Merge tag 'f2fs-for-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've tried to address some performance issues in
  f2fs_checkpoint and direct IO flows. Also, there was a work to enhance
  the page cache management used for compression. Other than them, we've
  done typical work including sysfs, code clean-ups, tracepoint, sanity
  check, in addition to bug fixes on corner cases.

  Enhancements:
   - use iomap for direct IO
   - try to avoid lock contention to improve f2fs_ckpt speed
   - avoid unnecessary memory allocation in compression flow
   - POSIX_FADV_DONTNEED drops the page cache containing compression
     pages
   - add some sysfs entries (gc_urgent_high_remaining, pending_discard)

  Bug fixes:
   - try not to expose unwritten blocks to user by DIO (this was added
     to avoid merge conflict; another patch is coming to address other
     missing case)
   - relax minor error condition for file pinning feature used in
     Android OTA
   - fix potential deadlock case in compression flow
   - should not truncate any block on pinned file

  In addition, we've done some code clean-ups and tracepoint/sanity
  check improvement"

* tag 'f2fs-for-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (29 commits)
  f2fs: do not allow partial truncation on pinned file
  f2fs: remove redunant invalidate compress pages
  f2fs: Simplify bool conversion
  f2fs: don't drop compressed page cache in .{invalidate,release}page
  f2fs: fix to reserve space for IO align feature
  f2fs: fix to check available space of CP area correctly in update_ckpt_flags()
  f2fs: support fault injection to f2fs_trylock_op()
  f2fs: clean up __find_inline_xattr() with __find_xattr()
  f2fs: fix to do sanity check on last xattr entry in __f2fs_setxattr()
  f2fs: do not bother checkpoint by f2fs_get_node_info
  f2fs: avoid down_write on nat_tree_lock during checkpoint
  f2fs: compress: fix potential deadlock of compress file
  f2fs: avoid EINVAL by SBI_NEED_FSCK when pinning a file
  f2fs: add gc_urgent_high_remaining sysfs node
  f2fs: fix to do sanity check in is_alive()
  f2fs: fix to avoid panic in is_alive() if metadata is inconsistent
  f2fs: fix to do sanity check on inode type during garbage collection
  f2fs: avoid duplicate call of mark_inode_dirty
  f2fs: show number of pending discard commands
  f2fs: support POSIX_FADV_DONTNEED drop compressed page cache
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -112,6 +112,11 @@ Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:	Set timeout to issue discard commands during umount.
 	        Default: 5 secs
 
+What:		/sys/fs/f2fs/<disk>/pending_discard
+Date:		November 2021
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Shows the number of pending discard commands in the queue.
+
 What:		/sys/fs/f2fs/<disk>/max_victim_search
 Date:		January 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
@@ -528,3 +533,10 @@ Description:	With "mode=fragment:block" mount options, we can scatter block allo
 		f2fs will allocate 1..<max_fragment_chunk> blocks in a chunk and make a hole
 		in the length of 1..<max_fragment_hole> by turns. This value can be set
 		between 1..512 and the default value is 4.
+
+What:		/sys/fs/f2fs/<disk>/gc_urgent_high_remaining
+Date:		December 2021
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	You can set the trial count limit for GC urgent high mode with this value.
+		If GC thread gets to the limit, the mode will turn back to GC normal mode.
+		By default, the value is zero, which means there is no limit like before.

Documentation/filesystems/f2fs.rst

@@ -198,6 +198,7 @@ fault_type=%d		 Support configuring fault injection type, should be
 			 FAULT_WRITE_IO		  0x000004000
 			 FAULT_SLAB_ALLOC	  0x000008000
 			 FAULT_DQUOT_INIT	  0x000010000
+			 FAULT_LOCK_OP		  0x000020000
 			 ===================	  ===========
 mode=%s			 Control block allocation mode which supports "adaptive"
 			 and "lfs". In "lfs" mode, there should be no random

fs/f2fs/Kconfig

@@ -7,6 +7,7 @@ config F2FS_FS
 	select CRYPTO_CRC32
 	select F2FS_FS_XATTR if FS_ENCRYPTION
 	select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
+	select FS_IOMAP
 	select LZ4_COMPRESS if F2FS_FS_LZ4
 	select LZ4_DECOMPRESS if F2FS_FS_LZ4
 	select LZ4HC_COMPRESS if F2FS_FS_LZ4HC

fs/f2fs/checkpoint.c

@@ -664,7 +664,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 	/* truncate all the data during iput */
 	iput(inode);
 
-	err = f2fs_get_node_info(sbi, ino, &ni);
+	err = f2fs_get_node_info(sbi, ino, &ni, false);
 	if (err)
 		goto err_out;
 
@@ -1302,8 +1302,8 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	unsigned long flags;
 
 	if (cpc->reason & CP_UMOUNT) {
-		if (le32_to_cpu(ckpt->cp_pack_total_block_count) >
-			sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks) {
+		if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
+			NM_I(sbi)->nat_bits_blocks > sbi->blocks_per_seg) {
 			clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
 			f2fs_notice(sbi, "Disable nat_bits due to no space");
 		} else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) &&

fs/f2fs/compress.c

@@ -154,6 +154,7 @@ void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse)
 	cc->rpages = NULL;
 	cc->nr_rpages = 0;
 	cc->nr_cpages = 0;
+	cc->valid_nr_cpages = 0;
 	if (!reuse)
 		cc->cluster_idx = NULL_CLUSTER;
 }
@@ -620,7 +621,6 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	const struct f2fs_compress_ops *cops =
 				f2fs_cops[fi->i_compress_algorithm];
 	unsigned int max_len, new_nr_cpages;
-	struct page **new_cpages;
 	u32 chksum = 0;
 	int i, ret;
 
@@ -635,6 +635,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	max_len = COMPRESS_HEADER_SIZE + cc->clen;
 	cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE);
+	cc->valid_nr_cpages = cc->nr_cpages;
 
 	cc->cpages = page_array_alloc(cc->inode, cc->nr_cpages);
 	if (!cc->cpages) {
@@ -685,13 +686,6 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 
 	new_nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE);
 
-	/* Now we're going to cut unnecessary tail pages */
-	new_cpages = page_array_alloc(cc->inode, new_nr_cpages);
-	if (!new_cpages) {
-		ret = -ENOMEM;
-		goto out_vunmap_cbuf;
-	}
-
 	/* zero out any unused part of the last page */
 	memset(&cc->cbuf->cdata[cc->clen], 0,
 			(new_nr_cpages * PAGE_SIZE) -
@@ -701,10 +695,8 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	vm_unmap_ram(cc->rbuf, cc->cluster_size);
 
 	for (i = 0; i < cc->nr_cpages; i++) {
-		if (i < new_nr_cpages) {
-			new_cpages[i] = cc->cpages[i];
+		if (i < new_nr_cpages)
 			continue;
-		}
 		f2fs_compress_free_page(cc->cpages[i]);
 		cc->cpages[i] = NULL;
 	}
@@ -712,9 +704,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 	if (cops->destroy_compress_ctx)
 		cops->destroy_compress_ctx(cc);
 
-	page_array_free(cc->inode, cc->cpages, cc->nr_cpages);
-	cc->cpages = new_cpages;
-	cc->nr_cpages = new_nr_cpages;
+	cc->valid_nr_cpages = new_nr_cpages;
 
 	trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx,
 							cc->clen, ret);
@@ -1296,7 +1286,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT;
 
-	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
 	if (err)
 		goto out_put_dnode;
 
@@ -1308,14 +1298,14 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	cic->magic = F2FS_COMPRESSED_PAGE_MAGIC;
 	cic->inode = inode;
-	atomic_set(&cic->pending_pages, cc->nr_cpages);
+	atomic_set(&cic->pending_pages, cc->valid_nr_cpages);
 	cic->rpages = page_array_alloc(cc->inode, cc->cluster_size);
 	if (!cic->rpages)
 		goto out_put_cic;
 
 	cic->nr_rpages = cc->cluster_size;
 
-	for (i = 0; i < cc->nr_cpages; i++) {
+	for (i = 0; i < cc->valid_nr_cpages; i++) {
 		f2fs_set_compressed_page(cc->cpages[i], inode,
 					cc->rpages[i + 1]->index, cic);
 		fio.compressed_page = cc->cpages[i];
@@ -1360,7 +1350,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 		if (fio.compr_blocks && __is_valid_data_blkaddr(blkaddr))
 			fio.compr_blocks++;
 
-		if (i > cc->nr_cpages) {
+		if (i > cc->valid_nr_cpages) {
 			if (__is_valid_data_blkaddr(blkaddr)) {
 				f2fs_invalidate_blocks(sbi, blkaddr);
 				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
@@ -1385,8 +1375,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 
 	if (fio.compr_blocks)
 		f2fs_i_compr_blocks_update(inode, fio.compr_blocks - 1, false);
-	f2fs_i_compr_blocks_update(inode, cc->nr_cpages, true);
-	add_compr_block_stat(inode, cc->nr_cpages);
+	f2fs_i_compr_blocks_update(inode, cc->valid_nr_cpages, true);
+	add_compr_block_stat(inode, cc->valid_nr_cpages);
 
 	set_inode_flag(cc->inode, FI_APPEND_WRITE);
 	if (cc->cluster_idx == 0)
@@ -1424,9 +1414,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
 	else
 		f2fs_unlock_op(sbi);
 out_free:
-	for (i = 0; i < cc->nr_cpages; i++) {
-		if (!cc->cpages[i])
-			continue;
+	for (i = 0; i < cc->valid_nr_cpages; i++) {
 		f2fs_compress_free_page(cc->cpages[i]);
 		cc->cpages[i] = NULL;
 	}
@@ -1468,25 +1456,38 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
 					enum iostat_type io_type)
 {
 	struct address_space *mapping = cc->inode->i_mapping;
-	int _submitted, compr_blocks, ret;
-	int i = -1, err = 0;
+	int _submitted, compr_blocks, ret, i;
 
 	compr_blocks = f2fs_compressed_blocks(cc);
-	if (compr_blocks < 0) {
-		err = compr_blocks;
-		goto out_err;
+
+	for (i = 0; i < cc->cluster_size; i++) {
+		if (!cc->rpages[i])
+			continue;
+
+		redirty_page_for_writepage(wbc, cc->rpages[i]);
+		unlock_page(cc->rpages[i]);
 	}
 
+	if (compr_blocks < 0)
+		return compr_blocks;
+
 	for (i = 0; i < cc->cluster_size; i++) {
 		if (!cc->rpages[i])
 			continue;
 retry_write:
+		lock_page(cc->rpages[i]);
+
 		if (cc->rpages[i]->mapping != mapping) {
+continue_unlock:
 			unlock_page(cc->rpages[i]);
 			continue;
 		}
 
-		BUG_ON(!PageLocked(cc->rpages[i]));
+		if (!PageDirty(cc->rpages[i]))
+			goto continue_unlock;
+
+		if (!clear_page_dirty_for_io(cc->rpages[i]))
+			goto continue_unlock;
 
 		ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted,
 						NULL, NULL, wbc, io_type,
@@ -1501,26 +1502,15 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
 				 * avoid deadlock caused by cluster update race
 				 * from foreground operation.
 				 */
-				if (IS_NOQUOTA(cc->inode)) {
-					err = 0;
-					goto out_err;
-				}
+				if (IS_NOQUOTA(cc->inode))
+					return 0;
 				ret = 0;
 				cond_resched();
 				congestion_wait(BLK_RW_ASYNC,
 						DEFAULT_IO_TIMEOUT);
-				lock_page(cc->rpages[i]);
-
-				if (!PageDirty(cc->rpages[i])) {
-					unlock_page(cc->rpages[i]);
-					continue;
-				}
-
-				clear_page_dirty_for_io(cc->rpages[i]);
 				goto retry_write;
 			}
-			err = ret;
-			goto out_err;
+			return ret;
 		}
 
 		*submitted += _submitted;
@@ -1529,14 +1519,6 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
 	f2fs_balance_fs(F2FS_M_SB(mapping), true);
 
 	return 0;
-out_err:
-	for (++i; i < cc->cluster_size; i++) {
-		if (!cc->rpages[i])
-			continue;
-		redirty_page_for_writepage(wbc, cc->rpages[i]);
-		unlock_page(cc->rpages[i]);
-	}
-	return err;
 }
 
 int f2fs_write_multi_pages(struct compress_ctx *cc,

fs/f2fs/f2fs.h

@@ -58,6 +58,7 @@ enum {
 	FAULT_WRITE_IO,
 	FAULT_SLAB_ALLOC,
 	FAULT_DQUOT_INIT,
+	FAULT_LOCK_OP,
 	FAULT_MAX,
 };
 
@@ -656,6 +657,7 @@ enum {
 #define FADVISE_KEEP_SIZE_BIT	0x10
 #define FADVISE_HOT_BIT		0x20
 #define FADVISE_VERITY_BIT	0x40
+#define FADVISE_TRUNC_BIT	0x80
 
 #define FADVISE_MODIFIABLE_BITS	(FADVISE_COLD_BIT | FADVISE_HOT_BIT)
 
@@ -683,6 +685,10 @@ enum {
 #define file_is_verity(inode)	is_file(inode, FADVISE_VERITY_BIT)
 #define file_set_verity(inode)	set_file(inode, FADVISE_VERITY_BIT)
 
+#define file_should_truncate(inode)	is_file(inode, FADVISE_TRUNC_BIT)
+#define file_need_truncate(inode)	set_file(inode, FADVISE_TRUNC_BIT)
+#define file_dont_truncate(inode)	clear_file(inode, FADVISE_TRUNC_BIT)
+
 #define DEF_DIR_LEVEL		0
 
 enum {
@@ -717,7 +723,7 @@ enum {
 	FI_INLINE_DOTS,		/* indicate inline dot dentries */
 	FI_DO_DEFRAG,		/* indicate defragment is running */
 	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
-	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
+	FI_PREALLOCATED_ALL,	/* all blocks for write were preallocated */
 	FI_HOT_DATA,		/* indicate file is hot */
 	FI_EXTRA_ATTR,		/* indicate file has extra attribute */
 	FI_PROJ_INHERIT,	/* indicate file inherits projectid */
@@ -1020,6 +1026,7 @@ struct f2fs_sm_info {
 	unsigned int segment_count;	/* total # of segments */
 	unsigned int main_segments;	/* # of segments in main area */
 	unsigned int reserved_segments;	/* # of reserved segments */
+	unsigned int additional_reserved_segments;/* reserved segs for IO align feature */
 	unsigned int ovp_segments;	/* # of overprovision segments */
 
 	/* a threshold to reclaim prefree segments */
@@ -1488,6 +1495,7 @@ struct compress_ctx {
 	unsigned int nr_rpages;		/* total page number in rpages */
 	struct page **cpages;		/* pages store compressed data in cluster */
 	unsigned int nr_cpages;		/* total page number in cpages */
+	unsigned int valid_nr_cpages;	/* valid page number in cpages */
 	void *rbuf;			/* virtual mapped address on rpages */
 	struct compress_data *cbuf;	/* virtual mapped address on cpages */
 	size_t rlen;			/* valid data length in rbuf */
@@ -1679,6 +1687,9 @@ struct f2fs_sb_info {
 	unsigned int cur_victim_sec;		/* current victim section num */
 	unsigned int gc_mode;			/* current GC state */
 	unsigned int next_victim_seg[2];	/* next segment in victim section */
+	spinlock_t gc_urgent_high_lock;
+	bool gc_urgent_high_limited;		/* indicates having limited trial count */
+	unsigned int gc_urgent_high_remaining;	/* remaining trial count for GC_URGENT_HIGH */
 
 	/* for skip statistic */
 	unsigned int atomic_files;		/* # of opened atomic file */
@@ -1803,13 +1814,6 @@ struct f2fs_sb_info {
 #endif
 };
 
-struct f2fs_private_dio {
-	struct inode *inode;
-	void *orig_private;
-	bio_end_io_t *orig_end_io;
-	bool write;
-};
-
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 #define f2fs_show_injection_info(sbi, type)					\
 	printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n",	\
@@ -2095,6 +2099,10 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 
 static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
 {
+	if (time_to_inject(sbi, FAULT_LOCK_OP)) {
+		f2fs_show_injection_info(sbi, FAULT_LOCK_OP);
+		return 0;
+	}
 	return down_read_trylock(&sbi->cp_rwsem);
 }
 
@@ -2200,6 +2208,11 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 
 	if (!__allow_reserved_blocks(sbi, inode, true))
 		avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
+
+	if (F2FS_IO_ALIGNED(sbi))
+		avail_user_block_count -= sbi->blocks_per_seg *
+				SM_I(sbi)->additional_reserved_segments;
+
 	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
 		if (avail_user_block_count > sbi->unusable_block_count)
 			avail_user_block_count -= sbi->unusable_block_count;
@@ -2446,6 +2459,11 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
 
 	if (!__allow_reserved_blocks(sbi, inode, false))
 		valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
+
+	if (F2FS_IO_ALIGNED(sbi))
+		valid_block_count += sbi->blocks_per_seg *
+				SM_I(sbi)->additional_reserved_segments;
+
 	user_block_count = sbi->user_block_count;
 	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		user_block_count -= sbi->unusable_block_count;
@@ -3118,12 +3136,16 @@ static inline int is_file(struct inode *inode, int type)
 
 static inline void set_file(struct inode *inode, int type)
 {
+	if (is_file(inode, type))
+		return;
 	F2FS_I(inode)->i_advise |= type;
 	f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 static inline void clear_file(struct inode *inode, int type)
 {
+	if (!is_file(inode, type))
+		return;
 	F2FS_I(inode)->i_advise &= ~type;
 	f2fs_mark_inode_dirty_sync(inode, true);
 }
@@ -3408,7 +3430,7 @@ int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
 bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
 bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
 int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
-						struct node_info *ni);
+				struct node_info *ni, bool checkpoint_context);
 pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
 int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
 int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
@@ -3616,7 +3638,6 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
 int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
 int f2fs_reserve_new_block(struct dnode_of_data *dn);
 int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
 int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
 struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
 			int op_flags, bool for_write);
@@ -3639,6 +3660,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
 				struct writeback_control *wbc,
 				enum iostat_type io_type,
 				int compr_blocks, bool allow_balance);
+void f2fs_write_failed(struct inode *inode, loff_t to);
 void f2fs_invalidate_page(struct page *page, unsigned int offset,
 			unsigned int length);
 int f2fs_release_page(struct page *page, gfp_t wait);
@@ -3652,6 +3674,7 @@ int f2fs_init_post_read_processing(void);
 void f2fs_destroy_post_read_processing(void);
 int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
 void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
+extern const struct iomap_ops f2fs_iomap_ops;
 
 /*
  * gc.c

fs/f2fs/gc.c

@@ -92,6 +92,18 @@ static int gc_thread_func(void *data)
 		 * So, I'd like to wait some time to collect dirty segments.
 		 */
 		if (sbi->gc_mode == GC_URGENT_HIGH) {
+			spin_lock(&sbi->gc_urgent_high_lock);
+			if (sbi->gc_urgent_high_limited) {
+				if (!sbi->gc_urgent_high_remaining) {
+					sbi->gc_urgent_high_limited = false;
+					spin_unlock(&sbi->gc_urgent_high_lock);
+					sbi->gc_mode = GC_NORMAL;
+					continue;
+				}
+				sbi->gc_urgent_high_remaining--;
+			}
+			spin_unlock(&sbi->gc_urgent_high_lock);
+
 			wait_ms = gc_th->urgent_sleep_time;
 			down_write(&sbi->gc_lock);
 			goto do_gc;
@@ -947,7 +959,7 @@ static int gc_node_segment(struct f2fs_sb_info *sbi,
 			continue;
 		}
 
-		if (f2fs_get_node_info(sbi, nid, &ni)) {
+		if (f2fs_get_node_info(sbi, nid, &ni, false)) {
 			f2fs_put_page(node_page, 1);
 			continue;
 		}
@@ -1015,7 +1027,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	if (IS_ERR(node_page))
 		return false;
 
-	if (f2fs_get_node_info(sbi, nid, dni)) {
+	if (f2fs_get_node_info(sbi, nid, dni, false)) {
 		f2fs_put_page(node_page, 1);
 		return false;
 	}
@@ -1026,6 +1038,9 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 	}
 
+	if (f2fs_check_nid_range(sbi, dni->ino))
+		return false;
+
 	*nofs = ofs_of_node(node_page);
 	source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node);
 	f2fs_put_page(node_page, 1);
@@ -1039,7 +1054,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 			if (!test_and_set_bit(segno, SIT_I(sbi)->invalid_segmap)) {
 				f2fs_err(sbi, "mismatched blkaddr %u (source_blkaddr %u) in seg %u",
 					 blkaddr, source_blkaddr, segno);
-				f2fs_bug_on(sbi, 1);
+				set_sbi_flag(sbi, SBI_NEED_FSCK);
 			}
 		}
 #endif
@@ -1206,7 +1221,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
 
 	f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
 
-	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
+	err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
 	if (err)
 		goto put_out;
 
@@ -1456,7 +1471,8 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 		if (phase == 3) {
 			inode = f2fs_iget(sb, dni.ino);
-			if (IS_ERR(inode) || is_bad_inode(inode))
+			if (IS_ERR(inode) || is_bad_inode(inode) ||
+					special_file(inode->i_mode))
 				continue;
 
 			if (!down_write_trylock(

fs/f2fs/inline.c

@@ -131,7 +131,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	if (err)
 		return err;
 
-	err = f2fs_get_node_info(fio.sbi, dn->nid, &ni);
+	err = f2fs_get_node_info(fio.sbi, dn->nid, &ni, false);
 	if (err) {
 		f2fs_truncate_data_blocks_range(dn, 1);
 		f2fs_put_dnode(dn);
@@ -786,7 +786,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
 		ilen = start + len;
 	ilen -= start;
 
-	err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+	err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni, false);
 	if (err)
 		goto out;
 

fs/f2fs/inode.c

@@ -516,6 +516,11 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 	} else if (ino == F2FS_COMPRESS_INO(sbi)) {
 #ifdef CONFIG_F2FS_FS_COMPRESSION
 		inode->i_mapping->a_ops = &f2fs_compress_aops;
+		/*
+		 * generic_error_remove_page only truncates pages of regular
+		 * inode
+		 */
+		inode->i_mode |= S_IFREG;
 #endif
 		mapping_set_gfp_mask(inode->i_mapping,
 			GFP_NOFS | __GFP_HIGHMEM | __GFP_MOVABLE);
@@ -544,6 +549,14 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
 		goto bad_inode;
 	}
 	f2fs_set_inode_flags(inode);
+
+	if (file_should_truncate(inode)) {
+		ret = f2fs_truncate(inode);
+		if (ret)
+			goto bad_inode;
+		file_dont_truncate(inode);
+	}
+
 	unlock_new_inode(inode);
 	trace_f2fs_iget(inode);
 	return inode;
@@ -738,7 +751,8 @@ void f2fs_evict_inode(struct inode *inode)
 	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages_final(&inode->i_data);
 
-	if (test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode))
+	if ((inode->i_nlink || is_bad_inode(inode)) &&
+		test_opt(sbi, COMPRESS_CACHE) && f2fs_compressed_file(inode))
 		f2fs_invalidate_compress_pages(sbi, inode->i_ino);
 
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
@@ -868,7 +882,7 @@ void f2fs_handle_failed_inode(struct inode *inode)
 	 * so we can prevent losing this orphan when encoutering checkpoint
 	 * and following suddenly power-off.
 	 */
-	err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
+	err = f2fs_get_node_info(sbi, inode->i_ino, &ni, false);
 	if (err) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "May loss orphan inode, run fsck to fix.");

fs/f2fs/iostat.c

@@ -92,7 +92,7 @@ static inline void __record_iostat_latency(struct f2fs_sb_info *sbi)
 	struct f2fs_iostat_latency iostat_lat[MAX_IO_TYPE][NR_PAGE_TYPE];
 	struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
 
-	spin_lock_irq(&sbi->iostat_lat_lock);
+	spin_lock_bh(&sbi->iostat_lat_lock);
 	for (idx = 0; idx < MAX_IO_TYPE; idx++) {
 		for (io = 0; io < NR_PAGE_TYPE; io++) {
 			cnt = io_lat->bio_cnt[idx][io];
@@ -106,7 +106,7 @@ static inline void __record_iostat_latency(struct f2fs_sb_info *sbi)
 			io_lat->bio_cnt[idx][io] = 0;
 		}
 	}
-	spin_unlock_irq(&sbi->iostat_lat_lock);
+	spin_unlock_bh(&sbi->iostat_lat_lock);
 
 	trace_f2fs_iostat_latency(sbi, iostat_lat);
 }
@@ -120,9 +120,9 @@ static inline void f2fs_record_iostat(struct f2fs_sb_info *sbi)
 		return;
 
 	/* Need double check under the lock */
-	spin_lock(&sbi->iostat_lock);
+	spin_lock_bh(&sbi->iostat_lock);
 	if (time_is_after_jiffies(sbi->iostat_next_period)) {
-		spin_unlock(&sbi->iostat_lock);
+		spin_unlock_bh(&sbi->iostat_lock);
 		return;
 	}
 	sbi->iostat_next_period = jiffies +
@@ -133,7 +133,7 @@ static inline void f2fs_record_iostat(struct f2fs_sb_info *sbi)
 				sbi->prev_rw_iostat[i];
 		sbi->prev_rw_iostat[i] = sbi->rw_iostat[i];
 	}
-	spin_unlock(&sbi->iostat_lock);
+	spin_unlock_bh(&sbi->iostat_lock);
 
 	trace_f2fs_iostat(sbi, iostat_diff);
 
@@ -145,16 +145,16 @@ void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
 	struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
 	int i;
 
-	spin_lock(&sbi->iostat_lock);
+	spin_lock_bh(&sbi->iostat_lock);
 	for (i = 0; i < NR_IO_TYPE; i++) {
 		sbi->rw_iostat[i] = 0;
 		sbi->prev_rw_iostat[i] = 0;
 	}
-	spin_unlock(&sbi->iostat_lock);
+	spin_unlock_bh(&sbi->iostat_lock);
 
-	spin_lock_irq(&sbi->iostat_lat_lock);
+	spin_lock_bh(&sbi->iostat_lat_lock);
 	memset(io_lat, 0, sizeof(struct iostat_lat_info));
-	spin_unlock_irq(&sbi->iostat_lat_lock);
+	spin_unlock_bh(&sbi->iostat_lat_lock);
 }
 
 void f2fs_update_iostat(struct f2fs_sb_info *sbi,
@@ -163,19 +163,16 @@ void f2fs_update_iostat(struct f2fs_sb_info *sbi,
 	if (!sbi->iostat_enable)
 		return;
 
-	spin_lock(&sbi->iostat_lock);
+	spin_lock_bh(&sbi->iostat_lock);
 	sbi->rw_iostat[type] += io_bytes;
 
-	if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
-		sbi->rw_iostat[APP_BUFFERED_IO] =
-			sbi->rw_iostat[APP_WRITE_IO] -
-			sbi->rw_iostat[APP_DIRECT_IO];
+	if (type == APP_BUFFERED_IO || type == APP_DIRECT_IO)
+		sbi->rw_iostat[APP_WRITE_IO] += io_bytes;
 
-	if (type == APP_READ_IO || type == APP_DIRECT_READ_IO)
-		sbi->rw_iostat[APP_BUFFERED_READ_IO] =
-			sbi->rw_iostat[APP_READ_IO] -
-			sbi->rw_iostat[APP_DIRECT_READ_IO];
-	spin_unlock(&sbi->iostat_lock);
+	if (type == APP_BUFFERED_READ_IO || type == APP_DIRECT_READ_IO)
+		sbi->rw_iostat[APP_READ_IO] += io_bytes;
+
+	spin_unlock_bh(&sbi->iostat_lock);
 
 	f2fs_record_iostat(sbi);
 }
@@ -185,7 +182,6 @@ static inline void __update_iostat_latency(struct bio_iostat_ctx *iostat_ctx,
 {
 	unsigned long ts_diff;
 	unsigned int iotype = iostat_ctx->type;
-	unsigned long flags;
 	struct f2fs_sb_info *sbi = iostat_ctx->sbi;
 	struct iostat_lat_info *io_lat = sbi->iostat_io_lat;
 	int idx;
@@ -206,12 +202,12 @@ static inline void __update_iostat_latency(struct bio_iostat_ctx *iostat_ctx,
 			idx = WRITE_ASYNC_IO;
 	}
 
-	spin_lock_irqsave(&sbi->iostat_lat_lock, flags);
+	spin_lock_bh(&sbi->iostat_lat_lock);
 	io_lat->sum_lat[idx][iotype] += ts_diff;
 	io_lat->bio_cnt[idx][iotype]++;
 	if (ts_diff > io_lat->peak_lat[idx][iotype])
 		io_lat->peak_lat[idx][iotype] = ts_diff;
-	spin_unlock_irqrestore(&sbi->iostat_lat_lock, flags);
+	spin_unlock_bh(&sbi->iostat_lat_lock);
 }
 
 void iostat_update_and_unbind_ctx(struct bio *bio, int rw)

fs/f2fs/node.c

@@ -430,6 +430,10 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *new, *e;
 
+	/* Let's mitigate lock contention of nat_tree_lock during checkpoint */
+	if (rwsem_is_locked(&sbi->cp_global_sem))
+		return;
+
 	new = __alloc_nat_entry(sbi, nid, false);
 	if (!new)
 		return;
@@ -539,7 +543,7 @@ int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
 }
 
 int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
-						struct node_info *ni)
+				struct node_info *ni, bool checkpoint_context)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -572,9 +576,10 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	 * nat_tree_lock. Therefore, we should retry, if we failed to grab here
 	 * while not bothering checkpoint.
 	 */
-	if (!rwsem_is_locked(&sbi->cp_global_sem)) {
+	if (!rwsem_is_locked(&sbi->cp_global_sem) || checkpoint_context) {
 		down_read(&curseg->journal_rwsem);
-	} else if (!down_read_trylock(&curseg->journal_rwsem)) {
+	} else if (rwsem_is_contended(&nm_i->nat_tree_lock) ||
+				!down_read_trylock(&curseg->journal_rwsem)) {
 		up_read(&nm_i->nat_tree_lock);
 		goto retry;
 	}
@@ -887,7 +892,7 @@ static int truncate_node(struct dnode_of_data *dn)
 	int err;
 	pgoff_t index;
 
-	err = f2fs_get_node_info(sbi, dn->nid, &ni);
+	err = f2fs_get_node_info(sbi, dn->nid, &ni, false);
 	if (err)
 		return err;
 
@@ -1286,7 +1291,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
 		goto fail;
 
 #ifdef CONFIG_F2FS_CHECK_FS
-	err = f2fs_get_node_info(sbi, dn->nid, &new_ni);
+	err = f2fs_get_node_info(sbi, dn->nid, &new_ni, false);
 	if (err) {
 		dec_valid_node_count(sbi, dn->inode, !ofs);
 		goto fail;
@@ -1348,7 +1353,7 @@ static int read_node_page(struct page *page, int op_flags)
 		return LOCKED_PAGE;
 	}
 
-	err = f2fs_get_node_info(sbi, page->index, &ni);
+	err = f2fs_get_node_info(sbi, page->index, &ni, false);
 	if (err)
 		return err;
 
@@ -1600,7 +1605,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
 	nid = nid_of_node(page);
 	f2fs_bug_on(sbi, page->index != nid);
 
-	if (f2fs_get_node_info(sbi, nid, &ni))
+	if (f2fs_get_node_info(sbi, nid, &ni, !do_balance))
 		goto redirty_out;
 
 	if (wbc->for_reclaim) {
@@ -2701,7 +2706,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
 		goto recover_xnid;
 
 	/* 1: invalidate the previous xattr nid */
-	err = f2fs_get_node_info(sbi, prev_xnid, &ni);
+	err = f2fs_get_node_info(sbi, prev_xnid, &ni, false);
 	if (err)
 		return err;
 
@@ -2741,7 +2746,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
 	struct page *ipage;
 	int err;
 
-	err = f2fs_get_node_info(sbi, ino, &old_ni);
+	err = f2fs_get_node_info(sbi, ino, &old_ni, false);
 	if (err)
 		return err;
 

fs/f2fs/recovery.c

@@ -596,7 +596,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 	f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
 
-	err = f2fs_get_node_info(sbi, dn.nid, &ni);
+	err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
 	if (err)
 		goto err;
 

fs/f2fs/segment.c

@@ -253,7 +253,7 @@ static int __revoke_inmem_pages(struct inode *inode,
 				goto next;
 			}
 
-			err = f2fs_get_node_info(sbi, dn.nid, &ni);
+			err = f2fs_get_node_info(sbi, dn.nid, &ni, false);
 			if (err) {
 				f2fs_put_dnode(&dn);
 				return err;

fs/f2fs/segment.h

@@ -538,7 +538,8 @@ static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
 
 static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi)
 {
-	return SM_I(sbi)->reserved_segments;
+	return SM_I(sbi)->reserved_segments +
+			SM_I(sbi)->additional_reserved_segments;
 }
 
 static inline unsigned int free_sections(struct f2fs_sb_info *sbi)

fs/f2fs/super.c

@@ -59,6 +59,7 @@ const char *f2fs_fault_name[FAULT_MAX] = {
 	[FAULT_WRITE_IO]	= "write IO error",
 	[FAULT_SLAB_ALLOC]	= "slab alloc",
 	[FAULT_DQUOT_INIT]	= "dquot initialize",
+	[FAULT_LOCK_OP]		= "lock_op",
 };
 
 void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
@@ -321,6 +322,46 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
 					   F2FS_OPTION(sbi).s_resgid));
 }
 
+static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi)
+{
+	unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec;
+	unsigned int avg_vblocks;
+	unsigned int wanted_reserved_segments;
+	block_t avail_user_block_count;
+
+	if (!F2FS_IO_ALIGNED(sbi))
+		return 0;
+
+	/* average valid block count in section in worst case */
+	avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi);
+
+	/*
+	 * we need enough free space when migrating one section in worst case
+	 */
+	wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) *
+						reserved_segments(sbi);
+	wanted_reserved_segments -= reserved_segments(sbi);
+
+	avail_user_block_count = sbi->user_block_count -
+				sbi->current_reserved_blocks -
+				F2FS_OPTION(sbi).root_reserved_blocks;
+
+	if (wanted_reserved_segments * sbi->blocks_per_seg >
+					avail_user_block_count) {
+		f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u",
+			wanted_reserved_segments,
+			avail_user_block_count >> sbi->log_blocks_per_seg);
+		return -ENOSPC;
+	}
+
+	SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments;
+
+	f2fs_info(sbi, "IO align feature needs additional reserved segment: %u",
+			 wanted_reserved_segments);
+
+	return 0;
+}
+
 static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
 {
 	if (!F2FS_OPTION(sbi).unusable_cap_perc)
@@ -3540,6 +3581,7 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	sbi->seq_file_ra_mul = MIN_RA_MUL;
 	sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
 	sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
+	spin_lock_init(&sbi->gc_urgent_high_lock);
 
 	sbi->dir_level = DEF_DIR_LEVEL;
 	sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
@@ -4179,6 +4221,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_nm;
 	}
 
+	err = adjust_reserved_segment(sbi);
+	if (err)
+		goto free_nm;
+
 	/* For write statistics */
 	sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
 

fs/f2fs/sysfs.c

@@ -118,6 +118,15 @@ static ssize_t sb_status_show(struct f2fs_attr *a,
 	return sprintf(buf, "%lx\n", sbi->s_flag);
 }
 
+static ssize_t pending_discard_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	if (!SM_I(sbi)->dcc_info)
+		return -EINVAL;
+	return sprintf(buf, "%llu\n", (unsigned long long)atomic_read(
+				&SM_I(sbi)->dcc_info->discard_cmd_cnt));
+}
+
 static ssize_t features_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
@@ -414,7 +423,9 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 	if (a->struct_type == RESERVED_BLOCKS) {
 		spin_lock(&sbi->stat_lock);
 		if (t > (unsigned long)(sbi->user_block_count -
-				F2FS_OPTION(sbi).root_reserved_blocks)) {
+				F2FS_OPTION(sbi).root_reserved_blocks -
+				sbi->blocks_per_seg *
+				SM_I(sbi)->additional_reserved_segments)) {
 			spin_unlock(&sbi->stat_lock);
 			return -EINVAL;
 		}
@@ -477,6 +488,15 @@ static ssize_t __sbi_store(struct f2fs_attr *a,
 		return count;
 	}
 
+	if (!strcmp(a->attr.name, "gc_urgent_high_remaining")) {
+		spin_lock(&sbi->gc_urgent_high_lock);
+		sbi->gc_urgent_high_limited = t != 0;
+		sbi->gc_urgent_high_remaining = t;
+		spin_unlock(&sbi->gc_urgent_high_lock);
+
+		return count;
+	}
+
 #ifdef CONFIG_F2FS_IOSTAT
 	if (!strcmp(a->attr.name, "iostat_enable")) {
 		sbi->iostat_enable = !!t;
@@ -732,6 +752,7 @@ F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
 #endif
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, data_io_flag, data_io_flag);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, node_io_flag, node_io_flag);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent_high_remaining, gc_urgent_high_remaining);
 F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, ckpt_thread_ioprio, ckpt_thread_ioprio);
 F2FS_GENERAL_RO_ATTR(dirty_segments);
 F2FS_GENERAL_RO_ATTR(free_segments);
@@ -743,6 +764,7 @@ F2FS_GENERAL_RO_ATTR(unusable);
 F2FS_GENERAL_RO_ATTR(encoding);
 F2FS_GENERAL_RO_ATTR(mounted_time_sec);
 F2FS_GENERAL_RO_ATTR(main_blkaddr);
+F2FS_GENERAL_RO_ATTR(pending_discard);
 #ifdef CONFIG_F2FS_STAT_FS
 F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
 F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
@@ -811,6 +833,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(main_blkaddr),
 	ATTR_LIST(max_small_discards),
 	ATTR_LIST(discard_granularity),
+	ATTR_LIST(pending_discard),
 	ATTR_LIST(batched_trim_sections),
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
@@ -843,6 +866,7 @@ static struct attribute *f2fs_attrs[] = {
 #endif
 	ATTR_LIST(data_io_flag),
 	ATTR_LIST(node_io_flag),
+	ATTR_LIST(gc_urgent_high_remaining),
 	ATTR_LIST(ckpt_thread_ioprio),
 	ATTR_LIST(dirty_segments),
 	ATTR_LIST(free_segments),

fs/f2fs/xattr.c

@@ -226,15 +226,18 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int index)
 }
 
 static struct f2fs_xattr_entry *__find_xattr(void *base_addr,
-				void *last_base_addr, int index,
-				size_t len, const char *name)
+				void *last_base_addr, void **last_addr,
+				int index, size_t len, const char *name)
 {
 	struct f2fs_xattr_entry *entry;
 
 	list_for_each_xattr(entry, base_addr) {
 		if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
-			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr)
+			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+			if (last_addr)
+				*last_addr = entry;
 			return NULL;
+		}
 
 		if (entry->e_name_index != index)
 			continue;
@@ -254,19 +257,9 @@ static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode,
 	unsigned int inline_size = inline_xattr_size(inode);
 	void *max_addr = base_addr + inline_size;
 
-	list_for_each_xattr(entry, base_addr) {
-		if ((void *)entry + sizeof(__u32) > max_addr ||
-			(void *)XATTR_NEXT_ENTRY(entry) > max_addr) {
-			*last_addr = entry;
-			return NULL;
-		}
-		if (entry->e_name_index != index)
-			continue;
-		if (entry->e_name_len != len)
-			continue;
-		if (!memcmp(entry->e_name, name, len))
-			break;
-	}
+	entry = __find_xattr(base_addr, max_addr, last_addr, index, len, name);
+	if (!entry)
+		return NULL;
 
 	/* inline xattr header or entry across max inline xattr size */
 	if (IS_XATTR_LAST_ENTRY(entry) &&
@@ -368,7 +361,7 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
 	else
 		cur_addr = txattr_addr;
 
-	*xe = __find_xattr(cur_addr, last_txattr_addr, index, len, name);
+	*xe = __find_xattr(cur_addr, last_txattr_addr, NULL, index, len, name);
 	if (!*xe) {
 		f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
 								inode->i_ino);
@@ -659,7 +652,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	last_base_addr = (void *)base_addr + XATTR_SIZE(inode);
 
 	/* find entry with wanted name. */
-	here = __find_xattr(base_addr, last_base_addr, index, len, name);
+	here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name);
 	if (!here) {
 		f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
 								inode->i_ino);
@@ -684,8 +677,17 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	}
 
 	last = here;
-	while (!IS_XATTR_LAST_ENTRY(last))
+	while (!IS_XATTR_LAST_ENTRY(last)) {
+		if ((void *)(last) + sizeof(__u32) > last_base_addr ||
+			(void *)XATTR_NEXT_ENTRY(last) > last_base_addr) {
+			f2fs_err(F2FS_I_SB(inode), "inode (%lu) has invalid last xattr entry, entry_size: %zu",
+					inode->i_ino, ENTRY_SIZE(last));
+			set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+			error = -EFSCORRUPTED;
+			goto exit;
+		}
 		last = XATTR_NEXT_ENTRY(last);
+	}
 
 	newsize = XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + len + size);
 

include/trace/events/f2fs.h

@@ -540,17 +540,17 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
 
 TRACE_EVENT(f2fs_file_write_iter,
 
-	TP_PROTO(struct inode *inode, unsigned long offset,
-		unsigned long length, int ret),
+	TP_PROTO(struct inode *inode, loff_t offset, size_t length,
+		 ssize_t ret),
 
 	TP_ARGS(inode, offset, length, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(unsigned long, offset)
-		__field(unsigned long, length)
-		__field(int,	ret)
+		__field(loff_t, offset)
+		__field(size_t, length)
+		__field(ssize_t, ret)
 	),
 
 	TP_fast_assign(
@@ -562,7 +562,7 @@ TRACE_EVENT(f2fs_file_write_iter,
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, "
-		"offset = %lu, length = %lu, written(err) = %d",
+		"offset = %lld, length = %zu, written(err) = %zd",
 		show_dev_ino(__entry),
 		__entry->offset,
 		__entry->length,
@@ -936,14 +936,14 @@ TRACE_EVENT(f2fs_fallocate,
 
 TRACE_EVENT(f2fs_direct_IO_enter,
 
-	TP_PROTO(struct inode *inode, loff_t offset, unsigned long len, int rw),
+	TP_PROTO(struct inode *inode, struct kiocb *iocb, long len, int rw),
 
-	TP_ARGS(inode, offset, len, rw),
+	TP_ARGS(inode, iocb, len, rw),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(loff_t,	pos)
+		__field(struct kiocb *,	iocb)
 		__field(unsigned long,	len)
 		__field(int,	rw)
 	),
@@ -951,15 +951,18 @@ TRACE_EVENT(f2fs_direct_IO_enter,
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->ino	= inode->i_ino;
-		__entry->pos	= offset;
+		__entry->iocb	= iocb;
 		__entry->len	= len;
 		__entry->rw	= rw;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu rw = %d",
+	TP_printk("dev = (%d,%d), ino = %lu pos = %lld len = %lu ki_flags = %x ki_hint = %x ki_ioprio = %x rw = %d",
 		show_dev_ino(__entry),
-		__entry->pos,
+		__entry->iocb->ki_pos,
 		__entry->len,
+		__entry->iocb->ki_flags,
+		__entry->iocb->ki_hint,
+		__entry->iocb->ki_ioprio,
 		__entry->rw)
 );