Merge tag 'f2fs-for-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've tuned f2fs to improve general performance by
  serializing block allocation and enhancing discard flows like fstrim
  which avoids user IO contention. And we've added fsync_mode=nobarrier
  which gives an option to user where it skips issuing cache_flush
  commands to underlying flash storage. And there are many bug fixes
  related to fuzzed images, revoked atomic writes, quota ops, and minor
  direct IO.

  Enhancements:
   - add fsync_mode=nobarrier which bypasses cache_flush command
   - enhance the discarding flow which avoids user IOs and issues in
     LBA order
   - readahead some encrypted blocks during GC
   - enable in-memory inode checksum to verify the blocks if
     F2FS_CHECK_FS is set
   - enhance nat_bits behavior
   - set -o discard by default
   - set REQ_RAHEAD to bio in ->readpages

  Bug fixes:
   - fix a corner case to corrupt atomic_writes revoking flow
   - revisit i_gc_rwsem to fix race conditions
   - fix some dio behaviors captured by xfstests
   - correct handling errors given by quota-related failures
   - add many sanity check flows to avoid fuzz test failures
   - add more error number propagation to their callers
   - fix several corner cases to continue fault injection w/ shutdown
     loop"

* tag 'f2fs-for-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (89 commits)
  f2fs: readahead encrypted block during GC
  f2fs: avoid fi->i_gc_rwsem[WRITE] lock in f2fs_gc
  f2fs: fix performance issue observed with multi-thread sequential read
  f2fs: fix to skip verifying block address for non-regular inode
  f2fs: rework fault injection handling to avoid a warning
  f2fs: support fault_type mount option
  f2fs: fix to return success when trimming meta area
  f2fs: fix use-after-free of dicard command entry
  f2fs: support discard submission error injection
  f2fs: split discard command in prior to block layer
  f2fs: wake up gc thread immediately when gc_urgent is set
  f2fs: fix incorrect range->len in f2fs_trim_fs()
  f2fs: refresh recent accessed nat entry in lru list
  f2fs: fix avoid race between truncate and background GC
  f2fs: avoid race between zero_range and background GC
  f2fs: fix to do sanity check with block address in main area v2
  f2fs: fix to do sanity check with inline flags
  f2fs: fix to reset i_gc_failures correctly
  f2fs: fix invalid memory access
  f2fs: fix to avoid broken of dnode block list
  ...

1 files changed, 106 insertions, 53 deletions

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 9f1c96caebda..e8b6b89bddb8 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -28,6 +28,7 @@ struct kmem_cache *f2fs_inode_entry_slab;
 
 void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 {
+	f2fs_build_fault_attr(sbi, 0, 0);
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
 	if (!end_io)
 		f2fs_flush_merged_writes(sbi);
@@ -70,6 +71,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.encrypted_page = NULL,
 		.is_meta = is_meta,
 	};
+	int err;
 
 	if (unlikely(!is_meta))
 		fio.op_flags &= ~REQ_META;
@@ -84,9 +86,10 @@ repeat:
 
 	fio.page = page;
 
-	if (f2fs_submit_page_bio(&fio)) {
+	err = f2fs_submit_page_bio(&fio);
+	if (err) {
 		f2fs_put_page(page, 1);
-		goto repeat;
+		return ERR_PTR(err);
 	}
 
 	lock_page(page);
@@ -95,14 +98,9 @@ repeat:
 		goto repeat;
 	}
 
-	/*
-	 * if there is any IO error when accessing device, make our filesystem
-	 * readonly and make sure do not write checkpoint with non-uptodate
-	 * meta page.
-	 */
 	if (unlikely(!PageUptodate(page))) {
-		memset(page_address(page), 0, PAGE_SIZE);
-		f2fs_stop_checkpoint(sbi, false);
+		f2fs_put_page(page, 1);
+		return ERR_PTR(-EIO);
 	}
 out:
 	return page;
@@ -113,13 +111,32 @@ struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	return __get_meta_page(sbi, index, true);
 }
 
+struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+	struct page *page;
+	int count = 0;
+
+retry:
+	page = __get_meta_page(sbi, index, true);
+	if (IS_ERR(page)) {
+		if (PTR_ERR(page) == -EIO &&
+				++count <= DEFAULT_RETRY_IO_COUNT)
+			goto retry;
+
+		f2fs_stop_checkpoint(sbi, false);
+		f2fs_bug_on(sbi, 1);
+	}
+
+	return page;
+}
+
 /* for POR only */
 struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
 {
 	return __get_meta_page(sbi, index, false);
 }
 
-bool f2fs_is_valid_meta_blkaddr(struct f2fs_sb_info *sbi,
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 					block_t blkaddr, int type)
 {
 	switch (type) {
@@ -140,8 +157,20 @@ bool f2fs_is_valid_meta_blkaddr(struct f2fs_sb_info *sbi,
 			return false;
 		break;
 	case META_POR:
+	case DATA_GENERIC:
 		if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
-			blkaddr < MAIN_BLKADDR(sbi)))
+			blkaddr < MAIN_BLKADDR(sbi))) {
+			if (type == DATA_GENERIC) {
+				f2fs_msg(sbi->sb, KERN_WARNING,
+					"access invalid blkaddr:%u", blkaddr);
+				WARN_ON(1);
+			}
+			return false;
+		}
+		break;
+	case META_GENERIC:
+		if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
+			blkaddr >= MAIN_BLKADDR(sbi)))
 			return false;
 		break;
 	default:
@@ -176,7 +205,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 	blk_start_plug(&plug);
 	for (; nrpages-- > 0; blkno++) {
 
-		if (!f2fs_is_valid_meta_blkaddr(sbi, blkno, type))
+		if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
 			goto out;
 
 		switch (type) {
@@ -242,11 +271,8 @@ static int __f2fs_write_meta_page(struct page *page,
 
 	trace_f2fs_writepage(page, META);
 
-	if (unlikely(f2fs_cp_error(sbi))) {
-		dec_page_count(sbi, F2FS_DIRTY_META);
-		unlock_page(page);
-		return 0;
-	}
+	if (unlikely(f2fs_cp_error(sbi)))
+		goto redirty_out;
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto redirty_out;
 	if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
@@ -529,13 +555,12 @@ int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
 
 	spin_lock(&im->ino_lock);
 
-#ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_ORPHAN)) {
 		spin_unlock(&im->ino_lock);
 		f2fs_show_injection_info(FAULT_ORPHAN);
 		return -ENOSPC;
 	}
-#endif
+
 	if (unlikely(im->ino_num >= sbi->max_orphans))
 		err = -ENOSPC;
 	else
@@ -572,12 +597,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	struct inode *inode;
 	struct node_info ni;
-	int err = f2fs_acquire_orphan_inode(sbi);
-
-	if (err)
-		goto err_out;
-
-	__add_ino_entry(sbi, ino, 0, ORPHAN_INO);
+	int err;
 
 	inode = f2fs_iget_retry(sbi->sb, ino);
 	if (IS_ERR(inode)) {
@@ -600,14 +620,15 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 	/* truncate all the data during iput */
 	iput(inode);
 
-	f2fs_get_node_info(sbi, ino, &ni);
+	err = f2fs_get_node_info(sbi, ino, &ni);
+	if (err)
+		goto err_out;
 
 	/* ENOMEM was fully retried in f2fs_evict_inode. */
 	if (ni.blk_addr != NULL_ADDR) {
 		err = -EIO;
 		goto err_out;
 	}
-	__remove_ino_entry(sbi, ino, ORPHAN_INO);
 	return 0;
 
 err_out:
@@ -639,7 +660,10 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	/* Needed for iput() to work correctly and not trash data */
 	sbi->sb->s_flags |= SB_ACTIVE;
 
-	/* Turn on quotas so that they are updated correctly */
+	/*
+	 * Turn on quotas which were not enabled for read-only mounts if
+	 * filesystem has quota feature, so that they are updated correctly.
+	 */
 	quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
 #endif
 
@@ -649,9 +673,15 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
 
 	for (i = 0; i < orphan_blocks; i++) {
-		struct page *page = f2fs_get_meta_page(sbi, start_blk + i);
+		struct page *page;
 		struct f2fs_orphan_block *orphan_blk;
 
+		page = f2fs_get_meta_page(sbi, start_blk + i);
+		if (IS_ERR(page)) {
+			err = PTR_ERR(page);
+			goto out;
+		}
+
 		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
 		for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
 			nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
@@ -742,10 +772,14 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 	__u32 crc = 0;
 
 	*cp_page = f2fs_get_meta_page(sbi, cp_addr);
+	if (IS_ERR(*cp_page))
+		return PTR_ERR(*cp_page);
+
 	*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
 
 	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
 	if (crc_offset > (blk_size - sizeof(__le32))) {
+		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING,
 			"invalid crc_offset: %zu", crc_offset);
 		return -EINVAL;
@@ -753,6 +787,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 
 	crc = cur_cp_crc(*cp_block);
 	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
+		f2fs_put_page(*cp_page, 1);
 		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
 		return -EINVAL;
 	}
@@ -772,14 +807,22 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
 					&cp_page_1, version);
 	if (err)
-		goto invalid_cp1;
+		return NULL;
+
+	if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
+					sbi->blocks_per_seg) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid cp_pack_total_block_count:%u",
+			le32_to_cpu(cp_block->cp_pack_total_block_count));
+		goto invalid_cp;
+	}
 	pre_version = *version;
 
 	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
 	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
 					&cp_page_2, version);
 	if (err)
-		goto invalid_cp2;
+		goto invalid_cp;
 	cur_version = *version;
 
 	if (cur_version == pre_version) {
@@ -787,9 +830,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		f2fs_put_page(cp_page_2, 1);
 		return cp_page_1;
 	}
-invalid_cp2:
 	f2fs_put_page(cp_page_2, 1);
-invalid_cp1:
+invalid_cp:
 	f2fs_put_page(cp_page_1, 1);
 	return NULL;
 }
@@ -838,15 +880,15 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
-	/* Sanity checking of checkpoint */
-	if (f2fs_sanity_check_ckpt(sbi))
-		goto free_fail_no_cp;
-
 	if (cur_page == cp1)
 		sbi->cur_cp_pack = 1;
 	else
 		sbi->cur_cp_pack = 2;
 
+	/* Sanity checking of checkpoint */
+	if (f2fs_sanity_check_ckpt(sbi))
+		goto free_fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;
 
@@ -859,6 +901,8 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
 		unsigned char *ckpt = (unsigned char *)sbi->ckpt;
 
 		cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
+		if (IS_ERR(cur_page))
+			goto free_fail_no_cp;
 		sit_bitmap_ptr = page_address(cur_page);
 		memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
 		f2fs_put_page(cur_page, 1);
@@ -980,12 +1024,10 @@ retry:
 
 		iput(inode);
 		/* We need to give cpu to another writers. */
-		if (ino == cur_ino) {
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+		if (ino == cur_ino)
 			cond_resched();
-		} else {
+		else
 			ino = cur_ino;
-		}
 	} else {
 		/*
 		 * We should submit bio, since it exists several
@@ -1119,7 +1161,7 @@ static void unblock_operations(struct f2fs_sb_info *sbi)
 	f2fs_unlock_all(sbi);
 }
 
-static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
+void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 {
 	DEFINE_WAIT(wait);
 
@@ -1129,6 +1171,9 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 		if (!get_pages(sbi, F2FS_WB_CP_DATA))
 			break;
 
+		if (unlikely(f2fs_cp_error(sbi)))
+			break;
+
 		io_schedule_timeout(5*HZ);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
@@ -1202,8 +1247,12 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi,
 
 	/* writeout cp pack 2 page */
 	err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO);
-	f2fs_bug_on(sbi, err);
+	if (unlikely(err && f2fs_cp_error(sbi))) {
+		f2fs_put_page(page, 1);
+		return;
+	}
 
+	f2fs_bug_on(sbi, err);
 	f2fs_put_page(page, 0);
 
 	/* submit checkpoint (with barrier if NOBARRIER is not set) */
@@ -1229,7 +1278,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
 		f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
 		if (unlikely(f2fs_cp_error(sbi)))
-			return -EIO;
+			break;
 	}
 
 	/*
@@ -1309,7 +1358,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			f2fs_sync_meta_pages(sbi, META, LONG_MAX,
 							FS_CP_META_IO);
 			if (unlikely(f2fs_cp_error(sbi)))
-				return -EIO;
+				break;
 		}
 	}
 
@@ -1348,10 +1397,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
 
 	/* wait for previous submitted meta pages writeback */
-	wait_on_all_pages_writeback(sbi);
-
-	if (unlikely(f2fs_cp_error(sbi)))
-		return -EIO;
+	f2fs_wait_on_all_pages_writeback(sbi);
 
 	/* flush all device cache */
 	err = f2fs_flush_device_cache(sbi);
@@ -1360,12 +1406,19 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* barrier and flush checkpoint cp pack 2 page if it can */
 	commit_checkpoint(sbi, ckpt, start_blk);
-	wait_on_all_pages_writeback(sbi);
+	f2fs_wait_on_all_pages_writeback(sbi);
+
+	/*
+	 * invalidate intermediate page cache borrowed from meta inode
+	 * which are used for migration of encrypted inode's blocks.
+	 */
+	if (f2fs_sb_has_encrypt(sbi->sb))
+		invalidate_mapping_pages(META_MAPPING(sbi),
+				MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
 
 	f2fs_release_ino_entry(sbi, false);
 
-	if (unlikely(f2fs_cp_error(sbi)))
-		return -EIO;
+	f2fs_reset_fsync_node_info(sbi);
 
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 	clear_sbi_flag(sbi, SBI_NEED_CP);
@@ -1381,7 +1434,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
 
-	return 0;
+	return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
 }
 
 /*