Merge branch 'for-3.20/core' into for-3.20/drivers

We need the tagging changes for the libata conversion.

block/blk-lib.c

@@ -283,23 +283,45 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @discard:	whether to discard the block range
  *
  * Description:
- *  Generate and issue number of bios with zerofiled pages.
+
+ *  Zero-fill a block range.  If the discard flag is set and the block
+ *  device guarantees that subsequent READ operations to the block range
+ *  in question will return zeroes, the blocks will be discarded. Should
+ *  the discard request fail, if the discard flag is not set, or if
+ *  discard_zeroes_data is not supported, this function will resort to
+ *  zeroing the blocks manually, thus provisioning (allocating,
+ *  anchoring) them. If the block device supports the WRITE SAME command
+ *  blkdev_issue_zeroout() will use it to optimize the process of
+ *  clearing the block range. Otherwise the zeroing will be performed
+ *  using regular WRITE calls.
  */
 
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			 sector_t nr_sects, gfp_t gfp_mask)
+			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
 {
+	struct request_queue *q = bdev_get_queue(bdev);
+	unsigned char bdn[BDEVNAME_SIZE];
+
+	if (discard && blk_queue_discard(q) && q->limits.discard_zeroes_data) {
+
+		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, 0))
+			return 0;
+
+		bdevname(bdev, bdn);
+		pr_warn("%s: DISCARD failed. Manually zeroing.\n", bdn);
+	}
+
 	if (bdev_write_same(bdev)) {
-		unsigned char bdn[BDEVNAME_SIZE];
 
 		if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
 					     ZERO_PAGE(0)))
 			return 0;
 
 		bdevname(bdev, bdn);
-		pr_err("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
+		pr_warn("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
 	}
 
 	return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);

block/blk-mq-tag.c

@@ -140,35 +140,39 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	return atomic_read(&hctx->nr_active) < depth;
 }
 
-static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
+static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag,
+			 bool nowrap)
 {
-	int tag, org_last_tag, end;
-	bool wrap = last_tag != 0;
+	int tag, org_last_tag = last_tag;
 
-	org_last_tag = last_tag;
-	end = bm->depth;
-	do {
-restart:
-		tag = find_next_zero_bit(&bm->word, end, last_tag);
-		if (unlikely(tag >= end)) {
+	while (1) {
+		tag = find_next_zero_bit(&bm->word, bm->depth, last_tag);
+		if (unlikely(tag >= bm->depth)) {
 			/*
-			 * We started with an offset, start from 0 to
+			 * We started with an offset, and we didn't reset the
+			 * offset to 0 in a failure case, so start from 0 to
 			 * exhaust the map.
 			 */
-			if (wrap) {
-				wrap = false;
-				end = org_last_tag;
-				last_tag = 0;
-				goto restart;
+			if (org_last_tag && last_tag && !nowrap) {
+				last_tag = org_last_tag = 0;
+				continue;
 			}
 			return -1;
 		}
+
+		if (!test_and_set_bit(tag, &bm->word))
+			break;
+
 		last_tag = tag + 1;
-	} while (test_and_set_bit(tag, &bm->word));
+		if (last_tag >= bm->depth - 1)
+			last_tag = 0;
+	}
 
 	return tag;
 }
 
+#define BT_ALLOC_RR(tags) (tags->alloc_policy == BLK_TAG_ALLOC_RR)
+
 /*
  * Straight forward bitmap tag implementation, where each bit is a tag
  * (cleared == free, and set == busy). The small twist is using per-cpu
@@ -181,7 +185,7 @@ static int __bt_get_word(struct blk_align_bitmap *bm, unsigned int last_tag)
  * until the map is exhausted.
  */
 static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
-		    unsigned int *tag_cache)
+		    unsigned int *tag_cache, struct blk_mq_tags *tags)
 {
 	unsigned int last_tag, org_last_tag;
 	int index, i, tag;
@@ -193,15 +197,24 @@ static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
 	index = TAG_TO_INDEX(bt, last_tag);
 
 	for (i = 0; i < bt->map_nr; i++) {
-		tag = __bt_get_word(&bt->map[index], TAG_TO_BIT(bt, last_tag));
+		tag = __bt_get_word(&bt->map[index], TAG_TO_BIT(bt, last_tag),
+				    BT_ALLOC_RR(tags));
 		if (tag != -1) {
 			tag += (index << bt->bits_per_word);
 			goto done;
 		}
 
-		last_tag = 0;
-		if (++index >= bt->map_nr)
+		/*
+		 * Jump to next index, and reset the last tag to be the
+		 * first tag of that index
+		 */
+		index++;
+		last_tag = (index << bt->bits_per_word);
+
+		if (index >= bt->map_nr) {
 			index = 0;
+			last_tag = 0;
+		}
 	}
 
 	*tag_cache = 0;
@@ -212,7 +225,7 @@ static int __bt_get(struct blk_mq_hw_ctx *hctx, struct blk_mq_bitmap_tags *bt,
 	 * up using the specific cached tag.
 	 */
 done:
-	if (tag == org_last_tag) {
+	if (tag == org_last_tag || unlikely(BT_ALLOC_RR(tags))) {
 		last_tag = tag + 1;
 		if (last_tag >= bt->depth - 1)
 			last_tag = 0;
@@ -241,13 +254,13 @@ static struct bt_wait_state *bt_wait_ptr(struct blk_mq_bitmap_tags *bt,
 static int bt_get(struct blk_mq_alloc_data *data,
 		struct blk_mq_bitmap_tags *bt,
 		struct blk_mq_hw_ctx *hctx,
-		unsigned int *last_tag)
+		unsigned int *last_tag, struct blk_mq_tags *tags)
 {
 	struct bt_wait_state *bs;
 	DEFINE_WAIT(wait);
 	int tag;
 
-	tag = __bt_get(hctx, bt, last_tag);
+	tag = __bt_get(hctx, bt, last_tag, tags);
 	if (tag != -1)
 		return tag;
 
@@ -258,7 +271,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 	do {
 		prepare_to_wait(&bs->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt, last_tag);
+		tag = __bt_get(hctx, bt, last_tag, tags);
 		if (tag != -1)
 			break;
 
@@ -273,7 +286,7 @@ static int bt_get(struct blk_mq_alloc_data *data,
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt, last_tag);
+		tag = __bt_get(hctx, bt, last_tag, tags);
 		if (tag != -1)
 			break;
 
@@ -304,7 +317,7 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	int tag;
 
 	tag = bt_get(data, &data->hctx->tags->bitmap_tags, data->hctx,
-			&data->ctx->last_tag);
+			&data->ctx->last_tag, data->hctx->tags);
 	if (tag >= 0)
 		return tag + data->hctx->tags->nr_reserved_tags;
 
@@ -320,7 +333,8 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data)
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero);
+	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL, &zero,
+		data->hctx->tags);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 
@@ -392,7 +406,8 @@ void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, unsigned int tag,
 
 		BUG_ON(real_tag >= tags->nr_tags);
 		bt_clear_tag(&tags->bitmap_tags, real_tag);
-		*last_tag = real_tag;
+		if (likely(tags->alloc_policy == BLK_TAG_ALLOC_FIFO))
+			*last_tag = real_tag;
 	} else {
 		BUG_ON(tag >= tags->nr_reserved_tags);
 		bt_clear_tag(&tags->breserved_tags, tag);
@@ -529,10 +544,12 @@ static void bt_free(struct blk_mq_bitmap_tags *bt)
 }
 
 static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
-						   int node)
+						   int node, int alloc_policy)
 {
 	unsigned int depth = tags->nr_tags - tags->nr_reserved_tags;
 
+	tags->alloc_policy = alloc_policy;
+
 	if (bt_alloc(&tags->bitmap_tags, depth, node, false))
 		goto enomem;
 	if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, node, true))
@@ -546,7 +563,8 @@ static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags,
 }
 
 struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
-				     unsigned int reserved_tags, int node)
+				     unsigned int reserved_tags,
+				     int node, int alloc_policy)
 {
 	struct blk_mq_tags *tags;
 
@@ -562,7 +580,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags,
 	tags->nr_tags = total_tags;
 	tags->nr_reserved_tags = reserved_tags;
 
-	return blk_mq_init_bitmap_tags(tags, node);
+	return blk_mq_init_bitmap_tags(tags, node, alloc_policy);
 }
 
 void blk_mq_free_tags(struct blk_mq_tags *tags)

block/blk-mq-tag.h

@@ -42,10 +42,12 @@ struct blk_mq_tags {
 
 	struct request **rqs;
 	struct list_head page_list;
+
+	int alloc_policy;
 };
 
 
-extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node);
+extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy);
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);

block/blk-mq.c

@@ -1374,7 +1374,8 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 	size_t rq_size, left;
 
 	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,
-				set->numa_node);
+				set->numa_node,
+				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
 	if (!tags)
 		return NULL;
 

block/blk-tag.c

@@ -119,7 +119,7 @@ init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth)
 }
 
 static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
-						   int depth)
+						int depth, int alloc_policy)
 {
 	struct blk_queue_tag *tags;
 
@@ -131,6 +131,8 @@ static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
 		goto fail;
 
 	atomic_set(&tags->refcnt, 1);
+	tags->alloc_policy = alloc_policy;
+	tags->next_tag = 0;
 	return tags;
 fail:
 	kfree(tags);
@@ -140,10 +142,11 @@ static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q,
 /**
  * blk_init_tags - initialize the tag info for an external tag map
  * @depth:	the maximum queue depth supported
+ * @alloc_policy: tag allocation policy
  **/
-struct blk_queue_tag *blk_init_tags(int depth)
+struct blk_queue_tag *blk_init_tags(int depth, int alloc_policy)
 {
-	return __blk_queue_init_tags(NULL, depth);
+	return __blk_queue_init_tags(NULL, depth, alloc_policy);
 }
 EXPORT_SYMBOL(blk_init_tags);
 
@@ -152,19 +155,20 @@ EXPORT_SYMBOL(blk_init_tags);
  * @q:  the request queue for the device
  * @depth:  the maximum queue depth supported
  * @tags: the tag to use
+ * @alloc_policy: tag allocation policy
  *
  * Queue lock must be held here if the function is called to resize an
  * existing map.
  **/
 int blk_queue_init_tags(struct request_queue *q, int depth,
-			struct blk_queue_tag *tags)
+			struct blk_queue_tag *tags, int alloc_policy)
 {
 	int rc;
 
 	BUG_ON(tags && q->queue_tags && tags != q->queue_tags);
 
 	if (!tags && !q->queue_tags) {
-		tags = __blk_queue_init_tags(q, depth);
+		tags = __blk_queue_init_tags(q, depth, alloc_policy);
 
 		if (!tags)
 			return -ENOMEM;
@@ -344,16 +348,29 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	}
 
 	do {
-		tag = find_first_zero_bit(bqt->tag_map, max_depth);
-		if (tag >= max_depth)
-			return 1;
+		if (bqt->alloc_policy == BLK_TAG_ALLOC_FIFO) {
+			tag = find_first_zero_bit(bqt->tag_map, max_depth);
+			if (tag >= max_depth)
+				return 1;
+		} else {
+			int start = bqt->next_tag;
+			int size = min_t(int, bqt->max_depth, max_depth + start);
+			tag = find_next_zero_bit(bqt->tag_map, size, start);
+			if (tag >= size && start + size > bqt->max_depth) {
+				size = start + size - bqt->max_depth;
+				tag = find_first_zero_bit(bqt->tag_map, size);
+			}
+			if (tag >= size)
+				return 1;
+		}
 
 	} while (test_and_set_bit_lock(tag, bqt->tag_map));
 	/*
 	 * We need lock ordering semantics given by test_and_set_bit_lock.
 	 * See blk_queue_end_tag for details.
 	 */
 
+	bqt->next_tag = (tag + 1) % bqt->max_depth;
 	rq->cmd_flags |= REQ_QUEUED;
 	rq->tag = tag;
 	bqt->tag_index[tag] = rq;

block/cfq-iosched.c

@@ -3656,12 +3656,17 @@ static struct cfq_queue *
 cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 	      struct bio *bio, gfp_t gfp_mask)
 {
-	const int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
-	const int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
+	int ioprio_class = IOPRIO_PRIO_CLASS(cic->ioprio);
+	int ioprio = IOPRIO_PRIO_DATA(cic->ioprio);
 	struct cfq_queue **async_cfqq = NULL;
 	struct cfq_queue *cfqq = NULL;
 
 	if (!is_sync) {
+		if (!ioprio_valid(cic->ioprio)) {
+			struct task_struct *tsk = current;
+			ioprio = task_nice_ioprio(tsk);
+			ioprio_class = task_nice_ioclass(tsk);
+		}
 		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
 		cfqq = *async_cfqq;
 	}

block/ioctl.c

@@ -198,7 +198,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
 	if (start + len > (i_size_read(bdev->bd_inode) >> 9))
 		return -EINVAL;
 
-	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL);
+	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL, false);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)