1 files changed, 166 insertions, 100 deletions

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 0307702d114d..e823731110e3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/nospec.h>
 #include <linux/backing-dev.h>
+#include <linux/freezer.h>
 #include <trace/events/ext4.h>
 
 #ifdef CONFIG_EXT4_DEBUG
@@ -1801,6 +1802,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
 		return err;
 
 	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) {
@@ -1808,6 +1812,7 @@ int 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);
 
@@ -1834,12 +1839,10 @@ 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 */
@@ -1872,6 +1875,7 @@ 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);
 
@@ -3091,9 +3095,9 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 				struct ext4_allocation_request *ar)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
+	struct ext4_super_block *es = sbi->s_es;
 	int bsbits, max;
-	ext4_lblk_t end;
-	loff_t size, start_off;
+	loff_t size, start_off, end;
 	loff_t orig_size __maybe_unused;
 	ext4_lblk_t start;
 	struct ext4_inode_info *ei = EXT4_I(ac->ac_inode);
@@ -3122,7 +3126,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 
 	/* first, let's learn actual file size
 	 * given current request is allocated */
-	size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
+	size = extent_logical_end(sbi, &ac->ac_o_ex);
 	size = size << bsbits;
 	if (size < i_size_read(ac->ac_inode))
 		size = i_size_read(ac->ac_inode);
@@ -3172,6 +3176,19 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	size = size >> bsbits;
 	start = start_off >> bsbits;
 
+	/*
+	 * For tiny groups (smaller than 8MB) the chosen allocation
+	 * alignment may be larger than group size. Make sure the
+	 * alignment does not move allocation to a different group which
+	 * makes mballoc fail assertions later.
+	 */
+	start = max(start, rounddown(ac->ac_o_ex.fe_logical,
+			(ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb)));
+
+	/* avoid unnecessary preallocation that may trigger assertions */
+	if (start + size > EXT_MAX_BLOCKS)
+		size = EXT_MAX_BLOCKS - start;
+
 	/* don't cover already allocated blocks in selected range */
 	if (ar->pleft && start <= ar->lleft) {
 		size -= ar->lleft + 1 - start;
@@ -3192,7 +3209,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	/* check we don't cross already preallocated blocks */
 	rcu_read_lock();
 	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
-		ext4_lblk_t pa_end;
+		loff_t pa_end;
 
 		if (pa->pa_deleted)
 			continue;
@@ -3202,8 +3219,7 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 			continue;
 		}
 
-		pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
-						  pa->pa_len);
+		pa_end = pa_logical_end(EXT4_SB(ac->ac_sb), pa);
 
 		/* PA must not overlap original request */
 		BUG_ON(!(ac->ac_o_ex.fe_logical >= pa_end ||
@@ -3232,12 +3248,11 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	/* XXX: extra loop to check we really don't overlap preallocations */
 	rcu_read_lock();
 	list_for_each_entry_rcu(pa, &ei->i_prealloc_list, pa_inode_list) {
-		ext4_lblk_t pa_end;
+		loff_t pa_end;
 
 		spin_lock(&pa->pa_lock);
 		if (pa->pa_deleted == 0) {
-			pa_end = pa->pa_lstart + EXT4_C2B(EXT4_SB(ac->ac_sb),
-							  pa->pa_len);
+			pa_end = pa_logical_end(EXT4_SB(ac->ac_sb), pa);
 			BUG_ON(!(start >= pa_end || end <= pa->pa_lstart));
 		}
 		spin_unlock(&pa->pa_lock);
@@ -3262,18 +3277,21 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	ac->ac_g_ex.fe_len = EXT4_NUM_B2C(sbi, size);
 
 	/* define goal start in order to merge */
-	if (ar->pright && (ar->lright == (start + size))) {
+	if (ar->pright && (ar->lright == (start + size)) &&
+	    ar->pright >= size &&
+	    ar->pright - size >= le32_to_cpu(es->s_first_data_block)) {
 		/* merge to the right */
 		ext4_get_group_no_and_offset(ac->ac_sb, ar->pright - size,
-						&ac->ac_f_ex.fe_group,
-						&ac->ac_f_ex.fe_start);
+						&ac->ac_g_ex.fe_group,
+						&ac->ac_g_ex.fe_start);
 		ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
 	}
-	if (ar->pleft && (ar->lleft + 1 == start)) {
+	if (ar->pleft && (ar->lleft + 1 == start) &&
+	    ar->pleft + 1 < ext4_blocks_count(es)) {
 		/* merge to the left */
 		ext4_get_group_no_and_offset(ac->ac_sb, ar->pleft + 1,
-						&ac->ac_f_ex.fe_group,
-						&ac->ac_f_ex.fe_start);
+						&ac->ac_g_ex.fe_group,
+						&ac->ac_g_ex.fe_start);
 		ac->ac_flags |= EXT4_MB_HINT_TRY_GOAL;
 	}
 
@@ -3365,6 +3383,7 @@ static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
 	BUG_ON(start < pa->pa_pstart);
 	BUG_ON(end > pa->pa_pstart + EXT4_C2B(sbi, pa->pa_len));
 	BUG_ON(pa->pa_free < len);
+	BUG_ON(ac->ac_b_ex.fe_len <= 0);
 	pa->pa_free -= len;
 
 	mb_debug(1, "use %llu/%u from inode pa %p\n", start, len, pa);
@@ -3447,8 +3466,7 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac)
 		/* all fields in this condition don't change,
 		 * so we can skip locking for them */
 		if (ac->ac_o_ex.fe_logical < pa->pa_lstart ||
-		    ac->ac_o_ex.fe_logical >= (pa->pa_lstart +
-					       EXT4_C2B(sbi, pa->pa_len)))
+		    ac->ac_o_ex.fe_logical >= pa_logical_end(sbi, pa))
 			continue;
 
 		/* non-extent files can't have physical blocks past 2^32 */
@@ -3669,10 +3687,11 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		return -ENOMEM;
 
 	if (ac->ac_b_ex.fe_len < ac->ac_g_ex.fe_len) {
-		int winl;
-		int wins;
-		int win;
-		int offs;
+		struct ext4_free_extent ex = {
+			.fe_logical = ac->ac_g_ex.fe_logical,
+			.fe_len = ac->ac_g_ex.fe_len,
+		};
+		loff_t orig_goal_end = extent_logical_end(sbi, &ex);
 
 		/* we can't allocate as much as normalizer wants.
 		 * so, found space must get proper lstart
@@ -3680,26 +3699,34 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
 		BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
 
-		/* we're limited by original request in that
-		 * logical block must be covered any way
-		 * winl is window we can move our chunk within */
-		winl = ac->ac_o_ex.fe_logical - ac->ac_g_ex.fe_logical;
+		/*
+		 * Use the below logic for adjusting best extent as it keeps
+		 * fragmentation in check while ensuring logical range of best
+		 * extent doesn't overflow out of goal extent:
+		 *
+		 * 1. Check if best ex can be kept at end of goal and still
+		 *    cover original start
+		 * 2. Else, check if best ex can be kept at start of goal and
+		 *    still cover original start
+		 * 3. Else, keep the best ex at start of original request.
+		 */
+		ex.fe_len = ac->ac_b_ex.fe_len;
 
-		/* also, we should cover whole original request */
-		wins = EXT4_C2B(sbi, ac->ac_b_ex.fe_len - ac->ac_o_ex.fe_len);
+		ex.fe_logical = orig_goal_end - EXT4_C2B(sbi, ex.fe_len);
+		if (ac->ac_o_ex.fe_logical >= ex.fe_logical)
+			goto adjust_bex;
 
-		/* the smallest one defines real window */
-		win = min(winl, wins);
+		ex.fe_logical = ac->ac_g_ex.fe_logical;
+		if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex))
+			goto adjust_bex;
 
-		offs = ac->ac_o_ex.fe_logical %
-			EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
-		if (offs && offs < win)
-			win = offs;
+		ex.fe_logical = ac->ac_o_ex.fe_logical;
+adjust_bex:
+		ac->ac_b_ex.fe_logical = ex.fe_logical;
 
-		ac->ac_b_ex.fe_logical = ac->ac_o_ex.fe_logical -
-			EXT4_NUM_B2C(sbi, win);
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
 		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
+		BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end);
 	}
 
 	/* preallocation can change ac_b_ex, thus we store actually
@@ -3886,7 +3913,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
 	trace_ext4_mb_release_group_pa(sb, pa);
 	BUG_ON(pa->pa_deleted == 0);
 	ext4_get_group_no_and_offset(sb, pa->pa_pstart, &group, &bit);
-	BUG_ON(group != e4b->bd_group && pa->pa_len != 0);
+	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;
+	}
 	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);
@@ -4203,7 +4234,7 @@ static void ext4_mb_group_or_file(struct ext4_allocation_context *ac)
 	if (unlikely(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY))
 		return;
 
-	size = ac->ac_o_ex.fe_logical + EXT4_C2B(sbi, ac->ac_o_ex.fe_len);
+	size = extent_logical_end(sbi, &ac->ac_o_ex);
 	isize = (i_size_read(ac->ac_inode) + ac->ac_sb->s_blocksize - 1)
 		>> bsbits;
 
@@ -4920,8 +4951,8 @@ do_more:
 		 * them with group lock_held
 		 */
 		if (test_opt(sb, DISCARD)) {
-			err = ext4_issue_discard(sb, block_group, bit, count,
-						 NULL);
+			err = ext4_issue_discard(sb, block_group, bit,
+						 count_clusters, NULL);
 			if (err && err != -EOPNOTSUPP)
 				ext4_msg(sb, KERN_WARNING, "discard request in"
 					 " group:%d block:%d count:%lu failed"
@@ -5129,19 +5160,19 @@ error_return:
  * @sb:		super block for the file system
  * @start:	starting block of the free extent in the alloc. group
  * @count:	number of blocks to TRIM
- * @group:	alloc. group we are working with
  * @e4b:	ext4 buddy for the group
  *
  * Trim "count" blocks starting at "start" in the "group". To assure that no
  * one will allocate those blocks, mark it as used in buddy bitmap. This must
  * be called with under the group lock.
  */
-static int ext4_trim_extent(struct super_block *sb, int start, int count,
-			     ext4_group_t group, struct ext4_buddy *e4b)
+static int ext4_trim_extent(struct super_block *sb,
+		int start, int count, struct ext4_buddy *e4b)
 __releases(bitlock)
 __acquires(bitlock)
 {
 	struct ext4_free_extent ex;
+	ext4_group_t group = e4b->bd_group;
 	int ret = 0;
 
 	trace_ext4_trim_extent(sb, group, start, count);
@@ -5164,6 +5195,81 @@ __acquires(bitlock)
 	return ret;
 }
 
+static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,
+					   ext4_group_t grp)
+{
+	unsigned long nr_clusters_in_group;
+
+	if (grp < (ext4_get_groups_count(sb) - 1))
+		nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb);
+	else
+		nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) -
+					ext4_group_first_block_no(sb, grp))
+				       >> EXT4_CLUSTER_BITS(sb);
+
+	return nr_clusters_in_group - 1;
+}
+
+static bool ext4_trim_interrupted(void)
+{
+	return fatal_signal_pending(current) || freezing(current);
+}
+
+static int ext4_try_to_trim_range(struct super_block *sb,
+		struct ext4_buddy *e4b, ext4_grpblk_t start,
+		ext4_grpblk_t max, ext4_grpblk_t minblocks)
+{
+	ext4_grpblk_t next, count, free_count, last, origin_start;
+	bool set_trimmed = false;
+	void *bitmap;
+
+	last = ext4_last_grp_cluster(sb, e4b->bd_group);
+	bitmap = e4b->bd_bitmap;
+	if (start == 0 && max >= last)
+		set_trimmed = true;
+	origin_start = start;
+	start = max(e4b->bd_info->bb_first_free, start);
+	count = 0;
+	free_count = 0;
+
+	while (start <= max) {
+		start = mb_find_next_zero_bit(bitmap, max + 1, start);
+		if (start > max)
+			break;
+
+		next = mb_find_next_bit(bitmap, last + 1, start);
+		if (origin_start == 0 && next >= last)
+			set_trimmed = true;
+
+		if ((next - start) >= minblocks) {
+			int ret = ext4_trim_extent(sb, start, next - start, e4b);
+
+			if (ret && ret != -EOPNOTSUPP)
+				return count;
+			count += next - start;
+		}
+		free_count += next - start;
+		start = next + 1;
+
+		if (ext4_trim_interrupted())
+			return count;
+
+		if (need_resched()) {
+			ext4_unlock_group(sb, e4b->bd_group);
+			cond_resched();
+			ext4_lock_group(sb, e4b->bd_group);
+		}
+
+		if ((e4b->bd_info->bb_free - free_count) < minblocks)
+			break;
+	}
+
+	if (set_trimmed)
+		EXT4_MB_GRP_SET_TRIMMED(e4b->bd_info);
+
+	return count;
+}
+
 /**
  * ext4_trim_all_free -- function to trim all free space in alloc. group
  * @sb:			super block for file system
@@ -5187,10 +5293,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 		   ext4_grpblk_t start, ext4_grpblk_t max,
 		   ext4_grpblk_t minblocks)
 {
-	void *bitmap;
-	ext4_grpblk_t next, count = 0, free_count = 0;
 	struct ext4_buddy e4b;
-	int ret = 0;
+	int ret;
 
 	trace_ext4_trim_all_free(sb, group, start, max);
 
@@ -5200,58 +5304,20 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 			     ret, group);
 		return ret;
 	}
-	bitmap = e4b.bd_bitmap;
 
 	ext4_lock_group(sb, group);
-	if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) &&
-	    minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks))
-		goto out;
-
-	start = (e4b.bd_info->bb_first_free > start) ?
-		e4b.bd_info->bb_first_free : start;
 
-	while (start <= max) {
-		start = mb_find_next_zero_bit(bitmap, max + 1, start);
-		if (start > max)
-			break;
-		next = mb_find_next_bit(bitmap, max + 1, start);
-
-		if ((next - start) >= minblocks) {
-			ret = ext4_trim_extent(sb, start,
-					       next - start, group, &e4b);
-			if (ret && ret != -EOPNOTSUPP)
-				break;
-			ret = 0;
-			count += next - start;
-		}
-		free_count += next - start;
-		start = next + 1;
-
-		if (fatal_signal_pending(current)) {
-			count = -ERESTARTSYS;
-			break;
-		}
-
-		if (need_resched()) {
-			ext4_unlock_group(sb, group);
-			cond_resched();
-			ext4_lock_group(sb, group);
-		}
-
-		if ((e4b.bd_info->bb_free - free_count) < minblocks)
-			break;
-	}
+	if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
+	    minblocks < EXT4_SB(sb)->s_last_trim_minblks)
+		ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
+	else
+		ret = 0;
 
-	if (!ret) {
-		ret = count;
-		EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
-	}
-out:
 	ext4_unlock_group(sb, group);
 	ext4_mb_unload_buddy(&e4b);
 
 	ext4_debug("trimmed %d blocks in the group %d\n",
-		count, group);
+		ret, group);
 
 	return ret;
 }
@@ -5296,7 +5362,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		if (minlen > EXT4_CLUSTERS_PER_GROUP(sb))
 			goto out;
 	}
-	if (end >= max_blks)
+	if (end >= max_blks - 1)
 		end = max_blks - 1;
 	if (end <= first_data_blk)
 		goto out;
@@ -5313,6 +5379,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
 
 	for (group = first_group; group <= last_group; group++) {
+		if (ext4_trim_interrupted())
+			break;
 		grp = ext4_get_group_info(sb, group);
 		/* We only do this if the grp has never been initialized */
 		if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
@@ -5329,10 +5397,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 		 */
 		if (group == last_group)
 			end = last_cluster;
-
 		if (grp->bb_free >= minlen) {
 			cnt = ext4_trim_all_free(sb, group, first_cluster,
-						end, minlen);
+						 end, minlen);
 			if (cnt < 0) {
 				ret = cnt;
 				break;
@@ -5348,7 +5415,7 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
 	}
 
 	if (!ret)
-		atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
+		EXT4_SB(sb)->s_last_trim_minblks = minlen;
 
 out:
 	range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits;
@@ -5377,8 +5444,7 @@ ext4_mballoc_query_range(
 
 	ext4_lock_group(sb, group);
 
-	start = (e4b.bd_info->bb_first_free > start) ?
-		e4b.bd_info->bb_first_free : start;
+	start = max(e4b.bd_info->bb_first_free, start);
 	if (end >= EXT4_CLUSTERS_PER_GROUP(sb))
 		end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;