scsi: hisi_sas: use threaded irq to process CQ interrupts

Currently IRQ_EFFECTIVE_AFF_MASK is enabled for ARM_GIC and ARM_GIC3, so it
only allows a single target CPU in the affinity mask to process interrupts
and also interrupt thread, and the performance of using threaded irq is
almost the same as tasklet. But if the config is not enabled, the interrupt
thread will be allowed all the CPUs in the affinity mask. At that situation
it improves the performance (about 20%).

Note: IRQ_EFFECTIVE_AFF_MASK is configured differently for different
architecture chip, and it seems to be better to make it be configured
easily.

Link: https://lore.kernel.org/r/1579522957-4393-2-git-send-email-john.garry@huawei.com
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 10 insertions, 16 deletions

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 545eaff5f3ee..a0e05a118f2c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3111,9 +3111,9 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
 	return IRQ_HANDLED;
 }
 
-static void cq_tasklet_v2_hw(unsigned long val)
+static irqreturn_t  cq_thread_v2_hw(int irq_no, void *p)
 {
-	struct hisi_sas_cq *cq = (struct hisi_sas_cq *)val;
+	struct hisi_sas_cq *cq = p;
 	struct hisi_hba *hisi_hba = cq->hisi_hba;
 	struct hisi_sas_slot *slot;
 	struct hisi_sas_itct *itct;
@@ -3181,6 +3181,8 @@ static void cq_tasklet_v2_hw(unsigned long val)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
@@ -3191,9 +3193,7 @@ static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
 
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
 
-	tasklet_schedule(&cq->tasklet);
-
-	return IRQ_HANDLED;
+	return IRQ_WAKE_THREAD;
 }
 
 static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
@@ -3360,18 +3360,18 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 
 	for (queue_no = 0; queue_no < hisi_hba->queue_count; queue_no++) {
 		struct hisi_sas_cq *cq = &hisi_hba->cq[queue_no];
-		struct tasklet_struct *t = &cq->tasklet;
 
-		irq = irq_map[queue_no + 96];
-		rc = devm_request_irq(dev, irq, cq_interrupt_v2_hw, 0,
-				      DRV_NAME " cq", cq);
+		cq->irq_no = 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);
 			rc = -ENOENT;
 			goto err_out;
 		}
-		tasklet_init(t, cq_tasklet_v2_hw, (unsigned long)cq);
 	}
 
 	hisi_hba->cq_nvecs = hisi_hba->queue_count;
@@ -3432,7 +3432,6 @@ static int soft_reset_v2_hw(struct hisi_hba *hisi_hba)
 
 	interrupt_disable_v2_hw(hisi_hba);
 	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
-	hisi_sas_kill_tasklets(hisi_hba);
 
 	hisi_sas_stop_phys(hisi_hba);
 
@@ -3606,11 +3605,6 @@ static int hisi_sas_v2_probe(struct platform_device *pdev)
 
 static int hisi_sas_v2_remove(struct platform_device *pdev)
 {
-	struct sas_ha_struct *sha = platform_get_drvdata(pdev);
-	struct hisi_hba *hisi_hba = sha->lldd_ha;
-
-	hisi_sas_kill_tasklets(hisi_hba);
-
 	return hisi_sas_remove(pdev);
 }