Merge branch 'akpm' (updates from Andrew Morton)

Merge second patch-bomb from Andrew Morton:
 - misc fixes
 - audit stuff
 - fanotify/inotify/dnotify things
 - most of the rest of MM.  The new cache shrinker code from Glauber and
   Dave Chinner probably isn't quite stabilized yet.
 - ptrace
 - ipc
 - partitions
 - reboot cleanups
 - add LZ4 decompressor, use it for kernel compression

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  lib/scatterlist: error handling in __sg_alloc_table()
  scsi_debug: fix do_device_access() with wrap around range
  crypto: talitos: use sg_pcopy_to_buffer()
  lib/scatterlist: introduce sg_pcopy_from_buffer() and sg_pcopy_to_buffer()
  lib/scatterlist: factor out sg_miter_get_next_page() from sg_miter_next()
  crypto: add lz4 Cryptographic API
  lib: add lz4 compressor module
  arm: add support for LZ4-compressed kernel
  lib: add support for LZ4-compressed kernel
  decompressor: add LZ4 decompressor module
  lib: add weak clz/ctz functions
  reboot: move arch/x86 reboot= handling to generic kernel
  reboot: arm: change reboot_mode to use enum reboot_mode
  reboot: arm: prepare reboot_mode for moving to generic kernel code
  reboot: arm: remove unused restart_mode fields from some arm subarchs
  reboot: unicore32: prepare reboot_mode for moving to generic kernel code
  reboot: x86: prepare reboot_mode for moving to generic kernel code
  reboot: checkpatch.pl the new kernel/reboot.c file
  reboot: move shutdown/reboot related functions to kernel/reboot.c
  reboot: remove -stable friendly PF_THREAD_BOUND define
  ...

8 files changed, 119 insertions, 89 deletions

diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 21664fcf3616..4241e6f39e86 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -86,6 +86,7 @@ struct msdos_sb_info {
 	const void *dir_ops;	      /* Opaque; default directory operations */
 	int dir_per_block;	      /* dir entries per block */
 	int dir_per_block_bits;	      /* log2(dir_per_block) */
+	unsigned int vol_id;		/*volume ID*/
 
 	int fatent_shift;
 	struct fatent_operations *fatent_ops;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index b0b632e50ddb..9b104f543056 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -114,6 +114,12 @@ out:
 	return err;
 }
 
+static int fat_ioctl_get_volume_id(struct inode *inode, u32 __user *user_attr)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+	return put_user(sbi->vol_id, user_attr);
+}
+
 long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -124,6 +130,8 @@ long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return fat_ioctl_get_attributes(inode, user_attr);
 	case FAT_IOCTL_SET_ATTRIBUTES:
 		return fat_ioctl_set_attributes(filp, user_attr);
+	case FAT_IOCTL_GET_VOLUME_ID:
+		return fat_ioctl_get_volume_id(inode, user_attr);
 	default:
 		return -ENOTTY;	/* Inappropriate ioctl for device */
 	}
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 5d4513cb1b3c..11b51bb55b42 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1415,6 +1415,18 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 		brelse(fsinfo_bh);
 	}
 
+	/* interpret volume ID as a little endian 32 bit integer */
+	if (sbi->fat_bits == 32)
+		sbi->vol_id = (((u32)b->fat32.vol_id[0]) |
+					((u32)b->fat32.vol_id[1] << 8) |
+					((u32)b->fat32.vol_id[2] << 16) |
+					((u32)b->fat32.vol_id[3] << 24));
+	else /* fat 16 or 12 */
+		sbi->vol_id = (((u32)b->fat16.vol_id[0]) |
+					((u32)b->fat16.vol_id[1] << 8) |
+					((u32)b->fat16.vol_id[2] << 16) |
+					((u32)b->fat16.vol_id[3] << 24));
+
 	sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
 	sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index a85ac4e33436..68851ff2fd41 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -963,7 +963,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 /*
  * Retrieve work items and do the writeback they describe
  */
-long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+static long wb_do_writeback(struct bdi_writeback *wb)
 {
 	struct backing_dev_info *bdi = wb->bdi;
 	struct wb_writeback_work *work;
@@ -971,12 +971,6 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
 
 	set_bit(BDI_writeback_running, &wb->bdi->state);
 	while ((work = get_next_work_item(bdi)) != NULL) {
-		/*
-		 * Override sync mode, in case we must wait for completion
-		 * because this thread is exiting now.
-		 */
-		if (force_wait)
-			work->sync_mode = WB_SYNC_ALL;
 
 		trace_writeback_exec(bdi, work);
 
@@ -1025,7 +1019,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 		 * rescuer as work_list needs to be drained.
 		 */
 		do {
-			pages_written = wb_do_writeback(wb, 0);
+			pages_written = wb_do_writeback(wb);
 			trace_writeback_pages_written(pages_written);
 		} while (!list_empty(&bdi->work_list));
 	} else {
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 2bfe6dc413a0..1fedd5f7ccc4 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -31,7 +31,6 @@ int dir_notify_enable __read_mostly = 1;
 static struct kmem_cache *dnotify_struct_cache __read_mostly;
 static struct kmem_cache *dnotify_mark_cache __read_mostly;
 static struct fsnotify_group *dnotify_group __read_mostly;
-static DEFINE_MUTEX(dnotify_mark_mutex);
 
 /*
  * dnotify will attach one of these to each inode (i_fsnotify_marks) which
@@ -183,7 +182,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
 		return;
 	dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
 
-	mutex_lock(&dnotify_mark_mutex);
+	mutex_lock(&dnotify_group->mark_mutex);
 
 	spin_lock(&fsn_mark->lock);
 	prev = &dn_mark->dn;
@@ -199,11 +198,12 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
 
 	spin_unlock(&fsn_mark->lock);
 
-	/* nothing else could have found us thanks to the dnotify_mark_mutex */
+	/* nothing else could have found us thanks to the dnotify_groups
+	   mark_mutex */
 	if (dn_mark->dn == NULL)
-		fsnotify_destroy_mark(fsn_mark, dnotify_group);
+		fsnotify_destroy_mark_locked(fsn_mark, dnotify_group);
 
-	mutex_unlock(&dnotify_mark_mutex);
+	mutex_unlock(&dnotify_group->mark_mutex);
 
 	fsnotify_put_mark(fsn_mark);
 }
@@ -326,7 +326,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 	new_dn_mark->dn = NULL;
 
 	/* this is needed to prevent the fcntl/close race described below */
-	mutex_lock(&dnotify_mark_mutex);
+	mutex_lock(&dnotify_group->mark_mutex);
 
 	/* add the new_fsn_mark or find an old one. */
 	fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode);
@@ -334,7 +334,8 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 		dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
 		spin_lock(&fsn_mark->lock);
 	} else {
-		fsnotify_add_mark(new_fsn_mark, dnotify_group, inode, NULL, 0);
+		fsnotify_add_mark_locked(new_fsn_mark, dnotify_group, inode,
+					 NULL, 0);
 		spin_lock(&new_fsn_mark->lock);
 		fsn_mark = new_fsn_mark;
 		dn_mark = new_dn_mark;
@@ -348,9 +349,9 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 
 	/* if (f != filp) means that we lost a race and another task/thread
 	 * actually closed the fd we are still playing with before we grabbed
-	 * the dnotify_mark_mutex and fsn_mark->lock.  Since closing the fd is the
-	 * only time we clean up the marks we need to get our mark off
-	 * the list. */
+	 * the dnotify_groups mark_mutex and fsn_mark->lock.  Since closing the
+	 * fd is the only time we clean up the marks we need to get our mark
+	 * off the list. */
 	if (f != filp) {
 		/* if we added ourselves, shoot ourselves, it's possible that
 		 * the flush actually did shoot this fsn_mark.  That's fine too
@@ -385,9 +386,9 @@ out:
 	spin_unlock(&fsn_mark->lock);
 
 	if (destroy)
-		fsnotify_destroy_mark(fsn_mark, dnotify_group);
+		fsnotify_destroy_mark_locked(fsn_mark, dnotify_group);
 
-	mutex_unlock(&dnotify_mark_mutex);
+	mutex_unlock(&dnotify_group->mark_mutex);
 	fsnotify_put_mark(fsn_mark);
 out_err:
 	if (new_fsn_mark)
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 1ea52f7c031f..e44cb6427df3 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -122,6 +122,7 @@ static int fill_event_metadata(struct fsnotify_group *group,
 	metadata->event_len = FAN_EVENT_METADATA_LEN;
 	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata->vers = FANOTIFY_METADATA_VERSION;
+	metadata->reserved = 0;
 	metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
 	metadata->pid = pid_vnr(event->tgid);
 	if (unlikely(event->mask & FAN_Q_OVERFLOW))
@@ -523,14 +524,18 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
 	__u32 removed;
 	int destroy_mark;
 
+	mutex_lock(&group->mark_mutex);
 	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
-	if (!fsn_mark)
+	if (!fsn_mark) {
+		mutex_unlock(&group->mark_mutex);
 		return -ENOENT;
+	}
 
 	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
 						 &destroy_mark);
 	if (destroy_mark)
-		fsnotify_destroy_mark(fsn_mark, group);
+		fsnotify_destroy_mark_locked(fsn_mark, group);
+	mutex_unlock(&group->mark_mutex);
 
 	fsnotify_put_mark(fsn_mark);
 	if (removed & real_mount(mnt)->mnt_fsnotify_mask)
@@ -547,14 +552,19 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
 	__u32 removed;
 	int destroy_mark;
 
+	mutex_lock(&group->mark_mutex);
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
-	if (!fsn_mark)
+	if (!fsn_mark) {
+		mutex_unlock(&group->mark_mutex);
 		return -ENOENT;
+	}
 
 	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
 						 &destroy_mark);
 	if (destroy_mark)
-		fsnotify_destroy_mark(fsn_mark, group);
+		fsnotify_destroy_mark_locked(fsn_mark, group);
+	mutex_unlock(&group->mark_mutex);
+
 	/* matches the fsnotify_find_inode_mark() */
 	fsnotify_put_mark(fsn_mark);
 	if (removed & inode->i_fsnotify_mask)
@@ -590,35 +600,55 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
 	return mask & ~oldmask;
 }
 
+static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
+						   struct inode *inode,
+						   struct vfsmount *mnt)
+{
+	struct fsnotify_mark *mark;
+	int ret;
+
+	if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+		return ERR_PTR(-ENOSPC);
+
+	mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+	if (!mark)
+		return ERR_PTR(-ENOMEM);
+
+	fsnotify_init_mark(mark, fanotify_free_mark);
+	ret = fsnotify_add_mark_locked(mark, group, inode, mnt, 0);
+	if (ret) {
+		fsnotify_put_mark(mark);
+		return ERR_PTR(ret);
+	}
+
+	return mark;
+}
+
+
 static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 				      struct vfsmount *mnt, __u32 mask,
 				      unsigned int flags)
 {
 	struct fsnotify_mark *fsn_mark;
 	__u32 added;
-	int ret = 0;
 
+	mutex_lock(&group->mark_mutex);
 	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
 	if (!fsn_mark) {
-		if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
-			return -ENOSPC;
-
-		fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
-		if (!fsn_mark)
-			return -ENOMEM;
-
-		fsnotify_init_mark(fsn_mark, fanotify_free_mark);
-		ret = fsnotify_add_mark(fsn_mark, group, NULL, mnt, 0);
-		if (ret)
-			goto err;
+		fsn_mark = fanotify_add_new_mark(group, NULL, mnt);
+		if (IS_ERR(fsn_mark)) {
+			mutex_unlock(&group->mark_mutex);
+			return PTR_ERR(fsn_mark);
+		}
 	}
 	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+	mutex_unlock(&group->mark_mutex);
 
 	if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
 		fsnotify_recalc_vfsmount_mask(mnt);
-err:
+
 	fsnotify_put_mark(fsn_mark);
-	return ret;
+	return 0;
 }
 
 static int fanotify_add_inode_mark(struct fsnotify_group *group,
@@ -627,7 +657,6 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *fsn_mark;
 	__u32 added;
-	int ret = 0;
 
 	pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
 
@@ -641,27 +670,23 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 	    (atomic_read(&inode->i_writecount) > 0))
 		return 0;
 
+	mutex_lock(&group->mark_mutex);
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
 	if (!fsn_mark) {
-		if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
-			return -ENOSPC;
-
-		fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
-		if (!fsn_mark)
-			return -ENOMEM;
-
-		fsnotify_init_mark(fsn_mark, fanotify_free_mark);
-		ret = fsnotify_add_mark(fsn_mark, group, inode, NULL, 0);
-		if (ret)
-			goto err;
+		fsn_mark = fanotify_add_new_mark(group, inode, NULL);
+		if (IS_ERR(fsn_mark)) {
+			mutex_unlock(&group->mark_mutex);
+			return PTR_ERR(fsn_mark);
+		}
 	}
 	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+	mutex_unlock(&group->mark_mutex);
 
 	if (added & ~inode->i_fsnotify_mask)
 		fsnotify_recalc_inode_mask(inode);
-err:
+
 	fsnotify_put_mark(fsn_mark);
-	return ret;
+	return 0;
 }
 
 /* fanotify syscalls */
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 959815c1e017..60f954a891ab 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -636,7 +636,8 @@ static int inotify_new_watch(struct fsnotify_group *group,
 		goto out_err;
 
 	/* we are on the idr, now get on the inode */
-	ret = fsnotify_add_mark(&tmp_i_mark->fsn_mark, group, inode, NULL, 0);
+	ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
+				       NULL, 0);
 	if (ret) {
 		/* we failed to get on the inode, get off the idr */
 		inotify_remove_from_idr(group, tmp_i_mark);
@@ -660,19 +661,13 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod
 {
 	int ret = 0;
 
-retry:
+	mutex_lock(&group->mark_mutex);
 	/* try to update and existing watch with the new arg */
 	ret = inotify_update_existing_watch(group, inode, arg);
 	/* no mark present, try to add a new one */
 	if (ret == -ENOENT)
 		ret = inotify_new_watch(group, inode, arg);
-	/*
-	 * inotify_new_watch could race with another thread which did an
-	 * inotify_new_watch between the update_existing and the add watch
-	 * here, go back and try to update an existing mark again.
-	 */
-	if (ret == -EEXIST)
-		goto retry;
+	mutex_unlock(&group->mark_mutex);
 
 	return ret;
 }
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index fc6b49bf7360..923fe4a5f503 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -20,28 +20,29 @@
  * fsnotify inode mark locking/lifetime/and refcnting
  *
  * REFCNT:
- * The mark->refcnt tells how many "things" in the kernel currently are
- * referencing this object.  The object typically will live inside the kernel
- * with a refcnt of 2, one for each list it is on (i_list, g_list).  Any task
- * which can find this object holding the appropriete locks, can take a reference
- * and the object itself is guaranteed to survive until the reference is dropped.
+ * The group->recnt and mark->refcnt tell how many "things" in the kernel
+ * currently are referencing the objects. Both kind of objects typically will
+ * live inside the kernel with a refcnt of 2, one for its creation and one for
+ * the reference a group and a mark hold to each other.
+ * If you are holding the appropriate locks, you can take a reference and the
+ * object itself is guaranteed to survive until the reference is dropped.
  *
  * LOCKING:
- * There are 3 spinlocks involved with fsnotify inode marks and they MUST
- * be taken in order as follows:
+ * There are 3 locks involved with fsnotify inode marks and they MUST be taken
+ * in order as follows:
  *
+ * group->mark_mutex
  * mark->lock
- * group->mark_lock
  * inode->i_lock
  *
- * mark->lock protects 2 things, mark->group and mark->inode.  You must hold
- * that lock to dereference either of these things (they could be NULL even with
- * the lock)
- *
- * group->mark_lock protects the marks_list anchored inside a given group
- * and each mark is hooked via the g_list.  It also sorta protects the
- * free_g_list, which when used is anchored by a private list on the stack of the
- * task which held the group->mark_lock.
+ * group->mark_mutex protects the marks_list anchored inside a given group and
+ * each mark is hooked via the g_list.  It also protects the groups private
+ * data (i.e group limits).
+
+ * mark->lock protects the marks attributes like its masks and flags.
+ * Furthermore it protects the access to a reference of the group that the mark
+ * is assigned to as well as the access to a reference of the inode/vfsmount
+ * that is being watched by the mark.
  *
  * inode->i_lock protects the i_fsnotify_marks list anchored inside a
  * given inode and each mark is hooked via the i_list. (and sorta the
@@ -64,18 +65,11 @@
  * inode.  We take i_lock and walk the i_fsnotify_marks safely.  For each
  * mark on the list we take a reference (so the mark can't disappear under us).
  * We remove that mark form the inode's list of marks and we add this mark to a
- * private list anchored on the stack using i_free_list;  At this point we no
- * longer fear anything finding the mark using the inode's list of marks.
- *
- * We can safely and locklessly run the private list on the stack of everything
- * we just unattached from the original inode.  For each mark on the private list
- * we grab the mark-> and can thus dereference mark->group and mark->inode.  If
- * we see the group and inode are not NULL we take those locks.  Now holding all
- * 3 locks we can completely remove the mark from other tasks finding it in the
- * future.  Remember, 10 things might already be referencing this mark, but they
- * better be holding a ref.  We drop our reference we took before we unhooked it
- * from the inode.  When the ref hits 0 we can free the mark.
- *
+ * private list anchored on the stack using i_free_list; we walk i_free_list
+ * and before we destroy the mark we make sure that we dont race with a
+ * concurrent destroy_group by getting a ref to the marks group and taking the
+ * groups mutex.
+
  * Very similarly for freeing by group, except we use free_g_list.
  *
  * This has the very interesting property of being able to run concurrently with