Merge tag 'f2fs-for-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "This series introduces a device aliasing feature where user can carve
  out partitions but reclaim the space back by deleting aliased file in
  root dir.

  In addition to that, there're numerous minor bug fixes in zoned device
  support, checkpoint=disable, extent cache management, fiemap, and
  lazytime mount option. The full list of noticeable changes can be
  found below.

  Enhancements:
   - introduce device aliasing file
   - add stats in debugfs to show multiple devices
   - add a sysfs node to limit max read extent count per-inode
   - modify f2fs_is_checkpoint_ready logic to allow more data to be
     written with the CP disable
   - decrease spare area for pinned files for zoned devices

  Fixes:
   - Revert "f2fs: remove unreachable lazytime mount option parsing"
   - adjust unusable cap before checkpoint=disable mode
   - fix to drop all discards after creating snapshot on lvm device
   - fix to shrink read extent node in batches
   - fix changing cursegs if recovery fails on zoned device
   - fix to adjust appropriate length for fiemap
   - fix fiemap failure issue when page size is 16KB
   - fix to avoid forcing direct write to use buffered IO on inline_data
     inode
   - fix to map blocks correctly for direct write
   - fix to account dirty data in __get_secs_required()
   - fix null-ptr-deref in f2fs_submit_page_bio()
   - fix inconsistent update of i_blocks in release_compress_blocks and
     reserve_compress_blocks"

* tag 'f2fs-for-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (40 commits)
  f2fs: fix to drop all discards after creating snapshot on lvm device
  f2fs: add a sysfs node to limit max read extent count per-inode
  f2fs: fix to shrink read extent node in batches
  f2fs: print message if fscorrupted was found in f2fs_new_node_page()
  f2fs: clear SBI_POR_DOING before initing inmem curseg
  f2fs: fix changing cursegs if recovery fails on zoned device
  f2fs: adjust unusable cap before checkpoint=disable mode
  f2fs: fix to requery extent which cross boundary of inquiry
  f2fs: fix to adjust appropriate length for fiemap
  f2fs: clean up w/ F2FS_{BLK_TO_BYTES,BTYES_TO_BLK}
  f2fs: fix to do cast in F2FS_{BLK_TO_BYTES, BTYES_TO_BLK} to avoid overflow
  f2fs: replace deprecated strcpy with strscpy
  Revert "f2fs: remove unreachable lazytime mount option parsing"
  f2fs: fix to avoid forcing direct write to use buffered IO on inline_data inode
  f2fs: fix to map blocks correctly for direct write
  f2fs: fix race in concurrent f2fs_stop_gc_thread
  f2fs: fix fiemap failure issue when page size is 16KB
  f2fs: remove redundant atomic file check in defragment
  f2fs: fix to convert log type to segment data type correctly
  f2fs: clean up the unused variable additional_reserved_segments
  ...

1 files changed, 89 insertions, 30 deletions

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 62ac440d9416..347b3b647834 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -24,6 +24,7 @@ bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
 	struct extent_info ei;
+	int devi;
 
 	get_read_extent_info(&ei, i_ext);
 
@@ -38,7 +39,36 @@ bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
 			  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,
@@ -76,6 +106,9 @@ static bool __init_may_extent_tree(struct inode *inode, enum extent_type type)
 
 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.
@@ -346,21 +379,22 @@ 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,
@@ -401,6 +435,11 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 	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);
 	if (en) {
@@ -463,6 +502,11 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 		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;
@@ -579,6 +623,30 @@ 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)
 {
@@ -649,7 +717,9 @@ 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,
@@ -717,9 +787,6 @@ 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;
@@ -737,6 +804,9 @@ 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);
 }
@@ -899,10 +969,14 @@ 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);
@@ -1041,23 +1115,6 @@ 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);
@@ -1066,7 +1123,6 @@ 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;
 
@@ -1074,7 +1130,6 @@ 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) {
@@ -1083,6 +1138,9 @@ 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);
 }
@@ -1156,6 +1214,7 @@ 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)