[patch]x86: spread tlb flush vector between nodes

[Shaohua Li <shaohua.li@intel.com>]

Currently flush tlb vector allocation is based on below equation:
	sender = smp_processor_id() % 8
This isn't optimal, CPUs from different node can have the same vector, this
causes a lot of lock contention. Instead, we can assign the same vectors to
CPUs from the same node, while different node has different vectors. This has
below advantages:
a. if there is lock contention, the lock contention is between CPUs from one
node. This should be much cheaper than the contention between nodes.
b. completely avoid lock contention between nodes. This especially benefits
kswapd, which is the biggest user of tlb flush, since kswapd sets its affinity
to specific node.

In my test, this could reduce > 20% CPU overhead in extreme case.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
---
 arch/x86/mm/tlb.c |   47 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

Index: linux-2.6/arch/x86/mm/tlb.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/tlb.c	2010-10-13 20:40:19.000000000 +0800
+++ linux-2.6/arch/x86/mm/tlb.c	2010-10-13 23:19:26.000000000 +0800
@@ -5,6 +5,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/cpu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -52,6 +53,8 @@
    want false sharing in the per cpu data segment. */
 static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
 
+static int tlb_vector_offset[NR_CPUS] __read_mostly;
+
 /*
  * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
@@ -173,7 +176,7 @@
 	union smp_flush_state *f;
 
 	/* Caller has disabled preemption */
-	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
+	sender = tlb_vector_offset[smp_processor_id()];
 	f = &flush_state[sender];
 
 	/*
@@ -218,6 +221,46 @@
 	flush_tlb_others_ipi(cpumask, mm, va);
 }
 
+static void __cpuinit calculate_tlb_offset(void)
+{
+	int cpu, node, nr_node_vecs;
+	/*
+	 * we are changing tlb_vector_offset[] for each CPU in runtime, but this
+	 * will not cause inconsistency, as the write is atomic under X86. we
+	 * might see more lock contentions in a short time, but after all CPU's
+	 * tlb_vector_offset[] are changed, everything should go normal
+	 *
+	 * Note: if NUM_INVALIDATE_TLB_VECTORS % nr_online_nodes !=0, we might
+	 * waste some vectors.
+	 **/
+	if (nr_online_nodes > NUM_INVALIDATE_TLB_VECTORS)
+		nr_node_vecs = 1;
+	else
+		nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
+
+	for_each_online_node(node) {
+		int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) *
+			nr_node_vecs;
+		int cpu_offset = 0;
+		for_each_cpu(cpu, cpumask_of_node(node)) {
+			tlb_vector_offset[cpu] = node_offset + cpu_offset;
+			cpu_offset++;
+			cpu_offset = cpu_offset % nr_node_vecs;
+		}
+	}
+}
+
+static int tlb_cpuhp_notify(struct notifier_block *n,
+		unsigned long action, void *hcpu)
+{
+	switch (action & 0xf) {
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		calculate_tlb_offset();
+	}
+	return NOTIFY_OK;
+}
+
 static int __cpuinit init_smp_flush(void)
 {
 	int i;
@@ -225,6 +268,8 @@
 	for (i = 0; i < ARRAY_SIZE(flush_state); i++)
 		raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
+	calculate_tlb_offset();
+	hotcpu_notifier(tlb_cpuhp_notify, 0);
 	return 0;
 }
 core_initcall(init_smp_flush);