1 files changed, 156 insertions, 105 deletions

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 0e2d49140c07..0ed84cc065a7 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -19,37 +19,56 @@
 #include "node.h"
 #include <trace/events/f2fs.h>
 
-bool sanity_check_extent_cache(struct inode *inode)
+bool sanity_check_extent_cache(struct inode *inode, struct folio *ifolio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct extent_tree *et = fi->extent_tree[EX_READ];
-	struct extent_info *ei;
-
-	if (!et)
-		return true;
+	struct f2fs_extent *i_ext = &F2FS_INODE(ifolio)->i_ext;
+	struct extent_info ei;
+	int devi;
 
-	ei = &et->largest;
-	if (!ei->len)
-		return true;
+	get_read_extent_info(&ei, i_ext);
 
-	/* Let's drop, if checkpoint got corrupted. */
-	if (is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) {
-		ei->len = 0;
-		et->largest_updated = true;
+	if (!ei.len)
 		return true;
-	}
 
-	if (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE) ||
-	    !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+	if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) ||
+	    !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1,
 					DATA_GENERIC_ENHANCE)) {
-		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix",
 			  __func__, inode->i_ino,
-			  ei->blk, ei->fofs, ei->len);
+			  ei.blk, ei.fofs, ei.len);
 		return false;
 	}
-	return true;
+
+	if (!IS_DEVICE_ALIASING(inode))
+		return true;
+
+	for (devi = 0; devi < sbi->s_ndevs; devi++) {
+		if (FDEV(devi).start_blk != ei.blk ||
+				FDEV(devi).end_blk != ei.blk + ei.len - 1)
+			continue;
+
+		if (devi == 0) {
+			f2fs_warn(sbi,
+			    "%s: inode (ino=%lx) is an alias of meta device",
+			    __func__, inode->i_ino);
+			return false;
+		}
+
+		if (bdev_is_zoned(FDEV(devi).bdev)) {
+			f2fs_warn(sbi,
+			    "%s: device alias inode (ino=%lx)'s extent info "
+			    "[%u, %u, %u] maps to zoned block device",
+			    __func__, inode->i_ino, ei.blk, ei.fofs, ei.len);
+			return false;
+		}
+		return true;
+	}
+
+	f2fs_warn(sbi, "%s: device alias inode (ino=%lx)'s extent info "
+			"[%u, %u, %u] is inconsistent w/ any devices",
+			__func__, inode->i_ino, ei.blk, ei.fofs, ei.len);
+	return false;
 }
 
 static void __set_extent_info(struct extent_info *ei,
@@ -74,45 +93,22 @@ static void __set_extent_info(struct extent_info *ei,
 	}
 }
 
-static bool __may_read_extent_tree(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
-	if (!test_opt(sbi, READ_EXTENT_CACHE))
-		return false;
-	if (is_inode_flag_set(inode, FI_NO_EXTENT))
-		return false;
-	if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) &&
-			 !f2fs_sb_has_readonly(sbi))
-		return false;
-	return S_ISREG(inode->i_mode);
-}
-
-static bool __may_age_extent_tree(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-
-	if (!test_opt(sbi, AGE_EXTENT_CACHE))
-		return false;
-	if (is_inode_flag_set(inode, FI_COMPRESSED_FILE))
-		return false;
-	if (file_is_cold(inode))
-		return false;
-
-	return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode);
-}
-
 static bool __init_may_extent_tree(struct inode *inode, enum extent_type type)
 {
 	if (type == EX_READ)
-		return __may_read_extent_tree(inode);
-	else if (type == EX_BLOCK_AGE)
-		return __may_age_extent_tree(inode);
+		return test_opt(F2FS_I_SB(inode), READ_EXTENT_CACHE) &&
+			S_ISREG(inode->i_mode);
+	if (type == EX_BLOCK_AGE)
+		return test_opt(F2FS_I_SB(inode), AGE_EXTENT_CACHE) &&
+			(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode));
 	return false;
 }
 
 static bool __may_extent_tree(struct inode *inode, enum extent_type type)
 {
+	if (IS_DEVICE_ALIASING(inode) && type == EX_READ)
+		return true;
+
 	/*
 	 * for recovered files during mount do not create extents
 	 * if shrinker is not registered.
@@ -120,7 +116,22 @@ static bool __may_extent_tree(struct inode *inode, enum extent_type type)
 	if (list_empty(&F2FS_I_SB(inode)->s_list))
 		return false;
 
-	return __init_may_extent_tree(inode, type);
+	if (!__init_may_extent_tree(inode, type))
+		return false;
+
+	if (type == EX_READ) {
+		if (is_inode_flag_set(inode, FI_NO_EXTENT))
+			return false;
+		if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) &&
+				 !f2fs_sb_has_readonly(F2FS_I_SB(inode)))
+			return false;
+	} else if (type == EX_BLOCK_AGE) {
+		if (is_inode_flag_set(inode, FI_COMPRESSED_FILE))
+			return false;
+		if (file_is_cold(inode))
+			return false;
+	}
+	return true;
 }
 
 static void __try_update_largest_extent(struct extent_tree *et,
@@ -368,62 +379,66 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode,
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
-					struct extent_tree *et)
+				struct extent_tree *et, unsigned int nr_shrink)
 {
 	struct rb_node *node, *next;
 	struct extent_node *en;
-	unsigned int count = atomic_read(&et->node_cnt);
+	unsigned int count;
 
 	node = rb_first_cached(&et->root);
-	while (node) {
+
+	for (count = 0; node && count < nr_shrink; count++) {
 		next = rb_next(node);
 		en = rb_entry(node, struct extent_node, rb_node);
 		__release_extent_node(sbi, et, en);
 		node = next;
 	}
 
-	return count - atomic_read(&et->node_cnt);
+	return count;
 }
 
 static void __drop_largest_extent(struct extent_tree *et,
 					pgoff_t fofs, unsigned int len)
 {
-	if (fofs < et->largest.fofs + et->largest.len &&
+	if (fofs < (pgoff_t)et->largest.fofs + et->largest.len &&
 			fofs + len > et->largest.fofs) {
 		et->largest.len = 0;
 		et->largest_updated = true;
 	}
 }
 
-void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
+void f2fs_init_read_extent_tree(struct inode *inode, struct folio *ifolio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree_info *eti = &sbi->extent_tree[EX_READ];
-	struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
+	struct f2fs_extent *i_ext = &F2FS_INODE(ifolio)->i_ext;
 	struct extent_tree *et;
 	struct extent_node *en;
-	struct extent_info ei;
+	struct extent_info ei = {0};
 
 	if (!__may_extent_tree(inode, EX_READ)) {
 		/* drop largest read extent */
-		if (i_ext && i_ext->len) {
-			f2fs_wait_on_page_writeback(ipage, NODE, true, true);
+		if (i_ext->len) {
+			f2fs_folio_wait_writeback(ifolio, NODE, true, true);
 			i_ext->len = 0;
-			set_page_dirty(ipage);
+			folio_mark_dirty(ifolio);
 		}
-		goto out;
+		set_inode_flag(inode, FI_NO_EXTENT);
+		return;
 	}
 
 	et = __grab_extent_tree(inode, EX_READ);
 
-	if (!i_ext || !i_ext->len)
-		goto out;
-
 	get_read_extent_info(&ei, i_ext);
 
 	write_lock(&et->lock);
-	if (atomic_read(&et->node_cnt))
-		goto unlock_out;
+	if (atomic_read(&et->node_cnt) || !ei.len)
+		goto skip;
+
+	if (IS_DEVICE_ALIASING(inode)) {
+		et->largest = ei;
+		goto skip;
+	}
 
 	en = __attach_extent_node(sbi, et, &ei, NULL,
 				&et->root.rb_root.rb_node, true);
@@ -435,11 +450,13 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 		list_add_tail(&en->list, &eti->extent_list);
 		spin_unlock(&eti->extent_lock);
 	}
-unlock_out:
+skip:
+	/* Let's drop, if checkpoint got corrupted. */
+	if (f2fs_cp_error(sbi)) {
+		et->largest.len = 0;
+		et->largest_updated = true;
+	}
 	write_unlock(&et->lock);
-out:
-	if (!F2FS_I(inode)->extent_tree[EX_READ])
-		set_inode_flag(inode, FI_NO_EXTENT);
 }
 
 void f2fs_init_age_extent_tree(struct inode *inode)
@@ -478,13 +495,18 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 
 	if (type == EX_READ &&
 			et->largest.fofs <= pgofs &&
-			et->largest.fofs + et->largest.len > pgofs) {
+			(pgoff_t)et->largest.fofs + et->largest.len > pgofs) {
 		*ei = et->largest;
 		ret = true;
 		stat_inc_largest_node_hit(sbi);
 		goto out;
 	}
 
+	if (IS_DEVICE_ALIASING(inode)) {
+		ret = false;
+		goto out;
+	}
+
 	en = __lookup_extent_node(&et->root, et->cached_en, pgofs);
 	if (!en)
 		goto out;
@@ -582,7 +604,13 @@ static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 			p = &(*p)->rb_right;
 			leftmost = false;
 		} else {
+			f2fs_err_ratelimited(sbi, "%s: corrupted extent, type: %d, "
+				"extent node in rb tree [%u, %u, %u], age [%llu, %llu], "
+				"extent node to insert [%u, %u, %u], age [%llu, %llu]",
+				__func__, et->type, en->ei.fofs, en->ei.blk, en->ei.len, en->ei.age,
+				en->ei.last_blocks, ei->fofs, ei->blk, ei->len, ei->age, ei->last_blocks);
 			f2fs_bug_on(sbi, 1);
+			return NULL;
 		}
 	}
 
@@ -601,6 +629,30 @@ do_insert:
 	return en;
 }
 
+static unsigned int __destroy_extent_node(struct inode *inode,
+					enum extent_type type)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
+	unsigned int nr_shrink = type == EX_READ ?
+				READ_EXTENT_CACHE_SHRINK_NUMBER :
+				AGE_EXTENT_CACHE_SHRINK_NUMBER;
+	unsigned int node_cnt = 0;
+
+	if (!et || !atomic_read(&et->node_cnt))
+		return 0;
+
+	while (atomic_read(&et->node_cnt)) {
+		write_lock(&et->lock);
+		node_cnt += __free_extent_tree(sbi, et, nr_shrink);
+		write_unlock(&et->lock);
+	}
+
+	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+
+	return node_cnt;
+}
+
 static void __update_extent_tree_range(struct inode *inode,
 			struct extent_info *tei, enum extent_type type)
 {
@@ -618,6 +670,15 @@ static void __update_extent_tree_range(struct inode *inode,
 	if (!et)
 		return;
 
+	if (unlikely(len == 0)) {
+		f2fs_err_ratelimited(sbi, "%s: extent len is zero, type: %d, "
+			"extent [%u, %u, %u], age [%llu, %llu]",
+			__func__, type, tei->fofs, tei->blk, tei->len,
+			tei->age, tei->last_blocks);
+		f2fs_bug_on(sbi, 1);
+		return;
+	}
+
 	if (type == EX_READ)
 		trace_f2fs_update_read_extent_tree_range(inode, fofs, len,
 						tei->blk, 0);
@@ -671,7 +732,9 @@ static void __update_extent_tree_range(struct inode *inode,
 		}
 
 		if (end < org_end && (type != EX_READ ||
-				org_end - end >= F2FS_MIN_EXTENT_LEN)) {
+			(org_end - end >= F2FS_MIN_EXTENT_LEN &&
+			atomic_read(&et->node_cnt) <
+					sbi->max_read_extent_count))) {
 			if (parts) {
 				__set_extent_info(&ei,
 					end, org_end - end,
@@ -739,16 +802,13 @@ static void __update_extent_tree_range(struct inode *inode,
 		}
 	}
 
-	if (is_inode_flag_set(inode, FI_NO_EXTENT))
-		__free_extent_tree(sbi, et);
-
 	if (et->largest_updated) {
 		et->largest_updated = false;
 		updated = true;
 	}
 	goto out_read_extent_cache;
 update_age_extent_cache:
-	if (!tei->last_blocks)
+	if (tei->last_blocks == F2FS_EXTENT_AGE_INVALID)
 		goto out_read_extent_cache;
 
 	__set_extent_info(&ei, fofs, len, 0, false,
@@ -759,6 +819,9 @@ update_age_extent_cache:
 out_read_extent_cache:
 	write_unlock(&et->lock);
 
+	if (is_inode_flag_set(inode, FI_NO_EXTENT))
+		__destroy_extent_node(inode, EX_READ);
+
 	if (updated)
 		f2fs_mark_inode_dirty_sync(inode, true);
 }
@@ -849,7 +912,7 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
 			cur_age = cur_blocks - tei.last_blocks;
 		else
 			/* allocated_data_blocks overflow */
-			cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
+			cur_age = (ULLONG_MAX - 1) - tei.last_blocks + cur_blocks;
 
 		if (tei.age)
 			ei->age = __calculate_block_age(sbi, cur_age, tei.age);
@@ -867,10 +930,8 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
 		goto out;
 
 	if (__is_valid_data_blkaddr(blkaddr) &&
-	    !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
-		f2fs_bug_on(sbi, 1);
+	    !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE))
 		return -EINVAL;
-	}
 out:
 	/*
 	 * init block age with zero, this can happen when the block age extent
@@ -888,7 +949,7 @@ static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type typ
 	if (!__may_extent_tree(dn->inode, type))
 		return;
 
-	ei.fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+	ei.fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_folio), dn->inode) +
 								dn->ofs_in_node;
 	ei.len = 1;
 
@@ -923,10 +984,14 @@ static unsigned int __shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink
 	list_for_each_entry_safe(et, next, &eti->zombie_list, list) {
 		if (atomic_read(&et->node_cnt)) {
 			write_lock(&et->lock);
-			node_cnt += __free_extent_tree(sbi, et);
+			node_cnt += __free_extent_tree(sbi, et,
+					nr_shrink - node_cnt - tree_cnt);
 			write_unlock(&et->lock);
 		}
-		f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+
+		if (atomic_read(&et->node_cnt))
+			goto unlock_out;
+
 		list_del_init(&et->list);
 		radix_tree_delete(&eti->extent_tree_root, et->ino);
 		kmem_cache_free(extent_tree_slab, et);
@@ -1049,6 +1114,7 @@ void f2fs_update_age_extent_cache_range(struct dnode_of_data *dn,
 	struct extent_info ei = {
 		.fofs = fofs,
 		.len = len,
+		.last_blocks = F2FS_EXTENT_AGE_INVALID,
 	};
 
 	if (!__may_extent_tree(dn->inode, EX_BLOCK_AGE))
@@ -1065,23 +1131,6 @@ unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink
 	return __shrink_extent_tree(sbi, nr_shrink, EX_BLOCK_AGE);
 }
 
-static unsigned int __destroy_extent_node(struct inode *inode,
-					enum extent_type type)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
-	unsigned int node_cnt = 0;
-
-	if (!et || !atomic_read(&et->node_cnt))
-		return 0;
-
-	write_lock(&et->lock);
-	node_cnt = __free_extent_tree(sbi, et);
-	write_unlock(&et->lock);
-
-	return node_cnt;
-}
-
 void f2fs_destroy_extent_node(struct inode *inode)
 {
 	__destroy_extent_node(inode, EX_READ);
@@ -1090,7 +1139,6 @@ void f2fs_destroy_extent_node(struct inode *inode)
 
 static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
 	bool updated = false;
 
@@ -1098,7 +1146,6 @@ static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 		return;
 
 	write_lock(&et->lock);
-	__free_extent_tree(sbi, et);
 	if (type == EX_READ) {
 		set_inode_flag(inode, FI_NO_EXTENT);
 		if (et->largest.len) {
@@ -1107,6 +1154,9 @@ static void __drop_extent_tree(struct inode *inode, enum extent_type type)
 		}
 	}
 	write_unlock(&et->lock);
+
+	__destroy_extent_node(inode, type);
+
 	if (updated)
 		f2fs_mark_inode_dirty_sync(inode, true);
 }
@@ -1180,6 +1230,7 @@ void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
 	sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD;
 	sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD;
 	sbi->last_age_weight = LAST_AGE_WEIGHT;
+	sbi->max_read_extent_count = DEF_MAX_READ_EXTENT_COUNT;
 }
 
 int __init f2fs_create_extent_cache(void)