1 files changed, 429 insertions, 99 deletions

diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a65d357f89a9..1596502f7375 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -189,7 +189,7 @@ void f2fs_register_inmem_page(struct inode *inode, struct page *page)
 
 	f2fs_trace_pid(page);
 
-	f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
+	f2fs_set_page_private(page, ATOMIC_WRITTEN_PAGE);
 
 	new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
 
@@ -728,7 +728,7 @@ init_thread:
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
 		err = PTR_ERR(fcc->f2fs_issue_flush);
-		kvfree(fcc);
+		kfree(fcc);
 		SM_I(sbi)->fcc_info = NULL;
 		return err;
 	}
@@ -747,7 +747,7 @@ void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 		kthread_stop(flush_thread);
 	}
 	if (free) {
-		kvfree(fcc);
+		kfree(fcc);
 		SM_I(sbi)->fcc_info = NULL;
 	}
 }
@@ -759,6 +759,9 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
 	if (!f2fs_is_multi_device(sbi))
 		return 0;
 
+	if (test_opt(sbi, NOBARRIER))
+		return 0;
+
 	for (i = 1; i < sbi->s_ndevs; i++) {
 		if (!f2fs_test_bit(i, (char *)&sbi->dirty_device))
 			continue;
@@ -799,7 +802,7 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 
 		if (__is_large_section(sbi)) {
 			unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
-			unsigned short valid_blocks =
+			block_t valid_blocks =
 				get_valid_blocks(sbi, segno, true);
 
 			f2fs_bug_on(sbi, unlikely(!valid_blocks ||
@@ -815,7 +818,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 		enum dirty_type dirty_type)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	unsigned short valid_blocks;
+	block_t valid_blocks;
 
 	if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
 		dirty_i->nr_dirty[dirty_type]--;
@@ -859,20 +862,22 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned short valid_blocks, ckpt_valid_blocks;
+	unsigned int usable_blocks;
 
 	if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno))
 		return;
 
+	usable_blocks = f2fs_usable_blks_in_seg(sbi, segno);
 	mutex_lock(&dirty_i->seglist_lock);
 
 	valid_blocks = get_valid_blocks(sbi, segno, false);
 	ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno);
 
 	if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) ||
-				ckpt_valid_blocks == sbi->blocks_per_seg)) {
+		ckpt_valid_blocks == usable_blocks)) {
 		__locate_dirty_segment(sbi, segno, PRE);
 		__remove_dirty_segment(sbi, segno, DIRTY);
-	} else if (valid_blocks < sbi->blocks_per_seg) {
+	} else if (valid_blocks < usable_blocks) {
 		__locate_dirty_segment(sbi, segno, DIRTY);
 	} else {
 		/* Recovery routine with SSR needs this */
@@ -915,9 +920,11 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)
 	for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) {
 		se = get_seg_entry(sbi, segno);
 		if (IS_NODESEG(se->type))
-			holes[NODE] += sbi->blocks_per_seg - se->valid_blocks;
+			holes[NODE] += f2fs_usable_blks_in_seg(sbi, segno) -
+							se->valid_blocks;
 		else
-			holes[DATA] += sbi->blocks_per_seg - se->valid_blocks;
+			holes[DATA] += f2fs_usable_blks_in_seg(sbi, segno) -
+							se->valid_blocks;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
@@ -1521,7 +1528,7 @@ retry:
 			goto next;
 		if (unlikely(dcc->rbtree_check))
 			f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
-								&dcc->root));
+							&dcc->root, false));
 		blk_start_plug(&plug);
 		list_for_each_entry_safe(dc, tmp, pend_list, list) {
 			f2fs_bug_on(sbi, dc->state != D_PREP);
@@ -1958,7 +1965,7 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
 
 	mutex_lock(&dirty_i->seglist_lock);
 	for_each_set_bit(segno, dirty_i->dirty_segmap[PRE], MAIN_SEGS(sbi))
-		__set_test_and_free(sbi, segno);
+		__set_test_and_free(sbi, segno, false);
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
@@ -2101,7 +2108,7 @@ init_thread:
 				"f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(dcc->f2fs_issue_discard)) {
 		err = PTR_ERR(dcc->f2fs_issue_discard);
-		kvfree(dcc);
+		kfree(dcc);
 		SM_I(sbi)->dcc_info = NULL;
 		return err;
 	}
@@ -2125,7 +2132,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
 	if (unlikely(atomic_read(&dcc->discard_cmd_cnt)))
 		f2fs_issue_discard_timeout(sbi);
 
-	kvfree(dcc);
+	kfree(dcc);
 	SM_I(sbi)->dcc_info = NULL;
 }
 
@@ -2150,6 +2157,39 @@ static void __set_sit_entry_type(struct f2fs_sb_info *sbi, int type,
 		__mark_sit_entry_dirty(sbi, segno);
 }
 
+static inline unsigned long long get_segment_mtime(struct f2fs_sb_info *sbi,
+								block_t blkaddr)
+{
+	unsigned int segno = GET_SEGNO(sbi, blkaddr);
+
+	if (segno == NULL_SEGNO)
+		return 0;
+	return get_seg_entry(sbi, segno)->mtime;
+}
+
+static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr,
+						unsigned long long old_mtime)
+{
+	struct seg_entry *se;
+	unsigned int segno = GET_SEGNO(sbi, blkaddr);
+	unsigned long long ctime = get_mtime(sbi, false);
+	unsigned long long mtime = old_mtime ? old_mtime : ctime;
+
+	if (segno == NULL_SEGNO)
+		return;
+
+	se = get_seg_entry(sbi, segno);
+
+	if (!se->mtime)
+		se->mtime = mtime;
+	else
+		se->mtime = div_u64(se->mtime * se->valid_blocks + mtime,
+						se->valid_blocks + 1);
+
+	if (ctime > SIT_I(sbi)->max_mtime)
+		SIT_I(sbi)->max_mtime = ctime;
+}
+
 static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 {
 	struct seg_entry *se;
@@ -2167,12 +2207,9 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
 
 	f2fs_bug_on(sbi, (new_vblocks < 0 ||
-				(new_vblocks > sbi->blocks_per_seg)));
+			(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
 
 	se->valid_blocks = new_vblocks;
-	se->mtime = get_mtime(sbi, false);
-	if (se->mtime > SIT_I(sbi)->max_mtime)
-		SIT_I(sbi)->max_mtime = se->mtime;
 
 	/* Update valid block bitmap */
 	if (del > 0) {
@@ -2265,6 +2302,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
 	/* add it into sit main buffer */
 	down_write(&sit_i->sentry_lock);
 
+	update_segment_mtime(sbi, addr, 0);
 	update_sit_entry(sbi, addr, -1);
 
 	/* add it into dirty seglist */
@@ -2344,7 +2382,9 @@ int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
  */
 struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
 {
-	return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
+	if (unlikely(f2fs_cp_error(sbi)))
+		return ERR_PTR(-EIO);
+	return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno));
 }
 
 void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
@@ -2389,9 +2429,9 @@ static void write_current_sum_page(struct f2fs_sb_info *sbi,
 	f2fs_put_page(page, 1);
 }
 
-static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
+static int is_next_segment_free(struct f2fs_sb_info *sbi,
+				struct curseg_info *curseg, int type)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	unsigned int segno = curseg->segno + 1;
 	struct free_segmap_info *free_i = FREE_I(sbi);
 
@@ -2495,7 +2535,9 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	struct summary_footer *sum_footer;
+	unsigned short seg_type = curseg->seg_type;
 
+	curseg->inited = true;
 	curseg->segno = curseg->next_segno;
 	curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
 	curseg->next_blkoff = 0;
@@ -2503,24 +2545,36 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
 
 	sum_footer = &(curseg->sum_blk->footer);
 	memset(sum_footer, 0, sizeof(struct summary_footer));
-	if (IS_DATASEG(type))
+
+	sanity_check_seg_type(sbi, seg_type);
+
+	if (IS_DATASEG(seg_type))
 		SET_SUM_TYPE(sum_footer, SUM_TYPE_DATA);
-	if (IS_NODESEG(type))
+	if (IS_NODESEG(seg_type))
 		SET_SUM_TYPE(sum_footer, SUM_TYPE_NODE);
-	__set_sit_entry_type(sbi, type, curseg->segno, modified);
+	__set_sit_entry_type(sbi, seg_type, curseg->segno, modified);
 }
 
 static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 {
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned short seg_type = curseg->seg_type;
+
+	sanity_check_seg_type(sbi, seg_type);
+
 	/* if segs_per_sec is large than 1, we need to keep original policy. */
 	if (__is_large_section(sbi))
-		return CURSEG_I(sbi, type)->segno;
+		return curseg->segno;
+
+	/* inmem log may not locate on any segment after mount */
+	if (!curseg->inited)
+		return 0;
 
 	if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		return 0;
 
 	if (test_opt(sbi, NOHEAP) &&
-		(type == CURSEG_HOT_DATA || IS_NODESEG(type)))
+		(seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type)))
 		return 0;
 
 	if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
@@ -2530,7 +2584,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 	if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE)
 		return 0;
 
-	return CURSEG_I(sbi, type)->segno;
+	return curseg->segno;
 }
 
 /*
@@ -2540,12 +2594,14 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	unsigned short seg_type = curseg->seg_type;
 	unsigned int segno = curseg->segno;
 	int dir = ALLOC_LEFT;
 
-	write_sum_page(sbi, curseg->sum_blk,
+	if (curseg->inited)
+		write_sum_page(sbi, curseg->sum_blk,
 				GET_SUM_BLOCK(sbi, segno));
-	if (type == CURSEG_WARM_DATA || type == CURSEG_COLD_DATA)
+	if (seg_type == CURSEG_WARM_DATA || seg_type == CURSEG_COLD_DATA)
 		dir = ALLOC_RIGHT;
 
 	if (test_opt(sbi, NOHEAP))
@@ -2594,7 +2650,7 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
  * This function always allocates a used segment(from dirty seglist) by SSR
  * manner, so it should recover the existing segment information of valid blocks
  */
-static void change_curseg(struct f2fs_sb_info *sbi, int type)
+static void change_curseg(struct f2fs_sb_info *sbi, int type, bool flush)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -2602,8 +2658,10 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
 	struct f2fs_summary_block *sum_node;
 	struct page *sum_page;
 
-	write_sum_page(sbi, curseg->sum_blk,
-				GET_SUM_BLOCK(sbi, curseg->segno));
+	if (flush)
+		write_sum_page(sbi, curseg->sum_blk,
+					GET_SUM_BLOCK(sbi, curseg->segno));
+
 	__set_test_and_inuse(sbi, new_segno);
 
 	mutex_lock(&dirty_i->seglist_lock);
@@ -2616,29 +2674,139 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
 	__next_free_blkoff(sbi, curseg, 0);
 
 	sum_page = f2fs_get_sum_page(sbi, new_segno);
-	f2fs_bug_on(sbi, IS_ERR(sum_page));
+	if (IS_ERR(sum_page)) {
+		/* GC won't be able to use stale summary pages by cp_error */
+		memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE);
+		return;
+	}
 	sum_node = (struct f2fs_summary_block *)page_address(sum_page);
 	memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
 	f2fs_put_page(sum_page, 1);
 }
 
-static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
+				int alloc_mode, unsigned long long age);
+
+static void get_atssr_segment(struct f2fs_sb_info *sbi, int type,
+					int target_type, int alloc_mode,
+					unsigned long long age)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+
+	curseg->seg_type = target_type;
+
+	if (get_ssr_segment(sbi, type, alloc_mode, age)) {
+		struct seg_entry *se = get_seg_entry(sbi, curseg->next_segno);
+
+		curseg->seg_type = se->type;
+		change_curseg(sbi, type, true);
+	} else {
+		/* allocate cold segment by default */
+		curseg->seg_type = CURSEG_COLD_DATA;
+		new_curseg(sbi, type, true);
+	}
+	stat_inc_seg_type(sbi, curseg);
+}
+
+static void __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC);
+
+	if (!sbi->am.atgc_enabled)
+		return;
+
+	down_read(&SM_I(sbi)->curseg_lock);
+
+	mutex_lock(&curseg->curseg_mutex);
+	down_write(&SIT_I(sbi)->sentry_lock);
+
+	get_atssr_segment(sbi, CURSEG_ALL_DATA_ATGC, CURSEG_COLD_DATA, SSR, 0);
+
+	up_write(&SIT_I(sbi)->sentry_lock);
+	mutex_unlock(&curseg->curseg_mutex);
+
+	up_read(&SM_I(sbi)->curseg_lock);
+
+}
+void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+	__f2fs_init_atgc_curseg(sbi);
+}
+
+static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+
+	mutex_lock(&curseg->curseg_mutex);
+	if (!curseg->inited)
+		goto out;
+
+	if (get_valid_blocks(sbi, curseg->segno, false)) {
+		write_sum_page(sbi, curseg->sum_blk,
+				GET_SUM_BLOCK(sbi, curseg->segno));
+	} else {
+		mutex_lock(&DIRTY_I(sbi)->seglist_lock);
+		__set_test_and_free(sbi, curseg->segno, true);
+		mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
+	}
+out:
+	mutex_unlock(&curseg->curseg_mutex);
+}
+
+void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+	__f2fs_save_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
+
+	if (sbi->am.atgc_enabled)
+		__f2fs_save_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC);
+}
+
+static void __f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi, int type)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+
+	mutex_lock(&curseg->curseg_mutex);
+	if (!curseg->inited)
+		goto out;
+	if (get_valid_blocks(sbi, curseg->segno, false))
+		goto out;
+
+	mutex_lock(&DIRTY_I(sbi)->seglist_lock);
+	__set_test_and_inuse(sbi, curseg->segno);
+	mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
+out:
+	mutex_unlock(&curseg->curseg_mutex);
+}
+
+void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+	__f2fs_restore_inmem_curseg(sbi, CURSEG_COLD_DATA_PINNED);
+
+	if (sbi->am.atgc_enabled)
+		__f2fs_restore_inmem_curseg(sbi, CURSEG_ALL_DATA_ATGC);
+}
+
+static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
+				int alloc_mode, unsigned long long age)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
 	unsigned segno = NULL_SEGNO;
+	unsigned short seg_type = curseg->seg_type;
 	int i, cnt;
 	bool reversed = false;
 
+	sanity_check_seg_type(sbi, seg_type);
+
 	/* f2fs_need_SSR() already forces to do this */
-	if (!v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+	if (!v_ops->get_victim(sbi, &segno, BG_GC, seg_type, alloc_mode, age)) {
 		curseg->next_segno = segno;
 		return 1;
 	}
 
 	/* For node segments, let's do SSR more intensively */
-	if (IS_NODESEG(type)) {
-		if (type >= CURSEG_WARM_NODE) {
+	if (IS_NODESEG(seg_type)) {
+		if (seg_type >= CURSEG_WARM_NODE) {
 			reversed = true;
 			i = CURSEG_COLD_NODE;
 		} else {
@@ -2646,7 +2814,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
 		}
 		cnt = NR_CURSEG_NODE_TYPE;
 	} else {
-		if (type >= CURSEG_WARM_DATA) {
+		if (seg_type >= CURSEG_WARM_DATA) {
 			reversed = true;
 			i = CURSEG_COLD_DATA;
 		} else {
@@ -2656,9 +2824,9 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
 	}
 
 	for (; cnt-- > 0; reversed ? i-- : i++) {
-		if (i == type)
+		if (i == seg_type)
 			continue;
-		if (!v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+		if (!v_ops->get_victim(sbi, &segno, BG_GC, i, alloc_mode, age)) {
 			curseg->next_segno = segno;
 			return 1;
 		}
@@ -2687,13 +2855,15 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 	if (force)
 		new_curseg(sbi, type, true);
 	else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
-					type == CURSEG_WARM_NODE)
+					curseg->seg_type == CURSEG_WARM_NODE)
 		new_curseg(sbi, type, false);
-	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) &&
+	else if (curseg->alloc_type == LFS &&
+			is_next_segment_free(sbi, curseg, type) &&
 			likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		new_curseg(sbi, type, false);
-	else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
-		change_curseg(sbi, type);
+	else if (f2fs_need_SSR(sbi) &&
+			get_ssr_segment(sbi, type, SSR, 0))
+		change_curseg(sbi, type, true);
 	else
 		new_curseg(sbi, type, false);
 
@@ -2714,8 +2884,8 @@ void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
 	if (segno < start || segno > end)
 		goto unlock;
 
-	if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type))
-		change_curseg(sbi, type);
+	if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type, SSR, 0))
+		change_curseg(sbi, type, true);
 	else
 		new_curseg(sbi, type, true);
 
@@ -2738,11 +2908,15 @@ static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type)
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	unsigned int old_segno;
 
+	if (!curseg->inited)
+		goto alloc;
+
 	if (!curseg->next_blkoff &&
 		!get_valid_blocks(sbi, curseg->segno, false) &&
 		!get_ckpt_valid_blocks(sbi, curseg->segno))
 		return;
 
+alloc:
 	old_segno = curseg->segno;
 	SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
 	locate_dirty_segment(sbi, old_segno);
@@ -2806,7 +2980,7 @@ next:
 	mutex_lock(&dcc->cmd_lock);
 	if (unlikely(dcc->rbtree_check))
 		f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi,
-								&dcc->root));
+							&dcc->root, false));
 
 	dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root,
 					NULL, start,
@@ -2930,12 +3104,11 @@ out:
 	return err;
 }
 
-static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
+static bool __has_curseg_space(struct f2fs_sb_info *sbi,
+					struct curseg_info *curseg)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	if (curseg->next_blkoff < sbi->blocks_per_seg)
-		return true;
-	return false;
+	return curseg->next_blkoff < f2fs_usable_blks_in_seg(sbi,
+							curseg->segno);
 }
 
 int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
@@ -3075,8 +3248,13 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
 	if (fio->type == DATA) {
 		struct inode *inode = fio->page->mapping->host;
 
-		if (is_cold_data(fio->page) || file_is_cold(inode) ||
-				f2fs_compressed_file(inode))
+		if (is_cold_data(fio->page)) {
+			if (fio->sbi->am.atgc_enabled)
+				return CURSEG_ALL_DATA_ATGC;
+			else
+				return CURSEG_COLD_DATA;
+		}
+		if (file_is_cold(inode) || f2fs_compressed_file(inode))
 			return CURSEG_COLD_DATA;
 		if (file_is_hot(inode) ||
 				is_inode_flag_set(inode, FI_HOT_DATA) ||
@@ -3126,27 +3304,25 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
-	bool put_pin_sem = false;
-
-	if (type == CURSEG_COLD_DATA) {
-		/* GC during CURSEG_COLD_DATA_PINNED allocation */
-		if (down_read_trylock(&sbi->pin_sem)) {
-			put_pin_sem = true;
-		} else {
-			type = CURSEG_WARM_DATA;
-			curseg = CURSEG_I(sbi, type);
-		}
-	} else if (type == CURSEG_COLD_DATA_PINNED) {
-		type = CURSEG_COLD_DATA;
-	}
+	unsigned long long old_mtime;
+	bool from_gc = (type == CURSEG_ALL_DATA_ATGC);
+	struct seg_entry *se = NULL;
 
 	down_read(&SM_I(sbi)->curseg_lock);
 
 	mutex_lock(&curseg->curseg_mutex);
 	down_write(&sit_i->sentry_lock);
 
+	if (from_gc) {
+		f2fs_bug_on(sbi, GET_SEGNO(sbi, old_blkaddr) == NULL_SEGNO);
+		se = get_seg_entry(sbi, GET_SEGNO(sbi, old_blkaddr));
+		sanity_check_seg_type(sbi, se->type);
+		f2fs_bug_on(sbi, IS_NODESEG(se->type));
+	}
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
+	f2fs_bug_on(sbi, curseg->next_blkoff >= sbi->blocks_per_seg);
+
 	f2fs_wait_discard_bio(sbi, *new_blkaddr);
 
 	/*
@@ -3160,6 +3336,14 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 
 	stat_inc_block_count(sbi, curseg);
 
+	if (from_gc) {
+		old_mtime = get_segment_mtime(sbi, old_blkaddr);
+	} else {
+		update_segment_mtime(sbi, old_blkaddr, 0);
+		old_mtime = 0;
+	}
+	update_segment_mtime(sbi, *new_blkaddr, old_mtime);
+
 	/*
 	 * SIT information should be updated before segment allocation,
 	 * since SSR needs latest valid block information.
@@ -3168,9 +3352,13 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		update_sit_entry(sbi, old_blkaddr, -1);
 
-	if (!__has_curseg_space(sbi, type))
-		sit_i->s_ops->allocate_segment(sbi, type, false);
-
+	if (!__has_curseg_space(sbi, curseg)) {
+		if (from_gc)
+			get_atssr_segment(sbi, type, se->type,
+						AT_SSR, se->mtime);
+		else
+			sit_i->s_ops->allocate_segment(sbi, type, false);
+	}
 	/*
 	 * segment dirty status should be updated after segment allocation,
 	 * so we just need to update status only one time after previous
@@ -3204,9 +3392,6 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	mutex_unlock(&curseg->curseg_mutex);
 
 	up_read(&SM_I(sbi)->curseg_lock);
-
-	if (put_pin_sem)
-		up_read(&sbi->pin_sem);
 }
 
 static void update_device_state(struct f2fs_io_info *fio)
@@ -3355,7 +3540,8 @@ static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi,
 
 void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 				block_t old_blkaddr, block_t new_blkaddr,
-				bool recover_curseg, bool recover_newaddr)
+				bool recover_curseg, bool recover_newaddr,
+				bool from_gc)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
@@ -3400,17 +3586,22 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	/* change the current segment */
 	if (segno != curseg->segno) {
 		curseg->next_segno = segno;
-		change_curseg(sbi, type);
+		change_curseg(sbi, type, true);
 	}
 
 	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
 	__add_sum_entry(sbi, type, sum);
 
-	if (!recover_curseg || recover_newaddr)
+	if (!recover_curseg || recover_newaddr) {
+		if (!from_gc)
+			update_segment_mtime(sbi, new_blkaddr, 0);
 		update_sit_entry(sbi, new_blkaddr, 1);
+	}
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
 		invalidate_mapping_pages(META_MAPPING(sbi),
 					old_blkaddr, old_blkaddr);
+		if (!from_gc)
+			update_segment_mtime(sbi, old_blkaddr, 0);
 		update_sit_entry(sbi, old_blkaddr, -1);
 	}
 
@@ -3422,7 +3613,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	if (recover_curseg) {
 		if (old_cursegno != curseg->segno) {
 			curseg->next_segno = old_cursegno;
-			change_curseg(sbi, type);
+			change_curseg(sbi, type, true);
 		}
 		curseg->next_blkoff = old_blkoff;
 	}
@@ -3442,7 +3633,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 	set_summary(&sum, dn->nid, dn->ofs_in_node, version);
 
 	f2fs_do_replace_block(sbi, &sum, old_addr, new_addr,
-					recover_curseg, recover_newaddr);
+					recover_curseg, recover_newaddr, false);
 
 	f2fs_update_data_blkaddr(dn, new_addr);
 }
@@ -3574,7 +3765,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 		blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
 							CURSEG_HOT_DATA]);
 		if (__exist_node_summaries(sbi))
-			blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
+			blk_addr = sum_blk_addr(sbi, NR_CURSEG_PERSIST_TYPE, type);
 		else
 			blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
 	} else {
@@ -3652,8 +3843,9 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 	}
 
 	if (__exist_node_summaries(sbi))
-		f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
-					NR_CURSEG_TYPE - type, META_CP, true);
+		f2fs_ra_meta_pages(sbi,
+				sum_blk_addr(sbi, NR_CURSEG_PERSIST_TYPE, type),
+				NR_CURSEG_PERSIST_TYPE - type, META_CP, true);
 
 	for (; type <= CURSEG_COLD_NODE; type++) {
 		err = read_normal_summaries(sbi, type);
@@ -3781,7 +3973,7 @@ int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
 					unsigned int segno)
 {
-	return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno));
+	return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno));
 }
 
 static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
@@ -4155,14 +4347,14 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 	struct curseg_info *array;
 	int i;
 
-	array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)),
-			     GFP_KERNEL);
+	array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE,
+					sizeof(*array)), GFP_KERNEL);
 	if (!array)
 		return -ENOMEM;
 
 	SM_I(sbi)->curseg_array = array;
 
-	for (i = 0; i < NR_CURSEG_TYPE; i++) {
+	for (i = 0; i < NO_CHECK_TYPE; i++) {
 		mutex_init(&array[i].curseg_mutex);
 		array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL);
 		if (!array[i].sum_blk)
@@ -4172,8 +4364,15 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 				sizeof(struct f2fs_journal), GFP_KERNEL);
 		if (!array[i].journal)
 			return -ENOMEM;
+		if (i < NR_PERSISTENT_LOG)
+			array[i].seg_type = CURSEG_HOT_DATA + i;
+		else if (i == CURSEG_COLD_DATA_PINNED)
+			array[i].seg_type = CURSEG_COLD_DATA;
+		else if (i == CURSEG_ALL_DATA_ATGC)
+			array[i].seg_type = CURSEG_COLD_DATA;
 		array[i].segno = NULL_SEGNO;
 		array[i].next_blkoff = 0;
+		array[i].inited = false;
 	}
 	return restore_curseg_summaries(sbi);
 }
@@ -4294,9 +4493,12 @@ static void init_free_segmap(struct f2fs_sb_info *sbi)
 {
 	unsigned int start;
 	int type;
+	struct seg_entry *sentry;
 
 	for (start = 0; start < MAIN_SEGS(sbi); start++) {
-		struct seg_entry *sentry = get_seg_entry(sbi, start);
+		if (f2fs_usable_blks_in_seg(sbi, start) == 0)
+			continue;
+		sentry = get_seg_entry(sbi, start);
 		if (!sentry->valid_blocks)
 			__set_free(sbi, start);
 		else
@@ -4316,8 +4518,8 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int segno = 0, offset = 0, secno;
-	unsigned short valid_blocks;
-	unsigned short blks_per_sec = BLKS_PER_SEC(sbi);
+	block_t valid_blocks, usable_blks_in_seg;
+	block_t blks_per_sec = BLKS_PER_SEC(sbi);
 
 	while (1) {
 		/* find dirty segment based on free segmap */
@@ -4326,9 +4528,10 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 			break;
 		offset = segno + 1;
 		valid_blocks = get_valid_blocks(sbi, segno, false);
-		if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
+		usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno);
+		if (valid_blocks == usable_blks_in_seg || !valid_blocks)
 			continue;
-		if (valid_blocks > sbi->blocks_per_seg) {
+		if (valid_blocks > usable_blks_in_seg) {
 			f2fs_bug_on(sbi, 1);
 			continue;
 		}
@@ -4408,11 +4611,13 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi)
 	 * In LFS/SSR curseg, .next_blkoff should point to an unused blkaddr;
 	 * In LFS curseg, all blkaddr after .next_blkoff should be unused.
 	 */
-	for (i = 0; i < NO_CHECK_TYPE; i++) {
+	for (i = 0; i < NR_PERSISTENT_LOG; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
 		struct seg_entry *se = get_seg_entry(sbi, curseg->segno);
 		unsigned int blkofs = curseg->next_blkoff;
 
+		sanity_check_seg_type(sbi, curseg->seg_type);
+
 		if (f2fs_test_bit(blkofs, se->cur_valid_map))
 			goto out;
 
@@ -4637,7 +4842,7 @@ int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
 {
 	int i, ret;
 
-	for (i = 0; i < NO_CHECK_TYPE; i++) {
+	for (i = 0; i < NR_PERSISTENT_LOG; i++) {
 		ret = fix_curseg_write_pointer(sbi, i);
 		if (ret)
 			return ret;
@@ -4678,6 +4883,101 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
 
 	return 0;
 }
+
+static bool is_conv_zone(struct f2fs_sb_info *sbi, unsigned int zone_idx,
+						unsigned int dev_idx)
+{
+	if (!bdev_is_zoned(FDEV(dev_idx).bdev))
+		return true;
+	return !test_bit(zone_idx, FDEV(dev_idx).blkz_seq);
+}
+
+/* Return the zone index in the given device */
+static unsigned int get_zone_idx(struct f2fs_sb_info *sbi, unsigned int secno,
+					int dev_idx)
+{
+	block_t sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno));
+
+	return (sec_start_blkaddr - FDEV(dev_idx).start_blk) >>
+						sbi->log_blocks_per_blkz;
+}
+
+/*
+ * Return the usable segments in a section based on the zone's
+ * corresponding zone capacity. Zone is equal to a section.
+ */
+static inline unsigned int f2fs_usable_zone_segs_in_sec(
+		struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	unsigned int dev_idx, zone_idx, unusable_segs_in_sec;
+
+	dev_idx = f2fs_target_device_index(sbi, START_BLOCK(sbi, segno));
+	zone_idx = get_zone_idx(sbi, GET_SEC_FROM_SEG(sbi, segno), dev_idx);
+
+	/* Conventional zone's capacity is always equal to zone size */
+	if (is_conv_zone(sbi, zone_idx, dev_idx))
+		return sbi->segs_per_sec;
+
+	/*
+	 * If the zone_capacity_blocks array is NULL, then zone capacity
+	 * is equal to the zone size for all zones
+	 */
+	if (!FDEV(dev_idx).zone_capacity_blocks)
+		return sbi->segs_per_sec;
+
+	/* Get the segment count beyond zone capacity block */
+	unusable_segs_in_sec = (sbi->blocks_per_blkz -
+				FDEV(dev_idx).zone_capacity_blocks[zone_idx]) >>
+				sbi->log_blocks_per_seg;
+	return sbi->segs_per_sec - unusable_segs_in_sec;
+}
+
+/*
+ * Return the number of usable blocks in a segment. The number of blocks
+ * returned is always equal to the number of blocks in a segment for
+ * segments fully contained within a sequential zone capacity or a
+ * conventional zone. For segments partially contained in a sequential
+ * zone capacity, the number of usable blocks up to the zone capacity
+ * is returned. 0 is returned in all other cases.
+ */
+static inline unsigned int f2fs_usable_zone_blks_in_seg(
+			struct f2fs_sb_info *sbi, unsigned int segno)
+{
+	block_t seg_start, sec_start_blkaddr, sec_cap_blkaddr;
+	unsigned int zone_idx, dev_idx, secno;
+
+	secno = GET_SEC_FROM_SEG(sbi, segno);
+	seg_start = START_BLOCK(sbi, segno);
+	dev_idx = f2fs_target_device_index(sbi, seg_start);
+	zone_idx = get_zone_idx(sbi, secno, dev_idx);
+
+	/*
+	 * Conventional zone's capacity is always equal to zone size,
+	 * so, blocks per segment is unchanged.
+	 */
+	if (is_conv_zone(sbi, zone_idx, dev_idx))
+		return sbi->blocks_per_seg;
+
+	if (!FDEV(dev_idx).zone_capacity_blocks)
+		return sbi->blocks_per_seg;
+
+	sec_start_blkaddr = START_BLOCK(sbi, GET_SEG_FROM_SEC(sbi, secno));
+	sec_cap_blkaddr = sec_start_blkaddr +
+				FDEV(dev_idx).zone_capacity_blocks[zone_idx];
+
+	/*
+	 * If segment starts before zone capacity and spans beyond
+	 * zone capacity, then usable blocks are from seg start to
+	 * zone capacity. If the segment starts after the zone capacity,
+	 * then there are no usable blocks.
+	 */
+	if (seg_start >= sec_cap_blkaddr)
+		return 0;
+	if (seg_start + sbi->blocks_per_seg > sec_cap_blkaddr)
+		return sec_cap_blkaddr - seg_start;
+
+	return sbi->blocks_per_seg;
+}
 #else
 int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
 {
@@ -4688,7 +4988,36 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
 {
 	return 0;
 }
+
+static inline unsigned int f2fs_usable_zone_blks_in_seg(struct f2fs_sb_info *sbi,
+							unsigned int segno)
+{
+	return 0;
+}
+
+static inline unsigned int f2fs_usable_zone_segs_in_sec(struct f2fs_sb_info *sbi,
+							unsigned int segno)
+{
+	return 0;
+}
 #endif
+unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
+					unsigned int segno)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return f2fs_usable_zone_blks_in_seg(sbi, segno);
+
+	return sbi->blocks_per_seg;
+}
+
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
+					unsigned int segno)
+{
+	if (f2fs_sb_has_blkzoned(sbi))
+		return f2fs_usable_zone_segs_in_sec(sbi, segno);
+
+	return sbi->segs_per_sec;
+}
 
 /*
  * Update min, max modified time for cost-benefit GC algorithm
@@ -4715,6 +5044,7 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
 			sit_i->min_mtime = mtime;
 	}
 	sit_i->max_mtime = get_mtime(sbi, false);
+	sit_i->dirty_max_mtime = 0;
 	up_write(&sit_i->sentry_lock);
 }
 
@@ -4830,7 +5160,7 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
 
 	destroy_victim_secmap(sbi);
 	SM_I(sbi)->dirty_info = NULL;
-	kvfree(dirty_i);
+	kfree(dirty_i);
 }
 
 static void destroy_curseg(struct f2fs_sb_info *sbi)
@@ -4842,10 +5172,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 		return;
 	SM_I(sbi)->curseg_array = NULL;
 	for (i = 0; i < NR_CURSEG_TYPE; i++) {
-		kvfree(array[i].sum_blk);
-		kvfree(array[i].journal);
+		kfree(array[i].sum_blk);
+		kfree(array[i].journal);
 	}
-	kvfree(array);
+	kfree(array);
 }
 
 static void destroy_free_segmap(struct f2fs_sb_info *sbi)
@@ -4856,7 +5186,7 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi)
 	SM_I(sbi)->free_info = NULL;
 	kvfree(free_i->free_segmap);
 	kvfree(free_i->free_secmap);
-	kvfree(free_i);
+	kfree(free_i);
 }
 
 static void destroy_sit_info(struct f2fs_sb_info *sbi)
@@ -4868,7 +5198,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 
 	if (sit_i->sentries)
 		kvfree(sit_i->bitmap);
-	kvfree(sit_i->tmp_map);
+	kfree(sit_i->tmp_map);
 
 	kvfree(sit_i->sentries);
 	kvfree(sit_i->sec_entries);
@@ -4880,7 +5210,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 	kvfree(sit_i->sit_bitmap_mir);
 	kvfree(sit_i->invalid_segmap);
 #endif
-	kvfree(sit_i);
+	kfree(sit_i);
 }
 
 void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
@@ -4896,7 +5226,7 @@ void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi)
 	destroy_free_segmap(sbi);
 	destroy_sit_info(sbi);
 	sbi->sm_info = NULL;
-	kvfree(sm_info);
+	kfree(sm_info);
 }
 
 int __init f2fs_create_segment_manager_caches(void)