Merge branch 'locks-3.15' of git://git.samba.org/jlayton/linux

Pull file locking updates from Jeff Layton:
 "Highlights:

   - maintainership change for fs/locks.c.  Willy's not interested in
     maintaining it these days, and is OK with Bruce and I taking it.
   - fix for open vs setlease race that Al ID'ed
   - cleanup and consolidation of file locking code
   - eliminate unneeded BUG() call
   - merge of file-private lock implementation"

* 'locks-3.15' of git://git.samba.org/jlayton/linux:
  locks: make locks_mandatory_area check for file-private locks
  locks: fix locks_mandatory_locked to respect file-private locks
  locks: require that flock->l_pid be set to 0 for file-private locks
  locks: add new fcntl cmd values for handling file private locks
  locks: skip deadlock detection on FL_FILE_PVT locks
  locks: pass the cmd value to fcntl_getlk/getlk64
  locks: report l_pid as -1 for FL_FILE_PVT locks
  locks: make /proc/locks show IS_FILE_PVT locks as type "FLPVT"
  locks: rename locks_remove_flock to locks_remove_file
  locks: consolidate checks for compatible filp->f_mode values in setlk handlers
  locks: fix posix lock range overflow handling
  locks: eliminate BUG() call when there's an unexpected lock on file close
  locks: add __acquires and __releases annotations to locks_start and locks_stop
  locks: remove "inline" qualifier from fl_link manipulation functions
  locks: clean up comment typo
  locks: close potential race between setlease and open
  MAINTAINERS: update entry for fs/locks.c

MAINTAINERS

@@ -3521,7 +3521,8 @@ F:	include/scsi/libfcoe.h
 F:	include/uapi/scsi/fc/
 
 FILE LOCKING (flock() and fcntl()/lockf())
-M:	Matthew Wilcox <matthew@wil.cx>
+M:	Jeff Layton <jlayton@redhat.com>
+M:	J. Bruce Fields <bfields@fieldses.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	include/linux/fcntl.h

arch/arm/kernel/sys_oabi-compat.c

@@ -203,6 +203,9 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd,
 	int ret;
 
 	switch (cmd) {
+	case F_GETLKP:
+	case F_SETLKP:
+	case F_SETLKPW:
 	case F_GETLK64:
 	case F_SETLK64:
 	case F_SETLKW64:

fs/compat.c

@@ -399,12 +399,28 @@ static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *u
 }
 #endif
 
+static unsigned int
+convert_fcntl_cmd(unsigned int cmd)
+{
+	switch (cmd) {
+	case F_GETLK64:
+		return F_GETLK;
+	case F_SETLK64:
+		return F_SETLK;
+	case F_SETLKW64:
+		return F_SETLKW;
+	}
+
+	return cmd;
+}
+
 COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 		       compat_ulong_t, arg)
 {
 	mm_segment_t old_fs;
 	struct flock f;
 	long ret;
+	unsigned int conv_cmd;
 
 	switch (cmd) {
 	case F_GETLK:
@@ -441,16 +457,18 @@ COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	case F_GETLK64:
 	case F_SETLK64:
 	case F_SETLKW64:
+	case F_GETLKP:
+	case F_SETLKP:
+	case F_SETLKPW:
 		ret = get_compat_flock64(&f, compat_ptr(arg));
 		if (ret != 0)
 			break;
 		old_fs = get_fs();
 		set_fs(KERNEL_DS);
-		ret = sys_fcntl(fd, (cmd == F_GETLK64) ? F_GETLK :
-				((cmd == F_SETLK64) ? F_SETLK : F_SETLKW),
-				(unsigned long)&f);
+		conv_cmd = convert_fcntl_cmd(cmd);
+		ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f);
 		set_fs(old_fs);
-		if (cmd == F_GETLK64 && ret == 0) {
+		if ((conv_cmd == F_GETLK || conv_cmd == F_GETLKP) && ret == 0) {
 			/* need to return lock information - see above for commentary */
 			if (f.l_start > COMPAT_LOFF_T_MAX)
 				ret = -EOVERFLOW;
@@ -471,8 +489,15 @@ COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
 		       compat_ulong_t, arg)
 {
-	if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64))
+	switch (cmd) {
+	case F_GETLK64:
+	case F_SETLK64:
+	case F_SETLKW64:
+	case F_GETLKP:
+	case F_SETLKP:
+	case F_SETLKPW:
 		return -EINVAL;
+	}
 	return compat_sys_fcntl64(fd, cmd, arg);
 }
 

fs/fcntl.c

@@ -272,9 +272,19 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_SETFL:
 		err = setfl(fd, filp, arg);
 		break;
+#if BITS_PER_LONG != 32
+	/* 32-bit arches must use fcntl64() */
+	case F_GETLKP:
+#endif
 	case F_GETLK:
-		err = fcntl_getlk(filp, (struct flock __user *) arg);
+		err = fcntl_getlk(filp, cmd, (struct flock __user *) arg);
 		break;
+#if BITS_PER_LONG != 32
+	/* 32-bit arches must use fcntl64() */
+	case F_SETLKP:
+	case F_SETLKPW:
+#endif
+		/* Fallthrough */
 	case F_SETLK:
 	case F_SETLKW:
 		err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
@@ -389,10 +399,13 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	
 	switch (cmd) {
 	case F_GETLK64:
-			err = fcntl_getlk64(f.file, (struct flock64 __user *) arg);
+	case F_GETLKP:
+		err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg);
 		break;
 	case F_SETLK64:
 	case F_SETLKW64:
+	case F_SETLKP:
+	case F_SETLKPW:
 		err = fcntl_setlk64(fd, f.file, cmd,
 				(struct flock64 __user *) arg);
 		break;

fs/file_table.c

@@ -235,7 +235,7 @@ static void __fput(struct file *file)
 	 * in the file cleanup chain.
 	 */
 	eventpoll_release(file);
-	locks_remove_flock(file);
+	locks_remove_file(file);
 
 	if (unlikely(file->f_flags & FASYNC)) {
 		if (file->f_op->fasync)

fs/namei.c

@@ -2569,7 +2569,7 @@ static int handle_truncate(struct file *filp)
 	/*
 	 * Refuse to truncate files with mandatory locks held on them.
 	 */
-	error = locks_verify_locked(inode);
+	error = locks_verify_locked(filp);
 	if (!error)
 		error = security_path_truncate(path);
 	if (!error) {

include/linux/fs.h

@@ -893,6 +893,7 @@ static inline int file_check_writeable(struct file *filp)
 #define FL_SLEEP	128	/* A blocking lock */
 #define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
+#define FL_FILE_PVT	1024	/* lock is private to the file */
 
 /*
  * Special return value from posix_lock_file() and vfs_lock_file() for
@@ -997,12 +998,12 @@ struct file_lock {
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 #ifdef CONFIG_FILE_LOCKING
-extern int fcntl_getlk(struct file *, struct flock __user *);
+extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
 extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
 			struct flock __user *);
 
 #if BITS_PER_LONG == 32
-extern int fcntl_getlk64(struct file *, struct flock64 __user *);
+extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
 extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 			struct flock64 __user *);
 #endif
@@ -1017,7 +1018,7 @@ extern struct file_lock * locks_alloc_lock(void);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
 extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
-extern void locks_remove_flock(struct file *);
+extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
 extern void posix_test_lock(struct file *, struct file_lock *);
 extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
@@ -1035,7 +1036,8 @@ extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
 #else /* !CONFIG_FILE_LOCKING */
-static inline int fcntl_getlk(struct file *file, struct flock __user *user)
+static inline int fcntl_getlk(struct file *file, unsigned int cmd,
+			      struct flock __user *user)
 {
 	return -EINVAL;
 }
@@ -1047,7 +1049,8 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file,
 }
 
 #if BITS_PER_LONG == 32
-static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user)
+static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
+				struct flock64 __user *user)
 {
 	return -EINVAL;
 }
@@ -1088,7 +1091,7 @@ static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
 	return;
 }
 
-static inline void locks_remove_flock(struct file *filp)
+static inline void locks_remove_file(struct file *filp)
 {
 	return;
 }
@@ -1916,6 +1919,11 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 
+static inline struct inode *file_inode(struct file *f)
+{
+	return f->f_inode;
+}
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -1925,7 +1933,7 @@ extern struct kobject *fs_kobj;
 #define FLOCK_VERIFY_WRITE 2
 
 #ifdef CONFIG_FILE_LOCKING
-extern int locks_mandatory_locked(struct inode *);
+extern int locks_mandatory_locked(struct file *);
 extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
 
 /*
@@ -1948,10 +1956,10 @@ static inline int mandatory_lock(struct inode *ino)
 	return IS_MANDLOCK(ino) && __mandatory_lock(ino);
 }
 
-static inline int locks_verify_locked(struct inode *inode)
+static inline int locks_verify_locked(struct file *file)
 {
-	if (mandatory_lock(inode))
-		return locks_mandatory_locked(inode);
+	if (mandatory_lock(file_inode(file)))
+		return locks_mandatory_locked(file);
 	return 0;
 }
 
@@ -1971,6 +1979,12 @@ static inline int locks_verify_truncate(struct inode *inode,
 
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
+	/*
+	 * Since this check is lockless, we must ensure that any refcounts
+	 * taken are done before checking inode->i_flock. Otherwise, we could
+	 * end up racing with tasks trying to set a new lease on this file.
+	 */
+	smp_mb();
 	if (inode->i_flock)
 		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
@@ -2006,7 +2020,7 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 }
 
 #else /* !CONFIG_FILE_LOCKING */
-static inline int locks_mandatory_locked(struct inode *inode)
+static inline int locks_mandatory_locked(struct file *file)
 {
 	return 0;
 }
@@ -2028,7 +2042,7 @@ static inline int mandatory_lock(struct inode *inode)
 	return 0;
 }
 
-static inline int locks_verify_locked(struct inode *inode)
+static inline int locks_verify_locked(struct file *file)
 {
 	return 0;
 }
@@ -2302,11 +2316,6 @@ static inline bool execute_ok(struct inode *inode)
 	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
 }
 
-static inline struct inode *file_inode(struct file *f)
-{
-	return f->f_inode;
-}
-
 static inline void file_start_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))

include/uapi/asm-generic/fcntl.h

@@ -132,6 +132,22 @@
 #define F_GETOWNER_UIDS	17
 #endif
 
+/*
+ * fd "private" POSIX locks.
+ *
+ * Usually POSIX locks held by a process are released on *any* close and are
+ * not inherited across a fork().
+ *
+ * These cmd values will set locks that conflict with normal POSIX locks, but
+ * are "owned" by the opened file, not the process. This means that they are
+ * inherited across fork() like BSD (flock) locks, and they are only released
+ * automatically when the last reference to the the open file against which
+ * they were acquired is put.
+ */
+#define F_GETLKP	36
+#define F_SETLKP	37
+#define F_SETLKPW	38
+
 #define F_OWNER_TID	0
 #define F_OWNER_PID	1
 #define F_OWNER_PGRP	2
@@ -186,8 +202,6 @@ struct flock {
 };
 #endif
 
-#ifndef CONFIG_64BIT
-
 #ifndef HAVE_ARCH_STRUCT_FLOCK64
 #ifndef __ARCH_FLOCK64_PAD
 #define __ARCH_FLOCK64_PAD
@@ -202,6 +216,5 @@ struct flock64 {
 	__ARCH_FLOCK64_PAD
 };
 #endif
-#endif /* !CONFIG_64BIT */
 
 #endif /* _ASM_GENERIC_FCNTL_H */

mm/mmap.c

@@ -1299,7 +1299,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			/*
 			 * Make sure there are no mandatory locks on the file.
 			 */
-			if (locks_verify_locked(inode))
+			if (locks_verify_locked(file))
 				return -EAGAIN;
 
 			vm_flags |= VM_SHARED | VM_MAYSHARE;

mm/nommu.c

@@ -995,7 +995,7 @@ static int validate_mmap_request(struct file *file,
 			    (file->f_mode & FMODE_WRITE))
 				return -EACCES;
 
-			if (locks_verify_locked(file_inode(file)))
+			if (locks_verify_locked(file))
 				return -EAGAIN;
 
 			if (!(capabilities & BDI_CAP_MAP_DIRECT))

security/selinux/hooks.c

@@ -3317,6 +3317,9 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd,
 	case F_GETLK:
 	case F_SETLK:
 	case F_SETLKW:
+	case F_GETLKP:
+	case F_SETLKP:
+	case F_SETLKPW:
 #if BITS_PER_LONG == 32
 	case F_GETLK64:
 	case F_SETLK64: