x86/apic: Reduce cache line misses in __x2apic_send_IPI_mask()

Using per-cpu storage for @x86_cpu_to_logical_apicid is not optimal.

Broadcast IPI will need at least one cache line per cpu to access this
field.

__x2apic_send_IPI_mask() is using standard bitmask operators.

By converting x86_cpu_to_logical_apicid to an array, we divide by 16x
number of needed cache lines, because we find 16 values per cache
line. CPU prefetcher can kick nicely.

Also move @cluster_masks to READ_MOSTLY section to avoid false sharing.

Tested on a dual socket host with 256 cpus, cost for a full broadcast
is now 11 usec instead of 33 usec.

Signed-off-by: Eric Dumazet <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: edumazet

arch/x86/kernel/apic/x2apic_cluster.c

@@ -15,9 +15,15 @@ struct cluster_mask {
 	struct cpumask	mask;
 };
 
-static DEFINE_PER_CPU(u32, x86_cpu_to_logical_apicid);
+/*
+ * __x2apic_send_IPI_mask() possibly needs to read
+ * x86_cpu_to_logical_apicid for all online cpus in a sequential way.
+ * Using per cpu variable would cost one cache line per cpu.
+ */
+static u32 *x86_cpu_to_logical_apicid __read_mostly;
+
 static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
-static DEFINE_PER_CPU(struct cluster_mask *, cluster_masks);
+static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks);
 static struct cluster_mask *cluster_hotplug_mask;
 
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
@@ -27,7 +33,7 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 
 static void x2apic_send_IPI(int cpu, int vector)
 {
-	u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu);
+	u32 dest = x86_cpu_to_logical_apicid[cpu];
 
 	/* x2apic MSRs are special and need a special fence: */
 	weak_wrmsr_fence();
@@ -58,7 +64,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 
 		dest = 0;
 		for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask)
-			dest |= per_cpu(x86_cpu_to_logical_apicid, clustercpu);
+			dest |= x86_cpu_to_logical_apicid[clustercpu];
 
 		if (!dest)
 			continue;
@@ -94,7 +100,7 @@ static void x2apic_send_IPI_all(int vector)
 
 static u32 x2apic_calc_apicid(unsigned int cpu)
 {
-	return per_cpu(x86_cpu_to_logical_apicid, cpu);
+	return x86_cpu_to_logical_apicid[cpu];
 }
 
 static void init_x2apic_ldr(void)
@@ -103,7 +109,7 @@ static void init_x2apic_ldr(void)
 	u32 cluster, apicid = apic_read(APIC_LDR);
 	unsigned int cpu;
 
-	this_cpu_write(x86_cpu_to_logical_apicid, apicid);
+	x86_cpu_to_logical_apicid[smp_processor_id()] = apicid;
 
 	if (cmsk)
 		goto update;
@@ -166,12 +172,21 @@ static int x2apic_dead_cpu(unsigned int dead_cpu)
 
 static int x2apic_cluster_probe(void)
 {
+	u32 slots;
+
 	if (!x2apic_mode)
 		return 0;
 
+	slots = max_t(u32, L1_CACHE_BYTES/sizeof(u32), nr_cpu_ids);
+	x86_cpu_to_logical_apicid = kcalloc(slots, sizeof(u32), GFP_KERNEL);
+	if (!x86_cpu_to_logical_apicid)
+		return 0;
+
 	if (cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "x86/x2apic:prepare",
 			      x2apic_prepare_cpu, x2apic_dead_cpu) < 0) {
 		pr_err("Failed to register X2APIC_PREPARE\n");
+		kfree(x86_cpu_to_logical_apicid);
+		x86_cpu_to_logical_apicid = NULL;
 		return 0;
 	}
 	init_x2apic_ldr();