[PATCH 5/5 Xenial SRU] x86/topology: Fix AMD core count

[tim.gardner at canonical.com]

From: Peter Zijlstra <peterz at infradead.org>

BugLink: http://bugs.launchpad.net/bugs/1570441

It turns out AMD gets x86_max_cores wrong when there are compute
units.

The issue is that Linux assumes:

	nr_logical_cpus = nr_cores * nr_siblings

But AMD reports its CU unit as 2 cores, but then sets num_smp_siblings
to 2 as well.

Boris: fixup ras/mce_amd_inj.c too, to compute the Node Base Core
properly, according to the new nomenclature.

Fixes: 1f12e32f4cd5 ("x86/topology: Create logical package id")
Reported-by: Xiong Zhou <jencce.kernel at gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz at infradead.org>
Signed-off-by: Borislav Petkov <bp at suse.de>
Cc: Andreas Herrmann <aherrmann at suse.com>
Cc: Andy Lutomirski <luto at kernel.org>
Link: http://lkml.kernel.org/r/20160317095220.GO6344@twins.programming.kicks-ass.net
Signed-off-by: Thomas Gleixner <tglx at linutronix.de>

(cherry picked from commit ee6825c80e870fff1a370c718ec77022ade0889b)
Signed-off-by: Tim Gardner <tim.gardner at canonical.com>
---
 arch/x86/include/asm/smp.h | 1 +
 arch/x86/kernel/cpu/amd.c  | 8 ++++----
 arch/x86/ras/mce_amd_inj.c | 3 ++-
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index bef4e14..f12ceef 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -167,6 +167,7 @@ static inline int wbinvd_on_all_cpus(void)
 	wbinvd();
 	return 0;
 }
+#define smp_num_siblings	1
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a8816b3..2cc4267 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -312,9 +312,9 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		node_id = ecx & 7;
 
 		/* get compute unit information */
-		smp_num_siblings = ((ebx >> 8) & 3) + 1;
+		cores_per_cu = smp_num_siblings = ((ebx >> 8) & 3) + 1;
+		c->x86_max_cores /= smp_num_siblings;
 		c->compute_unit_id = ebx & 0xff;
-		cores_per_cu += ((ebx >> 8) & 3);
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
@@ -330,8 +330,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		cores_per_node = c->x86_max_cores / nodes_per_socket;
-		cus_per_node = cores_per_node / cores_per_cu;
+		cus_per_node = c->x86_max_cores / nodes_per_socket;
+		cores_per_node = cus_per_node * cores_per_cu;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
 		per_cpu(cpu_llc_id, cpu) = node_id;
diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c
index 55d38cf..9e02dca 100644
--- a/arch/x86/ras/mce_amd_inj.c
+++ b/arch/x86/ras/mce_amd_inj.c
@@ -20,6 +20,7 @@
 #include <linux/pci.h>
 
 #include <asm/mce.h>
+#include <asm/smp.h>
 #include <asm/amd_nb.h>
 #include <asm/irq_vectors.h>
 
@@ -206,7 +207,7 @@ static u32 get_nbc_for_node(int node_id)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 	u32 cores_per_node;
 
-	cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket();
+	cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket();
 
 	return cores_per_node * node_id;
 }
-- 
1.9.1