cxlflash: Increase cmd_per_lun for better throughput

With the current value of cmd_per_lun at 16, the throughput
over a single adapter is limited to around 150kIOPS.

Increase the value of cmd_per_lun to 256 to improve
throughput. With this change a single adapter is able to
attain close to the maximum throughput (380kIOPS).
Also change the number of RRQ entries that can be queued.
Signed-off-by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>
Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com>
Reviewed-by: Uma Krishnan <ukrishn@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/cxlflash/common.h

@@ -34,7 +34,6 @@ extern const struct file_operations cxlflash_cxl_fops;
 								   sectors
 								*/
 
-#define NUM_RRQ_ENTRY    16     /* for master issued cmds */
 #define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
 
 /* AFU command retry limit */
@@ -48,9 +47,12 @@ extern const struct file_operations cxlflash_cxl_fops;
 							   index derivation
 							 */
 
-#define CXLFLASH_MAX_CMDS               16
+#define CXLFLASH_MAX_CMDS               256
 #define CXLFLASH_MAX_CMDS_PER_LUN       CXLFLASH_MAX_CMDS
 
+/* RRQ for master issued cmds */
+#define NUM_RRQ_ENTRY                   CXLFLASH_MAX_CMDS
+
 
 static inline void check_sizes(void)
 {
@@ -149,7 +151,7 @@ struct afu_cmd {
 struct afu {
 	/* Stuff requiring alignment go first. */
 
-	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 128B RRQ */
+	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
 	/*
 	 * Command & data for AFU commands.
 	 */

drivers/scsi/cxlflash/main.c

@@ -2253,7 +2253,7 @@ static struct scsi_host_template driver_template = {
 	.eh_device_reset_handler = cxlflash_eh_device_reset_handler,
 	.eh_host_reset_handler = cxlflash_eh_host_reset_handler,
 	.change_queue_depth = cxlflash_change_queue_depth,
-	.cmd_per_lun = 16,
+	.cmd_per_lun = CXLFLASH_MAX_CMDS_PER_LUN,
 	.can_queue = CXLFLASH_MAX_CMDS,
 	.this_id = -1,
 	.sg_tablesize = SG_NONE,	/* No scatter gather support */