btrfs: keep track of free space bitmap trim status cleanliness

There is a cap in btrfs in the amount of free extents that a block group
can have. When it surpasses that threshold, future extents are placed
into bitmaps. Instead of keeping track of if a certain bit is trimmed or
not in a second bitmap, keep track of the relative state of the bitmap.

With async discard, trimming bitmaps becomes a more frequent operation.
As a trade off with simplicity, we keep track of if discarding a bitmap
is in progress. If we fully scan a bitmap and trim as necessary, the
bitmap is marked clean. This has some caveats as the min block size may
skip over regions deemed too small. But this should be a reasonable
trade off rather than keeping a second bitmap and making allocation
paths more complex. The downside is we may overtrim, but ideally the min
block size should prevent us from doing that too often and getting stuck
trimming pathological cases.

BTRFS_TRIM_STATE_TRIMMING is added to indicate a bitmap is in the
process of being trimmed. If additional free space is added to that
bitmap, the bit is cleared. A bitmap will be marked
BTRFS_TRIM_STATE_TRIMMED if the trimming code was able to reach the end
of it and the former is still set.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 80 insertions, 9 deletions

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 669809d5214e..063f4db44024 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1979,11 +1979,18 @@ again:
 
 static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
 			       struct btrfs_free_space *info, u64 offset,
-			       u64 bytes)
+			       u64 bytes, enum btrfs_trim_state trim_state)
 {
 	u64 bytes_to_set = 0;
 	u64 end;
 
+	/*
+	 * This is a tradeoff to make bitmap trim state minimal.  We mark the
+	 * whole bitmap untrimmed if at any point we add untrimmed regions.
+	 */
+	if (trim_state == BTRFS_TRIM_STATE_UNTRIMMED)
+		info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
+
 	end = info->offset + (u64)(BITS_PER_BITMAP * ctl->unit);
 
 	bytes_to_set = min(end - offset, bytes);
@@ -2058,10 +2065,12 @@ static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl,
 	struct btrfs_block_group *block_group = NULL;
 	int added = 0;
 	u64 bytes, offset, bytes_added;
+	enum btrfs_trim_state trim_state;
 	int ret;
 
 	bytes = info->bytes;
 	offset = info->offset;
+	trim_state = info->trim_state;
 
 	if (!ctl->op->use_bitmap(ctl, info))
 		return 0;
@@ -2096,8 +2105,8 @@ again:
 		}
 
 		if (entry->offset == offset_to_bitmap(ctl, offset)) {
-			bytes_added = add_bytes_to_bitmap(ctl, entry,
-							  offset, bytes);
+			bytes_added = add_bytes_to_bitmap(ctl, entry, offset,
+							  bytes, trim_state);
 			bytes -= bytes_added;
 			offset += bytes_added;
 		}
@@ -2116,7 +2125,8 @@ no_cluster_bitmap:
 		goto new_bitmap;
 	}
 
-	bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
+	bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes,
+					  trim_state);
 	bytes -= bytes_added;
 	offset += bytes_added;
 	added = 0;
@@ -2150,6 +2160,7 @@ new_bitmap:
 		/* allocate the bitmap */
 		info->bitmap = kmem_cache_zalloc(btrfs_free_space_bitmap_cachep,
 						 GFP_NOFS);
+		info->trim_state = BTRFS_TRIM_STATE_TRIMMED;
 		spin_lock(&ctl->tree_lock);
 		if (!info->bitmap) {
 			ret = -ENOMEM;
@@ -3324,6 +3335,37 @@ out:
 	return ret;
 }
 
+/*
+ * If we break out of trimming a bitmap prematurely, we should reset the
+ * trimming bit.  In a rather contrieved case, it's possible to race here so
+ * reset the state to BTRFS_TRIM_STATE_UNTRIMMED.
+ *
+ * start = start of bitmap
+ * end = near end of bitmap
+ *
+ * Thread 1:			Thread 2:
+ * trim_bitmaps(start)
+ *				trim_bitmaps(end)
+ *				end_trimming_bitmap()
+ * reset_trimming_bitmap()
+ */
+static void reset_trimming_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset)
+{
+	struct btrfs_free_space *entry;
+
+	spin_lock(&ctl->tree_lock);
+	entry = tree_search_offset(ctl, offset, 1, 0);
+	if (entry)
+		entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
+	spin_unlock(&ctl->tree_lock);
+}
+
+static void end_trimming_bitmap(struct btrfs_free_space *entry)
+{
+	if (btrfs_free_space_trimming_bitmap(entry))
+		entry->trim_state = BTRFS_TRIM_STATE_TRIMMED;
+}
+
 static int trim_bitmaps(struct btrfs_block_group *block_group,
 			u64 *total_trimmed, u64 start, u64 end, u64 minlen)
 {
@@ -3348,16 +3390,33 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
 		}
 
 		entry = tree_search_offset(ctl, offset, 1, 0);
-		if (!entry) {
+		if (!entry || btrfs_free_space_trimmed(entry)) {
 			spin_unlock(&ctl->tree_lock);
 			mutex_unlock(&ctl->cache_writeout_mutex);
 			next_bitmap = true;
 			goto next;
 		}
 
+		/*
+		 * Async discard bitmap trimming begins at by setting the start
+		 * to be key.objectid and the offset_to_bitmap() aligns to the
+		 * start of the bitmap.  This lets us know we are fully
+		 * scanning the bitmap rather than only some portion of it.
+		 */
+		if (start == offset)
+			entry->trim_state = BTRFS_TRIM_STATE_TRIMMING;
+
 		bytes = minlen;
 		ret2 = search_bitmap(ctl, entry, &start, &bytes, false);
 		if (ret2 || start >= end) {
+			/*
+			 * This keeps the invariant that all bytes are trimmed
+			 * if BTRFS_TRIM_STATE_TRIMMED is set on a bitmap.
+			 */
+			if (ret2 && !minlen)
+				end_trimming_bitmap(entry);
+			else
+				entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 			spin_unlock(&ctl->tree_lock);
 			mutex_unlock(&ctl->cache_writeout_mutex);
 			next_bitmap = true;
@@ -3366,6 +3425,7 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
 
 		bytes = min(bytes, end - start);
 		if (bytes < minlen) {
+			entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 			spin_unlock(&ctl->tree_lock);
 			mutex_unlock(&ctl->cache_writeout_mutex);
 			goto next;
@@ -3383,18 +3443,21 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
 
 		ret = do_trimming(block_group, total_trimmed, start, bytes,
 				  start, bytes, &trim_entry);
-		if (ret)
+		if (ret) {
+			reset_trimming_bitmap(ctl, offset);
 			break;
+		}
 next:
 		if (next_bitmap) {
 			offset += BITS_PER_BITMAP * ctl->unit;
+			start = offset;
 		} else {
 			start += bytes;
-			if (start >= offset + BITS_PER_BITMAP * ctl->unit)
-				offset += BITS_PER_BITMAP * ctl->unit;
 		}
 
 		if (fatal_signal_pending(current)) {
+			if (start != offset)
+				reset_trimming_bitmap(ctl, offset);
 			ret = -ERESTARTSYS;
 			break;
 		}
@@ -3448,7 +3511,9 @@ void btrfs_put_block_group_trimming(struct btrfs_block_group *block_group)
 int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen)
 {
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	int ret;
+	u64 rem = 0;
 
 	*trimmed = 0;
 
@@ -3465,6 +3530,10 @@ int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 		goto out;
 
 	ret = trim_bitmaps(block_group, trimmed, start, end, minlen);
+	div64_u64_rem(end, BITS_PER_BITMAP * ctl->unit, &rem);
+	/* If we ended in the middle of a bitmap, reset the trimming flag */
+	if (rem)
+		reset_trimming_bitmap(ctl, offset_to_bitmap(ctl, end));
 out:
 	btrfs_put_block_group_trimming(block_group);
 	return ret;
@@ -3649,6 +3718,7 @@ int test_add_free_space_entry(struct btrfs_block_group *cache,
 	struct btrfs_free_space_ctl *ctl = cache->free_space_ctl;
 	struct btrfs_free_space *info = NULL, *bitmap_info;
 	void *map = NULL;
+	enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_TRIMMED;
 	u64 bytes_added;
 	int ret;
 
@@ -3690,7 +3760,8 @@ again:
 		info = NULL;
 	}
 
-	bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes);
+	bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes,
+					  trim_state);
 
 	bytes -= bytes_added;
 	offset += bytes_added;