crypto: marvell/cesa - irq balance

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

From my testing with IPSec AES 256 SHA256
on my clearfog base with 2 Cores I get a 2x speed increase:

Before the patch: 26.74 Kpps
With the patch: 56.11 Kpps

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

drivers/crypto/marvell/cesa/cesa.c

···
 	struct mv_cesa_dev *cesa;
 	struct mv_cesa_engine *engines;
 	struct resource *res;
-	int irq, ret, i;
+	int irq, ret, i, cpu;
 	u32 sram_size;
 
 	if (cesa_dev) {
···
 			goto err_cleanup;
 		}
 
+		engine->irq = irq;
+
 		/*
 		 * Not all platforms can gate the CESA clocks: do not complain
 		 * if the clock does not exist.
···
 		if (ret)
 			goto err_cleanup;
 
+		/* Set affinity */
+		cpu = cpumask_local_spread(engine->id, NUMA_NO_NODE);
+		irq_set_affinity_hint(irq, get_cpu_mask(cpu));
+
 		crypto_init_queue(&engine->queue, CESA_CRYPTO_DEFAULT_MAX_QLEN);
 		atomic_set(&engine->load, 0);
 		INIT_LIST_HEAD(&engine->complete_queue);
···
 		clk_disable_unprepare(cesa->engines[i].zclk);
 		clk_disable_unprepare(cesa->engines[i].clk);
 		mv_cesa_put_sram(pdev, i);
+		if (cesa->engines[i].irq > 0)
+			irq_set_affinity_hint(cesa->engines[i].irq, NULL);
 	}
 
 	return ret;
···
 		clk_disable_unprepare(cesa->engines[i].zclk);
 		clk_disable_unprepare(cesa->engines[i].clk);
 		mv_cesa_put_sram(pdev, i);
+		irq_set_affinity_hint(cesa->engines[i].irq, NULL);
 	}
 
 	return 0;

drivers/crypto/marvell/cesa/cesa.h

···
 	atomic_t load;
 	struct mv_cesa_tdma_chain chain;
 	struct list_head complete_queue;
+	int irq;
 };
 
 /**