1 files changed, 42 insertions, 54 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 88534eb0e7c2..51c93929a146 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
-/* -*- mode: c; c-basic-offset: 8; -*-
- * vim: noexpandtab sw=8 ts=8 sts=0:
- *
+/*
  * alloc.c
  *
  * Extent allocs and frees
@@ -1060,7 +1058,6 @@ bail:
 			brelse(bhs[i]);
 			bhs[i] = NULL;
 		}
-		mlog_errno(status);
 	}
 	return status;
 }
@@ -2043,7 +2040,7 @@ static void ocfs2_complete_edge_insert(handle_t *handle,
 	int i, idx;
 	struct ocfs2_extent_list *el, *left_el, *right_el;
 	struct ocfs2_extent_rec *left_rec, *right_rec;
-	struct buffer_head *root_bh = left_path->p_node[subtree_index].bh;
+	struct buffer_head *root_bh;
 
 	/*
 	 * Update the counts and position values within all the
@@ -3942,7 +3939,7 @@ rotate:
 	 * above.
 	 *
 	 * This leaf needs to have space, either by the empty 1st
-	 * extent record, or by virtue of an l_next_rec < l_count.
+	 * extent record, or by virtue of an l_next_free_rec < l_count.
 	 */
 	ocfs2_rotate_leaf(el, insert_rec);
 }
@@ -4708,7 +4705,7 @@ int ocfs2_insert_extent(handle_t *handle,
 			struct ocfs2_alloc_context *meta_ac)
 {
 	int status;
-	int uninitialized_var(free_records);
+	int free_records;
 	struct buffer_head *last_eb_bh = NULL;
 	struct ocfs2_insert_type insert = {0, };
 	struct ocfs2_extent_rec rec;
@@ -5943,6 +5940,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 		status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
 						 OCFS2_JOURNAL_ACCESS_WRITE);
 		if (status < 0) {
+			ocfs2_commit_trans(osb, handle);
 			mlog_errno(status);
 			goto bail;
 		}
@@ -5967,6 +5965,7 @@ static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
 						     data_alloc_bh, start_blk,
 						     num_clusters);
 			if (status < 0) {
+				ocfs2_commit_trans(osb, handle);
 				mlog_errno(status);
 				goto bail;
 			}
@@ -5982,7 +5981,7 @@ bail:
 	return status;
 }
 
-/* Expects you to already be holding tl_inode->i_mutex */
+/* Expects you to already be holding tl_inode->i_rwsem */
 int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 {
 	int status;
@@ -6014,14 +6013,14 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb)
 		goto out;
 	}
 
-	/* Appending truncate log(TA) and and flushing truncate log(TF) are
+	/* Appending truncate log(TA) and flushing truncate log(TF) are
 	 * two separated transactions. They can be both committed but not
 	 * checkpointed. If crash occurs then, both two transaction will be
 	 * replayed with several already released to global bitmap clusters.
 	 * Then truncate log will be replayed resulting in cluster double free.
 	 */
 	jbd2_journal_lock_updates(journal->j_journal);
-	status = jbd2_journal_flush(journal->j_journal);
+	status = jbd2_journal_flush(journal->j_journal, 0);
 	jbd2_journal_unlock_updates(journal->j_journal);
 	if (status < 0) {
 		mlog_errno(status);
@@ -6924,13 +6923,12 @@ static int ocfs2_grab_eof_pages(struct inode *inode, loff_t start, loff_t end,
 }
 
 /*
- * Zero the area past i_size but still within an allocated
- * cluster. This avoids exposing nonzero data on subsequent file
- * extends.
+ * Zero partial cluster for a hole punch or truncate. This avoids exposing
+ * nonzero data on subsequent file extends.
  *
  * We need to call this before i_size is updated on the inode because
  * otherwise block_write_full_page() will skip writeout of pages past
- * i_size. The new_i_size parameter is passed for this reason.
+ * i_size.
  */
 int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 				  u64 range_start, u64 range_end)
@@ -6948,6 +6946,15 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 	if (!ocfs2_sparse_alloc(OCFS2_SB(sb)))
 		return 0;
 
+	/*
+	 * Avoid zeroing pages fully beyond current i_size. It is pointless as
+	 * underlying blocks of those pages should be already zeroed out and
+	 * page writeback will skip them anyway.
+	 */
+	range_end = min_t(u64, range_end, i_size_read(inode));
+	if (range_start >= range_end)
+		return 0;
+
 	pages = kcalloc(ocfs2_pages_per_cluster(sb),
 			sizeof(struct page *), GFP_NOFS);
 	if (pages == NULL) {
@@ -6956,9 +6963,6 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
 		goto out;
 	}
 
-	if (range_start == range_end)
-		goto out;
-
 	ret = ocfs2_extent_map_get_blocks(inode,
 					  range_start >> sb->s_blocksize_bits,
 					  &phys, NULL, &ext_flags);
@@ -7048,35 +7052,26 @@ void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di)
 int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 					 struct buffer_head *di_bh)
 {
-	int ret, i, has_data, num_pages = 0;
+	int ret, has_data, num_pages = 0;
 	int need_free = 0;
 	u32 bit_off, num;
 	handle_t *handle;
-	u64 uninitialized_var(block);
+	u64 block;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	struct ocfs2_alloc_context *data_ac = NULL;
-	struct page **pages = NULL;
-	loff_t end = osb->s_clustersize;
+	struct page *page = NULL;
 	struct ocfs2_extent_tree et;
 	int did_quota = 0;
 
 	has_data = i_size_read(inode) ? 1 : 0;
 
 	if (has_data) {
-		pages = kcalloc(ocfs2_pages_per_cluster(osb->sb),
-				sizeof(struct page *), GFP_NOFS);
-		if (pages == NULL) {
-			ret = -ENOMEM;
-			mlog_errno(ret);
-			return ret;
-		}
-
 		ret = ocfs2_reserve_clusters(osb, 1, &data_ac);
 		if (ret) {
 			mlog_errno(ret);
-			goto free_pages;
+			goto out;
 		}
 	}
 
@@ -7096,7 +7091,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 	}
 
 	if (has_data) {
-		unsigned int page_end;
+		unsigned int page_end = min_t(unsigned, PAGE_SIZE,
+							osb->s_clustersize);
 		u64 phys;
 
 		ret = dquot_alloc_space_nodirty(inode,
@@ -7120,15 +7116,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		 */
 		block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);
 
-		/*
-		 * Non sparse file systems zero on extend, so no need
-		 * to do that now.
-		 */
-		if (!ocfs2_sparse_alloc(osb) &&
-		    PAGE_SIZE < osb->s_clustersize)
-			end = PAGE_SIZE;
-
-		ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
+		ret = ocfs2_grab_eof_pages(inode, 0, page_end, &page,
+					   &num_pages);
 		if (ret) {
 			mlog_errno(ret);
 			need_free = 1;
@@ -7139,20 +7128,15 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 		 * This should populate the 1st page for us and mark
 		 * it up to date.
 		 */
-		ret = ocfs2_read_inline_data(inode, pages[0], di_bh);
+		ret = ocfs2_read_inline_data(inode, page, di_bh);
 		if (ret) {
 			mlog_errno(ret);
 			need_free = 1;
 			goto out_unlock;
 		}
 
-		page_end = PAGE_SIZE;
-		if (PAGE_SIZE > osb->s_clustersize)
-			page_end = osb->s_clustersize;
-
-		for (i = 0; i < num_pages; i++)
-			ocfs2_map_and_dirty_page(inode, handle, 0, page_end,
-						 pages[i], i > 0, &phys);
+		ocfs2_map_and_dirty_page(inode, handle, 0, page_end, page, 0,
+					 &phys);
 	}
 
 	spin_lock(&oi->ip_lock);
@@ -7183,8 +7167,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 	}
 
 out_unlock:
-	if (pages)
-		ocfs2_unlock_and_free_pages(pages, num_pages);
+	if (page)
+		ocfs2_unlock_and_free_pages(&page, num_pages);
 
 out_commit:
 	if (ret < 0 && did_quota)
@@ -7208,8 +7192,6 @@ out_commit:
 out:
 	if (data_ac)
 		ocfs2_free_alloc_context(data_ac);
-free_pages:
-	kfree(pages);
 	return ret;
 }
 
@@ -7403,6 +7385,10 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	struct ocfs2_inline_data *idata = &di->id2.i_data;
 
+	/* No need to punch hole beyond i_size. */
+	if (start >= i_size_read(inode))
+		return 0;
+
 	if (end > i_size_read(inode))
 		end = i_size_read(inode);
 
@@ -7441,7 +7427,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
 	/*
 	 * No need to worry about the data page here - it's been
 	 * truncated already and inline data doesn't need it for
-	 * pushing zero's to disk, so we'll let readpage pick it up
+	 * pushing zero's to disk, so we'll let read_folio pick it up
 	 * later.
 	 */
 	if (trunc) {
@@ -7651,8 +7637,10 @@ out_mutex:
 	 * main_bm related locks for avoiding the current IO starve, then go to
 	 * trim the next group
 	 */
-	if (ret >= 0 && group <= last_group)
+	if (ret >= 0 && group <= last_group) {
+		cond_resched();
 		goto next_group;
+	}
 out:
 	range->len = trimmed * sb->s_blocksize;
 	return ret;