @@
- nr_open
- overflowuid
- overflowgid
+- protected_hardlinks
+- protected_symlinks
- pipe-user-pages-hard
- pipe-user-pages-soft
- suid_dumpable
@@ -180,6 +182,46 @@
==============================================================
+protected_hardlinks:
+
+A long-standing class of security issues is the hardlink-based
+time-of-check-time-of-use race, most commonly seen in world-writable
+directories like /tmp. The common method of exploitation of this flaw
+is to cross privilege boundaries when following a given hardlink (i.e. a
+root process follows a hardlink created by another user). Additionally,
+on systems without separated partitions, this stops unauthorized users
+from "pinning" vulnerable setuid/setgid files against being upgraded by
+the administrator, or linking to special files.
+
+When set to "0", hardlink creation behavior is unrestricted.
+
+When set to "1" hardlinks cannot be created by users if they do not
+already own the source file, or do not have read/write access to it.
+
+This protection is based on the restrictions in Openwall and grsecurity.
+
+==============================================================
+
+protected_symlinks:
+
+A long-standing class of security issues is the symlink-based
+time-of-check-time-of-use race, most commonly seen in world-writable
+directories like /tmp. The common method of exploitation of this flaw
+is to cross privilege boundaries when following a given symlink (i.e. a
+root process follows a symlink belonging to another user). For a likely
+incomplete list of hundreds of examples across the years, please see:
+http://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=/tmp
+
+When set to "0", symlink following behavior is unrestricted.
+
+When set to "1" symlinks are permitted to be followed only when outside
+a sticky world-writable directory, or when the uid of the symlink and
+follower match, or when the directory owner matches the symlink's owner.
+
+This protection is based on the restrictions in Openwall and grsecurity.
+
+==============================================================
+
suid_dumpable:
This value can be used to query and set the core dump mode for setuid
diff --git a/arch/alpha/include/asm/fcntl.h b/arch/alpha/include/asm/fcntl.h
index 6d9e805..09f49a6 100644
--- a/arch/alpha/include/asm/fcntl.h
+++ b/arch/alpha/include/asm/fcntl.h
@@ -32,6 +32,7 @@
#define O_SYNC (__O_SYNC|O_DSYNC)
#define O_PATH 040000000
+#define __O_TMPFILE 0100000000
#define F_GETLK 7
#define F_SETLK 8
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 49ee319..bb15f2b 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -289,7 +289,7 @@
{
int retval;
struct cdfs_args tmp;
- char *devname;
+ struct filename *devname;
retval = -EFAULT;
if (copy_from_user(&tmp, args, sizeof(tmp)))
@@ -298,7 +298,7 @@
retval = PTR_ERR(devname);
if (IS_ERR(devname))
goto out;
- retval = do_mount(devname, dirname, "ext2", flags, NULL);
+ retval = do_mount(devname->name, dirname, "ext2", flags, NULL);
putname(devname);
out:
return retval;
@@ -309,7 +309,7 @@
{
int retval;
struct cdfs_args tmp;
- char *devname;
+ struct filename *devname;
retval = -EFAULT;
if (copy_from_user(&tmp, args, sizeof(tmp)))
@@ -318,7 +318,7 @@
retval = PTR_ERR(devname);
if (IS_ERR(devname))
goto out;
- retval = do_mount(devname, dirname, "iso9660", flags, NULL);
+ retval = do_mount(devname->name, dirname, "iso9660", flags, NULL);
putname(devname);
out:
return retval;
@@ -339,7 +339,7 @@
int, flag, void __user *, data)
{
int retval;
- char *name;
+ struct filename *name;
name = getname(path);
retval = PTR_ERR(name);
@@ -347,13 +347,13 @@
goto out;
switch (typenr) {
case 1:
- retval = osf_ufs_mount(name, data, flag);
+ retval = osf_ufs_mount(name->name, data, flag);
break;
case 6:
- retval = osf_cdfs_mount(name, data, flag);
+ retval = osf_cdfs_mount(name->name, data, flag);
break;
case 9:
- retval = osf_procfs_mount(name, data, flag);
+ retval = osf_procfs_mount(name->name, data, flag);
break;
default:
retval = -EINVAL;
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index 76cbb05..38c97d0 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -67,13 +67,13 @@
const char __user *const __user *envp, struct pt_regs *regs)
{
int error;
- char * filename;
+ struct filename *filename;
filename = getname(filenamei);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
out:
return error;
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 92c5af9..1bb0a8a 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -388,14 +388,14 @@
struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname(ufilename);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, uargv, uenvp, regs);
+ error = do_execve(filename->name, uargv, uenvp, regs);
putname(filename);
out:
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index c0f4fe2..0c412da 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -211,14 +211,14 @@
const char __user *const __user *envp)
{
int error;
- char *filename;
+ struct filename *filename;
struct pt_regs *regs = (struct pt_regs *)((&name) + 6);
filename = getname(name);
error = PTR_ERR(filename);
if (IS_ERR(filename))
return error;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
return error;
}
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index bee8df4..15ac715 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -212,14 +212,14 @@
struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname(fname);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
out:
return error;
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index 0570e8c..4e99922 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -224,7 +224,7 @@
struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname(fname);
error = PTR_ERR(filename);
@@ -232,7 +232,7 @@
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
out:
return error;
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 0e9c315..b40d346 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -214,14 +214,14 @@
int dummy, ...)
{
int error;
- char * filename;
+ struct filename *filename;
struct pt_regs *regs = (struct pt_regs *) ((unsigned char *)&dummy-4);
filename = getname(name);
error = PTR_ERR(filename);
if (IS_ERR(filename))
return error;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
return error;
}
diff --git a/arch/hexagon/kernel/syscall.c b/arch/hexagon/kernel/syscall.c
index 2fd0764..ef3756a 100644
--- a/arch/hexagon/kernel/syscall.c
+++ b/arch/hexagon/kernel/syscall.c
@@ -40,7 +40,7 @@
const char __user *const __user *envp)
{
struct pt_regs *pregs = current_thread_info()->regs;
- char *filename;
+ struct filename *filename;
int retval;
filename = getname(ufilename);
@@ -48,7 +48,7 @@
if (IS_ERR(filename))
return retval;
- retval = do_execve(filename, argv, envp, pregs);
+ retval = do_execve(filename->name, argv, envp, pregs);
putname(filename);
return retval;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index ce74e14..7babeed 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -633,14 +633,14 @@
const char __user *const __user *envp,
struct pt_regs *regs)
{
- char *fname;
+ struct filename *fname;
int error;
fname = getname(filename);
error = PTR_ERR(fname);
if (IS_ERR(fname))
goto out;
- error = do_execve(fname, argv, envp, regs);
+ error = do_execve(fname->name, argv, envp, regs);
putname(fname);
out:
return error;
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 3a4a32b..02f8b37 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -293,14 +293,14 @@
unsigned long r6, struct pt_regs regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname(ufilename);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, uargv, uenvp, ®s);
+ error = do_execve(filename->name, uargv, uenvp, ®s);
putname(filename);
out:
return error;
diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c
index e5b154f..404c0f2 100644
--- a/arch/microblaze/kernel/sys_microblaze.c
+++ b/arch/microblaze/kernel/sys_microblaze.c
@@ -54,13 +54,13 @@
struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname(filenamei);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
out:
return error;
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 922a554..3a21ace 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -83,13 +83,13 @@
asmlinkage int sys32_execve(nabi_no_regargs struct pt_regs regs)
{
int error;
- char * filename;
+ struct filename *filename;
filename = getname(compat_ptr(regs.regs[4]));
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = compat_do_execve(filename, compat_ptr(regs.regs[5]),
+ error = compat_do_execve(filename->name, compat_ptr(regs.regs[5]),
compat_ptr(regs.regs[6]), ®s);
putname(filename);
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index b08220c..2bd561b 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -133,13 +133,13 @@
asmlinkage int sys_execve(nabi_no_regargs struct pt_regs regs)
{
int error;
- char * filename;
+ struct filename *filename;
filename = getname((const char __user *) (long)regs.regs[4]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *) (long)regs.regs[5],
(const char __user *const __user *) (long)regs.regs[6],
®s);
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 55210f3..c35f3ab 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -271,7 +271,7 @@
struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname(name);
error = PTR_ERR(filename);
@@ -279,7 +279,7 @@
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
out:
diff --git a/arch/parisc/hpux/fs.c b/arch/parisc/hpux/fs.c
index 0dc8543..1573fc0 100644
--- a/arch/parisc/hpux/fs.c
+++ b/arch/parisc/hpux/fs.c
@@ -34,14 +34,14 @@
int hpux_execve(struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname((const char __user *) regs->gr[26]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *) regs->gr[25],
(const char __user *const __user *) regs->gr[24],
regs);
diff --git a/arch/parisc/include/asm/fcntl.h b/arch/parisc/include/asm/fcntl.h
index 0304b92..34a46cb 100644
--- a/arch/parisc/include/asm/fcntl.h
+++ b/arch/parisc/include/asm/fcntl.h
@@ -20,6 +20,7 @@
#define O_INVISIBLE 004000000 /* invisible I/O, for DMAPI/XDSM */
#define O_PATH 020000000
+#define __O_TMPFILE 040000000
#define F_GETLK64 8
#define F_SETLK64 9
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index d4b94b3..3821f1c 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -339,13 +339,13 @@
asmlinkage int sys_execve(struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname((const char __user *) regs->gr[26]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *) regs->gr[25],
(const char __user *const __user *) regs->gr[24],
regs);
diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c
index dc9a624..bf5b93a 100644
--- a/arch/parisc/kernel/sys_parisc32.c
+++ b/arch/parisc/kernel/sys_parisc32.c
@@ -60,14 +60,14 @@
asmlinkage int sys32_execve(struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
DBG(("sys32_execve(%p) r26 = 0x%lx\n", regs, regs->gr[26]));
filename = getname((const char __user *) regs->gr[26]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = compat_do_execve(filename, compat_ptr(regs->gr[25]),
+ error = compat_do_execve(filename->name, compat_ptr(regs->gr[25]),
compat_ptr(regs->gr[24]), regs);
putname(filename);
out:
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 5665dcc..5b7d8ff 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -70,7 +70,7 @@
ret = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
ret = spufs_create(&path, dentry, flags, mode, neighbor);
- path_put(&path);
+ done_path_create(&path, dentry);
}
return ret;
diff --git a/arch/score/kernel/sys_score.c b/arch/score/kernel/sys_score.c
index e478bf9..86e8d29 100644
--- a/arch/score/kernel/sys_score.c
+++ b/arch/score/kernel/sys_score.c
@@ -92,14 +92,14 @@
score_execve(struct pt_regs *regs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname((char __user*)regs->regs[4]);
error = PTR_ERR(filename);
if (IS_ERR(filename))
return error;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *)regs->regs[5],
(const char __user *const __user *)regs->regs[6],
regs);
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 94273aa..1b69859 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -302,14 +302,14 @@
{
struct pt_regs *regs = RELOC_HIDE(&__regs, 0);
int error;
- char *filename;
+ struct filename *filename;
filename = getname(ufilename);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, uargv, uenvp, regs);
+ error = do_execve(filename->name, uargv, uenvp, regs);
putname(filename);
out:
return error;
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index 4264583..1d68866 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -490,14 +490,14 @@
struct pt_regs *pregs)
{
int error;
- char *filename;
+ struct filename *filename;
filename = getname((char __user *)ufilename);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *)uargv,
(const char __user *const __user *)uenvp,
pregs);
diff --git a/arch/sparc/include/asm/fcntl.h b/arch/sparc/include/asm/fcntl.h
index d0b83f6..7e8ace5 100644
--- a/arch/sparc/include/asm/fcntl.h
+++ b/arch/sparc/include/asm/fcntl.h
@@ -35,6 +35,7 @@
#define O_SYNC (__O_SYNC|O_DSYNC)
#define O_PATH 0x1000000
+#define __O_TMPFILE 0x2000000
#define F_GETOWN 5 /* for sockets. */
#define F_SETOWN 6 /* for sockets. */
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index efa0754..091b7a4 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -625,7 +625,7 @@
asmlinkage int sparc_execve(struct pt_regs *regs)
{
int error, base = 0;
- char *filename;
+ struct filename *filename;
/* Check for indirect call. */
if(regs->u_regs[UREG_G1] == 0)
@@ -635,7 +635,7 @@
error = PTR_ERR(filename);
if(IS_ERR(filename))
goto out;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *)
regs->u_regs[base + UREG_I1],
(const char __user *const __user *)
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index aff0c72..fcaa594 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -722,7 +722,7 @@
asmlinkage int sparc_execve(struct pt_regs *regs)
{
int error, base = 0;
- char *filename;
+ struct filename *filename;
/* User register window flush is done by entry.S */
@@ -734,7 +734,7 @@
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename,
+ error = do_execve(filename->name,
(const char __user *const __user *)
regs->u_regs[base + UREG_I1],
(const char __user *const __user *)
diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index 29c478f..3d2fc19 100644
--- a/arch/sparc/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
@@ -403,7 +403,7 @@
asmlinkage long sparc32_execve(struct pt_regs *regs)
{
int error, base = 0;
- char *filename;
+ struct filename *filename;
/* User register window flush is done by entry.S */
@@ -416,7 +416,7 @@
if (IS_ERR(filename))
goto out;
- error = compat_do_execve(filename,
+ error = compat_do_execve(filename->name,
compat_ptr(regs->u_regs[base + UREG_I1]),
compat_ptr(regs->u_regs[base + UREG_I2]), regs);
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 54e6c64..026d975 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -619,13 +619,13 @@
struct pt_regs *, regs)
{
long error;
- char *filename;
+ struct filename *filename;
filename = getname(path);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
if (error == 0)
single_step_execve();
@@ -640,13 +640,13 @@
struct pt_regs *regs)
{
long error;
- char *filename;
+ struct filename *filename;
filename = getname(path);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = compat_do_execve(filename, argv, envp, regs);
+ error = compat_do_execve(filename->name, argv, envp, regs);
putname(filename);
if (error == 0)
single_step_execve();
diff --git a/arch/unicore32/kernel/sys.c b/arch/unicore32/kernel/sys.c
index 3afe60a..04d6464 100644
--- a/arch/unicore32/kernel/sys.c
+++ b/arch/unicore32/kernel/sys.c
@@ -51,13 +51,13 @@
struct pt_regs *regs)
{
int error;
- char *fn;
+ struct filename *fn;
fn = getname(filename);
error = PTR_ERR(fn);
if (IS_ERR(fn))
goto out;
- error = do_execve(fn, argv, envp, regs);
+ error = do_execve(fn->name, argv, envp, regs);
putname(fn);
out:
return error;
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 6a2d6ed..2312ca5 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -322,13 +322,13 @@
struct pt_regs *regs)
{
long error;
- char * filename;
+ struct filename *filename;
filename = getname(name);
error = PTR_ERR(filename);
if (IS_ERR(filename))
goto out;
- error = do_execve(filename, argv, envp, regs);
+ error = do_execve(filename->name, argv, envp, regs);
putname(filename);
out:
return error;
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 25af06d..0ea96b0 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -156,9 +156,7 @@
if (!err)
/* mark as kernel-created inode */
dentry->d_inode->i_private = &thread;
- dput(dentry);
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
+ done_path_create(&path, dentry);
return err;
}
@@ -218,10 +216,7 @@
/* mark as kernel-created inode */
dentry->d_inode->i_private = &thread;
}
- dput(dentry);
-
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
+ done_path_create(&path, dentry);
return err;
}
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index e78956c..34c59f1 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -144,7 +144,7 @@
extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nameidata);
+ unsigned int flags);
extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index d529437..64600b5 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -100,13 +100,13 @@
}
}
-static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct p9_fid *fid;
struct inode *inode;
struct v9fs_inode *v9inode;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 014c8dd..d2364b2 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -712,88 +712,34 @@
}
/**
- * v9fs_vfs_create - VFS hook to create files
+ * v9fs_vfs_create - VFS hook to create a regular file
+ *
+ * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called
+ * for mknod(2).
+ *
* @dir: directory inode that is being created
* @dentry: dentry that is being deleted
* @mode: create permissions
- * @nd: path information
*
*/
static int
v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- int err;
- u32 perm;
- int flags;
- struct file *filp;
- struct v9fs_inode *v9inode;
- struct v9fs_session_info *v9ses;
- struct p9_fid *fid, *inode_fid;
+ struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
+ u32 perm = unixmode2p9mode(v9ses, mode);
+ struct p9_fid *fid;
- err = 0;
- fid = NULL;
- v9ses = v9fs_inode2v9ses(dir);
- perm = unixmode2p9mode(v9ses, mode);
- if (nd)
- flags = nd->intent.open.flags;
- else
- flags = O_RDWR;
-
- fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
- v9fs_uflags2omode(flags,
- v9fs_proto_dotu(v9ses)));
- if (IS_ERR(fid)) {
- err = PTR_ERR(fid);
- fid = NULL;
- goto error;
- }
+ /* P9_OEXCL? */
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
v9fs_invalidate_inode_attr(dir);
- /* if we are opening a file, assign the open fid to the file */
- if (nd) {
- v9inode = V9FS_I(dentry->d_inode);
- mutex_lock(&v9inode->v_mutex);
- if (v9ses->cache && !v9inode->writeback_fid &&
- ((flags & O_ACCMODE) != O_RDONLY)) {
- /*
- * clone a fid and add it to writeback_fid
- * we do it during open time instead of
- * page dirty time via write_begin/page_mkwrite
- * because we want write after unlink usecase
- * to work.
- */
- inode_fid = v9fs_writeback_fid(dentry);
- if (IS_ERR(inode_fid)) {
- err = PTR_ERR(inode_fid);
- mutex_unlock(&v9inode->v_mutex);
- goto error;
- }
- v9inode->writeback_fid = (void *) inode_fid;
- }
- mutex_unlock(&v9inode->v_mutex);
- filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
- if (IS_ERR(filp)) {
- err = PTR_ERR(filp);
- goto error;
- }
-
- filp->private_data = fid;
-#ifdef CONFIG_9P_FSCACHE
- if (v9ses->cache)
- v9fs_cache_inode_set_cookie(dentry->d_inode, filp);
-#endif
- } else
- p9_client_clunk(fid);
+ p9_client_clunk(fid);
return 0;
-
-error:
- if (fid)
- p9_client_clunk(fid);
-
- return err;
}
/**
@@ -839,7 +785,7 @@
*/
struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nameidata)
+ unsigned int flags)
{
struct dentry *res;
struct super_block *sb;
@@ -849,8 +795,8 @@
char *name;
int result = 0;
- p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p nameidata: %p\n",
- dir, dentry->d_name.name, dentry, nameidata);
+ p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n",
+ dir, dentry->d_name.name, dentry, flags);
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
@@ -910,6 +856,86 @@
return ERR_PTR(result);
}
+static int
+v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
+{
+ int err;
+ u32 perm;
+ struct v9fs_inode *v9inode;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid, *inode_fid;
+ struct dentry *res = NULL;
+
+ if (d_unhashed(dentry)) {
+ res = v9fs_vfs_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || dentry->d_inode)
+ return finish_no_open(file, res);
+
+ err = 0;
+ fid = NULL;
+ v9ses = v9fs_inode2v9ses(dir);
+ perm = unixmode2p9mode(v9ses, mode);
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
+ v9fs_uflags2omode(flags,
+ v9fs_proto_dotu(v9ses)));
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ fid = NULL;
+ goto error;
+ }
+
+ v9fs_invalidate_inode_attr(dir);
+ v9inode = V9FS_I(dentry->d_inode);
+ mutex_lock(&v9inode->v_mutex);
+ if (v9ses->cache && !v9inode->writeback_fid &&
+ ((flags & O_ACCMODE) != O_RDONLY)) {
+ /*
+ * clone a fid and add it to writeback_fid
+ * we do it during open time instead of
+ * page dirty time via write_begin/page_mkwrite
+ * because we want write after unlink usecase
+ * to work.
+ */
+ inode_fid = v9fs_writeback_fid(dentry);
+ if (IS_ERR(inode_fid)) {
+ err = PTR_ERR(inode_fid);
+ mutex_unlock(&v9inode->v_mutex);
+ goto error;
+ }
+ v9inode->writeback_fid = (void *) inode_fid;
+ }
+ mutex_unlock(&v9inode->v_mutex);
+ err = finish_open(file, dentry, generic_file_open, opened);
+ if (err)
+ goto error;
+
+ file->private_data = fid;
+#ifdef CONFIG_9P_FSCACHE
+ if (v9ses->cache)
+ v9fs_cache_inode_set_cookie(dentry->d_inode, file);
+#endif
+
+ *opened |= FILE_CREATED;
+out:
+ dput(res);
+ return err;
+
+error:
+ if (fid)
+ p9_client_clunk(fid);
+ goto out;
+}
+
/**
* v9fs_vfs_unlink - VFS unlink hook to delete an inode
* @i: inode that is being unlinked
@@ -1488,6 +1514,7 @@
static const struct inode_operations v9fs_dir_inode_operations_dotu = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
+ .atomic_open = v9fs_vfs_atomic_open,
.symlink = v9fs_vfs_symlink,
.link = v9fs_vfs_link,
.unlink = v9fs_vfs_unlink,
@@ -1502,6 +1529,7 @@
static const struct inode_operations v9fs_dir_inode_operations = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
+ .atomic_open = v9fs_vfs_atomic_open,
.unlink = v9fs_vfs_unlink,
.mkdir = v9fs_vfs_mkdir,
.rmdir = v9fs_vfs_rmdir,
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index a86a78d..3d53bc2 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -248,20 +248,25 @@
* @dir: directory inode that is being created
* @dentry: dentry that is being deleted
* @mode: create permissions
- * @nd: path information
*
*/
static int
v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
- struct nameidata *nd)
+ bool excl)
+{
+ return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
+}
+
+static int
+v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t omode,
+ int *opened)
{
int err = 0;
gid_t gid;
- int flags;
umode_t mode;
char *name = NULL;
- struct file *filp;
struct p9_qid qid;
struct inode *inode;
struct p9_fid *fid = NULL;
@@ -269,18 +274,22 @@
struct p9_fid *dfid, *ofid, *inode_fid;
struct v9fs_session_info *v9ses;
struct posix_acl *pacl = NULL, *dacl = NULL;
+ struct dentry *res = NULL;
+
+ if (d_unhashed(dentry)) {
+ res = v9fs_vfs_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || dentry->d_inode)
+ return finish_no_open(file, res);
v9ses = v9fs_inode2v9ses(dir);
- if (nd)
- flags = nd->intent.open.flags;
- else {
- /*
- * create call without LOOKUP_OPEN is due
- * to mknod of regular files. So use mknod
- * operation.
- */
- return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
- }
name = (char *) dentry->d_name.name;
p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
@@ -290,7 +299,7 @@
if (IS_ERR(dfid)) {
err = PTR_ERR(dfid);
p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
- return err;
+ goto out;
}
/* clone a fid to use for creation */
@@ -298,7 +307,7 @@
if (IS_ERR(ofid)) {
err = PTR_ERR(ofid);
p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
- return err;
+ goto out;
}
gid = v9fs_get_fsgid_for_create(dir);
@@ -363,17 +372,18 @@
}
mutex_unlock(&v9inode->v_mutex);
/* Since we are opening a file, assign the open fid to the file */
- filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
- if (IS_ERR(filp)) {
- err = PTR_ERR(filp);
+ err = finish_open(file, dentry, generic_file_open, opened);
+ if (err)
goto err_clunk_old_fid;
- }
- filp->private_data = ofid;
+ file->private_data = ofid;
#ifdef CONFIG_9P_FSCACHE
if (v9ses->cache)
- v9fs_cache_inode_set_cookie(inode, filp);
+ v9fs_cache_inode_set_cookie(inode, file);
#endif
- return 0;
+ *opened |= FILE_CREATED;
+out:
+ dput(res);
+ return err;
error:
if (fid)
@@ -382,7 +392,7 @@
if (ofid)
p9_client_clunk(ofid);
v9fs_set_create_acl(NULL, &dacl, &pacl);
- return err;
+ goto out;
}
/**
@@ -1000,6 +1010,7 @@
const struct inode_operations v9fs_dir_inode_operations_dotl = {
.create = v9fs_vfs_create_dotl,
+ .atomic_open = v9fs_vfs_atomic_open_dotl,
.lookup = v9fs_vfs_lookup,
.link = v9fs_vfs_link_dotl,
.symlink = v9fs_vfs_symlink_dotl,
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 3d83075a..b3be2e7 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -266,7 +266,7 @@
};
static struct dentry *
-adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode = NULL;
struct object_info obj;
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 45a0ce4..3a48293 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -154,9 +154,9 @@
/* namei.c */
extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len);
-extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *);
+extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
extern int affs_unlink(struct inode *dir, struct dentry *dentry);
-extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *);
+extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool);
extern int affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
extern int affs_rmdir(struct inode *dir, struct dentry *dentry);
extern int affs_link(struct dentry *olddentry, struct inode *dir,
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 4780694..ff65884 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -211,7 +211,7 @@
}
struct dentry *
-affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct buffer_head *bh;
@@ -255,7 +255,7 @@
}
int
-affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e22dc4b..db47790 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -20,16 +20,16 @@
#include "internal.h"
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
static int afs_dir_open(struct inode *inode, struct file *file);
static int afs_readdir(struct file *file, void *dirent, filldir_t filldir);
-static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd);
+static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
static int afs_d_delete(const struct dentry *dentry);
static void afs_d_release(struct dentry *dentry);
static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
loff_t fpos, u64 ino, unsigned dtype);
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd);
+ bool excl);
static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
static int afs_rmdir(struct inode *dir, struct dentry *dentry);
static int afs_unlink(struct inode *dir, struct dentry *dentry);
@@ -516,7 +516,7 @@
* look up an entry in a directory
*/
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct afs_vnode *vnode;
struct afs_fid fid;
@@ -598,7 +598,7 @@
* - NOTE! the hit can be a negative hit too, so we can't assume we have an
* inode
*/
-static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct afs_vnode *vnode, *dir;
struct afs_fid uninitialized_var(fid);
@@ -607,7 +607,7 @@
void *dir_version;
int ret;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
vnode = AFS_FS_I(dentry->d_inode);
@@ -949,7 +949,7 @@
* create a regular file on an AFS filesystem
*/
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct afs_file_status status;
struct afs_callback cb;
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 298cf89..9682c33 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -22,7 +22,7 @@
static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
static int afs_mntpt_open(struct inode *inode, struct file *file);
static void afs_mntpt_expiry_timed_out(struct work_struct *work);
@@ -104,7 +104,7 @@
*/
static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
_enter("%p,%p{%p{%s},%s}",
dir,
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 5158337..5da37c8 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -32,7 +32,7 @@
static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
#endif
static int autofs4_dir_open(struct inode *inode, struct file *file);
-static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
+static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int);
static struct vfsmount *autofs4_d_automount(struct path *);
static int autofs4_d_manage(struct dentry *, bool);
static void autofs4_dentry_release(struct dentry *);
@@ -458,7 +458,7 @@
}
/* Lookups in the root directory */
-static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct autofs_sb_info *sbi;
struct autofs_info *ino;
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 37268c5..83aefc5 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -173,13 +173,13 @@
};
static int bad_inode_create (struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
return -EIO;
}
static struct dentry *bad_inode_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
return ERR_PTR(-EIO);
}
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 805a16b..c668147 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -34,7 +34,7 @@
static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int);
static int befs_readpage(struct file *file, struct page *page);
static sector_t befs_bmap(struct address_space *mapping, sector_t block);
-static struct dentry *befs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int);
static struct inode *befs_iget(struct super_block *, unsigned long);
static struct inode *befs_alloc_inode(struct super_block *sb);
static void befs_destroy_inode(struct inode *inode);
@@ -159,7 +159,7 @@
}
static struct dentry *
-befs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode = NULL;
struct super_block *sb = dir->i_sb;
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index d12c796..2785ef9 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -85,7 +85,7 @@
extern void dump_imap(const char *, struct super_block *);
static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int err;
struct inode *inode;
@@ -133,7 +133,7 @@
}
static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct buffer_head *bh;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 61b16c6..4990ebd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4163,7 +4163,7 @@
}
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *ret;
@@ -4836,7 +4836,7 @@
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 7f0771d..b0b5f7c 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -567,7 +567,7 @@
if (ret < 0)
goto create_error;
start = jiffies;
- ret = vfs_create(dir->d_inode, next, S_IFREG, NULL);
+ ret = vfs_create(dir->d_inode, next, S_IFREG, true);
cachefiles_hist(cachefiles_create_histogram, start);
if (ret < 0)
goto create_error;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 455b643..8a63471 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -576,7 +576,7 @@
* the MDS so that it gets our 'caps wanted' value in a single op.
*/
static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -594,14 +594,6 @@
if (err < 0)
return ERR_PTR(err);
- /* open (but not create!) intent? */
- if (nd &&
- (nd->flags & LOOKUP_OPEN) &&
- !(nd->intent.open.flags & O_CREAT)) {
- int mode = nd->intent.open.create_mode & ~current->fs->umask;
- return ceph_lookup_open(dir, dentry, nd, mode, 1);
- }
-
/* can we conclude ENOENT locally? */
if (dentry->d_inode == NULL) {
struct ceph_inode_info *ci = ceph_inode(dir);
@@ -642,13 +634,51 @@
return dentry;
}
+int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
+{
+ int err;
+ struct dentry *res = NULL;
+
+ if (!(flags & O_CREAT)) {
+ if (dentry->d_name.len > NAME_MAX)
+ return -ENAMETOOLONG;
+
+ err = ceph_init_dentry(dentry);
+ if (err < 0)
+ return err;
+
+ return ceph_lookup_open(dir, dentry, file, flags, mode, opened);
+ }
+
+ if (d_unhashed(dentry)) {
+ res = ceph_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* We don't deal with positive dentries here */
+ if (dentry->d_inode)
+ return finish_no_open(file, res);
+
+ *opened |= FILE_CREATED;
+ err = ceph_lookup_open(dir, dentry, file, flags, mode, opened);
+ dput(res);
+
+ return err;
+}
+
/*
* If we do a create but get no trace back from the MDS, follow up with
* a lookup (the VFS expects us to link up the provided dentry).
*/
int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
- struct dentry *result = ceph_lookup(dir, dentry, NULL);
+ struct dentry *result = ceph_lookup(dir, dentry, 0);
if (result && !IS_ERR(result)) {
/*
@@ -700,25 +730,9 @@
}
static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- dout("create in dir %p dentry %p name '%.*s'\n",
- dir, dentry, dentry->d_name.len, dentry->d_name.name);
-
- if (ceph_snap(dir) != CEPH_NOSNAP)
- return -EROFS;
-
- if (nd) {
- BUG_ON((nd->flags & LOOKUP_OPEN) == 0);
- dentry = ceph_lookup_open(dir, dentry, nd, mode, 0);
- /* hrm, what should i do here if we get aliased? */
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- return 0;
- }
-
- /* fall back to mknod */
- return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0);
+ return ceph_mknod(dir, dentry, mode, 0);
}
static int ceph_symlink(struct inode *dir, struct dentry *dentry,
@@ -1028,12 +1042,12 @@
/*
* Check if cached dentry can be trusted.
*/
-static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int valid = 0;
struct inode *dir;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
@@ -1080,7 +1094,7 @@
}
static int ceph_snapdir_d_revalidate(struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
/*
* Eventually, we'll want to revalidate snapped metadata
@@ -1357,6 +1371,7 @@
.rmdir = ceph_unlink,
.rename = ceph_rename,
.create = ceph_create,
+ .atomic_open = ceph_atomic_open,
};
const struct dentry_operations ceph_dentry_ops = {
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ed72428..93584b1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -214,22 +214,15 @@
* may_open() fails, the struct *file gets cleaned up (i.e.
* ceph_release gets called). So fear not!
*/
-/*
- * flags
- * path_lookup_open -> LOOKUP_OPEN
- * path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE
- */
-struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir)
+int ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
- struct file *file;
struct ceph_mds_request *req;
struct dentry *ret;
int err;
- int flags = nd->intent.open.flags;
dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n",
dentry, dentry->d_name.len, dentry->d_name.name, flags, mode);
@@ -237,7 +230,7 @@
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req))
- return ERR_CAST(req);
+ return PTR_ERR(req);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
if (flags & O_CREAT) {
@@ -255,14 +248,17 @@
err = ceph_handle_notrace_create(dir, dentry);
if (err)
goto out;
- file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open);
- if (IS_ERR(file))
- err = PTR_ERR(file);
+ err = finish_open(file, req->r_dentry, ceph_open, opened);
out:
ret = ceph_finish_lookup(req, dentry, err);
ceph_mdsc_put_request(req);
dout("ceph_lookup_open result=%p\n", ret);
- return ret;
+
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
+
+ dput(ret);
+ return err;
}
int ceph_release(struct inode *inode, struct file *file)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fc35036..f4d5522 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -806,9 +806,9 @@
loff_t off, size_t len);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
extern int ceph_open(struct inode *inode, struct file *file);
-extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir);
+extern int ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+ struct file *od, unsigned flags,
+ umode_t mode, int *opened);
extern int ceph_release(struct inode *inode, struct file *filp);
/* dir.c */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 541ef81..5f206b6 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -768,6 +768,7 @@
};
const struct inode_operations cifs_dir_inode_ops = {
.create = cifs_create,
+ .atomic_open = cifs_atomic_open,
.lookup = cifs_lookup,
.getattr = cifs_getattr,
.unlink = cifs_unlink,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 6536535..1c49c5a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -45,9 +45,12 @@
extern const struct inode_operations cifs_dir_inode_ops;
extern struct inode *cifs_root_iget(struct super_block *);
extern int cifs_create(struct inode *, struct dentry *, umode_t,
- struct nameidata *);
+ bool excl);
+extern int cifs_atomic_open(struct inode *, struct dentry *,
+ struct file *, unsigned, umode_t,
+ int *);
extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
- struct nameidata *);
+ unsigned int);
extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ec4e9a2..a180265 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -133,100 +133,133 @@
return full_path;
}
+/*
+ * Don't allow the separator character in a path component.
+ * The VFS will not allow "/", but "\" is allowed by posix.
+ */
+static int
+check_name(struct dentry *direntry)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+ int i;
+
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
+ for (i = 0; i < direntry->d_name.len; i++) {
+ if (direntry->d_name.name[i] == '\\') {
+ cFYI(1, "Invalid file name");
+ return -EINVAL;
+ }
+ }
+ }
+ return 0;
+}
+
+
/* Inode operations in similar order to how they appear in Linux file fs.h */
-int
-cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
- struct nameidata *nd)
+static int cifs_do_create(struct inode *inode, struct dentry *direntry,
+ int xid, struct tcon_link *tlink, unsigned oflags,
+ umode_t mode, __u32 *oplock, __u16 *fileHandle,
+ int *created)
{
int rc = -ENOENT;
- int xid;
int create_options = CREATE_NOT_DIR;
- __u32 oplock = 0;
- int oflags;
- /*
- * BB below access is probably too much for mknod to request
- * but we have to do query and setpathinfo so requesting
- * less could fail (unless we want to request getatr and setatr
- * permissions (only). At least for POSIX we do not have to
- * request so much.
- */
- int desiredAccess = GENERIC_READ | GENERIC_WRITE;
- __u16 fileHandle;
- struct cifs_sb_info *cifs_sb;
- struct tcon_link *tlink;
- struct cifs_tcon *tcon;
+ int desiredAccess;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct cifs_tcon *tcon = tlink_tcon(tlink);
char *full_path = NULL;
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
- int disposition = FILE_OVERWRITE_IF;
+ int disposition;
- xid = GetXid();
-
- cifs_sb = CIFS_SB(inode->i_sb);
- tlink = cifs_sb_tlink(cifs_sb);
- if (IS_ERR(tlink)) {
- FreeXid(xid);
- return PTR_ERR(tlink);
- }
- tcon = tlink_tcon(tlink);
-
+ *oplock = 0;
if (tcon->ses->server->oplocks)
- oplock = REQ_OPLOCK;
-
- if (nd)
- oflags = nd->intent.open.file->f_flags;
- else
- oflags = O_RDONLY | O_CREAT;
+ *oplock = REQ_OPLOCK;
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
rc = -ENOMEM;
- goto cifs_create_out;
+ goto out;
}
if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
+ !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_open(full_path, &newinode,
- inode->i_sb, mode, oflags, &oplock, &fileHandle, xid);
- /* EIO could indicate that (posix open) operation is not
- supported, despite what server claimed in capability
- negotiation. EREMOTE indicates DFS junction, which is not
- handled in posix open */
-
- if (rc == 0) {
- if (newinode == NULL) /* query inode info */
+ inode->i_sb, mode, oflags, oplock, fileHandle, xid);
+ switch (rc) {
+ case 0:
+ if (newinode == NULL) {
+ /* query inode info */
goto cifs_create_get_file_info;
- else /* success, no need to query */
- goto cifs_create_set_dentry;
- } else if ((rc != -EIO) && (rc != -EREMOTE) &&
- (rc != -EOPNOTSUPP) && (rc != -EINVAL))
- goto cifs_create_out;
- /* else fallthrough to retry, using older open call, this is
- case where server does not support this SMB level, and
- falsely claims capability (also get here for DFS case
- which should be rare for path not covered on files) */
+ }
+
+ if (!S_ISREG(newinode->i_mode)) {
+ /*
+ * The server may allow us to open things like
+ * FIFOs, but the client isn't set up to deal
+ * with that. If it's not a regular file, just
+ * close it and proceed as if it were a normal
+ * lookup.
+ */
+ CIFSSMBClose(xid, tcon, *fileHandle);
+ goto cifs_create_get_file_info;
+ }
+ /* success, no need to query */
+ goto cifs_create_set_dentry;
+
+ case -ENOENT:
+ goto cifs_create_get_file_info;
+
+ case -EIO:
+ case -EINVAL:
+ /*
+ * EIO could indicate that (posix open) operation is not
+ * supported, despite what server claimed in capability
+ * negotiation.
+ *
+ * POSIX open in samba versions 3.3.1 and earlier could
+ * incorrectly fail with invalid parameter.
+ */
+ tcon->broken_posix_open = true;
+ break;
+
+ case -EREMOTE:
+ case -EOPNOTSUPP:
+ /*
+ * EREMOTE indicates DFS junction, which is not handled
+ * in posix open. If either that or op not supported
+ * returned, follow the normal lookup.
+ */
+ break;
+
+ default:
+ goto out;
+ }
+ /*
+ * fallthrough to retry, using older open call, this is case
+ * where server does not support this SMB level, and falsely
+ * claims capability (also get here for DFS case which should be
+ * rare for path not covered on files)
+ */
}
- if (nd) {
- /* if the file is going to stay open, then we
- need to set the desired access properly */
- desiredAccess = 0;
- if (OPEN_FMODE(oflags) & FMODE_READ)
- desiredAccess |= GENERIC_READ; /* is this too little? */
- if (OPEN_FMODE(oflags) & FMODE_WRITE)
- desiredAccess |= GENERIC_WRITE;
+ desiredAccess = 0;
+ if (OPEN_FMODE(oflags) & FMODE_READ)
+ desiredAccess |= GENERIC_READ; /* is this too little? */
+ if (OPEN_FMODE(oflags) & FMODE_WRITE)
+ desiredAccess |= GENERIC_WRITE;
- if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
- disposition = FILE_CREATE;
- else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
- disposition = FILE_OVERWRITE_IF;
- else if ((oflags & O_CREAT) == O_CREAT)
- disposition = FILE_OPEN_IF;
- else
- cFYI(1, "Create flag not set in create function");
- }
+ disposition = FILE_OVERWRITE_IF;
+ if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+ disposition = FILE_CREATE;
+ else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
+ disposition = FILE_OVERWRITE_IF;
+ else if ((oflags & O_CREAT) == O_CREAT)
+ disposition = FILE_OPEN_IF;
+ else
+ cFYI(1, "Create flag not set in create function");
/* BB add processing to set equivalent of mode - e.g. via CreateX with
ACLs */
@@ -234,7 +267,7 @@
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
rc = -ENOMEM;
- goto cifs_create_out;
+ goto out;
}
/*
@@ -250,7 +283,7 @@
if (tcon->ses->capabilities & CAP_NT_SMBS)
rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
desiredAccess, create_options,
- &fileHandle, &oplock, buf, cifs_sb->local_nls,
+ fileHandle, oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
else
rc = -EIO; /* no NT SMB support fall into legacy open below */
@@ -259,17 +292,17 @@
/* old server, retry the open legacy style */
rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
desiredAccess, create_options,
- &fileHandle, &oplock, buf, cifs_sb->local_nls,
+ fileHandle, oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
}
if (rc) {
cFYI(1, "cifs_create returned 0x%x", rc);
- goto cifs_create_out;
+ goto out;
}
/* If Open reported that we actually created a file
then we now have to set the mode if possible */
- if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) {
+ if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
struct cifs_unix_set_info_args args = {
.mode = mode,
.ctime = NO_CHANGE_64,
@@ -278,6 +311,7 @@
.device = 0,
};
+ *created |= FILE_CREATED;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
args.uid = (__u64) current_fsuid();
if (inode->i_mode & S_ISGID)
@@ -288,7 +322,7 @@
args.uid = NO_CHANGE_64;
args.gid = NO_CHANGE_64;
}
- CIFSSMBUnixSetFileInfo(xid, tcon, &args, fileHandle,
+ CIFSSMBUnixSetFileInfo(xid, tcon, &args, *fileHandle,
current->tgid);
} else {
/* BB implement mode setting via Windows security
@@ -305,11 +339,11 @@
inode->i_sb, xid);
else {
rc = cifs_get_inode_info(&newinode, full_path, buf,
- inode->i_sb, xid, &fileHandle);
+ inode->i_sb, xid, fileHandle);
if (newinode) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
newinode->i_mode = mode;
- if ((oplock & CIFS_CREATE_ACTION) &&
+ if ((*oplock & CIFS_CREATE_ACTION) &&
(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
newinode->i_uid = current_fsuid();
if (inode->i_mode & S_ISGID)
@@ -321,40 +355,139 @@
}
cifs_create_set_dentry:
- if (rc == 0)
- d_instantiate(direntry, newinode);
- else
+ if (rc != 0) {
cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
-
- if (newinode && nd) {
- struct cifsFileInfo *pfile_info;
- struct file *filp;
-
- filp = lookup_instantiate_filp(nd, direntry, generic_file_open);
- if (IS_ERR(filp)) {
- rc = PTR_ERR(filp);
- CIFSSMBClose(xid, tcon, fileHandle);
- goto cifs_create_out;
- }
-
- pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock);
- if (pfile_info == NULL) {
- fput(filp);
- CIFSSMBClose(xid, tcon, fileHandle);
- rc = -ENOMEM;
- }
- } else {
- CIFSSMBClose(xid, tcon, fileHandle);
+ goto out;
}
+ d_drop(direntry);
+ d_add(direntry, newinode);
-cifs_create_out:
+ /* ENOENT for create? How weird... */
+ rc = -ENOENT;
+ if (!newinode) {
+ CIFSSMBClose(xid, tcon, *fileHandle);
+ goto out;
+ }
+ rc = 0;
+
+out:
kfree(buf);
kfree(full_path);
+ return rc;
+}
+
+int
+cifs_atomic_open(struct inode *inode, struct dentry *direntry,
+ struct file *file, unsigned oflags, umode_t mode,
+ int *opened)
+{
+ int rc;
+ int xid;
+ struct tcon_link *tlink;
+ struct cifs_tcon *tcon;
+ __u16 fileHandle;
+ __u32 oplock;
+ struct file *filp;
+ struct cifsFileInfo *pfile_info;
+
+ /* Posix open is only called (at lookup time) for file create now. For
+ * opens (rather than creates), because we do not know if it is a file
+ * or directory yet, and current Samba no longer allows us to do posix
+ * open on dirs, we could end up wasting an open call on what turns out
+ * to be a dir. For file opens, we wait to call posix open till
+ * cifs_open. It could be added to atomic_open in the future but the
+ * performance tradeoff of the extra network request when EISDIR or
+ * EACCES is returned would have to be weighed against the 50% reduction
+ * in network traffic in the other paths.
+ */
+ if (!(oflags & O_CREAT)) {
+ struct dentry *res = cifs_lookup(inode, direntry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ return finish_no_open(file, res);
+ }
+
+ rc = check_name(direntry);
+ if (rc)
+ return rc;
+
+ xid = GetXid();
+
+ cFYI(1, "parent inode = 0x%p name is: %s and dentry = 0x%p",
+ inode, direntry->d_name.name, direntry);
+
+ tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+ filp = ERR_CAST(tlink);
+ if (IS_ERR(tlink))
+ goto free_xid;
+
+ tcon = tlink_tcon(tlink);
+
+ rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
+ &oplock, &fileHandle, opened);
+
+ if (rc)
+ goto out;
+
+ rc = finish_open(file, direntry, generic_file_open, opened);
+ if (rc) {
+ CIFSSMBClose(xid, tcon, fileHandle);
+ goto out;
+ }
+
+ pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock);
+ if (pfile_info == NULL) {
+ CIFSSMBClose(xid, tcon, fileHandle);
+ fput(filp);
+ rc = -ENOMEM;
+ }
+
+out:
cifs_put_tlink(tlink);
+free_xid:
FreeXid(xid);
return rc;
}
+int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
+ bool excl)
+{
+ int rc;
+ int xid = GetXid();
+ /*
+ * BB below access is probably too much for mknod to request
+ * but we have to do query and setpathinfo so requesting
+ * less could fail (unless we want to request getatr and setatr
+ * permissions (only). At least for POSIX we do not have to
+ * request so much.
+ */
+ unsigned oflags = O_EXCL | O_CREAT | O_RDWR;
+ struct tcon_link *tlink;
+ __u16 fileHandle;
+ __u32 oplock;
+ int created = FILE_CREATED;
+
+ cFYI(1, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p",
+ inode, direntry->d_name.name, direntry);
+
+ tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+ rc = PTR_ERR(tlink);
+ if (IS_ERR(tlink))
+ goto free_xid;
+
+ rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
+ &oplock, &fileHandle, &created);
+ if (!rc)
+ CIFSSMBClose(xid, tlink_tcon(tlink), fileHandle);
+
+ cifs_put_tlink(tlink);
+free_xid:
+ FreeXid(xid);
+
+ return rc;
+}
+
int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
dev_t device_number)
{
@@ -488,20 +621,15 @@
struct dentry *
cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
- struct nameidata *nd)
+ unsigned int flags)
{
int xid;
int rc = 0; /* to get around spurious gcc warning, set to zero here */
- __u32 oplock;
- __u16 fileHandle = 0;
- bool posix_open = false;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- struct cifsFileInfo *cfile;
struct inode *newInode = NULL;
char *full_path = NULL;
- struct file *filp;
xid = GetXid();
@@ -518,31 +646,9 @@
}
pTcon = tlink_tcon(tlink);
- oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0;
-
- /*
- * Don't allow the separator character in a path component.
- * The VFS will not allow "/", but "\" is allowed by posix.
- */
- if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
- int i;
- for (i = 0; i < direntry->d_name.len; i++)
- if (direntry->d_name.name[i] == '\\') {
- cFYI(1, "Invalid file name");
- rc = -EINVAL;
- goto lookup_out;
- }
- }
-
- /*
- * O_EXCL: optimize away the lookup, but don't hash the dentry. Let
- * the VFS handle the create.
- */
- if (nd && (nd->flags & LOOKUP_EXCL)) {
- d_instantiate(direntry, NULL);
- rc = 0;
+ rc = check_name(direntry);
+ if (rc)
goto lookup_out;
- }
/* can not grab the rename sem here since it would
deadlock in the cases (beginning of sys_rename itself)
@@ -560,80 +666,16 @@
}
cFYI(1, "Full path: %s inode = 0x%p", full_path, direntry->d_inode);
- /* Posix open is only called (at lookup time) for file create now.
- * For opens (rather than creates), because we do not know if it
- * is a file or directory yet, and current Samba no longer allows
- * us to do posix open on dirs, we could end up wasting an open call
- * on what turns out to be a dir. For file opens, we wait to call posix
- * open till cifs_open. It could be added here (lookup) in the future
- * but the performance tradeoff of the extra network request when EISDIR
- * or EACCES is returned would have to be weighed against the 50%
- * reduction in network traffic in the other paths.
- */
if (pTcon->unix_ext) {
- if (nd && !(nd->flags & LOOKUP_DIRECTORY) &&
- (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open &&
- (nd->intent.open.file->f_flags & O_CREAT)) {
- rc = cifs_posix_open(full_path, &newInode,
- parent_dir_inode->i_sb,
- nd->intent.open.create_mode,
- nd->intent.open.file->f_flags, &oplock,
- &fileHandle, xid);
- /*
- * The check below works around a bug in POSIX
- * open in samba versions 3.3.1 and earlier where
- * open could incorrectly fail with invalid parameter.
- * If either that or op not supported returned, follow
- * the normal lookup.
- */
- switch (rc) {
- case 0:
- /*
- * The server may allow us to open things like
- * FIFOs, but the client isn't set up to deal
- * with that. If it's not a regular file, just
- * close it and proceed as if it were a normal
- * lookup.
- */
- if (newInode && !S_ISREG(newInode->i_mode)) {
- CIFSSMBClose(xid, pTcon, fileHandle);
- break;
- }
- case -ENOENT:
- posix_open = true;
- case -EOPNOTSUPP:
- break;
- default:
- pTcon->broken_posix_open = true;
- }
- }
- if (!posix_open)
- rc = cifs_get_inode_info_unix(&newInode, full_path,
- parent_dir_inode->i_sb, xid);
- } else
+ rc = cifs_get_inode_info_unix(&newInode, full_path,
+ parent_dir_inode->i_sb, xid);
+ } else {
rc = cifs_get_inode_info(&newInode, full_path, NULL,
parent_dir_inode->i_sb, xid, NULL);
+ }
if ((rc == 0) && (newInode != NULL)) {
d_add(direntry, newInode);
- if (posix_open) {
- filp = lookup_instantiate_filp(nd, direntry,
- generic_file_open);
- if (IS_ERR(filp)) {
- rc = PTR_ERR(filp);
- CIFSSMBClose(xid, pTcon, fileHandle);
- goto lookup_out;
- }
-
- cfile = cifs_new_fileinfo(fileHandle, filp, tlink,
- oplock);
- if (cfile == NULL) {
- fput(filp);
- CIFSSMBClose(xid, pTcon, fileHandle);
- rc = -ENOMEM;
- goto lookup_out;
- }
- }
/* since paths are not looked up by component - the parent
directories are presumed to be good here */
renew_parental_timestamps(direntry);
@@ -658,9 +700,9 @@
}
static int
-cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
+cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
{
- if (nd && (nd->flags & LOOKUP_RCU))
+ if (flags & LOOKUP_RCU)
return -ECHILD;
if (direntry->d_inode) {
@@ -689,7 +731,7 @@
* This may be nfsd (or something), anyway, we can't see the
* intent of this. So, since this can be for creation, drop it.
*/
- if (!nd)
+ if (!flags)
return 0;
/*
@@ -697,7 +739,7 @@
* case sensitive name which is specified by user if this is
* for creation.
*/
- if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
return 0;
if (time_after(jiffies, direntry->d_time + HZ) || !lookupCacheEnabled)
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 1775158..49fe52d 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -30,8 +30,8 @@
#include "coda_int.h"
/* dir inode-ops */
-static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, struct nameidata *nd);
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, struct nameidata *nd);
+static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, bool excl);
+static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, unsigned int flags);
static int coda_link(struct dentry *old_dentry, struct inode *dir_inode,
struct dentry *entry);
static int coda_unlink(struct inode *dir_inode, struct dentry *entry);
@@ -46,7 +46,7 @@
static int coda_readdir(struct file *file, void *buf, filldir_t filldir);
/* dentry ops */
-static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd);
+static int coda_dentry_revalidate(struct dentry *de, unsigned int flags);
static int coda_dentry_delete(const struct dentry *);
/* support routines */
@@ -94,7 +94,7 @@
/* inode operations for directories */
/* access routines: lookup, readlink, permission */
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd)
+static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags)
{
struct super_block *sb = dir->i_sb;
const char *name = entry->d_name.name;
@@ -188,7 +188,7 @@
}
/* creation routines: create, mknod, mkdir, link, symlink */
-static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, struct nameidata *nd)
+static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl)
{
int error;
const char *name=de->d_name.name;
@@ -536,12 +536,12 @@
}
/* called when a cache lookup succeeds */
-static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd)
+static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
{
struct inode *inode;
struct coda_inode_info *cii;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = de->d_inode;
diff --git a/fs/compat.c b/fs/compat.c
index febe27d..4185d1c 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -780,16 +780,16 @@
char *kernel_type;
unsigned long data_page;
char *kernel_dev;
- char *dir_page;
+ struct filename *dir;
int retval;
retval = copy_mount_string(type, &kernel_type);
if (retval < 0)
goto out;
- dir_page = getname(dir_name);
- retval = PTR_ERR(dir_page);
- if (IS_ERR(dir_page))
+ dir = getname(dir_name);
+ retval = PTR_ERR(dir);
+ if (IS_ERR(dir))
goto out1;
retval = copy_mount_string(dev_name, &kernel_dev);
@@ -811,7 +811,7 @@
}
}
- retval = do_mount(kernel_dev, dir_page, kernel_type,
+ retval = do_mount(kernel_dev, dir->name, kernel_type,
flags, (void*)data_page);
out4:
@@ -819,7 +819,7 @@
out3:
kfree(kernel_dev);
out2:
- putname(dir_page);
+ putname(dir);
out1:
kfree(kernel_type);
out:
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 7e6c52d..7414ae2 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -442,7 +442,7 @@
static struct dentry * configfs_lookup(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
struct configfs_dirent * sd;
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 5c8fb68..c57ad84 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -417,7 +417,7 @@
/*
* Lookup and fill in the inode data..
*/
-static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
unsigned int offset = 0;
struct inode *inode = NULL;
diff --git a/fs/dcache.c b/fs/dcache.c
index 788f06b..f74399f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -153,16 +153,12 @@
* In contrast, 'ct' and 'tcount' can be from a pathname, and do
* need the careful unaligned handling.
*/
-static inline int dentry_cmp(const unsigned char *cs, size_t scount,
- const unsigned char *ct, size_t tcount)
+static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
unsigned long a,b,mask;
- if (unlikely(scount != tcount))
- return 1;
-
for (;;) {
- a = load_unaligned_zeropad(cs);
+ a = *(unsigned long *)cs;
b = load_unaligned_zeropad(ct);
if (tcount < sizeof(unsigned long))
break;
@@ -180,12 +176,8 @@
#else
-static inline int dentry_cmp(const unsigned char *cs, size_t scount,
- const unsigned char *ct, size_t tcount)
+static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
- if (scount != tcount)
- return 1;
-
do {
if (*cs != *ct)
return 1;
@@ -198,15 +190,73 @@
#endif
+struct external_name {
+ union {
+ atomic_t count;
+ struct rcu_head head;
+ } u;
+ unsigned char name[];
+};
+
+static inline struct external_name *external_name(struct dentry *dentry)
+{
+ return container_of(dentry->d_name.name, struct external_name, name[0]);
+}
+
+static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
+{
+ const unsigned char *cs;
+ /*
+ * Be careful about RCU walk racing with rename:
+ * use ACCESS_ONCE to fetch the name pointer.
+ *
+ * NOTE! Even if a rename will mean that the length
+ * was not loaded atomically, we don't care. The
+ * RCU walk will check the sequence count eventually,
+ * and catch it. And we won't overrun the buffer,
+ * because we're reading the name pointer atomically,
+ * and a dentry name is guaranteed to be properly
+ * terminated with a NUL byte.
+ *
+ * End result: even if 'len' is wrong, we'll exit
+ * early because the data cannot match (there can
+ * be no NUL in the ct/tcount data)
+ */
+ cs = ACCESS_ONCE(dentry->d_name.name);
+ smp_read_barrier_depends();
+ return dentry_string_cmp(cs, ct, tcount);
+}
+
static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- if (dname_external(dentry))
- kfree(dentry->d_name.name);
kmem_cache_free(dentry_cache, dentry);
}
+static void __d_free_external(struct rcu_head *head)
+{
+ struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
+ kfree(external_name(dentry));
+ kmem_cache_free(dentry_cache, dentry);
+}
+
+static void dentry_free(struct dentry *dentry)
+{
+ if (unlikely(dname_external(dentry))) {
+ struct external_name *p = external_name(dentry);
+ if (likely(atomic_dec_and_test(&p->u.count))) {
+ call_rcu(&dentry->d_u.d_rcu, __d_free_external);
+ return;
+ }
+ }
+ /* if dentry was never visible to RCU, immediate free is OK */
+ if (!(dentry->d_flags & DCACHE_RCUACCESS))
+ __d_free(&dentry->d_u.d_rcu);
+ else
+ call_rcu(&dentry->d_u.d_rcu, __d_free);
+}
+
/*
* no locks, please.
*/
@@ -218,11 +268,7 @@
if (dentry->d_op && dentry->d_op->d_release)
dentry->d_op->d_release(dentry);
- /* if dentry was never visible to RCU, immediate free is OK */
- if (!(dentry->d_flags & DCACHE_RCUACCESS))
- __d_free(&dentry->d_u.d_rcu);
- else
- call_rcu(&dentry->d_u.d_rcu, __d_free);
+ dentry_free(dentry);
}
void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
@@ -1309,22 +1355,35 @@
if (!dentry)
return NULL;
+ /*
+ * We guarantee that the inline name is always NUL-terminated.
+ * This way the memcpy() done by the name switching in rename
+ * will still always have a NUL at the end, even if we might
+ * be overwriting an internal NUL character
+ */
+ dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
if (name->len > DNAME_INLINE_LEN-1) {
- dname = kmalloc(name->len + 1, GFP_KERNEL);
- if (!dname) {
+ size_t size = offsetof(struct external_name, name[1]);
+ struct external_name *p = kmalloc(size + name->len, GFP_KERNEL);
+ if (!p) {
kmem_cache_free(dentry_cache, dentry);
return NULL;
}
+ atomic_set(&p->u.count, 1);
+ dname = p->name;
} else {
dname = dentry->d_iname;
}
- dentry->d_name.name = dname;
dentry->d_name.len = name->len;
dentry->d_name.hash = name->hash;
memcpy(dname, name->name, name->len);
dname[name->len] = 0;
+ /* Make sure we always see the terminating NUL character */
+ smp_wmb();
+ dentry->d_name.name = dname;
+
dentry->d_count = 1;
dentry->d_flags = 0;
spin_lock_init(&dentry->d_lock);
@@ -1490,18 +1549,18 @@
}
list_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
- struct qstr *qstr = &alias->d_name;
-
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
* parent changes, because the parent inode i_mutex is held.
*/
- if (qstr->hash != hash)
+ if (alias->d_name.hash != hash)
continue;
if (alias->d_parent != entry->d_parent)
continue;
- if (dentry_cmp(qstr->name, qstr->len, name, len))
+ if (alias->d_name.len != len)
+ continue;
+ if (dentry_cmp(alias, name, len))
continue;
__dget(alias);
return alias;
@@ -1540,7 +1599,7 @@
struct dentry *res = NULL;
if (root_inode) {
- static const struct qstr name = { .name = "/", .len = 1 };
+ static const struct qstr name = QSTR_INIT("/", 1);
res = __d_alloc(root_inode->i_sb, &name);
if (res)
@@ -1778,6 +1837,48 @@
}
EXPORT_SYMBOL(d_add_ci);
+/*
+ * Do the slow-case of the dentry name compare.
+ *
+ * Unlike the dentry_cmp() function, we need to atomically
+ * load the name, length and inode information, so that the
+ * filesystem can rely on them, and can use the 'name' and
+ * 'len' information without worrying about walking off the
+ * end of memory etc.
+ *
+ * Thus the read_seqcount_retry() and the "duplicate" info
+ * in arguments (the low-level filesystem should not look
+ * at the dentry inode or name contents directly, since
+ * rename can change them while we're in RCU mode).
+ */
+enum slow_d_compare {
+ D_COMP_OK,
+ D_COMP_NOMATCH,
+ D_COMP_SEQRETRY,
+};
+
+static noinline enum slow_d_compare slow_dentry_cmp(
+ const struct dentry *parent,
+ struct inode *inode,
+ struct dentry *dentry,
+ unsigned int seq,
+ const struct qstr *name)
+{
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
+ struct inode *i = dentry->d_inode;
+
+ if (read_seqcount_retry(&dentry->d_seq, seq)) {
+ cpu_relax();
+ return D_COMP_SEQRETRY;
+ }
+ if (parent->d_op->d_compare(parent, inode,
+ dentry, i,
+ tlen, tname, name))
+ return D_COMP_NOMATCH;
+ return D_COMP_OK;
+}
+
/**
* __d_lookup_rcu - search for a dentry (racy, store-free)
* @parent: parent dentry
@@ -1804,15 +1905,17 @@
* the returned dentry, so long as its parent's seqlock is checked after the
* child is looked up. Thus, an interlocking stepping of sequence lock checks
* is formed, giving integrity down the path walk.
+ *
+ * NOTE! The caller *has* to check the resulting dentry against the sequence
+ * number we've returned before using any of the resulting dentry state!
*/
struct dentry *__d_lookup_rcu(const struct dentry *parent,
const struct qstr *name,
- unsigned *seqp, struct inode **inode)
+ unsigned *seqp, struct inode *inode)
{
- unsigned int len = name->len;
- unsigned int hash = name->hash;
+ u64 hashlen = name->hash_len;
const unsigned char *str = name->name;
- struct hlist_bl_head *b = d_hash(parent, hash);
+ struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen));
struct hlist_bl_node *node;
struct dentry *dentry;
@@ -1838,49 +1941,47 @@
*/
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
unsigned seq;
- struct inode *i;
- const char *tname;
- int tlen;
-
- if (dentry->d_name.hash != hash)
- continue;
seqretry:
- seq = read_seqcount_begin(&dentry->d_seq);
+ /*
+ * The dentry sequence count protects us from concurrent
+ * renames, and thus protects inode, parent and name fields.
+ *
+ * The caller must perform a seqcount check in order
+ * to do anything useful with the returned dentry,
+ * including using the 'd_inode' pointer.
+ *
+ * NOTE! We do a "raw" seqcount_begin here. That means that
+ * we don't wait for the sequence count to stabilize if it
+ * is in the middle of a sequence change. If we do the slow
+ * dentry compare, we will do seqretries until it is stable,
+ * and if we end up with a successful lookup, we actually
+ * want to exit RCU lookup anyway.
+ */
+ seq = raw_seqcount_begin(&dentry->d_seq);
if (dentry->d_parent != parent)
continue;
if (d_unhashed(dentry))
continue;
- tlen = dentry->d_name.len;
- tname = dentry->d_name.name;
- i = dentry->d_inode;
- prefetch(tname);
- /*
- * This seqcount check is required to ensure name and
- * len are loaded atomically, so as not to walk off the
- * edge of memory when walking. If we could load this
- * atomically some other way, we could drop this check.
- */
- if (read_seqcount_retry(&dentry->d_seq, seq))
- goto seqretry;
- if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
- if (parent->d_op->d_compare(parent, *inode,
- dentry, i,
- tlen, tname, name))
- continue;
- } else {
- if (dentry_cmp(tname, tlen, str, len))
- continue;
- }
- /*
- * No extra seqcount check is required after the name
- * compare. The caller must perform a seqcount check in
- * order to do anything useful with the returned dentry
- * anyway.
- */
*seqp = seq;
- *inode = i;
- return dentry;
+
+ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
+ if (dentry->d_name.hash != hashlen_hash(hashlen))
+ continue;
+ switch (slow_dentry_cmp(parent, inode, dentry, seq, name)) {
+ case D_COMP_OK:
+ return dentry;
+ case D_COMP_NOMATCH:
+ continue;
+ default:
+ goto seqretry;
+ }
+ }
+
+ if (dentry->d_name.hash_len != hashlen)
+ continue;
+ if (!dentry_cmp(dentry, str, hashlen_len(hashlen)))
+ return dentry;
}
return NULL;
}
@@ -1959,8 +2060,6 @@
rcu_read_lock();
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
- const char *tname;
- int tlen;
if (dentry->d_name.hash != hash)
continue;
@@ -1975,15 +2074,17 @@
* It is safe to compare names since d_move() cannot
* change the qstr (protected by d_lock).
*/
- tlen = dentry->d_name.len;
- tname = dentry->d_name.name;
if (parent->d_flags & DCACHE_OP_COMPARE) {
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
if (parent->d_op->d_compare(parent, parent->d_inode,
dentry, dentry->d_inode,
tlen, tname, name))
goto next;
} else {
- if (dentry_cmp(tname, tlen, str, len))
+ if (dentry->d_name.len != len)
+ goto next;
+ if (dentry_cmp(dentry, str, len))
goto next;
}
@@ -2167,8 +2268,8 @@
static void switch_names(struct dentry *dentry, struct dentry *target)
{
- if (dname_external(target)) {
- if (dname_external(dentry)) {
+ if (unlikely(dname_external(target))) {
+ if (unlikely(dname_external(dentry))) {
/*
* Both external: swap the pointers
*/
@@ -2184,7 +2285,7 @@
target->d_name.name = target->d_iname;
}
} else {
- if (dname_external(dentry)) {
+ if (unlikely(dname_external(dentry))) {
/*
* dentry:external, target:internal. Give dentry's
* storage to target and make dentry internal
@@ -2206,6 +2307,25 @@
swap(dentry->d_name.len, target->d_name.len);
}
+static void copy_name(struct dentry *dentry, struct dentry *target)
+{
+ struct external_name *old_name = NULL;
+ if (unlikely(dname_external(dentry)))
+ old_name = external_name(dentry);
+ if (unlikely(dname_external(target))) {
+ atomic_inc(&external_name(target)->u.count);
+ dentry->d_name = target->d_name;
+ } else {
+ memcpy(dentry->d_iname, target->d_name.name,
+ target->d_name.len + 1);
+ dentry->d_name.name = dentry->d_iname;
+ dentry->d_name.len = target->d_name.len;
+ }
+ if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
+ kfree_rcu(old_name, u.head);
+}
+
+
static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
{
/*
@@ -2292,7 +2412,7 @@
list_del(&target->d_child);
/* Switch the names.. */
- switch_names(dentry, target);
+ copy_name(dentry, target);
swap(dentry->d_name.hash, target->d_name.hash);
/* ... and switch the parents */
@@ -3054,6 +3174,22 @@
goto again;
}
+void d_tmpfile(struct dentry *dentry, struct inode *inode)
+{
+ inode_dec_link_count(inode);
+ BUG_ON(dentry->d_name.name != dentry->d_iname ||
+ !list_empty(&dentry->d_u.d_alias) ||
+ !d_unlinked(dentry));
+ spin_lock(&dentry->d_parent->d_lock);
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+ dentry->d_name.len = sprintf(dentry->d_iname, "#%llu",
+ (unsigned long long)inode->i_ino);
+ spin_unlock(&dentry->d_lock);
+ spin_unlock(&dentry->d_parent->d_lock);
+ d_instantiate(dentry, inode);
+}
+EXPORT_SYMBOL(d_tmpfile);
+
/**
* find_inode_number - check for dentry with name
* @dir: directory to check
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 534c1d4..8c5df47 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -32,7 +32,7 @@
/**
* ecryptfs_d_revalidate - revalidate an ecryptfs dentry
* @dentry: The ecryptfs dentry
- * @nd: The associated nameidata
+ * @flags: lookup flags
*
* Called when the VFS needs to revalidate a dentry. This
* is called whenever a name lookup finds a dentry in the
@@ -42,39 +42,27 @@
* Returns 1 if valid, 0 otherwise.
*
*/
-static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *lower_dentry;
struct vfsmount *lower_mnt;
- struct dentry *dentry_save = NULL;
- struct vfsmount *vfsmount_save = NULL;
int rc = 1;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
- if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
- goto out;
- if (nd) {
- dentry_save = nd->path.dentry;
- vfsmount_save = nd->path.mnt;
- nd->path.dentry = lower_dentry;
- nd->path.mnt = lower_mnt;
- }
- rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
- if (nd) {
- nd->path.dentry = dentry_save;
- nd->path.mnt = vfsmount_save;
+ if (lower_dentry->d_op && lower_dentry->d_op->d_revalidate) {
+ rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
}
if (dentry->d_inode) {
- struct inode *lower_inode =
- ecryptfs_inode_to_lower(dentry->d_inode);
+ struct inode *inode = dentry->d_inode;
- fsstack_copy_attr_all(dentry->d_inode, lower_inode);
+ fsstack_copy_attr_all(inode, ecryptfs_inode_to_lower(inode));
+ if (!inode->i_nlink)
+ return 0;
}
-out:
return rc;
}
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index ab35b11..962366c 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -173,7 +173,7 @@
inode = ERR_CAST(lower_dir_dentry);
goto out;
}
- rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, NULL);
+ rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true);
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
@@ -240,7 +240,6 @@
* @dir: The inode of the directory in which to create the file.
* @dentry: The eCryptfs dentry
* @mode: The mode of the new file.
- * @nd: nameidata
*
* Creates a new file.
*
@@ -248,7 +247,7 @@
*/
static int
ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct inode *ecryptfs_inode;
int rc;
@@ -374,7 +373,7 @@
*/
static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
struct dentry *ecryptfs_dentry,
- struct nameidata *ecryptfs_nd)
+ unsigned int flags)
{
char *encrypted_and_encoded_name = NULL;
size_t encrypted_and_encoded_name_size;
diff --git a/fs/efs/efs.h b/fs/efs/efs.h
index d8305b5..5528926 100644
--- a/fs/efs/efs.h
+++ b/fs/efs/efs.h
@@ -129,7 +129,7 @@
extern efs_block_t efs_map_block(struct inode *, efs_block_t);
extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int);
-extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *efs_lookup(struct inode *, struct dentry *, unsigned int);
extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type);
extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid,
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index 832b10d..96f66d2 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -58,7 +58,8 @@
return(0);
}
-struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) {
+struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
efs_ino_t inodenum;
struct inode *inode = NULL;
diff --git a/fs/exec.c b/fs/exec.c
index 940cb6b..5c0bb37 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -116,7 +116,7 @@
SYSCALL_DEFINE1(uselib, const char __user *, library)
{
struct file *file;
- char *tmp = getname(library);
+ struct filename *tmp = getname(library);
int error = PTR_ERR(tmp);
static const struct open_flags uselib_flags = {
.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
@@ -786,13 +786,14 @@
{
struct file *file;
int err;
+ struct filename tmp = { .name = name };
static const struct open_flags open_exec_flags = {
.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
.acc_mode = MAY_EXEC | MAY_OPEN,
.intent = LOOKUP_OPEN
};
- file = do_filp_open(AT_FDCWD, name, &open_exec_flags, LOOKUP_FOLLOW);
+ file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags, LOOKUP_FOLLOW);
if (IS_ERR(file))
goto out;
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index fc7161d..4731fd9 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -46,7 +46,7 @@
}
static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode;
ino_t ino;
@@ -60,7 +60,7 @@
}
static int exofs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode = exofs_new_inode(dir, mode);
int err = PTR_ERR(inode);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index dffb865..e44d139 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -55,7 +55,7 @@
* Methods themselves.
*/
-static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode;
ino_t ino;
@@ -79,7 +79,7 @@
struct dentry *ext2_get_parent(struct dentry *child)
{
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot);
if (!ino)
return ERR_PTR(-ENOENT);
@@ -94,7 +94,7 @@
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd)
+static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
{
struct inode *inode;
@@ -119,6 +119,29 @@
return ext2_add_nondir(dentry, inode);
}
+static int ext2_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ struct inode *inode = ext2_new_inode(dir, mode, NULL);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ inode->i_op = &ext2_file_inode_operations;
+ if (ext2_use_xip(inode->i_sb)) {
+ inode->i_mapping->a_ops = &ext2_aops_xip;
+ inode->i_fop = &ext2_xip_file_operations;
+ } else if (test_opt(inode->i_sb, NOBH)) {
+ inode->i_mapping->a_ops = &ext2_nobh_aops;
+ inode->i_fop = &ext2_file_operations;
+ } else {
+ inode->i_mapping->a_ops = &ext2_aops;
+ inode->i_fop = &ext2_file_operations;
+ }
+ mark_inode_dirty(inode);
+ d_tmpfile(dentry, inode);
+ unlock_new_inode(inode);
+ return 0;
+}
+
static int ext2_mknod (struct inode * dir, struct dentry *dentry, umode_t mode, dev_t rdev)
{
struct inode * inode;
@@ -398,6 +421,7 @@
#endif
.setattr = ext2_setattr,
.get_acl = ext2_get_acl,
+ .tmpfile = ext2_tmpfile,
};
const struct inode_operations ext2_special_inode_operations = {
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index d7940b2..16791c5 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1011,7 +1011,7 @@
return NULL;
}
-static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode;
struct ext3_dir_entry_2 * de;
@@ -1045,7 +1045,7 @@
struct dentry *ext3_get_parent(struct dentry *child)
{
unsigned long ino;
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
struct ext3_dir_entry_2 * de;
struct buffer_head *bh;
@@ -1690,7 +1690,7 @@
* with d_instantiate().
*/
static int ext3_create (struct inode * dir, struct dentry * dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
handle_t *handle;
struct inode * inode;
@@ -1759,6 +1759,44 @@
return err;
}
+static int ext3_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ handle_t *handle;
+ struct inode *inode;
+ int err, retries = 0;
+
+ dquot_initialize(dir);
+
+retry:
+ handle = ext3_journal_start(dir, EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ 4 + EXT3_XATTR_TRANS_BLOCKS);
+
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ inode = ext3_new_inode (handle, dir, NULL, mode);
+ err = PTR_ERR(inode);
+ if (!IS_ERR(inode)) {
+ inode->i_op = &ext3_file_inode_operations;
+ inode->i_fop = &ext3_file_operations;
+ ext3_set_aops(inode);
+ d_tmpfile(dentry, inode);
+ err = ext3_orphan_add(handle, inode);
+ if (err)
+ goto err_unlock_inode;
+ mark_inode_dirty(inode);
+ unlock_new_inode(inode);
+ }
+ ext3_journal_stop(handle);
+ if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+err_unlock_inode:
+ ext3_journal_stop(handle);
+ unlock_new_inode(inode);
+ return err;
+}
+
static int ext3_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
{
handle_t *handle;
@@ -2302,7 +2340,7 @@
retry:
handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT3_INDEX_EXTRA_TRANS_BLOCKS);
+ EXT3_INDEX_EXTRA_TRANS_BLOCKS + 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2316,6 +2354,11 @@
err = ext3_add_entry(handle, dentry, inode);
if (!err) {
ext3_mark_inode_dirty(handle, inode);
+ /* this can happen only for tmpfile being
+ * linked the first time
+ */
+ if (inode->i_nlink == 1)
+ ext3_orphan_del(handle, inode);
d_instantiate(dentry, inode);
} else {
drop_nlink(inode);
@@ -2518,6 +2561,7 @@
.mkdir = ext3_mkdir,
.rmdir = ext3_rmdir,
.mknod = ext3_mknod,
+ .tmpfile = ext3_tmpfile,
.rename = ext3_rename,
.setattr = ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 704f6b4..972aa8f 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1019,7 +1019,7 @@
return NULL;
}
-static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct ext4_dir_entry_2 *de;
@@ -1052,10 +1052,7 @@
struct dentry *ext4_get_parent(struct dentry *child)
{
__u32 ino;
- static const struct qstr dotdot = {
- .name = "..",
- .len = 2,
- };
+ static const struct qstr dotdot = QSTR_INIT("..", 2);
struct ext4_dir_entry_2 * de;
struct buffer_head *bh;
@@ -1737,7 +1734,7 @@
* with d_instantiate().
*/
static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
handle_t *handle;
struct inode *inode;
@@ -1806,6 +1803,47 @@
return err;
}
+static int ext4_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ handle_t *handle;
+ struct inode *inode;
+ int err, retries = 0;
+
+ dquot_initialize(dir);
+
+retry:
+ handle = ext4_journal_start(dir, EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ 4 + EXT4_XATTR_TRANS_BLOCKS);
+
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ if (IS_DIRSYNC(dir))
+ ext4_handle_sync(handle);
+
+ inode = ext4_new_inode(handle, dir, mode, NULL, 0, NULL);
+ err = PTR_ERR(inode);
+ if (!IS_ERR(inode)) {
+ inode->i_op = &ext4_file_inode_operations;
+ inode->i_fop = &ext4_file_operations;
+ ext4_set_aops(inode);
+ d_tmpfile(dentry, inode);
+ err = ext4_orphan_add(handle, inode);
+ if (err)
+ goto err_unlock_inode;
+ mark_inode_dirty(inode);
+ unlock_new_inode(inode);
+ }
+ if (handle)
+ ext4_journal_stop(handle);
+ if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+err_unlock_inode:
+ ext4_journal_stop(handle);
+ unlock_new_inode(inode);
+ return err;
+}
+
static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
handle_t *handle;
@@ -2356,7 +2394,7 @@
retry:
handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS);
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2370,6 +2408,11 @@
err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
+ /* this can happen only for tmpfile being
+ * linked the first time
+ */
+ if (inode->i_nlink == 1)
+ ext4_orphan_del(handle, inode);
d_instantiate(dentry, inode);
} else {
drop_nlink(inode);
@@ -2577,6 +2620,7 @@
.mkdir = ext4_mkdir,
.rmdir = ext4_rmdir,
.mknod = ext4_mknod,
+ .tmpfile = ext4_tmpfile,
.rename = ext4_rename,
.setattr = ext4_setattr,
#ifdef CONFIG_EXT4_FS_XATTR
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index b8c9734..c5f6dce 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -124,7 +124,7 @@
}
static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
@@ -263,7 +263,7 @@
}
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct f2fs_dir_entry *de;
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 6637a9c..1099833 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -201,7 +201,7 @@
/***** Get inode using directory and name */
static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct fat_slot_info sinfo;
@@ -265,7 +265,7 @@
/***** Create a file */
static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode = NULL;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index a441d0a..75c5f39 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -41,9 +41,9 @@
return ret;
}
-static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int vfat_revalidate(struct dentry *dentry, unsigned int flags)
{
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
/* This is not negative dentry. Always valid. */
@@ -52,9 +52,9 @@
return vfat_revalidate_shortname(dentry);
}
-static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
+static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags)
{
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
/*
@@ -74,7 +74,7 @@
* This may be nfsd (or something), anyway, we can't see the
* intent of this. So, since this can be for creation, drop it.
*/
- if (!nd)
+ if (!flags)
return 0;
/*
@@ -82,7 +82,7 @@
* case sensitive name which is specified by user if this is
* for creation.
*/
- if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
return 0;
return vfat_revalidate_shortname(dentry);
@@ -714,7 +714,7 @@
}
static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct fat_slot_info sinfo;
@@ -772,7 +772,7 @@
}
static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 75e7c1f..281c0da 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -835,14 +835,14 @@
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
O_RDONLY | O_WRONLY | O_RDWR |
O_CREAT | O_EXCL | O_NOCTTY |
O_TRUNC | O_APPEND | /* O_NONBLOCK | */
__O_SYNC | O_DSYNC | FASYNC |
O_DIRECT | O_LARGEFILE | O_DIRECTORY |
O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- __FMODE_EXEC | O_PATH
+ __FMODE_EXEC | O_PATH | __O_TMPFILE
));
fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/filesystems.c b/fs/filesystems.c
index c412857..92567d9 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -124,7 +124,7 @@
static int fs_index(const char __user * __name)
{
struct file_system_type * tmp;
- char * name;
+ struct filename *name;
int err, index;
name = getname(__name);
@@ -135,7 +135,7 @@
err = -EINVAL;
read_lock(&file_systems_lock);
for (tmp=file_systems, index=0 ; tmp ; tmp=tmp->next, index++) {
- if (strcmp(tmp->name,name) == 0) {
+ if (strcmp(tmp->name, name->name) == 0) {
err = index;
break;
}
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 3360f1e..bd447e8 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -48,7 +48,7 @@
#define VXFS_BLOCK_PER_PAGE(sbp) ((PAGE_CACHE_SIZE / (sbp)->s_blocksize))
-static struct dentry * vxfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry * vxfs_lookup(struct inode *, struct dentry *, unsigned int);
static int vxfs_readdir(struct file *, void *, filldir_t);
const struct inode_operations vxfs_dir_inode_ops = {
@@ -203,7 +203,7 @@
* in the return pointer.
*/
static struct dentry *
-vxfs_lookup(struct inode *dip, struct dentry *dp, struct nameidata *nd)
+vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags)
{
struct inode *ip = NULL;
ino_t ino;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 6db7f1d..a7a7e99 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -154,7 +154,7 @@
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
-static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
+static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
{
struct inode *inode;
@@ -174,7 +174,7 @@
if (!inode)
return 0;
- if (nd && (nd->flags & LOOKUP_RCU))
+ if (flags & LOOKUP_RCU)
return -ECHILD;
fc = get_fuse_conn(inode);
@@ -361,7 +361,7 @@
}
static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
- struct nameidata *nd)
+ unsigned int flags)
{
int err;
struct fuse_entry_out outarg;
@@ -415,7 +415,8 @@
* 'mknod' + 'open' requests.
*/
static int fuse_create_open(struct inode *dir, struct dentry *entry,
- umode_t mode, struct nameidata *nd)
+ struct file *file, unsigned flags,
+ umode_t mode, int *opened)
{
int err;
struct inode *inode;
@@ -426,15 +427,11 @@
struct fuse_open_out outopen;
struct fuse_entry_out outentry;
struct fuse_file *ff;
- struct file *file;
- int flags = nd->intent.open.flags;
-
- if (fc->no_create)
- return -ENOSYS;
forget = fuse_alloc_forget();
+ err = -ENOMEM;
if (!forget)
- return -ENOMEM;
+ goto out_err;
req = fuse_get_req(fc);
err = PTR_ERR(req);
@@ -473,11 +470,8 @@
req->out.args[1].value = &outopen;
fuse_request_send(fc, req);
err = req->out.h.error;
- if (err) {
- if (err == -ENOSYS)
- fc->no_create = 1;
+ if (err)
goto out_free_ff;
- }
if (req->private_lower_rw_file != NULL)
ff->rw_lower_file = req->private_lower_rw_file;
@@ -496,28 +490,74 @@
flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
fuse_sync_release(ff, flags);
fuse_queue_forget(fc, forget, outentry.nodeid, 1);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto out_err;
}
kfree(forget);
d_instantiate(entry, inode);
fuse_change_entry_timeout(entry, &outentry);
fuse_invalidate_attr(dir);
- file = lookup_instantiate_filp(nd, entry, generic_file_open);
- if (IS_ERR(file)) {
+ err = finish_open(file, entry, generic_file_open, opened);
+ if (err) {
fuse_sync_release(ff, flags);
- return PTR_ERR(file);
+ } else {
+ file->private_data = fuse_file_get(ff);
+ fuse_finish_open(inode, file);
}
- file->private_data = fuse_file_get(ff);
- fuse_finish_open(inode, file);
- return 0;
-
- out_free_ff:
- fuse_file_free(ff);
- out_put_request:
- fuse_put_request(fc, req);
- out_put_forget_req:
- kfree(forget);
return err;
+
+out_free_ff:
+ fuse_file_free(ff);
+out_put_request:
+ fuse_put_request(fc, req);
+out_put_forget_req:
+ kfree(forget);
+out_err:
+ return err;
+}
+
+static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
+ struct file *file, unsigned flags,
+ umode_t mode, int *opened)
+{
+ int err;
+ struct fuse_conn *fc = get_fuse_conn(dir);
+ struct dentry *res = NULL;
+
+ if (d_unhashed(entry)) {
+ res = fuse_lookup(dir, entry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ entry = res;
+ }
+
+ if (!(flags & O_CREAT) || entry->d_inode)
+ goto no_open;
+
+ /* Only creates */
+ *opened |= FILE_CREATED;
+
+ if (fc->no_create)
+ goto mknod;
+
+ err = fuse_create_open(dir, entry, file, flags, mode, opened);
+ if (err == -ENOSYS) {
+ fc->no_create = 1;
+ goto mknod;
+ }
+out_dput:
+ dput(res);
+ return err;
+
+mknod:
+ err = fuse_mknod(dir, entry, mode, 0);
+ if (err)
+ goto out_dput;
+no_open:
+ return finish_no_open(file, res);
}
/*
@@ -619,14 +659,8 @@
}
static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- if (nd) {
- int err = fuse_create_open(dir, entry, mode, nd);
- if (err != -ENOSYS)
- return err;
- /* Fall back on mknod */
- }
return fuse_mknod(dir, entry, mode, 0);
}
@@ -1704,6 +1738,7 @@
.link = fuse_link,
.setattr = fuse_setattr,
.create = fuse_create,
+ .atomic_open = fuse_atomic_open,
.mknod = fuse_mknod,
.permission = fuse_permission,
.getattr = fuse_getattr,
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 0da8da2..4fddb3c 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -25,7 +25,7 @@
/**
* gfs2_drevalidate - Check directory lookup consistency
* @dentry: the mapping to check
- * @nd:
+ * @flags: lookup flags
*
* Check to make sure the lookup necessary to arrive at this inode from its
* parent is still good.
@@ -33,7 +33,7 @@
* Returns: 1 if the dentry is ok, 0 if it isn't
*/
-static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *parent;
struct gfs2_sbd *sdp;
@@ -44,7 +44,7 @@
int error;
int had_lock = 0;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index a836056..8aaeb07 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -821,7 +821,7 @@
struct buffer_head *bh;
struct gfs2_leaf *leaf;
struct gfs2_dirent *dent;
- struct qstr name = { .name = "", .len = 0, .hash = 0 };
+ struct qstr name = { .name = "" };
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
if (error)
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index a9ba244..8676747 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -755,11 +755,8 @@
*/
static int gfs2_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
- int excl = 0;
- if (nd && (nd->flags & LOOKUP_EXCL))
- excl = 1;
return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
}
@@ -775,7 +772,7 @@
*/
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (inode && !IS_ERR(inode)) {
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 62fc14e..422dde2 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -18,7 +18,7 @@
* hfs_lookup()
*/
static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
hfs_cat_rec rec;
struct hfs_find_data fd;
@@ -187,7 +187,7 @@
* the directory and the name (and its length) of the new file.
*/
static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
int res;
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 737dbeb..525fcfe 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -489,7 +489,7 @@
}
static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
hfs_cat_rec rec;
diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c
index 19cf291..91b91fd 100644
--- a/fs/hfs/sysdep.c
+++ b/fs/hfs/sysdep.c
@@ -13,12 +13,12 @@
/* dentry case-handling: just lowercase everything */
-static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd)
+static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
int diff;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 26b53fb..378ea0c 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -25,7 +25,7 @@
/* Find the entry inside dir named dentry->d_name */
static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct hfs_find_data fd;
@@ -465,7 +465,7 @@
}
static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return hfsplus_mknod(dir, dentry, mode, 0);
}
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 82b69ee..7009265 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -168,7 +168,7 @@
};
static struct dentry *hfsplus_file_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
struct hfs_find_data fd;
struct super_block *sb = dir->i_sb;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 07c516b..d3d3260 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -553,7 +553,7 @@
}
int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
char *name;
@@ -595,7 +595,7 @@
}
struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode;
char *name;
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 2fa0089..054a37e 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -189,7 +189,7 @@
* to tell read_inode to read fnode or not.
*/
-struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index de94617..942cd08 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -227,7 +227,7 @@
/* dir.c */
-struct dentry *hpfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+struct dentry *hpfs_lookup(struct inode *, struct dentry *, unsigned int);
extern const struct file_operations hpfs_dir_ops;
/* dnode.c */
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 30dd7b1..1006ff7 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -115,7 +115,7 @@
return err;
}
-static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index b73705f..7071a9d 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -138,7 +138,7 @@
}
static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *proc_dentry, *parent;
struct qstr *name = &dentry->d_name;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ff55307..126f89e 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -565,7 +565,7 @@
return retval;
}
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
diff --git a/fs/inode.c b/fs/inode.c
index 06d8bd4..dd2873b 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -333,8 +333,10 @@
*/
void inc_nlink(struct inode *inode)
{
- if (WARN_ON(inode->i_nlink == 0))
+ if (unlikely(inode->i_nlink == 0)) {
+ WARN_ON(!(inode->i_state & I_LINKABLE));
atomic_long_dec(&inode->i_sb->s_remove_count);
+ }
inode->__i_nlink++;
}
diff --git a/fs/internal.h b/fs/internal.h
index 7f89ecf..ed69dfc 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -81,22 +81,20 @@
/*
* open.c
*/
-struct nameidata;
-extern struct file *nameidata_to_filp(struct nameidata *);
-extern void release_open_intent(struct nameidata *);
struct open_flags {
int open_flag;
umode_t mode;
int acc_mode;
int intent;
};
-extern struct file *do_filp_open(int dfd, const char *pathname,
- const struct open_flags *op, int lookup_flags);
+extern struct file *do_filp_open(int dfd, struct filename *pathname,
+ const struct open_flags *op, int flags);
extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
const char *, const struct open_flags *, int lookup_flags);
extern long do_handle_open(int mountdirfd,
struct file_handle __user *ufh, int open_flag);
+extern int open_check_o_direct(struct file *f);
/*
* inode.c
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 0e73f63..3620ad1 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -114,7 +114,7 @@
int get_joliet_filename(struct iso_directory_record *, unsigned char *, struct inode *);
int get_acorn_filename(struct iso_directory_record *, char *, struct inode *);
-extern struct dentry *isofs_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int flags);
extern struct buffer_head *isofs_bread(struct inode *, sector_t);
extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long);
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 1e2946f..c167028 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -163,7 +163,7 @@
return 0;
}
-struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
int found;
unsigned long uninitialized_var(block);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index b560188..2324519 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -25,9 +25,9 @@
static int jffs2_readdir (struct file *, void *, filldir_t);
static int jffs2_create (struct inode *,struct dentry *,umode_t,
- struct nameidata *);
+ bool);
static struct dentry *jffs2_lookup (struct inode *,struct dentry *,
- struct nameidata *);
+ unsigned int);
static int jffs2_link (struct dentry *,struct inode *,struct dentry *);
static int jffs2_unlink (struct inode *,struct dentry *);
static int jffs2_symlink (struct inode *,struct dentry *,const char *);
@@ -74,7 +74,7 @@
nice and simple
*/
static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
- struct nameidata *nd)
+ unsigned int flags)
{
struct jffs2_inode_info *dir_f;
struct jffs2_full_dirent *fd = NULL, *fd_list;
@@ -175,7 +175,7 @@
static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct jffs2_raw_inode *ri;
struct jffs2_inode_info *f, *dir_f;
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 07c91ca..c426293 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -73,7 +73,7 @@
*
*/
static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int rc = 0;
tid_t tid; /* transaction id */
@@ -1436,7 +1436,7 @@
return rc;
}
-static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, unsigned int flags)
{
struct btstack btstack;
ino_t inum;
@@ -1570,7 +1570,7 @@
return result;
}
-static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags)
{
/*
* This is not negative dentry. Always valid.
@@ -1589,7 +1589,7 @@
* This may be nfsd (or something), anyway, we can't see the
* intent of this. So, since this can be for creation, drop it.
*/
- if (!nd)
+ if (!flags)
return 0;
/*
@@ -1597,7 +1597,7 @@
* case sensitive name which is specified by user if this is
* for creation.
*/
- if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
return 0;
return 1;
}
diff --git a/fs/libfs.c b/fs/libfs.c
index 65c126f..7231d37 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -53,7 +53,7 @@
* Lookup the data. This is trivial - if the dentry didn't already
* exist, we know it is negative. Set d_op to delete negative dentries.
*/
-struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
static const struct dentry_operations simple_dentry_operations = {
.d_delete = simple_delete_dentry,
@@ -68,7 +68,7 @@
int dcache_dir_open(struct inode *inode, struct file *file)
{
- static struct qstr cursor_name = {.len = 1, .name = "."};
+ static struct qstr cursor_name = QSTR_INIT(".", 1);
file->private_data = d_alloc(file->f_path.dentry, &cursor_name);
@@ -225,7 +225,7 @@
struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
struct dentry *dentry;
struct inode *root;
- struct qstr d_name = {.name = name, .len = strlen(name)};
+ struct qstr d_name = QSTR_INIT(name, strlen(name));
if (IS_ERR(s))
return ERR_CAST(s);
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index bea5d1b..26e4a94 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -349,7 +349,7 @@
}
static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct page *page;
struct logfs_disk_dentry *dd;
@@ -502,7 +502,7 @@
}
static int logfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 2d0ee17..cd950e2 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -18,7 +18,7 @@
return err;
}
-static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode = NULL;
ino_t ino;
@@ -54,8 +54,20 @@
return error;
}
+static int minix_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ int error;
+ struct inode *inode = minix_new_inode(dir, mode, &error);
+ if (inode) {
+ minix_set_inode(inode, 0);
+ mark_inode_dirty(inode);
+ d_tmpfile(dentry, inode);
+ }
+ return error;
+}
+
static int minix_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return minix_mknod(dir, dentry, mode, 0);
}
@@ -254,4 +266,5 @@
.mknod = minix_mknod,
.rename = minix_rename,
.getattr = minix_getattr,
+ .tmpfile = minix_tmpfile,
};
diff --git a/fs/namei.c b/fs/namei.c
index 792771b..909c01d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -116,63 +116,103 @@
* POSIX.1 2.4: an empty pathname is invalid (ENOENT).
* PATH_MAX includes the nul terminator --RR.
*/
-static int do_getname(const char __user *filename, char *page)
+void final_putname(struct filename *name)
{
- int retval;
- unsigned long len = PATH_MAX;
-
- if (!segment_eq(get_fs(), KERNEL_DS)) {
- if ((unsigned long) filename >= TASK_SIZE)
- return -EFAULT;
- if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
- len = TASK_SIZE - (unsigned long) filename;
+ if (name->separate) {
+ __putname(name->name);
+ kfree(name);
+ } else {
+ __putname(name);
}
-
- retval = strncpy_from_user(page, filename, len);
- if (retval > 0) {
- if (retval < len)
- return 0;
- return -ENAMETOOLONG;
- } else if (!retval)
- retval = -ENOENT;
- return retval;
}
-static char *getname_flags(const char __user *filename, int flags, int *empty)
-{
- char *result = __getname();
- int retval;
+#define EMBEDDED_NAME_MAX (PATH_MAX - sizeof(struct filename))
- if (!result)
+static struct filename *
+getname_flags(const char __user *filename, int flags, int *empty)
+{
+ struct filename *result, *err;
+ int len;
+ long max;
+ char *kname;
+
+ result = __getname();
+ if (unlikely(!result))
return ERR_PTR(-ENOMEM);
- retval = do_getname(filename, result);
- if (retval < 0) {
- if (retval == -ENOENT && empty)
- *empty = 1;
- if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
- __putname(result);
- return ERR_PTR(retval);
- }
+ /*
+ * First, try to embed the struct filename inside the names_cache
+ * allocation
+ */
+ kname = (char *)result + sizeof(*result);
+ result->name = kname;
+ result->separate = false;
+ max = EMBEDDED_NAME_MAX;
+
+recopy:
+ len = strncpy_from_user(kname, filename, max);
+ if (unlikely(len < 0)) {
+ err = ERR_PTR(len);
+ goto error;
}
+
+ /*
+ * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
+ * separate struct filename so we can dedicate the entire
+ * names_cache allocation for the pathname, and re-do the copy from
+ * userland.
+ */
+ if (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) {
+ kname = (char *)result;
+
+ result = kzalloc(sizeof(*result), GFP_KERNEL);
+ if (!result) {
+ err = ERR_PTR(-ENOMEM);
+ result = (struct filename *)kname;
+ goto error;
+ }
+ result->name = kname;
+ result->separate = true;
+ max = PATH_MAX;
+ goto recopy;
+ }
+
+ /* The empty path is special. */
+ if (unlikely(!len)) {
+ if (empty)
+ *empty = 1;
+ err = ERR_PTR(-ENOENT);
+ if (!(flags & LOOKUP_EMPTY))
+ goto error;
+ }
+
+ err = ERR_PTR(-ENAMETOOLONG);
+ if (unlikely(len >= PATH_MAX))
+ goto error;
+
+ result->uptr = filename;
audit_getname(result);
return result;
+
+error:
+ final_putname(result);
+ return err;
}
-char *getname(const char __user * filename)
+struct filename *
+getname(const char __user * filename)
{
return getname_flags(filename, 0, NULL);
}
+EXPORT_SYMBOL(getname);
#ifdef CONFIG_AUDITSYSCALL
-void putname(const char *name)
+void putname(struct filename *name)
{
if (unlikely(!audit_dummy_context()))
- audit_putname(name);
- else
- __putname(name);
+ return audit_putname(name);
+ final_putname(name);
}
-EXPORT_SYMBOL(putname);
#endif
static int check_acl(struct inode *inode, int mask)
@@ -435,6 +475,18 @@
* to restart the path walk from the beginning in ref-walk mode.
*/
+static inline void lock_rcu_walk(void)
+{
+ br_read_lock(&vfsmount_lock);
+ rcu_read_lock();
+}
+
+static inline void unlock_rcu_walk(void)
+{
+ rcu_read_unlock();
+ br_read_unlock(&vfsmount_lock);
+}
+
/**
* unlazy_walk - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
@@ -488,8 +540,7 @@
}
mntget(nd->path.mnt);
- rcu_read_unlock();
- br_read_unlock(&vfsmount_lock);
+ unlock_rcu_walk();
nd->flags &= ~LOOKUP_RCU;
return 0;
@@ -503,25 +554,9 @@
return -ECHILD;
}
-/**
- * release_open_intent - free up open intent resources
- * @nd: pointer to nameidata
- */
-void release_open_intent(struct nameidata *nd)
+static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
- struct file *file = nd->intent.open.file;
-
- if (file && !IS_ERR(file)) {
- if (file->f_path.dentry == NULL)
- put_filp(file);
- else
- fput(file);
- }
-}
-
-static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
- return dentry->d_op->d_revalidate(dentry, nd);
+ return dentry->d_op->d_revalidate(dentry, flags);
}
/**
@@ -546,15 +581,13 @@
spin_lock(&dentry->d_lock);
if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
spin_unlock(&dentry->d_lock);
- rcu_read_unlock();
- br_read_unlock(&vfsmount_lock);
+ unlock_rcu_walk();
return -ECHILD;
}
BUG_ON(nd->inode != dentry->d_inode);
spin_unlock(&dentry->d_lock);
mntget(nd->path.mnt);
- rcu_read_unlock();
- br_read_unlock(&vfsmount_lock);
+ unlock_rcu_walk();
}
if (likely(!(nd->flags & LOOKUP_JUMPED)))
@@ -567,7 +600,7 @@
return 0;
/* Note: we do not d_invalidate() */
- status = d_revalidate(dentry, nd);
+ status = d_revalidate(dentry, nd->flags);
if (status > 0)
return 0;
@@ -641,30 +674,158 @@
nd->path.dentry = path->dentry;
}
+/*
+ * Helper to directly jump to a known parsed path from ->follow_link,
+ * caller must have taken a reference to path beforehand.
+ */
+void nd_jump_link(struct nameidata *nd, struct path *path)
+{
+ path_put(&nd->path);
+
+ nd->path = *path;
+ nd->inode = nd->path.dentry->d_inode;
+ nd->flags |= LOOKUP_JUMPED;
+}
+
static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
{
struct inode *inode = link->dentry->d_inode;
- if (!IS_ERR(cookie) && inode->i_op->put_link)
+ if (inode->i_op->put_link)
inode->i_op->put_link(link->dentry, nd, cookie);
path_put(link);
}
+int sysctl_protected_symlinks __read_mostly = 0;
+int sysctl_protected_hardlinks __read_mostly = 0;
+
+/**
+ * may_follow_link - Check symlink following for unsafe situations
+ * @link: The path of the symlink
+ *
+ * In the case of the sysctl_protected_symlinks sysctl being enabled,
+ * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
+ * in a sticky world-writable directory. This is to protect privileged
+ * processes from failing races against path names that may change out
+ * from under them by way of other users creating malicious symlinks.
+ * It will permit symlinks to be followed only when outside a sticky
+ * world-writable directory, or when the uid of the symlink and follower
+ * match, or when the directory owner matches the symlink's owner.
+ *
+ * Returns 0 if following the symlink is allowed, -ve on error.
+ */
+static inline int may_follow_link(struct path *link, struct nameidata *nd)
+{
+ const struct inode *inode;
+ const struct inode *parent;
+
+ if (!sysctl_protected_symlinks)
+ return 0;
+
+ /* Allowed if owner and follower match. */
+ inode = link->dentry->d_inode;
+ if (current_cred()->fsuid == inode->i_uid)
+ return 0;
+
+ /* Allowed if parent directory not sticky and world-writable. */
+ parent = nd->path.dentry->d_inode;
+ if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
+ return 0;
+
+ /* Allowed if parent directory and link owner match. */
+ if (parent->i_uid == inode->i_uid)
+ return 0;
+
+ audit_log_link_denied("follow_link", link);
+ path_put_conditional(link, nd);
+ path_put(&nd->path);
+ return -EACCES;
+}
+
+/**
+ * safe_hardlink_source - Check for safe hardlink conditions
+ * @inode: the source inode to hardlink from
+ *
+ * Return false if at least one of the following conditions:
+ * - inode is not a regular file
+ * - inode is setuid
+ * - inode is setgid and group-exec
+ * - access failure for read and write
+ *
+ * Otherwise returns true.
+ */
+static bool safe_hardlink_source(struct inode *inode)
+{
+ umode_t mode = inode->i_mode;
+
+ /* Special files should not get pinned to the filesystem. */
+ if (!S_ISREG(mode))
+ return false;
+
+ /* Setuid files should not get pinned to the filesystem. */
+ if (mode & S_ISUID)
+ return false;
+
+ /* Executable setgid files should not get pinned to the filesystem. */
+ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
+ return false;
+
+ /* Hardlinking to unreadable or unwritable sources is dangerous. */
+ if (inode_permission(inode, MAY_READ | MAY_WRITE))
+ return false;
+
+ return true;
+}
+
+/**
+ * may_linkat - Check permissions for creating a hardlink
+ * @link: the source to hardlink from
+ *
+ * Block hardlink when all of:
+ * - sysctl_protected_hardlinks enabled
+ * - fsuid does not match inode
+ * - hardlink source is unsafe (see safe_hardlink_source() above)
+ * - not CAP_FOWNER
+ *
+ * Returns 0 if successful, -ve on error.
+ */
+static int may_linkat(struct path *link)
+{
+ const struct cred *cred;
+ struct inode *inode;
+
+ if (!sysctl_protected_hardlinks)
+ return 0;
+
+ cred = current_cred();
+ inode = link->dentry->d_inode;
+
+ /* Source inode owner (or CAP_FOWNER) can hardlink all they like,
+ * otherwise, it must be a safe source.
+ */
+ if (cred->fsuid == inode->i_uid || safe_hardlink_source(inode) ||
+ capable(CAP_FOWNER))
+ return 0;
+
+ audit_log_link_denied("linkat", link);
+ return -EPERM;
+}
+
static __always_inline int
follow_link(struct path *link, struct nameidata *nd, void **p)
{
- int error;
struct dentry *dentry = link->dentry;
+ int error;
+ char *s;
BUG_ON(nd->flags & LOOKUP_RCU);
if (link->mnt == nd->path.mnt)
mntget(link->mnt);
- if (unlikely(current->total_link_count >= 40)) {
- *p = ERR_PTR(-ELOOP); /* no ->put_link(), please */
- path_put(&nd->path);
- return -ELOOP;
- }
+ error = -ELOOP;
+ if (unlikely(current->total_link_count >= 40))
+ goto out_put_nd_path;
+
cond_resched();
current->total_link_count++;
@@ -672,30 +833,29 @@
nd_set_link(nd, NULL);
error = security_inode_follow_link(link->dentry, nd);
- if (error) {
- *p = ERR_PTR(error); /* no ->put_link(), please */
- path_put(&nd->path);
- return error;
- }
+ if (error)
+ goto out_put_nd_path;
nd->last_type = LAST_BIND;
*p = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(*p);
- if (!IS_ERR(*p)) {
- char *s = nd_get_link(nd);
- error = 0;
- if (s)
- error = __vfs_follow_link(nd, s);
- else if (nd->last_type == LAST_BIND) {
- nd->flags |= LOOKUP_JUMPED;
- nd->inode = nd->path.dentry->d_inode;
- if (nd->inode->i_op->follow_link) {
- /* stepped on a _really_ weird one */
- path_put(&nd->path);
- error = -ELOOP;
- }
- }
+ if (IS_ERR(*p))
+ goto out_put_nd_path;
+
+ error = 0;
+ s = nd_get_link(nd);
+ if (s) {
+ error = __vfs_follow_link(nd, s);
+ if (unlikely(error))
+ put_link(nd, link, *p);
}
+
+ return error;
+
+out_put_nd_path:
+ *p = NULL;
+ path_put(&nd->path);
+ path_put(link);
return error;
}
@@ -732,7 +892,7 @@
br_read_lock(&vfsmount_lock);
parent = mnt->mnt_parent;
- if (&parent->mnt == path->mnt) {
+ if (parent == mnt) {
br_read_unlock(&vfsmount_lock);
return 0;
}
@@ -998,8 +1158,7 @@
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
- rcu_read_unlock();
- br_read_unlock(&vfsmount_lock);
+ unlock_rcu_walk();
return -ECHILD;
}
@@ -1106,7 +1265,7 @@
* dir->d_inode->i_mutex must be held
*/
static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
- struct nameidata *nd, bool *need_lookup)
+ unsigned int flags, bool *need_lookup)
{
struct dentry *dentry;
int error;
@@ -1117,7 +1276,7 @@
if (d_need_lookup(dentry)) {
*need_lookup = true;
} else if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
- error = d_revalidate(dentry, nd);
+ error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
if (error < 0) {
dput(dentry);
@@ -1147,7 +1306,7 @@
* dir->d_inode->i_mutex must be held
*/
static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *old;
@@ -1157,7 +1316,7 @@
return ERR_PTR(-ENOENT);
}
- old = dir->i_op->lookup(dir, dentry, nd);
+ old = dir->i_op->lookup(dir, dentry, flags);
if (unlikely(old)) {
dput(dentry);
dentry = old;
@@ -1166,16 +1325,16 @@
}
static struct dentry *__lookup_hash(struct qstr *name,
- struct dentry *base, struct nameidata *nd)
+ struct dentry *base, unsigned int flags)
{
bool need_lookup;
struct dentry *dentry;
- dentry = lookup_dcache(name, base, nd, &need_lookup);
+ dentry = lookup_dcache(name, base, flags, &need_lookup);
if (!need_lookup)
return dentry;
- return lookup_real(base->d_inode, dentry, nd);
+ return lookup_real(base->d_inode, dentry, flags);
}
/*
@@ -1183,8 +1342,8 @@
* small and for now I'd prefer to have fast path as straight as possible.
* It _is_ time-critical.
*/
-static int do_lookup(struct nameidata *nd, struct qstr *name,
- struct path *path, struct inode **inode)
+static int lookup_fast(struct nameidata *nd, struct qstr *name,
+ struct path *path, struct inode **inode)
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
@@ -1199,12 +1358,25 @@
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
- *inode = nd->inode;
- dentry = __d_lookup_rcu(parent, name, &seq, inode);
+ dentry = __d_lookup_rcu(parent, name, &seq, nd->inode);
if (!dentry)
goto unlazy;
- /* Memory barrier in read_seqcount_begin of child is enough */
+ /*
+ * This sequence count validates that the inode matches
+ * the dentry name information from lookup.
+ */
+ *inode = dentry->d_inode;
+ if (read_seqcount_retry(&dentry->d_seq, seq))
+ return -ECHILD;
+
+ /*
+ * This sequence count validates that the parent had no
+ * changes while we did the lookup of the dentry above.
+ *
+ * The memory barrier in read_seqcount_begin of child is
+ * enough, we can use __read_seqcount_retry here.
+ */
if (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
nd->seq = seq;
@@ -1212,7 +1384,7 @@
if (unlikely(d_need_lookup(dentry)))
goto unlazy;
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
- status = d_revalidate(dentry, nd);
+ status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
if (status != -ECHILD)
need_reval = 0;
@@ -1242,7 +1414,7 @@
}
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
- status = d_revalidate(dentry, nd);
+ status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
if (status < 0) {
dput(dentry);
@@ -1253,7 +1425,7 @@
goto need_lookup;
}
}
-done:
+
path->mnt = mnt;
path->dentry = dentry;
err = follow_managed(path, nd->flags);
@@ -1267,14 +1439,34 @@
return 0;
need_lookup:
+ return 1;
+}
+
+/* Fast lookup failed, do it the slow way */
+static int lookup_slow(struct nameidata *nd, struct qstr *name,
+ struct path *path)
+{
+ struct dentry *dentry, *parent;
+ int err;
+
+ parent = nd->path.dentry;
BUG_ON(nd->inode != parent->d_inode);
mutex_lock(&parent->d_inode->i_mutex);
- dentry = __lookup_hash(name, parent, nd);
+ dentry = __lookup_hash(name, parent, nd->flags);
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- goto done;
+ path->mnt = nd->path.mnt;
+ path->dentry = dentry;
+ err = follow_managed(path, nd->flags);
+ if (unlikely(err < 0)) {
+ path_put_conditional(path, nd);
+ return err;
+ }
+ if (err)
+ nd->flags |= LOOKUP_JUMPED;
+ return 0;
}
static inline int may_lookup(struct nameidata *nd)
@@ -1309,8 +1501,7 @@
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
- rcu_read_unlock();
- br_read_unlock(&vfsmount_lock);
+ unlock_rcu_walk();
}
}
@@ -1346,22 +1537,27 @@
*/
if (unlikely(type != LAST_NORM))
return handle_dots(nd, type);
- err = do_lookup(nd, name, path, &inode);
+ err = lookup_fast(nd, name, path, &inode);
if (unlikely(err)) {
- terminate_walk(nd);
- return err;
+ if (err < 0)
+ goto out_err;
+
+ err = lookup_slow(nd, name, path);
+ if (err < 0)
+ goto out_err;
+
+ inode = path->dentry->d_inode;
}
- if (!inode) {
- path_to_nameidata(path, nd);
- terminate_walk(nd);
- return -ENOENT;
- }
+ err = -ENOENT;
+ if (!inode)
+ goto out_path_put;
+
if (should_follow_link(inode, follow)) {
if (nd->flags & LOOKUP_RCU) {
if (unlikely(nd->path.mnt != path->mnt ||
unlazy_walk(nd, path->dentry))) {
- terminate_walk(nd);
- return -ECHILD;
+ err = -ECHILD;
+ goto out_err;
}
}
BUG_ON(inode != path->dentry->d_inode);
@@ -1370,6 +1566,12 @@
path_to_nameidata(path, nd);
nd->inode = inode;
return 0;
+
+out_path_put:
+ path_to_nameidata(path, nd);
+out_err:
+ terminate_walk(nd);
+ return err;
}
/*
@@ -1398,9 +1600,10 @@
void *cookie;
res = follow_link(&link, nd, &cookie);
- if (!res)
- res = walk_component(nd, path, &nd->last,
- nd->last_type, LOOKUP_FOLLOW);
+ if (res)
+ break;
+ res = walk_component(nd, path, &nd->last,
+ nd->last_type, LOOKUP_FOLLOW);
put_link(nd, &link, cookie);
} while (res > 0);
@@ -1665,8 +1868,7 @@
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
- br_read_lock(&vfsmount_lock);
- rcu_read_lock();
+ lock_rcu_walk();
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
} else {
path_get(&nd->path);
@@ -1678,8 +1880,7 @@
if (*name=='/') {
if (flags & LOOKUP_RCU) {
- br_read_lock(&vfsmount_lock);
- rcu_read_lock();
+ lock_rcu_walk();
nd->seq = set_root_rcu(nd);
} else {
set_root(nd);
@@ -1691,8 +1892,7 @@
struct fs_struct *fs = current->fs;
unsigned seq;
- br_read_lock(&vfsmount_lock);
- rcu_read_lock();
+ lock_rcu_walk();
do {
seq = read_seqcount_begin(&fs->seq);
@@ -1729,8 +1929,7 @@
if (fput_needed)
*fp = file;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
- br_read_lock(&vfsmount_lock);
- rcu_read_lock();
+ lock_rcu_walk();
} else {
path_get(&file->f_path);
fput_light(file, fput_needed);
@@ -1791,10 +1990,14 @@
while (err > 0) {
void *cookie;
struct path link = path;
+ err = may_follow_link(&link, nd);
+ if (unlikely(err))
+ break;
nd->flags |= LOOKUP_PARENT;
err = follow_link(&link, nd, &cookie);
- if (!err)
- err = lookup_last(nd, &path);
+ if (err)
+ break;
+ err = lookup_last(nd, &path);
put_link(nd, &link, cookie);
}
}
@@ -1803,7 +2006,7 @@
err = complete_walk(nd);
if (!err && nd->flags & LOOKUP_DIRECTORY) {
- if (!nd->inode->i_op->lookup) {
+ if (!can_lookup(nd->inode)) {
path_put(&nd->path);
err = -ENOTDIR;
}
@@ -1829,24 +2032,33 @@
return err;
}
-static int do_path_lookup(int dfd, const char *name,
+static int filename_lookup(int dfd, struct filename *name,
unsigned int flags, struct nameidata *nd)
{
- int retval = path_lookupat(dfd, name, flags | LOOKUP_RCU, nd);
+ int retval = path_lookupat(dfd, name->name, flags | LOOKUP_RCU, nd);
if (unlikely(retval == -ECHILD))
- retval = path_lookupat(dfd, name, flags, nd);
+ retval = path_lookupat(dfd, name->name, flags, nd);
if (unlikely(retval == -ESTALE))
- retval = path_lookupat(dfd, name, flags | LOOKUP_REVAL, nd);
+ retval = path_lookupat(dfd, name->name,
+ flags | LOOKUP_REVAL, nd);
if (likely(!retval)) {
if (unlikely(!audit_dummy_context())) {
if (nd->path.dentry && nd->inode)
- audit_inode(name, nd->path.dentry);
+ audit_inode(name->name, nd->path.dentry);
}
}
return retval;
}
+static int do_path_lookup(int dfd, const char *name,
+ unsigned int flags, struct nameidata *nd)
+{
+ struct filename filename = { .name = name };
+
+ return filename_lookup(dfd, &filename, flags, nd);
+}
+
/* does lookup, returns the object with parent locked */
struct dentry *kern_path_locked(const char *name, struct path *path)
{
@@ -1860,7 +2072,7 @@
return ERR_PTR(-EINVAL);
}
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
- d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+ d = __lookup_hash(&nd.last, nd.path.dentry, 0);
if (IS_ERR(d)) {
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
@@ -1910,7 +2122,7 @@
*/
static struct dentry *lookup_hash(struct nameidata *nd)
{
- return __lookup_hash(&nd->last, nd->path.dentry, nd);
+ return __lookup_hash(&nd->last, nd->path.dentry, nd->flags);
}
/**
@@ -1939,6 +2151,11 @@
if (!len)
return ERR_PTR(-EACCES);
+ if (unlikely(name[0] == '.')) {
+ if (len < 2 || (len == 2 && name[1] == '.'))
+ return ERR_PTR(-EACCES);
+ }
+
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
@@ -1958,7 +2175,7 @@
if (err)
return ERR_PTR(err);
- return __lookup_hash(&this, base, NULL);
+ return __lookup_hash(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one_len2);
@@ -1972,13 +2189,13 @@
struct path *path, int *empty)
{
struct nameidata nd;
- char *tmp = getname_flags(name, flags, empty);
+ struct filename *tmp = getname_flags(name, flags, empty);
int err = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
BUG_ON(flags & LOOKUP_PARENT);
- err = do_path_lookup(dfd, tmp, flags, &nd);
+ err = filename_lookup(dfd, tmp, flags, &nd);
putname(tmp);
if (!err)
*path = nd.path;
@@ -1992,22 +2209,28 @@
return user_path_at_empty(dfd, name, flags, path, NULL);
}
-static int user_path_parent(int dfd, const char __user *path,
- struct nameidata *nd, char **name)
+/*
+ * NB: most callers don't do anything directly with the reference to the
+ * to struct filename, but the nd->last pointer points into the name string
+ * allocated by getname. So we must hold the reference to it until all
+ * path-walking is complete.
+ */
+static struct filename *
+user_path_parent(int dfd, const char __user *path, struct nameidata *nd)
{
- char *s = getname(path);
+ struct filename *s = getname(path);
int error;
if (IS_ERR(s))
- return PTR_ERR(s);
+ return s;
- error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd);
- if (error)
+ error = filename_lookup(dfd, s, LOOKUP_PARENT, nd);
+ if (error) {
putname(s);
- else
- *name = s;
+ return ERR_PTR(error);
+ }
- return error;
+ return s;
}
/*
@@ -2142,10 +2365,9 @@
}
int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool want_excl)
{
int error = may_create(mnt, dir, dentry);
-
if (error)
return error;
@@ -2156,7 +2378,7 @@
error = security_inode_create(dir, dentry, mode);
if (error)
return error;
- error = dir->i_op->create(dir, dentry, mode, nd);
+ error = dir->i_op->create(dir, dentry, mode, want_excl);
if (error)
return error;
@@ -2171,9 +2393,9 @@
EXPORT_SYMBOL(vfs_create2);
int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool want_excl)
{
- return vfs_create2(NULL, dir, dentry, mode, nd);
+ return vfs_create2(NULL, dir, dentry, mode, want_excl);
}
EXPORT_SYMBOL(vfs_create);
@@ -2259,20 +2481,281 @@
return flag;
}
+static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode)
+{
+ int error = security_path_mknod(dir, dentry, mode, 0);
+ if (error)
+ return error;
+
+ error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+ if (error)
+ return error;
+
+ return security_inode_create(dir->dentry->d_inode, dentry, mode);
+}
+
+/*
+ * Attempt to atomically look up, create and open a file from a negative
+ * dentry.
+ *
+ * Returns 0 if successful. The file will have been created and attached to
+ * @file by the filesystem calling finish_open().
+ *
+ * Returns 1 if the file was looked up only or didn't need creating. The
+ * caller will need to perform the open themselves. @path will have been
+ * updated to point to the new dentry. This may be negative.
+ *
+ * Returns an error code otherwise.
+ */
+static int atomic_open(struct nameidata *nd, struct dentry *dentry,
+ struct path *path, struct file *file,
+ const struct open_flags *op,
+ bool got_write, bool need_lookup,
+ int *opened)
+{
+ struct inode *dir = nd->path.dentry->d_inode;
+ unsigned open_flag = open_to_namei_flags(op->open_flag);
+ umode_t mode;
+ int error;
+ int acc_mode;
+ int create_error = 0;
+ struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
+
+ BUG_ON(dentry->d_inode);
+
+ /* Don't create child dentry for a dead directory. */
+ if (unlikely(IS_DEADDIR(dir))) {
+ error = -ENOENT;
+ goto out;
+ }
+
+ mode = op->mode;
+ if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
+ mode &= ~current_umask();
+
+ if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT)) {
+ open_flag &= ~O_TRUNC;
+ *opened |= FILE_CREATED;
+ }
+
+ /*
+ * Checking write permission is tricky, bacuse we don't know if we are
+ * going to actually need it: O_CREAT opens should work as long as the
+ * file exists. But checking existence breaks atomicity. The trick is
+ * to check access and if not granted clear O_CREAT from the flags.
+ *
+ * Another problem is returing the "right" error value (e.g. for an
+ * O_EXCL open we want to return EEXIST not EROFS).
+ */
+ if (((open_flag & (O_CREAT | O_TRUNC)) ||
+ (open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) {
+ if (!(open_flag & O_CREAT)) {
+ /*
+ * No O_CREATE -> atomicity not a requirement -> fall
+ * back to lookup + open
+ */
+ goto no_open;
+ } else if (open_flag & (O_EXCL | O_TRUNC)) {
+ /* Fall back and fail with the right error */
+ create_error = -EROFS;
+ goto no_open;
+ } else {
+ /* No side effects, safe to clear O_CREAT */
+ create_error = -EROFS;
+ open_flag &= ~O_CREAT;
+ }
+ }
+
+ if (open_flag & O_CREAT) {
+ error = may_o_create(&nd->path, dentry, mode);
+ if (error) {
+ create_error = error;
+ if (open_flag & O_EXCL)
+ goto no_open;
+ open_flag &= ~O_CREAT;
+ }
+ }
+
+ if (nd->flags & LOOKUP_DIRECTORY)
+ open_flag |= O_DIRECTORY;
+
+ file->f_path.dentry = DENTRY_NOT_SET;
+ file->f_path.mnt = nd->path.mnt;
+ error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode,
+ opened);
+ if (error < 0) {
+ if (create_error && error == -ENOENT)
+ error = create_error;
+ goto out;
+ }
+
+ acc_mode = op->acc_mode;
+ if (*opened & FILE_CREATED) {
+ fsnotify_create(dir, dentry);
+ acc_mode = MAY_OPEN;
+ }
+
+ if (error) { /* returned 1, that is */
+ if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+ error = -EIO;
+ goto out;
+ }
+ if (file->f_path.dentry) {
+ dput(dentry);
+ dentry = file->f_path.dentry;
+ }
+ if (create_error && dentry->d_inode == NULL) {
+ error = create_error;
+ goto out;
+ }
+ goto looked_up;
+ }
+
+ /*
+ * We didn't have the inode before the open, so check open permission
+ * here.
+ */
+ error = may_open(&file->f_path, acc_mode, open_flag);
+ if (error)
+ fput(file);
+
+out:
+ dput(dentry);
+ return error;
+
+no_open:
+ if (need_lookup) {
+ dentry = lookup_real(dir, dentry, nd->flags);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+
+ if (create_error) {
+ int open_flag = op->open_flag;
+
+ error = create_error;
+ if ((open_flag & O_EXCL)) {
+ if (!dentry->d_inode)
+ goto out;
+ } else if (!dentry->d_inode) {
+ goto out;
+ } else if ((open_flag & O_TRUNC) &&
+ S_ISREG(dentry->d_inode->i_mode)) {
+ goto out;
+ }
+ /* will fail later, go on to get the right error */
+ }
+ }
+looked_up:
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
+ return 1;
+}
+
+/*
+ * Look up and maybe create and open the last component.
+ *
+ * Must be called with i_mutex held on parent.
+ *
+ * Returns 0 if the file was successfully atomically created (if necessary) and
+ * opened. In this case the file will be returned attached to @file.
+ *
+ * Returns 1 if the file was not completely opened at this time, though lookups
+ * and creations will have been performed and the dentry returned in @path will
+ * be positive upon return if O_CREAT was specified. If O_CREAT wasn't
+ * specified then a negative dentry may be returned.
+ *
+ * An error code is returned otherwise.
+ *
+ * FILE_CREATE will be set in @*opened if the dentry was created and will be
+ * cleared otherwise prior to returning.
+ */
+static int lookup_open(struct nameidata *nd, struct path *path,
+ struct file *file,
+ const struct open_flags *op,
+ bool got_write, int *opened)
+{
+ struct dentry *dir = nd->path.dentry;
+ struct inode *dir_inode = dir->d_inode;
+ struct vfsmount *mnt = nd->path.mnt;
+ struct dentry *dentry;
+ int error;
+ bool need_lookup;
+
+ *opened &= ~FILE_CREATED;
+ dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+
+ /* Cached positive dentry: will open in f_op->open */
+ if (!need_lookup && dentry->d_inode)
+ goto out_no_open;
+
+ if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
+ return atomic_open(nd, dentry, path, file, op, got_write,
+ need_lookup, opened);
+ }
+
+ if (need_lookup) {
+ BUG_ON(dentry->d_inode);
+
+ dentry = lookup_real(dir_inode, dentry, nd->flags);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+ }
+
+ /* Negative dentry, just create the file */
+ if (!dentry->d_inode && (op->open_flag & O_CREAT)) {
+ umode_t mode = op->mode;
+ if (!IS_POSIXACL(dir->d_inode))
+ mode &= ~current_umask();
+ /*
+ * This write is needed to ensure that a
+ * rw->ro transition does not occur between
+ * the time when the file is created and when
+ * a permanent write count is taken through
+ * the 'struct file' in finish_open().
+ */
+ if (!got_write) {
+ error = -EROFS;
+ goto out_dput;
+ }
+ *opened |= FILE_CREATED;
+ error = security_path_mknod(&nd->path, dentry, mode, 0);
+ if (error)
+ goto out_dput;
+ error = vfs_create2(mnt, dir->d_inode, dentry, mode,
+ nd->flags & LOOKUP_EXCL);
+ if (error)
+ goto out_dput;
+ }
+out_no_open:
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
+ return 1;
+
+out_dput:
+ dput(dentry);
+ return error;
+}
+
/*
* Handle the last step of open()
*/
-static struct file *do_last(struct nameidata *nd, struct path *path,
- const struct open_flags *op, const char *pathname)
+static int do_last(struct nameidata *nd, struct path *path,
+ struct file *file, const struct open_flags *op,
+ int *opened, struct filename *name)
{
struct dentry *dir = nd->path.dentry;
- struct dentry *dentry;
int open_flag = op->open_flag;
- int will_truncate = open_flag & O_TRUNC;
- int want_write = 0;
+ bool will_truncate = (open_flag & O_TRUNC) != 0;
+ bool got_write = false;
int acc_mode = op->acc_mode;
- struct file *filp;
+ struct inode *inode;
+ bool symlink_ok = false;
+ struct path save_parent = { .dentry = NULL, .mnt = NULL };
+ bool retried = false;
int error;
+ const char *pathname = name->name;
nd->flags &= ~LOOKUP_PARENT;
nd->flags |= op->intent;
@@ -2282,120 +2765,112 @@
case LAST_DOT:
error = handle_dots(nd, nd->last_type);
if (error)
- return ERR_PTR(error);
+ return error;
/* fallthrough */
case LAST_ROOT:
error = complete_walk(nd);
if (error)
- return ERR_PTR(error);
+ return error;
audit_inode(pathname, nd->path.dentry);
if (open_flag & O_CREAT) {
error = -EISDIR;
- goto exit;
+ goto out;
}
- goto ok;
+ goto finish_open;
case LAST_BIND:
error = complete_walk(nd);
if (error)
- return ERR_PTR(error);
+ return error;
audit_inode(pathname, dir);
- goto ok;
+ goto finish_open;
}
if (!(open_flag & O_CREAT)) {
- int symlink_ok = 0;
if (nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
- symlink_ok = 1;
+ symlink_ok = true;
/* we _can_ be in RCU mode here */
- error = walk_component(nd, path, &nd->last, LAST_NORM,
- !symlink_ok);
+ error = lookup_fast(nd, &nd->last, path, &inode);
+ if (likely(!error))
+ goto finish_lookup;
+
if (error < 0)
- return ERR_PTR(error);
- if (error) /* symlink */
- return NULL;
- /* sayonara */
+ goto out;
+
+ BUG_ON(nd->inode != dir->d_inode);
+ } else {
+ /* create side of things */
+ /*
+ * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED
+ * has been cleared when we got to the last component we are
+ * about to look up
+ */
error = complete_walk(nd);
if (error)
- return ERR_PTR(error);
+ return error;
- error = -ENOTDIR;
- if (nd->flags & LOOKUP_DIRECTORY) {
- if (!nd->inode->i_op->lookup)
- goto exit;
- }
- audit_inode(pathname, nd->path.dentry);
- goto ok;
+ audit_inode(pathname, dir);
+ error = -EISDIR;
+ /* trailing slashes? */
+ if (nd->last.name[nd->last.len])
+ goto out;
}
- /* create side of things */
- /*
- * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been
- * cleared when we got to the last component we are about to look up
- */
- error = complete_walk(nd);
- if (error)
- return ERR_PTR(error);
-
- audit_inode(pathname, dir);
- error = -EISDIR;
- /* trailing slashes? */
- if (nd->last.name[nd->last.len])
- goto exit;
-
- mutex_lock(&dir->d_inode->i_mutex);
-
- dentry = lookup_hash(nd);
- error = PTR_ERR(dentry);
- if (IS_ERR(dentry)) {
- mutex_unlock(&dir->d_inode->i_mutex);
- goto exit;
- }
-
- path->dentry = dentry;
- path->mnt = nd->path.mnt;
-
- /* Negative dentry, just create the file */
- if (!dentry->d_inode) {
- umode_t mode = op->mode;
- if (!IS_POSIXACL(dir->d_inode))
- mode &= ~current_umask();
- /*
- * This write is needed to ensure that a
- * rw->ro transition does not occur between
- * the time when the file is created and when
- * a permanent write count is taken through
- * the 'struct file' in nameidata_to_filp().
- */
+retry_lookup:
+ if (op->open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
error = mnt_want_write(nd->path.mnt);
+ if (!error)
+ got_write = true;
+ /*
+ * do _not_ fail yet - we might not need that or fail with
+ * a different error; let lookup_open() decide; we'll be
+ * dropping this one anyway.
+ */
+ }
+ mutex_lock(&dir->d_inode->i_mutex);
+ error = lookup_open(nd, path, file, op, got_write, opened);
+ mutex_unlock(&dir->d_inode->i_mutex);
+
+ if (error <= 0) {
if (error)
- goto exit_mutex_unlock;
- want_write = 1;
+ goto out;
+
+ if ((*opened & FILE_CREATED) ||
+ !S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ will_truncate = false;
+
+ audit_inode(pathname, file->f_path.dentry);
+ goto opened;
+ }
+
+ if (*opened & FILE_CREATED) {
/* Don't check for write permission, don't truncate */
open_flag &= ~O_TRUNC;
- will_truncate = 0;
+ will_truncate = false;
acc_mode = MAY_OPEN;
- error = security_path_mknod(&nd->path, dentry, mode, 0);
- if (error)
- goto exit_mutex_unlock;
- error = vfs_create2(path->mnt, dir->d_inode, dentry, mode, nd);
- if (error)
- goto exit_mutex_unlock;
- mutex_unlock(&dir->d_inode->i_mutex);
- dput(nd->path.dentry);
- nd->path.dentry = dentry;
- goto common;
+ path_to_nameidata(path, nd);
+ goto finish_open_created;
}
/*
- * It already exists.
+ * create/update audit record if it already exists.
*/
- mutex_unlock(&dir->d_inode->i_mutex);
- audit_inode(pathname, path->dentry);
+ if (path->dentry->d_inode)
+ audit_inode(pathname, path->dentry);
+
+ /*
+ * If atomic_open() acquired write access it is dropped now due to
+ * possible mount and symlink following (this might be optimized away if
+ * necessary...)
+ */
+ if (got_write) {
+ mnt_drop_write(nd->path.mnt);
+ got_write = false;
+ }
error = -EEXIST;
- if (open_flag & O_EXCL)
+ if ((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))
goto exit_dput;
error = follow_managed(path, nd->flags);
@@ -2405,111 +2880,226 @@
if (error)
nd->flags |= LOOKUP_JUMPED;
+ BUG_ON(nd->flags & LOOKUP_RCU);
+ inode = path->dentry->d_inode;
+finish_lookup:
+ /* we _can_ be in RCU mode here */
error = -ENOENT;
- if (!path->dentry->d_inode)
- goto exit_dput;
+ if (!inode) {
+ path_to_nameidata(path, nd);
+ goto out;
+ }
- if (path->dentry->d_inode->i_op->follow_link)
- return NULL;
+ if (should_follow_link(inode, !symlink_ok)) {
+ if (nd->flags & LOOKUP_RCU) {
+ if (unlikely(unlazy_walk(nd, path->dentry))) {
+ error = -ECHILD;
+ goto out;
+ }
+ }
+ BUG_ON(inode != path->dentry->d_inode);
+ return 1;
+ }
- path_to_nameidata(path, nd);
- nd->inode = path->dentry->d_inode;
+ if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) {
+ path_to_nameidata(path, nd);
+ } else {
+ save_parent.dentry = nd->path.dentry;
+ save_parent.mnt = mntget(path->mnt);
+ nd->path.dentry = path->dentry;
+
+ }
+ nd->inode = inode;
/* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */
error = complete_walk(nd);
- if (error)
- return ERR_PTR(error);
+ if (error) {
+ path_put(&save_parent);
+ return error;
+ }
error = -EISDIR;
- if (S_ISDIR(nd->inode->i_mode))
- goto exit;
-ok:
+ if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode))
+ goto out;
+ error = -ENOTDIR;
+ if ((nd->flags & LOOKUP_DIRECTORY) && !can_lookup(nd->inode))
+ goto out;
+ audit_inode(pathname, nd->path.dentry);
+finish_open:
if (!S_ISREG(nd->inode->i_mode))
- will_truncate = 0;
+ will_truncate = false;
if (will_truncate) {
error = mnt_want_write(nd->path.mnt);
if (error)
- goto exit;
- want_write = 1;
+ goto out;
+ got_write = true;
}
-common:
+finish_open_created:
error = may_open(&nd->path, acc_mode, open_flag);
if (error)
- goto exit;
- filp = nameidata_to_filp(nd);
- if (!IS_ERR(filp)) {
- error = ima_file_check(filp, op->acc_mode);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
+ goto out;
+ file->f_path.mnt = nd->path.mnt;
+ error = finish_open(file, nd->path.dentry, NULL, opened);
+ if (error) {
+ if (error == -EOPENSTALE)
+ goto stale_open;
+ goto out;
}
- if (!IS_ERR(filp)) {
- if (will_truncate) {
- error = handle_truncate(filp);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- }
+opened:
+ error = open_check_o_direct(file);
+ if (error)
+ goto exit_fput;
+ error = ima_file_check(file, op->acc_mode);
+ if (error)
+ goto exit_fput;
+
+ if (will_truncate) {
+ error = handle_truncate(file);
+ if (error)
+ goto exit_fput;
}
out:
- if (want_write)
+ if (got_write)
mnt_drop_write(nd->path.mnt);
- path_put(&nd->path);
- return filp;
+ path_put(&save_parent);
+ terminate_walk(nd);
+ return error;
-exit_mutex_unlock:
- mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
path_put_conditional(path, nd);
-exit:
- filp = ERR_PTR(error);
goto out;
+exit_fput:
+ fput(file);
+ goto out;
+
+stale_open:
+ /* If no saved parent or already retried then can't retry */
+ if (!save_parent.dentry || retried)
+ goto out;
+
+ BUG_ON(save_parent.dentry != dir);
+ path_put(&nd->path);
+ nd->path = save_parent;
+ nd->inode = dir->d_inode;
+ save_parent.mnt = NULL;
+ save_parent.dentry = NULL;
+ if (got_write) {
+ mnt_drop_write(nd->path.mnt);
+ got_write = false;
+ }
+ retried = true;
+ goto retry_lookup;
}
-static struct file *path_openat(int dfd, const char *pathname,
+static int do_tmpfile(int dfd, struct filename *pathname,
+ struct nameidata *nd, int flags,
+ const struct open_flags *op,
+ struct file *file, int *opened)
+{
+ static const struct qstr name = QSTR_INIT("/", 1);
+ struct dentry *dentry, *child;
+ struct inode *dir;
+ int error = path_lookupat(dfd, pathname->name,
+ flags | LOOKUP_DIRECTORY, nd);
+ if (unlikely(error))
+ return error;
+ error = mnt_want_write(nd->path.mnt);
+ if (unlikely(error))
+ goto out;
+ /* we want directory to be writable */
+ error = inode_permission(nd->inode, MAY_WRITE | MAY_EXEC);
+ if (error)
+ goto out2;
+ dentry = nd->path.dentry;
+ dir = dentry->d_inode;
+ if (!dir->i_op->tmpfile) {
+ error = -EOPNOTSUPP;
+ goto out2;
+ }
+ child = d_alloc(dentry, &name);
+ if (unlikely(!child)) {
+ error = -ENOMEM;
+ goto out2;
+ }
+ nd->flags &= ~LOOKUP_DIRECTORY;
+ nd->flags |= op->intent;
+ dput(nd->path.dentry);
+ nd->path.dentry = child;
+ error = dir->i_op->tmpfile(dir, nd->path.dentry, op->mode);
+ if (error)
+ goto out2;
+ audit_inode(pathname->name, nd->path.dentry);
+ /* Don't check for other permissions, the inode was just created */
+ error = may_open(&nd->path, MAY_OPEN, op->open_flag);
+ if (error)
+ goto out2;
+ file->f_path.mnt = nd->path.mnt;
+ error = finish_open(file, nd->path.dentry, NULL, opened);
+ if (error)
+ goto out2;
+ error = open_check_o_direct(file);
+ if (error) {
+ fput(file);
+ } else if (!(op->open_flag & O_EXCL)) {
+ struct inode *inode = file->f_path.dentry->d_inode;
+ spin_lock(&inode->i_lock);
+ inode->i_state |= I_LINKABLE;
+ spin_unlock(&inode->i_lock);
+ }
+out2:
+ mnt_drop_write(nd->path.mnt);
+out:
+ path_put(&nd->path);
+ return error;
+}
+
+static struct file *path_openat(int dfd, struct filename *pathname,
struct nameidata *nd, const struct open_flags *op, int flags)
{
struct file *base = NULL;
- struct file *filp;
+ struct file *file;
struct path path;
+ int opened = 0;
int error;
- filp = get_empty_filp();
- if (!filp)
+ file = get_empty_filp();
+ if (!file)
return ERR_PTR(-ENFILE);
- filp->f_flags = op->open_flag;
- nd->intent.open.file = filp;
- nd->intent.open.flags = open_to_namei_flags(op->open_flag);
- nd->intent.open.create_mode = op->mode;
+ file->f_flags = op->open_flag;
- error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
+ if (unlikely(file->f_flags & __O_TMPFILE)) {
+ error = do_tmpfile(dfd, pathname, nd, flags, op, file, &opened);
+ goto out2;
+ }
+
+ error = path_init(dfd, pathname->name, flags | LOOKUP_PARENT, nd, &base);
if (unlikely(error))
- goto out_filp;
+ goto out;
current->total_link_count = 0;
- error = link_path_walk(pathname, nd);
+ error = link_path_walk(pathname->name, nd);
if (unlikely(error))
- goto out_filp;
+ goto out;
- filp = do_last(nd, &path, op, pathname);
- while (unlikely(!filp)) { /* trailing symlink */
+ error = do_last(nd, &path, file, op, &opened, pathname);
+ while (unlikely(error > 0)) { /* trailing symlink */
struct path link = path;
void *cookie;
if (!(nd->flags & LOOKUP_FOLLOW)) {
path_put_conditional(&path, nd);
path_put(&nd->path);
- filp = ERR_PTR(-ELOOP);
+ error = -ELOOP;
break;
}
+ error = may_follow_link(&link, nd);
+ if (unlikely(error))
+ break;
nd->flags |= LOOKUP_PARENT;
nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
error = follow_link(&link, nd, &cookie);
if (unlikely(error))
- filp = ERR_PTR(error);
- else
- filp = do_last(nd, &path, op, pathname);
+ break;
+ error = do_last(nd, &path, file, op, &opened, pathname);
put_link(nd, &link, cookie);
}
out:
@@ -2517,15 +3107,24 @@
path_put(&nd->root);
if (base)
fput(base);
- release_open_intent(nd);
- return filp;
-
-out_filp:
- filp = ERR_PTR(error);
- goto out;
+out2:
+ if (!(opened & FILE_OPENED)) {
+ BUG_ON(!error);
+ put_filp(file);
+ }
+ if (unlikely(error)) {
+ if (error == -EOPENSTALE) {
+ if (flags & LOOKUP_RCU)
+ error = -ECHILD;
+ else
+ error = -ESTALE;
+ }
+ file = ERR_PTR(error);
+ }
+ return file;
}
-struct file *do_filp_open(int dfd, const char *pathname,
+struct file *do_filp_open(int dfd, struct filename *pathname,
const struct open_flags *op, int flags)
{
struct nameidata nd;
@@ -2544,6 +3143,7 @@
{
struct nameidata nd;
struct file *file;
+ struct filename filename = { .name = name };
nd.root.mnt = mnt;
nd.root.dentry = dentry;
@@ -2553,11 +3153,11 @@
if (dentry->d_inode->i_op->follow_link && op->intent & LOOKUP_OPEN)
return ERR_PTR(-ELOOP);
- file = path_openat(-1, name, &nd, op, flags | LOOKUP_RCU);
+ file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_RCU);
if (unlikely(file == ERR_PTR(-ECHILD)))
- file = path_openat(-1, name, &nd, op, flags);
+ file = path_openat(-1, &filename, &nd, op, flags);
if (unlikely(file == ERR_PTR(-ESTALE)))
- file = path_openat(-1, name, &nd, op, flags | LOOKUP_REVAL);
+ file = path_openat(-1, &filename, &nd, op, flags | LOOKUP_REVAL);
return file;
}
@@ -2565,6 +3165,7 @@
{
struct dentry *dentry = ERR_PTR(-EEXIST);
struct nameidata nd;
+ int err2;
int error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd);
if (error)
return ERR_PTR(error);
@@ -2577,18 +3178,20 @@
goto out;
nd.flags &= ~LOOKUP_PARENT;
nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;
- nd.intent.open.flags = O_EXCL;
+ /* don't fail immediately if it's r/o, at least try to report other errors */
+ err2 = mnt_want_write(nd.path.mnt);
/*
* Do the final lookup.
*/
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
if (IS_ERR(dentry))
- goto fail;
+ goto unlock;
+ error = -EEXIST;
if (dentry->d_inode)
- goto eexist;
+ goto fail;
/*
* Special case - lookup gave negative, but... we had foo/bar/
* From the vfs_mknod() POV we just have a negative dentry -
@@ -2596,30 +3199,44 @@
* been asking for (non-existent) directory. -ENOENT for you.
*/
if (unlikely(!is_dir && nd.last.name[nd.last.len])) {
- dput(dentry);
- dentry = ERR_PTR(-ENOENT);
+ error = -ENOENT;
+ goto fail;
+ }
+ if (unlikely(err2)) {
+ error = err2;
goto fail;
}
*path = nd.path;
return dentry;
-eexist:
- dput(dentry);
- dentry = ERR_PTR(-EEXIST);
fail:
+ dput(dentry);
+ dentry = ERR_PTR(error);
+unlock:
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ if (!err2)
+ mnt_drop_write(nd.path.mnt);
out:
path_put(&nd.path);
return dentry;
}
EXPORT_SYMBOL(kern_path_create);
+void done_path_create(struct path *path, struct dentry *dentry)
+{
+ dput(dentry);
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
+ mnt_drop_write(path->mnt);
+ path_put(path);
+}
+EXPORT_SYMBOL(done_path_create);
+
struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir)
{
- char *tmp = getname(pathname);
+ struct filename *tmp = getname(pathname);
struct dentry *res;
if (IS_ERR(tmp))
return ERR_CAST(tmp);
- res = kern_path_create(dfd, tmp, path, is_dir);
+ res = kern_path_create(dfd, tmp->name, path, is_dir);
putname(tmp);
return res;
}
@@ -2632,8 +3249,7 @@
if (error)
return error;
- if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
- !ns_capable(inode_userns(dir), CAP_MKNOD))
+ if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
return -EPERM;
if (!dir->i_op->mknod)
@@ -2691,8 +3307,9 @@
struct path path;
int error;
- if (S_ISDIR(mode))
- return -EPERM;
+ error = may_mknod(mode);
+ if (error)
+ return error;
dentry = user_path_create(dfd, filename, &path, 0);
if (IS_ERR(dentry))
@@ -2700,18 +3317,12 @@
if (!IS_POSIXACL(path.dentry->d_inode))
mode &= ~current_umask();
- error = may_mknod(mode);
- if (error)
- goto out_dput;
- error = mnt_want_write(path.mnt);
- if (error)
- goto out_dput;
error = security_path_mknod(&path, dentry, mode, dev);
if (error)
- goto out_drop_write;
+ goto out;
switch (mode & S_IFMT) {
case 0: case S_IFREG:
- error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,NULL);
+ error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,true);
break;
case S_IFCHR: case S_IFBLK:
error = vfs_mknod2(path.mnt, path.dentry->d_inode,dentry,mode,
@@ -2721,12 +3332,8 @@
error = vfs_mknod(path.dentry->d_inode,dentry,mode,0);
break;
}
-out_drop_write:
- mnt_drop_write(path.mnt);
-out_dput:
- dput(dentry);
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
+out:
+ done_path_create(&path, dentry);
return error;
}
@@ -2780,19 +3387,10 @@
if (!IS_POSIXACL(path.dentry->d_inode))
mode &= ~current_umask();
- error = mnt_want_write(path.mnt);
- if (error)
- goto out_dput;
error = security_path_mkdir(&path, dentry, mode);
- if (error)
- goto out_drop_write;
- error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode);
-out_drop_write:
- mnt_drop_write(path.mnt);
-out_dput:
- dput(dentry);
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
+ if (!error)
+ error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode);
+ done_path_create(&path, dentry);
return error;
}
@@ -2872,13 +3470,13 @@
static long do_rmdir(int dfd, const char __user *pathname)
{
int error = 0;
- char * name;
+ struct filename *name;
struct dentry *dentry;
struct nameidata nd;
- error = user_path_parent(dfd, pathname, &nd, &name);
- if (error)
- return error;
+ name = user_path_parent(dfd, pathname, &nd);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
switch(nd.last_type) {
case LAST_DOTDOT:
@@ -2893,6 +3491,9 @@
}
nd.flags &= ~LOOKUP_PARENT;
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto exit1;
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
@@ -2903,19 +3504,15 @@
error = -ENOENT;
goto exit3;
}
- error = mnt_want_write(nd.path.mnt);
- if (error)
- goto exit3;
error = security_path_rmdir(&nd.path, dentry);
if (error)
- goto exit4;
+ goto exit3;
error = vfs_rmdir2(nd.path.mnt, nd.path.dentry->d_inode, dentry);
-exit4:
- mnt_drop_write(nd.path.mnt);
exit3:
dput(dentry);
exit2:
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ mnt_drop_write(nd.path.mnt);
exit1:
path_put(&nd.path);
putname(name);
@@ -2975,20 +3572,23 @@
static long do_unlinkat(int dfd, const char __user *pathname)
{
int error;
- char *name;
+ struct filename *name;
struct dentry *dentry;
struct nameidata nd;
struct inode *inode = NULL;
- error = user_path_parent(dfd, pathname, &nd, &name);
- if (error)
- return error;
+ name = user_path_parent(dfd, pathname, &nd);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
error = -EISDIR;
if (nd.last_type != LAST_NORM)
goto exit1;
nd.flags &= ~LOOKUP_PARENT;
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto exit1;
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
@@ -3001,21 +3601,17 @@
if (!inode)
goto slashes;
ihold(inode);
- error = mnt_want_write(nd.path.mnt);
- if (error)
- goto exit2;
error = security_path_unlink(&nd.path, dentry);
if (error)
- goto exit3;
+ goto exit2;
error = vfs_unlink2(nd.path.mnt, nd.path.dentry->d_inode, dentry);
-exit3:
- mnt_drop_write(nd.path.mnt);
- exit2:
+exit2:
dput(dentry);
}
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
if (inode)
iput(inode); /* truncate the inode here */
+ mnt_drop_write(nd.path.mnt);
exit1:
path_put(&nd.path);
putname(name);
@@ -3074,7 +3670,7 @@
int, newdfd, const char __user *, newname)
{
int error;
- char *from;
+ struct filename *from;
struct dentry *dentry;
struct path path;
@@ -3087,19 +3683,10 @@
if (IS_ERR(dentry))
goto out_putname;
- error = mnt_want_write(path.mnt);
- if (error)
- goto out_dput;
- error = security_path_symlink(&path, dentry, from);
- if (error)
- goto out_drop_write;
- error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from);
-out_drop_write:
- mnt_drop_write(path.mnt);
-out_dput:
- dput(dentry);
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
+ error = security_path_symlink(&path, dentry, from->name);
+ if (!error)
+ error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from->name);
+ done_path_create(&path, dentry);
out_putname:
putname(from);
return error;
@@ -3142,12 +3729,18 @@
mutex_lock(&inode->i_mutex);
/* Make sure we don't allow creating hardlink to an unlinked file */
- if (inode->i_nlink == 0)
+ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
error = -ENOENT;
else if (max_links && inode->i_nlink >= max_links)
error = -EMLINK;
else
error = dir->i_op->link(old_dentry, dir, new_dentry);
+
+ if (!error && (inode->i_state & I_LINKABLE)) {
+ spin_lock(&inode->i_lock);
+ inode->i_state &= ~I_LINKABLE;
+ spin_unlock(&inode->i_lock);
+ }
mutex_unlock(&inode->i_mutex);
if (!error)
fsnotify_link(dir, inode, new_dentry);
@@ -3206,19 +3799,15 @@
error = -EXDEV;
if (old_path.mnt != new_path.mnt)
goto out_dput;
- error = mnt_want_write(new_path.mnt);
- if (error)
+ error = may_linkat(&old_path);
+ if (unlikely(error))
goto out_dput;
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
- goto out_drop_write;
+ goto out_dput;
error = vfs_link2(old_path.mnt, old_path.dentry, new_path.dentry->d_inode, new_dentry);
-out_drop_write:
- mnt_drop_write(new_path.mnt);
out_dput:
- dput(new_dentry);
- mutex_unlock(&new_path.dentry->d_inode->i_mutex);
- path_put(&new_path);
+ done_path_create(&new_path, new_dentry);
out:
path_put(&old_path);
@@ -3399,17 +3988,21 @@
struct dentry *old_dentry, *new_dentry;
struct dentry *trap;
struct nameidata oldnd, newnd;
- char *from;
- char *to;
+ struct filename *from;
+ struct filename *to;
int error;
- error = user_path_parent(olddfd, oldname, &oldnd, &from);
- if (error)
+ from = user_path_parent(olddfd, oldname, &oldnd);
+ if (IS_ERR(from)) {
+ error = PTR_ERR(from);
goto exit;
+ }
- error = user_path_parent(newdfd, newname, &newnd, &to);
- if (error)
+ to = user_path_parent(newdfd, newname, &newnd);
+ if (IS_ERR(to)) {
+ error = PTR_ERR(to);
goto exit1;
+ }
error = -EXDEV;
if (oldnd.path.mnt != newnd.path.mnt)
@@ -3424,6 +4017,10 @@
if (newnd.last_type != LAST_NORM)
goto exit2;
+ error = mnt_want_write(oldnd.path.mnt);
+ if (error)
+ goto exit2;
+
oldnd.flags &= ~LOOKUP_PARENT;
newnd.flags &= ~LOOKUP_PARENT;
newnd.flags |= LOOKUP_RENAME_TARGET;
@@ -3459,23 +4056,19 @@
if (new_dentry == trap)
goto exit5;
- 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;
+ goto exit5;
error = vfs_rename2(oldnd.path.mnt, old_dir->d_inode, old_dentry,
new_dir->d_inode, new_dentry);
-exit6:
- mnt_drop_write(oldnd.path.mnt);
exit5:
dput(new_dentry);
exit4:
dput(old_dentry);
exit3:
unlock_rename(new_dir, old_dir);
+ mnt_drop_write(oldnd.path.mnt);
exit2:
path_put(&newnd.path);
putname(to);
@@ -3632,8 +4225,7 @@
EXPORT_SYMBOL(follow_down_one);
EXPORT_SYMBOL(follow_down);
EXPORT_SYMBOL(follow_up);
-EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
-EXPORT_SYMBOL(getname);
+EXPORT_SYMBOL(get_write_access); /* nfsd */
EXPORT_SYMBOL(lock_rename);
EXPORT_SYMBOL(page_follow_link_light);
EXPORT_SYMBOL(page_put_link);
diff --git a/fs/namespace.c b/fs/namespace.c
index f56d7dee..88fca9a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2445,7 +2445,7 @@
{
int ret;
char *kernel_type;
- char *kernel_dir;
+ struct filename *kernel_dir;
char *kernel_dev;
unsigned long data_page;
@@ -2467,7 +2467,7 @@
if (ret < 0)
goto out_data;
- ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags,
+ ret = do_mount(kernel_dev, kernel_dir->name, kernel_type, flags,
(void *) data_page);
free_page(data_page);
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index c1b2b54..4614b87 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -30,8 +30,8 @@
static int ncp_readdir(struct file *, void *, filldir_t);
-static int ncp_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
-static struct dentry *ncp_lookup(struct inode *, struct dentry *, struct nameidata *);
+static int ncp_create(struct inode *, struct dentry *, umode_t, bool);
+static struct dentry *ncp_lookup(struct inode *, struct dentry *, unsigned int);
static int ncp_unlink(struct inode *, struct dentry *);
static int ncp_mkdir(struct inode *, struct dentry *, umode_t);
static int ncp_rmdir(struct inode *, struct dentry *);
@@ -72,7 +72,7 @@
/*
* Dentry operations routines
*/
-static int ncp_lookup_validate(struct dentry *, struct nameidata *);
+static int ncp_lookup_validate(struct dentry *, unsigned int);
static int ncp_hash_dentry(const struct dentry *, const struct inode *,
struct qstr *);
static int ncp_compare_dentry(const struct dentry *, const struct inode *,
@@ -290,7 +290,7 @@
static int
-ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd)
+ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
{
struct ncp_server *server;
struct dentry *parent;
@@ -302,7 +302,7 @@
if (dentry == dentry->d_sb->s_root)
return 1;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
@@ -836,7 +836,7 @@
return result;
}
-static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct ncp_server *server = NCP_SERVER(dir);
struct inode *inode = NULL;
@@ -980,7 +980,7 @@
}
static int ncp_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return ncp_create_new(dir, dentry, mode, 0, 0);
}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8789210..18fc2f6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -46,8 +46,8 @@
static int nfs_opendir(struct inode *, struct file *);
static int nfs_closedir(struct inode *, struct file *);
static int nfs_readdir(struct file *, void *, filldir_t);
-static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
+static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
+static int nfs_create(struct inode *, struct dentry *, umode_t, bool);
static int nfs_mkdir(struct inode *, struct dentry *, umode_t);
static int nfs_rmdir(struct inode *, struct dentry *);
static int nfs_unlink(struct inode *, struct dentry *);
@@ -111,11 +111,13 @@
#ifdef CONFIG_NFS_V4
-static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_open_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd);
+static int nfs_atomic_open(struct inode *, struct dentry *,
+ struct file *, unsigned, umode_t,
+ int *);
const struct inode_operations nfs4_dir_inode_operations = {
- .create = nfs_open_create,
- .lookup = nfs_atomic_lookup,
+ .create = nfs_create,
+ .lookup = nfs_lookup,
+ .atomic_open = nfs_atomic_open,
.link = nfs_link,
.unlink = nfs_unlink,
.symlink = nfs_symlink,
@@ -477,10 +479,7 @@
static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
- struct qstr filename = {
- .len = entry->len,
- .name = entry->name,
- };
+ struct qstr filename = QSTR_INIT(entry->name, entry->len);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = parent->d_inode;
@@ -1009,27 +1008,14 @@
}
/*
- * Return the intent data that applies to this particular path component
- *
- * Note that the current set of intents only apply to the very last
- * component of the path and none of them is set before that last
- * component.
- */
-static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd,
- unsigned int mask)
-{
- return nd->flags & mask;
-}
-
-/*
* Use intent information to check whether or not we're going to do
* an O_EXCL create using this path component.
*/
-static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
+static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags)
{
if (NFS_PROTO(dir)->version == 2)
return 0;
- return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL);
+ return flags & LOOKUP_EXCL;
}
/*
@@ -1041,25 +1027,20 @@
*
*/
static inline
-int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd)
+int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
{
struct nfs_server *server = NFS_SERVER(inode);
if (IS_AUTOMOUNT(inode))
return 0;
- if (nd != NULL) {
- /* VFS wants an on-the-wire revalidation */
- if (nd->flags & LOOKUP_REVAL)
- goto out_force;
- /* This is an open(2) */
- if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 &&
- !(server->flags & NFS_MOUNT_NOCTO) &&
- (S_ISREG(inode->i_mode) ||
- S_ISDIR(inode->i_mode)))
- goto out_force;
- return 0;
- }
- return nfs_revalidate_inode(server, inode);
+ /* VFS wants an on-the-wire revalidation */
+ if (flags & LOOKUP_REVAL)
+ goto out_force;
+ /* This is an open(2) */
+ if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+ goto out_force;
+ return 0;
out_force:
return __nfs_revalidate_inode(server, inode);
}
@@ -1073,10 +1054,10 @@
*/
static inline
int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
/* Don't revalidate a negative dentry if we're creating a new file */
- if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0)
+ if (flags & LOOKUP_CREATE)
return 0;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
return 1;
@@ -1094,7 +1075,7 @@
* If the parent directory is seen to have changed, we throw out the
* cached dentry and do a new lookup.
*/
-static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *dir;
struct inode *inode;
@@ -1103,7 +1084,7 @@
struct nfs_fattr *fattr = NULL;
int error;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
@@ -1112,7 +1093,7 @@
inode = dentry->d_inode;
if (!inode) {
- if (nfs_neg_need_reval(dir, dentry, nd))
+ if (nfs_neg_need_reval(dir, dentry, flags))
goto out_bad;
goto out_valid;
}
@@ -1128,8 +1109,8 @@
goto out_set_verifier;
/* Force a full look up iff the parent directory has changed */
- if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) {
- if (nfs_lookup_verify_inode(inode, nd))
+ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) {
+ if (nfs_lookup_verify_inode(inode, flags))
goto out_zap_parent;
goto out_valid;
}
@@ -1263,7 +1244,7 @@
.d_release = nfs_d_release,
};
-static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *res;
struct dentry *parent;
@@ -1284,7 +1265,7 @@
* If we're doing an exclusive create, optimize away the lookup
* but don't hash the dentry.
*/
- if (nfs_is_exclusive_create(dir, nd)) {
+ if (nfs_is_exclusive_create(dir, flags)) {
d_instantiate(dentry, NULL);
res = NULL;
goto out;
@@ -1328,34 +1309,16 @@
}
#ifdef CONFIG_NFS_V4
-static int nfs_open_revalidate(struct dentry *, struct nameidata *);
+static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
const struct dentry_operations nfs4_dentry_operations = {
- .d_revalidate = nfs_open_revalidate,
+ .d_revalidate = nfs4_lookup_revalidate,
.d_delete = nfs_dentry_delete,
.d_iput = nfs_dentry_iput,
.d_automount = nfs_d_automount,
.d_release = nfs_d_release,
};
-/*
- * Use intent information to determine whether we need to substitute
- * the NFSv4-style stateful OPEN for the LOOKUP call
- */
-static int is_atomic_open(struct nameidata *nd)
-{
- if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0)
- return 0;
- /* NFS does not (yet) have a stateful open for directories */
- if (nd->flags & LOOKUP_DIRECTORY)
- return 0;
- /* Are we trying to write to a read only partition? */
- if (__mnt_is_readonly(nd->path.mnt) &&
- (nd->intent.open.flags & (O_CREAT|O_TRUNC|O_ACCMODE)))
- return 0;
- return 1;
-}
-
static fmode_t flags_to_mode(int flags)
{
fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
@@ -1377,138 +1340,143 @@
return 0;
}
-static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx)
+static int nfs_finish_open(struct nfs_open_context *ctx,
+ struct dentry *dentry,
+ struct file *file, unsigned open_flags,
+ int *opened)
{
- struct file *filp;
- int ret = 0;
+ int err;
+
+ if (ctx->dentry != dentry) {
+ dput(ctx->dentry);
+ ctx->dentry = dget(dentry);
+ }
/* If the open_intent is for execute, we have an extra check to make */
if (ctx->mode & FMODE_EXEC) {
- ret = nfs_may_open(ctx->dentry->d_inode,
- ctx->cred,
- nd->intent.open.flags);
- if (ret < 0)
+ err = nfs_may_open(dentry->d_inode, ctx->cred, open_flags);
+ if (err < 0)
goto out;
}
- filp = lookup_instantiate_filp(nd, ctx->dentry, do_open);
- if (IS_ERR(filp))
- ret = PTR_ERR(filp);
- else
- nfs_file_set_open_context(filp, ctx);
+
+ err = finish_open(file, dentry, do_open, opened);
+ if (err)
+ goto out;
+ nfs_file_set_open_context(file, ctx);
+
out:
put_nfs_open_context(ctx);
- return ret;
+ return err;
}
-static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned open_flags,
+ umode_t mode, int *opened)
{
struct nfs_open_context *ctx;
- struct iattr attr;
- struct dentry *res = NULL;
+ struct dentry *res;
+ struct iattr attr = { .ia_valid = ATTR_OPEN };
struct inode *inode;
- int open_flags;
int err;
- dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n",
+ /* Expect a negative dentry */
+ BUG_ON(dentry->d_inode);
+
+ dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n",
dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
- /* Check that we are indeed trying to open this file */
- if (!is_atomic_open(nd))
+ /* NFS only supports OPEN on regular files */
+ if ((open_flags & O_DIRECTORY)) {
+ if (!d_unhashed(dentry)) {
+ /*
+ * Hashed negative dentry with O_DIRECTORY: dentry was
+ * revalidated and is fine, no need to perform lookup
+ * again
+ */
+ return -ENOENT;
+ }
goto no_open;
-
- if (dentry->d_name.len > NFS_SERVER(dir)->namelen) {
- res = ERR_PTR(-ENAMETOOLONG);
- goto out;
}
- /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
- * the dentry. */
- if (nd->flags & LOOKUP_EXCL) {
- d_instantiate(dentry, NULL);
- goto out;
- }
+ if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
+ return -ENAMETOOLONG;
- open_flags = nd->intent.open.flags;
- attr.ia_valid = ATTR_OPEN;
-
- ctx = create_nfs_open_context(dentry, open_flags);
- res = ERR_CAST(ctx);
- if (IS_ERR(ctx))
- goto out;
-
- if (nd->flags & LOOKUP_CREATE) {
- attr.ia_mode = nd->intent.open.create_mode;
+ if (open_flags & O_CREAT) {
attr.ia_valid |= ATTR_MODE;
- attr.ia_mode &= ~current_umask();
- } else
- open_flags &= ~(O_EXCL | O_CREAT);
-
+ attr.ia_mode = mode & ~current_umask();
+ }
if (open_flags & O_TRUNC) {
attr.ia_valid |= ATTR_SIZE;
attr.ia_size = 0;
}
- /* Open the file on the server */
+ ctx = create_nfs_open_context(dentry, open_flags);
+ err = PTR_ERR(ctx);
+ if (IS_ERR(ctx))
+ goto out;
+
nfs_block_sillyrename(dentry->d_parent);
inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
+ d_drop(dentry);
if (IS_ERR(inode)) {
nfs_unblock_sillyrename(dentry->d_parent);
put_nfs_open_context(ctx);
- switch (PTR_ERR(inode)) {
- /* Make a negative dentry */
- case -ENOENT:
- d_add(dentry, NULL);
- res = NULL;
- goto out;
- /* This turned out not to be a regular file */
- case -EISDIR:
- case -ENOTDIR:
+ err = PTR_ERR(inode);
+ switch (err) {
+ case -ENOENT:
+ d_add(dentry, NULL);
+ break;
+ case -EISDIR:
+ case -ENOTDIR:
+ goto no_open;
+ case -ELOOP:
+ if (!(open_flags & O_NOFOLLOW))
goto no_open;
- case -ELOOP:
- if (!(nd->intent.open.flags & O_NOFOLLOW))
- goto no_open;
+ break;
/* case -EINVAL: */
- default:
- res = ERR_CAST(inode);
- goto out;
+ default:
+ break;
}
+ goto out;
}
res = d_add_unique(dentry, inode);
- nfs_unblock_sillyrename(dentry->d_parent);
- if (res != NULL) {
- dput(ctx->dentry);
- ctx->dentry = dget(res);
+ if (res != NULL)
dentry = res;
- }
- err = nfs_intent_set_file(nd, ctx);
- if (err < 0) {
- if (res != NULL)
- dput(res);
- return ERR_PTR(err);
- }
-out:
+
+ nfs_unblock_sillyrename(dentry->d_parent);
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- return res;
+
+ err = nfs_finish_open(ctx, dentry, file, open_flags, opened);
+
+ dput(res);
+out:
+ return err;
+
no_open:
- return nfs_lookup(dir, dentry, nd);
+ res = nfs_lookup(dir, dentry, 0);
+ err = PTR_ERR(res);
+ if (IS_ERR(res))
+ goto out;
+
+ return finish_no_open(file, res);
}
-static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *parent = NULL;
struct inode *inode;
struct inode *dir;
- struct nfs_open_context *ctx;
- struct iattr attr;
- int openflags, ret = 0;
+ int ret = 0;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
- inode = dentry->d_inode;
- if (!is_atomic_open(nd) || d_mountpoint(dentry))
+ if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
+ goto no_open;
+ if (d_mountpoint(dentry))
goto no_open;
+ inode = dentry->d_inode;
parent = dget_parent(dentry);
dir = parent->d_inode;
@@ -1516,7 +1484,7 @@
* optimize away revalidation of negative dentries.
*/
if (inode == NULL) {
- if (!nfs_neg_need_reval(dir, dentry, nd))
+ if (!nfs_neg_need_reval(dir, dentry, flags))
ret = 1;
goto out;
}
@@ -1524,107 +1492,21 @@
/* NFS only supports OPEN on regular files */
if (!S_ISREG(inode->i_mode))
goto no_open_dput;
- openflags = nd->intent.open.flags;
/* We cannot do exclusive creation on a positive dentry */
- if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
+ if (flags & LOOKUP_EXCL)
goto no_open_dput;
- /* We can't create new files here */
- openflags &= ~(O_CREAT|O_EXCL);
- ctx = create_nfs_open_context(dentry, openflags);
- ret = PTR_ERR(ctx);
- if (IS_ERR(ctx))
- goto out;
+ /* Let f_op->open() actually open (and revalidate) the file */
+ ret = 1;
- attr.ia_valid = ATTR_OPEN;
- if (openflags & O_TRUNC) {
- attr.ia_valid |= ATTR_SIZE;
- attr.ia_size = 0;
- nfs_wb_all(inode);
- }
-
- /*
- * Note: we're not holding inode->i_mutex and so may be racing with
- * operations that change the directory. We therefore save the
- * change attribute *before* we do the RPC call.
- */
- inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
- if (IS_ERR(inode)) {
- ret = PTR_ERR(inode);
- switch (ret) {
- case -EPERM:
- case -EACCES:
- case -EDQUOT:
- case -ENOSPC:
- case -EROFS:
- goto out_put_ctx;
- default:
- goto out_drop;
- }
- }
- iput(inode);
- if (inode != dentry->d_inode)
- goto out_drop;
-
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- ret = nfs_intent_set_file(nd, ctx);
- if (ret >= 0)
- ret = 1;
out:
dput(parent);
return ret;
-out_drop:
- d_drop(dentry);
- ret = 0;
-out_put_ctx:
- put_nfs_open_context(ctx);
- goto out;
no_open_dput:
dput(parent);
no_open:
- return nfs_lookup_revalidate(dentry, nd);
-}
-
-static int nfs_open_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
-{
- struct nfs_open_context *ctx = NULL;
- struct iattr attr;
- int error;
- int open_flags = O_CREAT|O_EXCL;
-
- dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
-
- attr.ia_mode = mode;
- attr.ia_valid = ATTR_MODE;
-
- if (nd)
- open_flags = nd->intent.open.flags;
-
- ctx = create_nfs_open_context(dentry, open_flags);
- error = PTR_ERR(ctx);
- if (IS_ERR(ctx))
- goto out_err_drop;
-
- error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx);
- if (error != 0)
- goto out_put_ctx;
- if (nd) {
- error = nfs_intent_set_file(nd, ctx);
- if (error < 0)
- goto out_err;
- } else {
- put_nfs_open_context(ctx);
- }
- return 0;
-out_put_ctx:
- put_nfs_open_context(ctx);
-out_err_drop:
- d_drop(dentry);
-out_err:
- return error;
+ return nfs_lookup_revalidate(dentry, flags);
}
#endif /* CONFIG_NFSV4 */
@@ -1678,11 +1560,11 @@
* reply path made it appear to have failed.
*/
static int nfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct iattr attr;
+ int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
int error;
- int open_flags = O_CREAT|O_EXCL;
dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1690,10 +1572,7 @@
attr.ia_mode = mode;
attr.ia_valid = ATTR_MODE;
- if (nd)
- open_flags = nd->intent.open.flags;
-
- error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL);
+ error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
if (error != 0)
goto out_err;
return 0;
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index aa9b709..dc45ada 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -871,12 +871,81 @@
static int
nfs4_file_open(struct inode *inode, struct file *filp)
{
+ struct nfs_open_context *ctx;
+ struct dentry *dentry = filp->f_path.dentry;
+ struct dentry *parent = NULL;
+ struct inode *dir;
+ unsigned openflags = filp->f_flags;
+ struct iattr attr;
+ int err;
+
+ BUG_ON(inode != dentry->d_inode);
/*
- * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
- * this point, then something is very wrong
+ * If no cached dentry exists or if it's negative, NFSv4 handled the
+ * opens in ->lookup() or ->create().
+ *
+ * We only get this far for a cached positive dentry. We skipped
+ * revalidation, so handle it here by dropping the dentry and returning
+ * -EOPENSTALE. The VFS will retry the lookup/create/open.
*/
- dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
- return -ENOTDIR;
+
+ dprintk("NFS: open file(%s/%s)\n",
+ dentry->d_parent->d_name.name,
+ dentry->d_name.name);
+
+ if ((openflags & O_ACCMODE) == 3)
+ openflags--;
+
+ /* We can't create new files here */
+ openflags &= ~(O_CREAT|O_EXCL);
+
+ parent = dget_parent(dentry);
+ dir = parent->d_inode;
+
+ ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode);
+ err = PTR_ERR(ctx);
+ if (IS_ERR(ctx))
+ goto out;
+
+ attr.ia_valid = ATTR_OPEN;
+ if (openflags & O_TRUNC) {
+ attr.ia_valid |= ATTR_SIZE;
+ attr.ia_size = 0;
+ nfs_wb_all(inode);
+ }
+
+ inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr);
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ switch (err) {
+ case -EPERM:
+ case -EACCES:
+ case -EDQUOT:
+ case -ENOSPC:
+ case -EROFS:
+ goto out_put_ctx;
+ default:
+ goto out_drop;
+ }
+ }
+ iput(inode);
+ if (inode != dentry->d_inode)
+ goto out_drop;
+
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ nfs_file_set_open_context(filp, ctx);
+ err = 0;
+
+out_put_ctx:
+ put_nfs_open_context(ctx);
+out:
+ dput(parent);
+ return err;
+
+out_drop:
+ d_drop(dentry);
+ err = -EOPENSTALE;
+ goto out_put_ctx;
}
const struct file_operations nfs4_file_operations = {
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 2ab36b4..50c1f24 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -314,7 +314,7 @@
*/
static int
nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
- int flags, struct nfs_open_context *ctx)
+ int flags)
{
struct nfs3_createdata *data;
umode_t mode = sattr->ia_mode;
@@ -398,8 +398,7 @@
{
struct nfs_removeargs arg = {
.fh = NFS_FH(dir),
- .name.len = name->len,
- .name.name = name->name,
+ .name = *name,
};
struct nfs_removeres res;
struct rpc_message msg = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index bf6b8df..ae6ba1d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2731,37 +2731,22 @@
}
/*
- * Got race?
- * We will need to arrange for the VFS layer to provide an atomic open.
- * Until then, this create/open method is prone to inefficiency and race
- * conditions due to the lookup, create, and open VFS calls from sys_open()
- * placed on the wire.
- *
- * Given the above sorry state of affairs, I'm simply sending an OPEN.
- * The file will be opened again in the subsequent VFS open call
- * (nfs4_proc_file_open).
- *
- * The open for read will just hang around to be used by any process that
- * opens the file O_RDONLY. This will all be resolved with the VFS changes.
+ * This is just for mknod. open(O_CREAT) will always do ->open_context().
*/
-
static int
nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
- int flags, struct nfs_open_context *ctx)
+ int flags)
{
- struct dentry *de = dentry;
+ struct nfs_open_context *ctx;
struct nfs4_state *state;
- struct rpc_cred *cred = NULL;
- fmode_t fmode = 0;
int status = 0;
- if (ctx != NULL) {
- cred = ctx->cred;
- de = ctx->dentry;
- fmode = ctx->mode;
- }
+ ctx = alloc_nfs_open_context(dentry, FMODE_READ);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
sattr->ia_mode &= ~current_umask();
- state = nfs4_do_open(dir, de, fmode, flags, sattr, cred);
+ state = nfs4_do_open(dir, dentry, ctx->mode, flags, sattr, ctx->cred);
d_drop(dentry);
if (IS_ERR(state)) {
status = PTR_ERR(state);
@@ -2769,11 +2754,9 @@
}
d_add(dentry, igrab(state->inode));
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- if (ctx != NULL)
- ctx->state = state;
- else
- nfs4_close_sync(state, fmode);
+ ctx->state = state;
out:
+ put_nfs_open_context(ctx);
return status;
}
@@ -2782,8 +2765,7 @@
struct nfs_server *server = NFS_SERVER(dir);
struct nfs_removeargs args = {
.fh = NFS_FH(dir),
- .name.len = name->len,
- .name.name = name->name,
+ .name = *name,
.bitmask = server->attr_bitmask,
};
struct nfs_removeres res = {
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index b63b6f4..636c662 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -259,7 +259,7 @@
static int
nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
- int flags, struct nfs_open_context *ctx)
+ int flags)
{
struct nfs_createdata *data;
struct rpc_message msg = {
@@ -335,8 +335,7 @@
{
struct nfs_removeargs arg = {
.fh = NFS_FH(dir),
- .name.len = name->len,
- .name.name = name->name,
+ .name = *name,
};
struct rpc_message msg = {
.rpc_proc = &nfs_procedures[NFSPROC_REMOVE],
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5686661..5beae3e 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1329,7 +1329,7 @@
err = 0;
switch (type) {
case S_IFREG:
- host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
if (!host_err)
nfsd_check_ignore_resizing(iap);
break;
@@ -1492,7 +1492,7 @@
goto out;
}
- host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
if (host_err < 0) {
fh_drop_write(fhp);
goto out_nfserr;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index fce2bbe..0ae1510 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -63,7 +63,7 @@
*/
static struct dentry *
-nilfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
ino_t ino;
@@ -85,7 +85,7 @@
* with d_instantiate().
*/
static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
struct nilfs_transaction_info ti;
@@ -441,7 +441,7 @@
{
unsigned long ino;
struct inode *inode;
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
struct nilfs_root *root;
ino = nilfs_inode_by_name(child->d_inode, &dotdot);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 5500124..fc1c5a8 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -22,6 +22,19 @@
#define FANOTIFY_DEFAULT_MAX_MARKS 8192
#define FANOTIFY_DEFAULT_MAX_LISTENERS 128
+/*
+ * All flags that may be specified in parameter event_f_flags of fanotify_init.
+ *
+ * Internal and external open flags are stored together in field f_flags of
+ * struct file. Only external open flags shall be allowed in event_f_flags.
+ * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
+ * excluded.
+ */
+#define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \
+ O_ACCMODE | O_APPEND | O_NONBLOCK | \
+ __O_SYNC | O_DSYNC | O_CLOEXEC | \
+ O_LARGEFILE | O_NOATIME )
+
extern const struct fsnotify_ops fanotify_fsnotify_ops;
static struct kmem_cache *fanotify_mark_cache __read_mostly;
@@ -691,6 +704,18 @@
if (flags & ~FAN_ALL_INIT_FLAGS)
return -EINVAL;
+ if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
+ return -EINVAL;
+
+ switch (event_f_flags & O_ACCMODE) {
+ case O_RDONLY:
+ case O_RDWR:
+ case O_WRONLY:
+ break;
+ default:
+ return -EINVAL;
+ }
+
user = get_current_user();
if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
free_uid(user);
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 358273e..436f360 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -101,7 +101,7 @@
* Locking: Caller must hold i_mutex on the directory.
*/
static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
- struct nameidata *nd)
+ unsigned int flags)
{
ntfs_volume *vol = NTFS_SB(dir_ino->i_sb);
struct inode *dent_inode;
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 26977cc..ab17f22 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -49,14 +49,13 @@
}
-static int ocfs2_dentry_revalidate(struct dentry *dentry,
- struct nameidata *nd)
+static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
int ret = 0; /* if all else fails, just return false */
struct ocfs2_super *osb;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 6e4f7c4..d66a30f 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -526,7 +526,7 @@
static int dlmfs_create(struct inode *dir,
struct dentry *dentry,
umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int status = 0;
struct inode *inode;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index a9856e3..50887f5 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -98,7 +98,7 @@
#define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
int status;
u64 blkno;
@@ -618,7 +618,7 @@
static int ocfs2_create(struct inode *dir,
struct dentry *dentry,
umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int ret;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 9f32d7c..30a0550 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4466,20 +4466,11 @@
goto out_dput;
}
- error = mnt_want_write(new_path.mnt);
- if (error) {
- mlog_errno(error);
- goto out_dput;
- }
-
error = ocfs2_vfs_reflink(old_path.dentry,
new_path.dentry->d_inode,
new_dentry, preserve);
- mnt_drop_write(new_path.mnt);
out_dput:
- dput(new_dentry);
- mutex_unlock(&new_path.dentry->d_inode->i_mutex);
- path_put(&new_path);
+ done_path_create(&new_path, new_dentry);
out:
path_put(&old_path);
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index f00576e..fb5b3ff 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -285,13 +285,13 @@
}
static int omfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return omfs_add_node(dir, dentry, mode | S_IFREG);
}
static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct buffer_head *bh;
struct inode *inode = NULL;
diff --git a/fs/open.c b/fs/open.c
index 45be216..ee0ff60 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -657,10 +657,23 @@
return error;
}
-static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
- struct file *f,
- int (*open)(struct inode *, struct file *),
- const struct cred *cred)
+int open_check_o_direct(struct file *f)
+{
+ /* NB: we're sure to have correct a_ops only after f_op->open */
+ if (f->f_flags & O_DIRECT) {
+ if (!f->f_mapping->a_ops ||
+ ((!f->f_mapping->a_ops->direct_IO) &&
+ (!f->f_mapping->a_ops->get_xip_mem))) {
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
+ struct file *f,
+ int (*open)(struct inode *, struct file *),
+ const struct cred *cred)
{
static const struct file_operations empty_fops = {};
struct inode *inode;
@@ -719,16 +732,6 @@
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
- /* NB: we're sure to have correct a_ops only after f_op->open */
- if (f->f_flags & O_DIRECT) {
- if (!f->f_mapping->a_ops ||
- ((!f->f_mapping->a_ops->direct_IO) &&
- (!f->f_mapping->a_ops->get_xip_mem))) {
- fput(f);
- f = ERR_PTR(-EINVAL);
- }
- }
-
return f;
cleanup_all:
@@ -749,76 +752,90 @@
f->f_path.dentry = NULL;
f->f_path.mnt = NULL;
cleanup_file:
- put_filp(f);
dput(dentry);
mntput(mnt);
return ERR_PTR(error);
}
+static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
+ struct file *f,
+ int (*open)(struct inode *, struct file *),
+ const struct cred *cred)
+{
+ struct file *res = do_dentry_open(dentry, mnt, f, open, cred);
+ if (!IS_ERR(res)) {
+ int error = open_check_o_direct(f);
+ if (error) {
+ fput(res);
+ res = ERR_PTR(error);
+ }
+ } else {
+ put_filp(f);
+ }
+ return res;
+}
+
/**
- * lookup_instantiate_filp - instantiates the open intent filp
- * @nd: pointer to nameidata
+ * finish_open - finish opening a file
+ * @file: file pointer
* @dentry: pointer to dentry
* @open: open callback
+ * @opened: state of open
*
- * Helper for filesystems that want to use lookup open intents and pass back
- * a fully instantiated struct file to the caller.
- * This function is meant to be called from within a filesystem's
- * lookup method.
- * Beware of calling it for non-regular files! Those ->open methods might block
- * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo,
- * leading to a deadlock, as nobody can open that fifo anymore, because
- * another process to open fifo will block on locked parent when doing lookup).
- * Note that in case of error, nd->intent.open.file is destroyed, but the
- * path information remains valid.
+ * This can be used to finish opening a file passed to i_op->atomic_open().
+ *
* If the open callback is set to NULL, then the standard f_op->open()
* filesystem callback is substituted.
+ *
+ * NB: the dentry reference is _not_ consumed. If, for example, the dentry is
+ * the return value of d_splice_alias(), then the caller needs to perform dput()
+ * on it after finish_open().
+ *
+ * On successful return @file is a fully instantiated open file. After this, if
+ * an error occurs in ->atomic_open(), it needs to clean up with fput().
+ *
+ * Returns zero on success or -errno if the open failed.
*/
-struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
- int (*open)(struct inode *, struct file *))
+int finish_open(struct file *file, struct dentry *dentry,
+ int (*open)(struct inode *, struct file *),
+ int *opened)
{
- const struct cred *cred = current_cred();
+ struct file *res;
+ BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
- if (IS_ERR(nd->intent.open.file))
- goto out;
- if (IS_ERR(dentry))
- goto out_err;
- nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
- nd->intent.open.file,
- open, cred);
-out:
- return nd->intent.open.file;
-out_err:
- release_open_intent(nd);
- nd->intent.open.file = ERR_CAST(dentry);
- goto out;
+ mntget(file->f_path.mnt);
+ dget(dentry);
+
+ res = do_dentry_open(dentry, file->f_path.mnt, file, open, current_cred());
+ if (!IS_ERR(res)) {
+ *opened |= FILE_OPENED;
+ return 0;
+ }
+
+ return PTR_ERR(res);
}
-EXPORT_SYMBOL_GPL(lookup_instantiate_filp);
+EXPORT_SYMBOL(finish_open);
/**
- * nameidata_to_filp - convert a nameidata to an open filp.
- * @nd: pointer to nameidata
- * @flags: open flags
+ * finish_no_open - finish ->atomic_open() without opening the file
*
- * Note that this function destroys the original nameidata
+ * @file: file pointer
+ * @dentry: dentry or NULL (as returned from ->lookup())
+ *
+ * This can be used to set the result of a successful lookup in ->atomic_open().
+ *
+ * NB: unlike finish_open() this function does consume the dentry reference and
+ * the caller need not dput() it.
+ *
+ * Returns "1" which must be the return value of ->atomic_open() after having
+ * called this function.
*/
-struct file *nameidata_to_filp(struct nameidata *nd)
+int finish_no_open(struct file *file, struct dentry *dentry)
{
- const struct cred *cred = current_cred();
- struct file *filp;
-
- /* Pick up the filp from the open intent */
- filp = nd->intent.open.file;
- nd->intent.open.file = NULL;
-
- /* Has the filesystem initialised the file for us? */
- if (filp->f_path.dentry == NULL) {
- path_get(&nd->path);
- filp = __dentry_open(nd->path.dentry, nd->path.mnt, filp,
- NULL, cred);
- }
- return filp;
+ file->f_path.dentry = dentry;
+ return 1;
}
+EXPORT_SYMBOL(finish_no_open);
/*
* dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
@@ -897,9 +914,10 @@
int lookup_flags = 0;
int acc_mode;
- if (!(flags & O_CREAT))
- mode = 0;
- op->mode = mode;
+ if (flags & (O_CREAT | __O_TMPFILE))
+ op->mode = (mode & S_IALLUGO) | S_IFREG;
+ else
+ op->mode = 0;
/* Must never be set by userspace */
flags &= ~FMODE_NONOTIFY;
@@ -913,11 +931,17 @@
if (flags & __O_SYNC)
flags |= O_DSYNC;
- /*
- * If we have O_PATH in the open flag. Then we
- * cannot have anything other than the below set of flags
- */
- if (flags & O_PATH) {
+ if (flags & __O_TMPFILE) {
+ if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
+ return -EINVAL;
+ acc_mode = MAY_OPEN | ACC_MODE(flags);
+ if (!(acc_mode & MAY_WRITE))
+ return -EINVAL;
+ } else if (flags & O_PATH) {
+ /*
+ * If we have O_PATH in the open flag. Then we
+ * cannot have anything other than the below set of flags
+ */
flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
acc_mode = 0;
} else {
@@ -953,6 +977,24 @@
}
/**
+ * file_open_name - open file and return file pointer
+ *
+ * @name: struct filename containing path to open
+ * @flags: open flags as per the open(2) second argument
+ * @mode: mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to. But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *file_open_name(struct filename *name, int flags, umode_t mode)
+{
+ struct open_flags op;
+ int lookup = build_open_flags(flags, mode, &op);
+ return do_filp_open(AT_FDCWD, name, &op, lookup);
+}
+
+/**
* filp_open - open file and return file pointer
*
* @filename: path to open
@@ -965,9 +1007,8 @@
*/
struct file *filp_open(const char *filename, int flags, umode_t mode)
{
- struct open_flags op;
- int lookup = build_open_flags(flags, mode, &op);
- return do_filp_open(AT_FDCWD, filename, &op, lookup);
+ struct filename name = {.name = filename};
+ return file_open_name(&name, flags, mode);
}
EXPORT_SYMBOL(filp_open);
@@ -989,7 +1030,7 @@
{
struct open_flags op;
int lookup = build_open_flags(flags, mode, &op);
- char *tmp = getname(filename);
+ struct filename *tmp = getname(filename);
int fd = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index 7e107f5..bce77df 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -170,13 +170,13 @@
.llseek = generic_file_llseek,
};
-static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, unsigned int);
static const struct inode_operations openprom_inode_operations = {
.lookup = openpromfs_lookup,
};
-static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct op_inode_info *ent_oi, *oi = OP_I(dir);
struct device_node *dp, *child;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 461927d..bf99be4 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1466,16 +1466,19 @@
static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
+ struct path path;
int error = -EACCES;
- /* We don't need a base pointer in the /proc filesystem */
- path_put(&nd->path);
-
/* Are we allowed to snoop on the tasks file descriptors? */
if (!proc_fd_access_allowed(inode))
goto out;
- error = PROC_I(inode)->op.proc_get_link(dentry, &nd->path);
+ error = PROC_I(inode)->op.proc_get_link(dentry, &path);
+ if (error)
+ goto out;
+
+ nd_jump_link(nd, &path);
+ return NULL;
out:
return ERR_PTR(error);
}
@@ -1640,13 +1643,13 @@
* made this apply to all per process world readable and executable
* directories.
*/
-int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
+int pid_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
const struct cred *cred;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
@@ -1820,7 +1823,7 @@
return proc_fd_info(dentry->d_inode, path, NULL);
}
-static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
@@ -1828,7 +1831,7 @@
struct files_struct *files;
const struct cred *cred;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
@@ -1904,7 +1907,7 @@
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (tid_fd_revalidate(dentry, NULL))
+ if (tid_fd_revalidate(dentry, 0))
error = NULL;
out:
@@ -1991,7 +1994,7 @@
}
static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
}
@@ -2038,7 +2041,7 @@
return 0;
}
-static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
bool exact_vma_exists = false;
@@ -2048,7 +2051,7 @@
struct inode *inode;
int status = 0;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
if (!capable(CAP_SYS_ADMIN)) {
@@ -2183,7 +2186,7 @@
}
static struct dentry *proc_map_files_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
struct vm_area_struct *vma;
@@ -2417,7 +2420,7 @@
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (tid_fd_revalidate(dentry, NULL))
+ if (tid_fd_revalidate(dentry, 0))
error = NULL;
out:
@@ -2426,7 +2429,7 @@
static struct dentry *proc_lookupfdinfo(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
}
@@ -2476,7 +2479,7 @@
d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
@@ -2676,7 +2679,7 @@
};
static struct dentry *proc_attr_dir_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
@@ -3088,7 +3091,8 @@
.llseek = default_llseek,
};
-static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
return proc_pident_lookup(dir, dentry,
tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
}
@@ -3211,13 +3215,13 @@
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
}
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *result;
struct task_struct *task;
@@ -3437,7 +3441,8 @@
tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
}
-static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
return proc_pident_lookup(dir, dentry,
tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
}
@@ -3475,13 +3480,13 @@
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
}
-static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *result = ERR_PTR(-ENOENT);
struct task_struct *task;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a1487e5..af8ac87 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -448,7 +448,7 @@
}
struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
return proc_lookup_de(PDE(dir), dir, dentry);
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 5f79bb8..8c5d6ba 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -107,7 +107,7 @@
extern spinlock_t proc_subdir_lock;
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int);
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
unsigned long task_vsize(struct mm_struct *);
unsigned long task_statm(struct mm_struct *,
@@ -133,7 +133,7 @@
* of the /proc/<pid> subdirectories.
*/
int proc_readdir(struct file *, void *, filldir_t);
-struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
+struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
@@ -143,7 +143,7 @@
int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
const char *name, int len,
instantiate_t instantiate, struct task_struct *task, const void *ptr);
-int pid_revalidate(struct dentry *dentry, struct nameidata *nd);
+int pid_revalidate(struct dentry *dentry, unsigned int flags);
struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task);
extern const struct dentry_operations pid_dentry_operations;
int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 08dfd6a..94aea23 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -114,7 +114,7 @@
struct super_block *sb = inode->i_sb;
struct proc_inode *ei = PROC_I(inode);
struct task_struct *task;
- struct dentry *ns_dentry;
+ struct path ns_path;
void *error = ERR_PTR(-EACCES);
task = get_proc_task(inode);
@@ -124,14 +124,14 @@
if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto out_put_task;
- ns_dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
- if (IS_ERR(ns_dentry)) {
- error = ERR_CAST(ns_dentry);
+ ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns_ops);
+ if (IS_ERR(ns_path.dentry)) {
+ error = ERR_CAST(ns_path.dentry);
goto out_put_task;
}
- dput(nd->path.dentry);
- nd->path.dentry = ns_dentry;
+ ns_path.mnt = mntget(nd->path.mnt);
+ nd_jump_link(nd, &ns_path);
error = NULL;
out_put_task:
@@ -203,7 +203,7 @@
d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
@@ -280,7 +280,7 @@
};
static struct dentry *proc_ns_dir_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
struct dentry *error;
struct task_struct *task = get_proc_task(dir);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 06e1cc1..fe72cd0 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -119,7 +119,7 @@
}
static struct dentry *proc_tgid_net_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
struct dentry *de;
struct net *net;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 668c397..bb63a08 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -434,7 +434,7 @@
}
static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct ctl_table_header *head = grab_header(dir);
struct ctl_table_header *h = NULL;
@@ -795,9 +795,9 @@
.getattr = proc_sys_getattr,
};
-static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
{
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
return !PROC_I(dentry->d_inode)->sysctl->unregistering;
}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index eed44bf..2344df0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -200,13 +200,12 @@
return 0;
}
-static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
- if (!proc_lookup(dir, dentry, nd)) {
+ if (!proc_lookup(dir, dentry, flags))
return NULL;
- }
- return proc_pid_lookup(dir, dentry, nd);
+ return proc_pid_lookup(dir, dentry, flags);
}
static int proc_root_readdir(struct file * filp,
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index a512c0b..d024505 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -95,7 +95,7 @@
return NULL;
}
-struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
int ino;
struct qnx4_inode_entry *de;
diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h
index 244d462..34e2d32 100644
--- a/fs/qnx4/qnx4.h
+++ b/fs/qnx4/qnx4.h
@@ -23,7 +23,7 @@
};
extern struct inode *qnx4_iget(struct super_block *, unsigned long);
-extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd);
+extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags);
extern unsigned long qnx4_count_free_blocks(struct super_block *sb);
extern unsigned long qnx4_block_map(struct inode *inode, long iblock);
diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c
index 8a97289..0561326 100644
--- a/fs/qnx6/namei.c
+++ b/fs/qnx6/namei.c
@@ -13,7 +13,7 @@
#include "qnx6.h"
struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
unsigned ino;
struct page *page;
diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h
index 6c5e02a..b00fcc9 100644
--- a/fs/qnx6/qnx6.h
+++ b/fs/qnx6/qnx6.h
@@ -45,7 +45,7 @@
extern struct inode *qnx6_iget(struct super_block *sb, unsigned ino);
extern struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
#ifdef CONFIG_QNX6FS_DEBUG
extern void qnx6_superblock_debug(struct qnx6_super_block *,
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index 9a39120..682b8201 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -315,11 +315,11 @@
#ifdef CONFIG_BLOCK
struct block_device *bdev;
struct super_block *sb;
- char *tmp = getname(special);
+ struct filename *tmp = getname(special);
if (IS_ERR(tmp))
return ERR_CAST(tmp);
- bdev = lookup_bdev(tmp);
+ bdev = lookup_bdev(tmp->name);
putname(tmp);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index a1fdabe..eab8c09 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -114,7 +114,7 @@
return retval;
}
-static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
return ramfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 84e8a69..3916be1 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -322,7 +322,7 @@
}
static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
int retval;
int lock_depth;
@@ -573,7 +573,7 @@
}
static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int retval;
struct inode *inode;
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 46fc1c2..d319963 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -62,7 +62,7 @@
static int xattr_create(struct inode *dir, struct dentry *dentry, int mode)
{
BUG_ON(!mutex_is_locked(&dir->i_mutex));
- return dir->i_op->create(dir, dentry, mode, NULL);
+ return dir->i_op->create(dir, dentry, mode, true);
}
#endif
@@ -942,7 +942,7 @@
return generic_permission(inode, mask);
}
-static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags)
{
return -EPERM;
}
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 590c390..0ecd71ce4 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -210,7 +210,7 @@
* look up an entry in a directory
*/
static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
unsigned long offset, maxoff;
struct inode *inode;
diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c
index bfb9ec1..b1fa0b8 100644
--- a/fs/sdcardfs/dentry.c
+++ b/fs/sdcardfs/dentry.c
@@ -26,7 +26,7 @@
* 0: tell VFS to invalidate dentry
* 1: dentry is valid
*/
-static int sdcardfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int err = 1;
struct path parent_lower_path, lower_path;
@@ -37,7 +37,7 @@
struct inode *inode;
struct sdcardfs_inode_data *data;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
spin_lock(&dentry->d_lock);
@@ -62,15 +62,9 @@
lower_cur_parent_dentry = dget_parent(lower_dentry);
if ((lower_dentry->d_flags & DCACHE_OP_REVALIDATE)) {
- struct path ptmp;
- if (nd) {
- pathcpy(&ptmp, &nd->path);
- pathcpy(&nd->path, &lower_path);
- }
- err = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
- if (nd)
- pathcpy(&nd->path, &ptmp);
+ err = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
if (err == 0) {
+ d_drop(dentry);
goto out;
}
}
@@ -78,12 +72,14 @@
spin_lock(&lower_dentry->d_lock);
if (d_unhashed(lower_dentry)) {
spin_unlock(&lower_dentry->d_lock);
+ d_drop(dentry);
err = 0;
goto out;
}
spin_unlock(&lower_dentry->d_lock);
if (parent_lower_dentry != lower_cur_parent_dentry) {
+ d_drop(dentry);
err = 0;
goto out;
}
@@ -97,6 +93,7 @@
}
if (!qstr_case_eq(&dentry->d_name, &lower_dentry->d_name)) {
+ __d_drop(dentry);
err = 0;
}
@@ -115,6 +112,7 @@
if (inode) {
data = top_data_get(SDCARDFS_I(inode));
if (!data || data->abandoned) {
+ d_drop(dentry);
err = 0;
}
if (data)
diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c
index 53f6c89..833e24a 100644
--- a/fs/sdcardfs/inode.c
+++ b/fs/sdcardfs/inode.c
@@ -61,7 +61,7 @@
}
static int sdcardfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool want_excl)
{
int err = 0;
struct dentry *lower_dentry;
@@ -99,9 +99,12 @@
err = -ENOMEM;
goto out_unlock;
}
+ copied_fs->umask = 0;
+ task_lock(current);
current->fs = copied_fs;
- current->fs->umask = 0;
- err = vfs_create2(lower_dentry_mnt, lower_parent_dentry->d_inode, lower_dentry, mode, nd);
+ task_unlock(current);
+
+ err = vfs_create2(lower_dentry_mnt, lower_parent_dentry->d_inode, lower_dentry, mode, want_excl);
if (err)
goto out;
@@ -115,7 +118,9 @@
out:
mnt_drop_write(lower_path.mnt);
+ task_lock(current);
current->fs = saved_fs;
+ task_unlock(current);
free_fs_struct(copied_fs);
out_unlock:
unlock_dir(lower_parent_dentry);
@@ -339,8 +344,11 @@
unlock_dir(lower_parent_dentry);
goto out_unlock;
}
+ copied_fs->umask = 0;
+ task_lock(current);
current->fs = copied_fs;
- current->fs->umask = 0;
+ task_unlock(current);
+
err = vfs_mkdir2(lower_mnt, lower_parent_dentry->d_inode, lower_dentry, mode);
if (err) {
@@ -401,7 +409,10 @@
}
out:
mnt_drop_write(lower_path.mnt);
+ task_lock(current);
current->fs = saved_fs;
+ task_unlock(current);
+
free_fs_struct(copied_fs);
out_unlock:
sdcardfs_put_lower_path(dentry, &lower_path);
diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c
index 06c95e3..34b6de0 100644
--- a/fs/sdcardfs/lookup.c
+++ b/fs/sdcardfs/lookup.c
@@ -227,7 +227,7 @@
* Fills in lower_parent_path with <dentry,mnt> on success.
*/
static struct dentry *__sdcardfs_lookup(struct dentry *dentry,
- struct nameidata *nd, struct path *lower_parent_path, userid_t id)
+ unsigned int flags, struct path *lower_parent_path, userid_t id)
{
int err = 0;
struct vfsmount *lower_dir_mnt;
@@ -356,10 +356,7 @@
* the VFS will continue the process of making this negative dentry
* into a positive one.
*/
- if (nd) {
- if (nd->flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET))
- err = 0;
- } else
+ if (flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET))
err = 0;
out:
@@ -380,7 +377,7 @@
* @nd : nameidata of parent inode
*/
struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *ret = NULL, *parent;
struct path lower_parent_path;
@@ -406,7 +403,7 @@
goto out;
}
- ret = __sdcardfs_lookup(dentry, nd, &lower_parent_path,
+ ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path,
SDCARDFS_I(dir)->data->userid);
if (IS_ERR(ret))
goto out;
diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c
index 86e0447..9c147e6 100644
--- a/fs/sdcardfs/main.c
+++ b/fs/sdcardfs/main.c
@@ -218,10 +218,7 @@
struct dentry *ret = NULL;
if (sb) {
- static const struct qstr name = {
- .name = "/",
- .len = 1
- };
+ static const struct qstr name = QSTR_INIT("/", 1);
ret = d_alloc(NULL, &name);
if (ret) {
diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h
index d31216c..c47e237 100644
--- a/fs/sdcardfs/sdcardfs.h
+++ b/fs/sdcardfs/sdcardfs.h
@@ -169,7 +169,7 @@
extern int new_dentry_private_data(struct dentry *dentry);
extern void free_dentry_private_data(struct dentry *dentry);
extern struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
extern struct inode *sdcardfs_iget(struct super_block *sb,
struct inode *lower_inode, userid_t id);
extern int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb,
@@ -673,7 +673,6 @@
return q1->len == q2->len && str_n_case_eq(q1->name, q2->name, q2->len);
}
-#define QSTR_INIT(n, l) { .name = n, .len = l }
#define QSTR_LITERAL(string) QSTR_INIT(string, sizeof(string)-1)
#endif /* not _SDCARDFS_H_ */
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index abcc58f..7834a51 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -134,7 +134,7 @@
static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
const unsigned char *name = dentry->d_name.name;
int len = dentry->d_name.len;
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 35a36d3..9d0c0a4 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -282,12 +282,12 @@
return !!(sd->s_flags & SYSFS_FLAG_REMOVED);
}
-static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
struct sysfs_dirent *sd;
int is_dir;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
sd = dentry->d_fsdata;
@@ -743,7 +743,7 @@
}
static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *ret = NULL;
struct dentry *parent = dentry->d_parent;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index d7466e2..1c0d5f2 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -43,7 +43,7 @@
.d_hash = sysv_hash,
};
-static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
struct inode * inode = NULL;
ino_t ino;
@@ -80,7 +80,7 @@
return err;
}
-static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd)
+static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
{
return sysv_mknod(dir, dentry, mode, 0);
}
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 4358a92..8b2914d 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -192,7 +192,7 @@
#endif
static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
int err;
union ubifs_key key;
@@ -254,7 +254,7 @@
}
static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
struct ubifs_info *c = dir->i_sb->s_fs_info;
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 16ad84d..abd5133 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2361,7 +2361,7 @@
* by passing 'ubifs_tnc_remove_nm()' the same key but
* an unmatchable name.
*/
- struct qstr noname = { .len = 0, .name = "" };
+ struct qstr noname = { .name = "" };
err = dbg_check_tnc(c, 0);
mutex_unlock(&c->tnc_mutex);
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 85b2722..7a8bafa 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -298,7 +298,7 @@
{
struct inode *inode, *host = dentry->d_inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
- struct qstr nm = { .name = name, .len = strlen(name) };
+ struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_dent_node *xent;
union ubifs_key key;
int err, type;
@@ -361,7 +361,7 @@
{
struct inode *inode, *host = dentry->d_inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
- struct qstr nm = { .name = name, .len = strlen(name) };
+ struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_inode *ui;
struct ubifs_dent_node *xent;
union ubifs_key key;
@@ -524,7 +524,7 @@
{
struct inode *inode, *host = dentry->d_inode;
struct ubifs_info *c = host->i_sb->s_fs_info;
- struct qstr nm = { .name = name, .len = strlen(name) };
+ struct qstr nm = QSTR_INIT(name, strlen(name));
struct ubifs_dent_node *xent;
union ubifs_key key;
int err;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 5c3bb75..e50340d 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -252,7 +252,7 @@
}
static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct fileIdentDesc cfi;
@@ -552,7 +552,7 @@
}
static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct udf_fileident_bh fibh;
struct inode *inode;
@@ -1194,7 +1194,7 @@
{
struct kernel_lb_addr tloc;
struct inode *inode = NULL;
- struct qstr dotdot = {.name = "..", .len = 2};
+ struct qstr dotdot = QSTR_INIT("..", 2);
struct fileIdentDesc cfi;
struct udf_fileident_bh fibh;
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index a2281ca..90d74b8 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -46,7 +46,7 @@
return err;
}
-static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode = NULL;
ino_t ino;
@@ -71,7 +71,7 @@
* with d_instantiate().
*/
static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
int err;
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 26f6cd6..b87b69a 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -146,10 +146,7 @@
static struct dentry *ufs_get_parent(struct dentry *child)
{
- struct qstr dot_dot = {
- .name = "..",
- .len = 2,
- };
+ struct qstr dot_dot = QSTR_INIT("..", 2);
ino_t ino;
ino = ufs_inode_by_name(child->d_inode, &dot_dot);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 3011b87..8129b84 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -182,7 +182,7 @@
struct inode *dir,
struct dentry *dentry,
umode_t mode,
- struct nameidata *nd)
+ bool flags)
{
return xfs_vn_mknod(dir, dentry, mode, 0);
}
@@ -200,7 +200,7 @@
xfs_vn_lookup(
struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct xfs_inode *cip;
struct xfs_name name;
@@ -225,7 +225,7 @@
xfs_vn_ci_lookup(
struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct xfs_inode *ip;
struct xfs_name xname;
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index 9e5b035..1add79f 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -84,6 +84,14 @@
#define O_PATH 010000000
#endif
+#ifndef __O_TMPFILE
+#define __O_TMPFILE 020000000
+#endif
+
+/* a horrid kludge trying to make sure that this will fail on old kernels */
+#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
+#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)
+
#ifndef O_NDELAY
#define O_NDELAY O_NONBLOCK
#endif
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 22f292a..23c2be7 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -130,6 +130,7 @@
#define AUDIT_LAST_KERN_ANOM_MSG 1799
#define AUDIT_ANOM_PROMISCUOUS 1700 /* Device changed promiscuous mode */
#define AUDIT_ANOM_ABEND 1701 /* Process ended abnormally */
+#define AUDIT_ANOM_LINK 1702 /* Suspicious use of file links */
#define AUDIT_INTEGRITY_DATA 1800 /* Data integrity verification */
#define AUDIT_INTEGRITY_METADATA 1801 /* Metadata integrity verification */
#define AUDIT_INTEGRITY_STATUS 1802 /* Integrity enable status */
@@ -449,6 +450,9 @@
extern int __init audit_register_class(int class, unsigned *list);
extern int audit_classify_syscall(int abi, unsigned syscall);
extern int audit_classify_arch(int arch);
+
+struct filename;
+
#ifdef CONFIG_AUDITSYSCALL
/* These are defined in auditsc.c */
/* Public API */
@@ -458,8 +462,8 @@
int major, unsigned long a0, unsigned long a1,
unsigned long a2, unsigned long a3);
extern void __audit_syscall_exit(int ret_success, long ret_value);
-extern void __audit_getname(const char *name);
-extern void audit_putname(const char *name);
+extern void __audit_getname(struct filename *name);
+extern void audit_putname(struct filename *name);
extern void __audit_inode(const char *name, const struct dentry *dentry);
extern void __audit_inode_child(const struct dentry *dentry,
const struct inode *parent);
@@ -492,7 +496,7 @@
__audit_syscall_exit(success, return_code);
}
}
-static inline void audit_getname(const char *name)
+static inline void audit_getname(struct filename *name)
{
if (unlikely(!audit_dummy_context()))
__audit_getname(name);
@@ -687,6 +691,8 @@
const struct path *path);
extern void audit_log_key(struct audit_buffer *ab,
char *key);
+extern void audit_log_link_denied(const char *operation,
+ struct path *link);
extern void audit_log_lost(const char *message);
#ifdef CONFIG_SECURITY
extern void audit_log_secctx(struct audit_buffer *ab, u32 secid);
@@ -716,6 +722,7 @@
#define audit_log_untrustedstring(a,s) do { ; } while (0)
#define audit_log_d_path(b, p, d) do { ; } while (0)
#define audit_log_key(b, k) do { ; } while (0)
+#define audit_log_link_denied(o, l) do { ; } while (0)
#define audit_log_secctx(b,s) do { ; } while (0)
#define audit_enabled 0
#endif
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 23301a0..a39ee4b 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -25,6 +25,13 @@
#define IS_ROOT(x) ((x) == (x)->d_parent)
+/* The hash is always the low bits of hash_len */
+#ifdef __LITTLE_ENDIAN
+ #define HASH_LEN_DECLARE u32 hash; u32 len;
+#else
+ #define HASH_LEN_DECLARE u32 len; u32 hash;
+#endif
+
/*
* "quick string" -- eases parameter passing, but more importantly
* saves "metadata" about the string (ie length and the hash).
@@ -33,11 +40,19 @@
* dentry.
*/
struct qstr {
- unsigned int hash;
- unsigned int len;
+ union {
+ struct {
+ HASH_LEN_DECLARE;
+ };
+ u64 hash_len;
+ };
const unsigned char *name;
};
+#define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
+#define hashlen_hash(hashlen) ((u32) (hashlen))
+#define hashlen_len(hashlen) ((u32)((hashlen) >> 32))
+
struct dentry_stat_t {
int nr_dentry;
int nr_unused;
@@ -129,7 +144,7 @@
};
struct dentry_operations {
- int (*d_revalidate)(struct dentry *, struct nameidata *);
+ int (*d_revalidate)(struct dentry *, unsigned int);
int (*d_hash)(const struct dentry *, const struct inode *,
struct qstr *);
int (*d_compare)(const struct dentry *, const struct inode *,
@@ -232,6 +247,8 @@
/* <clickety>-<click> the ramfs-type tree */
extern void d_genocide(struct dentry *);
+extern void d_tmpfile(struct dentry *, struct inode *);
+
extern struct dentry *d_find_alias(struct inode *);
extern void d_prune_aliases(struct inode *);
@@ -287,7 +304,7 @@
extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *);
extern struct dentry *__d_lookup_rcu(const struct dentry *parent,
const struct qstr *name,
- unsigned *seq, struct inode **inode);
+ unsigned *seq, struct inode *inode);
/**
* __d_rcu_to_refcount - take a refcount on dentry if sequence check is ok
diff --git a/include/linux/errno.h b/include/linux/errno.h
index 2d09bfa..e0de516 100644
--- a/include/linux/errno.h
+++ b/include/linux/errno.h
@@ -17,6 +17,7 @@
#define ENOIOCTLCMD 515 /* No ioctl command */
#define ERESTART_RESTARTBLOCK 516 /* restart by calling sys_restart_syscall */
#define EPROBE_DEFER 517 /* Driver requests probe retry */
+#define EOPENSTALE 518 /* open found a stale dentry */
/* Defined for the NFSv3 protocol */
#define EBADHANDLE 521 /* Illegal NFS file handle */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7b8ad44..2c6c82c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -453,6 +453,8 @@
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
+extern int sysctl_protected_symlinks;
+extern int sysctl_protected_hardlinks;
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
@@ -1574,8 +1576,8 @@
/*
* VFS helper functions..
*/
-extern int vfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
-extern int vfs_create2(struct vfsmount *, struct inode *, struct dentry *, umode_t, struct nameidata *);
+extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
+extern int vfs_create2(struct vfsmount *, struct inode *, struct dentry *, umode_t, bool);
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
extern int vfs_mkdir2(struct vfsmount *, struct inode *, struct dentry *, umode_t);
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
@@ -1676,7 +1678,7 @@
};
struct inode_operations {
- struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
+ struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
void * (*follow_link) (struct dentry *, struct nameidata *);
int (*permission) (struct inode *, int);
int (*permission2) (struct vfsmount *, struct inode *, int);
@@ -1685,7 +1687,7 @@
int (*readlink) (struct dentry *, char __user *,int);
void (*put_link) (struct dentry *, struct nameidata *, void *);
- int (*create) (struct inode *,struct dentry *,umode_t,struct nameidata *);
+ int (*create) (struct inode *,struct dentry *, umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct inode *,struct dentry *,const char *);
@@ -1706,6 +1708,10 @@
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*update_time)(struct inode *, struct timespec *, int);
+ int (*atomic_open)(struct inode *, struct dentry *,
+ struct file *, unsigned open_flag,
+ umode_t create_mode, int *opened);
+ int (*tmpfile) (struct inode *, struct dentry *, umode_t);
} ____cacheline_aligned;
struct seq_file;
@@ -1822,6 +1828,7 @@
#define I_REFERENCED (1 << 8)
#define __I_DIO_WAKEUP 9
#define I_DIO_WAKEUP (1 << I_DIO_WAKEUP)
+#define I_LINKABLE (1 << 10)
#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
@@ -2076,6 +2083,11 @@
#endif /* CONFIG_FILE_LOCKING */
/* fs/open.c */
+struct filename {
+ const char *name; /* pointer to actual string */
+ const __user char *uptr; /* original userland pointer */
+ bool separate; /* should "name" be freed? */
+};
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
struct file *filp);
@@ -2085,13 +2097,24 @@
loff_t len);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
umode_t mode);
+extern struct file *file_open_name(struct filename *, int, umode_t);
extern struct file *filp_open(const char *, int, umode_t);
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
const char *, int);
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
const struct cred *);
extern int filp_close(struct file *, fl_owner_t id);
-extern char * getname(const char __user *);
+
+extern struct filename *getname(const char __user *);
+
+enum {
+ FILE_CREATED = 1,
+ FILE_OPENED = 2
+};
+extern int finish_open(struct file *file, struct dentry *dentry,
+ int (*open)(struct inode *, struct file *),
+ int *opened);
+extern int finish_no_open(struct file *file, struct dentry *dentry);
/* fs/ioctl.c */
@@ -2103,13 +2126,14 @@
extern struct kmem_cache *names_cachep;
-#define __getname_gfp(gfp) kmem_cache_alloc(names_cachep, (gfp))
-#define __getname() __getname_gfp(GFP_KERNEL)
+extern void final_putname(struct filename *name);
+
+#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL)
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
#ifndef CONFIG_AUDITSYSCALL
-#define putname(name) __putname(name)
+#define putname(name) final_putname(name)
#else
-extern void putname(const char *name);
+extern void putname(struct filename *name);
#endif
#ifdef CONFIG_BLOCK
@@ -2597,7 +2621,7 @@
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
-extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
extern const struct file_operations simple_dir_operations;
extern const struct inode_operations simple_dir_inode_operations;
diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h
index 446ae03..ced2a0d 100644
--- a/include/linux/fscrypto.h
+++ b/include/linux/fscrypto.h
@@ -163,7 +163,6 @@
struct fscrypt_str crypto_buf;
};
-#define QSTR_INIT(n, l) { .name = n, .len = l }
#define FSTR_INIT(n, l) { .name = n, .len = l }
#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len)
#define fname_name(p) ((p)->disk_name.name)
diff --git a/include/linux/namei.h b/include/linux/namei.h
index afed3d3..d486e61 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -7,12 +7,6 @@
struct vfsmount;
-struct open_intent {
- int flags;
- int create_mode;
- struct file *file;
-};
-
enum { MAX_NESTED_LINKS = 8 };
struct nameidata {
@@ -25,11 +19,6 @@
int last_type;
unsigned depth;
char *saved_names[MAX_NESTED_LINKS + 1];
-
- /* Intent data */
- union {
- struct open_intent open;
- } intent;
};
/*
@@ -78,13 +67,11 @@
extern struct dentry *kern_path_create(int, const char *, struct path *, int);
extern struct dentry *user_path_create(int, const char __user *, struct path *, int);
+extern void done_path_create(struct path *, struct dentry *);
extern struct dentry *kern_path_locked(const char *, struct path *);
extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
const char *, unsigned int, struct path *);
-extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
- int (*open)(struct inode *, struct file *));
-
extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
extern struct dentry *lookup_one_len2(const char *, struct vfsmount *mnt, struct dentry *, int);
@@ -95,6 +82,8 @@
extern struct dentry *lock_rename(struct dentry *, struct dentry *);
extern void unlock_rename(struct dentry *, struct dentry *);
+extern void nd_jump_link(struct nameidata *nd, struct path *path);
+
static inline void nd_set_link(struct nameidata *nd, char *path)
{
nd->saved_names[nd->depth] = path;
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7ba3551..85200be 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1244,7 +1244,7 @@
int (*readlink)(struct inode *, struct page *, unsigned int,
unsigned int);
int (*create) (struct inode *, struct dentry *,
- struct iattr *, int, struct nfs_open_context *);
+ struct iattr *, int);
int (*remove) (struct inode *, struct qstr *);
void (*unlink_setup) (struct rpc_message *, struct inode *dir);
void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *);
diff --git a/include/linux/rmnet_data.h b/include/linux/rmnet_data.h
index 92c04b3..3932d28 100644
--- a/include/linux/rmnet_data.h
+++ b/include/linux/rmnet_data.h
@@ -208,8 +208,19 @@
* uint32_t MAP Flow Handle
* Returns: status code
*/
- RMNET_NETLINK_DEL_VND_TC_FLOW
+ RMNET_NETLINK_DEL_VND_TC_FLOW,
+
+ /*
+ * RMNET_NETLINK_NEW_VND_WITH_NAME - Creates a new virtual network
+ * device node with the specified
+ * device name
+ * Args: int32_t node number
+ * char[] vnd_name - Use as name
+ * Returns: status code
+ */
+ RMNET_NETLINK_NEW_VND_WITH_NAME
};
+#define RMNET_NETLINK_NEW_VND_WITH_NAME RMNET_NETLINK_NEW_VND_WITH_NAME
enum rmnet_config_endpoint_modes_e {
/* Pass the frame up the stack with no modifications to skb->dev */
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 42b0707..7442d6d 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -343,8 +343,9 @@
void __init mount_block_root(char *name, int flags)
{
- char *fs_names = __getname_gfp(GFP_KERNEL
- | __GFP_NOTRACK_FALSE_POSITIVE);
+ struct page *page = alloc_page(GFP_KERNEL |
+ __GFP_NOTRACK_FALSE_POSITIVE);
+ char *fs_names = page_address(page);
char *p;
#ifdef CONFIG_BLOCK
char b[BDEVNAME_SIZE];
@@ -396,7 +397,7 @@
#endif
panic("VFS: Unable to mount root fs on %s", b);
out:
- putname(fs_names);
+ put_page(page);
}
#ifdef CONFIG_ROOT_NFS
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index f032a6a..41eec1f 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -285,7 +285,7 @@
}
static int mqueue_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct inode *inode;
struct mq_attr *attr = dentry->d_fsdata;
@@ -624,7 +624,7 @@
ret = mnt_want_write(ipc_ns->mq_mnt);
if (ret)
goto out;
- ret = vfs_create2(ipc_ns->mq_mnt, dir->d_inode, dentry, mode, NULL);
+ ret = vfs_create2(ipc_ns->mq_mnt, dir->d_inode, dentry, mode, true);
dentry->d_fsdata = NULL;
if (ret)
goto out_drop_write;
@@ -678,7 +678,7 @@
{
struct dentry *dentry;
struct file *filp;
- char *name;
+ struct filename *name;
struct mq_attr attr;
int fd, error;
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
@@ -696,7 +696,7 @@
goto out_putname;
mutex_lock(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex);
- dentry = lookup_one_len2(name, ipc_ns->mq_mnt, ipc_ns->mq_mnt->mnt_root, strlen(name));
+ dentry = lookup_one_len2(name->name, ipc_ns->mq_mnt, ipc_ns->mq_mnt->mnt_root, strlen(name));
if (IS_ERR(dentry)) {
error = PTR_ERR(dentry);
goto out_putfd;
@@ -705,7 +705,7 @@
if (oflag & O_CREAT) {
if (dentry->d_inode) { /* entry already exists */
- audit_inode(name, dentry);
+ audit_inode(name->name, path.dentry);
if (oflag & O_EXCL) {
error = -EEXIST;
goto out;
@@ -721,7 +721,7 @@
error = -ENOENT;
goto out;
}
- audit_inode(name, dentry);
+ audit_inode(name->name, path.dentry);
filp = do_open(ipc_ns, dentry, oflag);
}
@@ -749,7 +749,7 @@
SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
{
int err;
- char *name;
+ struct filename *name;
struct dentry *dentry;
struct inode *inode = NULL;
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
@@ -760,7 +760,7 @@
mutex_lock_nested(&ipc_ns->mq_mnt->mnt_root->d_inode->i_mutex,
I_MUTEX_PARENT);
- dentry = lookup_one_len2(name, ipc_ns->mq_mnt, ipc_ns->mq_mnt->mnt_root,
+ dentry = lookup_one_len2(name->name, ipc_ns->mq_mnt, ipc_ns->mq_mnt->mnt_root,
strlen(name));
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
diff --git a/kernel/acct.c b/kernel/acct.c
index 02e6167..3e2aab7 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -193,7 +193,7 @@
}
}
-static int acct_on(char *name)
+static int acct_on(struct filename *pathname)
{
struct file *file;
struct vfsmount *mnt;
@@ -201,7 +201,7 @@
struct bsd_acct_struct *acct = NULL;
/* Difference from BSD - they don't do O_APPEND */
- file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+ file = file_open_name(pathname, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
if (IS_ERR(file))
return PTR_ERR(file);
@@ -260,7 +260,7 @@
return -EPERM;
if (name) {
- char *tmp = getname(name);
+ struct filename *tmp = getname(name);
if (IS_ERR(tmp))
return (PTR_ERR(tmp));
error = acct_on(tmp);
diff --git a/kernel/audit.c b/kernel/audit.c
index 1c7f2c6..fda8bd9 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1450,6 +1450,27 @@
}
/**
+ * audit_log_link_denied - report a link restriction denial
+ * @operation: specific link opreation
+ * @link: the path that triggered the restriction
+ */
+void audit_log_link_denied(const char *operation, struct path *link)
+{
+ struct audit_buffer *ab;
+
+ ab = audit_log_start(current->audit_context, GFP_KERNEL,
+ AUDIT_ANOM_LINK);
+ audit_log_format(ab, "op=%s action=denied", operation);
+ audit_log_format(ab, " pid=%d comm=", current->pid);
+ audit_log_untrustedstring(ab, current->comm);
+ audit_log_d_path(ab, " path=", link);
+ audit_log_format(ab, " dev=");
+ audit_log_untrustedstring(ab, link->dentry->d_inode->i_sb->s_id);
+ audit_log_format(ab, " ino=%lu", link->dentry->d_inode->i_ino);
+ audit_log_end(ab);
+}
+
+/**
* audit_log_end - end one audit record
* @ab: the audit_buffer
*
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index a010846..c67d030 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -108,27 +108,29 @@
* we don't let putname() free it (instead we free all of the saved
* pointers at syscall exit time).
*
- * Further, in fs/namei.c:path_lookup() we store the inode and device. */
+ * Further, in fs/namei.c:path_lookup() we store the inode and device.
+ */
struct audit_names {
- struct list_head list; /* audit_context->names_list */
- const char *name;
- unsigned long ino;
- dev_t dev;
- umode_t mode;
- uid_t uid;
- gid_t gid;
- dev_t rdev;
- u32 osid;
- struct audit_cap_data fcap;
- unsigned int fcap_ver;
- int name_len; /* number of name's characters to log */
- bool name_put; /* call __putname() for this name */
+ struct list_head list; /* audit_context->names_list */
+ struct filename *name;
+ unsigned long ino;
+ dev_t dev;
+ umode_t mode;
+ uid_t uid;
+ gid_t gid;
+ dev_t rdev;
+ u32 osid;
+ struct audit_cap_data fcap;
+ unsigned int fcap_ver;
+ int name_len; /* number of name's characters to log */
+ unsigned char type; /* record type */
+ bool name_put; /* call __putname() for this name */
/*
* This was an allocated audit_names and not from the array of
* names allocated in the task audit context. Thus this name
* should be freed on syscall exit
*/
- bool should_free;
+ bool should_free;
};
struct audit_aux_data {
@@ -1008,7 +1010,7 @@
context->ino_count);
list_for_each_entry(n, &context->names_list, list) {
printk(KERN_ERR "names[%d] = %p = %s\n", i,
- n->name, n->name ?: "(null)");
+ n->name, n->name->name ?: "(null)");
}
dump_stack();
return;
@@ -1533,7 +1535,7 @@
case AUDIT_NAME_FULL:
/* log the full path */
audit_log_format(ab, " name=");
- audit_log_untrustedstring(ab, n->name);
+ audit_log_untrustedstring(ab, n->name->name);
break;
case 0:
/* name was specified as a relative path and the
@@ -1543,7 +1545,7 @@
default:
/* log the name's directory component */
audit_log_format(ab, " name=");
- audit_log_n_untrustedstring(ab, n->name,
+ audit_log_n_untrustedstring(ab, n->name->name,
n->name_len);
}
} else
@@ -2037,7 +2039,7 @@
* Add a name to the list of audit names for this context.
* Called from fs/namei.c:getname().
*/
-void __audit_getname(const char *name)
+void __audit_getname(struct filename *name)
{
struct audit_context *context = current->audit_context;
struct audit_names *n;
@@ -2051,6 +2053,11 @@
return;
}
+#if AUDIT_DEBUG
+ /* The filename _must_ have a populated ->name */
+ BUG_ON(!name->name);
+#endif
+
n = audit_alloc_name(context);
if (!n)
return;
@@ -2070,7 +2077,7 @@
* then we delay the putname until syscall exit.
* Called from include/linux/fs.h:putname().
*/
-void audit_putname(const char *name)
+void audit_putname(struct filename *name)
{
struct audit_context *context = current->audit_context;
@@ -2085,7 +2092,7 @@
list_for_each_entry(n, &context->names_list, list)
printk(KERN_ERR "name[%d] = %p = %s\n", i,
- n->name, n->name ?: "(null)");
+ n->name, n->name->name ?: "(null)");
}
#endif
__putname(name);
@@ -2099,8 +2106,8 @@
" put_count=%d\n",
__FILE__, __LINE__,
context->serial, context->major,
- context->in_syscall, name, context->name_count,
- context->put_count);
+ context->in_syscall, name->name,
+ context->name_count, context->put_count);
dump_stack();
}
}
@@ -2159,7 +2166,7 @@
return;
list_for_each_entry_reverse(n, &context->names_list, list) {
- if (n->name && (n->name == name))
+ if (n->name && (n->name->name == name))
goto out;
}
@@ -2207,9 +2214,9 @@
continue;
if (n->ino == parent->i_ino &&
- !audit_compare_dname_path(dname, n->name, &dirlen)) {
+ !audit_compare_dname_path(dname, n->name->name, &dirlen)) {
n->name_len = dirlen; /* update parent data in place */
- found_parent = n->name;
+ found_parent = n->name->name;
goto add_names;
}
}
@@ -2220,13 +2227,13 @@
continue;
/* strcmp() is the more likely scenario */
- if (!strcmp(dname, n->name) ||
- !audit_compare_dname_path(dname, n->name, &dirlen)) {
+ if (!strcmp(dname, n->name->name) ||
+ !audit_compare_dname_path(dname, n->name->name, &dirlen)) {
if (inode)
audit_copy_inode(n, NULL, inode);
else
n->ino = (unsigned long)-1;
- found_child = n->name;
+ found_child = n->name->name;
goto add_names;
}
}
@@ -2248,7 +2255,7 @@
* directory. All names for this context are relinquished in
* audit_free_names() */
if (found_parent) {
- n->name = found_parent;
+ n->name->name = found_parent;
n->name_len = AUDIT_NAME_FULL;
/* don't call __putname() */
n->name_put = false;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3bdbeb6..b00baaf 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -808,7 +808,7 @@
*/
static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static const struct inode_operations cgroup_dir_inode_operations;
@@ -2536,7 +2536,7 @@
.rename = cgroup_rename,
};
-static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index be1f9c5..b85c420 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1561,6 +1561,24 @@
#endif
#endif
{
+ .procname = "protected_symlinks",
+ .data = &sysctl_protected_symlinks,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .procname = "protected_hardlinks",
+ .data = &sysctl_protected_hardlinks,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
.procname = "suid_dumpable",
.data = &suid_dumpable,
.maxlen = sizeof(int),
diff --git a/mm/shmem.c b/mm/shmem.c
index e281f06..a85ddc8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1520,6 +1520,37 @@
return error;
}
+static int
+shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ struct inode *inode;
+ int error = -ENOSPC;
+
+ inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE);
+ if (inode) {
+ error = security_inode_init_security(inode, dir,
+ NULL,
+ shmem_initxattrs, NULL);
+ if (error) {
+ if (error != -EOPNOTSUPP) {
+ iput(inode);
+ return error;
+ }
+ }
+#ifdef CONFIG_TMPFS_POSIX_ACL
+ error = generic_acl_init(inode, dir);
+ if (error) {
+ iput(inode);
+ return error;
+ }
+#else
+ error = 0;
+#endif
+ d_tmpfile(dentry, inode);
+ }
+ return error;
+}
+
static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int error;
@@ -1531,7 +1562,7 @@
}
static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return shmem_mknod(dir, dentry, mode | S_IFREG, 0);
}
@@ -2387,6 +2418,7 @@
.rmdir = shmem_rmdir,
.mknod = shmem_mknod,
.rename = shmem_rename,
+ .tmpfile = shmem_tmpfile,
#endif
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 9ae4c8d..f471533 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1605,7 +1605,7 @@
struct file *swap_file, *victim;
struct address_space *mapping;
struct inode *inode;
- char *pathname;
+ struct filename *pathname;
int oom_score_adj;
int i, type, prev;
int err;
@@ -1620,8 +1620,7 @@
if (IS_ERR(pathname))
goto out;
- victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0);
- putname(pathname);
+ victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0);
err = PTR_ERR(victim);
if (IS_ERR(victim))
goto out;
@@ -2067,7 +2066,7 @@
SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
{
struct swap_info_struct *p;
- char *name;
+ struct filename *name;
struct file *swap_file = NULL;
struct address_space *mapping;
int i;
@@ -2097,7 +2096,7 @@
name = NULL;
goto bad_swap;
}
- swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0);
+ swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0);
if (IS_ERR(swap_file)) {
error = PTR_ERR(swap_file);
swap_file = NULL;
@@ -2180,7 +2179,7 @@
printk(KERN_INFO "Adding %uk swap on %s. "
"Priority:%d extents:%d across:%lluk %s%s\n",
- p->pages<<(PAGE_SHIFT-10), name, p->prio,
+ p->pages<<(PAGE_SHIFT-10), name->name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
(p->flags & SWP_DISCARDABLE) ? "D" : "");
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index adf2990..7fee13b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -127,9 +127,7 @@
{
static uint32_t clntid;
char name[15];
- struct qstr q = {
- .name = name,
- };
+ struct qstr q = { .name = name };
struct dentry *dir, *dentry;
int error;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index b23f43a..8d112ed 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1059,12 +1059,9 @@
struct dentry *rpc_d_lookup_sb(const struct super_block *sb,
const unsigned char *dir_name)
{
- struct qstr dir = {
- .name = dir_name,
- .len = strlen(dir_name),
- .hash = full_name_hash(dir_name, strlen(dir_name)),
- };
+ struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name));
+ dir.hash = full_name_hash(dir.name, dir.len);
return d_lookup(sb->s_root, &dir);
}
EXPORT_SYMBOL_GPL(rpc_d_lookup_sb);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 52a2d11..b5e480e 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -875,19 +875,16 @@
*/
mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = mnt_want_write(path.mnt);
- if (err)
- goto out_mknod_dput;
err = security_path_mknod(&path, dentry, mode, 0);
if (err)
goto out_mknod_drop_write;
err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
out_mknod_drop_write:
- mnt_drop_write(path.mnt);
if (err)
goto out_mknod_dput;
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- dput(path.dentry);
+ mntget(path.mnt);
+ dget(dentry);
+ done_path_create(&path, dentry);
path.dentry = dentry;
addr->hash = UNIX_HASH_SIZE;
@@ -922,9 +919,7 @@
return err;
out_mknod_dput:
- dput(dentry);
- mutex_unlock(&path.dentry->d_inode->i_mutex);
- path_put(&path);
+ done_path_create(&path, dentry);
out_mknod_parent:
if (err == -EEXIST)
err = -EADDRINUSE;