1 files changed, 78 insertions, 62 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f44f668e407f..e4f7cf9d89c4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -564,14 +564,14 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
 
 			blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 			blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group,
 					      inode ? inode->i_ino : 0,
 					      blocknr,
 					      "freeing block already freed "
 					      "(bit %u)",
 					      first + i);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 		}
 		mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
 	}
@@ -677,7 +677,7 @@ do {									\
 	}								\
 } while (0)
 
-static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
+static void __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 				const char *function, int line)
 {
 	struct super_block *sb = e4b->bd_sb;
@@ -696,7 +696,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 	void *buddy2;
 
 	if (e4b->bd_info->bb_check_counter++ % 10)
-		return 0;
+		return;
 
 	while (order > 1) {
 		buddy = mb_find_buddy(e4b, order, &max);
@@ -758,7 +758,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 
 	grp = ext4_get_group_info(sb, e4b->bd_group);
 	if (!grp)
-		return NULL;
+		return;
 	list_for_each(cur, &grp->bb_prealloc_list) {
 		ext4_group_t groupnr;
 		struct ext4_prealloc_space *pa;
@@ -768,7 +768,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
 		for (i = 0; i < pa->pa_len; i++)
 			MB_CHECK_ASSERT(mb_test_bit(k + i, buddy));
 	}
-	return 0;
 }
 #undef MB_CHECK_ASSERT
 #define mb_check_buddy(e4b) __mb_check_buddy(e4b,	\
@@ -842,7 +841,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int new_order;
 
-	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+	if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0)
 		return;
 
 	new_order = mb_avg_fragment_size_order(sb,
@@ -871,7 +870,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
  * cr level needs an update.
  */
 static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac,
-			enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+			enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *iter;
@@ -945,7 +944,7 @@ ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int o
  * order. Updates *new_cr if cr level needs an update.
  */
 static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -990,7 +989,7 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *
  * much and fall to CR_GOAL_LEN_SLOW in that case.
  */
 static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac,
-		enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+		enum criteria *new_cr, ext4_group_t *group)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_group_info *grp = NULL;
@@ -1125,11 +1124,11 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 	}
 
 	if (*new_cr == CR_POWER2_ALIGNED) {
-		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group);
 	} else if (*new_cr == CR_GOAL_LEN_FAST) {
-		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_goal_fast(ac, new_cr, group);
 	} else if (*new_cr == CR_BEST_AVAIL_LEN) {
-		ext4_mb_choose_next_group_best_avail(ac, new_cr, group, ngroups);
+		ext4_mb_choose_next_group_best_avail(ac, new_cr, group);
 	} else {
 		/*
 		 * TODO: For CR=2, we can arrange groups in an rb tree sorted by
@@ -1233,6 +1232,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
 	atomic64_add(period, &sbi->s_mb_generation_time);
 }
 
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+	int count;
+	int order = 1;
+	void *buddy;
+
+	while ((buddy = mb_find_buddy(e4b, order++, &count)))
+		mb_set_bits(buddy, 0, count);
+
+	e4b->bd_info->bb_fragments = 0;
+	memset(e4b->bd_info->bb_counters, 0,
+		sizeof(*e4b->bd_info->bb_counters) *
+		(e4b->bd_sb->s_blocksize_bits + 2));
+
+	ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+		e4b->bd_bitmap, e4b->bd_group, e4b->bd_info);
+}
+
 /* The buddy information is attached the buddy cache inode
  * for convenience. The information regarding each group
  * is loaded via ext4_mb_load_buddy. The information involve
@@ -1891,11 +1908,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	mb_check_buddy(e4b);
 	mb_free_blocks_double(inode, e4b, first, count);
 
-	this_cpu_inc(discard_pa_seq);
-	e4b->bd_info->bb_free += count;
-	if (first < e4b->bd_info->bb_first_free)
-		e4b->bd_info->bb_first_free = first;
-
 	/* access memory sequentially: check left neighbour,
 	 * clear range and then check right neighbour
 	 */
@@ -1909,21 +1921,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		ext4_fsblk_t blocknr;
 
+		/*
+		 * Fastcommit replay can free already freed blocks which
+		 * corrupts allocation info. Regenerate it.
+		 */
+		if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+			mb_regenerate_buddy(e4b);
+			goto check;
+		}
+
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
-			ext4_grp_locked_error(sb, e4b->bd_group,
-					      inode ? inode->i_ino : 0,
-					      blocknr,
-					      "freeing already freed block (bit %u); block bitmap corrupt.",
-					      block);
-			ext4_mark_group_bitmap_corrupted(
-				sb, e4b->bd_group,
+		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
-		}
-		goto done;
+		ext4_grp_locked_error(sb, e4b->bd_group,
+				      inode ? inode->i_ino : 0, blocknr,
+				      "freeing already freed block (bit %u); block bitmap corrupt.",
+				      block);
+		return;
 	}
 
+	this_cpu_inc(discard_pa_seq);
+	e4b->bd_info->bb_free += count;
+	if (first < e4b->bd_info->bb_first_free)
+		e4b->bd_info->bb_first_free = first;
+
 	/* let's maintain fragments counter */
 	if (left_is_free && right_is_free)
 		e4b->bd_info->bb_fragments--;
@@ -1948,9 +1970,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	if (first <= last)
 		mb_buddy_mark_free(e4b, first >> 1, last >> 1);
 
-done:
 	mb_set_largest_free_order(sb, e4b->bd_info);
 	mb_update_avg_fragment_size(sb, e4b->bd_info);
+check:
 	mb_check_buddy(e4b);
 }
 
@@ -2276,6 +2298,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		return;
 
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
 
 	if (max > 0) {
@@ -2283,6 +2308,7 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		ext4_mb_use_best_found(ac, e4b);
 	}
 
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 }
@@ -2309,12 +2335,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 	if (err)
 		return err;
 
-	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
-		ext4_mb_unload_buddy(e4b);
-		return 0;
-	}
-
 	ext4_lock_group(ac->ac_sb, group);
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		goto out;
+
 	max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
 			     ac->ac_g_ex.fe_len, &ex);
 	ex.fe_logical = 0xDEADFA11; /* debug value */
@@ -2347,6 +2371,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
 		ac->ac_b_ex = ex;
 		ext4_mb_use_best_found(ac, e4b);
 	}
+out:
 	ext4_unlock_group(ac->ac_sb, group);
 	ext4_mb_unload_buddy(e4b);
 
@@ -2380,12 +2405,12 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
 
 		k = mb_find_next_zero_bit(buddy, max, 0);
 		if (k >= max) {
+			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
+					e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0,
 				"%d free clusters of order %d. But found 0",
 				grp->bb_counters[i], i);
-			ext4_mark_group_bitmap_corrupted(ac->ac_sb,
-					 e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 		ac->ac_found++;
@@ -2436,12 +2461,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 			 * free blocks even though group info says we
 			 * have free blocks
 			 */
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But bitmap says 0",
 					free);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			break;
 		}
 
@@ -2467,12 +2492,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
 		if (WARN_ON(ex.fe_len <= 0))
 			break;
 		if (free < ex.fe_len) {
+			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
 					"%d free clusters as per "
 					"group info. But got %d blocks",
 					free, ex.fe_len);
-			ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
-					EXT4_GROUP_INFO_BBITMAP_CORRUPT);
 			/*
 			 * The number of free blocks differs. This mostly
 			 * indicate that the bitmap is corrupt. So exit
@@ -3725,7 +3750,7 @@ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp)
 	return count;
 }
 
-int ext4_mb_release(struct super_block *sb)
+void ext4_mb_release(struct super_block *sb)
 {
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	ext4_group_t i;
@@ -3801,8 +3826,6 @@ int ext4_mb_release(struct super_block *sb)
 	}
 
 	free_percpu(sbi->s_locality_groups);
-
-	return 0;
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
@@ -5284,7 +5307,7 @@ static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
  * the caller MUST hold group/inode locks.
  * TODO: optimize the case when there are no in-core structures yet
  */
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 			struct ext4_prealloc_space *pa)
 {
@@ -5334,11 +5357,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 		 */
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
-
-	return 0;
 }
 
-static noinline_for_stack int
+static noinline_for_stack void
 ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 				struct ext4_prealloc_space *pa)
 {
@@ -5352,13 +5373,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
 		ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
 			     e4b->bd_group, group, pa->pa_pstart);
-		return 0;
+		return;
 	}
 	mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
 	atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
 	trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
-
-	return 0;
 }
 
 /*
@@ -5479,7 +5498,7 @@ out_dbg:
  *
  * FIXME!! Make sure it is valid at all the call sites
  */
-void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
+void ext4_discard_preallocations(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -5491,9 +5510,8 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	struct rb_node *iter;
 	int err;
 
-	if (!S_ISREG(inode->i_mode)) {
+	if (!S_ISREG(inode->i_mode))
 		return;
-	}
 
 	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
@@ -5501,15 +5519,12 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
 	mb_debug(sb, "discard preallocation for inode %lu\n",
 		 inode->i_ino);
 	trace_ext4_discard_preallocations(inode,
-			atomic_read(&ei->i_prealloc_active), needed);
-
-	if (needed == 0)
-		needed = UINT_MAX;
+			atomic_read(&ei->i_prealloc_active));
 
 repeat:
 	/* first, collect all pa's in the inode */
 	write_lock(&ei->i_prealloc_lock);
-	for (iter = rb_first(&ei->i_prealloc_node); iter && needed;
+	for (iter = rb_first(&ei->i_prealloc_node); iter;
 	     iter = rb_next(iter)) {
 		pa = rb_entry(iter, struct ext4_prealloc_space,
 			      pa_node.inode_node);
@@ -5533,7 +5548,6 @@ repeat:
 			spin_unlock(&pa->pa_lock);
 			rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
 			list_add(&pa->u.pa_tmp_list, &list);
-			needed--;
 			continue;
 		}
 
@@ -5943,7 +5957,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
 /*
  * release all resource we used in allocation
  */
-static int ext4_mb_release_context(struct ext4_allocation_context *ac)
+static void ext4_mb_release_context(struct ext4_allocation_context *ac)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	struct ext4_prealloc_space *pa = ac->ac_pa;
@@ -5980,7 +5994,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
 	if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
 		mutex_unlock(&ac->ac_lg->lg_mutex);
 	ext4_mb_collect_stats(ac);
-	return 0;
 }
 
 static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
@@ -6761,6 +6774,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
 	bool set_trimmed = false;
 	void *bitmap;
 
+	if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+		return 0;
+
 	last = ext4_last_grp_cluster(sb, e4b->bd_group);
 	bitmap = e4b->bd_bitmap;
 	if (start == 0 && max >= last)