Merge branch 'akpm' (patches from Andrew)

Merge patch-bomb from Andrew Morton:

 - inotify tweaks

 - some ocfs2 updates (many more are awaiting review)

 - various misc bits

 - kernel/watchdog.c updates

 - Some of mm.  I have a huge number of MM patches this time and quite a
   lot of it is quite difficult and much will be held over to next time.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (162 commits)
  selftests: vm: add tests for lock on fault
  mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage
  mm: introduce VM_LOCKONFAULT
  mm: mlock: add new mlock system call
  mm: mlock: refactor mlock, munlock, and munlockall code
  kasan: always taint kernel on report
  mm, slub, kasan: enable user tracking by default with KASAN=y
  kasan: use IS_ALIGNED in memory_is_poisoned_8()
  kasan: Fix a type conversion error
  lib: test_kasan: add some testcases
  kasan: update reference to kasan prototype repo
  kasan: move KASAN_SANITIZE in arch/x86/boot/Makefile
  kasan: various fixes in documentation
  kasan: update log messages
  kasan: accurately determine the type of the bad access
  kasan: update reported bug types for kernel memory accesses
  kasan: update reported bug types for not user nor kernel memory accesses
  mm/kasan: prevent deadlock in kasan reporting
  mm/kasan: don't use kasan shadow pointer in generic functions
  mm/kasan: MODULE_VADDR is not available on all archs
  ...

20 files changed, 204 insertions, 76 deletions

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index f23fd86697ea..7bf835f85bc8 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -231,7 +231,8 @@ out_unlock:
 	if (res < 0 && fl->fl_type != F_UNLCK) {
 		fl_type = fl->fl_type;
 		fl->fl_type = F_UNLCK;
-		res = locks_lock_file_wait(filp, fl);
+		/* Even if this fails we want to return the remote error */
+		locks_lock_file_wait(filp, fl);
 		fl->fl_type = fl_type;
 	}
 out:
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 7378169e90be..206a68b1db1a 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2149,7 +2149,12 @@ static void wait_sb_inodes(struct super_block *sb)
 		iput(old_inode);
 		old_inode = inode;
 
-		filemap_fdatawait(mapping);
+		/*
+		 * We keep the error status of individual mapping so that
+		 * applications can catch the writeback error using fsync(2).
+		 * See filemap_fdatawait_keep_errors() for details.
+		 */
+		filemap_fdatawait_keep_errors(mapping);
 
 		cond_resched();
 
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index a7fdbd868474..a709d80c8ebc 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -81,7 +81,7 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
 	unsigned int max_pages;
 	int i;
 
-	max_pages = min(nr_pages, BIO_MAX_PAGES);
+	max_pages = min_t(size_t, nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOFS, max_pages);
 	BUG_ON(!bio);
@@ -171,7 +171,7 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
 	unsigned int max_pages;
 	int i;
 
-	max_pages = min(nr_pages, BIO_MAX_PAGES);
+	max_pages = min_t(size_t, nr_pages, BIO_MAX_PAGES);
 
 	bio = bio_alloc(GFP_NOFS, max_pages);
 	BUG_ON(!bio);
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 6b6f0d472ae8..fd98e5100cab 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -83,9 +83,16 @@ static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 	inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
 	inode = igrab(mark->inode);
 	if (inode) {
+		/*
+		 * IN_ALL_EVENTS represents all of the mask bits
+		 * that we expose to userspace.  There is at
+		 * least one bit (FS_EVENT_ON_CHILD) which is
+		 * used only internally to the kernel.
+		 */
+		u32 mask = mark->mask & IN_ALL_EVENTS;
 		seq_printf(m, "inotify wd:%x ino:%lx sdev:%x mask:%x ignored_mask:%x ",
 			   inode_mark->wd, inode->i_ino, inode->i_sb->s_dev,
-			   mark->mask, mark->ignored_mask);
+			   mask, mark->ignored_mask);
 		show_mark_fhandle(m, inode);
 		seq_putc(m, '\n');
 		iput(inode);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 5b1e2a497e51..b8d08d0d0a4d 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -706,7 +706,19 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 	int ret;
 	unsigned flags = 0;
 
-	/* don't allow invalid bits: we don't want flags set */
+	/*
+	 * We share a lot of code with fs/dnotify.  We also share
+	 * the bit layout between inotify's IN_* and the fsnotify
+	 * FS_*.  This check ensures that only the inotify IN_*
+	 * bits get passed in and set in watches/events.
+	 */
+	if (unlikely(mask & ~ALL_INOTIFY_BITS))
+		return -EINVAL;
+	/*
+	 * Require at least one valid bit set in the mask.
+	 * Without _something_ set, we would have no events to
+	 * watch for.
+	 */
 	if (unlikely(!(mask & ALL_INOTIFY_BITS)))
 		return -EINVAL;
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 64b11d90eca6..7f604727f487 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -589,6 +589,7 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 			ret = -EIO;
 			goto bail;
 		}
+		set_buffer_new(bh_result);
 		up_write(&OCFS2_I(inode)->ip_alloc_sem);
 	}
 
@@ -864,6 +865,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
 		if (is_overwrite < 0) {
 			mlog_errno(is_overwrite);
+			ret = is_overwrite;
 			ocfs2_inode_unlock(inode, 1);
 			goto clean_orphan;
 		}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index fa15debcc02b..ddddef0021a0 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -219,7 +219,8 @@ struct o2hb_region {
 	unsigned		hr_unclean_stop:1,
 				hr_aborted_start:1,
 				hr_item_pinned:1,
-				hr_item_dropped:1;
+				hr_item_dropped:1,
+				hr_node_deleted:1;
 
 	/* protected by the hr_callback_sem */
 	struct task_struct 	*hr_task;
@@ -1078,7 +1079,13 @@ static int o2hb_thread(void *data)
 	set_user_nice(current, MIN_NICE);
 
 	/* Pin node */
-	o2nm_depend_this_node();
+	ret = o2nm_depend_this_node();
+	if (ret) {
+		mlog(ML_ERROR, "Node has been deleted, ret = %d\n", ret);
+		reg->hr_node_deleted = 1;
+		wake_up(&o2hb_steady_queue);
+		return 0;
+	}
 
 	while (!kthread_should_stop() &&
 	       !reg->hr_unclean_stop && !reg->hr_aborted_start) {
@@ -1787,7 +1794,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	spin_unlock(&o2hb_live_lock);
 
 	ret = wait_event_interruptible(o2hb_steady_queue,
-				atomic_read(&reg->hr_steady_iterations) == 0);
+				atomic_read(&reg->hr_steady_iterations) == 0 ||
+				reg->hr_node_deleted);
 	if (ret) {
 		atomic_set(&reg->hr_steady_iterations, 0);
 		reg->hr_aborted_start = 1;
@@ -1798,6 +1806,11 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		goto out3;
 	}
 
+	if (reg->hr_node_deleted) {
+		ret = -EINVAL;
+		goto out3;
+	}
+
 	/* Ok, we were woken.  Make sure it wasn't by drop_item() */
 	spin_lock(&o2hb_live_lock);
 	hb_task = reg->hr_task;
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6918f30d02cd..2ee7fe747cea 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1866,6 +1866,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 	int status;
 	unsigned int backoff;
 	unsigned int total_backoff = 0;
+	char wq_name[O2NM_MAX_NAME_LEN];
 
 	BUG_ON(!dlm);
 
@@ -1895,7 +1896,8 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
-	dlm->dlm_worker = create_singlethread_workqueue("dlm_wq");
+	snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name);
+	dlm->dlm_worker = create_singlethread_workqueue(wq_name);
 	if (!dlm->dlm_worker) {
 		status = -ENOMEM;
 		mlog_errno(status);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 58eaa5c0d387..9e4f862d20fe 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -205,7 +205,7 @@ int dlm_launch_recovery_thread(struct dlm_ctxt *dlm)
 	mlog(0, "starting dlm recovery thread...\n");
 
 	dlm->dlm_reco_thread_task = kthread_run(dlm_recovery_thread, dlm,
-						"dlm_reco_thread");
+			"dlm_reco-%s", dlm->name);
 	if (IS_ERR(dlm->dlm_reco_thread_task)) {
 		mlog_errno(PTR_ERR(dlm->dlm_reco_thread_task));
 		dlm->dlm_reco_thread_task = NULL;
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 2e5e6d5fffe8..c5f6c241ecd7 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -493,7 +493,8 @@ int dlm_launch_thread(struct dlm_ctxt *dlm)
 {
 	mlog(0, "Starting dlm_thread...\n");
 
-	dlm->dlm_thread_task = kthread_run(dlm_thread, dlm, "dlm_thread");
+	dlm->dlm_thread_task = kthread_run(dlm_thread, dlm, "dlm-%s",
+			dlm->name);
 	if (IS_ERR(dlm->dlm_thread_task)) {
 		mlog_errno(PTR_ERR(dlm->dlm_thread_task));
 		dlm->dlm_thread_task = NULL;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 1c91103c1333..20276e340339 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2998,7 +2998,8 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
 	}
 
 	/* launch downconvert thread */
-	osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc");
+	osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s",
+			osb->uuid_str);
 	if (IS_ERR(osb->dc_task)) {
 		status = PTR_ERR(osb->dc_task);
 		osb->dc_task = NULL;
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ca3431ee7f24..aac8b86f312e 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -112,6 +112,8 @@ struct ocfs2_inode_info
 #define OCFS2_INODE_OPEN_DIRECT		0x00000020
 /* Tell the inode wipe code it's not in orphan dir */
 #define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000040
+/* Entry in orphan dir with 'dio-' prefix */
+#define OCFS2_INODE_DIO_ORPHAN_ENTRY	0x00000080
 
 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
 {
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index ff82b28462a6..13534f4fe5b5 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1090,7 +1090,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
 	/* Launch the commit thread */
 	if (!local) {
 		osb->commit_task = kthread_run(ocfs2_commit_thread, osb,
-					       "ocfs2cmt");
+				"ocfs2cmt-%s", osb->uuid_str);
 		if (IS_ERR(osb->commit_task)) {
 			status = PTR_ERR(osb->commit_task);
 			osb->commit_task = NULL;
@@ -1507,7 +1507,7 @@ void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num)
 		goto out;
 
 	osb->recovery_thread_task =  kthread_run(__ocfs2_recovery_thread, osb,
-						 "ocfs2rec");
+			"ocfs2rec-%s", osb->uuid_str);
 	if (IS_ERR(osb->recovery_thread_task)) {
 		mlog_errno((int)PTR_ERR(osb->recovery_thread_task));
 		osb->recovery_thread_task = NULL;
@@ -2021,6 +2021,7 @@ struct ocfs2_orphan_filldir_priv {
 	struct dir_context	ctx;
 	struct inode		*head;
 	struct ocfs2_super	*osb;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 };
 
 static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
@@ -2036,12 +2037,22 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 	if (name_len == 2 && !strncmp("..", name, 2))
 		return 0;
 
+	/* do not include dio entry in case of orphan scan */
+	if ((p->orphan_reco_type == ORPHAN_NO_NEED_TRUNCATE) &&
+			(!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX,
+			OCFS2_DIO_ORPHAN_PREFIX_LEN)))
+		return 0;
+
 	/* Skip bad inodes so that recovery can continue */
 	iter = ocfs2_iget(p->osb, ino,
 			  OCFS2_FI_FLAG_ORPHAN_RECOVERY, 0);
 	if (IS_ERR(iter))
 		return 0;
 
+	if (!strncmp(name, OCFS2_DIO_ORPHAN_PREFIX,
+			OCFS2_DIO_ORPHAN_PREFIX_LEN))
+		OCFS2_I(iter)->ip_flags |= OCFS2_INODE_DIO_ORPHAN_ENTRY;
+
 	/* Skip inodes which are already added to recover list, since dio may
 	 * happen concurrently with unlink/rename */
 	if (OCFS2_I(iter)->ip_next_orphan) {
@@ -2060,14 +2071,16 @@ static int ocfs2_orphan_filldir(struct dir_context *ctx, const char *name,
 
 static int ocfs2_queue_orphans(struct ocfs2_super *osb,
 			       int slot,
-			       struct inode **head)
+			       struct inode **head,
+			       enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int status;
 	struct inode *orphan_dir_inode = NULL;
 	struct ocfs2_orphan_filldir_priv priv = {
 		.ctx.actor = ocfs2_orphan_filldir,
 		.osb = osb,
-		.head = *head
+		.head = *head,
+		.orphan_reco_type = orphan_reco_type
 	};
 
 	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
@@ -2170,7 +2183,7 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 	trace_ocfs2_recover_orphans(slot);
 
 	ocfs2_mark_recovering_orphan_dir(osb, slot);
-	ret = ocfs2_queue_orphans(osb, slot, &inode);
+	ret = ocfs2_queue_orphans(osb, slot, &inode, orphan_reco_type);
 	ocfs2_clear_recovering_orphan_dir(osb, slot);
 
 	/* Error here should be noted, but we want to continue with as
@@ -2186,25 +2199,51 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 		iter = oi->ip_next_orphan;
 		oi->ip_next_orphan = NULL;
 
-		mutex_lock(&inode->i_mutex);
-		ret = ocfs2_rw_lock(inode, 1);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto next;
-		}
-		/*
-		 * We need to take and drop the inode lock to
-		 * force read inode from disk.
-		 */
-		ret = ocfs2_inode_lock(inode, &di_bh, 1);
-		if (ret) {
-			mlog_errno(ret);
-			goto unlock_rw;
-		}
+		if (oi->ip_flags & OCFS2_INODE_DIO_ORPHAN_ENTRY) {
+			mutex_lock(&inode->i_mutex);
+			ret = ocfs2_rw_lock(inode, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto unlock_mutex;
+			}
+			/*
+			 * We need to take and drop the inode lock to
+			 * force read inode from disk.
+			 */
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret) {
+				mlog_errno(ret);
+				goto unlock_rw;
+			}
 
-		di = (struct ocfs2_dinode *)di_bh->b_data;
+			di = (struct ocfs2_dinode *)di_bh->b_data;
 
-		if (inode->i_nlink == 0) {
+			if (di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size_read(inode));
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+					goto unlock_inode;
+				}
+
+				ret = ocfs2_del_inode_from_orphan(osb, inode,
+						di_bh, 0, 0);
+				if (ret)
+					mlog_errno(ret);
+			}
+unlock_inode:
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			di_bh = NULL;
+unlock_rw:
+			ocfs2_rw_unlock(inode, 1);
+unlock_mutex:
+			mutex_unlock(&inode->i_mutex);
+
+			/* clear dio flag in ocfs2_inode_info */
+			oi->ip_flags &= ~OCFS2_INODE_DIO_ORPHAN_ENTRY;
+		} else {
 			spin_lock(&oi->ip_lock);
 			/* Set the proper information to get us going into
 			 * ocfs2_delete_inode. */
@@ -2212,28 +2251,6 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 			spin_unlock(&oi->ip_lock);
 		}
 
-		if ((orphan_reco_type == ORPHAN_NEED_TRUNCATE) &&
-				(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
-			ret = ocfs2_truncate_file(inode, di_bh,
-					i_size_read(inode));
-			if (ret < 0) {
-				if (ret != -ENOSPC)
-					mlog_errno(ret);
-				goto unlock_inode;
-			}
-
-			ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
-			if (ret)
-				mlog_errno(ret);
-		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
-unlock_inode:
-		ocfs2_inode_unlock(inode, 1);
-		brelse(di_bh);
-		di_bh = NULL;
-unlock_rw:
-		ocfs2_rw_unlock(inode, 1);
-next:
-		mutex_unlock(&inode->i_mutex);
 		iput(inode);
 		inode = iter;
 	}
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b7dfac226b1e..3b48ac25d8a7 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -106,8 +106,6 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 static void ocfs2_double_unlock(struct inode *inode1, struct inode *inode2);
 /* An orphan dir name is an 8 byte value, printed as a hex string */
 #define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
-#define OCFS2_DIO_ORPHAN_PREFIX "dio-"
-#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4
 
 static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
 				   unsigned int flags)
@@ -657,9 +655,18 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 		return status;
 	}
 
-	return __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
+	status = __ocfs2_mknod_locked(dir, inode, dev, new_fe_bh,
 				    parent_fe_bh, handle, inode_ac,
 				    fe_blkno, suballoc_loc, suballoc_bit);
+	if (status < 0) {
+		u64 bg_blkno = ocfs2_which_suballoc_group(fe_blkno, suballoc_bit);
+		int tmp = ocfs2_free_suballoc_bits(handle, inode_ac->ac_inode,
+				inode_ac->ac_bh, suballoc_bit, bg_blkno, 1);
+		if (tmp)
+			mlog_errno(tmp);
+	}
+
+	return status;
 }
 
 static int ocfs2_mkdir(struct inode *dir,
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e173329eb830..1155918d6784 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -26,6 +26,9 @@
 #ifndef OCFS2_NAMEI_H
 #define OCFS2_NAMEI_H
 
+#define OCFS2_DIO_ORPHAN_PREFIX "dio-"
+#define OCFS2_DIO_ORPHAN_PREFIX_LEN 4
+
 extern const struct inode_operations ocfs2_dir_iops;
 
 struct dentry *ocfs2_get_parent(struct dentry *child);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index e5d57cd32505..252119860e6c 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2920,16 +2920,13 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 	u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
 	struct page *page;
 	pgoff_t page_index;
-	unsigned int from, to, readahead_pages;
+	unsigned int from, to;
 	loff_t offset, end, map_end;
 	struct address_space *mapping = inode->i_mapping;
 
 	trace_ocfs2_duplicate_clusters_by_page(cpos, old_cluster,
 					       new_cluster, new_len);
 
-	readahead_pages =
-		(ocfs2_cow_contig_clusters(sb) <<
-		 OCFS2_SB(sb)->s_clustersize_bits) >> PAGE_CACHE_SHIFT;
 	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
 	end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits);
 	/*
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index d83d2602cf2b..fc6d25f6d444 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1920,7 +1920,10 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
 	status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits,
 				    res, &bits_left);
 	if (!status) {
-		hint = ocfs2_group_from_res(res);
+		if (ocfs2_is_cluster_bitmap(ac->ac_inode))
+			hint = res->sr_bg_blkno;
+		else
+			hint = ocfs2_group_from_res(res);
 		goto set_hint;
 	}
 	if (status < 0 && status != -ENOSPC) {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 29595af32866..bd3e9e68125b 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1032,6 +1032,16 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
 	return simple_read_from_buffer(buf, count, ppos, buffer, len);
 }
 
+/*
+ * /proc/pid/oom_adj exists solely for backwards compatibility with previous
+ * kernels.  The effective policy is defined by oom_score_adj, which has a
+ * different scale: oom_adj grew exponentially and oom_score_adj grows linearly.
+ * Values written to oom_adj are simply mapped linearly to oom_score_adj.
+ * Processes that become oom disabled via oom_adj will still be oom disabled
+ * with this implementation.
+ *
+ * oom_adj cannot be removed since existing userspace binaries use it.
+ */
 static ssize_t oom_adj_write(struct file *file, const char __user *buf,
 			     size_t count, loff_t *ppos)
 {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index b029d426c558..187b3b5f242e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -70,6 +70,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 		ptes >> 10,
 		pmds >> 10,
 		swap << (PAGE_SHIFT-10));
+	hugetlb_report_usage(m, mm);
 }
 
 unsigned long task_vsize(struct mm_struct *mm)
@@ -446,6 +447,8 @@ struct mem_size_stats {
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
 	unsigned long swap;
+	unsigned long shared_hugetlb;
+	unsigned long private_hugetlb;
 	u64 pss;
 	u64 swap_pss;
 };
@@ -625,12 +628,44 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 	seq_putc(m, '\n');
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
+				 unsigned long addr, unsigned long end,
+				 struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = walk->vma;
+	struct page *page = NULL;
+
+	if (pte_present(*pte)) {
+		page = vm_normal_page(vma, addr, *pte);
+	} else if (is_swap_pte(*pte)) {
+		swp_entry_t swpent = pte_to_swp_entry(*pte);
+
+		if (is_migration_entry(swpent))
+			page = migration_entry_to_page(swpent);
+	}
+	if (page) {
+		int mapcount = page_mapcount(page);
+
+		if (mapcount >= 2)
+			mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
+		else
+			mss->private_hugetlb += huge_page_size(hstate_vma(vma));
+	}
+	return 0;
+}
+#endif /* HUGETLB_PAGE */
+
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
 	struct mm_walk smaps_walk = {
 		.pmd_entry = smaps_pte_range,
+#ifdef CONFIG_HUGETLB_PAGE
+		.hugetlb_entry = smaps_hugetlb_range,
+#endif
 		.mm = vma->vm_mm,
 		.private = &mss,
 	};
@@ -652,6 +687,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
+		   "Shared_Hugetlb: %8lu kB\n"
+		   "Private_Hugetlb: %7lu kB\n"
 		   "Swap:           %8lu kB\n"
 		   "SwapPss:        %8lu kB\n"
 		   "KernelPageSize: %8lu kB\n"
@@ -667,6 +704,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
+		   mss.shared_hugetlb >> 10,
+		   mss.private_hugetlb >> 10,
 		   mss.swap >> 10,
 		   (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
 		   vma_kernel_pagesize(vma) >> 10,
@@ -753,19 +792,27 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 	pte_t ptent = *pte;
 
 	if (pte_present(ptent)) {
+		ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte);
 		ptent = pte_wrprotect(ptent);
 		ptent = pte_clear_soft_dirty(ptent);
+		ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent);
 	} else if (is_swap_pte(ptent)) {
 		ptent = pte_swp_clear_soft_dirty(ptent);
+		set_pte_at(vma->vm_mm, addr, pte, ptent);
 	}
-
-	set_pte_at(vma->vm_mm, addr, pte, ptent);
 }
+#else
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+}
+#endif
 
+#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
-	pmd_t pmd = *pmdp;
+	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
 
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
@@ -775,14 +822,7 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 
 	set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
 }
-
 #else
-
-static inline void clear_soft_dirty(struct vm_area_struct *vma,
-		unsigned long addr, pte_t *pte)
-{
-}
-
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
diff --git a/fs/sync.c b/fs/sync.c
index fbc98ee62044..4ec430ae2b0d 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -86,7 +86,12 @@ static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
 
 static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
 {
-	filemap_fdatawait(bdev->bd_inode->i_mapping);
+	/*
+	 * We keep the error status of individual mapping so that
+	 * applications can catch the writeback error using fsync(2).
+	 * See filemap_fdatawait_keep_errors() for details.
+	 */
+	filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping);
 }
 
 /*