1 files changed, 109 insertions, 111 deletions

diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 8589512c972e..73918e55bf04 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Moving/copying garbage collector
  *
@@ -9,9 +10,12 @@
 #include "debug.h"
 #include "request.h"
 
+#include <trace/events/bcache.h>
+
 struct moving_io {
+	struct closure		cl;
 	struct keybuf_key	*w;
-	struct search		s;
+	struct data_insert_op	op;
 	struct bbio		bio;
 };
 
@@ -19,158 +23,153 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
 {
 	struct cache_set *c = container_of(buf, struct cache_set,
 					   moving_gc_keys);
-	unsigned i;
-
-	for (i = 0; i < KEY_PTRS(k); i++) {
-		struct cache *ca = PTR_CACHE(c, k, i);
-		struct bucket *g = PTR_BUCKET(c, k, i);
+	unsigned int i;
 
-		if (GC_SECTORS_USED(g) < ca->gc_move_threshold)
+	for (i = 0; i < KEY_PTRS(k); i++)
+		if (ptr_available(c, k, i) &&
+		    GC_MOVE(PTR_BUCKET(c, k, i)))
 			return true;
-	}
 
 	return false;
 }
 
 /* Moving GC - IO loop */
 
-static void moving_io_destructor(struct closure *cl)
+static CLOSURE_CALLBACK(moving_io_destructor)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
+	closure_type(io, struct moving_io, cl);
+
 	kfree(io);
 }
 
-static void write_moving_finish(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving_finish)
 {
-	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
-	struct bio_vec *bv = bio_iovec_idx(bio, bio->bi_vcnt);
 
-	while (bv-- != bio->bi_io_vec)
-		__free_page(bv->bv_page);
+	bio_free_pages(bio);
 
-	pr_debug("%s %s", io->s.op.insert_collision
-		 ? "collision moving" : "moved",
-		 pkey(&io->w->key));
+	if (io->op.replace_collision)
+		trace_bcache_gc_copy_collision(&io->w->key);
 
-	bch_keybuf_del(&io->s.op.c->moving_gc_keys, io->w);
+	bch_keybuf_del(&io->op.c->moving_gc_keys, io->w);
 
-	atomic_dec_bug(&io->s.op.c->in_flight);
-	closure_wake_up(&io->s.op.c->moving_gc_wait);
+	up(&io->op.c->moving_in_flight);
 
 	closure_return_with_destructor(cl, moving_io_destructor);
 }
 
-static void read_moving_endio(struct bio *bio, int error)
+static void read_moving_endio(struct bio *bio)
 {
+	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct moving_io *io = container_of(bio->bi_private,
-					    struct moving_io, s.cl);
+					    struct moving_io, cl);
 
-	if (error)
-		io->s.error = error;
+	if (bio->bi_status)
+		io->op.status = bio->bi_status;
+	else if (!KEY_DIRTY(&b->key) &&
+		 ptr_stale(io->op.c, &b->key, 0)) {
+		io->op.status = BLK_STS_IOERR;
+	}
 
-	bch_bbio_endio(io->s.op.c, bio, error, "reading data to move");
+	bch_bbio_endio(io->op.c, bio, bio->bi_status, "reading data to move");
 }
 
 static void moving_init(struct moving_io *io)
 {
 	struct bio *bio = &io->bio.bio;
 
-	bio_init(bio);
+	bio_init_inline(bio, NULL,
+		 DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS), 0);
 	bio_get(bio);
-	bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
+	bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0);
 
-	bio->bi_size		= KEY_SIZE(&io->w->key) << 9;
-	bio->bi_max_vecs	= DIV_ROUND_UP(KEY_SIZE(&io->w->key),
-					       PAGE_SECTORS);
-	bio->bi_private		= &io->s.cl;
-	bio->bi_io_vec		= bio->bi_inline_vecs;
+	bio->bi_iter.bi_size	= KEY_SIZE(&io->w->key) << 9;
+	bio->bi_private		= &io->cl;
 	bch_bio_map(bio, NULL);
 }
 
-static void write_moving(struct closure *cl)
+static CLOSURE_CALLBACK(write_moving)
 {
-	struct search *s = container_of(cl, struct search, cl);
-	struct moving_io *io = container_of(s, struct moving_io, s);
-
-	if (!s->error) {
-		trace_bcache_write_moving(&io->bio.bio);
+	closure_type(io, struct moving_io, cl);
+	struct data_insert_op *op = &io->op;
 
+	if (!op->status) {
 		moving_init(io);
 
-		io->bio.bio.bi_sector	= KEY_START(&io->w->key);
-		s->op.lock		= -1;
-		s->op.write_prio	= 1;
-		s->op.cache_bio		= &io->bio.bio;
+		io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key);
+		op->write_prio		= 1;
+		op->bio			= &io->bio.bio;
 
-		s->writeback		= KEY_DIRTY(&io->w->key);
-		s->op.csum		= KEY_CSUM(&io->w->key);
+		op->writeback		= KEY_DIRTY(&io->w->key);
+		op->csum		= KEY_CSUM(&io->w->key);
 
-		s->op.type = BTREE_REPLACE;
-		bkey_copy(&s->op.replace, &io->w->key);
+		bkey_copy(&op->replace_key, &io->w->key);
+		op->replace		= true;
 
-		closure_init(&s->op.cl, cl);
-		bch_insert_data(&s->op.cl);
+		closure_call(&op->cl, bch_data_insert, NULL, cl);
 	}
 
-	continue_at(cl, write_moving_finish, NULL);
+	continue_at(cl, write_moving_finish, op->wq);
 }
 
-static void read_moving_submit(struct closure *cl)
+static CLOSURE_CALLBACK(read_moving_submit)
 {
-	struct search *s = container_of(cl, struct search, cl);
-	struct moving_io *io = container_of(s, struct moving_io, s);
+	closure_type(io, struct moving_io, cl);
 	struct bio *bio = &io->bio.bio;
 
-	trace_bcache_read_moving(bio);
-	bch_submit_bbio(bio, s->op.c, &io->w->key, 0);
+	bch_submit_bbio(bio, io->op.c, &io->w->key, 0);
 
-	continue_at(cl, write_moving, bch_gc_wq);
+	continue_at(cl, write_moving, io->op.wq);
 }
 
-static void read_moving(struct closure *cl)
+static void read_moving(struct cache_set *c)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, moving_gc);
 	struct keybuf_key *w;
 	struct moving_io *io;
 	struct bio *bio;
+	struct closure cl;
+
+	closure_init_stack(&cl);
 
 	/* XXX: if we error, background writeback could stall indefinitely */
 
 	while (!test_bit(CACHE_SET_STOPPING, &c->flags)) {
-		w = bch_keybuf_next_rescan(c, &c->moving_gc_keys, &MAX_KEY);
+		w = bch_keybuf_next_rescan(c, &c->moving_gc_keys,
+					   &MAX_KEY, moving_pred);
 		if (!w)
 			break;
 
-		io = kzalloc(sizeof(struct moving_io) + sizeof(struct bio_vec)
-			     * DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
-			     GFP_KERNEL);
+		if (ptr_stale(c, &w->key, 0)) {
+			bch_keybuf_del(&c->moving_gc_keys, w);
+			continue;
+		}
+
+		io = kzalloc(sizeof(*io) + sizeof(struct bio_vec) *
+				DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
+				GFP_KERNEL);
 		if (!io)
 			goto err;
 
 		w->private	= io;
 		io->w		= w;
-		io->s.op.inode	= KEY_INODE(&w->key);
-		io->s.op.c	= c;
+		io->op.inode	= KEY_INODE(&w->key);
+		io->op.c	= c;
+		io->op.wq	= c->moving_gc_wq;
 
 		moving_init(io);
 		bio = &io->bio.bio;
 
-		bio->bi_rw	= READ;
+		bio->bi_opf = REQ_OP_READ;
 		bio->bi_end_io	= read_moving_endio;
 
 		if (bch_bio_alloc_pages(bio, GFP_KERNEL))
 			goto err;
 
-		pr_debug("%s", pkey(&w->key));
-
-		closure_call(&io->s.cl, read_moving_submit, NULL, &c->gc.cl);
+		trace_bcache_gc_copy(&w->key);
 
-		if (atomic_inc_return(&c->in_flight) >= 64) {
-			closure_wait_event(&c->moving_gc_wait, cl,
-					   atomic_read(&c->in_flight) < 64);
-			continue_at(cl, read_moving, bch_gc_wq);
-		}
+		down(&c->moving_in_flight);
+		closure_call(&io->cl, read_moving_submit, NULL, &cl);
 	}
 
 	if (0) {
@@ -180,7 +179,7 @@ err:		if (!IS_ERR_OR_NULL(w->private))
 		bch_keybuf_del(&c->moving_gc_keys, w);
 	}
 
-	closure_return(cl);
+	closure_sync(&cl);
 }
 
 static bool bucket_cmp(struct bucket *l, struct bucket *r)
@@ -188,67 +187,66 @@ static bool bucket_cmp(struct bucket *l, struct bucket *r)
 	return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
 }
 
-static unsigned bucket_heap_top(struct cache *ca)
+static unsigned int bucket_heap_top(struct cache *ca)
 {
-	return GC_SECTORS_USED(heap_peek(&ca->heap));
+	struct bucket *b;
+
+	return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
 }
 
-void bch_moving_gc(struct closure *cl)
+void bch_moving_gc(struct cache_set *c)
 {
-	struct cache_set *c = container_of(cl, struct cache_set, gc.cl);
-	struct cache *ca;
+	struct cache *ca = c->cache;
 	struct bucket *b;
-	unsigned i;
+	unsigned long sectors_to_move, reserve_sectors;
 
 	if (!c->copy_gc_enabled)
-		closure_return(cl);
+		return;
 
 	mutex_lock(&c->bucket_lock);
 
-	for_each_cache(ca, c, i) {
-		unsigned sectors_to_move = 0;
-		unsigned reserve_sectors = ca->sb.bucket_size *
-			min(fifo_used(&ca->free), ca->free.size / 2);
+	sectors_to_move = 0;
+	reserve_sectors = ca->sb.bucket_size *
+			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
 
-		ca->heap.used = 0;
+	ca->heap.used = 0;
 
-		for_each_bucket(b, ca) {
-			if (!GC_SECTORS_USED(b))
-				continue;
+	for_each_bucket(b, ca) {
+		if (GC_MARK(b) == GC_MARK_METADATA ||
+		    !GC_SECTORS_USED(b) ||
+		    GC_SECTORS_USED(b) == ca->sb.bucket_size ||
+		    atomic_read(&b->pin))
+			continue;
 
-			if (!heap_full(&ca->heap)) {
-				sectors_to_move += GC_SECTORS_USED(b);
-				heap_add(&ca->heap, b, bucket_cmp);
-			} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
-				sectors_to_move -= bucket_heap_top(ca);
-				sectors_to_move += GC_SECTORS_USED(b);
-
-				ca->heap.data[0] = b;
-				heap_sift(&ca->heap, 0, bucket_cmp);
-			}
-		}
+		if (!heap_full(&ca->heap)) {
+			sectors_to_move += GC_SECTORS_USED(b);
+			heap_add(&ca->heap, b, bucket_cmp);
+		} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
+			sectors_to_move -= bucket_heap_top(ca);
+			sectors_to_move += GC_SECTORS_USED(b);
 
-		while (sectors_to_move > reserve_sectors) {
-			heap_pop(&ca->heap, b, bucket_cmp);
-			sectors_to_move -= GC_SECTORS_USED(b);
+			ca->heap.data[0] = b;
+			heap_sift(&ca->heap, 0, bucket_cmp);
 		}
+	}
 
-		ca->gc_move_threshold = bucket_heap_top(ca);
-
-		pr_debug("threshold %u", ca->gc_move_threshold);
+	while (sectors_to_move > reserve_sectors) {
+		heap_pop(&ca->heap, b, bucket_cmp);
+		sectors_to_move -= GC_SECTORS_USED(b);
 	}
 
+	while (heap_pop(&ca->heap, b, bucket_cmp))
+		SET_GC_MOVE(b, 1);
+
 	mutex_unlock(&c->bucket_lock);
 
 	c->moving_gc_keys.last_scanned = ZERO_KEY;
 
-	closure_init(&c->moving_gc, cl);
-	read_moving(&c->moving_gc);
-
-	closure_return(cl);
+	read_moving(c);
 }
 
 void bch_moving_init_cache_set(struct cache_set *c)
 {
-	bch_keybuf_init(&c->moving_gc_keys, moving_pred);
+	bch_keybuf_init(&c->moving_gc_keys);
+	sema_init(&c->moving_in_flight, 64);
 }