aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAndi Kleen <ak@suse.de>2007-07-21 17:10:03 +0200
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-07-21 18:37:08 -0700
commit67cddd947992b02f01ad093ec814738c5827d17c (patch)
tree5c10c3a1f645c119e0cc23ecdfc7c3c4dd7eacad
parent2aae950b21e4bc789d1fc6668faf67e8748300b7 (diff)
i386: Add L3 cache support to AMD CPUID4 emulation
With that an L3 cache is correctly reported in the cache information in /sys With fixes from Andreas Herrmann and Dean Gaudet and Joachim Deguara Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--arch/i386/kernel/cpu/amd.c8
-rw-r--r--arch/i386/kernel/cpu/intel_cacheinfo.c74
-rw-r--r--arch/x86_64/kernel/setup.c7
3 files changed, 65 insertions, 24 deletions
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index 6f47eeeb93e..815a5f0aa47 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -272,8 +272,12 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
}
#endif
- if (cpuid_eax(0x80000000) >= 0x80000006)
- num_cache_leaves = 3;
+ if (cpuid_eax(0x80000000) >= 0x80000006) {
+ if ((c->x86 == 0x10) && (cpuid_edx(0x80000006) & 0xf000))
+ num_cache_leaves = 4;
+ else
+ num_cache_leaves = 3;
+ }
if (amd_apic_timer_broken())
set_bit(X86_FEATURE_LAPIC_TIMER_BROKEN, c->x86_capability);
diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c
index 25b4b7d89ca..43db806b960 100644
--- a/arch/i386/kernel/cpu/intel_cacheinfo.c
+++ b/arch/i386/kernel/cpu/intel_cacheinfo.c
@@ -4,7 +4,7 @@
* Changes:
* Venkatesh Pallipadi : Adding cache identification through cpuid(4)
* Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
- * Andi Kleen : CPUID4 emulation on AMD.
+ * Andi Kleen / Andreas Herrmann : CPUID4 emulation on AMD.
*/
#include <linux/init.h>
@@ -135,7 +135,7 @@ unsigned short num_cache_leaves;
/* AMD doesn't have CPUID4. Emulate it here to report the same
information to the user. This makes some assumptions about the machine:
- No L3, L2 not shared, no SMT etc. that is currently true on AMD CPUs.
+ L2 not shared, no SMT etc. that is currently true on AMD CPUs.
In theory the TLBs could be reported as fake type (they are in "dummy").
Maybe later */
@@ -159,13 +159,26 @@ union l2_cache {
unsigned val;
};
+union l3_cache {
+ struct {
+ unsigned line_size : 8;
+ unsigned lines_per_tag : 4;
+ unsigned assoc : 4;
+ unsigned res : 2;
+ unsigned size_encoded : 14;
+ };
+ unsigned val;
+};
+
static const unsigned short assocs[] = {
[1] = 1, [2] = 2, [4] = 4, [6] = 8,
- [8] = 16,
+ [8] = 16, [0xa] = 32, [0xb] = 48,
+ [0xc] = 64,
[0xf] = 0xffff // ??
- };
-static const unsigned char levels[] = { 1, 1, 2 };
-static const unsigned char types[] = { 1, 2, 3 };
+};
+
+static const unsigned char levels[] = { 1, 1, 2, 3 };
+static const unsigned char types[] = { 1, 2, 3, 3 };
static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
union _cpuid4_leaf_ebx *ebx,
@@ -175,37 +188,58 @@ static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
unsigned line_size, lines_per_tag, assoc, size_in_kb;
union l1_cache l1i, l1d;
union l2_cache l2;
+ union l3_cache l3;
+ union l1_cache *l1 = &l1d;
eax->full = 0;
ebx->full = 0;
ecx->full = 0;
cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val);
- cpuid(0x80000006, &dummy, &dummy, &l2.val, &dummy);
-
- if (leaf > 2 || !l1d.val || !l1i.val || !l2.val)
- return;
-
- eax->split.is_self_initializing = 1;
- eax->split.type = types[leaf];
- eax->split.level = levels[leaf];
- eax->split.num_threads_sharing = 0;
- eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
-
- if (leaf <= 1) {
- union l1_cache *l1 = leaf == 0 ? &l1d : &l1i;
+ cpuid(0x80000006, &dummy, &dummy, &l2.val, &l3.val);
+
+ switch (leaf) {
+ case 1:
+ l1 = &l1i;
+ case 0:
+ if (!l1->val)
+ return;
assoc = l1->assoc;
line_size = l1->line_size;
lines_per_tag = l1->lines_per_tag;
size_in_kb = l1->size_in_kb;
- } else {
+ break;
+ case 2:
+ if (!l2.val)
+ return;
assoc = l2.assoc;
line_size = l2.line_size;
lines_per_tag = l2.lines_per_tag;
/* cpu_data has errata corrections for K7 applied */
size_in_kb = current_cpu_data.x86_cache_size;
+ break;
+ case 3:
+ if (!l3.val)
+ return;
+ assoc = l3.assoc;
+ line_size = l3.line_size;
+ lines_per_tag = l3.lines_per_tag;
+ size_in_kb = l3.size_encoded * 512;
+ break;
+ default:
+ return;
}
+ eax->split.is_self_initializing = 1;
+ eax->split.type = types[leaf];
+ eax->split.level = levels[leaf];
+ if (leaf == 3)
+ eax->split.num_threads_sharing = current_cpu_data.x86_max_cores - 1;
+ else
+ eax->split.num_threads_sharing = 0;
+ eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
+
+
if (assoc == 0xf)
eax->split.is_fully_associative = 1;
ebx->split.coherency_line_size = line_size - 1;
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 675b3d6de10..6fa0a302e2a 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -602,8 +602,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
if (c->extended_cpuid_level >= 0x80000008)
amd_detect_cmp(c);
- /* Fix cpuid4 emulation for more */
- num_cache_leaves = 3;
+ if (c->extended_cpuid_level >= 0x80000006 &&
+ (cpuid_edx(0x80000006) & 0xf000))
+ num_cache_leaves = 4;
+ else
+ num_cache_leaves = 3;
/* RDTSC can be speculated around */
clear_bit(X86_FEATURE_SYNC_RDTSC, &c->x86_capability);