scsi: lpfc: Change default queue allocation for reduced memory consumption

By default, the driver attempts to allocate a hdwq per logical cpu in order
to provide good cpu affinity. Some systems have extremely high cpu counts
and this can significantly raise memory consumption.

In testing on x86 platforms (non-AMD) it is found that sharing of a hdwq by
a physical cpu and its HT cpu can occur with little performance
degredation. By sharing, the hdwq count can be halved, significantly
reducing the memory overhead.

Change the default behavior of the driver on non-AMD x86 platforms to
share a hdwq by the cpu and its HT cpu.

Link: https://lore.kernel.org/r/20200501214310.91713-6-jsmart2021@gmail.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 18 insertions, 5 deletions

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 8e2a356911a9..45657a7502f6 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -627,6 +627,19 @@ struct lpfc_ras_fwlog {
 	enum ras_state state;    /* RAS logging running state */
 };
 
+enum lpfc_irq_chann_mode {
+	/* Assign IRQs to all possible cpus that have hardware queues */
+	NORMAL_MODE,
+
+	/* Assign IRQs only to cpus on the same numa node as HBA */
+	NUMA_MODE,
+
+	/* Assign IRQs only on non-hyperthreaded CPUs. This is the
+	 * same as normal_mode, but assign IRQS only on physical CPUs.
+	 */
+	NHT_MODE,
+};
+
 struct lpfc_hba {
 	/* SCSI interface function jump table entries */
 	struct lpfc_io_buf * (*lpfc_get_scsi_buf)
@@ -835,7 +848,6 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_mq_threshold;
 	uint32_t cfg_hdw_queue;
 	uint32_t cfg_irq_chann;
-	uint32_t cfg_irq_numa;
 	uint32_t cfg_suppress_rsp;
 	uint32_t cfg_nvme_oas;
 	uint32_t cfg_nvme_embed_cmd;
@@ -1003,6 +1015,7 @@ struct lpfc_hba {
 	mempool_t *active_rrq_pool;
 
 	struct fc_host_statistics link_stats;
+	enum lpfc_irq_chann_mode irq_chann_mode;
 	enum intr_type_t intr_type;
 	uint32_t intr_mode;
 #define LPFC_INTR_ERROR	0xFFFFFFFF
@@ -1314,19 +1327,19 @@ lpfc_phba_elsring(struct lpfc_hba *phba)
 }
 
 /**
- * lpfc_next_online_numa_cpu - Finds next online CPU on NUMA node
- * @numa_mask: Pointer to phba's numa_mask member.
+ * lpfc_next_online_cpu - Finds next online CPU on cpumask
+ * @mask: Pointer to phba's cpumask member.
  * @start: starting cpu index
  *
  * Note: If no valid cpu found, then nr_cpu_ids is returned.
  *
  **/
 static inline unsigned int
-lpfc_next_online_numa_cpu(const struct cpumask *numa_mask, unsigned int start)
+lpfc_next_online_cpu(const struct cpumask *mask, unsigned int start)
 {
 	unsigned int cpu_it;
 
-	for_each_cpu_wrap(cpu_it, numa_mask, start) {
+	for_each_cpu_wrap(cpu_it, mask, start) {
 		if (cpu_online(cpu_it))
 			break;
 	}