diff mbox series

[v3,4/5] megaraid_sas: Handle missing interrupts while re-enabling IRQs

Message ID 20210528131307.25683-5-chandrakanth.patil@broadcom.com
State New
Headers show
Series megaraid_sas: Update driver version to 07.717.02.00-rc1 | expand

Commit Message

Chandrakanth Patil May 28, 2021, 1:13 p.m. UTC 
While reenabling the IRQ after irq poll there may be a small window for
the firmware to post the replies with interrupts raised. In that case,
driver will not see the interrupts which lead to IOs timeout.

This issue hits only when there is a high IOs completion on a single reply
queue, which forces the driver to switch between the interrupt and IRQ
context.

To fix this, driver will process the reply queue one more time after
enabling the IRQ.

Link: https://lore.kernel.org/linux-scsi/20201102072746.27410-1-sreekanth.reddy@broadcom.com/
Cc: Tomas Henzl <thenzl@redhat.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Chandrakanth Patil <chandrakanth.patil@broadcom.com>
Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
---
 drivers/scsi/megaraid/megaraid_sas_fusion.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index f79c19010c92..142e60741094 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -3745,6 +3745,7 @@  static void megasas_sync_irqs(unsigned long instance_addr)
 		if (irq_ctx->irq_poll_scheduled) {
 			irq_ctx->irq_poll_scheduled = false;
 			enable_irq(irq_ctx->os_irq);
+			complete_cmd_fusion(instance, irq_ctx->MSIxIndex, irq_ctx);
 		}
 	}
 }
@@ -3776,6 +3777,7 @@  int megasas_irqpoll(struct irq_poll *irqpoll, int budget)
 		irq_poll_complete(irqpoll);
 		irq_ctx->irq_poll_scheduled = false;
 		enable_irq(irq_ctx->os_irq);
+		complete_cmd_fusion(instance, irq_ctx->MSIxIndex, irq_ctx);
 	}
 
 	return num_entries;
@@ -3792,6 +3794,7 @@  megasas_complete_cmd_dpc_fusion(unsigned long instance_addr)
 {
 	struct megasas_instance *instance =
 		(struct megasas_instance *)instance_addr;
+	struct megasas_irq_context *irq_ctx = NULL;
 	u32 count, MSIxIndex;
 
 	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
@@ -3800,8 +3803,10 @@  megasas_complete_cmd_dpc_fusion(unsigned long instance_addr)
 	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
 		return;
 
-	for (MSIxIndex = 0 ; MSIxIndex < count; MSIxIndex++)
-		complete_cmd_fusion(instance, MSIxIndex, NULL);
+	for (MSIxIndex = 0 ; MSIxIndex < count; MSIxIndex++) {
+		irq_ctx = &instance->irq_context[MSIxIndex];
+		complete_cmd_fusion(instance, MSIxIndex, irq_ctx);
+	}
 }
 
 /**