Commit 49db4d4e authored Sep 03, 2020 by Quinn Tran Committed by Martin K. Petersen Sep 22, 2020

scsi: qla2xxx: Performance tweak

Move statistics fields from vha struct to qpair to reduce memory thrashing.

Link: https://lore.kernel.org/r/20200904045128.23631-8-njavali@marvell.com

Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Nilesh Javali <njavali@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

parent d38cb849

drivers/scsi/qla2xxx/qla_attr.c

+40 −6

Original line number	Diff line number	Diff line
		@@ -2726,6 +2726,9 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
		struct link_statistics *stats;
		dma_addr_t stats_dma;
		struct fc_host_statistics *p = &vha->fc_host_stat;
		struct qla_qpair *qpair;
		int i;
		u64 ib = 0, ob = 0, ir = 0, or = 0;

		memset(p, -1, sizeof(*p));

		@@ -2762,6 +2765,27 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
		if (rval != QLA_SUCCESS)
		goto done_free;

		/* --- */
		for (i = 0; i < vha->hw->max_qpairs; i++) {
		qpair = vha->hw->queue_pair_map[i];
		if (!qpair)
		continue;
		ir += qpair->counters.input_requests;
		or += qpair->counters.output_requests;
		ib += qpair->counters.input_bytes;
		ob += qpair->counters.output_bytes;
		}
		ir += ha->base_qpair->counters.input_requests;
		or += ha->base_qpair->counters.output_requests;
		ib += ha->base_qpair->counters.input_bytes;
		ob += ha->base_qpair->counters.output_bytes;

		ir += vha->qla_stats.input_requests;
		or += vha->qla_stats.output_requests;
		ib += vha->qla_stats.input_bytes;
		ob += vha->qla_stats.output_bytes;
		/* --- */

		p->link_failure_count = le32_to_cpu(stats->link_fail_cnt);
		p->loss_of_sync_count = le32_to_cpu(stats->loss_sync_cnt);
		p->loss_of_signal_count = le32_to_cpu(stats->loss_sig_cnt);
		@@ -2781,15 +2805,16 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
		p->rx_words = le64_to_cpu(stats->fpm_recv_word_cnt);
		p->tx_words = le64_to_cpu(stats->fpm_xmit_word_cnt);
		} else {
		p->rx_words = vha->qla_stats.input_bytes;
		p->tx_words = vha->qla_stats.output_bytes;
		p->rx_words = ib >> 2;
		p->tx_words = ob >> 2;
		}
		}

		p->fcp_control_requests = vha->qla_stats.control_requests;
		p->fcp_input_requests = vha->qla_stats.input_requests;
		p->fcp_output_requests = vha->qla_stats.output_requests;
		p->fcp_input_megabytes = vha->qla_stats.input_bytes >> 20;
		p->fcp_output_megabytes = vha->qla_stats.output_bytes >> 20;
		p->fcp_input_requests = ir;
		p->fcp_output_requests = or;
		p->fcp_input_megabytes = ib >> 20;
		p->fcp_output_megabytes = ob >> 20;
		p->seconds_since_last_reset =
		get_jiffies_64() - vha->qla_stats.jiffies_at_last_reset;
		do_div(p->seconds_since_last_reset, HZ);
		@@ -2809,9 +2834,18 @@ qla2x00_reset_host_stats(struct Scsi_Host *shost)
		struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
		struct link_statistics *stats;
		dma_addr_t stats_dma;
		int i;
		struct qla_qpair *qpair;

		memset(&vha->qla_stats, 0, sizeof(vha->qla_stats));
		memset(&vha->fc_host_stat, 0, sizeof(vha->fc_host_stat));
		for (i = 0; i < vha->hw->max_qpairs; i++) {
		qpair = vha->hw->queue_pair_map[i];
		if (!qpair)
		continue;
		memset(&qpair->counters, 0, sizeof(qpair->counters));
		}
		memset(&ha->base_qpair->counters, 0, sizeof(qpair->counters));

		vha->qla_stats.jiffies_at_last_reset = get_jiffies_64();

drivers/scsi/qla2xxx/qla_def.h

+25 −8

Original line number	Diff line number	Diff line
		@@ -2443,12 +2443,6 @@ typedef struct fc_port {
		struct list_head list;
		struct scsi_qla_host *vha;

		uint8_t node_name[WWN_SIZE];
		uint8_t port_name[WWN_SIZE];
		port_id_t d_id;
		uint16_t loop_id;
		uint16_t old_loop_id;

		unsigned int conf_compl_supported:1;
		unsigned int deleted:2;
		unsigned int free_pending:1;
		@@ -2465,6 +2459,13 @@ typedef struct fc_port {
		unsigned int n2n_flag:1;
		unsigned int explicit_logout:1;
		unsigned int prli_pend_timer:1;
		uint8_t nvme_flag;

		uint8_t node_name[WWN_SIZE];
		uint8_t port_name[WWN_SIZE];
		port_id_t d_id;
		uint16_t loop_id;
		uint16_t old_loop_id;

		struct completion nvme_del_done;
		uint32_t nvme_prli_service_param;
		@@ -2473,7 +2474,7 @@ typedef struct fc_port {
		#define NVME_PRLI_SP_TARGET BIT_4
		#define NVME_PRLI_SP_DISCOVERY BIT_3
		#define NVME_PRLI_SP_FIRST_BURST BIT_0
		uint8_t nvme_flag;

		uint32_t nvme_first_burst_size;
		#define NVME_FLAG_REGISTERED 4
		#define NVME_FLAG_DELETING 2
		@@ -3510,6 +3511,14 @@ struct qla_tgt_counters {
		uint64_t num_term_xchg_sent;
		};

		struct qla_counters {
		uint64_t input_bytes;
		uint64_t input_requests;
		uint64_t output_bytes;
		uint64_t output_requests;

		};

		struct qla_qpair;

		/* Response queue data structure */
		@@ -3594,6 +3603,7 @@ struct qla_qpair {
		uint32_t enable_class_2:1;
		uint32_t enable_explicit_conf:1;
		uint32_t use_shadow_reg:1;
		uint32_t rcv_intr:1;

		uint16_t id; /* qp number used with FW */
		uint16_t vp_idx; /* vport ID */
		@@ -3609,13 +3619,16 @@ struct qla_qpair {
		struct qla_msix_entry msix; / point to &ha->msix_entries[x] */
		struct qla_hw_data *hw;
		struct work_struct q_work;
		struct qla_counters counters;

		struct list_head qp_list_elem; /* vha->qp_list */
		struct list_head hints_list;
		uint16_t cpuid;

		uint16_t retry_term_cnt;
		__le32 retry_term_exchg_addr;
		uint64_t retry_term_jiff;
		struct qla_tgt_counters tgt_counters;
		uint16_t cpuid;
		};

		/* Place holder for FW buffer parameters */
		@@ -4129,6 +4142,10 @@ struct qla_hw_data {
		#define USE_ASYNC_SCAN(ha) (IS_QLA25XX(ha) \|\| IS_QLA81XX(ha) \|\|\
		IS_QLA83XX(ha) \|\| IS_QLA27XX(ha) \|\| IS_QLA28XX(ha))

		#define IS_ZIO_THRESHOLD_CAPABLE(ha) \
		((IS_QLA83XX(ha) \|\| IS_QLA27XX(ha) \|\| IS_QLA28XX(ha)) &&\
		(ha->zio_mode == QLA_ZIO_MODE_6))

		/* HBA serial number */
		uint8_t serial0;
		uint8_t serial1;

drivers/scsi/qla2xxx/qla_init.c

+1 −3

Original line number	Diff line number	Diff line
		@@ -3700,9 +3700,7 @@ qla2x00_setup_chip(scsi_qla_host_t *vha)
		goto execute_fw_with_lr;
		}

		if ((IS_QLA83XX(ha) \|\| IS_QLA27XX(ha) \|\|
		IS_QLA28XX(ha)) &&
		(ha->zio_mode == QLA_ZIO_MODE_6))
		if (IS_ZIO_THRESHOLD_CAPABLE(ha))
		qla27xx_set_zio_threshold(vha,
		ha->last_zio_threshold);

drivers/scsi/qla2xxx/qla_iocb.c

+10 −8

Original line number	Diff line number	Diff line
		@@ -594,6 +594,7 @@ qla24xx_build_scsi_type_6_iocbs(srb_t sp, struct cmd_type_6 cmd_pkt,
		uint32_t dsd_list_len;
		struct dsd_dma *dsd_ptr;
		struct ct6_dsd *ctx;
		struct qla_qpair *qpair = sp->qpair;

		cmd = GET_CMD_SP(sp);

		@@ -612,12 +613,12 @@ qla24xx_build_scsi_type_6_iocbs(srb_t sp, struct cmd_type_6 cmd_pkt,
		/* Set transfer direction */
		if (cmd->sc_data_direction == DMA_TO_DEVICE) {
		cmd_pkt->control_flags = cpu_to_le16(CF_WRITE_DATA);
		vha->qla_stats.output_bytes += scsi_bufflen(cmd);
		vha->qla_stats.output_requests++;
		qpair->counters.output_bytes += scsi_bufflen(cmd);
		qpair->counters.output_requests++;
		} else if (cmd->sc_data_direction == DMA_FROM_DEVICE) {
		cmd_pkt->control_flags = cpu_to_le16(CF_READ_DATA);
		vha->qla_stats.input_bytes += scsi_bufflen(cmd);
		vha->qla_stats.input_requests++;
		qpair->counters.input_bytes += scsi_bufflen(cmd);
		qpair->counters.input_requests++;
		}

		cur_seg = scsi_sglist(cmd);
		@@ -704,6 +705,7 @@ qla24xx_build_scsi_iocbs(srb_t sp, struct cmd_type_7 cmd_pkt,
		struct scsi_cmnd *cmd;
		struct scatterlist *sg;
		int i;
		struct qla_qpair *qpair = sp->qpair;

		cmd = GET_CMD_SP(sp);

		@@ -721,12 +723,12 @@ qla24xx_build_scsi_iocbs(srb_t sp, struct cmd_type_7 cmd_pkt,
		/* Set transfer direction */
		if (cmd->sc_data_direction == DMA_TO_DEVICE) {
		cmd_pkt->task_mgmt_flags = cpu_to_le16(TMF_WRITE_DATA);
		vha->qla_stats.output_bytes += scsi_bufflen(cmd);
		vha->qla_stats.output_requests++;
		qpair->counters.output_bytes += scsi_bufflen(cmd);
		qpair->counters.output_requests++;
		} else if (cmd->sc_data_direction == DMA_FROM_DEVICE) {
		cmd_pkt->task_mgmt_flags = cpu_to_le16(TMF_READ_DATA);
		vha->qla_stats.input_bytes += scsi_bufflen(cmd);
		vha->qla_stats.input_requests++;
		qpair->counters.input_bytes += scsi_bufflen(cmd);
		qpair->counters.input_requests++;
		}

		/* One DSD is available in the Command Type 3 IOCB */

drivers/scsi/qla2xxx/qla_isr.c

+5 −3

Original line number	Diff line number	Diff line
		@@ -3440,8 +3440,10 @@ void qla24xx_process_response_queue(struct scsi_qla_host *vha,
		if (!ha->flags.fw_started)
		return;

		if (rsp->qpair->cpuid != smp_processor_id())
		if (rsp->qpair->cpuid != smp_processor_id() \|\| !rsp->qpair->rcv_intr) {
		rsp->qpair->rcv_intr = 1;
		qla_cpu_update(rsp->qpair, smp_processor_id());
		}

		while (rsp->ring_ptr->signature != RESPONSE_PROCESSED) {
		pkt = (struct sts_entry_24xx *)rsp->ring_ptr;
		@@ -3890,7 +3892,7 @@ qla2xxx_msix_rsp_q(int irq, void *dev_id)
		}
		ha = qpair->hw;

		queue_work(ha->wq, &qpair->q_work);
		queue_work_on(smp_processor_id(), ha->wq, &qpair->q_work);

		return IRQ_HANDLED;
		}
		@@ -3916,7 +3918,7 @@ qla2xxx_msix_rsp_q_hs(int irq, void *dev_id)
		wrt_reg_dword(&reg->hccr, HCCRX_CLR_RISC_INT);
		spin_unlock_irqrestore(&ha->hardware_lock, flags);

		queue_work(ha->wq, &qpair->q_work);
		queue_work_on(smp_processor_id(), ha->wq, &qpair->q_work);

		return IRQ_HANDLED;
		}