mpt2sas, mpt3sas: set cpu affinity for each MSIX vectors

Added a support to set cpu affinity mask for each MSIX vector enabled
by the HBA. So that, running the irqbalancer will balance interrupts among
the cpus.

Change_set:
1. Added affinity_hint varable of type cpumask_var_t in adapter_reply_queue
   structure. And allocated a memory for this varable by calling
   alloc_cpumask_var.
2. Call the API irq_set_affinity_hint for each MSIx vector to affiniate it
   with calculated cpus at driver inilization time.
3. While freeing the MSIX vector, call this same API to release the cpu
   affinity mask for each MSIx vector by providing the NULL value in
   cpumask argument.
4. then call the free_cpumask_var API to free the memory allocated in step 2.

Signed-off-by: Sreekanth Reddy <Sreekanth.Reddy@avagotech.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

4 files changed, 44 insertions, 6 deletions

diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.c b/drivers/scsi/mpt2sas/mpt2sas_base.c
index ee8ba5c..11248de 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.c
@@ -1300,6 +1300,8 @@ _base_free_irq(struct MPT2SAS_ADAPTER *ioc)
 
 	list_for_each_entry_safe(reply_q, next, &ioc->reply_queue_list, list) {
 		list_del(&reply_q->list);
+		irq_set_affinity_hint(reply_q->vector, NULL);
+		free_cpumask_var(reply_q->affinity_hint);
 		synchronize_irq(reply_q->vector);
 		free_irq(reply_q->vector, reply_q);
 		kfree(reply_q);
@@ -1329,6 +1331,11 @@ _base_request_irq(struct MPT2SAS_ADAPTER *ioc, u8 index, u32 vector)
 	reply_q->ioc = ioc;
 	reply_q->msix_index = index;
 	reply_q->vector = vector;
+
+	if (!alloc_cpumask_var(&reply_q->affinity_hint, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_clear(reply_q->affinity_hint);
+
 	atomic_set(&reply_q->busy, 0);
 	if (ioc->msix_enable)
 		snprintf(reply_q->name, MPT_NAME_LENGTH, "%s%d-msix%d",
@@ -1363,6 +1370,7 @@ static void
 _base_assign_reply_queues(struct MPT2SAS_ADAPTER *ioc)
 {
 	unsigned int cpu, nr_cpus, nr_msix, index = 0;
+	struct adapter_reply_queue *reply_q;
 
 	if (!_base_is_controller_msix_enabled(ioc))
 		return;
@@ -1377,20 +1385,30 @@ _base_assign_reply_queues(struct MPT2SAS_ADAPTER *ioc)
 
 	cpu = cpumask_first(cpu_online_mask);
 
-	do {
+	list_for_each_entry(reply_q, &ioc->reply_queue_list, list) {
+
 		unsigned int i, group = nr_cpus / nr_msix;
 
+		if (cpu >= nr_cpus)
+			break;
+
 		if (index < nr_cpus % nr_msix)
 			group++;
 
 		for (i = 0 ; i < group ; i++) {
 			ioc->cpu_msix_table[cpu] = index;
+			cpumask_or(reply_q->affinity_hint,
+				   reply_q->affinity_hint, get_cpu_mask(cpu));
 			cpu = cpumask_next(cpu, cpu_online_mask);
 		}
 
+		if (irq_set_affinity_hint(reply_q->vector,
+					   reply_q->affinity_hint))
+			dinitprintk(ioc, pr_info(MPT2SAS_FMT
+			    "error setting affinity hint for irq vector %d\n",
+			    ioc->name, reply_q->vector));
 		index++;
-
-	} while (cpu < nr_cpus);
+	}
 }
 
 /**
diff --git a/drivers/scsi/mpt2sas/mpt2sas_base.h b/drivers/scsi/mpt2sas/mpt2sas_base.h
index 72bffec..46e8d51 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_base.h
+++ b/drivers/scsi/mpt2sas/mpt2sas_base.h
@@ -587,6 +587,7 @@ struct adapter_reply_queue {
 	Mpi2ReplyDescriptorsUnion_t *reply_post_free;
 	char			name[MPT_NAME_LENGTH];
 	atomic_t		busy;
+	cpumask_var_t		affinity_hint;
 	struct list_head	list;
 };
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 549b500..14a781b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1584,6 +1584,8 @@ _base_free_irq(struct MPT3SAS_ADAPTER *ioc)
 
 	list_for_each_entry_safe(reply_q, next, &ioc->reply_queue_list, list) {
 		list_del(&reply_q->list);
+		irq_set_affinity_hint(reply_q->vector, NULL);
+		free_cpumask_var(reply_q->affinity_hint);
 		synchronize_irq(reply_q->vector);
 		free_irq(reply_q->vector, reply_q);
 		kfree(reply_q);
@@ -1613,6 +1615,11 @@ _base_request_irq(struct MPT3SAS_ADAPTER *ioc, u8 index, u32 vector)
 	reply_q->ioc = ioc;
 	reply_q->msix_index = index;
 	reply_q->vector = vector;
+
+	if (!alloc_cpumask_var(&reply_q->affinity_hint, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_clear(reply_q->affinity_hint);
+
 	atomic_set(&reply_q->busy, 0);
 	if (ioc->msix_enable)
 		snprintf(reply_q->name, MPT_NAME_LENGTH, "%s%d-msix%d",
@@ -1647,6 +1654,7 @@ static void
 _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
 {
 	unsigned int cpu, nr_cpus, nr_msix, index = 0;
+	struct adapter_reply_queue *reply_q;
 
 	if (!_base_is_controller_msix_enabled(ioc))
 		return;
@@ -1661,20 +1669,30 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc)
 
 	cpu = cpumask_first(cpu_online_mask);
 
-	do {
+	list_for_each_entry(reply_q, &ioc->reply_queue_list, list) {
+
 		unsigned int i, group = nr_cpus / nr_msix;
 
+		if (cpu >= nr_cpus)
+			break;
+
 		if (index < nr_cpus % nr_msix)
 			group++;
 
 		for (i = 0 ; i < group ; i++) {
 			ioc->cpu_msix_table[cpu] = index;
+			cpumask_or(reply_q->affinity_hint,
+				   reply_q->affinity_hint, get_cpu_mask(cpu));
 			cpu = cpumask_next(cpu, cpu_online_mask);
 		}
 
+		if (irq_set_affinity_hint(reply_q->vector,
+					   reply_q->affinity_hint))
+			dinitprintk(ioc, pr_info(MPT3SAS_FMT
+			    "error setting affinity hint for irq vector %d\n",
+			    ioc->name, reply_q->vector));
 		index++;
-
-	} while (cpu < nr_cpus);
+	}
 }
 
 /**
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 7e9f55b..afa8816 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -507,6 +507,7 @@ struct adapter_reply_queue {
 	Mpi2ReplyDescriptorsUnion_t *reply_post_free;
 	char			name[MPT_NAME_LENGTH];
 	atomic_t		busy;
+	cpumask_var_t		affinity_hint;
 	struct list_head	list;
 };