1 files changed, 168 insertions, 97 deletions
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index eade36c5ef13..396ef71f41e3 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -201,6 +201,12 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
 	clear_inode_flag(inode, FI_ATOMIC_FILE);
 	if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
 		clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
+		/*
+		 * The vfs inode keeps clean during commit, but the f2fs inode
+		 * doesn't. So clear the dirty state after commit and let
+		 * f2fs_mark_inode_dirty_sync ensure a consistent dirty state.
+		 */
+		f2fs_inode_synced(inode);
 		f2fs_mark_inode_dirty_sync(inode, true);
 	}
 	stat_dec_atomic_inode(inode);
@@ -245,7 +251,7 @@ retry:
 		if (!__is_valid_data_blkaddr(new_addr)) {
 			if (new_addr == NULL_ADDR)
 				dec_valid_block_count(sbi, inode, 1);
-			f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
+			f2fs_invalidate_blocks(sbi, dn.data_blkaddr, 1);
 			f2fs_update_data_blkaddr(&dn, new_addr);
 		} else {
 			f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
@@ -2090,7 +2096,9 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
 		return false;
 
 	if (!force) {
-		if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks ||
+		if (!f2fs_realtime_discard_enable(sbi) ||
+			(!se->valid_blocks &&
+				!IS_CURSEG(sbi, cpc->trim_start)) ||
 			SM_I(sbi)->dcc_info->nr_discards >=
 				SM_I(sbi)->dcc_info->max_discards)
 			return false;
@@ -2314,10 +2322,9 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
 	dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
 	dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY;
 	dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE;
-	if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT)
+	if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT ||
+		F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
 		dcc->discard_granularity = BLKS_PER_SEG(sbi);
-	else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
-		dcc->discard_granularity = BLKS_PER_SEC(sbi);
 
 	INIT_LIST_HEAD(&dcc->entry_list);
 	for (i = 0; i < MAX_PLIST_NUM; i++)
@@ -2426,78 +2433,38 @@ static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr,
 		SIT_I(sbi)->max_mtime = ctime;
 }
 
-static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+/*
+ * NOTE: when updating multiple blocks at the same time, please ensure
+ * that the consecutive input blocks belong to the same segment.
+ */
+static int update_sit_entry_for_release(struct f2fs_sb_info *sbi, struct seg_entry *se,
+				block_t blkaddr, unsigned int offset, int del)
 {
-	struct seg_entry *se;
-	unsigned int segno, offset;
-	long int new_vblocks;
 	bool exist;
 #ifdef CONFIG_F2FS_CHECK_FS
 	bool mir_exist;
 #endif
+	int i;
+	int del_count = -del;
 
-	segno = GET_SEGNO(sbi, blkaddr);
-	if (segno == NULL_SEGNO)
-		return;
-
-	se = get_seg_entry(sbi, segno);
-	new_vblocks = se->valid_blocks + del;
-	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
-
-	f2fs_bug_on(sbi, (new_vblocks < 0 ||
-			(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
-
-	se->valid_blocks = new_vblocks;
-
-	/* Update valid block bitmap */
-	if (del > 0) {
-		exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
-#ifdef CONFIG_F2FS_CHECK_FS
-		mir_exist = f2fs_test_and_set_bit(offset,
-						se->cur_valid_map_mir);
-		if (unlikely(exist != mir_exist)) {
-			f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
-				 blkaddr, exist);
-			f2fs_bug_on(sbi, 1);
-		}
-#endif
-		if (unlikely(exist)) {
-			f2fs_err(sbi, "Bitmap was wrongly set, blk:%u",
-				 blkaddr);
-			f2fs_bug_on(sbi, 1);
-			se->valid_blocks--;
-			del = 0;
-		}
-
-		if (f2fs_block_unit_discard(sbi) &&
-				!f2fs_test_and_set_bit(offset, se->discard_map))
-			sbi->discard_blks--;
+	f2fs_bug_on(sbi, GET_SEGNO(sbi, blkaddr) != GET_SEGNO(sbi, blkaddr + del_count - 1));
 
-		/*
-		 * SSR should never reuse block which is checkpointed
-		 * or newly invalidated.
-		 */
-		if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
-			if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
-				se->ckpt_valid_blocks++;
-		}
-	} else {
-		exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
+	for (i = 0; i < del_count; i++) {
+		exist = f2fs_test_and_clear_bit(offset + i, se->cur_valid_map);
 #ifdef CONFIG_F2FS_CHECK_FS
-		mir_exist = f2fs_test_and_clear_bit(offset,
+		mir_exist = f2fs_test_and_clear_bit(offset + i,
 						se->cur_valid_map_mir);
 		if (unlikely(exist != mir_exist)) {
 			f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d",
-				 blkaddr, exist);
+				blkaddr + i, exist);
 			f2fs_bug_on(sbi, 1);
 		}
 #endif
 		if (unlikely(!exist)) {
-			f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u",
-				 blkaddr);
+			f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", blkaddr + i);
 			f2fs_bug_on(sbi, 1);
 			se->valid_blocks++;
-			del = 0;
+			del += 1;
 		} else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
 			/*
 			 * If checkpoints are off, we must not reuse data that
@@ -2505,7 +2472,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 			 * before, we must track that to know how much space we
 			 * really have.
 			 */
-			if (f2fs_test_bit(offset, se->ckpt_valid_map)) {
+			if (f2fs_test_bit(offset + i, se->ckpt_valid_map)) {
 				spin_lock(&sbi->stat_lock);
 				sbi->unusable_block_count++;
 				spin_unlock(&sbi->stat_lock);
@@ -2513,12 +2480,91 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 		}
 
 		if (f2fs_block_unit_discard(sbi) &&
-			f2fs_test_and_clear_bit(offset, se->discard_map))
+				f2fs_test_and_clear_bit(offset + i, se->discard_map))
 			sbi->discard_blks++;
+
+		if (!f2fs_test_bit(offset + i, se->ckpt_valid_map))
+			se->ckpt_valid_blocks -= 1;
+	}
+
+	return del;
+}
+
+static int update_sit_entry_for_alloc(struct f2fs_sb_info *sbi, struct seg_entry *se,
+				block_t blkaddr, unsigned int offset, int del)
+{
+	bool exist;
+#ifdef CONFIG_F2FS_CHECK_FS
+	bool mir_exist;
+#endif
+
+	exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+	mir_exist = f2fs_test_and_set_bit(offset,
+					se->cur_valid_map_mir);
+	if (unlikely(exist != mir_exist)) {
+		f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
+			blkaddr, exist);
+		f2fs_bug_on(sbi, 1);
+	}
+#endif
+	if (unlikely(exist)) {
+		f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr);
+		f2fs_bug_on(sbi, 1);
+		se->valid_blocks--;
+		del = 0;
+	}
+
+	if (f2fs_block_unit_discard(sbi) &&
+			!f2fs_test_and_set_bit(offset, se->discard_map))
+		sbi->discard_blks--;
+
+	/*
+	 * SSR should never reuse block which is checkpointed
+	 * or newly invalidated.
+	 */
+	if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
+		if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+			se->ckpt_valid_blocks++;
 	}
+
 	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
 		se->ckpt_valid_blocks += del;
 
+	return del;
+}
+
+/*
+ * If releasing blocks, this function supports updating multiple consecutive blocks
+ * at one time, but please note that these consecutive blocks need to belong to the
+ * same segment.
+ */
+static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+{
+	struct seg_entry *se;
+	unsigned int segno, offset;
+	long int new_vblocks;
+
+	segno = GET_SEGNO(sbi, blkaddr);
+	if (segno == NULL_SEGNO)
+		return;
+
+	se = get_seg_entry(sbi, segno);
+	new_vblocks = se->valid_blocks + del;
+	offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+	f2fs_bug_on(sbi, (new_vblocks < 0 ||
+			(new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
+
+	se->valid_blocks = new_vblocks;
+
+	/* Update valid block bitmap */
+	if (del > 0) {
+		del = update_sit_entry_for_alloc(sbi, se, blkaddr, offset, del);
+	} else {
+		del = update_sit_entry_for_release(sbi, se, blkaddr, offset, del);
+	}
+
 	__mark_sit_entry_dirty(sbi, segno);
 
 	/* update total number of valid blocks to be written in ckpt area */
@@ -2528,25 +2574,43 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 		get_sec_entry(sbi, segno)->valid_blocks += del;
 }
 
-void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr,
+				unsigned int len)
 {
 	unsigned int segno = GET_SEGNO(sbi, addr);
 	struct sit_info *sit_i = SIT_I(sbi);
+	block_t addr_start = addr, addr_end = addr + len - 1;
+	unsigned int seg_num = GET_SEGNO(sbi, addr_end) - segno + 1;
+	unsigned int i = 1, max_blocks = sbi->blocks_per_seg, cnt;
 
 	f2fs_bug_on(sbi, addr == NULL_ADDR);
 	if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
 		return;
 
-	f2fs_invalidate_internal_cache(sbi, addr);
+	f2fs_invalidate_internal_cache(sbi, addr, len);
 
 	/* add it into sit main buffer */
 	down_write(&sit_i->sentry_lock);
 
-	update_segment_mtime(sbi, addr, 0);
-	update_sit_entry(sbi, addr, -1);
+	if (seg_num == 1)
+		cnt = len;
+	else
+		cnt = max_blocks - GET_BLKOFF_FROM_SEG0(sbi, addr);
+
+	do {
+		update_segment_mtime(sbi, addr_start, 0);
+		update_sit_entry(sbi, addr_start, -cnt);
 
-	/* add it into dirty seglist */
-	locate_dirty_segment(sbi, segno);
+		/* add it into dirty seglist */
+		locate_dirty_segment(sbi, segno);
+
+		/* update @addr_start and @cnt and @segno */
+		addr_start = START_BLOCK(sbi, ++segno);
+		if (++i == seg_num)
+			cnt = GET_BLKOFF_FROM_SEG0(sbi, addr_end) + 1;
+		else
+			cnt = max_blocks;
+	} while (i <= seg_num);
 
 	up_write(&sit_i->sentry_lock);
 }
@@ -2743,7 +2807,7 @@ find_other_zone:
 							MAIN_SECS(sbi));
 		if (secno >= MAIN_SECS(sbi)) {
 			ret = -ENOSPC;
-			f2fs_bug_on(sbi, 1);
+			f2fs_bug_on(sbi, !pinning);
 			goto out_unlock;
 		}
 	}
@@ -2785,7 +2849,7 @@ got_it:
 out_unlock:
 	spin_unlock(&free_i->segmap_lock);
 
-	if (ret == -ENOSPC)
+	if (ret == -ENOSPC && !pinning)
 		f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
 	return ret;
 }
@@ -2858,6 +2922,13 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
 	return curseg->segno;
 }
 
+static void reset_curseg_fields(struct curseg_info *curseg)
+{
+	curseg->inited = false;
+	curseg->segno = NULL_SEGNO;
+	curseg->next_segno = 0;
+}
+
 /*
  * Allocate a current working segment.
  * This function always allocates a free segment in LFS manner.
@@ -2876,7 +2947,7 @@ static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
 	ret = get_new_segment(sbi, &segno, new_sec, pinning);
 	if (ret) {
 		if (ret == -ENOSPC)
-			curseg->segno = NULL_SEGNO;
+			reset_curseg_fields(curseg);
 		return ret;
 	}
 
@@ -3647,13 +3718,6 @@ static void f2fs_randomize_chunk(struct f2fs_sb_info *sbi,
 		get_random_u32_inclusive(1, sbi->max_fragment_hole);
 }
 
-static void reset_curseg_fields(struct curseg_info *curseg)
-{
-	curseg->inited = false;
-	curseg->segno = NULL_SEGNO;
-	curseg->next_segno = 0;
-}
-
 int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		block_t old_blkaddr, block_t *new_blkaddr,
 		struct f2fs_summary *sum, int type,
@@ -3839,6 +3903,7 @@ static int log_type_to_seg_type(enum log_type type)
 
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
+	struct folio *folio = page_folio(fio->page);
 	enum log_type type = __get_segment_type(fio);
 	int seg_type = log_type_to_seg_type(type);
 	bool keep_order = (f2fs_lfs_mode(fio->sbi) &&
@@ -3849,15 +3914,15 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 
 	if (f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
 			&fio->new_blkaddr, sum, type, fio)) {
-		if (fscrypt_inode_uses_fs_layer_crypto(fio->page->mapping->host))
+		if (fscrypt_inode_uses_fs_layer_crypto(folio->mapping->host))
 			fscrypt_finalize_bounce_page(&fio->encrypted_page);
-		end_page_writeback(fio->page);
-		if (f2fs_in_warm_node_list(fio->sbi, fio->page))
+		folio_end_writeback(folio);
+		if (f2fs_in_warm_node_list(fio->sbi, folio))
 			f2fs_del_fsync_node_entry(fio->sbi, fio->page);
 		goto out;
 	}
 	if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
-		f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr);
+		f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr, 1);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_write(fio);
@@ -4049,7 +4114,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		update_sit_entry(sbi, new_blkaddr, 1);
 	}
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
-		f2fs_invalidate_internal_cache(sbi, old_blkaddr);
+		f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1);
 		if (!from_gc)
 			update_segment_mtime(sbi, old_blkaddr, 0);
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -4091,22 +4156,21 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 	f2fs_update_data_blkaddr(dn, new_addr);
 }
 
-void f2fs_wait_on_page_writeback(struct page *page,
-				enum page_type type, bool ordered, bool locked)
+void f2fs_folio_wait_writeback(struct folio *folio, enum page_type type,
+		bool ordered, bool locked)
 {
-	if (folio_test_writeback(page_folio(page))) {
-		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	if (folio_test_writeback(folio)) {
+		struct f2fs_sb_info *sbi = F2FS_F_SB(folio);
 
 		/* submit cached LFS IO */
-		f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
+		f2fs_submit_merged_write_cond(sbi, NULL, &folio->page, 0, type);
 		/* submit cached IPU IO */
-		f2fs_submit_merged_ipu_write(sbi, NULL, page);
+		f2fs_submit_merged_ipu_write(sbi, NULL, &folio->page);
 		if (ordered) {
-			wait_on_page_writeback(page);
-			f2fs_bug_on(sbi, locked &&
-				folio_test_writeback(page_folio(page)));
+			folio_wait_writeback(folio);
+			f2fs_bug_on(sbi, locked && folio_test_writeback(folio));
 		} else {
-			wait_for_stable_page(page);
+			folio_wait_stable(folio);
 		}
 	}
 }
@@ -5405,7 +5469,8 @@ int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
 {
 	int ret;
 
-	if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb))
+	if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb) ||
+	    f2fs_hw_is_readonly(sbi))
 		return 0;
 
 	f2fs_notice(sbi, "Checking entire write pointers");
@@ -5492,8 +5557,10 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
 	secno = GET_SEC_FROM_SEG(sbi, segno);
 	start = GET_SEG_FROM_SEC(sbi, secno);
 
-	if (!__is_large_section(sbi))
-		return get_seg_entry(sbi, start + i)->mtime;
+	if (!__is_large_section(sbi)) {
+		mtime = get_seg_entry(sbi, start + i)->mtime;
+		goto out;
+	}
 
 	for (i = 0; i < usable_segs_per_sec; i++) {
 		/* for large section, only check the mtime of valid segments */
@@ -5506,7 +5573,11 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
 	if (total_valid_blocks == 0)
 		return INVALID_MTIME;
 
-	return div_u64(mtime, total_valid_blocks);
+	mtime = div_u64(mtime, total_valid_blocks);
+out:
+	if (unlikely(mtime == INVALID_MTIME))
+		mtime -= 1;
+	return mtime;
 }
 
 /*