x86, numa: Fake apicid and pxm mappings for NUMA emulation
This patch adds the equivalent of acpi_fake_nodes() for AMD Northbridge
platforms. The goal is to fake the apicid-to-node mappings for NUMA
emulation so the physical topology of the machine is correctly maintained
within the kernel.
This change also fakes proximity domains for both ACPI and k8 code so the
physical distance between emulated nodes is maintained via
node_distance(). This exports the correct distances via
/sys/devices/system/node/.../distance based on the underlying topology.
A new helper function, fake_physnodes(), is introduced to correctly
invoke the correct NUMA code to fake these two mappings based on the
system type. If there is no underlying NUMA configuration, all cpus are
mapped to node 0 for local distance.
Since acpi_fake_nodes() is no longer called with CONFIG_ACPI_NUMA, it's
prototype can be removed from the header file for such a configuration.
Signed-off-by: David Rientjes <rientjes@google.com>
LKML-Reference: <alpine.DEB.2.00.1012221701360.3701@chino.kir.corp.google.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index fe050af..eb5cbb9 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -27,6 +27,7 @@
#include <asm/amd_nb.h>
static struct bootnode __initdata nodes[8];
+static unsigned char __initdata nodeids[8];
static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
static __init int find_northbridge(void)
@@ -69,21 +70,6 @@
early_init_lapic_mapping();
}
-#ifdef CONFIG_NUMA_EMU
-int __init amd_get_nodes(struct bootnode *physnodes)
-{
- int i;
- int ret = 0;
-
- for_each_node_mask(i, nodes_parsed) {
- physnodes[ret].start = nodes[i].start;
- physnodes[ret].end = nodes[i].end;
- ret++;
- }
- return ret;
-}
-#endif /* CONFIG_NUMA_EMU */
-
int __init amd_numa_init(unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long start = PFN_PHYS(start_pfn);
@@ -116,7 +102,7 @@
base = read_pci_config(0, nb, 1, 0x40 + i*8);
limit = read_pci_config(0, nb, 1, 0x44 + i*8);
- nodeid = limit & 7;
+ nodeids[i] = nodeid = limit & 7;
if ((base & 3) == 0) {
if (i < numnodes)
pr_info("Skipping disabled node %d\n", i);
@@ -196,6 +182,79 @@
return 0;
}
+#ifdef CONFIG_NUMA_EMU
+static s16 fake_apicid_to_node[MAX_LOCAL_APIC] __initdata = {
+ [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
+int __init amd_get_nodes(struct bootnode *physnodes)
+{
+ int i;
+ int ret = 0;
+
+ for_each_node_mask(i, nodes_parsed) {
+ physnodes[ret].start = nodes[i].start;
+ physnodes[ret].end = nodes[i].end;
+ ret++;
+ }
+ return ret;
+}
+
+static int __init find_node_by_addr(unsigned long addr)
+{
+ int ret = NUMA_NO_NODE;
+ int i;
+
+ for (i = 0; i < 8; i++)
+ if (addr >= nodes[i].start && addr < nodes[i].end) {
+ ret = i;
+ break;
+ }
+ return ret;
+}
+
+/*
+ * For NUMA emulation, fake proximity domain (_PXM) to node id mappings must be
+ * setup to represent the physical topology but reflect the emulated
+ * environment. For each emulated node, the real node which it appears on is
+ * found and a fake pxm to nid mapping is created which mirrors the actual
+ * locality. node_distance() then represents the correct distances between
+ * emulated nodes by using the fake acpi mappings to pxms.
+ */
+void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
+{
+ unsigned int bits;
+ unsigned int cores;
+ unsigned int apicid_base = 0;
+ int i;
+
+ bits = boot_cpu_data.x86_coreid_bits;
+ cores = 1 << bits;
+ early_get_boot_cpu_id();
+ if (boot_cpu_physical_apicid > 0)
+ apicid_base = boot_cpu_physical_apicid;
+
+ for (i = 0; i < nr_nodes; i++) {
+ int index;
+ int nid;
+ int j;
+
+ nid = find_node_by_addr(nodes[i].start);
+ if (nid == NUMA_NO_NODE)
+ continue;
+
+ index = nodeids[nid] << bits;
+ if (fake_apicid_to_node[index + apicid_base] == NUMA_NO_NODE)
+ for (j = apicid_base; j < cores + apicid_base; j++)
+ fake_apicid_to_node[index + j] = i;
+#ifdef CONFIG_ACPI_NUMA
+ __acpi_map_pxm_to_node(nid, i);
+#endif
+ }
+ memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+}
+#endif /* CONFIG_NUMA_EMU */
+
int __init amd_scan_nodes(void)
{
unsigned int bits;