[PATCH V3 2/8] scsi: megaraid_sas: fix selection of reply queue

[Ming Lei <ming.lei@xxxxxxxxxx>]

>From 84676c1f21 (genirq/affinity: assign vectors to all possible CPUs),
one msix vector can be created without any online CPU mapped, then
command may be queued, and won't be notified after its completion.

This patch setups mapping between cpu and reply queue according to irq
affinity info retrived by pci_irq_get_affinity(), and uses this info
to choose reply queue for queuing one command.

Then the chosen reply queue has to be active, and fixes IO hang caused
by using inactive reply queue which doesn't have any online CPU mapped.

Cc: Hannes Reinecke <hare@xxxxxxx>
Cc: Arun Easi <arun.easi@xxxxxxxxxx>
Cc: "Martin K. Petersen" <martin.petersen@xxxxxxxxxx>,
Cc: James Bottomley <james.bottomley@xxxxxxxxxxxxxxxxxxxxx>,
Cc: Christoph Hellwig <hch@xxxxxx>,
Cc: Don Brace <don.brace@xxxxxxxxxxxxx>
Cc: Kashyap Desai <kashyap.desai@xxxxxxxxxxxx>
Cc: Peter Rivera <peter.rivera@xxxxxxxxxxxx>
Cc: Laurence Oberman <loberman@xxxxxxxxxx>
Cc: Meelis Roos <mroos@xxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
 drivers/scsi/megaraid/megaraid_sas.h        |  2 +-
 drivers/scsi/megaraid/megaraid_sas_base.c   | 34 ++++++++++++++++++++++++++++-
 drivers/scsi/megaraid/megaraid_sas_fusion.c | 12 ++++------
 3 files changed, 38 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index ba6503f37756..a644d2be55b6 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -2127,7 +2127,7 @@ enum MR_PD_TYPE {
 #define MR_NVME_PAGE_SIZE_MASK		0x000000FF
 
 struct megasas_instance {
-
+	unsigned int *reply_map;
 	__le32 *producer;
 	dma_addr_t producer_h;
 	__le32 *consumer;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index a71ee67df084..065956cb2aeb 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5165,6 +5165,26 @@ megasas_setup_jbod_map(struct megasas_instance *instance)
 		instance->use_seqnum_jbod_fp = false;
 }
 
+static void megasas_setup_reply_map(struct megasas_instance *instance)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < instance->msix_vectors; queue++) {
+		mask = pci_irq_get_affinity(instance->pdev, queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			instance->reply_map[cpu] = queue;
+	}
+	return;
+
+fallback:
+	for_each_possible_cpu(cpu)
+		instance->reply_map[cpu] = 0;
+}
+
 /**
  * megasas_init_fw -	Initializes the FW
  * @instance:		Adapter soft state
@@ -5343,6 +5363,8 @@ static int megasas_init_fw(struct megasas_instance *instance)
 			goto fail_setup_irqs;
 	}
 
+	megasas_setup_reply_map(instance);
+
 	dev_info(&instance->pdev->dev,
 		"firmware supports msix\t: (%d)", fw_msix_count);
 	dev_info(&instance->pdev->dev,
@@ -6448,6 +6470,11 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	memset(instance, 0, sizeof(*instance));
 	atomic_set(&instance->fw_reset_no_pci_access, 0);
 
+	instance->reply_map = kzalloc(sizeof(unsigned int) * nr_cpu_ids,
+			GFP_KERNEL);
+	if (!instance->reply_map)
+		goto fail_alloc_reply_map;
+
 	/*
 	 * Initialize PCI related and misc parameters
 	 */
@@ -6539,8 +6566,9 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	if (instance->msix_vectors)
 		pci_free_irq_vectors(instance->pdev);
 fail_init_mfi:
+	kfree(instance->reply_map);
+fail_alloc_reply_map:
 	scsi_host_put(host);
-
 fail_alloc_instance:
 	pci_disable_device(pdev);
 
@@ -6746,6 +6774,8 @@ megasas_resume(struct pci_dev *pdev)
 	if (rval < 0)
 		goto fail_reenable_msix;
 
+	megasas_setup_reply_map(instance);
+
 	if (instance->adapter_type != MFI_SERIES) {
 		megasas_reset_reply_desc(instance);
 		if (megasas_ioc_init_fusion(instance)) {
@@ -6960,6 +6990,8 @@ static void megasas_detach_one(struct pci_dev *pdev)
 
 	megasas_free_ctrl_mem(instance);
 
+	kfree(instance->reply_map);
+
 	scsi_host_put(host);
 
 	pci_disable_device(pdev);
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 073ced07e662..2994176a0121 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -2655,11 +2655,8 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			fp_possible = (io_info.fpOkForIo > 0) ? true : false;
 	}
 
-	/* Use raw_smp_processor_id() for now until cmd->request->cpu is CPU
-	   id by default, not CPU group id, otherwise all MSI-X queues won't
-	   be utilized */
-	cmd->request_desc->SCSIIO.MSIxIndex = instance->msix_vectors ?
-		raw_smp_processor_id() % instance->msix_vectors : 0;
+	cmd->request_desc->SCSIIO.MSIxIndex =
+		instance->reply_map[raw_smp_processor_id()];
 
 	praid_context = &io_request->RaidContext;
 
@@ -2985,10 +2982,9 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 	}
 
 	cmd->request_desc->SCSIIO.DevHandle = io_request->DevHandle;
-	cmd->request_desc->SCSIIO.MSIxIndex =
-		instance->msix_vectors ?
-		(raw_smp_processor_id() % instance->msix_vectors) : 0;
 
+	cmd->request_desc->SCSIIO.MSIxIndex =
+		instance->reply_map[raw_smp_processor_id()];
 
 	if (!fp_possible) {
 		/* system pd firmware path */
-- 
2.9.5