Merge branch 'x86/x2apic' into x86/core
Conflicts:
arch/x86/kernel/cpu/common_64.c
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index a6ef672..0d9c993 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -7,6 +7,8 @@
#include <asm/pat.h>
#include <asm/processor.h>
+#include <mach_apic.h>
+
struct cpuid_bit {
u16 feature;
u8 reg;
@@ -48,6 +50,92 @@
}
}
+/* leaf 0xb SMT level */
+#define SMT_LEVEL 0
+
+/* leaf 0xb sub-leaf types */
+#define INVALID_TYPE 0
+#define SMT_TYPE 1
+#define CORE_TYPE 2
+
+#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff)
+#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f)
+#define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff)
+
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+void __cpuinit 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 core_select_mask, core_level_siblings;
+
+ if (c->cpuid_level < 0xb)
+ return;
+
+ cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+ /*
+ * check if the cpuid leaf 0xb is actually implemented.
+ */
+ if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+ return;
+
+ set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
+
+ /*
+ * initial apic id, which also represents 32-bit extended x2apic id.
+ */
+ c->initial_apicid = edx;
+
+ /*
+ * Populate HT related information from sub-leaf level 0.
+ */
+ core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+ core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+
+ sub_index = 1;
+ do {
+ cpuid_count(0xb, 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);
+ core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+ break;
+ }
+
+ sub_index++;
+ } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+
+ core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+
+#ifdef CONFIG_X86_32
+ c->cpu_core_id = phys_pkg_id(c->initial_apicid, ht_mask_width)
+ & core_select_mask;
+ c->phys_proc_id = phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+#else
+ c->cpu_core_id = phys_pkg_id(ht_mask_width) & core_select_mask;
+ c->phys_proc_id = phys_pkg_id(core_plus_mask_width);
+#endif
+ c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+
+
+ printk(KERN_INFO "CPU: Physical Processor ID: %d\n",
+ c->phys_proc_id);
+ if (c->x86_max_cores > 1)
+ printk(KERN_INFO "CPU: Processor Core ID: %d\n",
+ c->cpu_core_id);
+ return;
+#endif
+}
+
#ifdef CONFIG_X86_PAT
void __cpuinit validate_pat_support(struct cpuinfo_x86 *c)
{
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index ae007b3..bcb48ce 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -150,6 +150,9 @@
if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
goto out;
+ if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
+ return;
+
cpuid(1, &eax, &ebx, &ecx, &edx);
smp_num_siblings = (ebx & 0xff0000) >> 16;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c5ac081..959417b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -176,9 +176,16 @@
if (p)
strcpy(c->x86_model_id, p);
- c->x86_max_cores = num_cpu_cores(c);
+ detect_extended_topology(c);
- detect_ht(c);
+ if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+ /*
+ * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+ * detection.
+ */
+ c->x86_max_cores = num_cpu_cores(c);
+ detect_ht(c);
+ }
/* Work around errata */
Intel_errata_workarounds(c);
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
index 0a8128a..0c0a58d 100644
--- a/arch/x86/kernel/cpu/intel_64.c
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -80,7 +80,10 @@
if (c->x86 == 6)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
- c->x86_max_cores = intel_num_cpu_cores(c);
+
+ detect_extended_topology(c);
+ if (!cpu_has(c, X86_FEATURE_XTOPOLOGY))
+ c->x86_max_cores = intel_num_cpu_cores(c);
srat_detect_node();
}
diff --git a/arch/x86/kernel/genx2apic_cluster.c b/arch/x86/kernel/genx2apic_cluster.c
index fed9f68..e4bf2cc 100644
--- a/arch/x86/kernel/genx2apic_cluster.c
+++ b/arch/x86/kernel/genx2apic_cluster.c
@@ -120,14 +120,9 @@
return x;
}
-static unsigned int x2apic_read_id(void)
-{
- return apic_read(APIC_ID);
-}
-
static unsigned int phys_pkg_id(int index_msb)
{
- return x2apic_read_id() >> index_msb;
+ return current_cpu_data.initial_apicid >> index_msb;
}
static void x2apic_send_IPI_self(int vector)
diff --git a/arch/x86/kernel/genx2apic_phys.c b/arch/x86/kernel/genx2apic_phys.c
index 958d537..8f1343d 100644
--- a/arch/x86/kernel/genx2apic_phys.c
+++ b/arch/x86/kernel/genx2apic_phys.c
@@ -118,14 +118,9 @@
return x;
}
-static unsigned int x2apic_read_id(void)
-{
- return apic_read(APIC_ID);
-}
-
static unsigned int phys_pkg_id(int index_msb)
{
- return x2apic_read_id() >> index_msb;
+ return current_cpu_data.initial_apicid >> index_msb;
}
void x2apic_send_IPI_self(int vector)
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 6dfa2b3..7ac4d93 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -89,6 +89,7 @@
#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
#define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */
#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_XTOPOLOGY (3*32+21) /* cpu topology enum extensions */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index ae5bd1a..bbbbe1f 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -165,6 +165,7 @@
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern unsigned short num_cache_leaves;
+extern void detect_extended_topology(struct cpuinfo_x86 *c);
#if defined(CONFIG_X86_HT) || defined(CONFIG_X86_64)
extern void detect_ht(struct cpuinfo_x86 *c);
#else