[PATCH v7 1/7] VFS: Introduce new O_DENY* open flags

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



This patch adds 3 flags:
1) O_DENYREAD that doesn't permit read access,
2) O_DENYWRITE that doesn't permit write access,
3) O_DENYDELETE that doesn't permit delete or rename.

Network filesystems CIFS, SMB2.0, SMB3.0 and NFSv4 have such flags -
this change can benefit cifs and nfs modules as well as Samba and
NFS file servers that export the same directory for Windows clients,
or Wine applications that access the same files simultaneously.

These flags are only take affect for opens on mounts with new sharelock
option. They are translated to flock's flags:

!O_DENYREAD  -> LOCK_READ  | LOCK_MAND
!O_DENYWRITE -> LOCK_WRITE | LOCK_MAND

and set through flock_lock_file on a file. If the file can't be locked
due conflicts with another open with O_DENY* flags, a new -ESHAREDENIED
error code is returned.

Create codepath is slightly changed to prevent data races on newly
created files: when open with O_CREAT can return -ESHAREDENIED error
for successfully created files due to a sharelock set by another task.

Temporary disable O_DENYDELETE support - will enable it in further
patches.

Signed-off-by: Pavel Shilovsky <piastry@xxxxxxxxxxx>
---
 arch/alpha/include/uapi/asm/errno.h  |    2 +
 arch/alpha/include/uapi/asm/fcntl.h  |    3 ++
 arch/mips/include/uapi/asm/errno.h   |    2 +
 arch/parisc/include/uapi/asm/errno.h |    2 +
 arch/parisc/include/uapi/asm/fcntl.h |    3 ++
 arch/sparc/include/uapi/asm/errno.h  |    2 +
 arch/sparc/include/uapi/asm/fcntl.h  |    3 ++
 fs/fcntl.c                           |    5 +-
 fs/locks.c                           |   97 +++++++++++++++++++++++++++++++---
 fs/namei.c                           |   53 ++++++++++++++++++-
 fs/proc_namespace.c                  |    1 +
 include/linux/fs.h                   |    8 +++
 include/uapi/asm-generic/errno.h     |    2 +
 include/uapi/asm-generic/fcntl.h     |   11 ++++
 include/uapi/linux/fs.h              |    1 +
 15 files changed, 185 insertions(+), 10 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/errno.h b/arch/alpha/include/uapi/asm/errno.h
index 17f92aa..953a6d6 100644
--- a/arch/alpha/include/uapi/asm/errno.h
+++ b/arch/alpha/include/uapi/asm/errno.h
@@ -124,4 +124,6 @@
 
 #define EHWPOISON	139	/* Memory page has hardware error */
 
+#define ESHAREDENIED	140	/* File is locked with a sharelock */
+
 #endif
diff --git a/arch/alpha/include/uapi/asm/fcntl.h b/arch/alpha/include/uapi/asm/fcntl.h
index 09f49a6..265344b 100644
--- a/arch/alpha/include/uapi/asm/fcntl.h
+++ b/arch/alpha/include/uapi/asm/fcntl.h
@@ -33,6 +33,9 @@
 
 #define O_PATH		040000000
 #define __O_TMPFILE	0100000000
+#define O_DENYREAD	0200000000	/* Do not permit read access */
+#define O_DENYWRITE	0400000000	/* Do not permit write access */
+#define O_DENYDELETE	01000000000	/* Do not permit delete or rename */
 
 #define F_GETLK		7
 #define F_SETLK		8
diff --git a/arch/mips/include/uapi/asm/errno.h b/arch/mips/include/uapi/asm/errno.h
index 02d645d..f1a4068 100644
--- a/arch/mips/include/uapi/asm/errno.h
+++ b/arch/mips/include/uapi/asm/errno.h
@@ -123,6 +123,8 @@
 
 #define EHWPOISON	168	/* Memory page has hardware error */
 
+#define ESHAREDENIED	169	/* File is locked with a sharelock */
+
 #define EDQUOT		1133	/* Quota exceeded */
 
 
diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index f3a8aa5..654c232 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -124,4 +124,6 @@
 
 #define EHWPOISON	257	/* Memory page has hardware error */
 
+#define ESHAREDENIED	258	/* File is locked with a sharelock */
+
 #endif
diff --git a/arch/parisc/include/uapi/asm/fcntl.h b/arch/parisc/include/uapi/asm/fcntl.h
index 34a46cb..5865964 100644
--- a/arch/parisc/include/uapi/asm/fcntl.h
+++ b/arch/parisc/include/uapi/asm/fcntl.h
@@ -21,6 +21,9 @@
 
 #define O_PATH		020000000
 #define __O_TMPFILE	040000000
+#define O_DENYREAD	0200000000	/* Do not permit read access */
+#define O_DENYWRITE	0400000000	/* Do not permit write access */
+#define O_DENYDELETE	01000000000	/* Do not permit delete or rename */
 
 #define F_GETLK64	8
 #define F_SETLK64	9
diff --git a/arch/sparc/include/uapi/asm/errno.h b/arch/sparc/include/uapi/asm/errno.h
index 20423e17..fe339b5 100644
--- a/arch/sparc/include/uapi/asm/errno.h
+++ b/arch/sparc/include/uapi/asm/errno.h
@@ -114,4 +114,6 @@
 
 #define EHWPOISON	135	/* Memory page has hardware error */
 
+#define ESHAREDENIED	136	/* File is locked with a sharelock */
+
 #endif
diff --git a/arch/sparc/include/uapi/asm/fcntl.h b/arch/sparc/include/uapi/asm/fcntl.h
index 7e8ace5..ab68170 100644
--- a/arch/sparc/include/uapi/asm/fcntl.h
+++ b/arch/sparc/include/uapi/asm/fcntl.h
@@ -36,6 +36,9 @@
 
 #define O_PATH		0x1000000
 #define __O_TMPFILE	0x2000000
+#define O_DENYREAD	0x4000000	/* Do not permit read access */
+#define O_DENYWRITE	0x8000000	/* Do not permit write access */
+#define O_DENYDELETE	0x10000000	/* Do not permit delete or rename */
 
 #define F_GETOWN	5	/*  for sockets. */
 #define F_SETOWN	6	/*  for sockets. */
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ef68665..3f85887 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -729,14 +729,15 @@ static int __init fcntl_init(void)
 	 * 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(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+	BUILD_BUG_ON(23 - 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	| __O_TMPFILE
+		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
+		O_DENYREAD	| O_DENYWRITE	| O_DENYDELETE
 		));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/locks.c b/fs/locks.c
index 92a0f0a..ffde4d4 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -708,20 +708,73 @@ static int posix_locks_conflict(struct file_lock *caller_fl, struct file_lock *s
 	return (locks_conflict(caller_fl, sys_fl));
 }
 
-/* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific
- * checking before calling the locks_conflict().
+static unsigned int
+deny_flags_to_cmd(unsigned int flags)
+{
+	unsigned int cmd = LOCK_MAND;
+
+	if (!(flags & O_DENYREAD))
+		cmd |= LOCK_READ;
+	if (!(flags & O_DENYWRITE))
+		cmd |= LOCK_WRITE;
+
+	return cmd;
+}
+
+/*
+ * locks_mand_conflict - Determine if there's a share reservation conflict
+ * @caller_fl: lock we're attempting to acquire
+ * @sys_fl: lock already present on system that we're checking against
+ *
+ * Check to see if there's a share_reservation conflict. LOCK_READ/LOCK_WRITE
+ * tell us whether the reservation allows other readers and writers.
+ */
+static int
+locks_mand_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
+{
+	unsigned char caller_type = caller_fl->fl_type;
+	unsigned char sys_type = sys_fl->fl_type;
+	fmode_t caller_fmode = caller_fl->fl_file->f_mode;
+	fmode_t sys_fmode = sys_fl->fl_file->f_mode;
+
+	/* they can only conflict if FS is mounted with MS_SHARELOCK */
+	if (!IS_SHARELOCK(caller_fl->fl_file->f_path.dentry->d_inode))
+		return 0;
+
+	/* they can only conflict if they're both LOCK_MAND */
+	if (!(caller_type & LOCK_MAND) || !(sys_type & LOCK_MAND))
+		return 0;
+
+	if (!(caller_type & LOCK_READ) && (sys_fmode & FMODE_READ))
+		return 1;
+	if (!(caller_type & LOCK_WRITE) && (sys_fmode & FMODE_WRITE))
+		return 1;
+	if (!(sys_type & LOCK_READ) && (caller_fmode & FMODE_READ))
+		return 1;
+	if (!(sys_type & LOCK_WRITE) && (caller_fmode & FMODE_WRITE))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Determine if lock sys_fl blocks lock caller_fl. FLOCK specific checking
+ * before calling the locks_conflict().
  */
 static int flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl)
 {
-	/* FLOCK locks referring to the same filp do not conflict with
+	if (!IS_FLOCK(sys_fl))
+		return 0;
+	if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND))
+		return locks_mand_conflict(caller_fl, sys_fl);
+	/*
+	 * FLOCK locks referring to the same filp do not conflict with
 	 * each other.
 	 */
-	if (!IS_FLOCK(sys_fl) || (caller_fl->fl_file == sys_fl->fl_file))
-		return (0);
-	if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND))
+	if (caller_fl->fl_file == sys_fl->fl_file)
 		return 0;
 
-	return (locks_conflict(caller_fl, sys_fl));
+	return locks_conflict(caller_fl, sys_fl);
 }
 
 void
@@ -888,6 +941,36 @@ out:
 	return error;
 }
 
+/*
+ * Determine if a file is allowed to be opened with specified access and share
+ * modes. Lock the file and return 0 if checks passed, otherwise return
+ * -ESHAREDENIED.
+ */
+int
+sharelock_lock_file(struct file *filp)
+{
+	struct file_lock *lock;
+	int error = 0;
+
+	if (!IS_SHARELOCK(filp->f_path.dentry->d_inode))
+		return error;
+
+	/* Disable O_DENYDELETE support for now */
+	if (filp->f_flags & O_DENYDELETE)
+		return -EINVAL;
+
+	error = flock_make_lock(filp, &lock, deny_flags_to_cmd(filp->f_flags));
+	if (error)
+		return error;
+
+	error = flock_lock_file(filp, lock);
+	if (error == -EAGAIN)
+		error = -ESHAREDENIED;
+
+	locks_free_lock(lock);
+	return error;
+}
+
 static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock)
 {
 	struct file_lock *fl;
diff --git a/fs/namei.c b/fs/namei.c
index 3531dee..2b741a1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2725,9 +2725,14 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 		acc_mode = MAY_OPEN;
 	}
 	error = may_open(&file->f_path, acc_mode, open_flag);
-	if (error)
+	if (error) {
 		fput(file);
+		goto out;
+	}
 
+	error = sharelock_lock_file(file);
+	if (error)
+		fput(file);
 out:
 	dput(dentry);
 	return error;
@@ -2919,6 +2924,40 @@ retry_lookup:
 	}
 	mutex_lock(&dir->d_inode->i_mutex);
 	error = lookup_open(nd, path, file, op, got_write, opened);
+
+	/*
+	 * For sharelock mounts if a file was created but not opened, we need
+	 * to keep parent i_mutex until we finish the open to prevent races when
+	 * somebody opens newly created by us file and locks it with a sharelock
+	 * before we open it.
+	 */
+	if (IS_SHARELOCK(dir->d_inode) && error > 0 && *opened & FILE_CREATED) {
+		/* Don't check for write permission, don't truncate */
+		open_flag &= ~O_TRUNC;
+		will_truncate = false;
+		acc_mode = MAY_OPEN;
+		path_to_nameidata(path, nd);
+
+		error = may_open(&nd->path, acc_mode, open_flag);
+		if (error) {
+			mutex_unlock(&dir->d_inode->i_mutex);
+			goto out;
+		}
+		file->f_path.mnt = nd->path.mnt;
+		error = finish_open(file, nd->path.dentry, NULL, opened);
+		if (error) {
+			mutex_unlock(&dir->d_inode->i_mutex);
+			if (error == -EOPENSTALE)
+				goto stale_open;
+			goto out;
+		}
+		error = sharelock_lock_file(file);
+		mutex_unlock(&dir->d_inode->i_mutex);
+		if (error)
+			goto exit_fput;
+		goto opened;
+	}
+
 	mutex_unlock(&dir->d_inode->i_mutex);
 
 	if (error <= 0) {
@@ -3034,6 +3073,18 @@ finish_open_created:
 			goto stale_open;
 		goto out;
 	}
+
+	if (IS_SHARELOCK(dir->d_inode)) {
+		/*
+		 * Lock parent i_mutex to prevent races with sharelocks on
+		 * newly created files.
+		 */
+		mutex_lock(&dir->d_inode->i_mutex);
+		error = sharelock_lock_file(file);
+		mutex_unlock(&dir->d_inode->i_mutex);
+		if (error)
+			goto exit_fput;
+	}
 opened:
 	error = open_check_o_direct(file);
 	if (error)
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 439406e..dd374d4 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -44,6 +44,7 @@ static int show_sb_opts(struct seq_file *m, struct super_block *sb)
 		{ MS_SYNCHRONOUS, ",sync" },
 		{ MS_DIRSYNC, ",dirsync" },
 		{ MS_MANDLOCK, ",mand" },
+		{ MS_SHARELOCK, ",sharelock" },
 		{ 0, NULL }
 	};
 	const struct proc_fs_info *fs_infop;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 121f11f..aa061ca 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1029,6 +1029,7 @@ extern int vfs_setlease(struct file *, long, struct file_lock **);
 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);
+extern int sharelock_lock_file(struct file *);
 #else /* !CONFIG_FILE_LOCKING */
 static inline int fcntl_getlk(struct file *file, struct flock __user *user)
 {
@@ -1169,6 +1170,12 @@ static inline int lock_may_write(struct inode *inode, loff_t start,
 {
 	return 1;
 }
+
+static inline int sharelock_lock_file(struct file *filp)
+{
+	return 0;
+}
+
 #endif /* !CONFIG_FILE_LOCKING */
 
 
@@ -1675,6 +1682,7 @@ struct super_operations {
 #define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
 #define IS_IMA(inode)		((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
+#define IS_SHARELOCK(inode)	__IS_FLG(inode, MS_SHARELOCK)
 #define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
 
 /*
diff --git a/include/uapi/asm-generic/errno.h b/include/uapi/asm-generic/errno.h
index 1e1ea6e..aff869c 100644
--- a/include/uapi/asm-generic/errno.h
+++ b/include/uapi/asm-generic/errno.h
@@ -110,4 +110,6 @@
 
 #define EHWPOISON	133	/* Memory page has hardware error */
 
+#define ESHAREDENIED	134	/* File is locked with a sharelock */
+
 #endif
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 95e46c8..9881cfe 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -92,6 +92,17 @@
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
 #define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)      
 
+#ifndef O_DENYREAD
+#define O_DENYREAD	040000000	/* Do not permit read access */
+#endif
+/* FMODE_NONOTIFY	0100000000 */
+#ifndef O_DENYWRITE
+#define O_DENYWRITE	0200000000	/* Do not permit write access */
+#endif
+#ifndef O_DENYDELETE
+#define O_DENYDELETE	0400000000	/* Do not permit delete or rename */
+#endif
+
 #ifndef O_NDELAY
 #define O_NDELAY	O_NONBLOCK
 #endif
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 6c28b61..11f0ecf 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -86,6 +86,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_SHARELOCK	(1<<25) /* Allow share locks on an FS */
 
 /* These sb flags are internal to the kernel */
 #define MS_NOSEC	(1<<28)
-- 
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux