Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs changes from Al Viro.
 "A lot of misc stuff.  The obvious groups:
   * Miklos' atomic_open series; kills the damn abuse of
     ->d_revalidate() by NFS, which was the major stumbling block for
     all work in that area.
   * ripping security_file_mmap() and dealing with deadlocks in the
     area; sanitizing the neighborhood of vm_mmap()/vm_munmap() in
     general.
   * ->encode_fh() switched to saner API; insane fake dentry in
     mm/cleancache.c gone.
   * assorted annotations in fs (endianness, __user)
   * parts of Artem's ->s_dirty work (jff2 and reiserfs parts)
   * ->update_time() work from Josef.
   * other bits and pieces all over the place.

  Normally it would've been in two or three pull requests, but
  signal.git stuff had eaten a lot of time during this cycle ;-/"

Fix up trivial conflicts in Documentation/filesystems/vfs.txt (the
'truncate_range' inode method was removed by the VM changes, the VFS
update adds an 'update_time()' method), and in fs/btrfs/ulist.[ch] (due
to sparse fix added twice, with other changes nearby).

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (95 commits)
  nfs: don't open in ->d_revalidate
  vfs: retry last component if opening stale dentry
  vfs: nameidata_to_filp(): don't throw away file on error
  vfs: nameidata_to_filp(): inline __dentry_open()
  vfs: do_dentry_open(): don't put filp
  vfs: split __dentry_open()
  vfs: do_last() common post lookup
  vfs: do_last(): add audit_inode before open
  vfs: do_last(): only return EISDIR for O_CREAT
  vfs: do_last(): check LOOKUP_DIRECTORY
  vfs: do_last(): make ENOENT exit RCU safe
  vfs: make follow_link check RCU safe
  vfs: do_last(): use inode variable
  vfs: do_last(): inline walk_component()
  vfs: do_last(): make exit RCU safe
  vfs: split do_lookup()
  Btrfs: move over to use ->update_time
  fs: introduce inode operation ->update_time
  reiserfs: get rid of resierfs_sync_super
  reiserfs: mark the superblock as dirty a bit later
  ...

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 */

include/linux/exportfs.h

@@ -165,8 +165,8 @@ struct fid {
  */
 
 struct export_operations {
-	int (*encode_fh)(struct dentry *de, __u32 *fh, int *max_len,
-			int connectable);
+	int (*encode_fh)(struct inode *inode, __u32 *fh, int *max_len,
+			struct inode *parent);
 	struct dentry * (*fh_to_dentry)(struct super_block *sb, struct fid *fid,
 			int fh_len, int fh_type);
 	struct dentry * (*fh_to_parent)(struct super_block *sb, struct fid *fid,

include/linux/fs.h

@@ -1692,6 +1692,7 @@ struct inode_operations {
 	int (*removexattr) (struct dentry *, const char *);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
+	int (*update_time)(struct inode *, struct timespec *, int);
 } ____cacheline_aligned;
 
 struct seq_file;
@@ -1850,6 +1851,13 @@ static inline void inode_inc_iversion(struct inode *inode)
        spin_unlock(&inode->i_lock);
 }
 
+enum file_time_flags {
+	S_ATIME = 1,
+	S_MTIME = 2,
+	S_CTIME = 4,
+	S_VERSION = 8,
+};
+
 extern void touch_atime(struct path *);
 static inline void file_accessed(struct file *file)
 {
@@ -2583,7 +2591,7 @@ extern int inode_change_ok(const struct inode *, struct iattr *);
 extern int inode_newsize_ok(const struct inode *, loff_t offset);
 extern void setattr_copy(struct inode *inode, const struct iattr *attr);
 
-extern void file_update_time(struct file *file);
+extern int file_update_time(struct file *file);
 
 extern int generic_show_options(struct seq_file *m, struct dentry *root);
 extern void save_mount_options(struct super_block *sb, char *options);

include/linux/fsnotify_backend.h

@@ -60,7 +60,7 @@
 #define FS_EVENTS_POSS_ON_CHILD   (FS_ACCESS | FS_MODIFY | FS_ATTRIB |\
 				   FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN |\
 				   FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\
-				   FS_DELETE)
+				   FS_DELETE | FS_OPEN_PERM | FS_ACCESS_PERM)
 
 #define FS_MOVE			(FS_MOVED_FROM | FS_MOVED_TO)
 

include/linux/lglock.h

@@ -23,28 +23,17 @@
 #include <linux/lockdep.h>
 #include <linux/percpu.h>
 #include <linux/cpu.h>
+#include <linux/notifier.h>
 
 /* can make br locks by using local lock for read side, global lock for write */
-#define br_lock_init(name)	name##_lock_init()
-#define br_read_lock(name)	name##_local_lock()
-#define br_read_unlock(name)	name##_local_unlock()
-#define br_write_lock(name)	name##_global_lock_online()
-#define br_write_unlock(name)	name##_global_unlock_online()
+#define br_lock_init(name)	lg_lock_init(name, #name)
+#define br_read_lock(name)	lg_local_lock(name)
+#define br_read_unlock(name)	lg_local_unlock(name)
+#define br_write_lock(name)	lg_global_lock(name)
+#define br_write_unlock(name)	lg_global_unlock(name)
 
-#define DECLARE_BRLOCK(name)	DECLARE_LGLOCK(name)
 #define DEFINE_BRLOCK(name)	DEFINE_LGLOCK(name)
 
-
-#define lg_lock_init(name)	name##_lock_init()
-#define lg_local_lock(name)	name##_local_lock()
-#define lg_local_unlock(name)	name##_local_unlock()
-#define lg_local_lock_cpu(name, cpu)	name##_local_lock_cpu(cpu)
-#define lg_local_unlock_cpu(name, cpu)	name##_local_unlock_cpu(cpu)
-#define lg_global_lock(name)	name##_global_lock()
-#define lg_global_unlock(name)	name##_global_unlock()
-#define lg_global_lock_online(name) name##_global_lock_online()
-#define lg_global_unlock_online(name) name##_global_unlock_online()
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 #define LOCKDEP_INIT_MAP lockdep_init_map
 
@@ -59,142 +48,26 @@
 #define DEFINE_LGLOCK_LOCKDEP(name)
 #endif
 
-
-#define DECLARE_LGLOCK(name)						\
- extern void name##_lock_init(void);					\
- extern void name##_local_lock(void);					\
- extern void name##_local_unlock(void);					\
- extern void name##_local_lock_cpu(int cpu);				\
- extern void name##_local_unlock_cpu(int cpu);				\
- extern void name##_global_lock(void);					\
- extern void name##_global_unlock(void);				\
- extern void name##_global_lock_online(void);				\
- extern void name##_global_unlock_online(void);				\
+struct lglock {
+	arch_spinlock_t __percpu *lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lock_class_key lock_key;
+	struct lockdep_map    lock_dep_map;
+#endif
+};
 
 #define DEFINE_LGLOCK(name)						\
-									\
- DEFINE_SPINLOCK(name##_cpu_lock);					\
- cpumask_t name##_cpus __read_mostly;					\
- DEFINE_PER_CPU(arch_spinlock_t, name##_lock);				\
- DEFINE_LGLOCK_LOCKDEP(name);						\
-									\
- static int								\
- name##_lg_cpu_callback(struct notifier_block *nb,			\
-				unsigned long action, void *hcpu)	\
- {									\
-	switch (action & ~CPU_TASKS_FROZEN) {				\
-	case CPU_UP_PREPARE:						\
-		spin_lock(&name##_cpu_lock);				\
-		cpu_set((unsigned long)hcpu, name##_cpus);		\
-		spin_unlock(&name##_cpu_lock);				\
-		break;							\
-	case CPU_UP_CANCELED: case CPU_DEAD:				\
-		spin_lock(&name##_cpu_lock);				\
-		cpu_clear((unsigned long)hcpu, name##_cpus);		\
-		spin_unlock(&name##_cpu_lock);				\
-	}								\
-	return NOTIFY_OK;						\
- }									\
- static struct notifier_block name##_lg_cpu_notifier = {		\
-	.notifier_call = name##_lg_cpu_callback,			\
- };									\
- void name##_lock_init(void) {						\
-	int i;								\
-	LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \
-	for_each_possible_cpu(i) {					\
-		arch_spinlock_t *lock;					\
-		lock = &per_cpu(name##_lock, i);			\
-		*lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;	\
-	}								\
-	register_hotcpu_notifier(&name##_lg_cpu_notifier);		\
-	get_online_cpus();						\
-	for_each_online_cpu(i)						\
-		cpu_set(i, name##_cpus);				\
-	put_online_cpus();						\
- }									\
- EXPORT_SYMBOL(name##_lock_init);					\
-									\
- void name##_local_lock(void) {						\
-	arch_spinlock_t *lock;						\
-	preempt_disable();						\
-	rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_);	\
-	lock = &__get_cpu_var(name##_lock);				\
-	arch_spin_lock(lock);						\
- }									\
- EXPORT_SYMBOL(name##_local_lock);					\
-									\
- void name##_local_unlock(void) {					\
-	arch_spinlock_t *lock;						\
-	rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_);		\
-	lock = &__get_cpu_var(name##_lock);				\
-	arch_spin_unlock(lock);						\
-	preempt_enable();						\
- }									\
- EXPORT_SYMBOL(name##_local_unlock);					\
-									\
- void name##_local_lock_cpu(int cpu) {					\
-	arch_spinlock_t *lock;						\
-	preempt_disable();						\
-	rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_);	\
-	lock = &per_cpu(name##_lock, cpu);				\
-	arch_spin_lock(lock);						\
- }									\
- EXPORT_SYMBOL(name##_local_lock_cpu);					\
-									\
- void name##_local_unlock_cpu(int cpu) {				\
-	arch_spinlock_t *lock;						\
-	rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_);		\
-	lock = &per_cpu(name##_lock, cpu);				\
-	arch_spin_unlock(lock);						\
-	preempt_enable();						\
- }									\
- EXPORT_SYMBOL(name##_local_unlock_cpu);				\
-									\
- void name##_global_lock_online(void) {					\
-	int i;								\
-	spin_lock(&name##_cpu_lock);					\
-	rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_);		\
-	for_each_cpu(i, &name##_cpus) {					\
-		arch_spinlock_t *lock;					\
-		lock = &per_cpu(name##_lock, i);			\
-		arch_spin_lock(lock);					\
-	}								\
- }									\
- EXPORT_SYMBOL(name##_global_lock_online);				\
-									\
- void name##_global_unlock_online(void) {				\
-	int i;								\
-	rwlock_release(&name##_lock_dep_map, 1, _RET_IP_);		\
-	for_each_cpu(i, &name##_cpus) {					\
-		arch_spinlock_t *lock;					\
-		lock = &per_cpu(name##_lock, i);			\
-		arch_spin_unlock(lock);					\
-	}								\
-	spin_unlock(&name##_cpu_lock);					\
- }									\
- EXPORT_SYMBOL(name##_global_unlock_online);				\
-									\
- void name##_global_lock(void) {					\
-	int i;								\
-	preempt_disable();						\
-	rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_);		\
-	for_each_possible_cpu(i) {					\
-		arch_spinlock_t *lock;					\
-		lock = &per_cpu(name##_lock, i);			\
-		arch_spin_lock(lock);					\
-	}								\
- }									\
- EXPORT_SYMBOL(name##_global_lock);					\
-									\
- void name##_global_unlock(void) {					\
-	int i;								\
-	rwlock_release(&name##_lock_dep_map, 1, _RET_IP_);		\
-	for_each_possible_cpu(i) {					\
-		arch_spinlock_t *lock;					\
-		lock = &per_cpu(name##_lock, i);			\
-		arch_spin_unlock(lock);					\
-	}								\
-	preempt_enable();						\
- }									\
- EXPORT_SYMBOL(name##_global_unlock);
+	DEFINE_LGLOCK_LOCKDEP(name);					\
+	DEFINE_PER_CPU(arch_spinlock_t, name ## _lock)			\
+	= __ARCH_SPIN_LOCK_UNLOCKED;					\
+	struct lglock name = { .lock = &name ## _lock }
+
+void lg_lock_init(struct lglock *lg, char *name);
+void lg_local_lock(struct lglock *lg);
+void lg_local_unlock(struct lglock *lg);
+void lg_local_lock_cpu(struct lglock *lg, int cpu);
+void lg_local_unlock_cpu(struct lglock *lg, int cpu);
+void lg_global_lock(struct lglock *lg);
+void lg_global_unlock(struct lglock *lg);
+
 #endif

include/linux/mm.h

@@ -1392,7 +1392,7 @@ extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned lo
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long flags,
 	vm_flags_t vm_flags, unsigned long pgoff);
-extern unsigned long do_mmap(struct file *, unsigned long,
+extern unsigned long do_mmap_pgoff(struct file *, unsigned long,
         unsigned long, unsigned long,
         unsigned long, unsigned long);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t);

include/linux/security.h

@@ -86,9 +86,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
 extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
 extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
-extern int cap_file_mmap(struct file *file, unsigned long reqprot,
-			 unsigned long prot, unsigned long flags,
-			 unsigned long addr, unsigned long addr_only);
+extern int cap_mmap_addr(unsigned long addr);
+extern int cap_mmap_file(struct file *file, unsigned long reqprot,
+			 unsigned long prot, unsigned long flags);
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5);
@@ -586,15 +586,17 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	simple integer value.  When @arg represents a user space pointer, it
  *	should never be used by the security module.
  *	Return 0 if permission is granted.
- * @file_mmap :
+ * @mmap_addr :
+ *	Check permissions for a mmap operation at @addr.
+ *	@addr contains virtual address that will be used for the operation.
+ *	Return 0 if permission is granted.
+ * @mmap_file :
  *	Check permissions for a mmap operation.  The @file may be NULL, e.g.
  *	if mapping anonymous memory.
  *	@file contains the file structure for file to map (may be NULL).
  *	@reqprot contains the protection requested by the application.
  *	@prot contains the protection that will be applied by the kernel.
  *	@flags contains the operational flags.
- *	@addr contains virtual address that will be used for the operation.
- *	@addr_only contains a boolean: 0 if file-backed VMA, otherwise 1.
  *	Return 0 if permission is granted.
  * @file_mprotect:
  *	Check permissions before changing memory access permissions.
@@ -1481,10 +1483,10 @@ struct security_operations {
 	void (*file_free_security) (struct file *file);
 	int (*file_ioctl) (struct file *file, unsigned int cmd,
 			   unsigned long arg);
-	int (*file_mmap) (struct file *file,
+	int (*mmap_addr) (unsigned long addr);
+	int (*mmap_file) (struct file *file,
 			  unsigned long reqprot, unsigned long prot,
-			  unsigned long flags, unsigned long addr,
-			  unsigned long addr_only);
+			  unsigned long flags);
 	int (*file_mprotect) (struct vm_area_struct *vma,
 			      unsigned long reqprot,
 			      unsigned long prot);
@@ -1743,9 +1745,9 @@ int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_free(struct file *file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
-int security_file_mmap(struct file *file, unsigned long reqprot,
-			unsigned long prot, unsigned long flags,
-			unsigned long addr, unsigned long addr_only);
+int security_mmap_file(struct file *file, unsigned long prot,
+			unsigned long flags);
+int security_mmap_addr(unsigned long addr);
 int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			   unsigned long prot);
 int security_file_lock(struct file *file, unsigned int cmd);
@@ -2181,13 +2183,15 @@ static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 	return 0;
 }
 
-static inline int security_file_mmap(struct file *file, unsigned long reqprot,
-				     unsigned long prot,
-				     unsigned long flags,
-				     unsigned long addr,
-				     unsigned long addr_only)
+static inline int security_mmap_file(struct file *file, unsigned long prot,
+				     unsigned long flags)
 {
-	return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only);
+	return 0;
+}
+
+static inline int security_mmap_addr(unsigned long addr)
+{
+	return cap_mmap_addr(addr);
 }
 
 static inline int security_file_mprotect(struct vm_area_struct *vma,

include/linux/types.h

@@ -25,7 +25,7 @@ typedef __kernel_dev_t		dev_t;
 typedef __kernel_ino_t		ino_t;
 typedef __kernel_mode_t		mode_t;
 typedef unsigned short		umode_t;
-typedef __kernel_nlink_t	nlink_t;
+typedef __u32			nlink_t;
 typedef __kernel_off_t		off_t;
 typedef __kernel_pid_t		pid_t;
 typedef __kernel_daddr_t	daddr_t;