1 files changed, 361 insertions, 174 deletions

diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index a77f76f528b6..07dcbcbeb7c6 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fs/f2fs/segment.h
  *
@@ -16,39 +16,23 @@
 #define DEF_MAX_RECLAIM_PREFREE_SEGMENTS	4096	/* 8GB in maximum */
 
 #define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
+#define F2FS_MIN_META_SEGMENTS	8 /* SB + 2 (CP + SIT + NAT) + SSA */
+
+#define INVALID_MTIME ULLONG_MAX /* no valid blocks in a segment/section */
 
 /* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	((segno) - (free_i)->start_segno)
 #define GET_R2L_SEGNO(free_i, segno)	((segno) + (free_i)->start_segno)
 
 #define IS_DATASEG(t)	((t) <= CURSEG_COLD_DATA)
-#define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE)
-
-#define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
-#define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
-#define IS_COLD(t)	((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
-
-#define IS_CURSEG(sbi, seg)						\
-	(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
-	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
-
-#define IS_CURSEC(sbi, secno)						\
-	(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
-	  (sbi)->segs_per_sec) ||	\
-	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
-	  (sbi)->segs_per_sec))	\
+#define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE && (t) <= CURSEG_COLD_NODE)
+#define SE_PAGETYPE(se)	((IS_NODESEG((se)->type) ? NODE : DATA))
+
+static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
+						unsigned short seg_type)
+{
+	f2fs_bug_on(sbi, seg_type >= NR_PERSISTENT_LOG);
+}
 
 #define MAIN_BLKADDR(sbi)						\
 	(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : 				\
@@ -63,41 +47,55 @@
 #define TOTAL_SEGS(sbi)							\
 	(SM_I(sbi) ? SM_I(sbi)->segment_count : 				\
 		le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
-#define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
+#define TOTAL_BLKS(sbi)	(SEGS_TO_BLKS(sbi, TOTAL_SEGS(sbi)))
 
 #define MAX_BLKADDR(sbi)	(SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
 #define SEGMENT_SIZE(sbi)	(1ULL << ((sbi)->log_blocksize +	\
 					(sbi)->log_blocks_per_seg))
 
 #define START_BLOCK(sbi, segno)	(SEG0_BLKADDR(sbi) +			\
-	 (GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
+	 (SEGS_TO_BLKS(sbi, GET_R2L_SEGNO(FREE_I(sbi), segno))))
 
 #define NEXT_FREE_BLKADDR(sbi, curseg)					\
 	(START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
 
 #define GET_SEGOFF_FROM_SEG0(sbi, blk_addr)	((blk_addr) - SEG0_BLKADDR(sbi))
 #define GET_SEGNO_FROM_SEG0(sbi, blk_addr)				\
-	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
+	(BLKS_TO_SEGS(sbi, GET_SEGOFF_FROM_SEG0(sbi, blk_addr)))
 #define GET_BLKOFF_FROM_SEG0(sbi, blk_addr)				\
-	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
+	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (BLKS_PER_SEG(sbi) - 1))
 
 #define GET_SEGNO(sbi, blk_addr)					\
-	((!is_valid_data_blkaddr(sbi, blk_addr)) ?			\
+	((!__is_valid_data_blkaddr(blk_addr)) ?			\
 	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
 		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
-#define BLKS_PER_SEC(sbi)					\
-	((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
+#ifdef CONFIG_BLK_DEV_ZONED
+#define CAP_BLKS_PER_SEC(sbi)					\
+	(BLKS_PER_SEC(sbi) - (sbi)->unusable_blocks_per_sec)
+#define CAP_SEGS_PER_SEC(sbi)					\
+	(SEGS_PER_SEC(sbi) -					\
+	BLKS_TO_SEGS(sbi, (sbi)->unusable_blocks_per_sec))
+#else
+#define CAP_BLKS_PER_SEC(sbi) BLKS_PER_SEC(sbi)
+#define CAP_SEGS_PER_SEC(sbi) SEGS_PER_SEC(sbi)
+#endif
+#define GET_START_SEG_FROM_SEC(sbi, segno)			\
+	(rounddown(segno, SEGS_PER_SEC(sbi)))
 #define GET_SEC_FROM_SEG(sbi, segno)				\
-	((segno) / (sbi)->segs_per_sec)
+	(((segno) == -1) ? -1 : (segno) / SEGS_PER_SEC(sbi))
 #define GET_SEG_FROM_SEC(sbi, secno)				\
-	((secno) * (sbi)->segs_per_sec)
+	((secno) * SEGS_PER_SEC(sbi))
 #define GET_ZONE_FROM_SEC(sbi, secno)				\
-	((secno) / (sbi)->secs_per_zone)
+	(((secno) == -1) ? -1 : (secno) / (sbi)->secs_per_zone)
 #define GET_ZONE_FROM_SEG(sbi, segno)				\
 	GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
 
-#define GET_SUM_BLOCK(sbi, segno)				\
-	((sbi)->sm_info->ssa_blkaddr + (segno))
+#define SUMS_PER_BLOCK (F2FS_BLKSIZE / F2FS_SUM_BLKSIZE)
+#define GET_SUM_BLOCK(sbi, segno)	\
+	(SM_I(sbi)->ssa_blkaddr + (segno / SUMS_PER_BLOCK))
+#define GET_SUM_BLKOFF(segno) (segno % SUMS_PER_BLOCK)
+#define SUM_BLK_PAGE_ADDR(folio, segno)	\
+	(folio_address(folio) + GET_SUM_BLKOFF(segno) * F2FS_SUM_BLKSIZE)
 
 #define GET_SUM_TYPE(footer) ((footer)->entry_type)
 #define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type))
@@ -109,7 +107,7 @@
 #define	START_SEGNO(segno)		\
 	(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
 #define SIT_BLK_CNT(sbi)			\
-	((MAIN_SEGS(sbi) + SIT_ENTRY_PER_BLOCK - 1) / SIT_ENTRY_PER_BLOCK)
+	DIV_ROUND_UP(MAIN_SEGS(sbi), SIT_ENTRY_PER_BLOCK)
 #define f2fs_bitmap_size(nr)			\
 	(BITS_TO_LONGS(nr) * sizeof(unsigned long))
 
@@ -119,33 +117,28 @@
 	((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
 
 /*
- * indicate a block allocation direction: RIGHT and LEFT.
- * RIGHT means allocating new sections towards the end of volume.
- * LEFT means the opposite direction.
- */
-enum {
-	ALLOC_RIGHT = 0,
-	ALLOC_LEFT
-};
-
-/*
- * In the victim_sel_policy->alloc_mode, there are two block allocation modes.
+ * In the victim_sel_policy->alloc_mode, there are three block allocation modes.
  * LFS writes data sequentially with cleaning operations.
  * SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
+ * AT_SSR (Age Threshold based Slack Space Recycle) merges fragments into
+ * fragmented segment which has similar aging degree.
  */
 enum {
 	LFS = 0,
-	SSR
+	SSR,
+	AT_SSR,
 };
 
 /*
- * In the victim_sel_policy->gc_mode, there are two gc, aka cleaning, modes.
+ * In the victim_sel_policy->gc_mode, there are three gc, aka cleaning, modes.
  * GC_CB is based on cost-benefit algorithm.
  * GC_GREEDY is based on greedy algorithm.
+ * GC_AT is based on age-threshold algorithm.
  */
 enum {
 	GC_CB = 0,
 	GC_GREEDY,
+	GC_AT,
 	ALLOC_NEXT,
 	FLUSH_DEVICE,
 	MAX_GC_POLICY,
@@ -154,24 +147,29 @@ enum {
 /*
  * BG_GC means the background cleaning job.
  * FG_GC means the on-demand cleaning job.
- * FORCE_FG_GC means on-demand cleaning job in background.
  */
 enum {
 	BG_GC = 0,
 	FG_GC,
-	FORCE_FG_GC,
 };
 
 /* for a function parameter to select a victim segment */
 struct victim_sel_policy {
 	int alloc_mode;			/* LFS or SSR */
 	int gc_mode;			/* GC_CB or GC_GREEDY */
-	unsigned long *dirty_segmap;	/* dirty segment bitmap */
-	unsigned int max_search;	/* maximum # of segments to search */
+	unsigned long *dirty_bitmap;	/* dirty segment/section bitmap */
+	unsigned int max_search;	/*
+					 * maximum # of segments/sections
+					 * to search
+					 */
 	unsigned int offset;		/* last scanned bitmap offset */
 	unsigned int ofs_unit;		/* bitmap search unit */
 	unsigned int min_cost;		/* minimum cost */
+	unsigned long long oldest_age;	/* oldest age of segments having the same min cost */
 	unsigned int min_segno;		/* segment # having min. cost */
+	unsigned long long age;		/* mtime of GCed section*/
+	unsigned long long age_threshold;/* age threshold */
+	bool one_time_gc;		/* one time GC */
 };
 
 struct seg_entry {
@@ -184,7 +182,7 @@ struct seg_entry {
 	unsigned char *cur_valid_map_mir;	/* mirror of current valid bitmap */
 #endif
 	/*
-	 * # of valid blocks and the validity bitmap stored in the the last
+	 * # of valid blocks and the validity bitmap stored in the last
 	 * checkpoint pack. This information is used by the SSR mode.
 	 */
 	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
@@ -194,41 +192,28 @@ struct seg_entry {
 
 struct sec_entry {
 	unsigned int valid_blocks;	/* # of valid blocks in a section */
+	unsigned int ckpt_valid_blocks; /* # of valid blocks last cp in a section */
 };
 
-struct segment_allocation {
-	void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
-};
-
-/*
- * this value is set in page as a private data which indicate that
- * the page is atomically written, and it is in inmem_pages list.
- */
-#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
-#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
-
-#define IS_ATOMIC_WRITTEN_PAGE(page)			\
-		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
-#define IS_DUMMY_WRITTEN_PAGE(page)			\
-		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
-
 #define MAX_SKIP_GC_COUNT			16
 
-struct inmem_pages {
+struct revoke_entry {
 	struct list_head list;
-	struct page *page;
 	block_t old_addr;		/* for revoking when fail to commit */
+	pgoff_t index;
 };
 
 struct sit_info {
-	const struct segment_allocation *s_ops;
-
 	block_t sit_base_addr;		/* start block address of SIT area */
 	block_t sit_blocks;		/* # of blocks used by SIT area */
 	block_t written_valid_blocks;	/* # of valid blocks in main area */
+	char *bitmap;			/* all bitmaps pointer */
 	char *sit_bitmap;		/* SIT bitmap pointer */
 #ifdef CONFIG_F2FS_CHECK_FS
 	char *sit_bitmap_mir;		/* SIT bitmap mirror */
+
+	/* bitmap of segments to be ignored by GC in case of errors */
+	unsigned long *invalid_segmap;
 #endif
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
@@ -245,6 +230,8 @@ struct sit_info {
 	unsigned long long mounted_time;	/* mount time */
 	unsigned long long min_mtime;		/* min. modification time */
 	unsigned long long max_mtime;		/* max. modification time */
+	unsigned long long dirty_min_mtime;	/* rerange candidates in GC_AT */
+	unsigned long long dirty_max_mtime;	/* rerange candidates in GC_AT */
 
 	unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
 };
@@ -272,17 +259,14 @@ enum dirty_type {
 };
 
 struct dirty_seglist_info {
-	const struct victim_selection *v_ops;	/* victim selction operation */
 	unsigned long *dirty_segmap[NR_DIRTY_TYPE];
+	unsigned long *dirty_secmap;
 	struct mutex seglist_lock;		/* lock for segment bitmaps */
 	int nr_dirty[NR_DIRTY_TYPE];		/* # of dirty segments */
 	unsigned long *victim_secmap;		/* background GC victims */
-};
-
-/* victim selection function for cleaning and SSR */
-struct victim_selection {
-	int (*get_victim)(struct f2fs_sb_info *, unsigned int *,
-							int, int, char);
+	unsigned long *pinned_secmap;		/* pinned victims from foreground GC */
+	unsigned int pinned_secmap_cnt;		/* count of victims which has pinned data */
+	bool enable_pin_section;		/* enable pinning section */
 };
 
 /* for active log information */
@@ -292,10 +276,13 @@ struct curseg_info {
 	struct rw_semaphore journal_rwsem;	/* protect journal area */
 	struct f2fs_journal *journal;		/* cached journal info */
 	unsigned char alloc_type;		/* current allocation type */
+	unsigned short seg_type;		/* segment type like CURSEG_XXX_TYPE */
 	unsigned int segno;			/* current segment number */
 	unsigned short next_blkoff;		/* next block offset to write */
 	unsigned int zone;			/* current zone number */
 	unsigned int next_segno;		/* preallocated segment */
+	int fragment_remained_chunk;		/* remained block size in a chunk for block fragmentation mode */
+	bool inited;				/* indicate inmem log is inited */
 };
 
 struct sit_entry_set {
@@ -312,6 +299,28 @@ static inline struct curseg_info *CURSEG_I(struct f2fs_sb_info *sbi, int type)
 	return (struct curseg_info *)(SM_I(sbi)->curseg_array + type);
 }
 
+static inline bool is_curseg(struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	int i;
+
+	for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
+		if (segno == CURSEG_I(sbi, i)->segno)
+			return true;
+	}
+	return false;
+}
+
+static inline bool is_cursec(struct f2fs_sb_info *sbi, unsigned int secno)
+{
+	int i;
+
+	for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) {
+		if (secno == GET_SEC_FROM_SEG(sbi, CURSEG_I(sbi, i)->segno))
+			return true;
+	}
+	return false;
+}
+
 static inline struct seg_entry *get_seg_entry(struct f2fs_sb_info *sbi,
 						unsigned int segno)
 {
@@ -340,11 +349,59 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
 }
 
 static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
-				unsigned int segno)
+				unsigned int segno, bool use_section)
+{
+	if (use_section && __is_large_section(sbi))
+		return get_sec_entry(sbi, segno)->ckpt_valid_blocks;
+	else
+		return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+}
+
+static inline void set_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
+		unsigned int segno)
 {
-	return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
+	unsigned int blocks = 0;
+	int i;
+
+	for (i = 0; i < SEGS_PER_SEC(sbi); i++, start_segno++) {
+		struct seg_entry *se = get_seg_entry(sbi, start_segno);
+
+		blocks += se->ckpt_valid_blocks;
+	}
+	get_sec_entry(sbi, segno)->ckpt_valid_blocks = blocks;
 }
 
+#ifdef CONFIG_F2FS_CHECK_FS
+static inline void sanity_check_valid_blocks(struct f2fs_sb_info *sbi,
+		unsigned int segno)
+{
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
+	unsigned int blocks = 0;
+	int i;
+
+	for (i = 0; i < SEGS_PER_SEC(sbi); i++, start_segno++) {
+		struct seg_entry *se = get_seg_entry(sbi, start_segno);
+
+		blocks += se->ckpt_valid_blocks;
+	}
+
+	if (blocks != get_sec_entry(sbi, segno)->ckpt_valid_blocks) {
+		f2fs_err(sbi,
+			"Inconsistent ckpt valid blocks: "
+			"seg entry(%d) vs sec entry(%d) at secno %d",
+			blocks, get_sec_entry(sbi, segno)->ckpt_valid_blocks, secno);
+		f2fs_bug_on(sbi, 1);
+	}
+}
+#else
+static inline void sanity_check_valid_blocks(struct f2fs_sb_info *sbi,
+			unsigned int segno)
+{
+}
+#endif
 static inline void seg_info_from_raw_sit(struct seg_entry *se,
 					struct f2fs_sit_entry *rs)
 {
@@ -369,8 +426,8 @@ static inline void __seg_info_to_raw_sit(struct seg_entry *se,
 	rs->mtime = cpu_to_le64(se->mtime);
 }
 
-static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
-				struct page *page, unsigned int start)
+static inline void seg_info_to_sit_folio(struct f2fs_sb_info *sbi,
+				struct folio *folio, unsigned int start)
 {
 	struct f2fs_sit_block *raw_sit;
 	struct seg_entry *se;
@@ -379,7 +436,7 @@ static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi,
 					(unsigned long)MAIN_SEGS(sbi));
 	int i;
 
-	raw_sit = (struct f2fs_sit_block *)page_address(page);
+	raw_sit = folio_address(folio);
 	memset(raw_sit, 0, PAGE_SIZE);
 	for (i = 0; i < end - start; i++) {
 		rs = &raw_sit->entries[i];
@@ -419,8 +476,8 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	free_i->free_segments++;
 
 	next = find_next_bit(free_i->free_segmap,
-			start_segno + sbi->segs_per_sec, start_segno);
-	if (next >= start_segno + sbi->segs_per_sec) {
+			start_segno + SEGS_PER_SEC(sbi), start_segno);
+	if (next >= start_segno + f2fs_usable_segs_in_sec(sbi)) {
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
@@ -440,27 +497,42 @@ static inline void __set_inuse(struct f2fs_sb_info *sbi,
 }
 
 static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
-		unsigned int segno)
+		unsigned int segno, bool inmem)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
 	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
+	bool ret;
 
 	spin_lock(&free_i->segmap_lock);
-	if (test_and_clear_bit(segno, free_i->free_segmap)) {
-		free_i->free_segments++;
-
-		if (IS_CURSEC(sbi, secno))
-			goto skip_free;
-		next = find_next_bit(free_i->free_segmap,
-				start_segno + sbi->segs_per_sec, start_segno);
-		if (next >= start_segno + sbi->segs_per_sec) {
-			if (test_and_clear_bit(secno, free_i->free_secmap))
-				free_i->free_sections++;
-		}
-	}
-skip_free:
+	ret = test_and_clear_bit(segno, free_i->free_segmap);
+	if (!ret)
+		goto unlock_out;
+
+	free_i->free_segments++;
+
+	if (!inmem && is_cursec(sbi, secno))
+		goto unlock_out;
+
+	/* check large section */
+	next = find_next_bit(free_i->free_segmap,
+			     start_segno + SEGS_PER_SEC(sbi), start_segno);
+	if (next < start_segno + f2fs_usable_segs_in_sec(sbi))
+		goto unlock_out;
+
+	ret = test_and_clear_bit(secno, free_i->free_secmap);
+	if (!ret)
+		goto unlock_out;
+
+	free_i->free_sections++;
+
+	if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[BG_GC]) == secno)
+		sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
+	if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[FG_GC]) == secno)
+		sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
+
+unlock_out:
 	spin_unlock(&free_i->segmap_lock);
 }
 
@@ -502,7 +574,7 @@ static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
 	return FREE_I(sbi)->free_segments;
 }
 
-static inline int reserved_segments(struct f2fs_sb_info *sbi)
+static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi)
 {
 	return SM_I(sbi)->reserved_segments;
 }
@@ -534,61 +606,145 @@ static inline int overprovision_segments(struct f2fs_sb_info *sbi)
 
 static inline int reserved_sections(struct f2fs_sb_info *sbi)
 {
-	return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
+	return GET_SEC_FROM_SEG(sbi, reserved_segments(sbi));
+}
+
+static inline unsigned int get_left_section_blocks(struct f2fs_sb_info *sbi,
+					enum log_type type, unsigned int segno)
+{
+	if (f2fs_lfs_mode(sbi)) {
+		unsigned int used_blocks = __is_large_section(sbi) ? SEGS_TO_BLKS(sbi,
+				(segno - GET_START_SEG_FROM_SEC(sbi, segno))) : 0;
+		return CAP_BLKS_PER_SEC(sbi) - used_blocks -
+			CURSEG_I(sbi, type)->next_blkoff;
+	}
+	return CAP_BLKS_PER_SEC(sbi) - get_ckpt_valid_blocks(sbi, segno, true);
 }
 
-static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi)
+static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
+			unsigned int node_blocks, unsigned int data_blocks,
+			unsigned int dent_blocks)
 {
-	unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
-					get_pages(sbi, F2FS_DIRTY_DENTS);
-	unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
-	unsigned int segno, left_blocks;
+	unsigned int segno, left_blocks, blocks;
 	int i;
 
-	/* check current node segment */
-	for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
+	/* check current data/node sections in the worst case. */
+	for (i = CURSEG_HOT_DATA; i < NR_PERSISTENT_LOG; i++) {
 		segno = CURSEG_I(sbi, i)->segno;
-		left_blocks = sbi->blocks_per_seg -
-			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
 
-		if (node_blocks > left_blocks)
+		if (unlikely(segno == NULL_SEGNO))
+			return false;
+
+		left_blocks = get_left_section_blocks(sbi, i, segno);
+
+		blocks = i <= CURSEG_COLD_DATA ? data_blocks : node_blocks;
+		if (blocks > left_blocks)
 			return false;
 	}
 
-	/* check current data segment */
+	/* check current data section for dentry blocks. */
 	segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
-	left_blocks = sbi->blocks_per_seg -
-			get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+
+	if (unlikely(segno == NULL_SEGNO))
+		return false;
+
+	left_blocks = get_left_section_blocks(sbi, CURSEG_HOT_DATA, segno);
+
 	if (dent_blocks > left_blocks)
 		return false;
 	return true;
 }
 
+/*
+ * calculate needed sections for dirty node/dentry and call
+ * has_curseg_enough_space, please note that, it needs to account
+ * dirty data as well in lfs mode when checkpoint is disabled.
+ */
+static inline void __get_secs_required(struct f2fs_sb_info *sbi,
+		unsigned int *lower_p, unsigned int *upper_p, bool *curseg_p)
+{
+	unsigned int total_node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) +
+					get_pages(sbi, F2FS_DIRTY_DENTS) +
+					get_pages(sbi, F2FS_DIRTY_IMETA);
+	unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+	unsigned int total_data_blocks = 0;
+	unsigned int node_secs = total_node_blocks / CAP_BLKS_PER_SEC(sbi);
+	unsigned int dent_secs = total_dent_blocks / CAP_BLKS_PER_SEC(sbi);
+	unsigned int data_secs = 0;
+	unsigned int node_blocks = total_node_blocks % CAP_BLKS_PER_SEC(sbi);
+	unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi);
+	unsigned int data_blocks = 0;
+
+	if (f2fs_lfs_mode(sbi)) {
+		total_data_blocks = get_pages(sbi, F2FS_DIRTY_DATA);
+		data_secs = total_data_blocks / CAP_BLKS_PER_SEC(sbi);
+		data_blocks = total_data_blocks % CAP_BLKS_PER_SEC(sbi);
+	}
+
+	if (lower_p)
+		*lower_p = node_secs + dent_secs + data_secs;
+	if (upper_p)
+		*upper_p = node_secs + dent_secs + data_secs +
+			(node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0) +
+			(data_blocks ? 1 : 0);
+	if (curseg_p)
+		*curseg_p = has_curseg_enough_space(sbi,
+				node_blocks, data_blocks, dent_blocks);
+}
+
 static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
 					int freed, int needed)
 {
-	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
-	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
-	int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+	unsigned int free_secs, lower_secs, upper_secs;
+	bool curseg_space;
 
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
-	if (free_sections(sbi) + freed == reserved_sections(sbi) + needed &&
-			has_curseg_enough_space(sbi))
+	__get_secs_required(sbi, &lower_secs, &upper_secs, &curseg_space);
+
+	free_secs = free_sections(sbi) + freed;
+	lower_secs += needed + reserved_sections(sbi);
+	upper_secs += needed + reserved_sections(sbi);
+
+	if (free_secs > upper_secs)
 		return false;
-	return (free_sections(sbi) + freed) <=
-		(node_secs + 2 * dent_secs + imeta_secs +
-		reserved_sections(sbi) + needed);
+	if (free_secs <= lower_secs)
+		return true;
+	return !curseg_space;
 }
 
-static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
+static inline bool has_enough_free_secs(struct f2fs_sb_info *sbi,
+					int freed, int needed)
+{
+	return !has_not_enough_free_secs(sbi, freed, needed);
+}
+
+static inline bool has_enough_free_blks(struct f2fs_sb_info *sbi)
+{
+	unsigned int total_free_blocks = 0;
+	unsigned int avail_user_block_count;
+
+	spin_lock(&sbi->stat_lock);
+
+	avail_user_block_count = get_available_block_count(sbi, NULL, true);
+	total_free_blocks = avail_user_block_count - (unsigned int)valid_user_blocks(sbi);
+
+	spin_unlock(&sbi->stat_lock);
+
+	return total_free_blocks > 0;
+}
+
+static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
 {
 	if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
-		return 0;
-	if (likely(!has_not_enough_free_secs(sbi, 0, 0)))
-		return 0;
-	return -ENOSPC;
+		return true;
+	if (likely(has_enough_free_secs(sbi, 0, 0)))
+		return true;
+	if (!f2fs_lfs_mode(sbi) &&
+		likely(has_enough_free_blks(sbi)))
+		return true;
+	return false;
 }
 
 static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
@@ -613,8 +769,12 @@ static inline int utilization(struct f2fs_sb_info *sbi)
  *                     threashold,
  * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
  *                     storages. IPU will be triggered only if the # of dirty
- *                     pages over min_fsync_blocks.
- * F2FS_IPUT_DISABLE - disable IPU. (=default option)
+ *                     pages over min_fsync_blocks. (=default option)
+ * F2FS_IPU_ASYNC - do IPU given by asynchronous write requests.
+ * F2FS_IPU_NOCACHE - disable IPU bio cache.
+ * F2FS_IPU_HONOR_OPU_WRITE - use OPU write prior to IPU write if inode has
+ *                            FI_OPU_WRITE flag.
+ * F2FS_IPU_DISABLE - disable IPU. (=default option in LFS mode)
  */
 #define DEF_MIN_IPU_UTIL	70
 #define DEF_MIN_FSYNC_BLOCKS	8
@@ -622,6 +782,9 @@ static inline int utilization(struct f2fs_sb_info *sbi)
 
 #define SMALL_VOLUME_SEGMENTS	(16 * 512)	/* 16GB */
 
+#define F2FS_IPU_DISABLE	0
+
+/* Modification on enum should be synchronized with ipu_mode_names array */
 enum {
 	F2FS_IPU_FORCE,
 	F2FS_IPU_SSR,
@@ -629,8 +792,31 @@ enum {
 	F2FS_IPU_SSR_UTIL,
 	F2FS_IPU_FSYNC,
 	F2FS_IPU_ASYNC,
+	F2FS_IPU_NOCACHE,
+	F2FS_IPU_HONOR_OPU_WRITE,
+	F2FS_IPU_MAX,
 };
 
+static inline bool IS_F2FS_IPU_DISABLE(struct f2fs_sb_info *sbi)
+{
+	return SM_I(sbi)->ipu_policy == F2FS_IPU_DISABLE;
+}
+
+#define F2FS_IPU_POLICY(name)					\
+static inline bool IS_##name(struct f2fs_sb_info *sbi)		\
+{								\
+	return SM_I(sbi)->ipu_policy & BIT(name);		\
+}
+
+F2FS_IPU_POLICY(F2FS_IPU_FORCE);
+F2FS_IPU_POLICY(F2FS_IPU_SSR);
+F2FS_IPU_POLICY(F2FS_IPU_UTIL);
+F2FS_IPU_POLICY(F2FS_IPU_SSR_UTIL);
+F2FS_IPU_POLICY(F2FS_IPU_FSYNC);
+F2FS_IPU_POLICY(F2FS_IPU_ASYNC);
+F2FS_IPU_POLICY(F2FS_IPU_NOCACHE);
+F2FS_IPU_POLICY(F2FS_IPU_HONOR_OPU_WRITE);
+
 static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi,
 		int type)
 {
@@ -645,25 +831,21 @@ static inline unsigned char curseg_alloc_type(struct f2fs_sb_info *sbi,
 	return curseg->alloc_type;
 }
 
-static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
-{
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	return curseg->next_blkoff;
-}
-
-static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
+static inline bool valid_main_segno(struct f2fs_sb_info *sbi,
+		unsigned int segno)
 {
-	f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
+	return segno <= (MAIN_SEGS(sbi) - 1);
 }
 
-static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
+static inline void verify_fio_blkaddr(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 
-	if (__is_meta_io(fio))
-		verify_blkaddr(sbi, blk_addr, META_GENERIC);
-	else
-		verify_blkaddr(sbi, blk_addr, DATA_GENERIC);
+	if (__is_valid_data_blkaddr(fio->old_blkaddr))
+		verify_blkaddr(sbi, fio->old_blkaddr, __is_meta_io(fio) ?
+					META_GENERIC : DATA_GENERIC);
+	verify_blkaddr(sbi, fio->new_blkaddr, __is_meta_io(fio) ?
+					META_GENERIC : DATA_GENERIC_ENHANCE);
 }
 
 /*
@@ -672,42 +854,47 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
 static inline int check_block_count(struct f2fs_sb_info *sbi,
 		int segno, struct f2fs_sit_entry *raw_sit)
 {
-#ifdef CONFIG_F2FS_CHECK_FS
 	bool is_valid  = test_bit_le(0, raw_sit->valid_map) ? true : false;
 	int valid_blocks = 0;
 	int cur_pos = 0, next_pos;
+	unsigned int usable_blks_per_seg = f2fs_usable_blks_in_seg(sbi, segno);
 
 	/* check bitmap with valid block count */
 	do {
 		if (is_valid) {
 			next_pos = find_next_zero_bit_le(&raw_sit->valid_map,
-					sbi->blocks_per_seg,
+					usable_blks_per_seg,
 					cur_pos);
 			valid_blocks += next_pos - cur_pos;
 		} else
 			next_pos = find_next_bit_le(&raw_sit->valid_map,
-					sbi->blocks_per_seg,
+					usable_blks_per_seg,
 					cur_pos);
 		cur_pos = next_pos;
 		is_valid = !is_valid;
-	} while (cur_pos < sbi->blocks_per_seg);
+	} while (cur_pos < usable_blks_per_seg);
 
 	if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
-		f2fs_msg(sbi->sb, KERN_ERR,
-				"Mismatch valid blocks %d vs. %d",
-					GET_SIT_VBLOCKS(raw_sit), valid_blocks);
+		f2fs_err(sbi, "Mismatch valid blocks %d vs. %d",
+			 GET_SIT_VBLOCKS(raw_sit), valid_blocks);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		return -EINVAL;
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_SIT);
+		return -EFSCORRUPTED;
 	}
-#endif
+
+	if (usable_blks_per_seg < BLKS_PER_SEG(sbi))
+		f2fs_bug_on(sbi, find_next_bit_le(&raw_sit->valid_map,
+				BLKS_PER_SEG(sbi),
+				usable_blks_per_seg) != BLKS_PER_SEG(sbi));
+
 	/* check segment usage, and check boundary of a given segment number */
-	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
-					|| segno > TOTAL_SEGS(sbi) - 1)) {
-		f2fs_msg(sbi->sb, KERN_ERR,
-				"Wrong valid blocks %d or segno %u",
-					GET_SIT_VBLOCKS(raw_sit), segno);
+	if (unlikely(GET_SIT_VBLOCKS(raw_sit) > usable_blks_per_seg
+					|| !valid_main_segno(sbi, segno))) {
+		f2fs_err(sbi, "Wrong valid blocks %d or segno %u",
+			 GET_SIT_VBLOCKS(raw_sit), segno);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		return -EINVAL;
+		f2fs_handle_error(sbi, ERROR_INCONSISTENT_SIT);
+		return -EFSCORRUPTED;
 	}
 	return 0;
 }
@@ -719,7 +906,7 @@ static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
 	unsigned int offset = SIT_BLOCK_OFFSET(start);
 	block_t blk_addr = sit_i->sit_base_addr + offset;
 
-	check_seg_range(sbi, start);
+	f2fs_bug_on(sbi, !valid_main_segno(sbi, start));
 
 #ifdef CONFIG_F2FS_CHECK_FS
 	if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
@@ -761,7 +948,7 @@ static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi,
 						bool base_time)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	time64_t diff, now = ktime_get_real_seconds();
+	time64_t diff, now = ktime_get_boottime_seconds();
 
 	if (now >= sit_i->mounted_time)
 		return sit_i->elapsed_time + now - sit_i->mounted_time;
@@ -799,7 +986,7 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
 
 static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
 {
-	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
+	if (is_cursec(sbi, secno) || (sbi->cur_victim_sec == secno))
 		return true;
 	return false;
 }
@@ -817,11 +1004,11 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 		return 0;
 
 	if (type == DATA)
-		return sbi->blocks_per_seg;
+		return BLKS_PER_SEG(sbi);
 	else if (type == NODE)
-		return 8 * sbi->blocks_per_seg;
+		return SEGS_TO_BLKS(sbi, 8);
 	else if (type == META)
-		return 8 * BIO_MAX_PAGES;
+		return 8 * BIO_MAX_VECS;
 	else
 		return 0;
 }
@@ -838,7 +1025,7 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
 		return 0;
 
 	nr_to_write = wbc->nr_to_write;
-	desired = BIO_MAX_PAGES;
+	desired = BIO_MAX_VECS;
 	if (type == NODE)
 		desired <<= 1;
 
@@ -865,9 +1052,9 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
 		}
 	}
 	mutex_unlock(&dcc->cmd_lock);
-	if (!wakeup)
+	if (!wakeup || !is_idle(sbi, DISCARD_TIME))
 		return;
 wake_up:
-	dcc->discard_wake = 1;
+	dcc->discard_wake = true;
 	wake_up_interruptible_all(&dcc->discard_wait_queue);
 }