x86/topology: Add CPUID.1F multi-die/package support

Some new systems have multiple software-visible die within each package.

Update Linux parsing of the Intel CPUID "Extended Topology Leaf" to handle
either CPUID.B, or the new CPUID.1F.

Add cpuinfo_x86.die_id and cpuinfo_x86.max_dies to store the result.

die_id will be non-zero only for multi-die/package systems.
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: linux-doc@vger.kernel.org
Link: https://lkml.kernel.org/r/7b23d2d26d717b8e14ba137c94b70943f1ae4b5c.1557769318.git.len.brown@intel.com

Documentation/x86/topology.rst

@@ -49,6 +49,10 @@ Package-related topology information in the kernel:
 
     The number of cores in a package. This information is retrieved via CPUID.
 
+  - cpuinfo_x86.x86_max_dies:
+
+    The number of dies in a package. This information is retrieved via CPUID.
+
   - cpuinfo_x86.phys_proc_id:
 
     The physical ID of the package. This information is retrieved via CPUID

arch/x86/include/asm/processor.h

@@ -105,7 +105,8 @@ struct cpuinfo_x86 {
 	int			x86_power;
 	unsigned long		loops_per_jiffy;
 	/* cpuid returned max cores value: */
-	u16			 x86_max_cores;
+	u16			x86_max_cores;
+	u16			x86_max_dies;
 	u16			apicid;
 	u16			initial_apicid;
 	u16			x86_clflush_size;
@@ -117,6 +118,7 @@ struct cpuinfo_x86 {
 	u16			logical_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
+	u16			cpu_die_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;

arch/x86/kernel/cpu/topology.c

@@ -15,33 +15,63 @@
 /* leaf 0xb SMT level */
 #define SMT_LEVEL	0
 
-/* leaf 0xb sub-leaf types */
+/* extended topology sub-leaf types */
 #define INVALID_TYPE	0
 #define SMT_TYPE	1
 #define CORE_TYPE	2
+#define DIE_TYPE	5
 
 #define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-int detect_extended_topology_early(struct cpuinfo_x86 *c)
-{
 #ifdef CONFIG_SMP
+/*
+ * Check if given CPUID extended toplogy "leaf" is implemented
+ */
+static int check_extended_topology_leaf(int leaf)
+{
 	unsigned int eax, ebx, ecx, edx;
 
-	if (c->cpuid_level < 0xb)
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
 		return -1;
 
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	return 0;
+}
+/*
+ * Return best CPUID Extended Toplogy Leaf supported
+ */
+static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
+{
+	if (c->cpuid_level >= 0x1f) {
+		if (check_extended_topology_leaf(0x1f) == 0)
+			return 0x1f;
+	}
 
-	/*
-	 * check if the cpuid leaf 0xb is actually implemented.
-	 */
-	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+	if (c->cpuid_level >= 0xb) {
+		if (check_extended_topology_leaf(0xb) == 0)
+			return 0xb;
+	}
+
+	return -1;
+}
+#endif
+
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx;
+	int leaf;
+
+	leaf = detect_extended_topology_leaf(c);
+	if (leaf < 0)
 		return -1;
 
 	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
 
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	/*
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
@@ -52,7 +82,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * Check for extended topology enumeration cpuid leaf, and if it
  * exists, use it for populating initial_apicid and cpu topology
  * detection.
  */
@@ -60,22 +90,28 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
+	unsigned int die_select_mask, die_level_siblings;
+	int leaf;
 
-	if (detect_extended_topology_early(c) < 0)
+	leaf = detect_extended_topology_leaf(c);
+	if (leaf < 0)
 		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	c->initial_apicid = edx;
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
 	do {
-		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
 		 * Check for the Core type in the implemented sub leaves.
@@ -83,23 +119,34 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
 			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
 			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-			break;
+			die_level_siblings = core_level_siblings;
+			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+		}
+		if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
+			die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 
 		sub_index++;
 	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
 
 	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
-
-	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width)
-						 & core_select_mask;
-	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+	die_select_mask = (~(-1 << die_plus_mask_width)) >>
+				core_plus_mask_width;
+
+	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
+				ht_mask_width) & core_select_mask;
+	c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
+				core_plus_mask_width) & die_select_mask;
+	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
+				die_plus_mask_width);
 	/*
 	 * Reinit the apicid, now that we have extended initial_apicid.
 	 */
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+	c->x86_max_dies = (die_level_siblings / core_level_siblings);
 #endif
 	return 0;
 }

arch/x86/kernel/smpboot.c

@@ -389,6 +389,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
+		    c->cpu_die_id == o->cpu_die_id &&
 		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
 			if (c->cpu_core_id == o->cpu_core_id)
 				return topology_sane(c, o, "smt");
@@ -400,6 +401,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
+		   c->cpu_die_id == o->cpu_die_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
 		return topology_sane(c, o, "smt");
 	}