Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - more ocfs2 work

 - various leftovers

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  memory_hotplug: cond_resched in __remove_pages
  bfs: add sanity check at bfs_fill_super()
  kernel/sysctl.c: remove duplicated include
  kernel/kexec_file.c: remove some duplicated includes
  mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask
  ocfs2: fix clusters leak in ocfs2_defrag_extent()
  ocfs2: dlmglue: clean up timestamp handling
  ocfs2: don't put and assigning null to bh allocated outside
  ocfs2: fix a misuse a of brelse after failing ocfs2_check_dir_entry
  ocfs2: don't use iocb when EIOCBQUEUED returns
  ocfs2: without quota support, avoid calling quota recovery
  ocfs2: remove ocfs2_is_o2cb_active()
  mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings
  include/linux/notifier.h: SRCU: fix ctags
  mm: handle no memcg case in memcg_kmem_charge() properly

fs/bfs/inode.c

@@ -350,7 +350,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 
 	s->s_magic = BFS_MAGIC;
 
-	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end)) {
+	if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) ||
+	    le32_to_cpu(bfs_sb->s_start) < BFS_BSIZE) {
 		printf("Superblock is corrupted\n");
 		goto out1;
 	}
@@ -359,9 +360,11 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 					sizeof(struct bfs_inode)
 					+ BFS_ROOT_INO - 1;
 	imap_len = (info->si_lasti / 8) + 1;
-	info->si_imap = kzalloc(imap_len, GFP_KERNEL);
-	if (!info->si_imap)
+	info->si_imap = kzalloc(imap_len, GFP_KERNEL | __GFP_NOWARN);
+	if (!info->si_imap) {
+		printf("Cannot allocate %u bytes\n", imap_len);
 		goto out1;
+	}
 	for (i = 0; i < BFS_ROOT_INO; i++)
 		set_bit(i, info->si_imap);
 

fs/ocfs2/buffer_head_io.c

@@ -99,25 +99,34 @@ int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 	return ret;
 }
 
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
 int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			   unsigned int nr, struct buffer_head *bhs[])
 {
 	int status = 0;
 	unsigned int i;
 	struct buffer_head *bh;
+	int new_bh = 0;
 
 	trace_ocfs2_read_blocks_sync((unsigned long long)block, nr);
 
 	if (!nr)
 		goto bail;
 
+	/* Don't put buffer head and re-assign it to NULL if it is allocated
+	 * outside since the caller can't be aware of this alternation!
+	 */
+	new_bh = (bhs[0] == NULL);
+
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(osb->sb, block++);
 			if (bhs[i] == NULL) {
 				status = -ENOMEM;
 				mlog_errno(status);
-				goto bail;
+				break;
 			}
 		}
 		bh = bhs[i];
@@ -158,9 +167,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 		submit_bh(REQ_OP_READ, 0, bh);
 	}
 
+read_failure:
 	for (i = nr; i > 0; i--) {
 		bh = bhs[i - 1];
 
+		if (unlikely(status)) {
+			if (new_bh && bh) {
+				/* If middle bh fails, let previous bh
+				 * finish its read and then put it to
+				 * aovoid bh leak
+				 */
+				if (!buffer_jbd(bh))
+					wait_on_buffer(bh);
+				put_bh(bh);
+				bhs[i - 1] = NULL;
+			} else if (bh && buffer_uptodate(bh)) {
+				clear_buffer_uptodate(bh);
+			}
+			continue;
+		}
+
 		/* No need to wait on the buffer if it's managed by JBD. */
 		if (!buffer_jbd(bh))
 			wait_on_buffer(bh);
@@ -170,15 +196,17 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			 * so we can safely record this and loop back
 			 * to cleanup the other buffers. */
 			status = -EIO;
-			put_bh(bh);
-			bhs[i - 1] = NULL;
+			goto read_failure;
 		}
 	}
 
 bail:
 	return status;
 }
 
+/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it
+ * will be easier to handle read failure.
+ */
 int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		      struct buffer_head *bhs[], int flags,
 		      int (*validate)(struct super_block *sb,
@@ -188,6 +216,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 	int i, ignore_cache = 0;
 	struct buffer_head *bh;
 	struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+	int new_bh = 0;
 
 	trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags);
 
@@ -213,6 +242,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		goto bail;
 	}
 
+	/* Don't put buffer head and re-assign it to NULL if it is allocated
+	 * outside since the caller can't be aware of this alternation!
+	 */
+	new_bh = (bhs[0] == NULL);
+
 	ocfs2_metadata_cache_io_lock(ci);
 	for (i = 0 ; i < nr ; i++) {
 		if (bhs[i] == NULL) {
@@ -221,7 +255,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				ocfs2_metadata_cache_io_unlock(ci);
 				status = -ENOMEM;
 				mlog_errno(status);
-				goto bail;
+				/* Don't forget to put previous bh! */
+				break;
 			}
 		}
 		bh = bhs[i];
@@ -316,16 +351,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		}
 	}
 
-	status = 0;
-
+read_failure:
 	for (i = (nr - 1); i >= 0; i--) {
 		bh = bhs[i];
 
 		if (!(flags & OCFS2_BH_READAHEAD)) {
-			if (status) {
-				/* Clear the rest of the buffers on error */
-				put_bh(bh);
-				bhs[i] = NULL;
+			if (unlikely(status)) {
+				/* Clear the buffers on error including those
+				 * ever succeeded in reading
+				 */
+				if (new_bh && bh) {
+					/* If middle bh fails, let previous bh
+					 * finish its read and then put it to
+					 * aovoid bh leak
+					 */
+					if (!buffer_jbd(bh))
+						wait_on_buffer(bh);
+					put_bh(bh);
+					bhs[i] = NULL;
+				} else if (bh && buffer_uptodate(bh)) {
+					clear_buffer_uptodate(bh);
+				}
 				continue;
 			}
 			/* We know this can't have changed as we hold the
@@ -343,9 +389,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				 * uptodate. */
 				status = -EIO;
 				clear_buffer_needs_validate(bh);
-				put_bh(bh);
-				bhs[i] = NULL;
-				continue;
+				goto read_failure;
 			}
 
 			if (buffer_needs_validate(bh)) {
@@ -355,11 +399,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 				BUG_ON(buffer_jbd(bh));
 				clear_buffer_needs_validate(bh);
 				status = validate(sb, bh);
-				if (status) {
-					put_bh(bh);
-					bhs[i] = NULL;
-					continue;
-				}
+				if (status)
+					goto read_failure;
 			}
 		}
 

fs/ocfs2/dir.c

@@ -1897,8 +1897,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
-				brelse(bh);
-				continue;
+				break;
 			}
 			if (le64_to_cpu(de->inode)) {
 				unsigned char d_type = DT_UNKNOWN;

fs/ocfs2/dlmglue.c

@@ -2123,10 +2123,10 @@ static void ocfs2_downconvert_on_unlock(struct ocfs2_super *osb,
 
 /* LVB only has room for 64 bits of time here so we pack it for
  * now. */
-static u64 ocfs2_pack_timespec(struct timespec *spec)
+static u64 ocfs2_pack_timespec(struct timespec64 *spec)
 {
 	u64 res;
-	u64 sec = spec->tv_sec;
+	u64 sec = clamp_t(time64_t, spec->tv_sec, 0, 0x3ffffffffull);
 	u32 nsec = spec->tv_nsec;
 
 	res = (sec << OCFS2_SEC_SHIFT) | (nsec & OCFS2_NSEC_MASK);
@@ -2142,7 +2142,6 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
 	struct ocfs2_meta_lvb *lvb;
-	struct timespec ts;
 
 	lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
 
@@ -2163,15 +2162,12 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	lvb->lvb_igid      = cpu_to_be32(i_gid_read(inode));
 	lvb->lvb_imode     = cpu_to_be16(inode->i_mode);
 	lvb->lvb_inlink    = cpu_to_be16(inode->i_nlink);
-	ts = timespec64_to_timespec(inode->i_atime);
 	lvb->lvb_iatime_packed  =
-		cpu_to_be64(ocfs2_pack_timespec(&ts));
-	ts = timespec64_to_timespec(inode->i_ctime);
+		cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime));
 	lvb->lvb_ictime_packed =
-		cpu_to_be64(ocfs2_pack_timespec(&ts));
-	ts = timespec64_to_timespec(inode->i_mtime);
+		cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime));
 	lvb->lvb_imtime_packed =
-		cpu_to_be64(ocfs2_pack_timespec(&ts));
+		cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime));
 	lvb->lvb_iattr    = cpu_to_be32(oi->ip_attr);
 	lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features);
 	lvb->lvb_igeneration = cpu_to_be32(inode->i_generation);
@@ -2180,7 +2176,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode)
 	mlog_meta_lvb(0, lockres);
 }
 
-static void ocfs2_unpack_timespec(struct timespec *spec,
+static void ocfs2_unpack_timespec(struct timespec64 *spec,
 				  u64 packed_time)
 {
 	spec->tv_sec = packed_time >> OCFS2_SEC_SHIFT;
@@ -2189,7 +2185,6 @@ static void ocfs2_unpack_timespec(struct timespec *spec,
 
 static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 {
-	struct timespec ts;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres;
 	struct ocfs2_meta_lvb *lvb;
@@ -2217,15 +2212,12 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode)
 	i_gid_write(inode, be32_to_cpu(lvb->lvb_igid));
 	inode->i_mode    = be16_to_cpu(lvb->lvb_imode);
 	set_nlink(inode, be16_to_cpu(lvb->lvb_inlink));
-	ocfs2_unpack_timespec(&ts,
+	ocfs2_unpack_timespec(&inode->i_atime,
 			      be64_to_cpu(lvb->lvb_iatime_packed));
-	inode->i_atime = timespec_to_timespec64(ts);
-	ocfs2_unpack_timespec(&ts,
+	ocfs2_unpack_timespec(&inode->i_mtime,
 			      be64_to_cpu(lvb->lvb_imtime_packed));
-	inode->i_mtime = timespec_to_timespec64(ts);
-	ocfs2_unpack_timespec(&ts,
+	ocfs2_unpack_timespec(&inode->i_ctime,
 			      be64_to_cpu(lvb->lvb_ictime_packed));
-	inode->i_ctime = timespec_to_timespec64(ts);
 	spin_unlock(&oi->ip_lock);
 }
 
@@ -3603,7 +3595,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	 * we can recover correctly from node failure. Otherwise, we may get
 	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
 	 */
-	if (!ocfs2_is_o2cb_active() &&
+	if (ocfs2_userspace_stack(osb) &&
 	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
 		lvb = 1;
 

fs/ocfs2/file.c

@@ -2343,7 +2343,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 
 	written = __generic_file_write_iter(iocb, from);
 	/* buffered aio wouldn't have proper lock coverage today */
-	BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
+	BUG_ON(written == -EIOCBQUEUED && !direct_io);
 
 	/*
 	 * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io
@@ -2463,7 +2463,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	trace_generic_file_read_iter_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
-	BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
+	BUG_ON(ret == -EIOCBQUEUED && !direct_io);
 
 	/* see ocfs2_file_write_iter */
 	if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) {

fs/ocfs2/journal.c

@@ -1378,15 +1378,23 @@ static int __ocfs2_recovery_thread(void *arg)
 	int rm_quota_used = 0, i;
 	struct ocfs2_quota_recovery *qrec;
 
+	/* Whether the quota supported. */
+	int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb,
+			OCFS2_FEATURE_RO_COMPAT_USRQUOTA)
+		|| OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb,
+			OCFS2_FEATURE_RO_COMPAT_GRPQUOTA);
+
 	status = ocfs2_wait_on_mount(osb);
 	if (status < 0) {
 		goto bail;
 	}
 
-	rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS);
-	if (!rm_quota) {
-		status = -ENOMEM;
-		goto bail;
+	if (quota_enabled) {
+		rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS);
+		if (!rm_quota) {
+			status = -ENOMEM;
+			goto bail;
+		}
 	}
 restart:
 	status = ocfs2_super_lock(osb, 1);
@@ -1422,9 +1430,14 @@ static int __ocfs2_recovery_thread(void *arg)
 		 * then quota usage would be out of sync until some node takes
 		 * the slot. So we remember which nodes need quota recovery
 		 * and when everything else is done, we recover quotas. */
-		for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++);
-		if (i == rm_quota_used)
-			rm_quota[rm_quota_used++] = slot_num;
+		if (quota_enabled) {
+			for (i = 0; i < rm_quota_used
+					&& rm_quota[i] != slot_num; i++)
+				;
+
+			if (i == rm_quota_used)
+				rm_quota[rm_quota_used++] = slot_num;
+		}
 
 		status = ocfs2_recover_node(osb, node_num, slot_num);
 skip_recovery:
@@ -1452,16 +1465,19 @@ static int __ocfs2_recovery_thread(void *arg)
 	/* Now it is right time to recover quotas... We have to do this under
 	 * superblock lock so that no one can start using the slot (and crash)
 	 * before we recover it */
-	for (i = 0; i < rm_quota_used; i++) {
-		qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
-		if (IS_ERR(qrec)) {
-			status = PTR_ERR(qrec);
-			mlog_errno(status);
-			continue;
+	if (quota_enabled) {
+		for (i = 0; i < rm_quota_used; i++) {
+			qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
+			if (IS_ERR(qrec)) {
+				status = PTR_ERR(qrec);
+				mlog_errno(status);
+				continue;
+			}
+			ocfs2_queue_recovery_completion(osb->journal,
+					rm_quota[i],
+					NULL, NULL, qrec,
+					ORPHAN_NEED_TRUNCATE);
 		}
-		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec,
-						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
@@ -1483,7 +1499,8 @@ static int __ocfs2_recovery_thread(void *arg)
 
 	mutex_unlock(&osb->recovery_lock);
 
-	kfree(rm_quota);
+	if (quota_enabled)
+		kfree(rm_quota);
 
 	/* no one is callint kthread_stop() for us so the kthread() api
 	 * requires that we call do_exit().  And it isn't exported, but