x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit
The mapping between cpu/apicid and node is done via
apicid_to_node[] on 64bit and apicid_2_node[] +
apic->x86_32_numa_cpu_node() on 32bit. This difference makes it
difficult to further unify 32 and 64bit NUMA handling.
This patch unifies it by replacing both apicid_to_node[] and
apicid_2_node[] with __apicid_to_node[] array, which is accessed
by two accessors - set_apicid_to_node() and numa_cpu_node(). On
64bit, numa_cpu_node() always consults __apicid_to_node[]
directly while 32bit goes through apic->numa_cpu_node() method
to allow apic implementations to override it.
srat_detect_node() for amd cpus contains workaround for broken
NUMA configuration which assumes relationship between APIC ID,
HT node ID and NUMA topology. Leave it to access
__apicid_to_node[] directly as mapping through CPU might result
in undesirable behavior change. The comment is reformatted and
updated to note the ugliness.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Cc: eric.dumazet@gmail.com
Cc: yinghai@kernel.org
Cc: brgerst@gmail.com
Cc: gorcunov@gmail.com
Cc: shaohui.zheng@intel.com
Cc: rientjes@google.com
LKML-Reference: <1295789862-25482-14-git-send-email-tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: David Rientjes <rientjes@google.com>
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b3a7113..a7bca59 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -589,11 +589,10 @@
nid = acpi_get_node(handle);
if (nid == -1 || !node_online(nid))
return;
+ set_apicid_to_node(physid, nid);
#ifdef CONFIG_X86_64
- apicid_to_node[physid] = nid;
numa_set_node(cpu, nid);
#else /* CONFIG_X86_32 */
- apicid_2_node[physid] = nid;
cpu_to_node_map[cpu] = nid;
#endif
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 0f4f3c1..4686ea5 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2026,7 +2026,7 @@
int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
if (apicid != BAD_APICID)
- return apicid_2_node[apicid];
+ return __apicid_to_node[apicid];
return NUMA_NO_NODE;
#else
return 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7c7bedb..3cce8f2 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -234,17 +234,21 @@
#endif
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
+/*
+ * To workaround broken NUMA config. Read the comment in
+ * srat_detect_node().
+ */
static int __cpuinit nearby_node(int apicid)
{
int i, node;
for (i = apicid - 1; i >= 0; i--) {
- node = apicid_to_node[i];
+ node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
for (i = apicid + 1; i < MAX_LOCAL_APIC; i++) {
- node = apicid_to_node[i];
+ node = __apicid_to_node[i];
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
@@ -339,26 +343,35 @@
int node;
unsigned apicid = c->apicid;
- node = per_cpu(cpu_llc_id, cpu);
+ node = numa_cpu_node(cpu);
+ if (node == NUMA_NO_NODE)
+ node = per_cpu(cpu_llc_id, cpu);
- if (apicid_to_node[apicid] != NUMA_NO_NODE)
- node = apicid_to_node[apicid];
if (!node_online(node)) {
- /* Two possibilities here:
- - The CPU is missing memory and no node was created.
- In that case try picking one from a nearby CPU
- - The APIC IDs differ from the HyperTransport node IDs
- which the K8 northbridge parsing fills in.
- Assume they are all increased by a constant offset,
- but in the same order as the HT nodeids.
- If that doesn't result in a usable node fall back to the
- path for the previous case. */
-
+ /*
+ * Two possibilities here:
+ *
+ * - The CPU is missing memory and no node was created. In
+ * that case try picking one from a nearby CPU.
+ *
+ * - The APIC IDs differ from the HyperTransport node IDs
+ * which the K8 northbridge parsing fills in. Assume
+ * they are all increased by a constant offset, but in
+ * the same order as the HT nodeids. If that doesn't
+ * result in a usable node fall back to the path for the
+ * previous case.
+ *
+ * This workaround operates directly on the mapping between
+ * APIC ID and NUMA node, assuming certain relationship
+ * between APIC ID, HT node ID and NUMA topology. As going
+ * through CPU mapping may alter the outcome, directly
+ * access __apicid_to_node[].
+ */
int ht_nodeid = c->initial_apicid;
if (ht_nodeid >= 0 &&
- apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
- node = apicid_to_node[ht_nodeid];
+ __apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
+ node = __apicid_to_node[ht_nodeid];
/* Pick a nearby node */
if (!node_online(node))
node = nearby_node(apicid);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d16c2c5..6052004 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -279,11 +279,10 @@
#if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
unsigned node;
int cpu = smp_processor_id();
- int apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
/* Don't do the funky fallback heuristics the AMD version employs
for now. */
- node = apicid_to_node[apicid];
+ node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE || !node_online(node)) {
/* reuse the value from init_cpu_to_node() */
node = cpu_to_node(cpu);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 5319cdd..b7cfce5 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -71,10 +71,6 @@
#include <asm/smpboot_hooks.h>
#include <asm/i8259.h>
-#ifdef CONFIG_X86_32
-u8 apicid_2_node[MAX_LOCAL_APIC];
-#endif
-
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -170,7 +166,7 @@
int cpu = smp_processor_id();
int node;
- node = apic->x86_32_numa_cpu_node(cpu);
+ node = numa_cpu_node(cpu);
if (!node_online(node))
node = first_online_node;