Merge tag 'f2fs-for-6-6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "In this cycle, we don't have a highlighted feature enhancement, but
  mostly have fixed issues mainly in two parts: 1) zoned block device,
  and 2) compression support.

  For zoned block device, we've tried to improve the power-off recovery
  flow as much as possible. For compression, we found some corner cases
  caused by wrong compression policy and logics. Other than them, there
  were some reverts and stat corrections.

  Bug fixes:
   - use finish zone command when closing a zone
   - check zone type before sending async reset zone command
   - fix to assign compress_level for lz4 correctly
   - fix error path of f2fs_submit_page_read()
   - don't {,de}compress non-full cluster
   - send small discard commands during checkpoint back
   - flush inode if atomic file is aborted
   - correct to account gc/cp stats

  And, there are minor bug fixes, avoiding false lockdep warning, and
  clean-ups"

* tag 'f2fs-for-6-6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (25 commits)
  f2fs: use finish zone command when closing a zone
  f2fs: compress: fix to assign compress_level for lz4 correctly
  f2fs: fix error path of f2fs_submit_page_read()
  f2fs: clean up error handling in sanity_check_{compress_,}inode()
  f2fs: avoid false alarm of circular locking
  Revert "f2fs: do not issue small discard commands during checkpoint"
  f2fs: doc: fix description of max_small_discards
  f2fs: should update REQ_TIME for direct write
  f2fs: fix to account cp stats correctly
  f2fs: fix to account gc stats correctly
  f2fs: remove unneeded check condition in __f2fs_setxattr()
  f2fs: fix to update i_ctime in __f2fs_setxattr()
  Revert "f2fs: fix to do sanity check on extent cache correctly"
  f2fs: increase usage of folio_next_index() helper
  f2fs: Only lfs mode is allowed with zoned block device feature
  f2fs: check zone type before sending async reset zone command
  f2fs: compress: don't {,de}compress non-full cluster
  f2fs: allow f2fs_ioc_{,de}compress_file to be interrupted
  f2fs: don't reopen the main block device in f2fs_scan_devices
  f2fs: fix to avoid mmap vs set_compress_option case
  ...

Author: torvalds

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -102,9 +102,9 @@ What:		/sys/fs/f2fs/<disk>/max_small_discards
 Date:		November 2013
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
 Description:	Controls the issue rate of discard commands that consist of small
-		blocks less than 2MB. The candidates to be discarded are cached until
-		checkpoint is triggered, and issued during the checkpoint.
-		By default, it is disabled with 0.
+		blocks less than 2MB. The candidates to be discarded are cached during
+		checkpoint, and issued by issue_discard thread after checkpoint.
+		It is enabled by default.
 
 What:		/sys/fs/f2fs/<disk>/max_ordered_discard
 Date:		October 2022

fs/f2fs/checkpoint.c

@@ -1701,9 +1701,9 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	}
 
 	f2fs_restore_inmem_curseg(sbi);
+	stat_inc_cp_count(sbi);
 stop:
 	unblock_operations(sbi);
-	stat_inc_cp_count(sbi->stat_info);
 
 	if (cpc->reason & CP_RECOVERY)
 		f2fs_notice(sbi, "checkpoint: version = %llx", ckpt_ver);

fs/f2fs/compress.c

@@ -649,13 +649,8 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
 		goto destroy_compress_ctx;
 	}
 
-	for (i = 0; i < cc->nr_cpages; i++) {
+	for (i = 0; i < cc->nr_cpages; i++)
 		cc->cpages[i] = f2fs_compress_alloc_page();
-		if (!cc->cpages[i]) {
-			ret = -ENOMEM;
-			goto out_free_cpages;
-		}
-	}
 
 	cc->rbuf = f2fs_vmap(cc->rpages, cc->cluster_size);
 	if (!cc->rbuf) {
@@ -1574,8 +1569,6 @@ static int f2fs_prepare_decomp_mem(struct decompress_io_ctx *dic,
 		}
 
 		dic->tpages[i] = f2fs_compress_alloc_page();
-		if (!dic->tpages[i])
-			return -ENOMEM;
 	}
 
 	dic->rbuf = f2fs_vmap(dic->tpages, dic->cluster_size);
@@ -1656,11 +1649,6 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
 		struct page *page;
 
 		page = f2fs_compress_alloc_page();
-		if (!page) {
-			ret = -ENOMEM;
-			goto out_free;
-		}
-
 		f2fs_set_compressed_page(page, cc->inode,
 					start_idx + i + 1, dic);
 		dic->cpages[i] = page;

fs/f2fs/data.c

@@ -1167,6 +1167,9 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
 	f2fs_wait_on_block_writeback(inode, blkaddr);
 
 	if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+		iostat_update_and_unbind_ctx(bio);
+		if (bio->bi_private)
+			mempool_free(bio->bi_private, bio_post_read_ctx_pool);
 		bio_put(bio);
 		return -EFAULT;
 	}
@@ -1389,18 +1392,14 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
-repeat:
+
 	page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL);
 	if (IS_ERR(page))
 		return page;
 
 	/* wait for read completion */
 	lock_page(page);
-	if (unlikely(page->mapping != mapping)) {
-		f2fs_put_page(page, 1);
-		goto repeat;
-	}
-	if (unlikely(!PageUptodate(page))) {
+	if (unlikely(page->mapping != mapping || !PageUptodate(page))) {
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-EIO);
 	}
@@ -3236,8 +3235,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 					}
 					goto next;
 				}
-				done_index = folio->index +
-					folio_nr_pages(folio);
+				done_index = folio_next_index(folio);
 				done = 1;
 				break;
 			}

fs/f2fs/debug.c

@@ -215,6 +215,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->valid_blks[type] += blks;
 	}
 
+	for (i = 0; i < MAX_CALL_TYPE; i++)
+		si->cp_call_count[i] = atomic_read(&sbi->cp_call_count[i]);
+
 	for (i = 0; i < 2; i++) {
 		si->segment_count[i] = sbi->segment_count[i];
 		si->block_count[i] = sbi->block_count[i];
@@ -497,7 +500,9 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "  - Prefree: %d\n  - Free: %d (%d)\n\n",
 			   si->prefree_count, si->free_segs, si->free_secs);
 		seq_printf(s, "CP calls: %d (BG: %d)\n",
-				si->cp_count, si->bg_cp_count);
+			   si->cp_call_count[TOTAL_CALL],
+			   si->cp_call_count[BACKGROUND]);
+		seq_printf(s, "CP count: %d\n", si->cp_count);
 		seq_printf(s, "  - cp blocks : %u\n", si->meta_count[META_CP]);
 		seq_printf(s, "  - sit blocks : %u\n",
 				si->meta_count[META_SIT]);
@@ -511,12 +516,24 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "  - Total : %4d\n", si->nr_total_ckpt);
 		seq_printf(s, "  - Cur time : %4d(ms)\n", si->cur_ckpt_time);
 		seq_printf(s, "  - Peak time : %4d(ms)\n", si->peak_ckpt_time);
-		seq_printf(s, "GC calls: %d (BG: %d)\n",
-			   si->call_count, si->bg_gc);
-		seq_printf(s, "  - data segments : %d (%d)\n",
-				si->data_segs, si->bg_data_segs);
-		seq_printf(s, "  - node segments : %d (%d)\n",
-				si->node_segs, si->bg_node_segs);
+		seq_printf(s, "GC calls: %d (gc_thread: %d)\n",
+			   si->gc_call_count[BACKGROUND] +
+			   si->gc_call_count[FOREGROUND],
+			   si->gc_call_count[BACKGROUND]);
+		if (__is_large_section(sbi)) {
+			seq_printf(s, "  - data sections : %d (BG: %d)\n",
+					si->gc_secs[DATA][BG_GC] + si->gc_secs[DATA][FG_GC],
+					si->gc_secs[DATA][BG_GC]);
+			seq_printf(s, "  - node sections : %d (BG: %d)\n",
+					si->gc_secs[NODE][BG_GC] + si->gc_secs[NODE][FG_GC],
+					si->gc_secs[NODE][BG_GC]);
+		}
+		seq_printf(s, "  - data segments : %d (BG: %d)\n",
+				si->gc_segs[DATA][BG_GC] + si->gc_segs[DATA][FG_GC],
+				si->gc_segs[DATA][BG_GC]);
+		seq_printf(s, "  - node segments : %d (BG: %d)\n",
+				si->gc_segs[NODE][BG_GC] + si->gc_segs[NODE][FG_GC],
+				si->gc_segs[NODE][BG_GC]);
 		seq_puts(s, "  - Reclaimed segs :\n");
 		seq_printf(s, "    - Normal : %d\n", sbi->gc_reclaimed_segs[GC_NORMAL]);
 		seq_printf(s, "    - Idle CB : %d\n", sbi->gc_reclaimed_segs[GC_IDLE_CB]);
@@ -687,6 +704,8 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	atomic_set(&sbi->inplace_count, 0);
 	for (i = META_CP; i < META_MAX; i++)
 		atomic_set(&sbi->meta_count[i], 0);
+	for (i = 0; i < MAX_CALL_TYPE; i++)
+		atomic_set(&sbi->cp_call_count[i], 0);
 
 	atomic_set(&sbi->max_aw_cnt, 0);
 

fs/f2fs/f2fs.h

@@ -1383,6 +1383,13 @@ enum errors_option {
 	MOUNT_ERRORS_PANIC,	/* panic on errors */
 };
 
+enum {
+	BACKGROUND,
+	FOREGROUND,
+	MAX_CALL_TYPE,
+	TOTAL_CALL = FOREGROUND,
+};
+
 static inline int f2fs_test_bit(unsigned int nr, char *addr);
 static inline void f2fs_set_bit(unsigned int nr, char *addr);
 static inline void f2fs_clear_bit(unsigned int nr, char *addr);
@@ -1695,6 +1702,7 @@ struct f2fs_sb_info {
 	unsigned int io_skip_bggc;		/* skip background gc for in-flight IO */
 	unsigned int other_skip_bggc;		/* skip background gc for other reasons */
 	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
+	atomic_t cp_call_count[MAX_CALL_TYPE];	/* # of cp call */
 #endif
 	spinlock_t stat_lock;			/* lock for stat operations */
 
@@ -2114,15 +2122,6 @@ static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem)
 	return down_read_trylock(&sem->internal_rwsem);
 }
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
-{
-	down_read_nested(&sem->internal_rwsem, subclass);
-}
-#else
-#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
-#endif
-
 static inline void f2fs_up_read(struct f2fs_rwsem *sem)
 {
 	up_read(&sem->internal_rwsem);
@@ -2133,6 +2132,21 @@ static inline void f2fs_down_write(struct f2fs_rwsem *sem)
 	down_write(&sem->internal_rwsem);
 }
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
+{
+	down_read_nested(&sem->internal_rwsem, subclass);
+}
+
+static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass)
+{
+	down_write_nested(&sem->internal_rwsem, subclass);
+}
+#else
+#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
+#define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem)
+#endif
+
 static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem)
 {
 	return down_write_trylock(&sem->internal_rwsem);
@@ -3887,7 +3901,7 @@ struct f2fs_stat_info {
 	int nats, dirty_nats, sits, dirty_sits;
 	int free_nids, avail_nids, alloc_nids;
 	int total_count, utilization;
-	int bg_gc, nr_wb_cp_data, nr_wb_data;
+	int nr_wb_cp_data, nr_wb_data;
 	int nr_rd_data, nr_rd_node, nr_rd_meta;
 	int nr_dio_read, nr_dio_write;
 	unsigned int io_skip_bggc, other_skip_bggc;
@@ -3907,9 +3921,11 @@ struct f2fs_stat_info {
 	int rsvd_segs, overp_segs;
 	int dirty_count, node_pages, meta_pages, compress_pages;
 	int compress_page_hit;
-	int prefree_count, call_count, cp_count, bg_cp_count;
-	int tot_segs, node_segs, data_segs, free_segs, free_secs;
-	int bg_node_segs, bg_data_segs;
+	int prefree_count, free_segs, free_secs;
+	int cp_call_count[MAX_CALL_TYPE], cp_count;
+	int gc_call_count[MAX_CALL_TYPE];
+	int gc_segs[2][2];
+	int gc_secs[2][2];
 	int tot_blks, data_blks, node_blks;
 	int bg_data_blks, bg_node_blks;
 	int curseg[NR_CURSEG_TYPE];
@@ -3931,10 +3947,9 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 	return (struct f2fs_stat_info *)sbi->stat_info;
 }
 
-#define stat_inc_cp_count(si)		((si)->cp_count++)
-#define stat_inc_bg_cp_count(si)	((si)->bg_cp_count++)
-#define stat_inc_call_count(si)		((si)->call_count++)
-#define stat_inc_bggc_count(si)		((si)->bg_gc++)
+#define stat_inc_cp_call_count(sbi, foreground)				\
+		atomic_inc(&sbi->cp_call_count[(foreground)])
+#define stat_inc_cp_count(si)		(F2FS_STAT(sbi)->cp_count++)
 #define stat_io_skip_bggc_count(sbi)	((sbi)->io_skip_bggc++)
 #define stat_other_skip_bggc_count(sbi)	((sbi)->other_skip_bggc++)
 #define stat_inc_dirty_inode(sbi, type)	((sbi)->ndirty_inode[type]++)
@@ -4019,18 +4034,12 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		if (cur > max)						\
 			atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);	\
 	} while (0)
-#define stat_inc_seg_count(sbi, type, gc_type)				\
-	do {								\
-		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
-		si->tot_segs++;						\
-		if ((type) == SUM_TYPE_DATA) {				\
-			si->data_segs++;				\
-			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
-		} else {						\
-			si->node_segs++;				\
-			si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0;	\
-		}							\
-	} while (0)
+#define stat_inc_gc_call_count(sbi, foreground)				\
+		(F2FS_STAT(sbi)->gc_call_count[(foreground)]++)
+#define stat_inc_gc_sec_count(sbi, type, gc_type)			\
+		(F2FS_STAT(sbi)->gc_secs[(type)][(gc_type)]++)
+#define stat_inc_gc_seg_count(sbi, type, gc_type)			\
+		(F2FS_STAT(sbi)->gc_segs[(type)][(gc_type)]++)
 
 #define stat_inc_tot_blk_count(si, blks)				\
 	((si)->tot_blks += (blks))
@@ -4057,10 +4066,8 @@ void __init f2fs_create_root_stats(void);
 void f2fs_destroy_root_stats(void);
 void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
 #else
-#define stat_inc_cp_count(si)				do { } while (0)
-#define stat_inc_bg_cp_count(si)			do { } while (0)
-#define stat_inc_call_count(si)				do { } while (0)
-#define stat_inc_bggc_count(si)				do { } while (0)
+#define stat_inc_cp_call_count(sbi, foreground)		do { } while (0)
+#define stat_inc_cp_count(sbi)				do { } while (0)
 #define stat_io_skip_bggc_count(sbi)			do { } while (0)
 #define stat_other_skip_bggc_count(sbi)			do { } while (0)
 #define stat_inc_dirty_inode(sbi, type)			do { } while (0)
@@ -4088,7 +4095,9 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
 #define stat_inc_seg_type(sbi, curseg)			do { } while (0)
 #define stat_inc_block_count(sbi, curseg)		do { } while (0)
 #define stat_inc_inplace_blocks(sbi)			do { } while (0)
-#define stat_inc_seg_count(sbi, type, gc_type)		do { } while (0)
+#define stat_inc_gc_call_count(sbi, foreground)		do { } while (0)
+#define stat_inc_gc_sec_count(sbi, type, gc_type)	do { } while (0)
+#define stat_inc_gc_seg_count(sbi, type, gc_type)	do { } while (0)
 #define stat_inc_tot_blk_count(si, blks)		do { } while (0)
 #define stat_inc_data_blk_count(sbi, blks, gc_type)	do { } while (0)
 #define stat_inc_node_blk_count(sbi, blks, gc_type)	do { } while (0)
@@ -4425,6 +4434,22 @@ static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
 }
 #endif
 
+static inline int f2fs_bdev_index(struct f2fs_sb_info *sbi,
+				  struct block_device *bdev)
+{
+	int i;
+
+	if (!f2fs_is_multi_device(sbi))
+		return 0;
+
+	for (i = 0; i < sbi->s_ndevs; i++)
+		if (FDEV(i).bdev == bdev)
+			return i;
+
+	WARN_ON(1);
+	return -1;
+}
+
 static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi)
 {
 	return f2fs_sb_has_blkzoned(sbi);
@@ -4485,7 +4510,8 @@ static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi)
 static inline bool f2fs_may_compress(struct inode *inode)
 {
 	if (IS_SWAPFILE(inode) || f2fs_is_pinned_file(inode) ||
-		f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode))
+		f2fs_is_atomic_file(inode) || f2fs_has_inline_data(inode) ||
+		f2fs_is_mmap_file(inode))
 		return false;
 	return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
 }