scsi: megaraid_sas: fix selection of reply queue

Since commit 84676c1f21e8 ("genirq/affinity: assign vectors to all
possible CPUs") we could end up with an MSI-X vector that did not have
any online CPUs mapped. This would lead to I/O hangs since there was no
CPU to receive the completion.

Retrieve IRQ affinity information using pci_irq_get_affinity() and use
this mapping to choose a reply queue.

[mkp: tweaked commit desc]

Cc: Hannes Reinecke <hare@suse.de>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>,
Cc: James Bottomley <james.bottomley@hansenpartnership.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: Don Brace <don.brace@microsemi.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Meelis Roos <mroos@linux.ee>
Cc: Artem Bityutskiy <artem.bityutskiy@intel.com>
Fixes: 84676c1f21e8 ("genirq/affinity: assign vectors to all possible CPUs")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Acked-by: Kashyap Desai <kashyap.desai@broadcom.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Artem Bityutskiy <artem.bityutskiy@intel.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 36 insertions, 3 deletions

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 0f1d88f272be..7b2bed5ab04c 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5165,6 +5165,26 @@ skip_alloc:
 		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] = cpu % instance->msix_vectors;
+}
+
 /**
  * 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,
@@ -6123,20 +6145,29 @@ static inline int megasas_alloc_mfi_ctrl_mem(struct megasas_instance *instance)
  */
 static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
 {
+	instance->reply_map = kzalloc(sizeof(unsigned int) * nr_cpu_ids,
+				      GFP_KERNEL);
+	if (!instance->reply_map)
+		return -ENOMEM;
+
 	switch (instance->adapter_type) {
 	case MFI_SERIES:
 		if (megasas_alloc_mfi_ctrl_mem(instance))
-			return -ENOMEM;
+			goto fail;
 		break;
 	case VENTURA_SERIES:
 	case THUNDERBOLT_SERIES:
 	case INVADER_SERIES:
 		if (megasas_alloc_fusion_context(instance))
-			return -ENOMEM;
+			goto fail;
 		break;
 	}
 
 	return 0;
+ fail:
+	kfree(instance->reply_map);
+	instance->reply_map = NULL;
+	return -ENOMEM;
 }
 
 /*
@@ -6148,6 +6179,7 @@ static int megasas_alloc_ctrl_mem(struct megasas_instance *instance)
  */
 static inline void megasas_free_ctrl_mem(struct megasas_instance *instance)
 {
+	kfree(instance->reply_map);
 	if (instance->adapter_type == MFI_SERIES) {
 		if (instance->producer)
 			pci_free_consistent(instance->pdev, sizeof(u32),
@@ -6540,7 +6572,6 @@ fail_io_attach:
 		pci_free_irq_vectors(instance->pdev);
 fail_init_mfi:
 	scsi_host_put(host);
-
 fail_alloc_instance:
 	pci_disable_device(pdev);
 
@@ -6746,6 +6777,8 @@ 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)) {