X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=block%2Fbio.c;h=1fab762e079be5ab0c1e41d67701209c8ddf3af9;hb=3b629f8d6dc04d3af94429c18fe17239d6fbe2c3;hp=44205dfb6b60aaa5c5f7a8c4aa176176a1907412;hpb=9b1111fa80df22c8cb6f9f8634693812cb958f4f;p=linux-2.6-microblaze.git

diff --git a/block/bio.c b/block/bio.c
index 44205dfb6b60..1319dd2aa0b8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -25,6 +25,11 @@
 #include "blk.h"
 #include "blk-rq-qos.h"
 
+struct bio_alloc_cache {
+	struct bio_list		free_list;
+	unsigned int		nr;
+};
+
 static struct biovec_slab {
 	int nr_vecs;
 	char *name;
@@ -246,12 +251,40 @@ static void bio_free(struct bio *bio)
 void bio_init(struct bio *bio, struct bio_vec *table,
 	      unsigned short max_vecs)
 {
-	memset(bio, 0, sizeof(*bio));
+	bio->bi_next = NULL;
+	bio->bi_bdev = NULL;
+	bio->bi_opf = 0;
+	bio->bi_flags = 0;
+	bio->bi_ioprio = 0;
+	bio->bi_write_hint = 0;
+	bio->bi_status = 0;
+	bio->bi_iter.bi_sector = 0;
+	bio->bi_iter.bi_size = 0;
+	bio->bi_iter.bi_idx = 0;
+	bio->bi_iter.bi_bvec_done = 0;
+	bio->bi_end_io = NULL;
+	bio->bi_private = NULL;
+#ifdef CONFIG_BLK_CGROUP
+	bio->bi_blkg = NULL;
+	bio->bi_issue.value = 0;
+#ifdef CONFIG_BLK_CGROUP_IOCOST
+	bio->bi_iocost_cost = 0;
+#endif
+#endif
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	bio->bi_crypt_context = NULL;
+#endif
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	bio->bi_integrity = NULL;
+#endif
+	bio->bi_vcnt = 0;
+
 	atomic_set(&bio->__bi_remaining, 1);
 	atomic_set(&bio->__bi_cnt, 1);
 
-	bio->bi_io_vec = table;
 	bio->bi_max_vecs = max_vecs;
+	bio->bi_io_vec = table;
+	bio->bi_pool = NULL;
 }
 EXPORT_SYMBOL(bio_init);
 
@@ -495,16 +528,11 @@ EXPORT_SYMBOL(bio_kmalloc);
 
 void zero_fill_bio(struct bio *bio)
 {
-	unsigned long flags;
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, iter) {
-		char *data = bvec_kmap_irq(&bv, &flags);
-		memset(data, 0, bv.bv_len);
-		flush_dcache_page(bv.bv_page);
-		bvec_kunmap_irq(data, &flags);
-	}
+	bio_for_each_segment(bv, bio, iter)
+		memzero_bvec(&bv);
 }
 EXPORT_SYMBOL(zero_fill_bio);
 
@@ -591,6 +619,53 @@ void guard_bio_eod(struct bio *bio)
 	bio_truncate(bio, maxsector << 9);
 }
 
+#define ALLOC_CACHE_MAX		512
+#define ALLOC_CACHE_SLACK	 64
+
+static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
+				  unsigned int nr)
+{
+	unsigned int i = 0;
+	struct bio *bio;
+
+	while ((bio = bio_list_pop(&cache->free_list)) != NULL) {
+		cache->nr--;
+		bio_free(bio);
+		if (++i == nr)
+			break;
+	}
+}
+
+static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct bio_set *bs;
+
+	bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead);
+	if (bs->cache) {
+		struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu);
+
+		bio_alloc_cache_prune(cache, -1U);
+	}
+	return 0;
+}
+
+static void bio_alloc_cache_destroy(struct bio_set *bs)
+{
+	int cpu;
+
+	if (!bs->cache)
+		return;
+
+	cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
+	for_each_possible_cpu(cpu) {
+		struct bio_alloc_cache *cache;
+
+		cache = per_cpu_ptr(bs->cache, cpu);
+		bio_alloc_cache_prune(cache, -1U);
+	}
+	free_percpu(bs->cache);
+}
+
 /**
  * bio_put - release a reference to a bio
  * @bio:   bio to release reference to
@@ -601,16 +676,23 @@ void guard_bio_eod(struct bio *bio)
  **/
 void bio_put(struct bio *bio)
 {
-	if (!bio_flagged(bio, BIO_REFFED))
-		bio_free(bio);
-	else {
+	if (unlikely(bio_flagged(bio, BIO_REFFED))) {
 		BIO_BUG_ON(!atomic_read(&bio->__bi_cnt));
+		if (!atomic_dec_and_test(&bio->__bi_cnt))
+			return;
+	}
 
-		/*
-		 * last put frees it
-		 */
-		if (atomic_dec_and_test(&bio->__bi_cnt))
-			bio_free(bio);
+	if (bio_flagged(bio, BIO_PERCPU_CACHE)) {
+		struct bio_alloc_cache *cache;
+
+		bio_uninit(bio);
+		cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
+		bio_list_add_head(&cache->free_list, bio);
+		if (++cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK)
+			bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK);
+		put_cpu();
+	} else {
+		bio_free(bio);
 	}
 }
 EXPORT_SYMBOL(bio_put);
@@ -979,6 +1061,14 @@ static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
 	return 0;
 }
 
+static void bio_put_pages(struct page **pages, size_t size, size_t off)
+{
+	size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);
+
+	for (i = 0; i < nr; i++)
+		put_page(pages[i]);
+}
+
 #define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))
 
 /**
@@ -1023,8 +1113,10 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 			if (same_page)
 				put_page(page);
 		} else {
-			if (WARN_ON_ONCE(bio_full(bio, len)))
-                                return -EINVAL;
+			if (WARN_ON_ONCE(bio_full(bio, len))) {
+				bio_put_pages(pages + i, left, offset);
+				return -EINVAL;
+			}
 			__bio_add_page(bio, page, len, offset);
 		}
 		offset = 0;
@@ -1069,6 +1161,7 @@ static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
 		len = min_t(size_t, PAGE_SIZE - offset, left);
 		if (bio_add_hw_page(q, bio, page, len, offset,
 				max_append_sectors, &same_page) != len) {
+			bio_put_pages(pages + i, left, offset);
 			ret = -EINVAL;
 			break;
 		}
@@ -1191,27 +1284,15 @@ EXPORT_SYMBOL(bio_advance);
 void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 			struct bio *src, struct bvec_iter *src_iter)
 {
-	struct bio_vec src_bv, dst_bv;
-	void *src_p, *dst_p;
-	unsigned bytes;
-
 	while (src_iter->bi_size && dst_iter->bi_size) {
-		src_bv = bio_iter_iovec(src, *src_iter);
-		dst_bv = bio_iter_iovec(dst, *dst_iter);
-
-		bytes = min(src_bv.bv_len, dst_bv.bv_len);
-
-		src_p = kmap_atomic(src_bv.bv_page);
-		dst_p = kmap_atomic(dst_bv.bv_page);
+		struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
+		struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
+		unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
+		void *src_buf;
 
-		memcpy(dst_p + dst_bv.bv_offset,
-		       src_p + src_bv.bv_offset,
-		       bytes);
-
-		kunmap_atomic(dst_p);
-		kunmap_atomic(src_p);
-
-		flush_dcache_page(dst_bv.bv_page);
+		src_buf = bvec_kmap_local(&src_bv);
+		memcpy_to_bvec(&dst_bv, src_buf);
+		kunmap_local(src_buf);
 
 		bio_advance_iter_single(src, src_iter, bytes);
 		bio_advance_iter_single(dst, dst_iter, bytes);
@@ -1375,8 +1456,7 @@ static inline bool bio_remaining_done(struct bio *bio)
  *
  *   bio_endio() can be called several times on a bio that has been chained
  *   using bio_chain().  The ->bi_end_io() function will only be called the
- *   last time.  At this point the BLK_TA_COMPLETE tracing event will be
- *   generated if BIO_TRACE_COMPLETION is set.
+ *   last time.
  **/
 void bio_endio(struct bio *bio)
 {
@@ -1389,6 +1469,11 @@ again:
 	if (bio->bi_bdev)
 		rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio);
 
+	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+		trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio);
+		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
+	}
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
@@ -1402,11 +1487,6 @@ again:
 		goto again;
 	}
 
-	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
-		trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio);
-		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
-	}
-
 	blk_throtl_bio_endio(bio);
 	/* release cgroup info */
 	bio_uninit(bio);
@@ -1503,6 +1583,7 @@ int biovec_init_pool(mempool_t *pool, int pool_entries)
  */
 void bioset_exit(struct bio_set *bs)
 {
+	bio_alloc_cache_destroy(bs);
 	if (bs->rescue_workqueue)
 		destroy_workqueue(bs->rescue_workqueue);
 	bs->rescue_workqueue = NULL;
@@ -1564,12 +1645,18 @@ int bioset_init(struct bio_set *bs,
 	    biovec_init_pool(&bs->bvec_pool, pool_size))
 		goto bad;
 
-	if (!(flags & BIOSET_NEED_RESCUER))
-		return 0;
-
-	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
-	if (!bs->rescue_workqueue)
-		goto bad;
+	if (flags & BIOSET_NEED_RESCUER) {
+		bs->rescue_workqueue = alloc_workqueue("bioset",
+							WQ_MEM_RECLAIM, 0);
+		if (!bs->rescue_workqueue)
+			goto bad;
+	}
+	if (flags & BIOSET_PERCPU_CACHE) {
+		bs->cache = alloc_percpu(struct bio_alloc_cache);
+		if (!bs->cache)
+			goto bad;
+		cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
+	}
 
 	return 0;
 bad:
@@ -1596,6 +1683,46 @@ int bioset_init_from_src(struct bio_set *bs, struct bio_set *src)
 }
 EXPORT_SYMBOL(bioset_init_from_src);
 
+/**
+ * bio_alloc_kiocb - Allocate a bio from bio_set based on kiocb
+ * @kiocb:	kiocb describing the IO
+ * @nr_iovecs:	number of iovecs to pre-allocate
+ * @bs:		bio_set to allocate from
+ *
+ * Description:
+ *    Like @bio_alloc_bioset, but pass in the kiocb. The kiocb is only
+ *    used to check if we should dip into the per-cpu bio_set allocation
+ *    cache. The allocation uses GFP_KERNEL internally. On return, the
+ *    bio is marked BIO_PERCPU_CACHEABLE, and the final put of the bio
+ *    MUST be done from process context, not hard/soft IRQ.
+ *
+ */
+struct bio *bio_alloc_kiocb(struct kiocb *kiocb, unsigned short nr_vecs,
+			    struct bio_set *bs)
+{
+	struct bio_alloc_cache *cache;
+	struct bio *bio;
+
+	if (!(kiocb->ki_flags & IOCB_ALLOC_CACHE) || nr_vecs > BIO_INLINE_VECS)
+		return bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
+
+	cache = per_cpu_ptr(bs->cache, get_cpu());
+	bio = bio_list_pop(&cache->free_list);
+	if (bio) {
+		cache->nr--;
+		put_cpu();
+		bio_init(bio, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs);
+		bio->bi_pool = bs;
+		bio_set_flag(bio, BIO_PERCPU_CACHE);
+		return bio;
+	}
+	put_cpu();
+	bio = bio_alloc_bioset(GFP_KERNEL, nr_vecs, bs);
+	bio_set_flag(bio, BIO_PERCPU_CACHE);
+	return bio;
+}
+EXPORT_SYMBOL_GPL(bio_alloc_kiocb);
+
 static int __init init_bio(void)
 {
 	int i;
@@ -1610,6 +1737,9 @@ static int __init init_bio(void)
 				SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 	}
 
+	cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL,
+					bio_cpu_dead);
+
 	if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS))
 		panic("bio: can't allocate bios\n");