On Saturday, September 26, 2015 at 4:40:07 AM UTC+8, Denys Vlasenko
wrote:
> Before this change MAX_LOCAL_APIC had the fixed value of 32*1024.
> Such a big value causes several data arrays to be quite oversized:
>
> phys_cpu_present_map is 4 kbytes (one bit per apic id),
> __apicid_to_node[] is 64 kbytes,
> apic_version[] is 128 kbytes.
>
> On "usual" systems, APIC ids simply go from zero
> to maximum logical CPU number, mirroring CPU ids.
>
> On broken and unusual multi-socket systems
> APIC ids can be non-contiguous.
The Intel x2APIC spec states the upper 16-bits of APIC ID is the
cluster ID [1, p2-12], intended for future distributed systems. Beyond
the legacy 8-bit APIC ID, Numascale NumaConnect uses 4-bits for the
position of a server on each axis of a multi-dimension torus; SGI
NUMAlink also structures the APIC ID space.
Instead, define an array based on NR_CPUs to achieve a 1:1 mapping and
perform linear search; this addresses the binary bloat and the present
artificial APIC ID limits. With CONFIG_NR_CPUS=256:
$ size vmlinux vmlinux-patched
text data bss dec hex filename
18232877 1849656 2281472 22364005 1553f65 vmlinux
18233034 1786168 2281472 22300674 1544802 vmlinux-patched
Works peachy on a 256-core system with a 20-bit APIC ID space, and on a
48-core legacy 8-bit APIC ID system. If we care, I can make
numa_cpu_node O(1) lookup for typical cases.
Signed-off-by: Daniel J Blueman <dan...@numascale.com>
Daniel
[1]
http://www.intel.com/content/dam/doc/specification-update/64-architecture-x2apic-specification.pdf
---
arch/x86/include/asm/numa.h | 13 +++++++------
arch/x86/kernel/cpu/amd.c | 8 ++++----
arch/x86/mm/numa.c | 31 +++++++++++++++++++++++--------
3 files changed, 34 insertions(+), 18 deletions(-)
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 01b493e..33becb8 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -17,6 +17,11 @@
*/
#define NODE_MIN_SIZE (4*1024*1024)
+struct apicid_to_node {
+ int apicid;
+ s16 node;
+};
+
extern int numa_off;
/*
@@ -27,17 +32,13 @@ extern int numa_off;
* should be accessed by the accessors - set_apicid_to_node() and
* numa_cpu_node().
*/
-extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+extern struct apicid_to_node __apicid_to_node[NR_CPUS];
extern nodemask_t numa_nodes_parsed __initdata;
extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
extern void __init numa_set_distance(int from, int to, int distance);
-static inline void set_apicid_to_node(int apicid, s16 node)
-{
- __apicid_to_node[apicid] = node;
-}
-
+extern void set_apicid_to_node(int apicid, s16 node);
extern int numa_cpu_node(int cpu);
#else /* CONFIG_NUMA */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4a70fc6..e65c01c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -277,12 +277,12 @@ static int nearby_node(int apicid)
int i, node;
for (i = apicid - 1; i >= 0; i--) {
- node = __apicid_to_node[i];
+ node = __apicid_to_node[i].node;
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].node;
if (node != NUMA_NO_NODE && node_online(node))
return node;
}
@@ -422,8 +422,8 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
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].node != NUMA_NO_NODE)
+ node = __apicid_to_node[ht_nodeid].node;
/* Pick a nearby node */
if (!node_online(node))
node = nearby_node(apicid);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c3b3f65..70f03a0 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -56,16 +56,34 @@ early_param("numa", numa_setup);
/*
* apicid, cpu, node mappings
*/
-s16 __apicid_to_node[MAX_LOCAL_APIC] = {
- [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+
+struct apicid_to_node __apicid_to_node[NR_CPUS] = {
+ [0 ... NR_CPUS-1] = {-1, NUMA_NO_NODE}
};
+void set_apicid_to_node(int apicid, s16 node)
+{
+ static int ent;
+
+ /* Protect against small kernel on large system */
+ if (ent >= NR_CPUS)
+ return;
+
+ __apicid_to_node[ent].apicid = apicid;
+ __apicid_to_node[ent].node = node;
+ ent++;
+}
+
int numa_cpu_node(int cpu)
{
- int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+ int ent, apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+ if (apicid == BAD_APICID)
+ return NUMA_NO_NODE;
+
+ for (ent = 0; ent < NR_CPUS; ent++)
+ if (__apicid_to_node[ent].apicid == apicid)
+ return __apicid_to_node[ent].node;
- if (apicid != BAD_APICID)
- return __apicid_to_node[apicid];
return NUMA_NO_NODE;
}
@@ -607,9 +625,6 @@ static int __init numa_init(int (*init_func)(void))
int i;
int ret;
- for (i = 0; i < MAX_LOCAL_APIC; i++)
- set_apicid_to_node(i, NUMA_NO_NODE);
-
nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
