[PATCH v2 2/2] x86/cacheinfo: Properly parse CPUID(0x80000006) L2/L3 associativity

[Ahmed S. Darwish]

Complete the AMD CPUID(4) emulation logic, which uses CPUID(0x80000006)
for L2/L3 cache info and an assocs[] associativity mapping array, by
adding entries for 3-way caches and 6-way caches.

Properly handle the case where CPUID(0x80000006) returns an L2/L3
associativity of 9.  This is not real associativity, but a marker to
indicate that the respective L2/L3 cache information should be retrieved
from CPUID(0x8000001d) instead.  If such a marker is encountered, return
early from legacy_amd_cpuid4(), thus effectively emulating an "invalid
index" CPUID(4) response with a cache type of zero.

When checking if CPUID(0x80000006) L2/L3 cache info output is valid, and
given the associtivity marker 9 above, do not just check if the whole
ECX/EDX register is zero.  Rather, check if the associativity is zero or
9.  An associativity of zero implies no L2/L3 cache, which make it the
more correct check anyway vs. a zero check of the whole output register.

Fixes: a326e948c538 ("x86, cacheinfo: Fixup L3 cache information for AMD multi-node processors")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Ahmed S. Darwish <darwi@xxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/cacheinfo.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index f4817cd50cfb..52727f8c0006 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -89,9 +89,13 @@ static const enum cache_type cache_type_map[] = {
 /*
  * Fallback AMD CPUID(4) emulation
  * AMD CPUs with TOPOEXT can just use CPUID(0x8000001d)
+ *
+ * @AMD_L2_L3_INVALID_ASSOC: cache info for the respective L2/L3 cache should
+ * be determined from CPUID(0x8000001d) instead of CPUID(0x80000006).
  */
 
 #define AMD_CPUID4_FULLY_ASSOCIATIVE	0xffff
+#define AMD_L2_L3_INVALID_ASSOC		0x9
 
 union l1_cache {
 	struct {
@@ -128,7 +132,9 @@ union l3_cache {
 static const unsigned short assocs[] = {
 	[1]		= 1,
 	[2]		= 2,
+	[3]		= 3,
 	[4]		= 4,
+	[5]		= 6,
 	[6]		= 8,
 	[8]		= 16,
 	[0xa]		= 32,
@@ -172,7 +178,7 @@ static void legacy_amd_cpuid4(int index, union _cpuid4_leaf_eax *eax,
 		size_in_kb	= l1->size_in_kb;
 		break;
 	case 2:
-		if (!l2.val)
+		if (!l2.assoc || l2.assoc == AMD_L2_L3_INVALID_ASSOC)
 			return;
 
 		/* Use x86_cache_size as it might have K7 errata fixes */
@@ -182,7 +188,7 @@ static void legacy_amd_cpuid4(int index, union _cpuid4_leaf_eax *eax,
 		size_in_kb	= __this_cpu_read(cpu_info.x86_cache_size);
 		break;
 	case 3:
-		if (!l3.val)
+		if (!l3.assoc || l3.assoc == AMD_L2_L3_INVALID_ASSOC)
 			return;
 
 		assoc		= assocs[l3.assoc];
-- 
2.49.0