From a30a3d2067536cbcce26c055e70cc3a6ae4fd45c Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Fri, 17 Jan 2020 09:07:39 -0500
References: bsc#1174354
Git-commit: a30a3d2067536cbcce26c055e70cc3a6ae4fd45c
Patch-mainline: v5.6-rc1
Subject: [PATCH] btrfs: take overcommit into account in inc_block_group_ro

inc_block_group_ro does a calculation to see if we have enough room left
over if we mark this block group as read only in order to see if it's ok
to mark the block group as read only.

The problem is this calculation _only_ works for data, where our used is
always less than our total.  For metadata we will overcommit, so this
will almost always fail for metadata.

Fix this by exporting btrfs_can_overcommit, and then see if we have
enough space to remove the remaining free space in the block group we
are trying to mark read only.  If we do then we can mark this block
group as read only.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.c |   37 ++++++++++++++++++++++++++-----------
 fs/btrfs/space-info.c  |   11 ++++++-----
 fs/btrfs/space-info.h  |    3 +++
 3 files changed, 35 insertions(+), 16 deletions(-)

--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1172,7 +1172,6 @@ static int inc_block_group_ro(struct btr
 {
 	struct btrfs_space_info *sinfo = cache->space_info;
 	u64 num_bytes;
-	u64 sinfo_used;
 	int ret = -ENOSPC;
 
 	spin_lock(&sinfo->lock);
@@ -1199,19 +1199,38 @@ static int inc_block_group_ro(struct btr
 
 	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
 		    cache->bytes_super - btrfs_block_group_used(&cache->item);
-	sinfo_used = btrfs_space_info_used(sinfo, true);
 
 	/*
-	 * sinfo_used + num_bytes should always <= sinfo->total_bytes.
-	 *
-	 * Here we make sure if we mark this bg RO, we still have enough
-	 * free space as buffer.
+	 * Data never overcommits, even in mixed mode, so do just the straight
+	 * check of left over space in how much we have allocated.
 	 */
-	if (force || (sinfo_used + num_bytes <= sinfo->total_bytes)) {
+	if (force) {
+		ret = 0;
+	} else if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA) {
+		u64 sinfo_used = btrfs_space_info_used(sinfo, true);
+
+		/*
+		 * Here we make sure if we mark this bg RO, we still have enough
+		 * free space as buffer.
+		 */
+		if (sinfo_used + num_bytes <= sinfo->total_bytes)
+			ret = 0;
+	} else {
+		/*
+		 * We overcommit metadata, so we need to do the
+		 * btrfs_can_overcommit check here, and we need to pass in
+		 * BTRFS_RESERVE_NO_FLUSH to give ourselves the most amount of
+		 * leeway to allow us to mark this block group as read only.
+		 */
+		if (btrfs_can_overcommit(cache->fs_info, sinfo, num_bytes,
+					 BTRFS_RESERVE_NO_FLUSH))
+			ret = 0;
+	}
+
+	if (!ret) {
 		sinfo->bytes_readonly += num_bytes;
 		cache->ro++;
 		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
-		ret = 0;
 	}
 out:
 	spin_unlock(&cache->lock);
@@ -1207,9 +1225,6 @@ out:
 		btrfs_info(cache->fs_info,
 			"unable to make block group %llu ro",
 			cache->key.objectid);
-		btrfs_info(cache->fs_info,
-			"sinfo_used=%llu bg_num_bytes=%llu",
-			sinfo_used, num_bytes);
 		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0);
 	}
 	return ret;
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -182,7 +182,7 @@ static inline u64 calc_global_rsv_need_s
 	return (global->size << 1);
 }
 
-int can_overcommit(struct btrfs_fs_info *fs_info,
+int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
 			 struct btrfs_space_info *space_info, u64 bytes,
 			 enum btrfs_reserve_flush_enum flush)
 {
@@ -251,7 +251,7 @@ again:
 		ticket = list_first_entry(head, struct reserve_ticket,
 					  list);
 		if ((used + ticket->bytes <= space_info->total_bytes) ||
-		    can_overcommit(fs_info, space_info, ticket->bytes, flush)) {
+		    btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) {
 			btrfs_space_info_update_bytes_may_use(fs_info,
 							      space_info,
 							      ticket->bytes);
@@ -653,14 +653,14 @@ btrfs_calc_reclaim_metadata_size(struct
 		return to_reclaim;
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
-	if (can_overcommit(fs_info, space_info, to_reclaim,
+	if (btrfs_can_overcommit(fs_info, space_info, to_reclaim,
 			   BTRFS_RESERVE_FLUSH_ALL))
 		return 0;
 
 	used = space_info->bytes_used + space_info->bytes_reserved +
 	       space_info->bytes_pinned + space_info->bytes_readonly +
 	       space_info->bytes_may_use;
-	if (can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
+	if (btrfs_can_overcommit(fs_info, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -1025,7 +1025,7 @@ static int __reserve_metadata_bytes(stru
 	 */
 	if (!pending_tickets  &&
 	    ((used + orig_bytes <= space_info->total_bytes) ||
-	     can_overcommit(fs_info, space_info, orig_bytes, flush))) {
+	     btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) {
 		btrfs_space_info_update_bytes_may_use(fs_info, space_info,
 						      orig_bytes);
 		ret = 0;
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -128,6 +128,9 @@ int btrfs_reserve_metadata_bytes(struct
 				 enum btrfs_reserve_flush_enum flush);
 void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
 				struct btrfs_space_info *space_info);
+int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
+		        struct btrfs_space_info *space_info, u64 bytes,
+			enum btrfs_reserve_flush_enum flush);
 
 static inline void btrfs_space_info_free_bytes_may_use(
 				struct btrfs_fs_info *fs_info,