--- linux-4.18/fs/ext4/balloc.c	2019-11-28 14:55:26.506546036 +0300
+++ linux-4.18/fs/ext4/balloc.c	2019-12-02 11:21:50.565975537 +0300
@@ -404,7 +404,8 @@ verified:
  * Return buffer_head on success or NULL in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
+				 int ignore_locked)
 {
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -435,6 +436,13 @@ ext4_read_block_bitmap_nowait(struct
 	if (bitmap_uptodate(bh))
 		goto verify;
 
+	if (ignore_locked && buffer_locked(bh)) {
+		/* buffer under IO already, do not wait
+		 * if called for prefetching */
+		put_bh(bh);
+		return NULL;
+	}
+
 	lock_buffer(bh);
 	if (bitmap_uptodate(bh)) {
 		unlock_buffer(bh);
@@ -524,7 +532,7 @@ ext4_read_block_bitmap(struct super_b
 {
 	struct buffer_head *bh;
 
-	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	bh = ext4_read_block_bitmap_nowait(sb, block_group, 1);
 	if (!bh)
 		return NULL;
 	err = ext4_wait_block_bitmap(sb, block_group, bh);
--- linux-4.18/fs/ext4/ext4.h	2019-11-28 14:55:26.470545343 +0300
+++ linux-4.18/fs/ext4/ext4.h	2019-12-02 11:21:40.795779972 +0300
@@ -1446,6 +1446,8 @@ struct ext4_sb_info {
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
+	unsigned int s_mb_prefetch;
+	unsigned int s_mb_prefetch_limit;
 
 	/* stats for buddy allocator */
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
@@ -2401,7 +2403,8 @@ extern struct ext4_group_desc * ldisk
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 
 extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
-						ext4_group_t block_group);
+						ext4_group_t block_group,
+						int ignore_locked);
 extern int ext4_wait_block_bitmap(struct super_block *sb,
 				  ext4_group_t block_group,
 				  struct buffer_head *bh);
--- linux-4.18/fs/ext4/mballoc.c	2019-11-28 14:55:26.500545920 +0300
+++ linux-4.18/fs/ext4/mballoc.c	2019-12-02 11:21:46.656897291 +0300
@@ -868,7 +868,7 @@ static int ext4_mb_init_cache(struct
 			bh[i] = NULL;
 			continue;
 		}
-		if (!(bh[i] = ext4_read_block_bitmap_nowait(sb, group))) {
+		if (!(bh[i] = ext4_read_block_bitmap_nowait(sb, group, 0))) {
 			err = -ENOMEM;
 			goto out;
 		}
@@ -2104,6 +2112,87 @@ static int ext4_mb_good_group(struct
 	return 0;
 }
 
+/*
+ * each allocation context (i.e. a thread doing allocation) has own
+ * sliding prefetch window of @s_mb_prefetch size which starts at the
+ * very first goal and moves ahead of scaning.
+ * a side effect is that subsequent allocations will likely find
+ * the bitmaps in cache or at least in-flight.
+ */
+static void
+ext4_mb_prefetch(struct ext4_allocation_context *ac,
+		    ext4_group_t start)
+{
+	struct super_block *sb = ac->ac_sb;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_info *grp;
+	ext4_group_t group = start;
+	struct buffer_head *bh;
+	int nr;
+
+	/* limit prefetching at cr=0, otherwise mballoc can
+	 * spend a lot of time loading imperfect groups */
+	if (ac->ac_criteria < 2 && ac->ac_prefetch_ios >= sbi->s_mb_prefetch_limit)
+		return;
+
+	/* batch prefetching to get few READs in flight */
+	nr = ac->ac_prefetch - group;
+	if (ac->ac_prefetch < group)
+		/* wrapped to the first groups */
+		nr += ngroups;
+	if (nr > 0)
+		return;
+	BUG_ON(nr < 0);
+
+	nr = sbi->s_mb_prefetch;
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		/* align to flex_bg to get more bitmas with a single IO */
+		nr = (group / sbi->s_mb_prefetch) * sbi->s_mb_prefetch;
+		nr = nr + sbi->s_mb_prefetch - group;
+	}
+	while (nr-- > 0) {
+		grp = ext4_get_group_info(sb, group);
+		/* ignore empty groups - those will be skipped
+		 * during the scanning as well */
+		if (grp->bb_free > 0 && EXT4_MB_GRP_NEED_INIT(grp)) {
+			bh = ext4_read_block_bitmap_nowait(sb, group, 1);
+			if (bh && !IS_ERR(bh)) {
+				if (!buffer_uptodate(bh))
+					ac->ac_prefetch_ios++;
+				brelse(bh);
+			}
+		}
+		if (++group >= ngroups)
+			group = 0;
+	}
+	ac->ac_prefetch = group;
+}
+
+static void
+ext4_mb_prefetch_fini(struct ext4_allocation_context *ac)
+{
+	struct ext4_group_info *grp;
+	ext4_group_t group;
+	int nr, rc;
+
+	/* initialize last window of prefetched groups */
+	nr = ac->ac_prefetch_ios;
+	if (nr > EXT4_SB(ac->ac_sb)->s_mb_prefetch)
+		nr = EXT4_SB(ac->ac_sb)->s_mb_prefetch;
+	group = ac->ac_prefetch;
+	while (nr-- > 0) {
+		grp = ext4_get_group_info(ac->ac_sb, group);
+		if (grp->bb_free > 0 && EXT4_MB_GRP_NEED_INIT(grp)) {
+			rc = ext4_mb_init_group(ac->ac_sb, group);
+			if (rc)
+				break;
+		}
+		if (group-- == 0)
+			group = ext4_get_groups_count(ac->ac_sb) - 1;
+	}
+}
+
 static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
@@ -2176,6 +2264,7 @@ repeat:
 		 * from the goal value specified
 		 */
 		group = ac->ac_g_ex.fe_group;
+		ac->ac_prefetch = group;
 
 		for (i = 0; i < ngroups; group++, i++) {
 			int ret = 0;
@@ -2188,6 +2277,8 @@ repeat:
 			if (group >= ngroups)
 				group = 0;
 
+			ext4_mb_prefetch(ac, group);
+
 			/* This now checks without needing the buddy page */
 			ret = ext4_mb_good_group(ac, group, cr);
 			if (ret <= 0) {
@@ -2260,6 +2351,8 @@ repeat:
 out:
 	if (!err && ac->ac_status != AC_STATUS_FOUND && first_err)
 		err = first_err;
+	/* use prefetched bitmaps to init buddy so that read info is not lost */
+	ext4_mb_prefetch_fini(ac);
 	return err;
 }
 
@@ -2832,6 +2925,22 @@ int ext4_mb_init(struct super_block *
 		sbi->s_mb_large_req = sbi->s_stripe * 8;
 		sbi->s_mb_group_prealloc = sbi->s_stripe * 4;
 	}
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
+		/* a single flex group is supposed to be read by a single IO */
+		sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex;
+		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
+	} else {
+		sbi->s_mb_prefetch = 32;
+	}
+	if (sbi->s_mb_prefetch >= ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch = ext4_get_groups_count(sb);
+	/* now many real IOs to prefetch within a single allocation at cr=0
+	 * given cr=0 is an CPU-related optimization we shouldn't try to
+	 * load too many groups, at some point we should start to use what
+	 * we've got in memory.
+	 * with an average random access time 5ms, it'd take a second to get
+	 * 200 groups (* N with flex_bg), so let's make this limit 32 */
+	sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 32;
 
 	sbi->s_locality_groups = alloc_percpu(struct ext4_locality_group);
 	if (sbi->s_locality_groups == NULL) {
--- linux-4.18/fs/ext4/mballoc.h	2019-11-28 14:55:26.471545362 +0300
+++ linux-4.18/fs/ext4/mballoc.h	2019-12-02 11:21:57.028104886 +0300
@@ -177,6 +177,8 @@ struct ext4_allocation_context {
 	struct page *ac_buddy_page;
 	struct ext4_prealloc_space *ac_pa;
 	struct ext4_locality_group *ac_lg;
+	ext4_group_t ac_prefetch;
+	int ac_prefetch_ios; /* number of initialied prefetch IO */
 };
 
 #define AC_STATUS_CONTINUE	1
--- linux-4.18/fs/ext4/super.c	2019-11-28 14:55:26.502545959 +0300
+++ linux-4.18/fs/ext4/super.c	2019-11-28 20:07:48.104558177 +0300
@@ -190,6 +190,8 @@ EXT4_RW_ATTR_SBI_UI(msg_ratelimit_bur
 EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
 EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
 EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit);
 EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128);
 EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
 EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
@@ -223,6 +224,8 @@ static struct attribute *ext4_attrs[]
 	ATTR_LIST(errors_count),
 	ATTR_LIST(first_error_time),
 	ATTR_LIST(last_error_time),
+	ATTR_LIST(mb_prefetch),
+	ATTR_LIST(mb_prefetch_limit),
 	NULL,
 };