Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Regression and bug fixes:

   - Performance regression fix from 5.18 on a Rasberry Pi

   - Fix extent parsing bug which triggers a BUG_ON when a (corrupted)
     extent tree has has a non-root node when zero entries.

   - Fix a livelock where in the right (wrong) circumstances a large
     number of nfsd threads can try to write to a nearly full file
     system, and retry for hours(!)"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: limit the number of retries after discarding preallocations blocks
  ext4: fix bug in extents parsing when eh_entries == 0 and eh_depth > 0
  ext4: use buckets for cr 1 block scan instead of rbtree
  ext4: use locality group preallocation for small closed files
  ext4: make directory inode spreading reflect flexbg size
  ext4: avoid unnecessary spreading of allocations among groups
  ext4: make mballoc try target group first even with mb_optimize_scan

fs/ext4/ext4.h

@@ -167,8 +167,6 @@ enum SHIFT_DIRECTION {
 #define EXT4_MB_CR0_OPTIMIZED		0x8000
 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
 #define EXT4_MB_CR1_OPTIMIZED		0x00010000
-/* Perform linear traversal for one group */
-#define EXT4_MB_SEARCH_NEXT_LINEAR	0x00020000
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
 	struct inode *inode;
@@ -1600,8 +1598,8 @@ struct ext4_sb_info {
 	struct list_head s_discard_list;
 	struct work_struct s_discard_work;
 	atomic_t s_retry_alloc_pending;
-	struct rb_root s_mb_avg_fragment_size_root;
-	rwlock_t s_mb_rb_lock;
+	struct list_head *s_mb_avg_fragment_size;
+	rwlock_t *s_mb_avg_fragment_size_locks;
 	struct list_head *s_mb_largest_free_orders;
 	rwlock_t *s_mb_largest_free_orders_locks;
 
@@ -3413,6 +3411,8 @@ struct ext4_group_info {
 	ext4_grpblk_t	bb_first_free;	/* first free block */
 	ext4_grpblk_t	bb_free;	/* total free blocks */
 	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
+	int		bb_avg_fragment_size_order;	/* order of average
+							   fragment in BG */
 	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
 	ext4_group_t	bb_group;	/* Group number */
 	struct          list_head bb_prealloc_list;
@@ -3420,7 +3420,7 @@ struct ext4_group_info {
 	void            *bb_bitmap;
 #endif
 	struct rw_semaphore alloc_sem;
-	struct rb_node	bb_avg_fragment_size_rb;
+	struct list_head bb_avg_fragment_size_node;
 	struct list_head bb_largest_free_order_node;
 	ext4_grpblk_t	bb_counters[];	/* Nr of free power-of-two-block
 					 * regions, index is order.

fs/ext4/extents.c

@@ -460,6 +460,10 @@ static int __ext4_ext_check(const char *function, unsigned int line,
 		error_msg = "invalid eh_entries";
 		goto corrupted;
 	}
+	if (unlikely((eh->eh_entries == 0) && (depth > 0))) {
+		error_msg = "eh_entries is 0 but eh_depth is > 0";
+		goto corrupted;
+	}
 	if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) {
 		error_msg = "invalid extent entries";
 		goto corrupted;

fs/ext4/ialloc.c

@@ -510,7 +510,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 		goto fallback;
 	}
 
-	max_dirs = ndirs / ngroups + inodes_per_group / 16;
+	max_dirs = ndirs / ngroups + inodes_per_group*flex_size / 16;
 	min_inodes = avefreei - inodes_per_group*flex_size / 4;
 	if (min_inodes < 1)
 		min_inodes = 1;

fs/ext4/mballoc.h

@@ -178,7 +178,6 @@ struct ext4_allocation_context {
 	/* copy of the best found extent taken before preallocation efforts */
 	struct ext4_free_extent ac_f_ex;
 
-	ext4_group_t ac_last_optimal_group;
 	__u32 ac_groups_considered;
 	__u32 ac_flags;		/* allocation hints */
 	__u16 ac_groups_scanned;