1 files changed, 70 insertions, 23 deletions

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5f527073143e..ed2bca0fce92 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -87,7 +87,7 @@ static bool __is_cp_guaranteed(struct page *page)
 	sbi = F2FS_I_SB(inode);
 
 	if (inode->i_ino == F2FS_META_INO(sbi) ||
-			inode->i_ino ==  F2FS_NODE_INO(sbi) ||
+			inode->i_ino == F2FS_NODE_INO(sbi) ||
 			S_ISDIR(inode->i_mode) ||
 			(S_ISREG(inode->i_mode) &&
 			(f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
@@ -1073,12 +1073,13 @@ static void f2fs_release_read_bio(struct bio *bio)
 
 /* This can handle encryption stuffs */
 static int f2fs_submit_page_read(struct inode *inode, struct page *page,
-						block_t blkaddr, bool for_write)
+				 block_t blkaddr, int op_flags, bool for_write)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct bio *bio;
 
-	bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index, for_write);
+	bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
+					page->index, for_write);
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
@@ -1193,7 +1194,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
 
 int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
 {
-	struct extent_info ei  = {0,0,0};
+	struct extent_info ei = {0, 0, 0};
 	struct inode *inode = dn->inode;
 
 	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
@@ -1265,7 +1266,8 @@ got_it:
 		return page;
 	}
 
-	err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, for_write);
+	err = f2fs_submit_page_read(inode, page, dn.data_blkaddr,
+						op_flags, for_write);
 	if (err)
 		goto put_err;
 	return page;
@@ -1414,7 +1416,7 @@ alloc:
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	old_blkaddr = dn->data_blkaddr;
 	f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
-					&sum, seg_type, NULL, false);
+					&sum, seg_type, NULL);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		invalidate_mapping_pages(META_MAPPING(sbi),
 					old_blkaddr, old_blkaddr);
@@ -1474,7 +1476,7 @@ map_blocks:
 	return err;
 }
 
-void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
 {
 	if (flag == F2FS_GET_BLOCK_PRE_AIO) {
 		if (lock)
@@ -1539,7 +1541,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 
 next_dnode:
 	if (map->m_may_create)
-		__do_map_lock(sbi, flag, true);
+		f2fs_do_map_lock(sbi, flag, true);
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -1688,7 +1690,7 @@ skip:
 	f2fs_put_dnode(&dn);
 
 	if (map->m_may_create) {
-		__do_map_lock(sbi, flag, false);
+		f2fs_do_map_lock(sbi, flag, false);
 		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 	goto next_dnode;
@@ -1714,7 +1716,7 @@ sync_out:
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (map->m_may_create) {
-		__do_map_lock(sbi, flag, false);
+		f2fs_do_map_lock(sbi, flag, false);
 		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 out:
@@ -1861,6 +1863,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
 			flags |= FIEMAP_EXTENT_LAST;
 
 		err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+		trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
 		if (err || err == 1)
 			return err;
 	}
@@ -1884,8 +1887,10 @@ static int f2fs_xattr_fiemap(struct inode *inode,
 		flags = FIEMAP_EXTENT_LAST;
 	}
 
-	if (phys)
+	if (phys) {
 		err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+		trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
+	}
 
 	return (err < 0 ? err : 0);
 }
@@ -1979,6 +1984,7 @@ next:
 
 		ret = fiemap_fill_next_extent(fieinfo, logical,
 				phys, size, flags);
+		trace_f2fs_fiemap(inode, logical, phys, size, flags, ret);
 		if (ret)
 			goto out;
 		size = 0;
@@ -2213,9 +2219,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
 	if (ret)
 		goto out;
 
-	/* cluster was overwritten as normal cluster */
-	if (dn.data_blkaddr != COMPRESS_ADDR)
-		goto out;
+	f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
 
 	for (i = 1; i < cc->cluster_size; i++) {
 		block_t blkaddr;
@@ -2342,6 +2346,7 @@ static int f2fs_mpage_readpages(struct inode *inode,
 	unsigned nr_pages = rac ? readahead_count(rac) : 1;
 	unsigned max_nr_pages = nr_pages;
 	int ret = 0;
+	bool drop_ra = false;
 
 	map.m_pblk = 0;
 	map.m_lblk = 0;
@@ -2352,10 +2357,26 @@ static int f2fs_mpage_readpages(struct inode *inode,
 	map.m_seg_type = NO_CHECK_TYPE;
 	map.m_may_create = false;
 
+	/*
+	 * Two readahead threads for same address range can cause race condition
+	 * which fragments sequential read IOs. So let's avoid each other.
+	 */
+	if (rac && readahead_count(rac)) {
+		if (READ_ONCE(F2FS_I(inode)->ra_offset) == readahead_index(rac))
+			drop_ra = true;
+		else
+			WRITE_ONCE(F2FS_I(inode)->ra_offset,
+						readahead_index(rac));
+	}
+
 	for (; nr_pages; nr_pages--) {
 		if (rac) {
 			page = readahead_page(rac);
 			prefetchw(&page->flags);
+			if (drop_ra) {
+				f2fs_put_page(page, 1);
+				continue;
+			}
 		}
 
 #ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -2418,6 +2439,9 @@ next_page:
 	}
 	if (bio)
 		__submit_bio(F2FS_I_SB(inode), bio, DATA);
+
+	if (rac && readahead_count(rac) && !drop_ra)
+		WRITE_ONCE(F2FS_I(inode)->ra_offset, -1);
 	return ret;
 }
 
@@ -2772,8 +2796,20 @@ write:
 
 	/* Dentry/quota blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) {
+		/*
+		 * We need to wait for node_write to avoid block allocation during
+		 * checkpoint. This can only happen to quota writes which can cause
+		 * the below discard race condition.
+		 */
+		if (IS_NOQUOTA(inode))
+			down_read(&sbi->node_write);
+
 		fio.need_lock = LOCK_DONE;
 		err = f2fs_do_write_data_page(&fio);
+
+		if (IS_NOQUOTA(inode))
+			up_read(&sbi->node_write);
+
 		goto done;
 	}
 
@@ -3268,7 +3304,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 
 	if (f2fs_has_inline_data(inode) ||
 			(pos & PAGE_MASK) >= i_size_read(inode)) {
-		__do_map_lock(sbi, flag, true);
+		f2fs_do_map_lock(sbi, flag, true);
 		locked = true;
 	}
 
@@ -3305,7 +3341,7 @@ restart:
 			err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
 			if (err || dn.data_blkaddr == NULL_ADDR) {
 				f2fs_put_dnode(&dn);
-				__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
+				f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
 								true);
 				WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO);
 				locked = true;
@@ -3321,7 +3357,7 @@ out:
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (locked)
-		__do_map_lock(sbi, flag, false);
+		f2fs_do_map_lock(sbi, flag, false);
 	return err;
 }
 
@@ -3433,7 +3469,7 @@ repeat:
 			err = -EFSCORRUPTED;
 			goto fail;
 		}
-		err = f2fs_submit_page_read(inode, page, blkaddr, true);
+		err = f2fs_submit_page_read(inode, page, blkaddr, 0, true);
 		if (err)
 			goto fail;
 
@@ -3483,6 +3519,10 @@ static int f2fs_write_end(struct file *file,
 	if (f2fs_compressed_file(inode) && fsdata) {
 		f2fs_compress_write_end(inode, fsdata, page->index, copied);
 		f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+
+		if (pos + copied > i_size_read(inode) &&
+				!f2fs_verity_in_progress(inode))
+			f2fs_i_size_write(inode, pos + copied);
 		return copied;
 	}
 #endif
@@ -3742,10 +3782,9 @@ static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block)
 	}
 
 	f2fs_put_dnode(&dn);
-
 	return blknr;
 #else
-	return -EOPNOTSUPP;
+	return 0;
 #endif
 }
 
@@ -3753,18 +3792,26 @@ static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block)
 static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 {
 	struct inode *inode = mapping->host;
+	struct buffer_head tmp = {
+		.b_size = i_blocksize(inode),
+	};
+	sector_t blknr = 0;
 
 	if (f2fs_has_inline_data(inode))
-		return 0;
+		goto out;
 
 	/* make sure allocating whole blocks */
 	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		filemap_write_and_wait(mapping);
 
 	if (f2fs_compressed_file(inode))
-		return f2fs_bmap_compress(inode, block);
+		blknr = f2fs_bmap_compress(inode, block);
 
-	return generic_block_bmap(mapping, block, get_data_block_bmap);
+	if (!get_data_block_bmap(inode, block, &tmp, 0))
+		blknr = tmp.b_blocknr;
+out:
+	trace_f2fs_bmap(inode, block, blknr);
+	return blknr;
 }
 
 #ifdef CONFIG_MIGRATION