Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/hch/vfs-queue

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/hch/vfs-queue: (21 commits)
  leases: fix write-open/read-lease race
  nfs: drop unnecessary locking in llseek
  ext4: replace cut'n'pasted llseek code with generic_file_llseek_size
  vfs: add generic_file_llseek_size
  vfs: do (nearly) lockless generic_file_llseek
  direct-io: merge direct_io_walker into __blockdev_direct_IO
  direct-io: inline the complete submission path
  direct-io: separate map_bh from dio
  direct-io: use a slab cache for struct dio
  direct-io: rearrange fields in dio/dio_submit to avoid holes
  direct-io: fix a wrong comment
  direct-io: separate fields only used in the submission path from struct dio
  vfs: fix spinning prevention in prune_icache_sb
  vfs: add a comment to inode_permission()
  vfs: pass all mask flags check_acl and posix_acl_permission
  vfs: add hex format for MAY_* flag values
  vfs: indicate that the permission functions take all the MAY_* flags
  compat: sync compat_stats with statfs.
  vfs: add "device" tag to /proc/self/mountstats
  cleanup: vfs: small comment fix for block_invalidatepage
  ...

Fix up trivial conflict in fs/gfs2/file.c (llseek changes)

arch/mips/include/asm/compat.h

@@ -111,7 +111,8 @@ struct compat_statfs {
 	int		f_bavail;
 	compat_fsid_t	f_fsid;
 	int		f_namelen;
-	int		f_spare[6];
+	int		f_flags;
+	int		f_spare[5];
 };
 
 #define COMPAT_RLIM_INFINITY	0x7fffffffUL

arch/parisc/include/asm/compat.h

@@ -105,7 +105,8 @@ struct compat_statfs {
 	__kernel_fsid_t	f_fsid;
 	s32		f_namelen;
 	s32		f_frsize;
-	s32		f_spare[5];
+	s32		f_flags;
+	s32		f_spare[4];
 };
 
 struct compat_sigcontext {

arch/powerpc/include/asm/compat.h

@@ -100,7 +100,8 @@ struct compat_statfs {
 	compat_fsid_t	f_fsid;
 	int		f_namelen;	/* SunOS ignores this field. */
 	int		f_frsize;
-	int		f_spare[5];
+	int		f_flags;
+	int		f_spare[4];
 };
 
 #define COMPAT_RLIM_OLD_INFINITY	0x7fffffff

arch/s390/include/asm/compat.h

@@ -131,7 +131,8 @@ struct compat_statfs {
 	compat_fsid_t	f_fsid;
 	s32		f_namelen;
 	s32		f_frsize;
-	s32		f_spare[6];
+	s32		f_flags;
+	s32		f_spare[5];
 };
 
 #define COMPAT_RLIM_OLD_INFINITY	0x7fffffff

arch/sparc/include/asm/compat.h

@@ -134,7 +134,8 @@ struct compat_statfs {
 	compat_fsid_t	f_fsid;
 	int		f_namelen;	/* SunOS ignores this field. */
 	int		f_frsize;
-	int		f_spare[5];
+	int		f_flags;
+	int		f_spare[4];
 };
 
 #define COMPAT_RLIM_INFINITY 0x7fffffff

arch/x86/include/asm/compat.h

@@ -108,7 +108,8 @@ struct compat_statfs {
 	compat_fsid_t	f_fsid;
 	int		f_namelen;	/* SunOS ignores this field. */
 	int		f_frsize;
-	int		f_spare[5];
+	int		f_flags;
+	int		f_spare[4];
 };
 
 #define COMPAT_RLIM_OLD_INFINITY	0x7fffffff

fs/btrfs/file.c

@@ -1821,7 +1821,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
 	switch (origin) {
 	case SEEK_END:
 	case SEEK_CUR:
-		offset = generic_file_llseek_unlocked(file, offset, origin);
+		offset = generic_file_llseek(file, offset, origin);
 		goto out;
 	case SEEK_DATA:
 	case SEEK_HOLE:

fs/buffer.c

@@ -1470,13 +1470,13 @@ static void discard_buffer(struct buffer_head * bh)
 }
 
 /**
- * block_invalidatepage - invalidate part of all of a buffer-backed page
+ * block_invalidatepage - invalidate part or all of a buffer-backed page
  *
  * @page: the page which is affected
  * @offset: the index of the truncation point
  *
  * block_invalidatepage() is called when all or part of the page has become
- * invalidatedby a truncate operation.
+ * invalidated by a truncate operation.
  *
  * block_invalidatepage() does not have to release all buffers, but it must
  * ensure that no dirty buffer is left outside @offset and that no I/O

fs/cifs/cifsfs.c

@@ -730,7 +730,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin)
 		if (rc < 0)
 			return (loff_t)rc;
 	}
-	return generic_file_llseek_unlocked(file, offset, origin);
+	return generic_file_llseek(file, offset, origin);
 }
 
 static int cifs_setlease(struct file *file, long arg, struct file_lock **lease)

fs/compat.c

@@ -246,11 +246,8 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
 	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
 	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
 	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
-	    __put_user(0, &ubuf->f_spare[0]) || 
+	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
-	    __put_user(0, &ubuf->f_spare[1]) || 
+	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
-	    __put_user(0, &ubuf->f_spare[2]) || 
-	    __put_user(0, &ubuf->f_spare[3]) || 
-	    __put_user(0, &ubuf->f_spare[4]))
 		return -EFAULT;
 	return 0;
 }

fs/ext4/file.c

@@ -224,53 +224,8 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
 		maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
 	else
 		maxbytes = inode->i_sb->s_maxbytes;
-	mutex_lock(&inode->i_mutex);
-	switch (origin) {
-	case SEEK_END:
-		offset += inode->i_size;
-		break;
-	case SEEK_CUR:
-		if (offset == 0) {
-			mutex_unlock(&inode->i_mutex);
-			return file->f_pos;
-		}
-		offset += file->f_pos;
-		break;
-	case SEEK_DATA:
-		/*
-		 * In the generic case the entire file is data, so as long as
-		 * offset isn't at the end of the file then the offset is data.
-		 */
-		if (offset >= inode->i_size) {
-			mutex_unlock(&inode->i_mutex);
-			return -ENXIO;
-		}
-		break;
-	case SEEK_HOLE:
-		/*
-		 * There is a virtual hole at the end of the file, so as long as
-		 * offset isn't i_size or larger, return i_size.
-		 */
-		if (offset >= inode->i_size) {
-			mutex_unlock(&inode->i_mutex);
-			return -ENXIO;
-		}
-		offset = inode->i_size;
-		break;
-	}
 
-	if (offset < 0 || offset > maxbytes) {
+	return generic_file_llseek_size(file, offset, origin, maxbytes);
-		mutex_unlock(&inode->i_mutex);
-		return -EINVAL;
-	}
-
-	if (offset != file->f_pos) {
-		file->f_pos = offset;
-		file->f_version = 0;
-	}
-	mutex_unlock(&inode->i_mutex);
-
-	return offset;
 }
 
 const struct file_operations ext4_file_operations = {

fs/gfs2/file.c

@@ -66,13 +66,13 @@ static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
 					   &i_gh);
 		if (!error) {
-			error = generic_file_llseek_unlocked(file, offset, origin);
+			error = generic_file_llseek(file, offset, origin);
 			gfs2_glock_dq_uninit(&i_gh);
 		}
 		break;
 	case SEEK_CUR:
 	case SEEK_SET:
-		error = generic_file_llseek_unlocked(file, offset, origin);
+		error = generic_file_llseek(file, offset, origin);
 		break;
 	default:
 		error = -EINVAL;

fs/inode.c

@@ -634,7 +634,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
 		 * inode to the back of the list so we don't spin on it.
 		 */
 		if (!spin_trylock(&inode->i_lock)) {
-			list_move(&inode->i_lru, &sb->s_inode_lru);
+			list_move_tail(&inode->i_lru, &sb->s_inode_lru);
 			continue;
 		}
 

fs/namei.c

@@ -221,14 +221,12 @@ static int check_acl(struct inode *inode, int mask)
 }
 
 /*
- * This does basic POSIX ACL permission checking
+ * This does the basic permission checking
  */
 static int acl_permission_check(struct inode *inode, int mask)
 {
 	unsigned int mode = inode->i_mode;
 
-	mask &= MAY_READ | MAY_WRITE | MAY_EXEC | MAY_NOT_BLOCK;
-
 	if (current_user_ns() != inode_userns(inode))
 		goto other_perms;
 
@@ -257,7 +255,7 @@ other_perms:
 /**
  * generic_permission -  check for access rights on a Posix-like filesystem
  * @inode:	inode to check access rights for
- * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
  *
  * Used to check for read/write/execute permissions on a file.
  * We use "fsuid" for this, letting us set arbitrary permissions
@@ -273,7 +271,7 @@ int generic_permission(struct inode *inode, int mask)
 	int ret;
 
 	/*
-	 * Do the basic POSIX ACL permission checks.
+	 * Do the basic permission checks.
 	 */
 	ret = acl_permission_check(inode, mask);
 	if (ret != -EACCES)
@@ -331,12 +329,14 @@ static inline int do_inode_permission(struct inode *inode, int mask)
 /**
  * inode_permission  -  check for access rights to a given inode
  * @inode:	inode to check permission on
- * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...)
  *
  * Used to check for read/write/execute permissions on an inode.
  * We use "fsuid" for this, letting us set arbitrary permissions
  * for filesystem access without changing the "normal" uids which
  * are used for other things.
+ *
+ * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
  */
 int inode_permission(struct inode *inode, int mask)
 {
@@ -2035,10 +2035,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
 	if (flag & O_NOATIME && !inode_owner_or_capable(inode))
 		return -EPERM;
 
-	/*
+	return 0;
-	 * Ensure there are no outstanding leases on the file.
-	 */
-	return break_lease(inode, flag);
 }
 
 static int handle_truncate(struct file *filp)

fs/namespace.c

@@ -1109,6 +1109,7 @@ static int show_vfsstat(struct seq_file *m, void *v)
 
 	/* device */
 	if (mnt->mnt_sb->s_op->show_devname) {
+		seq_puts(m, "device ");
 		err = mnt->mnt_sb->s_op->show_devname(m, mnt);
 	} else {
 		if (mnt->mnt_devname) {

fs/nfs/file.c

@@ -180,8 +180,6 @@ force_reval:
 
 static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 {
-	loff_t loff;
-
 	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
 			filp->f_path.dentry->d_parent->d_name.name,
 			filp->f_path.dentry->d_name.name,
@@ -197,13 +195,9 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 		int retval = nfs_revalidate_file_size(inode, filp);
 		if (retval < 0)
 			return (loff_t)retval;
+	}
 
-		spin_lock(&inode->i_lock);
+	return generic_file_llseek(filp, offset, origin);
-		loff = generic_file_llseek_unlocked(filp, offset, origin);
-		spin_unlock(&inode->i_lock);
-	} else
-		loff = generic_file_llseek_unlocked(filp, offset, origin);
-	return loff;
 }
 
 /*

fs/open.c

@@ -685,6 +685,10 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	if (error)
 		goto cleanup_all;
 
+	error = break_lease(inode, f->f_flags);
+	if (error)
+		goto cleanup_all;
+
 	if (!open && f->f_op)
 		open = f->f_op->open;
 	if (open) {

fs/posix_acl.c

@@ -218,6 +218,8 @@ posix_acl_permission(struct inode *inode, const struct posix_acl *acl, int want)
 	const struct posix_acl_entry *pa, *pe, *mask_obj;
 	int found = 0;
 
+	want &= MAY_READ | MAY_WRITE | MAY_EXEC | MAY_NOT_BLOCK;
+
 	FOREACH_ACL_ENTRY(pa, acl, pe) {
                 switch(pa->e_tag) {
                         case ACL_USER_OBJ:

fs/read_write.c

@@ -35,23 +35,45 @@ static inline int unsigned_offsets(struct file *file)
 	return file->f_mode & FMODE_UNSIGNED_OFFSET;
 }
 
+static loff_t lseek_execute(struct file *file, struct inode *inode,
+		loff_t offset, loff_t maxsize)
+{
+	if (offset < 0 && !unsigned_offsets(file))
+		return -EINVAL;
+	if (offset > maxsize)
+		return -EINVAL;
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	return offset;
+}
+
 /**
- * generic_file_llseek_unlocked - lockless generic llseek implementation
+ * generic_file_llseek_size - generic llseek implementation for regular files
  * @file:	file structure to seek on
  * @offset:	file offset to seek to
  * @origin:	type of seek
+ * @size:	max size of file system
  *
- * Updates the file offset to the value specified by @offset and @origin.
+ * This is a variant of generic_file_llseek that allows passing in a custom
- * Locking must be provided by the caller.
+ * file size.
+ *
+ * Synchronization:
+ * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms)
+ * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes.
+ * read/writes behave like SEEK_SET against seeks.
  */
 loff_t
-generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
+generic_file_llseek_size(struct file *file, loff_t offset, int origin,
+		loff_t maxsize)
 {
 	struct inode *inode = file->f_mapping->host;
 
 	switch (origin) {
 	case SEEK_END:
-		offset += inode->i_size;
+		offset += i_size_read(inode);
 		break;
 	case SEEK_CUR:
 		/*
@@ -62,14 +84,22 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
 		 */
 		if (offset == 0)
 			return file->f_pos;
-		offset += file->f_pos;
+		/*
-		break;
+		 * f_lock protects against read/modify/write race with other
+		 * SEEK_CURs. Note that parallel writes and reads behave
+		 * like SEEK_SET.
+		 */
+		spin_lock(&file->f_lock);
+		offset = lseek_execute(file, inode, file->f_pos + offset,
+				       maxsize);
+		spin_unlock(&file->f_lock);
+		return offset;
 	case SEEK_DATA:
 		/*
 		 * In the generic case the entire file is data, so as long as
 		 * offset isn't at the end of the file then the offset is data.
 		 */
-		if (offset >= inode->i_size)
+		if (offset >= i_size_read(inode))
 			return -ENXIO;
 		break;
 	case SEEK_HOLE:
@@ -77,26 +107,15 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
 		 * There is a virtual hole at the end of the file, so as long as
 		 * offset isn't i_size or larger, return i_size.
 		 */
-		if (offset >= inode->i_size)
+		if (offset >= i_size_read(inode))
 			return -ENXIO;
-		offset = inode->i_size;
+		offset = i_size_read(inode);
 		break;
 	}
 
-	if (offset < 0 && !unsigned_offsets(file))
+	return lseek_execute(file, inode, offset, maxsize);
-		return -EINVAL;
-	if (offset > inode->i_sb->s_maxbytes)
-		return -EINVAL;
-
-	/* Special lock needed here? */
-	if (offset != file->f_pos) {
-		file->f_pos = offset;
-		file->f_version = 0;
-	}
-
-	return offset;
 }
-EXPORT_SYMBOL(generic_file_llseek_unlocked);
+EXPORT_SYMBOL(generic_file_llseek_size);
 
 /**
  * generic_file_llseek - generic llseek implementation for regular files
@@ -110,13 +129,10 @@ EXPORT_SYMBOL(generic_file_llseek_unlocked);
  */
 loff_t generic_file_llseek(struct file *file, loff_t offset, int origin)
 {
-	loff_t rval;
+	struct inode *inode = file->f_mapping->host;
 
-	mutex_lock(&file->f_dentry->d_inode->i_mutex);
+	return generic_file_llseek_size(file, offset, origin,
-	rval = generic_file_llseek_unlocked(file, offset, origin);
+					inode->i_sb->s_maxbytes);
-	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
-
-	return rval;
 }
 EXPORT_SYMBOL(generic_file_llseek);
 

include/linux/fs.h

@@ -58,14 +58,15 @@ struct inodes_stat_t {
 
 #define NR_FILE  8192	/* this can well be larger on a larger system */
 
-#define MAY_EXEC 1
+#define MAY_EXEC		0x00000001
-#define MAY_WRITE 2
+#define MAY_WRITE		0x00000002
-#define MAY_READ 4
+#define MAY_READ		0x00000004
-#define MAY_APPEND 8
+#define MAY_APPEND		0x00000008
-#define MAY_ACCESS 16
+#define MAY_ACCESS		0x00000010
-#define MAY_OPEN 32
+#define MAY_OPEN		0x00000020
-#define MAY_CHDIR 64
+#define MAY_CHDIR		0x00000040
-#define MAY_NOT_BLOCK 128	/* called from RCU mode, don't block */
+/* called from RCU mode, don't block */
+#define MAY_NOT_BLOCK		0x00000080
 
 /*
  * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
@@ -963,7 +964,12 @@ struct file {
 #define f_dentry	f_path.dentry
 #define f_vfsmnt	f_path.mnt
 	const struct file_operations	*f_op;
-	spinlock_t		f_lock;  /* f_ep_links, f_flags, no IRQ */
+
+	/*
+	 * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
+	 * Must not be taken from IRQ context.
+	 */
+	spinlock_t		f_lock;
 #ifdef CONFIG_SMP
 	int			f_sb_list_cpu;
 #endif
@@ -2401,8 +2407,8 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
 extern loff_t noop_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
 extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
-extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset,
+extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
-			int origin);
+		int origin, loff_t maxsize);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 

mm/filemap.c

@@ -2115,6 +2115,7 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes)
 	} else {
 		const struct iovec *iov = i->iov;
 		size_t base = i->iov_offset;
+		unsigned long nr_segs = i->nr_segs;
 
 		/*
 		 * The !iov->iov_len check ensures we skip over unlikely
@@ -2130,11 +2131,13 @@ void iov_iter_advance(struct iov_iter *i, size_t bytes)
 			base += copy;
 			if (iov->iov_len == base) {
 				iov++;
+				nr_segs--;
 				base = 0;
 			}
 		}
 		i->iov = iov;
 		i->iov_offset = base;
+		i->nr_segs = nr_segs;
 	}
 }
 EXPORT_SYMBOL(iov_iter_advance);