[PATCH 2/2] scsi: hisi_sas: Expose HW queues for v2 hw

[John Garry]

As a performance enhancement, make the completion queue interrupts managed.

In addition, in commit bf0beec0607d ("blk-mq: drain I/O when all CPUs in a
hctx are offline"), CPU hotplug for MQ devices using managed interrupts
is made safe. So expose HW queues to blk-mq to take advantage of this.

Flag Scsi_host.host_tagset is also set to ensure that the HBA is not sent
more commands than it can handle. However the driver still does not use
request tag for IPTT as there are many HW bugs means that special rules
apply for IPTT allocation.

Signed-off-by: John Garry <john.garry@xxxxxxxxxx>
---
 drivers/scsi/hisi_sas/hisi_sas.h       |  4 ++
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 11 +++++
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 66 +++++++++++++++++++++-----
 3 files changed, 68 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 2b28dd405600..e821dd32dd28 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -14,6 +14,7 @@
 #include <linux/debugfs.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/irq.h>
 #include <linux/lcm.h>
 #include <linux/libata.h>
 #include <linux/mfd/syscon.h>
@@ -294,6 +295,7 @@ enum {
 
 struct hisi_sas_hw {
 	int (*hw_init)(struct hisi_hba *hisi_hba);
+	int (*interrupt_preinit)(struct hisi_hba *hisi_hba);
 	void (*setup_itct)(struct hisi_hba *hisi_hba,
 			   struct hisi_sas_device *device);
 	int (*slot_index_alloc)(struct hisi_hba *hisi_hba,
@@ -393,6 +395,8 @@ struct hisi_hba {
 	u32 refclk_frequency_mhz;
 	u8 sas_addr[SAS_ADDR_SIZE];
 
+	int *irq_map; /* v2 hw */
+
 	int n_phy;
 	spinlock_t lock;
 	struct semaphore sem;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index c34f60a600f1..ffb2b32fd35f 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2628,6 +2628,13 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 	return NULL;
 }
 
+static int hisi_sas_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+	if (hisi_hba->hw->interrupt_preinit)
+		return hisi_hba->hw->interrupt_preinit(hisi_hba);
+	return 0;
+}
+
 int hisi_sas_probe(struct platform_device *pdev,
 		   const struct hisi_sas_hw *hw)
 {
@@ -2685,6 +2692,10 @@ int hisi_sas_probe(struct platform_device *pdev,
 		sha->sas_port[i] = &hisi_hba->port[i].sas_port;
 	}
 
+	rc = hisi_sas_interrupt_preinit(hisi_hba);
+	if (rc)
+		goto err_out_ha;
+
 	rc = scsi_add_host(shost, &pdev->dev);
 	if (rc)
 		goto err_out_ha;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index b57177b52fac..9adfdefef9ca 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3302,6 +3302,28 @@ static irq_handler_t fatal_interrupts[HISI_SAS_FATAL_INT_NR] = {
 	fatal_axi_int_v2_hw
 };
 
+#define CQ0_IRQ_INDEX (96)
+
+static int hisi_sas_v2_interrupt_preinit(struct hisi_hba *hisi_hba)
+{
+	struct platform_device *pdev = hisi_hba->platform_dev;
+	struct Scsi_Host *shost = hisi_hba->shost;
+	struct irq_affinity desc = {
+		.pre_vectors = CQ0_IRQ_INDEX,
+		.post_vectors = 16,
+	};
+	int resv = desc.pre_vectors + desc.post_vectors, minvec = resv + 1, nvec;
+
+	nvec = devm_platform_get_irqs_affinity(pdev, &desc, minvec, 128,
+					       &hisi_hba->irq_map);
+	if (nvec < 0)
+		return nvec;
+
+	shost->nr_hw_queues = hisi_hba->cq_nvecs = nvec - resv;
+
+	return 0;
+}
+
 /*
  * There is a limitation in the hip06 chipset that we need
  * to map in all mbigen interrupts, even if they are not used.
@@ -3310,14 +3332,11 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 {
 	struct platform_device *pdev = hisi_hba->platform_dev;
 	struct device *dev = &pdev->dev;
-	int irq, rc = 0, irq_map[128];
+	int irq, rc = 0;
 	int i, phy_no, fatal_no, queue_no;
 
-	for (i = 0; i < 128; i++)
-		irq_map[i] = platform_get_irq(pdev, i);
-
 	for (i = 0; i < HISI_SAS_PHY_INT_NR; i++) {
-		irq = irq_map[i + 1]; /* Phy up/down is irq1 */
+		irq = hisi_hba->irq_map[i + 1]; /* Phy up/down is irq1 */
 		rc = devm_request_irq(dev, irq, phy_interrupts[i], 0,
 				      DRV_NAME " phy", hisi_hba);
 		if (rc) {
@@ -3331,7 +3350,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 	for (phy_no = 0; phy_no < hisi_hba->n_phy; phy_no++) {
 		struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 
-		irq = irq_map[phy_no + 72];
+		irq = hisi_hba->irq_map[phy_no + 72];
 		rc = devm_request_irq(dev, irq, sata_int_v2_hw, 0,
 				      DRV_NAME " sata", phy);
 		if (rc) {
@@ -3343,7 +3362,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 	}
 
 	for (fatal_no = 0; fatal_no < HISI_SAS_FATAL_INT_NR; fatal_no++) {
-		irq = irq_map[fatal_no + 81];
+		irq = hisi_hba->irq_map[fatal_no + 81];
 		rc = devm_request_irq(dev, irq, fatal_interrupts[fatal_no], 0,
 				      DRV_NAME " fatal", hisi_hba);
 		if (rc) {
@@ -3354,24 +3373,22 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 		}
 	}
 
-	for (queue_no = 0; queue_no < hisi_hba->queue_count; queue_no++) {
+	for (queue_no = 0; queue_no < hisi_hba->cq_nvecs; queue_no++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[queue_no];
 
-		cq->irq_no = irq_map[queue_no + 96];
+		cq->irq_no = hisi_hba->irq_map[queue_no + 96];
 		rc = devm_request_threaded_irq(dev, cq->irq_no,
 					       cq_interrupt_v2_hw,
 					       cq_thread_v2_hw, IRQF_ONESHOT,
 					       DRV_NAME " cq", cq);
 		if (rc) {
 			dev_err(dev, "irq init: could not request cq interrupt %d, rc=%d\n",
-				irq, rc);
+					cq->irq_no, rc);
 			rc = -ENOENT;
 			goto err_out;
 		}
+		cq->irq_mask = irq_get_affinity_mask(cq->irq_no);
 	}
-
-	hisi_hba->cq_nvecs = hisi_hba->queue_count;
-
 err_out:
 	return rc;
 }
@@ -3529,6 +3546,26 @@ static struct device_attribute *host_attrs_v2_hw[] = {
 	NULL
 };
 
+static int map_queues_v2_hw(struct Scsi_Host *shost)
+{
+	struct hisi_hba *hisi_hba = shost_priv(shost);
+	struct blk_mq_queue_map *qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT];
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < qmap->nr_queues; queue++) {
+		mask = irq_get_affinity_mask(hisi_hba->irq_map[96 + queue]);
+		if (!mask)
+			continue;
+
+		for_each_cpu(cpu, mask)
+			qmap->mq_map[cpu] = qmap->queue_offset + queue;
+	}
+
+	return 0;
+
+}
+
 static struct scsi_host_template sht_v2_hw = {
 	.name			= DRV_NAME,
 	.proc_name		= DRV_NAME,
@@ -3553,10 +3590,13 @@ static struct scsi_host_template sht_v2_hw = {
 #endif
 	.shost_attrs		= host_attrs_v2_hw,
 	.host_reset		= hisi_sas_host_reset,
+	.map_queues		= map_queues_v2_hw,
+	.host_tagset		= 1,
 };
 
 static const struct hisi_sas_hw hisi_sas_v2_hw = {
 	.hw_init = hisi_sas_v2_init,
+	.interrupt_preinit = hisi_sas_v2_interrupt_preinit,
 	.setup_itct = setup_itct_v2_hw,
 	.slot_index_alloc = slot_index_alloc_quirk_v2_hw,
 	.alloc_dev = alloc_dev_quirk_v2_hw,
-- 
2.26.2