Merge tag 'x86-core-2023-10-29-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Thomas Gleixner:

 - Limit the hardcoded topology quirk for Hygon CPUs to those which have
   a model ID less than 4.

   The newer models have the topology CPUID leaf 0xB correctly
   implemented and are not affected.

 - Make SMT control more robust against enumeration failures

   SMT control was added to allow controlling SMT at boottime or
   runtime. The primary purpose was to provide a simple mechanism to
   disable SMT in the light of speculation attack vectors.

   It turned out that the code is sensible to enumeration failures and
   worked only by chance for XEN/PV. XEN/PV has no real APIC enumeration
   which means the primary thread mask is not set up correctly. By
   chance a XEN/PV boot ends up with smp_num_siblings == 2, which makes
   the hotplug control stay at its default value "enabled". So the mask
   is never evaluated.

   The ongoing rework of the topology evaluation caused XEN/PV to end up
   with smp_num_siblings == 1, which sets the SMT control to "not
   supported" and the empty primary thread mask causes the hotplug core
   to deny the bringup of the APS.

   Make the decision logic more robust and take 'not supported' and 'not
   implemented' into account for the decision whether a CPU should be
   booted or not.

 - Fake primary thread mask for XEN/PV

   Pretend that all XEN/PV vCPUs are primary threads, which makes the
   usage of the primary thread mask valid on XEN/PV. That is consistent
   with because all of the topology information on XEN/PV is fake or
   even non-existent.

 - Encapsulate topology information in cpuinfo_x86

   Move the randomly scattered topology data into a separate data
   structure for readability and as a preparatory step for the topology
   evaluation overhaul.

 - Consolidate APIC ID data type to u32

   It's fixed width hardware data and not randomly u16, int, unsigned
   long or whatever developers decided to use.

 - Cure the abuse of cpuinfo for persisting logical IDs.

   Per CPU cpuinfo is used to persist the logical package and die IDs.
   That's really not the right place simply because cpuinfo is subject
   to be reinitialized when a CPU goes through an offline/online cycle.

   Use separate per CPU data for the persisting to enable the further
   topology management rework. It will be removed once the new topology
   management is in place.

 - Provide a debug interface for inspecting topology information

   Useful in general and extremly helpful for validating the topology
   management rework in terms of correctness or "bug" compatibility.

* tag 'x86-core-2023-10-29-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/apic, x86/hyperv: Use u32 in hv_snp_boot_ap() too
  x86/cpu: Provide debug interface
  x86/cpu/topology: Cure the abuse of cpuinfo for persisting logical ids
  x86/apic: Use u32 for wakeup_secondary_cpu[_64]()
  x86/apic: Use u32 for [gs]et_apic_id()
  x86/apic: Use u32 for phys_pkg_id()
  x86/apic: Use u32 for cpu_present_to_apicid()
  x86/apic: Use u32 for check_apicid_used()
  x86/apic: Use u32 for APIC IDs in global data
  x86/apic: Use BAD_APICID consistently
  x86/cpu: Move cpu_l[l2]c_id into topology info
  x86/cpu: Move logical package and die IDs into topology info
  x86/cpu: Remove pointless evaluation of x86_coreid_bits
  x86/cpu: Move cu_id into topology info
  x86/cpu: Move cpu_core_id into topology info
  hwmon: (fam15h_power) Use topology_core_id()
  scsi: lpfc: Use topology_core_id()
  x86/cpu: Move cpu_die_id into topology info
  x86/cpu: Move phys_proc_id into topology info
  x86/cpu: Encapsulate topology information in cpuinfo_x86
  ...

1 files changed, 15 insertions, 19 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d97d473545a6..a7eab05e5f29 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -382,7 +382,7 @@ static int nearby_node(int apicid)
 #endif
 
 /*
- * Fix up cpu_core_id for pre-F17h systems to be in the
+ * Fix up topo::core_id for pre-F17h systems to be in the
  * [0 .. cores_per_node - 1] range. Not really needed but
  * kept so as not to break existing setups.
  */
@@ -394,7 +394,7 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
 		return;
 
 	cus_per_node = c->x86_max_cores / nodes_per_socket;
-	c->cpu_core_id %= cus_per_node;
+	c->topo.core_id %= cus_per_node;
 }
 
 /*
@@ -405,8 +405,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
  */
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	int cpu = smp_processor_id();
-
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
 		int err;
@@ -414,13 +412,13 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
-		c->cpu_die_id  = ecx & 0xff;
+		c->topo.die_id  = ecx & 0xff;
 
 		if (c->x86 == 0x15)
-			c->cu_id = ebx & 0xff;
+			c->topo.cu_id = ebx & 0xff;
 
 		if (c->x86 >= 0x17) {
-			c->cpu_core_id = ebx & 0xff;
+			c->topo.core_id = ebx & 0xff;
 
 			if (smp_num_siblings > 1)
 				c->x86_max_cores /= smp_num_siblings;
@@ -434,15 +432,14 @@ 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);
+		cacheinfo_amd_init_llc_id(c);
 
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		c->cpu_die_id = value & 7;
-
-		per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
+		c->topo.die_id = value & 7;
+		c->topo.llc_id = c->topo.die_id;
 	} else
 		return;
 
@@ -459,15 +456,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 static void amd_detect_cmp(struct cpuinfo_x86 *c)
 {
 	unsigned bits;
-	int cpu = smp_processor_id();
 
 	bits = c->x86_coreid_bits;
 	/* Low order bits define the core id (index of core in socket) */
-	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+	c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
 	/* Convert the initial APIC ID into the socket ID */
-	c->phys_proc_id = c->initial_apicid >> bits;
+	c->topo.pkg_id = c->topo.initial_apicid >> bits;
 	/* use socket ID also for last level cache */
-	per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
+	c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
 }
 
 u32 amd_get_nodes_per_socket(void)
@@ -481,11 +477,11 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 #ifdef CONFIG_NUMA
 	int cpu = smp_processor_id();
 	int node;
-	unsigned apicid = c->apicid;
+	unsigned apicid = c->topo.apicid;
 
 	node = numa_cpu_node(cpu);
 	if (node == NUMA_NO_NODE)
-		node = get_llc_id(cpu);
+		node = per_cpu_llc_id(cpu);
 
 	/*
 	 * On multi-fabric platform (e.g. Numascale NumaChip) a
@@ -515,7 +511,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
 		 * through CPU mapping may alter the outcome, directly
 		 * access __apicid_to_node[].
 		 */
-		int ht_nodeid = c->initial_apicid;
+		int ht_nodeid = c->topo.initial_apicid;
 
 		if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
 			node = __apicid_to_node[ht_nodeid];
@@ -1061,7 +1057,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_FSRS);
 
 	/* get apicid instead of initial apic id from cpuid */
-	c->apicid = read_apic_id();
+	c->topo.apicid = read_apic_id();
 
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)