Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  truncate: use new helpers
  truncate: new helpers
  fs: fix overflow in sys_mount() for in-kernel calls
  fs: Make unload_nls() NULL pointer safe
  freeze_bdev: grab active reference to frozen superblocks
  freeze_bdev: kill bd_mount_sem
  exofs: remove BKL from super operations
  fs/romfs: correct error-handling code
  vfs: seq_file: add helpers for data filling
  vfs: remove redundant position check in do_sendfile
  vfs: change sb->s_maxbytes to a loff_t
  vfs: explicitly cast s_maxbytes in fiemap_check_ranges
  libfs: return error code on failed attr set
  seq_file: return a negative error code when seq_path_root() fails.
  vfs: optimize touch_time() too
  vfs: optimization for touch_atime()
  vfs: split generic_forget_inode() so that hugetlbfs does not have to copy it
  fs/inode.c: add dev-id and inode number for debugging in init_special_inode()
  libfs: make simple_read_from_buffer conventional

41 files changed, 532 insertions, 533 deletions

diff --git a/Documentation/vm/locking b/Documentation/vm/locking
index f366fa956179..25fadb448760 100644
--- a/Documentation/vm/locking
+++ b/Documentation/vm/locking
@@ -80,7 +80,7 @@ Note: PTL can also be used to guarantee that no new clones using the
 mm start up ... this is a loose form of stability on mm_users. For
 example, it is used in copy_mm to protect against a racing tlb_gather_mmu
 single address space optimization, so that the zap_page_range (from
-vmtruncate) does not lose sending ipi's to cloned threads that might 
+truncate) does not lose sending ipi's to cloned threads that might
 be spawned underneath it and go to user mode to drag in pte's into tlbs.
 
 swap_lock
diff --git a/fs/attr.c b/fs/attr.c
index 9fe1b1bd30a8..96d394bdaddf 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -18,7 +18,7 @@
 /* Taken over from the old code... */
 
 /* POSIX UID/GID verification for setting inode attributes. */
-int inode_change_ok(struct inode *inode, struct iattr *attr)
+int inode_change_ok(const struct inode *inode, struct iattr *attr)
 {
         int retval = -EPERM;
         unsigned int ia_valid = attr->ia_valid;
@@ -60,9 +60,51 @@ fine:
 error:
         return retval;
 }
-
 EXPORT_SYMBOL(inode_change_ok);
 
+/**
+ * inode_newsize_ok - may this inode be truncated to a given size
+ * @inode:      the inode to be truncated
+ * @offset:     the new size to assign to the inode
+ * @Returns:    0 on success, -ve errno on failure
+ *
+ * inode_newsize_ok will check filesystem limits and ulimits to check that the
+ * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
+ * when necessary. Caller must not proceed with inode size change if failure is
+ * returned. @inode must be a file (not directory), with appropriate
+ * permissions to allow truncate (inode_newsize_ok does NOT check these
+ * conditions).
+ *
+ * inode_newsize_ok must be called with i_mutex held.
+ */
+int inode_newsize_ok(const struct inode *inode, loff_t offset)
+{
+        if (inode->i_size < offset) {
+                unsigned long limit;
+
+                limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+                if (limit != RLIM_INFINITY && offset > limit)
+                        goto out_sig;
+                if (offset > inode->i_sb->s_maxbytes)
+                        goto out_big;
+        } else {
+                /*
+                 * truncation of in-use swapfiles is disallowed - it would
+                 * cause subsequent swapout to scribble on the now-freed
+                 * blocks.
+                 */
+                if (IS_SWAPFILE(inode))
+                        return -ETXTBSY;
+        }
+
+        return 0;
+out_sig:
+        send_sig(SIGXFSZ, current, 0);
+out_big:
+        return -EFBIG;
+}
+EXPORT_SYMBOL(inode_newsize_ok);
+
 int inode_setattr(struct inode * inode, struct iattr * attr)
 {
         unsigned int ia_valid = attr->ia_valid;
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index dd376c124e71..33baf27fac78 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -737,12 +737,7 @@ befs_put_super(struct super_block *sb)
 {
         kfree(BEFS_SB(sb)->mount_opts.iocharset);
         BEFS_SB(sb)->mount_opts.iocharset = NULL;
-
-        if (BEFS_SB(sb)->nls) {
-                unload_nls(BEFS_SB(sb)->nls);
-                BEFS_SB(sb)->nls = NULL;
-        }
-
+        unload_nls(BEFS_SB(sb)->nls);
         kfree(sb->s_fs_info);
         sb->s_fs_info = NULL;
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5d1ed50bd46c..9cf4b926f8e4 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -216,8 +216,6 @@ EXPORT_SYMBOL(fsync_bdev);
  * freeze_bdev  --  lock a filesystem and force it into a consistent state
  * @bdev:       blockdevice to lock
  *
- * This takes the block device bd_mount_sem to make sure no new mounts
- * happen on bdev until thaw_bdev() is called.
  * If a superblock is found on this device, we take the s_umount semaphore
  * on it to make sure nobody unmounts until the snapshot creation is done.
  * The reference counter (bd_fsfreeze_count) guarantees that only the last
@@ -232,46 +230,55 @@ struct super_block *freeze_bdev(struct block_device *bdev)
         int error = 0;
 
         mutex_lock(&bdev->bd_fsfreeze_mutex);
-        if (bdev->bd_fsfreeze_count > 0) {
-                bdev->bd_fsfreeze_count++;
+        if (++bdev->bd_fsfreeze_count > 1) {
+                /*
+                 * We don't even need to grab a reference - the first call
+                 * to freeze_bdev grab an active reference and only the last
+                 * thaw_bdev drops it.
+                 */
                 sb = get_super(bdev);
+                drop_super(sb);
                 mutex_unlock(&bdev->bd_fsfreeze_mutex);
                 return sb;
         }
-        bdev->bd_fsfreeze_count++;
-
-        down(&bdev->bd_mount_sem);
-        sb = get_super(bdev);
-        if (sb && !(sb->s_flags & MS_RDONLY)) {
-                sb->s_frozen = SB_FREEZE_WRITE;
-                smp_wmb();
-
-                sync_filesystem(sb);
-
-                sb->s_frozen = SB_FREEZE_TRANS;
-                smp_wmb();
-
-                sync_blockdev(sb->s_bdev);
-
-                if (sb->s_op->freeze_fs) {
-                        error = sb->s_op->freeze_fs(sb);
-                        if (error) {
-                                printk(KERN_ERR
-                                        "VFS:Filesystem freeze failed\n");
-                                sb->s_frozen = SB_UNFROZEN;
-                                drop_super(sb);
-                                up(&bdev->bd_mount_sem);
-                                bdev->bd_fsfreeze_count--;
-                                mutex_unlock(&bdev->bd_fsfreeze_mutex);
-                                return ERR_PTR(error);
-                        }
+
+        sb = get_active_super(bdev);
+        if (!sb)
+                goto out;
+        if (sb->s_flags & MS_RDONLY) {
+                deactivate_locked_super(sb);
+                mutex_unlock(&bdev->bd_fsfreeze_mutex);
+                return sb;
+        }
+
+        sb->s_frozen = SB_FREEZE_WRITE;
+        smp_wmb();
+
+        sync_filesystem(sb);
+
+        sb->s_frozen = SB_FREEZE_TRANS;
+        smp_wmb();
+
+        sync_blockdev(sb->s_bdev);
+
+        if (sb->s_op->freeze_fs) {
+                error = sb->s_op->freeze_fs(sb);
+                if (error) {
+                        printk(KERN_ERR
+                                "VFS:Filesystem freeze failed\n");
+                        sb->s_frozen = SB_UNFROZEN;
+                        deactivate_locked_super(sb);
+                        bdev->bd_fsfreeze_count--;
+                        mutex_unlock(&bdev->bd_fsfreeze_mutex);
+                        return ERR_PTR(error);
                 }
         }
+        up_write(&sb->s_umount);
 
+ out:
         sync_blockdev(bdev);
         mutex_unlock(&bdev->bd_fsfreeze_mutex);
-
-        return sb;      /* thaw_bdev releases s->s_umount and bd_mount_sem */
+        return sb;      /* thaw_bdev releases s->s_umount */
 }
 EXPORT_SYMBOL(freeze_bdev);
 
@@ -284,44 +291,44 @@ EXPORT_SYMBOL(freeze_bdev);
  */
 int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 {
-        int error = 0;
+        int error = -EINVAL;
 
         mutex_lock(&bdev->bd_fsfreeze_mutex);
-        if (!bdev->bd_fsfreeze_count) {
-                mutex_unlock(&bdev->bd_fsfreeze_mutex);
-                return -EINVAL;
-        }
-
-        bdev->bd_fsfreeze_count--;
-        if (bdev->bd_fsfreeze_count > 0) {
-                if (sb)
-                        drop_super(sb);
-                mutex_unlock(&bdev->bd_fsfreeze_mutex);
-                return 0;
-        }
-
-        if (sb) {
-                BUG_ON(sb->s_bdev != bdev);
-                if (!(sb->s_flags & MS_RDONLY)) {
-                        if (sb->s_op->unfreeze_fs) {
-                                error = sb->s_op->unfreeze_fs(sb);
-                                if (error) {
-                                        printk(KERN_ERR
-                                                "VFS:Filesystem thaw failed\n");
-                                        sb->s_frozen = SB_FREEZE_TRANS;
-                                        bdev->bd_fsfreeze_count++;
-                                        mutex_unlock(&bdev->bd_fsfreeze_mutex);
-                                        return error;
-                                }
-                        }
-                        sb->s_frozen = SB_UNFROZEN;
-                        smp_wmb();
-                        wake_up(&sb->s_wait_unfrozen);
+        if (!bdev->bd_fsfreeze_count)
+                goto out_unlock;
+
+        error = 0;
+        if (--bdev->bd_fsfreeze_count > 0)
+                goto out_unlock;
+
+        if (!sb)
+                goto out_unlock;
+
+        BUG_ON(sb->s_bdev != bdev);
+        down_write(&sb->s_umount);
+        if (sb->s_flags & MS_RDONLY)
+                goto out_deactivate;
+
+        if (sb->s_op->unfreeze_fs) {
+                error = sb->s_op->unfreeze_fs(sb);
+                if (error) {
+                        printk(KERN_ERR
+                                "VFS:Filesystem thaw failed\n");
+                        sb->s_frozen = SB_FREEZE_TRANS;
+                        bdev->bd_fsfreeze_count++;
+                        mutex_unlock(&bdev->bd_fsfreeze_mutex);
+                        return error;
                 }
-                drop_super(sb);
         }
 
-        up(&bdev->bd_mount_sem);
+        sb->s_frozen = SB_UNFROZEN;
+        smp_wmb();
+        wake_up(&sb->s_wait_unfrozen);
+
+out_deactivate:
+        if (sb)
+                deactivate_locked_super(sb);
+out_unlock:
         mutex_unlock(&bdev->bd_fsfreeze_mutex);
         return 0;
 }
@@ -430,7 +437,6 @@ static void init_once(void *foo)
 
         memset(bdev, 0, sizeof(*bdev));
         mutex_init(&bdev->bd_mutex);
-        sema_init(&bdev->bd_mount_sem, 1);
         INIT_LIST_HEAD(&bdev->bd_inodes);
         INIT_LIST_HEAD(&bdev->bd_list);
 #ifdef CONFIG_SYSFS
diff --git a/fs/buffer.c b/fs/buffer.c
index 209f7f15f5f8..24afd7422ae8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2239,16 +2239,10 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
         struct address_space *mapping = inode->i_mapping;
         struct page *page;