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

…nux/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
  ...

Documentation/arch/x86/topology.rst

@@ -55,19 +55,19 @@ 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:
+  - cpuinfo_x86.topo.die_id:
 
     The physical ID of the die. This information is retrieved via CPUID.
 
-  - cpuinfo_x86.phys_proc_id:
+  - cpuinfo_x86.topo.pkg_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.
+    packages within a socket. This value may differ from topo.die_id.
 
-  - cpuinfo_x86.logical_proc_id:
+  - cpuinfo_x86.topo.logical_pkg_id:
 
     The logical ID of the package. As we do not trust BIOSes to enumerate the
     packages in a consistent way, we introduced the concept of logical package
@@ -79,9 +79,7 @@ Package-related topology information in the kernel:
     The maximum possible number of packages in the system. Helpful for per
     package facilities to preallocate per package information.
 
-  - cpu_llc_id:
-
-    A per-CPU variable containing:
+  - cpuinfo_x86.topo.llc_id:
 
       - On Intel, the first APIC ID of the list of CPUs sharing the Last Level
         Cache

arch/x86/events/amd/uncore.c

@@ -772,7 +772,7 @@ void amd_uncore_l3_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	info.split.aux_data = 0;
 	info.split.num_pmcs = NUM_COUNTERS_L2;
 	info.split.gid = 0;
-	info.split.cid = get_llc_id(cpu);
+	info.split.cid = per_cpu_llc_id(cpu);
 
 	if (boot_cpu_data.x86 >= 0x17)
 		info.split.num_pmcs = NUM_COUNTERS_L3;

arch/x86/events/intel/uncore.c

@@ -74,7 +74,7 @@ int uncore_device_to_die(struct pci_dev *dev)
 		struct cpuinfo_x86 *c = &cpu_data(cpu);
 
 		if (c->initialized && cpu_to_node(cpu) == node)
-			return c->logical_die_id;
+			return c->topo.logical_die_id;
 	}
 
 	return -1;

arch/x86/hyperv/hv_vtl.c

@@ -196,7 +196,7 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id)
 	return ret;
 }
 
-static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip)
+static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
 {
 	int vp_id;
 

arch/x86/hyperv/ivm.c

@@ -288,7 +288,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
 		free_page((unsigned long)vmsa);
 }
 
-int hv_snp_boot_ap(int cpu, unsigned long start_ip)
+int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
 {
 	struct sev_es_save_area *vmsa = (struct sev_es_save_area *)
 		__get_free_page(GFP_KERNEL | __GFP_ZERO);

arch/x86/include/asm/apic.h

@@ -54,7 +54,7 @@ extern int local_apic_timer_c2_ok;
 extern bool apic_is_disabled;
 extern unsigned int lapic_timer_period;
 
-extern int cpuid_to_apicid[];
+extern u32 cpuid_to_apicid[];
 
 extern enum apic_intr_mode_id apic_intr_mode;
 enum apic_intr_mode_id {
@@ -292,19 +292,19 @@ struct apic {
 	int	(*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
 	bool	(*apic_id_registered)(void);
 
-	bool	(*check_apicid_used)(physid_mask_t *map, int apicid);
+	bool	(*check_apicid_used)(physid_mask_t *map, u32 apicid);
 	void	(*init_apic_ldr)(void);
 	void	(*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
-	int	(*cpu_present_to_apicid)(int mps_cpu);
-	int	(*phys_pkg_id)(int cpuid_apic, int index_msb);
+	u32	(*cpu_present_to_apicid)(int mps_cpu);
+	u32	(*phys_pkg_id)(u32 cpuid_apic, int index_msb);
 
-	u32	(*get_apic_id)(unsigned long x);
-	u32	(*set_apic_id)(unsigned int id);
+	u32	(*get_apic_id)(u32 id);
+	u32	(*set_apic_id)(u32 apicid);
 
 	/* wakeup_secondary_cpu */
-	int	(*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
 	/* wakeup secondary CPU using 64-bit wakeup point */
-	int	(*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
 
 	char	*name;
 };
@@ -322,8 +322,8 @@ struct apic_override {
 	void	(*send_IPI_self)(int vector);
 	u64	(*icr_read)(void);
 	void	(*icr_write)(u32 low, u32 high);
-	int	(*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
-	int	(*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
 };
 
 /*
@@ -493,16 +493,6 @@ static inline bool lapic_vector_set_in_irr(unsigned int vector)
 	return !!(irr & (1U << (vector % 32)));
 }
 
-static inline unsigned default_get_apic_id(unsigned long x)
-{
-	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-
-	if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
-		return (x >> 24) & 0xFF;
-	else
-		return (x >> 24) & 0x0F;
-}
-
 /*
  * Warm reset vector position:
  */
@@ -517,9 +507,9 @@ extern void generic_bigsmp_probe(void);
 
 extern struct apic apic_noop;
 
-static inline unsigned int read_apic_id(void)
+static inline u32 read_apic_id(void)
 {
-	unsigned int reg = apic_read(APIC_ID);
+	u32 reg = apic_read(APIC_ID);
 
 	return apic->get_apic_id(reg);
 }
@@ -538,13 +528,12 @@ extern int default_apic_id_valid(u32 apicid);
 extern u32 apic_default_calc_apicid(unsigned int cpu);
 extern u32 apic_flat_calc_apicid(unsigned int cpu);
 
-extern bool default_check_apicid_used(physid_mask_t *map, int apicid);
 extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
-extern int default_cpu_present_to_apicid(int mps_cpu);
+extern u32 default_cpu_present_to_apicid(int mps_cpu);
 
 #else /* CONFIG_X86_LOCAL_APIC */
 
-static inline unsigned int read_apic_id(void) { return 0; }
+static inline u32 read_apic_id(void) { return 0; }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 

arch/x86/include/asm/cacheinfo.h

@@ -7,9 +7,6 @@ extern unsigned int memory_caching_control;
 #define CACHE_MTRR 0x01
 #define CACHE_PAT  0x02
 
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu);
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu);
-
 void cache_disable(void);
 void cache_enable(void);
 void set_cache_aps_delayed_init(bool val);

arch/x86/include/asm/mpspec.h

@@ -37,7 +37,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES];
 
 extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
-extern unsigned int boot_cpu_physical_apicid;
+extern u32 boot_cpu_physical_apicid;
 extern u8 boot_cpu_apic_version;
 
 #ifdef CONFIG_X86_LOCAL_APIC

arch/x86/include/asm/mshyperv.h

@@ -276,11 +276,11 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 bool hv_ghcb_negotiate_protocol(void);
 void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
-int hv_snp_boot_ap(int cpu, unsigned long start_ip);
+int hv_snp_boot_ap(u32 cpu, unsigned long start_ip);
 #else
 static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
 static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
-static inline int hv_snp_boot_ap(int cpu, unsigned long start_ip) { return 0; }
+static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; }
 #endif
 
 #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)

arch/x86/include/asm/processor.h

@@ -75,11 +75,36 @@ extern u16 __read_mostly tlb_lld_4m[NR_INFO];
 extern u16 __read_mostly tlb_lld_1g[NR_INFO];
 
 /*
- *  CPU type and hardware bug flags. Kept separately for each CPU.
- *  Members of this structure are referenced in head_32.S, so think twice
- *  before touching them. [mj]
+ * CPU type and hardware bug flags. Kept separately for each CPU.
  */
 
+struct cpuinfo_topology {
+	// Real APIC ID read from the local APIC
+	u32			apicid;
+	// The initial APIC ID provided by CPUID
+	u32			initial_apicid;
+
+	// Physical package ID
+	u32			pkg_id;
+
+	// Physical die ID on AMD, Relative on Intel
+	u32			die_id;
+
+	// Compute unit ID - AMD specific
+	u32			cu_id;
+
+	// Core ID relative to the package
+	u32			core_id;
+
+	// Logical ID mappings
+	u32			logical_pkg_id;
+	u32			logical_die_id;
+
+	// Cache level topology IDs
+	u32			llc_id;
+	u32			l2c_id;
+};
+
 struct cpuinfo_x86 {
 	__u8			x86;		/* CPU family */
 	__u8			x86_vendor;	/* CPU vendor */
@@ -96,7 +121,6 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
-	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
@@ -112,6 +136,7 @@ struct cpuinfo_x86 {
 	};
 	char			x86_vendor_id[16];
 	char			x86_model_id[64];
+	struct cpuinfo_topology	topo;
 	/* in KB - valid for CPUS which support this call: */
 	unsigned int		x86_cache_size;
 	int			x86_cache_alignment;	/* In bytes */
@@ -125,19 +150,9 @@ struct cpuinfo_x86 {
 	u64			ppin;
 	/* cpuid returned max cores value: */
 	u16			x86_max_cores;
-	u16			apicid;
-	u16			initial_apicid;
 	u16			x86_clflush_size;
 	/* number of cores as seen by the OS: */
 	u16			booted_cores;
-	/* Physical processor id: */
-	u16			phys_proc_id;
-	/* Logical processor id: */
-	u16			logical_proc_id;
-	/* Core id: */
-	u16			cpu_core_id;
-	u16			cpu_die_id;
-	u16			logical_die_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	/*  Is SMT active on this core? */
@@ -678,7 +693,15 @@ extern int set_tsc_mode(unsigned int val);
 
 DECLARE_PER_CPU(u64, msr_misc_features_shadow);
 
-extern u16 get_llc_id(unsigned int cpu);
+static inline u32 per_cpu_llc_id(unsigned int cpu)
+{
+	return per_cpu(cpu_info.topo.llc_id, cpu);
+}
+
+static inline u32 per_cpu_l2c_id(unsigned int cpu)
+{
+	return per_cpu(cpu_info.topo.l2c_id, cpu);
+}
 
 #ifdef CONFIG_CPU_SUP_AMD
 extern u32 amd_get_nodes_per_socket(void);

arch/x86/include/asm/smp.h

@@ -17,10 +17,8 @@ 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(cpumask_var_t, cpu_l2c_shared_map);
-DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
-DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
 
-DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
 
 struct task_struct;

arch/x86/include/asm/topology.h

@@ -105,17 +105,17 @@ static inline void setup_node_to_cpumask_map(void) { }
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 extern const struct cpumask *cpu_clustergroup_mask(int cpu);
 
-#define topology_logical_package_id(cpu)	(cpu_data(cpu).logical_proc_id)
-#define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
-#define topology_logical_die_id(cpu)		(cpu_data(cpu).logical_die_id)
-#define topology_die_id(cpu)			(cpu_data(cpu).cpu_die_id)
-#define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
+#define topology_logical_package_id(cpu)	(cpu_data(cpu).topo.logical_pkg_id)
+#define topology_physical_package_id(cpu)	(cpu_data(cpu).topo.pkg_id)
+#define topology_logical_die_id(cpu)		(cpu_data(cpu).topo.logical_die_id)
+#define topology_die_id(cpu)			(cpu_data(cpu).topo.die_id)
+#define topology_core_id(cpu)			(cpu_data(cpu).topo.core_id)
 #define topology_ppin(cpu)			(cpu_data(cpu).ppin)
 
 extern unsigned int __max_die_per_package;
 
 #ifdef CONFIG_SMP
-#define topology_cluster_id(cpu)		(per_cpu(cpu_l2c_id, cpu))
+#define topology_cluster_id(cpu)		(cpu_data(cpu).topo.l2c_id)
 #define topology_die_cpumask(cpu)		(per_cpu(cpu_die_map, cpu))
 #define topology_cluster_cpumask(cpu)		(cpu_clustergroup_mask(cpu))
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))

arch/x86/include/asm/x86_init.h

@@ -177,7 +177,7 @@ struct x86_init_ops {
  * struct x86_cpuinit_ops - platform specific cpu hotplug setups
  * @setup_percpu_clockev:	set up the per cpu clock event device
  * @early_percpu_clock_init:	early init of the per cpu clock event device
- * @fixup_cpu_id:		fixup function for cpuinfo_x86::phys_proc_id
+ * @fixup_cpu_id:		fixup function for cpuinfo_x86::topo.pkg_id
  * @parallel_bringup:		Parallel bringup control
  */
 struct x86_cpuinit_ops {

arch/x86/kernel/acpi/boot.c

@@ -362,7 +362,7 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e
 }
 
 #ifdef CONFIG_X86_64
-static int acpi_wakeup_cpu(int apicid, unsigned long start_ip)
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
 {
 	/*
 	 * Remap mailbox memory only for the first call to acpi_wakeup_cpu().
@@ -859,7 +859,7 @@ int acpi_unmap_cpu(int cpu)
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
 #endif
 
-	per_cpu(x86_cpu_to_apicid, cpu) = -1;
+	per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
 	set_cpu_present(cpu, false);
 	num_processors--;
 

arch/x86/kernel/amd_nb.c

@@ -394,7 +394,7 @@ int amd_get_subcaches(int cpu)
 
 	pci_read_config_dword(link, 0x1d4, &mask);
 
-	return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf;
+	return (mask >> (4 * cpu_data(cpu).topo.core_id)) & 0xf;
 }
 
 int amd_set_subcaches(int cpu, unsigned long mask)
@@ -420,7 +420,7 @@ int amd_set_subcaches(int cpu, unsigned long mask)
 		pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
 	}
 
-	cuid = cpu_data(cpu).cpu_core_id;
+	cuid = cpu_data(cpu).topo.core_id;
 	mask <<= 4 * cuid;
 	mask |= (0xf ^ (1 << cuid)) << 26;