1 files changed, 101 insertions, 23 deletions

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 65d0a10c76ad..91c007d26c1e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -40,6 +40,18 @@
 #include "scsi_priv.h"
 #include "scsi_logging.h"
 
+/*
+ * Size of integrity metadata is usually small, 1 inline sg should
+ * cover normal cases.
+ */
+#ifdef CONFIG_ARCH_NO_SG_CHAIN
+#define  SCSI_INLINE_PROT_SG_CNT  0
+#define  SCSI_INLINE_SG_CNT  0
+#else
+#define  SCSI_INLINE_PROT_SG_CNT  1
+#define  SCSI_INLINE_SG_CNT  2
+#endif
+
 static struct kmem_cache *scsi_sdb_cache;
 static struct kmem_cache *scsi_sense_cache;
 static struct kmem_cache *scsi_sense_isadma_cache;
@@ -72,11 +84,11 @@ int scsi_init_sense_cache(struct Scsi_Host *shost)
 	struct kmem_cache *cache;
 	int ret = 0;
 
+	mutex_lock(&scsi_sense_cache_mutex);
 	cache = scsi_select_sense_cache(shost->unchecked_isa_dma);
 	if (cache)
-		return 0;
+		goto exit;
 
-	mutex_lock(&scsi_sense_cache_mutex);
 	if (shost->unchecked_isa_dma) {
 		scsi_sense_isadma_cache =
 			kmem_cache_create("scsi_sense_cache(DMA)",
@@ -92,7 +104,7 @@ int scsi_init_sense_cache(struct Scsi_Host *shost)
 		if (!scsi_sense_cache)
 			ret = -ENOMEM;
 	}
-
+ exit:
 	mutex_unlock(&scsi_sense_cache_mutex);
 	return ret;
 }
@@ -542,9 +554,11 @@ static void scsi_uninit_cmd(struct scsi_cmnd *cmd)
 static void scsi_mq_free_sgtables(struct scsi_cmnd *cmd)
 {
 	if (cmd->sdb.table.nents)
-		sg_free_table_chained(&cmd->sdb.table, true);
+		sg_free_table_chained(&cmd->sdb.table,
+				SCSI_INLINE_SG_CNT);
 	if (scsi_prot_sg_count(cmd))
-		sg_free_table_chained(&cmd->prot_sdb->table, true);
+		sg_free_table_chained(&cmd->prot_sdb->table,
+				SCSI_INLINE_PROT_SG_CNT);
 }
 
 static void scsi_mq_uninit_cmd(struct scsi_cmnd *cmd)
@@ -977,7 +991,8 @@ static blk_status_t scsi_init_sgtable(struct request *req,
 	 * If sg table allocation fails, requeue request later.
 	 */
 	if (unlikely(sg_alloc_table_chained(&sdb->table,
-			blk_rq_nr_phys_segments(req), sdb->table.sgl)))
+			blk_rq_nr_phys_segments(req), sdb->table.sgl,
+			SCSI_INLINE_SG_CNT)))
 		return BLK_STS_RESOURCE;
 
 	/* 
@@ -1031,7 +1046,8 @@ blk_status_t scsi_init_io(struct scsi_cmnd *cmd)
 		ivecs = blk_rq_count_integrity_sg(rq->q, rq->bio);
 
 		if (sg_alloc_table_chained(&prot_sdb->table, ivecs,
-				prot_sdb->table.sgl)) {
+				prot_sdb->table.sgl,
+				SCSI_INLINE_PROT_SG_CNT)) {
 			ret = BLK_STS_RESOURCE;
 			goto out_free_sgtables;
 		}
@@ -1073,6 +1089,18 @@ static void scsi_initialize_rq(struct request *rq)
 	cmd->retries = 0;
 }
 
+/*
+ * Only called when the request isn't completed by SCSI, and not freed by
+ * SCSI
+ */
+static void scsi_cleanup_rq(struct request *rq)
+{
+	if (rq->rq_flags & RQF_DONTPREP) {
+		scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+		rq->rq_flags &= ~RQF_DONTPREP;
+	}
+}
+
 /* Add a command to the list used by the aacraid and dpt_i2o drivers */
 void scsi_add_cmd_to_list(struct scsi_cmnd *cmd)
 {
@@ -1436,7 +1464,7 @@ static void scsi_softirq_done(struct request *rq)
 	disposition = scsi_decide_disposition(cmd);
 	if (disposition != SUCCESS &&
 	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
-		sdev_printk(KERN_ERR, cmd->device,
+		scmd_printk(KERN_ERR, cmd,
 			    "timing out command, waited %lus\n",
 			    wait_for/HZ);
 		disposition = SUCCESS;
@@ -1542,9 +1570,9 @@ static int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 }
 
 /* Size in bytes of the sg-list stored in the scsi-mq command-private data. */
-static unsigned int scsi_mq_sgl_size(struct Scsi_Host *shost)
+static unsigned int scsi_mq_inline_sgl_size(struct Scsi_Host *shost)
 {
-	return min_t(unsigned int, shost->sg_tablesize, SG_CHUNK_SIZE) *
+	return min_t(unsigned int, shost->sg_tablesize, SCSI_INLINE_SG_CNT) *
 		sizeof(struct scatterlist);
 }
 
@@ -1650,10 +1678,11 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 		blk_mq_start_request(req);
 	}
 
+	cmd->flags &= SCMD_PRESERVED_FLAGS;
 	if (sdev->simple_tags)
 		cmd->flags |= SCMD_TAGGED;
-	else
-		cmd->flags &= ~SCMD_TAGGED;
+	if (bd->last)
+		cmd->flags |= SCMD_LAST;
 
 	scsi_init_cmd_errh(cmd);
 	cmd->scsi_done = scsi_mq_done;
@@ -1726,7 +1755,7 @@ static int scsi_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	if (scsi_host_get_prot(shost)) {
 		sg = (void *)cmd + sizeof(struct scsi_cmnd) +
 			shost->hostt->cmd_size;
-		cmd->prot_sdb = (void *)sg + scsi_mq_sgl_size(shost);
+		cmd->prot_sdb = (void *)sg + scsi_mq_inline_sgl_size(shost);
 	}
 
 	return 0;
@@ -1768,6 +1797,10 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 		blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
 	}
 
+	if (dev->dma_mask) {
+		shost->max_sectors = min_t(unsigned int, shost->max_sectors,
+				dma_max_mapping_size(dev) >> SECTOR_SHIFT);
+	}
 	blk_queue_max_hw_sectors(q, shost->max_sectors);
 	if (shost->unchecked_isa_dma)
 		blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
@@ -1775,7 +1808,8 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 	dma_set_seg_boundary(dev, shost->dma_boundary);
 
 	blk_queue_max_segment_size(q, shost->max_segment_size);
-	dma_set_max_seg_size(dev, shost->max_segment_size);
+	blk_queue_virt_boundary(q, shost->virt_boundary_mask);
+	dma_set_max_seg_size(dev, queue_max_segment_size(q));
 
 	/*
 	 * Set a reasonable default alignment:  The larger of 32-byte (dword),
@@ -1788,10 +1822,38 @@ void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(__scsi_init_queue);
 
+static const struct blk_mq_ops scsi_mq_ops_no_commit = {
+	.get_budget	= scsi_mq_get_budget,
+	.put_budget	= scsi_mq_put_budget,
+	.queue_rq	= scsi_queue_rq,
+	.complete	= scsi_softirq_done,
+	.timeout	= scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+	.show_rq	= scsi_show_rq,
+#endif
+	.init_request	= scsi_mq_init_request,
+	.exit_request	= scsi_mq_exit_request,
+	.initialize_rq_fn = scsi_initialize_rq,
+	.cleanup_rq	= scsi_cleanup_rq,
+	.busy		= scsi_mq_lld_busy,
+	.map_queues	= scsi_map_queues,
+};
+
+
+static void scsi_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+	struct scsi_device *sdev = q->queuedata;
+	struct Scsi_Host *shost = sdev->host;
+
+	shost->hostt->commit_rqs(shost, hctx->queue_num);
+}
+
 static const struct blk_mq_ops scsi_mq_ops = {
 	.get_budget	= scsi_mq_get_budget,
 	.put_budget	= scsi_mq_put_budget,
 	.queue_rq	= scsi_queue_rq,
+	.commit_rqs	= scsi_commit_rqs,
 	.complete	= scsi_softirq_done,
 	.timeout	= scsi_timeout,
 #ifdef CONFIG_BLK_DEBUG_FS
@@ -1800,6 +1862,7 @@ static const struct blk_mq_ops scsi_mq_ops = {
 	.init_request	= scsi_mq_init_request,
 	.exit_request	= scsi_mq_exit_request,
 	.initialize_rq_fn = scsi_initialize_rq,
+	.cleanup_rq	= scsi_cleanup_rq,
 	.busy		= scsi_mq_lld_busy,
 	.map_queues	= scsi_map_queues,
 };
@@ -1820,13 +1883,18 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
 {
 	unsigned int cmd_size, sgl_size;
 
-	sgl_size = scsi_mq_sgl_size(shost);
+	sgl_size = max_t(unsigned int, sizeof(struct scatterlist),
+				scsi_mq_inline_sgl_size(shost));
 	cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size;
 	if (scsi_host_get_prot(shost))
-		cmd_size += sizeof(struct scsi_data_buffer) + sgl_size;
+		cmd_size += sizeof(struct scsi_data_buffer) +
+			sizeof(struct scatterlist) * SCSI_INLINE_PROT_SG_CNT;
 
 	memset(&shost->tag_set, 0, sizeof(shost->tag_set));
-	shost->tag_set.ops = &scsi_mq_ops;
+	if (shost->hostt->commit_rqs)
+		shost->tag_set.ops = &scsi_mq_ops;
+	else
+		shost->tag_set.ops = &scsi_mq_ops_no_commit;
 	shost->tag_set.nr_hw_queues = shost->nr_hw_queues ? : 1;
 	shost->tag_set.queue_depth = shost->can_queue;
 	shost->tag_set.cmd_size = cmd_size;
@@ -1855,7 +1923,8 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q)
 {
 	struct scsi_device *sdev = NULL;
 
-	if (q->mq_ops == &scsi_mq_ops)
+	if (q->mq_ops == &scsi_mq_ops_no_commit ||
+	    q->mq_ops == &scsi_mq_ops)
 		sdev = q->queuedata;
 	if (!sdev || !get_device(&sdev->sdev_gendev))
 		sdev = NULL;
@@ -2616,10 +2685,6 @@ EXPORT_SYMBOL_GPL(scsi_internal_device_block_nowait);
  * a legal transition). When the device is in this state, command processing
  * is paused until the device leaves the SDEV_BLOCK state. See also
  * scsi_internal_device_unblock().
- *
- * To do: avoid that scsi_send_eh_cmnd() calls queuecommand() after
- * scsi_internal_device_block() has blocked a SCSI device and also
- * remove the rport mutex lock and unlock calls from srp_queuecommand().
  */
 static int scsi_internal_device_block(struct scsi_device *sdev)
 {
@@ -2660,6 +2725,14 @@ void scsi_start_queue(struct scsi_device *sdev)
 int scsi_internal_device_unblock_nowait(struct scsi_device *sdev,
 					enum scsi_device_state new_state)
 {
+	switch (new_state) {
+	case SDEV_RUNNING:
+	case SDEV_TRANSPORT_OFFLINE:
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	/*
 	 * Try to transition the scsi device to SDEV_RUNNING or one of the
 	 * offlined states and goose the device queue if successful.
@@ -2717,7 +2790,12 @@ static int scsi_internal_device_unblock(struct scsi_device *sdev,
 static void
 device_block(struct scsi_device *sdev, void *data)
 {
-	scsi_internal_device_block(sdev);
+	int ret;
+
+	ret = scsi_internal_device_block(sdev);
+
+	WARN_ONCE(ret, "scsi_internal_device_block(%s) failed: ret = %d\n",
+		  dev_name(&sdev->sdev_gendev), ret);
 }
 
 static int