sparc64: fix and optimize irq distribution

irq_choose_cpu() should compare the affinity mask against cpu_online_map
rather than CPU_MASK_ALL, since irq_select_affinity() sets the interrupt's
affinity mask to cpu_online_map "and" CPU_MASK_ALL (which ends up being
just cpu_online_map).  The mask comparison in irq_choose_cpu() will always
fail since the two masks are not the same.  So the CPU chosen is the first CPU
in the intersection of cpu_online_map and CPU_MASK_ALL, which is always CPU0.
That means all interrupts are reassigned to CPU0...

Distributing interrupts to CPUs in a linearly increasing round robin fashion
is not optimal for the UltraSPARC T1/T2.  Also, the irq_rover in
irq_choose_cpu() causes an interrupt to be assigned to a different
processor each time the interrupt is allocated and released.  This may lead
to an unbalanced distribution over time.

A static mapping of interrupts to processors is done to optimize and balance
interrupt distribution.  For the T1/T2, interrupts are spread to different
cores first, and then to strands within a core.

The following is some benchmarks showing the effects of interrupt
distribution on a T2.  The test was done with iperf using a pair of T5220
boxes, each with a 10GBe NIU (XAUI) connected back to back.

  TCP     | Stock       Linear RR IRQ  Optimized IRQ
  Streams | 2.6.30-rc5  Distribution   Distribution
          | GBits/sec   GBits/sec      GBits/sec
  --------+-----------------------------------------
    1       0.839       0.862          0.868
    8       1.16        4.96           5.88
   16       1.15        6.40           8.04
  100       1.09        7.28           8.68
Signed-off-by: Hong H. Pham <hong.pham@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/kernel/Makefile

@@ -54,6 +54,7 @@ obj-$(CONFIG_SPARC64)   += sstate.o
 obj-$(CONFIG_SPARC64)   += mdesc.o
 obj-$(CONFIG_SPARC64)	+= pcr.o
 obj-$(CONFIG_SPARC64)	+= nmi.o
+obj-$(CONFIG_SPARC64_SMP) += cpumap.o
 
 # sparc32 do not use GENERIC_HARDIRQS but uses the generic devres implementation
 obj-$(CONFIG_SPARC32)     += devres.o

arch/sparc/kernel/cpumap.h

+#ifndef _CPUMAP_H
+#define _CPUMAP_H
+
+#ifdef CONFIG_SMP
+extern void cpu_map_rebuild(void);
+extern int  map_to_cpu(unsigned int index);
+#define cpu_map_init() cpu_map_rebuild()
+#else
+#define cpu_map_init() do {} while (0)
+static inline int map_to_cpu(unsigned int index)
+{
+	return raw_smp_processor_id();
+}
+#endif
+
+#endif

arch/sparc/kernel/irq_64.c

@@ -45,6 +45,7 @@
 #include <asm/cacheflush.h>
 
 #include "entry.h"
+#include "cpumap.h"
 
 #define NUM_IVECS	(IMAP_INR + 1)
 
@@ -256,35 +257,13 @@ static int irq_choose_cpu(unsigned int virt_irq)
 	int cpuid;
 
 	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
-	if (cpus_equal(mask, CPU_MASK_ALL)) {
-		static int irq_rover;
-		static DEFINE_SPINLOCK(irq_rover_lock);
-		unsigned long flags;
-
-		/* Round-robin distribution... */
-	do_round_robin:
-		spin_lock_irqsave(&irq_rover_lock, flags);
-
-		while (!cpu_online(irq_rover)) {
-			if (++irq_rover >= nr_cpu_ids)
-				irq_rover = 0;
-		}
-		cpuid = irq_rover;
-		do {
-			if (++irq_rover >= nr_cpu_ids)
-				irq_rover = 0;
-		} while (!cpu_online(irq_rover));
-
-		spin_unlock_irqrestore(&irq_rover_lock, flags);
+	if (cpus_equal(mask, cpu_online_map)) {
+		cpuid = map_to_cpu(virt_irq);
 	} else {
 		cpumask_t tmp;
 
 		cpus_and(tmp, cpu_online_map, mask);
-
-		if (cpus_empty(tmp))
-			goto do_round_robin;
-
-		cpuid = first_cpu(tmp);
+		cpuid = cpus_empty(tmp) ? map_to_cpu(virt_irq) : first_cpu(tmp);
 	}
 
 	return cpuid;

arch/sparc/kernel/smp_64.c

@@ -48,6 +48,8 @@
 #include <asm/ldc.h>
 #include <asm/hypervisor.h>
 
+#include "cpumap.h"
+
 int sparc64_multi_core __read_mostly;
 
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
@@ -1314,6 +1316,8 @@ int __cpu_disable(void)
 	cpu_clear(cpu, cpu_online_map);
 	ipi_call_unlock();
 
+	cpu_map_rebuild();
+
 	return 0;
 }