1 files changed, 57 insertions, 70 deletions

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index ed40d8600656..3ed39c823826 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -36,6 +36,7 @@
 #include <linux/sched/clock.h>
 #include <linux/rculist.h>
 #include <linux/delay.h>
+#include <linux/sort.h>
 #include <trace/events/bcache.h>
 
 /*
@@ -88,10 +89,9 @@
  * Test module load/unload
  */
 
-#define MAX_NEED_GC		64
-#define MAX_SAVE_PRIO		72
-#define MAX_GC_TIMES		100
-#define MIN_GC_NODES		100
+#define MAX_GC_TIMES_SHIFT	7  /* 128 loops */
+#define GC_NODES_MIN		10
+#define GC_SLEEP_MS_MIN		10
 #define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
@@ -149,19 +149,19 @@ void bch_btree_node_read_done(struct btree *b)
 {
 	const char *err = "bad btree header";
 	struct bset *i = btree_bset_first(b);
-	struct btree_iter iter;
+	struct btree_iter *iter;
 
 	/*
 	 * c->fill_iter can allocate an iterator with more memory space
 	 * than static MAX_BSETS.
 	 * See the comment arount cache_set->fill_iter.
 	 */
-	iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
-	iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
-	iter.heap.nr = 0;
+	iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
+	iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
+	iter->used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter.b = &b->keys;
+	iter->b = &b->keys;
 #endif
 
 	if (!i->seq)
@@ -199,7 +199,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i != b->keys.set[0].data && !i->keys)
 			goto err;
 
-		bch_btree_iter_push(&iter, i->start, bset_bkey_last(i));
+		bch_btree_iter_push(iter, i->start, bset_bkey_last(i));
 
 		b->written += set_blocks(i, block_bytes(b->c->cache));
 	}
@@ -211,7 +211,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i->seq == b->keys.set[0].data->seq)
 			goto err;
 
-	bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort);
+	bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort);
 
 	i = b->keys.set[0].data;
 	err = "short btree key";
@@ -223,7 +223,7 @@ void bch_btree_node_read_done(struct btree *b)
 		bch_bset_init_next(&b->keys, write_block(b),
 				   bset_magic(&b->c->cache->sb));
 out:
-	mempool_free(iter.heap.data, &b->c->fill_iter);
+	mempool_free(iter, &b->c->fill_iter);
 	return;
 err:
 	set_btree_node_io_error(b);
@@ -372,7 +372,7 @@ static void do_btree_node_write(struct btree *b)
 	SET_PTR_OFFSET(&k.key, 0, PTR_OFFSET(&k.key, 0) +
 		       bset_sector_offset(&b->keys, i));
 
-	if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) {
+	if (!bch_bio_alloc_pages(b->bio, GFP_NOWAIT)) {
 		struct bio_vec *bv;
 		void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1));
 		struct bvec_iter_all iter_all;
@@ -559,8 +559,6 @@ static void mca_data_alloc(struct btree *b, struct bkey *k, gfp_t gfp)
 	}
 }
 
-#define cmp_int(l, r)		((l > r) - (l < r))
-
 #ifdef CONFIG_PROVE_LOCKING
 static int btree_lock_cmp_fn(const struct lockdep_map *_a,
 			     const struct lockdep_map *_b)
@@ -1309,11 +1307,9 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 	uint8_t stale = 0;
 	unsigned int keys = 0, good_keys = 0;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bset_tree *t;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	gc->nodes++;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) {
@@ -1572,11 +1568,9 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 static unsigned int btree_gc_count_keys(struct btree *b)
 {
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	unsigned int ret = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
 		ret += bkey_u64s(k);
 
@@ -1585,29 +1579,29 @@ static unsigned int btree_gc_count_keys(struct btree *b)
 
 static size_t btree_gc_min_nodes(struct cache_set *c)
 {
-	size_t min_nodes;
+	size_t min_nodes = GC_NODES_MIN;
 
-	/*
-	 * Since incremental GC would stop 100ms when front
-	 * side I/O comes, so when there are many btree nodes,
-	 * if GC only processes constant (100) nodes each time,
-	 * GC would last a long time, and the front side I/Os
-	 * would run out of the buckets (since no new bucket
-	 * can be allocated during GC), and be blocked again.
-	 * So GC should not process constant nodes, but varied
-	 * nodes according to the number of btree nodes, which
-	 * realized by dividing GC into constant(100) times,
-	 * so when there are many btree nodes, GC can process
-	 * more nodes each time, otherwise, GC will process less
-	 * nodes each time (but no less than MIN_GC_NODES)
-	 */
-	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
-	if (min_nodes < MIN_GC_NODES)
-		min_nodes = MIN_GC_NODES;
+	if (atomic_read(&c->search_inflight) == 0) {
+		size_t n = c->gc_stats.nodes >> MAX_GC_TIMES_SHIFT;
+
+		if (min_nodes < n)
+			min_nodes = n;
+	}
 
 	return min_nodes;
 }
 
+static uint64_t btree_gc_sleep_ms(struct cache_set *c)
+{
+	uint64_t sleep_ms;
+
+	if (atomic_read(&c->bucket_wait_cnt) > 0)
+		sleep_ms = GC_SLEEP_MS_MIN;
+	else
+		sleep_ms = GC_SLEEP_MS;
+
+	return sleep_ms;
+}
 
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
@@ -1615,18 +1609,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	int ret = 0;
 	bool should_rewrite;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct gc_merge_info r[GC_MERGE_NODES];
 	struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
+	bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
 
 	for (i = r; i < r + ARRAY_SIZE(r); i++)
 		i->b = ERR_PTR(-EINTR);
 
 	while (1) {
-		k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
+		k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad);
 		if (k) {
 			r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
 						  true, b);
@@ -1675,8 +1669,7 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
-		if (atomic_read(&b->c->search_inflight) &&
-		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
+		if (gc->nodes >= (gc->nodes_pre + btree_gc_min_nodes(b->c))) {
 			gc->nodes_pre =  gc->nodes;
 			ret = -EAGAIN;
 			break;
@@ -1853,8 +1846,8 @@ static void bch_btree_gc(struct cache_set *c)
 		cond_resched();
 
 		if (ret == -EAGAIN)
-			schedule_timeout_interruptible(msecs_to_jiffies
-						       (GC_SLEEP_MS));
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(btree_gc_sleep_ms(c)));
 		else if (ret)
 			pr_warn("gc failed!\n");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -1921,9 +1914,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 {
 	int ret = 0;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
-
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	struct btree_iter_stack iter;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(b->c, b->level, k);
@@ -1931,10 +1922,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	bch_initial_mark_key(b->c, b->level + 1, &b->key);
 
 	if (b->level) {
-		bch_btree_iter_init(&b->keys, &iter, NULL);
+		bch_btree_iter_stack_init(&b->keys, &iter, NULL);
 
 		do {
-			k = bch_btree_iter_next_filter(&iter, &b->keys,
+			k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad);
 			if (k) {
 				btree_node_prefetch(b, k);
@@ -1962,7 +1953,7 @@ static int bch_btree_check_thread(void *arg)
 	struct btree_check_info *info = arg;
 	struct btree_check_state *check_state = info->state;
 	struct cache_set *c = check_state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
@@ -1970,11 +1961,9 @@ static int bch_btree_check_thread(void *arg)
 	cur_idx = prev_idx = 0;
 	ret = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/* root node keys are checked before thread created */
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -1992,7 +1981,7 @@ static int bch_btree_check_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -2065,11 +2054,9 @@ int bch_btree_check(struct cache_set *c)
 	int ret = 0;
 	int i;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct btree_check_state check_state;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/* check and mark root node keys */
 	for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(c, c->root->level, k);
@@ -2563,12 +2550,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 	if (b->level) {
 		struct bkey *k;
-		struct btree_iter iter;
+		struct btree_iter_stack iter;
 
-		min_heap_init(&iter.heap, NULL, MAX_BSETS);
-		bch_btree_iter_init(&b->keys, &iter, from);
+		bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
+		while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad))) {
 			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
@@ -2597,12 +2583,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 {
 	int ret = MAP_CONTINUE;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&b->keys, &iter, from);
+	bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
+	while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
 			: bcache_btree(map_keys_recurse, k,
@@ -2836,7 +2822,8 @@ void bch_btree_exit(void)
 
 int __init bch_btree_init(void)
 {
-	btree_io_wq = alloc_workqueue("bch_btree_io", WQ_MEM_RECLAIM, 0);
+	btree_io_wq = alloc_workqueue("bch_btree_io",
+				      WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!btree_io_wq)
 		return -ENOMEM;