[patch V4 33/41] x86/cpu: Use common topology code for AMD

From: Thomas Gleixner
Date: Mon Aug 14 2023 - 04:56:42 EST


Switch it over to the new topology evaluation mechanism and remove the
random bits and pieces which are sprinkled all over the place.

No functional change intended.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Tested-by: Juergen Gross <jgross@xxxxxxxx>
Tested-by: Sohil Mehta <sohil.mehta@xxxxxxxxx>
Tested-by: Michael Kelley <mikelley@xxxxxxxxxxxxx>

---
arch/x86/include/asm/processor.h | 2
arch/x86/include/asm/topology.h | 5 +
arch/x86/kernel/cpu/amd.c | 146 ----------------------------------
arch/x86/kernel/cpu/mce/inject.c | 3
arch/x86/kernel/cpu/topology_common.c | 5 -
5 files changed, 10 insertions(+), 151 deletions(-)

--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -705,10 +705,8 @@ static inline u32 per_cpu_l2c_id(unsigne
}

#ifdef CONFIG_CPU_SUP_AMD
-extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
#else
-static inline u32 amd_get_nodes_per_socket(void) { return 0; }
static inline u32 amd_get_highest_perf(void) { return 0; }
#endif

--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -121,6 +121,11 @@ struct x86_topology_system {

extern struct x86_topology_system x86_topo_system;

+static inline unsigned int topology_get_domain_size(enum x86_topology_domains dom)
+{
+ return x86_topo_system.dom_size[dom];
+}
+
extern const struct cpumask *cpu_coregroup_mask(int cpu);
extern const struct cpumask *cpu_clustergroup_mask(int cpu);

--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -28,13 +28,6 @@
#include "cpu.h"

/*
- * nodes_per_socket: Stores the number of nodes per socket.
- * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX
- * Node Identifiers[10:8]
- */
-static u32 nodes_per_socket = 1;
-
-/*
* AMD errata checking
*
* Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or
@@ -372,97 +365,6 @@ static int nearby_node(int apicid)
}
#endif

-/*
- * 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.
- */
-static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
-{
- u32 cus_per_node;
-
- if (c->x86 >= 0x17)
- return;
-
- cus_per_node = c->x86_max_cores / nodes_per_socket;
- c->topo.core_id %= cus_per_node;
-}
-
-/*
- * Fixup core topology information for
- * (1) AMD multi-node processors
- * Assumption: Number of cores in each internal node is the same.
- * (2) AMD processors supporting compute units
- */
-static void amd_get_topology(struct cpuinfo_x86 *c)
-{
- /* get information required for multi-node processors */
- if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
- int err;
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-
- c->topo.die_id = ecx & 0xff;
-
- if (c->x86 == 0x15)
- c->topo.cu_id = ebx & 0xff;
-
- if (c->x86 >= 0x17) {
- c->topo.core_id = ebx & 0xff;
-
- if (smp_num_siblings > 1)
- c->x86_max_cores /= smp_num_siblings;
- }
-
- /*
- * In case leaf B is available, use it to derive
- * topology information.
- */
- err = detect_extended_topology(c);
- if (!err)
- c->x86_coreid_bits = get_count_order(c->x86_max_cores);
-
- cacheinfo_amd_init_llc_id(c, c->topo.die_id);
-
- } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
- u64 value;
-
- rdmsrl(MSR_FAM10H_NODE_ID, value);
- c->topo.die_id = value & 7;
- c->topo.llc_id = c->topo.die_id;
- } else
- return;
-
- if (nodes_per_socket > 1) {
- set_cpu_cap(c, X86_FEATURE_AMD_DCM);
- legacy_fixup_core_id(c);
- }
-}
-
-/*
- * On a AMD dual core setup the lower bits of the APIC id distinguish the cores.
- * Assumes number of cores is a power of two.
- */
-static void amd_detect_cmp(struct cpuinfo_x86 *c)
-{
- unsigned bits;
-
- bits = c->x86_coreid_bits;
- /* Low order bits define the core id (index of core in socket) */
- c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
- /* Convert the initial APIC ID into the socket ID */
- c->topo.pkg_id = c->topo.initial_apicid >> bits;
- /* use socket ID also for last level cache */
- c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
-}
-
-u32 amd_get_nodes_per_socket(void)
-{
- return nodes_per_socket;
-}
-EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket);
-
static void srat_detect_node(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_NUMA
@@ -514,32 +416,6 @@ static void srat_detect_node(struct cpui
#endif
}

-static void early_init_amd_mc(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_SMP
- unsigned bits, ecx;
-
- /* Multi core CPU? */
- if (c->extended_cpuid_level < 0x80000008)
- return;
-
- ecx = cpuid_ecx(0x80000008);
-
- c->x86_max_cores = (ecx & 0xff) + 1;
-
- /* CPU telling us the core id bits shift? */
- bits = (ecx >> 12) & 0xF;
-
- /* Otherwise recompute */
- if (bits == 0) {
- while ((1 << bits) < c->x86_max_cores)
- bits++;
- }
-
- c->x86_coreid_bits = bits;
-#endif
-}
-
static void bsp_init_amd(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -572,18 +448,6 @@ static void bsp_init_amd(struct cpuinfo_
if (cpu_has(c, X86_FEATURE_MWAITX))
use_mwaitx_delay();

- if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
- u32 ecx;
-
- ecx = cpuid_ecx(0x8000001e);
- __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
- } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
- u64 value;
-
- rdmsrl(MSR_FAM10H_NODE_ID, value);
- __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
- }
-
if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
!boot_cpu_has(X86_FEATURE_VIRT_SSBD) &&
c->x86 >= 0x15 && c->x86 <= 0x17) {
@@ -665,8 +529,6 @@ static void early_init_amd(struct cpuinf
u64 value;
u32 dummy;

- early_init_amd_mc(c);
-
if (c->x86 >= 0xf)
set_cpu_cap(c, X86_FEATURE_K8);

@@ -754,9 +616,6 @@ static void early_init_amd(struct cpuinf
}
}
}
-
- if (cpu_has(c, X86_FEATURE_TOPOEXT))
- smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
}

static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -1037,9 +896,6 @@ static void init_amd(struct cpuinfo_x86
if (cpu_has(c, X86_FEATURE_FSRM))
set_cpu_cap(c, X86_FEATURE_FSRS);

- /* get apicid instead of initial apic id from cpuid */
- c->topo.apicid = read_apic_id();
-
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
clear_cpu_cap(c, X86_FEATURE_MCE);
@@ -1067,8 +923,6 @@ static void init_amd(struct cpuinfo_x86

cpu_detect_cache_sizes(c);

- amd_detect_cmp(c);
- amd_get_topology(c);
srat_detect_node(c);

init_amd_cacheinfo(c);
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -433,8 +433,7 @@ static u32 get_nbc_for_node(int node_id)
struct cpuinfo_x86 *c = &boot_cpu_data;
u32 cores_per_node;

- cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket();
-
+ cores_per_node = (c->x86_max_cores * smp_num_siblings) / topology_amd_nodes_per_pkg();
return cores_per_node * node_id;
}

--- a/arch/x86/kernel/cpu/topology_common.c
+++ b/arch/x86/kernel/cpu/topology_common.c
@@ -72,7 +72,6 @@ bool topo_is_converted(struct cpuinfo_x8
{
/* Temporary until everything is converted over. */
switch (boot_cpu_data.x86_vendor) {
- case X86_VENDOR_AMD:
case X86_VENDOR_HYGON:
return false;
default:
@@ -133,6 +132,10 @@ static void parse_topology(struct topo_s
tscan->ebx1_nproc_shift = get_count_order(ebx.nproc);

switch (c->x86_vendor) {
+ case X86_VENDOR_AMD:
+ if (IS_ENABLED(CONFIG_CPU_SUP_AMD))
+ cpu_parse_topology_amd(tscan);
+ break;
case X86_VENDOR_CENTAUR:
case X86_VENDOR_ZHAOXIN:
parse_legacy(tscan);