Merge tag 'x86_cpu_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpuid updates from Borislav Petkov:
 "Only AMD-specific changes this time:

   - Save the AMD physical die ID into cpuinfo_x86.cpu_die_id and
     convert all code to use it (Yazen Ghannam)

   - Remove a dead and unused TSEG region remapping workaround on AMD
     (Arvind Sankar)"

* tag 'x86_cpu_for_v5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cpu/amd: Remove dead code for TSEG region remapping
  x86/topology: Set cpu_die_id only if DIE_TYPE found
  EDAC/mce_amd: Use struct cpuinfo_x86.cpu_die_id for AMD NodeId
  x86/CPU/AMD: Remove amd_get_nb_id()
  x86/CPU/AMD: Save AMD NodeId as cpu_die_id

Documentation/x86/topology.rst

@@ -41,6 +41,8 @@ Package
 Packages contain a number of cores plus shared resources, e.g. DRAM
 controller, shared caches etc.
 
+Modern systems may also use the term 'Die' for package.
+
 AMD nomenclature for package is 'Node'.
 
 Package-related topology information in the kernel:
@@ -53,11 +55,18 @@ Package-related topology information in the kernel:
 
     The number of dies in a package. This information is retrieved via CPUID.
 
+  - cpuinfo_x86.cpu_die_id:
+
+    The physical ID of the die. This information is retrieved via CPUID.
+
   - cpuinfo_x86.phys_proc_id:
 
     The physical ID of the package. This information is retrieved via CPUID
     and deduced from the APIC IDs of the cores in the package.
 
+    Modern systems use this value for the socket. There may be multiple
+    packages within a socket. This value may differ from cpu_die_id.
+
   - cpuinfo_x86.logical_proc_id:
 
     The logical ID of the package. As we do not trust BIOSes to enumerate the

arch/x86/events/amd/core.c

@@ -538,7 +538,7 @@ static void amd_pmu_cpu_starting(int cpu)
 	if (!x86_pmu.amd_nb_constraints)
 		return;
 
-	nb_id = amd_get_nb_id(cpu);
+	nb_id = topology_die_id(cpu);
 	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	for_each_online_cpu(i) {

arch/x86/include/asm/cacheinfo.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_CACHEINFO_H
 #define _ASM_X86_CACHEINFO_H
 
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id);
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu);
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu);
 
 #endif /* _ASM_X86_CACHEINFO_H */

arch/x86/include/asm/processor.h

@@ -813,10 +813,8 @@ extern int set_tsc_mode(unsigned int val);
 DECLARE_PER_CPU(u64, msr_misc_features_shadow);
 
 #ifdef CONFIG_CPU_SUP_AMD
-extern u16 amd_get_nb_id(int cpu);
 extern u32 amd_get_nodes_per_socket(void);
 #else
-static inline u16 amd_get_nb_id(int cpu)		{ return 0; }
 static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
 #endif
 

arch/x86/kernel/amd_nb.c

@@ -384,7 +384,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 
 int amd_get_subcaches(int cpu)
 {
-	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
+	struct pci_dev *link = node_to_amd_nb(topology_die_id(cpu))->link;
 	unsigned int mask;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
@@ -398,7 +398,7 @@ int amd_get_subcaches(int cpu)
 int amd_set_subcaches(int cpu, unsigned long mask)
 {
 	static unsigned int reset, ban;
-	struct amd_northbridge *nb = node_to_amd_nb(amd_get_nb_id(cpu));
+	struct amd_northbridge *nb = node_to_amd_nb(topology_die_id(cpu));
 	unsigned int reg;
 	int cuid;
 

arch/x86/kernel/cpu/amd.c

@@ -23,7 +23,6 @@
 
 #ifdef CONFIG_X86_64
 # include <asm/mmconfig.h>
-# include <asm/set_memory.h>
 #endif
 
 #include "cpu.h"
@@ -330,7 +329,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
  */
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u8 node_id;
 	int cpu = smp_processor_id();
 
 	/* get information required for multi-node processors */
@@ -340,7 +338,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
-		node_id  = ecx & 0xff;
+		c->cpu_die_id  = ecx & 0xff;
 
 		if (c->x86 == 0x15)
 			c->cu_id = ebx & 0xff;
@@ -360,15 +358,15 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		if (!err)
 			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
 
-		cacheinfo_amd_init_llc_id(c, cpu, node_id);
+		cacheinfo_amd_init_llc_id(c, cpu);
 
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		node_id = value & 7;
+		c->cpu_die_id = value & 7;
 
-		per_cpu(cpu_llc_id, cpu) = node_id;
+		per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
 	} else
 		return;
 
@@ -393,7 +391,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	/* Convert the initial APIC ID into the socket ID */
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
-	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+	per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
 }
 
 static void amd_detect_ppin(struct cpuinfo_x86 *c)
@@ -425,12 +423,6 @@ static void amd_detect_ppin(struct cpuinfo_x86 *c)
 	clear_cpu_cap(c, X86_FEATURE_AMD_PPIN);
 }
 
-u16 amd_get_nb_id(int cpu)
-{
-	return per_cpu(cpu_llc_id, cpu);
-}
-EXPORT_SYMBOL_GPL(amd_get_nb_id);
-
 u32 amd_get_nodes_per_socket(void)
 {
 	return nodes_per_socket;
@@ -516,26 +508,6 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c)
 
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
-
-#ifdef CONFIG_X86_64
-	if (c->x86 >= 0xf) {
-		unsigned long long tseg;
-
-		/*
-		 * Split up direct mapping around the TSEG SMM area.
-		 * Don't do it for gbpages because there seems very little
-		 * benefit in doing so.
-		 */
-		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
-			unsigned long pfn = tseg >> PAGE_SHIFT;
-
-			pr_debug("tseg: %010llx\n", tseg);
-			if (pfn_range_is_mapped(pfn, pfn + 1))
-				set_memory_4k((unsigned long)__va(tseg), 1);
-		}
-	}
-#endif
-
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
 
 		if (c->x86 > 0x10 ||

arch/x86/kernel/cpu/cacheinfo.c

@@ -580,7 +580,7 @@ static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 	if (index < 3)
 		return;
 
-	node = amd_get_nb_id(smp_processor_id());
+	node = topology_die_id(smp_processor_id());
 	this_leaf->nb = node_to_amd_nb(node);
 	if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
 		amd_calc_l3_indices(this_leaf->nb);
@@ -646,7 +646,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
 	return i;
 }
 
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
 {
 	/*
 	 * We may have multiple LLCs if L3 caches exist, so check if we
@@ -657,7 +657,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 
 	if (c->x86 < 0x17) {
 		/* LLC is at the node level. */
-		per_cpu(cpu_llc_id, cpu) = node_id;
+		per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
 	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
 		 * LLC is at the core complex level.
@@ -684,7 +684,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 	}
 }
 
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu)
 {
 	/*
 	 * We may have multiple LLCs if L3 caches exist, so check if we

arch/x86/kernel/cpu/hygon.c

@@ -14,9 +14,6 @@
 #include <asm/cacheinfo.h>
 #include <asm/spec-ctrl.h>
 #include <asm/delay.h>
-#ifdef CONFIG_X86_64
-# include <asm/set_memory.h>
-#endif
 
 #include "cpu.h"
 
@@ -65,7 +62,6 @@ static void hygon_get_topology_early(struct cpuinfo_x86 *c)
  */
 static void hygon_get_topology(struct cpuinfo_x86 *c)
 {
-	u8 node_id;
 	int cpu = smp_processor_id();
 
 	/* get information required for multi-node processors */
@@ -75,7 +71,7 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
-		node_id  = ecx & 0xff;
+		c->cpu_die_id  = ecx & 0xff;
 
 		c->cpu_core_id = ebx & 0xff;
 
@@ -93,14 +89,14 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
 		/* Socket ID is ApicId[6] for these processors. */
 		c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
 
-		cacheinfo_hygon_init_llc_id(c, cpu, node_id);
+		cacheinfo_hygon_init_llc_id(c, cpu);
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		node_id = value & 7;
+		c->cpu_die_id = value & 7;
 
-		per_cpu(cpu_llc_id, cpu) = node_id;
+		per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
 	} else
 		return;
 
@@ -123,7 +119,7 @@ static void hygon_detect_cmp(struct cpuinfo_x86 *c)
 	/* Convert the initial APIC ID into the socket ID */
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
-	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+	per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
 }
 
 static void srat_detect_node(struct cpuinfo_x86 *c)
@@ -204,23 +200,6 @@ static void early_init_hygon_mc(struct cpuinfo_x86 *c)
 
 static void bsp_init_hygon(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_X86_64
-	unsigned long long tseg;
-
-	/*
-	 * Split up direct mapping around the TSEG SMM area.
-	 * Don't do it for gbpages because there seems very little
-	 * benefit in doing so.
-	 */
-	if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
-		unsigned long pfn = tseg >> PAGE_SHIFT;
-
-		pr_debug("tseg: %010llx\n", tseg);
-		if (pfn_range_is_mapped(pfn, pfn + 1))
-			set_memory_4k((unsigned long)__va(tseg), 1);
-	}
-#endif
-
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
 		u64 val;
 

arch/x86/kernel/cpu/mce/amd.c

@@ -1341,7 +1341,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu,
 		return -ENODEV;
 
 	if (is_shared_bank(bank)) {
-		nb = node_to_amd_nb(amd_get_nb_id(cpu));
+		nb = node_to_amd_nb(topology_die_id(cpu));
 
 		/* threshold descriptor already initialized on this node? */
 		if (nb && nb->bank4) {
@@ -1445,7 +1445,7 @@ static void threshold_remove_bank(struct threshold_bank *bank)
 		 * The last CPU on this node using the shared bank is going
 		 * away, remove that bank now.
 		 */
-		nb = node_to_amd_nb(amd_get_nb_id(smp_processor_id()));
+		nb = node_to_amd_nb(topology_die_id(smp_processor_id()));
 		nb->bank4 = NULL;
 	}
 

arch/x86/kernel/cpu/mce/inject.c

@@ -522,8 +522,8 @@ static void do_inject(void)
 	if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
 	    b == 4 &&
 	    boot_cpu_data.x86 < 0x17) {
-		toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
-		cpu = get_nbc_for_node(amd_get_nb_id(cpu));
+		toggle_nb_mca_mst_cpu(topology_die_id(cpu));
+		cpu = get_nbc_for_node(topology_die_id(cpu));
 	}
 
 	get_online_cpus();

arch/x86/kernel/cpu/topology.c

@@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	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;
+	bool die_level_present = false;
 	int leaf;
 
 	leaf = detect_extended_topology_leaf(c);
@@ -126,6 +127,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 		if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
+			die_level_present = true;
 			die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
 			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
@@ -139,8 +141,12 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 
 	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;
+
+	if (die_level_present) {
+		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);
 	/*

drivers/edac/amd64_edac.c

@@ -1136,7 +1136,7 @@ static int k8_early_channel_count(struct amd64_pvt *pvt)
 /* On F10h and later ErrAddr is MC4_ADDR[47:1] */
 static u64 get_error_address(struct amd64_pvt *pvt, struct mce *m)
 {
-	u16 mce_nid = amd_get_nb_id(m->extcpu);
+	u16 mce_nid = topology_die_id(m->extcpu);
 	struct mem_ctl_info *mci;
 	u8 start_bit = 1;
 	u8 end_bit   = 47;
@@ -3047,7 +3047,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid)
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		if (amd_get_nb_id(cpu) == nid)
+		if (topology_die_id(cpu) == nid)
 			cpumask_set_cpu(cpu, mask);
 }
 

drivers/edac/mce_amd.c

@@ -869,7 +869,7 @@ static void decode_mc3_mce(struct mce *m)
 static void decode_mc4_mce(struct mce *m)
 {
 	unsigned int fam = x86_family(m->cpuid);
-	int node_id = amd_get_nb_id(m->extcpu);
+	int node_id = topology_die_id(m->extcpu);
 	u16 ec = EC(m->status);
 	u8 xec = XEC(m->status, 0x1f);
 	u8 offset = 0;
@@ -1003,7 +1003,7 @@ static void decode_smca_error(struct mce *m)
 		pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]);
 
 	if (bank_type == SMCA_UMC && xec == 0 && decode_dram_ecc)
-		decode_dram_ecc(cpu_to_node(m->extcpu), m);
+		decode_dram_ecc(topology_die_id(m->extcpu), m);
 }
 
 static inline void amd_decode_err_code(u16 ec)