multi-die/package support

No semantic changes.

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
 Documentation/cputopology.txt | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

Documentation/cputopology.txt +14 -13

index c6e7e9196a8b..2698da7e4f49 100644
@@ -3,76 +3,76 @@ How CPU topology info is exported via sysfs
 ===========================================
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo output of some architectures:
+to /proc/cpuinfo output of some architectures.  They reside in
+/sys/devices/system/cpu/cpuX/topology/:
 
-1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
+physical_package_id:
 
 	physical package id of cpuX. Typically corresponds to a physical
 	socket number, but the actual value is architecture and platform
 	dependent.
 
-2) /sys/devices/system/cpu/cpuX/topology/core_id:
+core_id:
 
 	the CPU core ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/book_id:
+book_id:
 
 	the book ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-4) /sys/devices/system/cpu/cpuX/topology/drawer_id:
+drawer_id:
 
 	the drawer ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-5) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	core as cpuX.
 
-6) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+thread_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	core as cpuX.
 
-7) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-8) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+core_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	physical_package_id.
 
-9) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
-10) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+book_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	book_id.
 
-11) /sys/devices/system/cpu/cpuX/topology/drawer_siblings:
+drawer_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	drawer_id.
 
-12) /sys/devices/system/cpu/cpuX/topology/drawer_siblings_list:
+drawer_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	drawer_id.

Documentation/cputopology.txt +0 -0

 they reflect the cpu and cache hierarchy.

Quoted 4 lines

+if CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively.

CONFIG_SCHED_BOOK and CONFIG_DRAWER are currently only used on s390,
where

fwiw: CONFIG_SCHED_DRAWER

From: Len Brown <[email protected]>

Some new systems have multiple software-visible die within each package. The new CPUID.1F leaf can enumerate this multi-die/package topology.

CPUID.1F a super-set of the CPUID.B "Extended Toplogy Leaf", and a common updated routine can parse either leaf.

Legacy systems without CPUID.1F, and systems without multi-die/package hardware, will see no functional change from this patch series.

Multi-die/package systems will use CPUID.B before this patch, and CPUID.1F after this patch. In the CPUID.B case, all die appear (incorrectly) to software as individual packages. In the CPUID.1F case, the package id's reflect reality, and die_id's become meaningful.

Subsequent patches in this series update the kernel to be multi-die aware. In particular, some software needs to know the difference between a die-scope MSR and a package-scope MSR.

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
  Documentation/x86/topology.txt   |  4 ++
  arch/x86/include/asm/processor.h |  4 +-
  arch/x86/kernel/cpu/topology.c   | 82 ++++++++++++++++++++++++--------
  arch/x86/kernel/smpboot.c        |  4 +-
  4 files changed, 73 insertions(+), 21 deletions(-)

Documentation/x86/topology.txt +4 -0

index 06b3cdbc4048..8107b6cfc9ea 100644
@@ -46,6 +46,10 @@ The topology of a system is described in the units of:
 
      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 +3 -1

index 33051436c864..f2856fe03715 100644
@@ -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 +63 -19

index 8f6c784141d1..6dce6ee77849 100644
@@ -15,33 +15,61 @@
  /* 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 +80,7 @@ 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.
   */

@@ -60,46 +88,62 @@ 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.
  		 */
  		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
  			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			die_level_siblings = core_level_siblings;
  			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-			break;
+		}
+		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 +2 -0

index ccd1f2a8e557..4250a87f57db 100644
@@ -393,6 +393,7 @@ 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");

@@ -404,6 +405,7 @@ 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");
  	}

Quoted 4 lines

arch/x86/kernel/smpboot.c +0 -0

@@ -461,7 +463,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
   */
  static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  {

arch/x86/kernel/smpboot.c static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) · line 469

Quoted 5 lines

arch/x86/kernel/smpboot.c +1 -1

-	if (c->>phys_proc_id == o->>phys_proc_id)
+	if (c->>cpu_die_id == o->>cpu_die_id)
  		return true;
  	return false;
  }

Shouldn't we check the unique_die_id here?
Die from different package can have the same cpu_die_id.

From: Len Brown <[email protected]>

Some new systems have multiple software-visible die within each package. The new CPUID.1F leaf can enumerate this multi-die/package topology.

CPUID.1F a super-set of the CPUID.B "Extended Toplogy Leaf", and a common updated routine can parse either leaf.

Legacy systems without CPUID.1F, and systems without multi-die/package hardware, will see no functional change from this patch series.

Multi-die/package systems will use CPUID.B before this patch, and CPUID.1F after this patch. In the CPUID.B case, all die appear (incorrectly) to software as individual packages. In the CPUID.1F case, the package id's reflect reality, and die_id's become meaningful.

Subsequent patches in this series update the kernel to be multi-die aware. In particular, some software needs to know the difference between a die-scope MSR and a package-scope MSR.

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
  Documentation/x86/topology.txt   |  4 ++
  arch/x86/include/asm/processor.h |  4 +-
  arch/x86/kernel/cpu/topology.c   | 82 ++++++++++++++++++++++++--------
  arch/x86/kernel/smpboot.c        |  4 +-
  4 files changed, 73 insertions(+), 21 deletions(-)

Documentation/x86/topology.txt +4 -0

index 06b3cdbc4048..8107b6cfc9ea 100644
@@ -46,6 +46,10 @@ The topology of a system is described in the units of:
 
      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 +3 -1

index 33051436c864..f2856fe03715 100644
@@ -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 +0 -0

index 8f6c784141d1..6dce6ee77849 100644

arch/x86/kernel/cpu/topology.c +61 -18

  #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 +80,7 @@ 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.
   */

@@ -60,46 +88,62 @@ 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.
  		 */
  		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
  			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			die_level_siblings = core_level_siblings;
  			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-			break;
+		}
+		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 +3 -1

index ccd1f2a8e557..4250a87f57db 100644
@@ -393,6 +393,7 @@ 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");

@@ -404,6 +405,7 @@ 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");
  	}

@@ -461,7 +463,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
   */
  static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  {
-	if (c->phys_proc_id == o->phys_proc_id)
+	if (c->cpu_die_id == o->cpu_die_id)
  		return true;
  	return false;
  }

arch/x86/kernel/cpu/topology.c line 22

Quoted 6 lines

arch/x86/kernel/cpu/topology.c +2 -1

-/* 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

This patch set is going to export die topology via sysfs while the extended topology sub-leaf type could be one of followings:
SMT/Core/Module/Tile/Die according to CPUID.1F from SDM.

Why not choose to export module/tile topology as well?

From: Len Brown <[email protected]>

Some new systems have multiple software-visible die within each package. The new CPUID.1F leaf can enumerate this multi-die/package topology.

CPUID.1F a super-set of the CPUID.B "Extended Toplogy Leaf", and a common updated routine can parse either leaf.

Legacy systems without CPUID.1F, and systems without multi-die/package hardware, will see no functional change from this patch series.

Multi-die/package systems will use CPUID.B before this patch, and CPUID.1F after this patch. In the CPUID.B case, all die appear (incorrectly) to software as individual packages. In the CPUID.1F case, the package id's reflect reality, and die_id's become meaningful.

Subsequent patches in this series update the kernel to be multi-die aware. In particular, some software needs to know the difference between a die-scope MSR and a package-scope MSR.

arch/x86/kernel/cpu/topology.c +8 -0

+/*
+ * Check if given CPUID extended toplogy "leaf" is implemented
+ */
+static int check_extended_topology_leaf(int leaf)
+{
 	unsigned int eax, ebx, ecx, edx;
 
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
 		return -1;
 

arch/x86/kernel/cpu/topology.c +14 -0

+	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 +80,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
 }
 
 /*
+ * Check for extended topology enumeration cpuid leaf, and if it
  * exists, use it for populating initial_apicid and cpu topology
  * detection.
  */

arch/x86/kernel/cpu/topology.c +6 -0

 		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
+	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(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
 		 * Check for the Core type in the implemented sub leaves.
 		 */
 		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
 			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			die_level_siblings = core_level_siblings;

arch/x86/kernel/cpu/topology.c +10 -0

 	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_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;
 }
 

It would've been nice to have the CPUID instruction 1F leaf reference 3B-3.9 in the SDM, and maybe mention this here too.

Also, figure 8-6 uses Q,R ID, without prior mention.

You haven't explained, and I can't readily find it in the SDM either, how these topology bits relate to caches and interconnects.

Will these die thingies share LLC, or will LLC be per die. Will NUMA span dies or not.

Thanks for the comments, Peter. I'll update the patch to address the syntax points. (Maybe checkpatch.pl should be updated to reflect your preferences?).

About macros vs C. I agree with your preference.
I used macros to be consistent with the existing code, and to be as backport friendly as possible.
(a number of distros need to pull these patches into their supported kernels) Sure, I'm willing to write in a cosmetic-only patch, after the functional changes are upstream.

Quoted 2 lines

It would've been nice to have the CPUID instruction 1F leaf reference 3B-3.9 in the SDM, and maybe mention this here too.

I didn't mention SDM sections because they change -- leaving stale pointers in our commit messages. The SDM is re-published 4 times per year.

Quoted 5 lines

You haven't explained, and I can't readily find it in the SDM either, how these topology bits relate to caches and interconnects.

Will these die thingies share LLC, or will LLC be per die. Will NUMA span dies or not.

Excellent question.
Cache enumeration in Leaf-4 is totally unchanged.
ACPI NUMA tables are totally unchanged.

From a scheduler point of view, imagine that a SKX system with 4 die in 4 packages was mechanically re-designed so that those 4 die resided in 2 double-sized packages.

They may have tweaked the links between the die, but logically it is identical and compatible, and the legacy kernel will function properly.

So the effect of Leaf B,1F is that it defines the scope of MSRs. eg. what processors does a die-scope MSR cover. That is why the rest of the patch is about sysfs topology, and about package MSR scope.

Yes, there will be more exotic MSR situations in future products -- the first ones are pretty simple -- something called a package-scope-MSR in the SDM today becomes a die-scope-MSR in this generation on a multi-die/package system.

It also reflects how many packages appear in sysfs, and this can effect licensing of some kinds of software.

Quoted 6 lines

Quoted 2 lines

It would've been nice to have the CPUID instruction 1F leaf reference 3B-3.9 in the SDM, and maybe mention this here too.

I didn't mention SDM sections because they change -- leaving stale pointers in our commit messages. The SDM is re-published 4 times per year.

Yah, I know. Which is why I keep all SDMs. So if you say, book 3 section 8 of Jul'17, I can find it :-)

Quoted 2 lines

Cache enumeration in Leaf-4 is totally unchanged.
ACPI NUMA tables are totally unchanged.

Sure; and yet Sub-NUMA-Clustering broke stuff in interesting ways. I'm trying to get a feel for how these levels will interact with all that.

Before that SNC stuff, caches had never spanned NODEs (and I still think that is 'creative' at best).

Quoted 7 lines

From a scheduler point of view, imagine that a SKX system with 4 die in 4 packages was mechanically re-designed so that those 4 die resided in 2 double-sized packages.

They may have tweaked the links between the die, but logically it is identical and compatible, and the legacy kernel will function properly.

This example has LLC in die and yes that works.

But I can imagine things like L2 in tile and L3 across tiles but within DIE and then it _might_ make sense to still consider the tile for scheduling.

Another option is having the LLC off die; also not unheard of.

And then there's many creative and slightly crazy ways this can all be combined :/

Quoted 8 lines

So the effect of Leaf B,1F is that it defines the scope of MSRs. eg. what processors does a die-scope MSR cover. That is why the rest of the patch is about sysfs topology, and about package MSR scope.

Yes, there will be more exotic MSR situations in future products -- the first ones are pretty simple -- something called a package-scope-MSR in the SDM today becomes a die-scope-MSR in this generation on a multi-die/package system.

Yes :-(

Quoted 2 lines

It also reflects how many packages appear in sysfs, and this can effect licensing of some kinds of software.

That's just plain insanity and we should not let that affect our sysfs interfaces.

The SDM is like software -- usually (but not always) you are better off with the latest version:-)

arch/x86/kernel/smpboot.c +2 -0

index ccd1f2a8e557..4250a87f57db 100644
@@ -393,6 +393,7 @@ 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");

@@ -404,6 +405,7 @@ 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");
 	}

Le 19/02/2019 à 04:40, Len Brown a écrit :

Quoted 21 lines

arch/x86/kernel/smpboot.c +2 -0

index ccd1f2a8e557..4250a87f57db 100644
@@ -393,6 +393,7 @@ 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");

@@ -404,6 +405,7 @@ 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");
  	}

arch/x86/kernel/smpboot.c static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) · line 469

Quoted 8 lines

arch/x86/kernel/smpboot.c +1 -1

@@ -461,7 +463,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
   */
  static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  {
-	if (c->phys_proc_id == o->phys_proc_id)
+	if (c->cpu_die_id == o->cpu_die_id)
  		return true;
  	return false;
  }

Hello Len,

I am testing your patches in a VM with CPUID.1f QEMU patches (author Like Xu is CC'ed), booted to get 2 packages with 1 NUMA node each and 2 dies each:

-smp cpus=16,threads=2,cores=2,dies=2,sockets=2 -numa node,cpus=0-7,nodeid=0 -numa node,cpus=8-15,nodeid=1

sysfs files expose wrong information:
core_siblings contains threads of the local die AND of die with same number in other processors, eg cpu 0-3 and 8-11 instead of 0-3 only.

The issue is that you seem to assume that die ids will always be unique across multiple packages.

Is this a valid assumption? If so, QEMU patches should be fixed.
If not, I fixed the issue by changing match_die() to check both phys_proc_id and cpu_die_id:

static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)

{
	if (c->phys_proc_id == o->phys_proc_id && c->cpu_die_id == o->cpu_die_id)
  		return true;
	return false;
}

Thanks
Brice

arch/x86/kernel/smpboot.c +1 -0

index ccd1f2a8e557..4250a87f57db 100644
@@ -393,6 +393,7 @@ 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"); @@ -404,6 +405,7 @@ static 

bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)

arch/x86/kernel/smpboot.c +1 -0

 		}
 
 	} 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");
 	}

From: Len Brown <[email protected]>

like core_siblings, except it shows which die are in the same package.

This is needed for lscpu(1) to correctly display die topology.

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
  Documentation/cputopology.txt   | 10 ++++++++++
  arch/x86/include/asm/smp.h      |  1 +
  arch/x86/include/asm/topology.h |  1 +
  arch/x86/kernel/smpboot.c       | 20 ++++++++++++++++++++
  arch/x86/xen/smp_pv.c           |  1 +
  drivers/base/topology.c         |  6 ++++++
  include/linux/topology.h        |  3 +++
  7 files changed, 42 insertions(+)

Documentation/cputopology.txt +10 -0

index 287213b4517b..7dd2ae3df233 100644
@@ -56,6 +56,16 @@ core_siblings_list:
  	human-readable list of cpuX's hardware threads within the same
  	die_id.
 
+die_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	physical_package_id.
+
+die_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	physical_package_id.
+
  book_siblings:
 
  	internal kernel map of cpuX's hardware threads within the same

arch/x86/include/asm/smp.h +1 -0

index 2e95b6c1bca3..39266d193597 100644
@@ -23,6 +23,7 @@ extern unsigned int num_processors;
 
  DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
  DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
  /* cpus sharing the last level cache: */
  DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
  DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);

arch/x86/include/asm/topology.h +0 -0

index 281be6bbc80d..a52a572147ba 100644

arch/x86/include/asm/topology.h +0 -0

  #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 

arch/x86/kernel/smpboot.c +20 -0

index 4250a87f57db..42d37e4a1918 100644
@@ -90,6 +90,10 @@ EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
  DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
  EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
+/* representing HT and core and die siblings of each logical CPU */
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
+EXPORT_PER_CPU_SYMBOL(cpu_die_map);
+
  DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
  /* Per CPU bogomips and other parameters */

@@ -461,6 +465,12 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
   * multicore group inside a NUMA node.  If this happens, we will
   * discard the MC level of the topology later.
   */
+static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if (c->phys_proc_id == o->phys_proc_id)
+		return true;
+	return false;
+}
  static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  {
  	if (c->cpu_die_id == o->cpu_die_id)

@@ -530,6 +540,7 @@ void set_cpu_sibling_map(int cpu)
  		cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu));
  		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
  		cpumask_set_cpu(cpu, topology_core_cpumask(cpu));
+		cpumask_set_cpu(cpu, topology_die_cpumask(cpu));
  		c->booted_cores = 1;
  		return;
  	}

@@ -576,8 +587,12 @@ void set_cpu_sibling_map(int cpu)
  			} else if (i != cpu && !c->booted_cores)
  				c->booted_cores = cpu_data(i).booted_cores;
  		}
+
  		if (match_die(c, o) && !topology_same_node(c, o))
  			x86_has_numa_in_package = true;
+
+		if ((i == cpu) || (has_mp && match_pkg(c, o)))
+			link_mask(topology_die_cpumask, cpu, i);
  	}
 
  	threads = cpumask_weight(topology_sibling_cpumask(cpu));

@@ -1173,6 +1188,7 @@ static __init void disable_smp(void)
  		physid_set_mask_of_physid(0, &phys_cpu_present_map);
  	cpumask_set_cpu(0, topology_sibling_cpumask(0));
  	cpumask_set_cpu(0, topology_core_cpumask(0));
+	cpumask_set_cpu(0, topology_die_cpumask(0));
  }
 
  /*

@@ -1268,6 +1284,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
  	for_each_possible_cpu(i) {
  		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
  		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
  		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
  	}
 

@@ -1488,6 +1505,8 @@ static void remove_siblinginfo(int cpu)
  			cpu_data(sibling).booted_cores--;
  	}
 
+	for_each_cpu(sibling, topology_die_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
  	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
  		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
  	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))

@@ -1495,6 +1514,7 @@ static void remove_siblinginfo(int cpu)
  	cpumask_clear(cpu_llc_shared_mask(cpu));
  	cpumask_clear(topology_sibling_cpumask(cpu));
  	cpumask_clear(topology_core_cpumask(cpu));
+	cpumask_clear(topology_die_cpumask(cpu));
  	c->cpu_core_id = 0;
  	c->booted_cores = 0;
  	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);

arch/x86/xen/smp_pv.c +1 -0

index 145506f9fdbe..ac13b0be8448 100644
@@ -251,6 +251,7 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
  	for_each_possible_cpu(i) {
  		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
  		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_die_map, i), GFP_KERNEL);
  		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
  	}
  	set_cpu_sibling_map(0);

drivers/base/topology.c +6 -0

index 50352cf96f85..5b1317ae3262 100644
@@ -57,6 +57,10 @@ define_siblings_show_func(core_siblings, core_cpumask);
  static DEVICE_ATTR_RO(core_siblings);
  static DEVICE_ATTR_RO(core_siblings_list);
 
+define_siblings_show_func(die_siblings, die_cpumask);
+static DEVICE_ATTR_RO(die_siblings);
+static DEVICE_ATTR_RO(die_siblings_list);
+
  #ifdef CONFIG_SCHED_BOOK
  define_id_show_func(book_id);
  static DEVICE_ATTR_RO(book_id);

@@ -81,6 +85,8 @@ static struct attribute *default_attrs[] = {
  	&dev_attr_thread_siblings_list.attr,
  	&dev_attr_core_siblings.attr,
  	&dev_attr_core_siblings_list.attr,
+	&dev_attr_die_siblings.attr,
+	&dev_attr_die_siblings_list.attr,
  #ifdef CONFIG_SCHED_BOOK
  	&dev_attr_book_id.attr,
  	&dev_attr_book_siblings.attr,

include/linux/topology.h +3 -0

index 5cc8595dd0e4..47a3e3c08036 100644
@@ -196,6 +196,9 @@ static inline int cpu_to_mem(int cpu)
  #ifndef topology_core_cpumask
  #define topology_core_cpumask(cpu)		cpumask_of(cpu)
  #endif
+#ifndef topology_die_cpumask
+#define topology_die_cpumask(cpu)		cpumask_of(cpu)
+#endif
 
  #ifdef CONFIG_SCHED_SMT
  static inline const struct cpumask *cpu_smt_mask(int cpu)

Quoted 21 lines

(quoted diff) +0 -0

b/Documentation/cputopology.txt index 287213b4517b..7dd2ae3df233 100644

Documentation/cputopology.txt +10 -0

@@ -56,6 +56,16 @@ core_siblings_list:
  	human-readable list of cpuX's hardware threads within the same
  	die_id.
 
+die_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	physical_package_id.
+
+die_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	physical_package_id.
+
  book_siblings:
 

Documentation/cputopology.txt core_siblings_list: · line 71

Quoted 1 line

Documentation/cputopology.txt +0 -0

  	internal kernel map of cpuX's hardware threads within the same diff 

Could you please update the document regarding to topology_die_cpumask and topology_core_cpumask in Documentation/x86/topology.txt

Thanks for the comments, Kan,

Quoted 21 lines

Quoted 21 lines

(quoted diff) +0 -0

b/Documentation/cputopology.txt index 287213b4517b..7dd2ae3df233 100644

Documentation/cputopology.txt +10 -0

@@ -56,6 +56,16 @@ core_siblings_list:
   	human-readable list of cpuX's hardware threads within the same
   	die_id.
 
+die_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	physical_package_id.
+
+die_siblings_list:
+
+	human-readable list of cpuX's hardware threads within the same
+	physical_package_id.
+
   book_siblings:
 

Quoted 3 lines

Documentation/cputopology.txt core_siblings_list: · line 71

Quoted 1 line

Documentation/cputopology.txt +0 -0

   	internal kernel map of cpuX's hardware threads within the same diff

Could you please update the document regarding to topology_die_cpumask and topology_core_cpumask in Documentation/x86/topology.txt

I agree that the top part of this file, as updated above, should document the external sysfs interface...

I'm less excited about the center of the file trying to document the internal implementation -- as the source code is actually more clear than the document, but here is an update, consistent with the existing file. Let me know if it does not fully address your comment.

Thanks,

(quoted diff) +0 -2

-Len
---

Documentation/cputopology.txt +6 -4

index 7dd2ae3..f39c759 100644
@@ -102,6 +102,7 @@ these macros in include/asm-XXX/topology.h::
         #define topology_drawer_id(cpu)
         #define topology_sibling_cpumask(cpu)
         #define topology_core_cpumask(cpu)
+       #define topology_die_cpumask(cpu)
         #define topology_book_cpumask(cpu)
         #define topology_drawer_cpumask(cpu)
 

@@ -114,10 +115,11 @@ To be consistent on all architectures, include/linux/topology.h
  provides default definitions for any of the above macros that are
  not defined by include/asm-XXX/topology.h:
 
-1) physical_package_id: -1
-2) core_id: 0
-3) sibling_cpumask: just the given CPU
-4) core_cpumask: just the given CPU
+1) topology_physical_package_id: -1
+2) topology_core_id: 0
+3) topology_sibling_cpumask: just the given CPU
+4) topology_core_cpumask: just the given CPU
+5) topology_die_cpumask: just the given CPU
 
  For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
  default definitions for topology_book_id() and topology_book_cpumask().

Besides the generic document, I think we should update x86 document as well, which is in Documentation/x86/topology.txt.

The definition of topology_core_cpumask has to be changed to per die, right?

From: Len Brown <[email protected]>

like core_siblings, except it shows which die are in the same package.

This is needed for lscpu(1) to correctly display die topology.

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
 Documentation/cputopology.txt   | 10 ++++++++++
 arch/x86/include/asm/smp.h      |  1 +
 arch/x86/include/asm/topology.h |  1 +
 arch/x86/kernel/smpboot.c       | 20 ++++++++++++++++++++
 arch/x86/xen/smp_pv.c           |  1 +
 drivers/base/topology.c         |  6 ++++++
 include/linux/topology.h        |  3 +++
 7 files changed, 42 insertions(+)

Documentation/cputopology.txt +0 -0

index 287213b4517b..7dd2ae3df233 100644
@@ -56,6 +56,16 @@ core_siblings_list:
 	human-readable list of cpuX's hardware threads within the same
 	die_id.
 

Patches #4 and #5 are changing the meaning the core_siblings (in the past, it always returned all threads in the entire package). All existing user-space tools will see each die as a separate package until they are updated to read die_siblings too. It only matters for multi-die CPUs when running a recent kernel with an old userspace tool, but it may still be consider as a sysfs ABI change.

Worse, things will break again if you ever add tile_siblings for CPUID.1f "Tiles". User-space will suddenly see 2 dies of 2 cores instead 1 die of 2 tiles of 2 cores.

I understand that this isn't easy to fix. But I want to make sure people are aware of the meaning of this change.

The proper way to avoid this is to stop having file foo_siblings refer to "the container of foo" instead of "foo itself" (because that container changes when you add intermediate levels). Rename sysfs files like below, and you don't get any breakage anymore when adding intermediate levels:

thread_siblings -> core_threads (can we do sysfs alias or symlink to keep the old name?)

core_siblings -> die_threads

die_siblings -> package_threads (needs an alias too)

The documentation would also be much easier to read since "die_threads" is obviously "human-readable list of cpuX's hardware threads within the same die_id". And no need to modify the doc anymore when adding levels :)

Here is my list of applications that care about the new CPUID leaf and the concepts of packages and die:

cpuid
lscpu
x86_energy_perf_policy
turbostat

From: Zhang Rui <[email protected]>

Simplify how the code to discover a package is called. Rename find_package_by_id() to rapl_find_package()

No functional change.

Signed-off-by Zhang Rui <[email protected]>

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
 drivers/powercap/intel_rapl.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

drivers/powercap/intel_rapl.c +9 -10

index 6cdb2c14eee4..6057d9695fed 100644
@@ -264,8 +264,9 @@ static struct powercap_control_type *control_type; /* PowerCap Controller */
 static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */
 
 /* caller to ensure CPU hotplug lock is held */
-static struct rapl_package *find_package_by_id(int id)
+static struct rapl_package *rapl_find_package(int cpu)
 {
+       int id = topology_physical_package_id(cpu);
        struct rapl_package *rp;
 
        list_for_each_entry(rp, &rapl_packages, plist) {

@@ -1298,7 +1299,7 @@ static int __init rapl_register_psys(void)
        rd->rpl[0].name = pl1_name;
        rd->rpl[1].prim_id = PL2_ENABLE;
        rd->rpl[1].name = pl2_name;
-       rd->rp = find_package_by_id(0);
+       rd->rp = rapl_find_package(0);
 
        power_zone = powercap_register_zone(&rd->power_zone, control_type,
                                            "psys", NULL,

@@ -1454,8 +1455,9 @@ static void rapl_remove_package(struct rapl_package *rp)
 }
 
 /* called from CPU hotplug notifier, hotplug lock held */
-static struct rapl_package *rapl_add_package(int cpu, int pkgid)
+static struct rapl_package *rapl_add_package(int cpu)
 {
+       int id = topology_physical_package_id(cpu);
        struct rapl_package *rp;
        int ret;
 

@@ -1464,7 +1466,7 @@ static struct rapl_package *rapl_add_package(int cpu, int pkgid)
                return ERR_PTR(-ENOMEM);
 
        /* add the new package to the list */
-       rp->id = pkgid;
+       rp->id = id;
        rp->lead_cpu = cpu;
 
        /* check if the package contains valid domains */

@@ -1495,12 +1497,11 @@ static struct rapl_package *rapl_add_package(int cpu, int pkgid)
  */
 static int rapl_cpu_online(unsigned int cpu)
 {
-       int pkgid = topology_physical_package_id(cpu);
        struct rapl_package *rp;
 
-       rp = find_package_by_id(pkgid);
+       rp = rapl_find_package(cpu);
        if (!rp) {
-               rp = rapl_add_package(cpu, pkgid);
+               rp = rapl_add_package(cpu);
                if (IS_ERR(rp))
                        return PTR_ERR(rp);
        }

@@ -1510,11 +1511,10 @@ static int rapl_cpu_online(unsigned int cpu)
 
 static int rapl_cpu_down_prep(unsigned int cpu)
 {
-       int pkgid = topology_physical_package_id(cpu);
        struct rapl_package *rp;
        int lead_cpu;
 
-       rp = find_package_by_id(pkgid);
+       rp = rapl_find_package(cpu);
        if (!rp)
                return 0;
 
--

2.18.0-rc0

From: Zhang Rui <[email protected]>

On the new dual-die/package systems, the RAPL MSR becomes die-scope. Thus instead of one powercap device per physical package, now there should be one powercap device for each unique die on these systems.

This patch introduces intel_rapl driver support for new dual-die/package systems.

On the hardwares that do not have multi-die, topology_unique_die_id() equals topology_physical_package_id(), thus there is no functional change.

Signed-off-by Zhang Rui <[email protected]>

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
 drivers/powercap/intel_rapl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/powercap/intel_rapl.c +2 -3

index 6057d9695fed..e004707283da 100644
@@ -266,7 +266,7 @@ static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */
 /* caller to ensure CPU hotplug lock is held */
 static struct rapl_package *rapl_find_package(int cpu)
 {
-       int id = topology_physical_package_id(cpu);
+       int id = topology_unique_die_id(cpu);
        struct rapl_package *rp;
 
        list_for_each_entry(rp, &rapl_packages, plist) {

@@ -1457,7 +1457,7 @@ static void rapl_remove_package(struct rapl_package *rp)
 /* called from CPU hotplug notifier, hotplug lock held */
 static struct rapl_package *rapl_add_package(int cpu)
 {
-       int id = topology_physical_package_id(cpu);
+       int id = topology_unique_die_id(cpu);
        struct rapl_package *rp;
        int ret;
 
--

2.18.0-rc0

From: Zhang Rui <[email protected]>

On the new dual-die/package systems, the RAPL MSR becomes die-scope. Thus instead of one powercap device per physical package, now there should be one powercap device for each unique die on these systems.

This patch introduces intel_rapl driver support for new dual-die/package systems.

On the hardwares that do not have multi-die, topology_unique_die_id() equals topology_physical_package_id(), thus there is no functional change.

Signed-off-by Zhang Rui <[email protected]>

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
 drivers/powercap/intel_rapl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/powercap/intel_rapl.c +1 -1

index 6057d9695fed..e004707283da 100644
@@ -266,7 +266,7 @@ static struct rapl_domain *platform_rapl_domain; /* Platform (PSys) domain */
 /* caller to ensure CPU hotplug lock is held */
 static struct rapl_package *rapl_find_package(int cpu)
 {
-	int id = topology_physical_package_id(cpu);
+	int id = topology_unique_die_id(cpu);
 	struct rapl_package *rp;
 
 	list_for_each_entry(rp, &rapl_packages, plist) {

drivers/powercap/intel_rapl.c static void rapl_remove_package(struct rapl_package *rp) · line 1462

Quoted 9 lines

      list_for_each_entry(rp, &rapl_packages, plist) {

drivers/powercap/intel_rapl.c +1 -1

@@ -1457,7 +1457,7 @@ static void rapl_remove_package(struct rapl_package *rp)
 /* called from CPU hotplug notifier, hotplug lock held */
 static struct rapl_package *rapl_add_package(int cpu)
 {
-     int id = topology_physical_package_id(cpu);
+     int id = topology_unique_die_id(cpu);
      struct rapl_package *rp;
      int ret;

And now your new function names are misnomers.

Quoted 11 lines · Peter Zijlstra

drivers/powercap/intel_rapl.c static void rapl_remove_package(struct rapl_package *rp) · line 1462

Quoted 9 lines

      list_for_each_entry(rp, &rapl_packages, plist) {

drivers/powercap/intel_rapl.c +1 -1

@@ -1457,7 +1457,7 @@ static void rapl_remove_package(struct rapl_package *rp)
 /* called from CPU hotplug notifier, hotplug lock held */
 static struct rapl_package *rapl_add_package(int cpu)
 {
-     int id = topology_physical_package_id(cpu);
+     int id = topology_unique_die_id(cpu);
      struct rapl_package *rp;
      int ret;

And now your new function names are misnomers.

That is fair.

Seems that a subsequent re-name-only patch is appropriate.

Quoted 18 lines · Len Brown

Quoted 13 lines · Peter Zijlstra

drivers/powercap/intel_rapl.c static void rapl_remove_package(struct · line 1463

Quoted 12 lines

      list_for_each_entry(rp, &rapl_packages, plist) {

drivers/powercap/intel_rapl.c +1 -1

@@ -1457,7 +1457,7 @@ static void rapl_remove_package(struct
 rapl_package *rp)
  /* called from CPU hotplug notifier, hotplug lock held */
  static struct rapl_package *rapl_add_package(int cpu)
  {
-     int id = topology_physical_package_id(cpu);
+     int id = topology_unique_die_id(cpu);
       struct rapl_package *rp;
       int ret;

And now your new function names are misnomers.

Quoted 3 lines

That is fair.

Seems that a subsequent re-name-only patch is appropriate.

I'm not sure that re-naming these functions is a good idea.

Fundamentally, the reason stems from the SDM being in-consistent. And the reason that the SDM is inconsistent is for compatibility.

ie. the PACKAGE MSRs in the SDM are still called PACKAGE MSRs, even though on a multi-die system, they are DIE scoped. There is no plan to re-name all of those MSRs.

And so what do you call a routine that parses a PACKAGE_RAPL domain? Well, it is still called PACKAGE MSR, even though the code is smart enough
to know that on a multi-die system, its scope is die-scoped, not package-scoped.

And yes, just to confuse things, there WILL be PACKAGE scope MSRs in the future that span multiple die on multi-die systems.  No, it will not
be a surprise when they appear -- by definition, they will be different
and incompatible with previous PACKAGE MSRs.  We will need to update some software to be smart about handling them -- no blind assumptions on using the word "package" in this context.

So unless Rui disagrees, I'm inclined to leave these routine names alone.

thanks,
Len Brown, Intel Open Source Technology Center

From: Zhang Rui <[email protected]>

The RAPL domain "name" attribute contains "Package-N", which is ambiguous on multi-die per-package systems.

Update the name to "package-X-die-Y" on those systems.

No change on systems without multi-die.

Driver debug messages are also updated.

Signed-off-by Zhang Rui <[email protected]>

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
 drivers/powercap/intel_rapl.c | 57 ++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 25 deletions(-)

drivers/powercap/intel_rapl.c +32 -26

index e004707283da..c990eee45239 100644
@@ -178,12 +178,15 @@ struct rapl_domain {
 #define power_zone_to_rapl_domain(_zone) \
        container_of(_zone, struct rapl_domain, power_zone)
 
+/* maximum rapl package domain name: package-%d-die-%d */
+#define PACKAGE_DOMAIN_NAME_LENGTH 30
 
-/* Each physical package contains multiple domains, these are the common
+
+/* Each rapl package contains multiple domains, these are the common
  * data across RAPL domains within a package.
  */
 struct rapl_package {
-       unsigned int id; /* physical package/socket id */
+       unsigned int id; /* logical die id, equals physical 1-die systems */
        unsigned int nr_domains;
        unsigned long domain_map; /* bit map of active domains */
        unsigned int power_unit;

@@ -198,6 +201,7 @@ struct rapl_package {
        int lead_cpu; /* one active cpu per package for access */
        /* Track active cpus */
        struct cpumask cpumask;
+       char name[PACKAGE_DOMAIN_NAME_LENGTH];
 };
 
 struct rapl_defaults {

@@ -926,8 +930,8 @@ static int rapl_check_unit_core(struct rapl_package *rp, int cpu)
        value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
        rp->time_unit = 1000000 / (1 << value);
 
-       pr_debug("Core CPU package %d energy=%dpJ, time=%dus, power=%duW\n",
-               rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
+       pr_debug("Core CPU %s energy=%dpJ, time=%dus, power=%duW\n",
+               rp->name, rp->energy_unit, rp->time_unit, rp->power_unit);
 
        return 0;
 }

@@ -951,8 +955,8 @@ static int rapl_check_unit_atom(struct rapl_package *rp, int cpu)
        value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
        rp->time_unit = 1000000 / (1 << value);
 
-       pr_debug("Atom package %d energy=%dpJ, time=%dus, power=%duW\n",
-               rp->id, rp->energy_unit, rp->time_unit, rp->power_unit);
+       pr_debug("Atom %s energy=%dpJ, time=%dus, power=%duW\n",
+               rp->name, rp->energy_unit, rp->time_unit, rp->power_unit);
 
        return 0;
 }

@@ -1179,7 +1183,7 @@ static void rapl_update_domain_data(struct rapl_package *rp)
        u64 val;
 
        for (dmn = 0; dmn < rp->nr_domains; dmn++) {
-               pr_debug("update package %d domain %s data\n", rp->id,
+               pr_debug("update %s domain %s data\n", rp->name,
                         rp->domains[dmn].name);
                /* exclude non-raw primitives */
                for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++) {

@@ -1204,7 +1208,6 @@ static void rapl_unregister_powercap(void)
 static int rapl_package_register_powercap(struct rapl_package *rp)
 {
        struct rapl_domain *rd;
-       char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/
        struct powercap_zone *power_zone = NULL;
        int nr_pl, ret;
 

@@ -1215,20 +1218,16 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
        for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
                if (rd->id == RAPL_DOMAIN_PACKAGE) {
                        nr_pl = find_nr_power_limit(rd);
-                       pr_debug("register socket %d package domain %s\n",
-                               rp->id, rd->name);
-                       memset(dev_name, 0, sizeof(dev_name));
-                       snprintf(dev_name, sizeof(dev_name), "%s-%d",
-                               rd->name, rp->id);
+                       pr_debug("register package domain %s\n", rp->name);
                        power_zone = powercap_register_zone(&rd->power_zone,
                                                        control_type,
-                                                       dev_name, NULL,
+                                                       rp->name, NULL,
                                                        &zone_ops[rd->id],
                                                        nr_pl,
                                                        &constraint_ops);
                        if (IS_ERR(power_zone)) {
-                               pr_debug("failed to register package, %d\n",
-                                       rp->id);
+                               pr_debug("failed to register power zone %s\n",
+                                       rp->name);
                                return PTR_ERR(power_zone);
                        }
                        /* track parent zone in per package/socket data */

@@ -1254,8 +1253,8 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
                                                &constraint_ops);
 
                if (IS_ERR(power_zone)) {
-                       pr_debug("failed to register power_zone, %d:%s:%s\n",
-                               rp->id, rd->name, dev_name);
+                       pr_debug("failed to register power_zone, %s:%s\n",
+                               rp->name, rd->name);
                        ret = PTR_ERR(power_zone);
                        goto err_cleanup;
                }

@@ -1268,7 +1267,7 @@ static int rapl_package_register_powercap(struct rapl_package *rp)
         * failed after the first domain setup.
         */
        while (--rd >= rp->domains) {
-               pr_debug("unregister package %d domain %s\n", rp->id, rd->name);
+               pr_debug("unregister %s domain %s\n", rp->name, rd->name);
                powercap_unregister_zone(control_type, &rd->power_zone);
        }
 

@@ -1378,8 +1377,8 @@ static void rapl_detect_powerlimit(struct rapl_domain *rd)
        /* check if the domain is locked by BIOS, ignore if MSR doesn't exist */
        if (!rapl_read_data_raw(rd, FW_LOCK, false, &val64)) {
                if (val64) {
-                       pr_info("RAPL package %d domain %s locked by BIOS\n",
-                               rd->rp->id, rd->name);
+                       pr_info("RAPL %s domain %s locked by BIOS\n",
+                               rd->rp->name, rd->name);
                        rd->state |= DOMAIN_STATE_BIOS_LOCKED;
                }
        }

@@ -1408,10 +1407,10 @@ static int rapl_detect_domains(struct rapl_package *rp, int cpu)
        }
        rp->nr_domains = bitmap_weight(&rp->domain_map, RAPL_DOMAIN_MAX);
        if (!rp->nr_domains) {
-               pr_debug("no valid rapl domains found in package %d\n", rp->id);
+               pr_debug("no valid rapl domains found in %s\n", rp->name);
                return -ENODEV;
        }
-       pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id);
+       pr_debug("found %d domains on %s\n", rp->nr_domains, rp->name);
 
        rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain),
                        GFP_KERNEL);

@@ -1444,8 +1443,8 @@ static void rapl_remove_package(struct rapl_package *rp)
                        rd_package = rd;
                        continue;
                }
-               pr_debug("remove package, undo power limit on %d: %s\n",
-                        rp->id, rd->name);
+               pr_debug("remove package, undo power limit on %s: %s\n",
+                        rp->name, rd->name);
                powercap_unregister_zone(control_type, &rd->power_zone);
        }
        /* do parent zone last */

@@ -1459,6 +1458,7 @@ static struct rapl_package *rapl_add_package(int cpu)
 {
        int id = topology_unique_die_id(cpu);
        struct rapl_package *rp;
+       struct cpuinfo_x86 *c = &cpu_data(cpu);
        int ret;
 
        rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL);

@@ -1469,6 +1469,13 @@ static struct rapl_package *rapl_add_package(int cpu)
        rp->id = id;
        rp->lead_cpu = cpu;
 
+       if (c->x86_max_dies > 1)
+               snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH,
+                       "package-%d-die-%d", c->phys_proc_id, c->cpu_die_id);
+       else
+               snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d",
+                       c->phys_proc_id);
+
        /* check if the package contains valid domains */
        if (rapl_detect_domains(rp, cpu) ||
                rapl_defaults->check_unit(rp, cpu)) {
--

2.18.0-rc0

From: Zhang Rui <[email protected]>

This patch introduces coretemp driver support
for new dual-die/package systems.

On the new dual-die/package systems, the package temperature MSRs becomes die-scope. Thus instead of one hwmon device per physical package, now there should be one hwmon device for each die on these systems.

On the hardwares that do not have multi-die support, topology_unique_die_id() equals topology_physical_package_id(), thus the only difference is that physical package id is used as the coretemp platform device id, instead of logical package id on these systems.

Signed-off-by Zhang Rui <[email protected]>

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
  drivers/hwmon/coretemp.c | 9 +++++----
  1 file changed, 5 insertions(+), 4 deletions(-)

drivers/hwmon/coretemp.c +5 -4

index 5d34f7271e67..a0b6b2247c3a 100644
@@ -435,7 +435,7 @@ static int chk_ucode_version(unsigned int cpu)
 
  static struct platform_device *coretemp_get_pdev(unsigned int cpu)
  {
-	int pkgid = topology_logical_package_id(cpu);
+	int pkgid = topology_unique_die_id(cpu);
 
  	if (pkgid >= 0 && pkgid < max_packages)
  		return pkg_devices[pkgid];

@@ -579,7 +579,7 @@ static struct platform_driver coretemp_driver = {
 
  static struct platform_device *coretemp_device_add(unsigned int cpu)
  {
-	int err, pkgid = topology_logical_package_id(cpu);
+	int err, pkgid = topology_unique_die_id(cpu);
  	struct platform_device *pdev;
 
  	if (pkgid < 0)

@@ -703,7 +703,7 @@ static int coretemp_cpu_offline(unsigned int cpu)
  	 * the rest.
  	 */
  	if (cpumask_empty(&pd->cpumask)) {
-		pkg_devices[topology_logical_package_id(cpu)] = NULL;
+		pkg_devices[topology_unique_die_id(cpu)] = NULL;
  		platform_device_unregister(pdev);
  		return 0;
  	}

@@ -732,6 +732,7 @@ static enum cpuhp_state coretemp_hp_online;
  static int __init coretemp_init(void)
  {
  	int err;
+	struct cpuinfo_x86 *c = &cpu_data(0);
 
  	/*
  	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal

@@ -741,7 +742,7 @@ static int __init coretemp_init(void)
  	if (!x86_match_cpu(coretemp_ids))
  		return -ENODEV;
 
-	max_packages = topology_max_packages();
+	max_packages = topology_max_packages() * c->x86_max_dies;
  	pkg_devices = kcalloc(max_packages, sizeof(struct platform_device *),
  			      GFP_KERNEL);
  	if (!pkg_devices)

From: Zhang Rui <[email protected]>

This patch introduces coretemp driver support
for new dual-die/package systems.

On the new dual-die/package systems, the package temperature MSRs becomes die-scope. Thus instead of one hwmon device per physical package, now there should be one hwmon device for each die on these systems.

On the hardwares that do not have multi-die support, topology_unique_die_id() equals topology_physical_package_id(), thus the only difference is that physical package id is used as the coretemp platform device id, instead of logical package id on these systems.

Signed-off-by Zhang Rui <[email protected]>

Signed-off-by Len Brown <[email protected]>

Cc [email protected]

Cc [email protected]

Signed-off-by Len Brown <[email protected]>

---
  drivers/hwmon/coretemp.c | 9 +++++----
  1 file changed, 5 insertions(+), 4 deletions(-)

drivers/hwmon/coretemp.c +5 -4

index 5d34f7271e67..a0b6b2247c3a 100644
@@ -435,7 +435,7 @@ static int chk_ucode_version(unsigned int cpu)
 
  static struct platform_device *coretemp_get_pdev(unsigned int cpu)
  {
-	int pkgid = topology_logical_package_id(cpu);
+	int pkgid = topology_unique_die_id(cpu);
 
  	if (pkgid >= 0 && pkgid < max_packages)
  		return pkg_devices[pkgid];

@@ -579,7 +579,7 @@ static struct platform_driver coretemp_driver = {
 
  static struct platform_device *coretemp_device_add(unsigned int cpu)
  {
-	int err, pkgid = topology_logical_package_id(cpu);
+	int err, pkgid = topology_unique_die_id(cpu);
  	struct platform_device *pdev;
 
  	if (pkgid < 0)

@@ -703,7 +703,7 @@ static int coretemp_cpu_offline(unsigned int cpu)
  	 * the rest.
  	 */
  	if (cpumask_empty(&pd->cpumask)) {
-		pkg_devices[topology_logical_package_id(cpu)] = NULL;
+		pkg_devices[topology_unique_die_id(cpu)] = NULL;
  		platform_device_unregister(pdev);
  		return 0;
  	}

@@ -732,6 +732,7 @@ static enum cpuhp_state coretemp_hp_online;
  static int __init coretemp_init(void)
  {
  	int err;
+	struct cpuinfo_x86 *c = &cpu_data(0);
 
  	/*
  	 * CPUID.06H.EAX[0] indicates whether the CPU has thermal

@@ -741,7 +742,7 @@ static int __init coretemp_init(void)
  	if (!x86_match_cpu(coretemp_ids))
  		return -ENODEV;
 
-	max_packages = topology_max_packages();
+	max_packages = topology_max_packages() * c->x86_max_dies;
  	pkg_devices = kcalloc(max_packages, sizeof(struct platform_device *),
  			      GFP_KERNEL);
  	if (!pkg_devices)