crypto: inside-secure - irq balance

Balance the irqs of the inside secure driver over all
available cpus.
Currently all interrupts are handled by the first CPU.

From my testing with IPSec AES-GCM 256
on my MCbin with 4 Cores I get a 50% speed increase:

Before the patch: 99.73 Kpps
With the patch: 151.25 Kpps

Signed-off-by: Sven Auhagen <[e-mail]>
Signed-off-by: Herbert Xu <[e-mail]>

drivers/crypto/inside-secure/safexcel.c

···
 
 static int safexcel_request_ring_irq(void *pdev, int irqid,
 				     int is_pci_dev,
+				     int ring_id,
 				     irq_handler_t handler,
 				     irq_handler_t threaded_handler,
 				     struct safexcel_ring_irq_data *ring_irq_priv)
 {
-	int ret, irq;
+	int ret, irq, cpu;
 	struct device *dev;
 
 	if (IS_ENABLED(CONFIG_PCI) && is_pci_dev) {
···
 		dev_err(dev, "unable to request IRQ %d\n", irq);
 		return ret;
 	}
+
+	/* Set affinity */
+	cpu = cpumask_local_spread(ring_id, NUMA_NO_NODE);
+	irq_set_affinity_hint(irq, get_cpu_mask(cpu));
 
 	return irq;
 }
···
 		irq = safexcel_request_ring_irq(pdev,
 						EIP197_IRQ_NUMBER(i, is_pci_dev),
 						is_pci_dev,
+						i,
 						safexcel_irq_ring,
 						safexcel_irq_ring_thread,
 						ring_irq);
···
 			return irq;
 		}
 
+		priv->ring[i].irq = irq;
 		priv->ring[i].work_data.priv = priv;
 		priv->ring[i].work_data.ring = i;
 		INIT_WORK(&priv->ring[i].work_data.work,
···
 	clk_disable_unprepare(priv->reg_clk);
 	clk_disable_unprepare(priv->clk);
 
-	for (i = 0; i < priv->config.rings; i++)
+	for (i = 0; i < priv->config.rings; i++) {
+		irq_set_affinity_hint(priv->ring[i].irq, NULL);
 		destroy_workqueue(priv->ring[i].workqueue);
+	}
 
 	return 0;
 }

drivers/crypto/inside-secure/safexcel.h

···
 	 */
 	struct crypto_async_request *req;
 	struct crypto_async_request *backlog;
+
+	/* irq of this ring */
+	int irq;
 };
 
 /* EIP integration context flags */