[PATCH v2] x86, amd: Get multi-node CPU info from NodeId MSR instead of PCI config space

[Andreas Herrmann <herrmann.der.user@googlemail.com>]

Use NodeId MSR to get NodeId and number of nodes per processor.

Signed-off-by: Andreas Herrmann <andreas.herrmann3@amd.com>
---
 arch/x86/include/asm/cpufeature.h |    1 +
 arch/x86/include/asm/msr-index.h  |    1 +
 arch/x86/kernel/cpu/amd.c         |   53 ++++++++++--------------------------
 3 files changed, 17 insertions(+), 38 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 613700f..637e1ec 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -153,6 +153,7 @@
 #define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
 #define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+#define X86_FEATURE_NODEID_MSR	(6*32+19) /* NodeId MSR */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4ffe09b..9d976a7 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -123,6 +123,7 @@
 #define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
+#define MSR_FAM10H_NODE_ID		0xc001100c
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7128b37..5dcd638 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -254,59 +254,36 @@ static int __cpuinit nearby_node(int apicid)
 
 /*
  * Fixup core topology information for AMD multi-node processors.
- * Assumption 1: Number of cores in each internal node is the same.
- * Assumption 2: Mixed systems with both single-node and dual-node
- *               processors are not supported.
+ * Assumption: Number of cores in each internal node is the same.
  */
 #ifdef CONFIG_X86_HT
 static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_PCI
-	u32 t, cpn;
-	u8 n, n_id;
+	unsigned long long value;
+	u32 nodes, cores_per_node;
 	int cpu = smp_processor_id();
 
+	if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
+		return;
+
 	/* fixup topology information only once for a core */
 	if (cpu_has(c, X86_FEATURE_AMD_DCM))
 		return;
 
-	/* check for multi-node processor on boot cpu */
-	t = read_pci_config(0, 24, 3, 0xe8);
-	if (!(t & (1 << 29)))
+	rdmsrl(MSR_FAM10H_NODE_ID, value);
+
+	nodes = ((value >> 3) & 7) + 1;
+	if (nodes == 1)
 		return;
 
 	set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+	cores_per_node = c->x86_max_cores / nodes;
 
-	/* cores per node: each internal node has half the number of cores */
-	cpn = c->x86_max_cores >> 1;
+	/* store NodeID, use llc_shared_map to store sibling info */
+	per_cpu(cpu_llc_id, cpu) = value & 7;
 
-	/* even-numbered NB_id of this dual-node processor */
-	n = c->phys_proc_id << 1;
-
-	/*
-	 * determine internal node id and assign cores fifty-fifty to
-	 * each node of the dual-node processor
-	 */
-	t = read_pci_config(0, 24 + n, 3, 0xe8);
-	n = (t>>30) & 0x3;
-	if (n == 0) {
-		if (c->cpu_core_id < cpn)
-			n_id = 0;
-		else
-			n_id = 1;
-	} else {
-		if (c->cpu_core_id < cpn)
-			n_id = 1;
-		else
-			n_id = 0;
-	}
-
-	/* compute entire NodeID, use llc_shared_map to store sibling info */
-	per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id;
-
-	/* fixup core id to be in range from 0 to cpn */
-	c->cpu_core_id = c->cpu_core_id % cpn;
-#endif
+	/* fixup core id to be in range from 0 to (cores_per_node - 1) */
+	c->cpu_core_id = c->cpu_core_id % cores_per_node;
 }
 #endif
 
-- 
1.6.5.3