[PATCH v4 1/2] cpuid: Add a helper in scattered.c to return cpuid leaf info

From: He Chen
Date: Tue Nov 08 2016 - 03:54:17 EST

Some sparse cpuid leafs are gathered in a fake leaf to save size of
x86_capability array in current code, but sometimes, kernel or other
modules (e.g. KVM cpuid enumeration) may need actual hardware leaf
information.

This patch adds a helper get_scattered_cpuid_leaf to rebuild actual
cpuid leaf, and it can be called outside by modules. Also, export
enum cpuid_regs in pt.c and scattered.c to enum cpuid_regs_idx in
processor.h.
---
arch/x86/events/intel/pt.c | 45 ++++++++++++++------------------
arch/x86/include/asm/processor.h | 14 ++++++++++
arch/x86/kernel/cpu/scattered.c | 56 ++++++++++++++++++++++++++--------------
arch/x86/kernel/cpuid.c | 4 ---
4 files changed, 70 insertions(+), 49 deletions(-)

diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index c5047b8..1c1b9fe 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -36,13 +36,6 @@ static DEFINE_PER_CPU(struct pt, pt_ctx);

static struct pt_pmu pt_pmu;

-enum cpuid_regs {
- CR_EAX = 0,
- CR_ECX,
- CR_EDX,
- CR_EBX
-};
-
/*
* Capabilities of Intel PT hardware, such as number of address bits or
* supported output schemes, are cached and exported to userspace as "caps"
@@ -64,21 +57,21 @@ static struct pt_cap_desc {
u8 reg;
u32 mask;
} pt_caps[] = {
- PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff),
- PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)),
- PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)),
- PT_CAP(ip_filtering, 0, CR_EBX, BIT(2)),
- PT_CAP(mtc, 0, CR_EBX, BIT(3)),
- PT_CAP(ptwrite, 0, CR_EBX, BIT(4)),
- PT_CAP(power_event_trace, 0, CR_EBX, BIT(5)),
- PT_CAP(topa_output, 0, CR_ECX, BIT(0)),
- PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)),
- PT_CAP(single_range_output, 0, CR_ECX, BIT(2)),
- PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)),
- PT_CAP(num_address_ranges, 1, CR_EAX, 0x3),
- PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000),
- PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff),
- PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000),
+ PT_CAP(max_subleaf, 0, CPUID_EAX, 0xffffffff),
+ PT_CAP(cr3_filtering, 0, CPUID_EBX, BIT(0)),
+ PT_CAP(psb_cyc, 0, CPUID_EBX, BIT(1)),
+ PT_CAP(ip_filtering, 0, CPUID_EBX, BIT(2)),
+ PT_CAP(mtc, 0, CPUID_EBX, BIT(3)),
+ PT_CAP(ptwrite, 0, CPUID_EBX, BIT(4)),
+ PT_CAP(power_event_trace, 0, CPUID_EBX, BIT(5)),
+ PT_CAP(topa_output, 0, CPUID_ECX, BIT(0)),
+ PT_CAP(topa_multiple_entries, 0, CPUID_ECX, BIT(1)),
+ PT_CAP(single_range_output, 0, CPUID_ECX, BIT(2)),
+ PT_CAP(payloads_lip, 0, CPUID_ECX, BIT(31)),
+ PT_CAP(num_address_ranges, 1, CPUID_EAX, 0x3),
+ PT_CAP(mtc_periods, 1, CPUID_EAX, 0xffff0000),
+ PT_CAP(cycle_thresholds, 1, CPUID_EBX, 0xffff),
+ PT_CAP(psb_periods, 1, CPUID_EBX, 0xffff0000),
};

static u32 pt_cap_get(enum pt_capabilities cap)
@@ -213,10 +206,10 @@ static int __init pt_pmu_hw_init(void)

for (i = 0; i < PT_CPUID_LEAVES; i++) {
cpuid_count(20, i,
- &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM],
- &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM],
- &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM],
- &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]);
+ &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
+ &pt_pmu.caps[CPUID_EBX + i*PT_CPUID_REGS_NUM],
+ &pt_pmu.caps[CPUID_ECX + i*PT_CPUID_REGS_NUM],
+ &pt_pmu.caps[CPUID_EDX + i*PT_CPUID_REGS_NUM]);
}

ret = -ENOMEM;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf..e7f8c62 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -137,6 +137,17 @@ struct cpuinfo_x86 {
u32 microcode;
};

+struct cpuid_regs {
+ u32 eax, ebx, ecx, edx;
+};
+
+enum cpuid_regs_idx {
+ CPUID_EAX = 0,
+ CPUID_EBX,
+ CPUID_ECX,
+ CPUID_EDX,
+};
+
#define X86_VENDOR_INTEL 0
#define X86_VENDOR_CYRIX 1
#define X86_VENDOR_AMD 2
@@ -178,6 +189,9 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
void print_cpu_msr(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern u32 get_scattered_cpuid_leaf(unsigned int level,
+ unsigned int sub_leaf,
+ enum cpuid_regs_idx reg);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);

diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 1db8dc4..ef131ea 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -17,11 +17,17 @@ struct cpuid_bit {
u32 sub_leaf;
};

-enum cpuid_regs {
- CR_EAX = 0,
- CR_ECX,
- CR_EDX,
- CR_EBX
+/* Please keep the leaf sorted by cpuid_bit.level for faster search. */
+static const struct cpuid_bit cpuid_bits[] = {
+ { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
+ { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
+ { X86_FEATURE_INTEL_PT, CPUID_EBX, 25, 0x00000007, 0 },
+ { X86_FEATURE_AVX512_4VNNIW, CPUID_EDX, 2, 0x00000007, 0 },
+ { X86_FEATURE_AVX512_4FMAPS, CPUID_EDX, 3, 0x00000007, 0 },
+ { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 },
+ { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
+ { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
+ { 0, 0, 0, 0, 0 }
};

void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
@@ -30,18 +36,6 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
u32 regs[4];
const struct cpuid_bit *cb;

- static const struct cpuid_bit cpuid_bits[] = {
- { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 },
- { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 },
- { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 },
- { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 },
- { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 },
- { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 },
- { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 },
- { 0, 0, 0, 0, 0 }
- };
-
for (cb = cpuid_bits; cb->feature; cb++) {

/* Verify that the level is valid */
@@ -50,10 +44,34 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
max_level > (cb->level | 0xffff))
continue;

- cpuid_count(cb->level, cb->sub_leaf, &regs[CR_EAX],
- &regs[CR_EBX], &regs[CR_ECX], &regs[CR_EDX]);
+ cpuid_count(cb->level, cb->sub_leaf, &regs[CPUID_EAX],
+ &regs[CPUID_EBX], &regs[CPUID_ECX], &regs[CPUID_EDX]);

if (regs[cb->reg] & (1 << cb->bit))
set_cpu_cap(c, cb->feature);
}
}
+
+u32 get_scattered_cpuid_leaf(unsigned int level, unsigned int sub_leaf,
+ enum cpuid_regs_idx reg)
+{
+ const struct cpuid_bit *cb;
+ u32 cpuid_val = 0;
+
+ for (cb = cpuid_bits; cb->feature; cb++) {
+
+ if (level > cb->level)
+ continue;
+
+ if (level < cb->level)
+ break;
+
+ if (reg == cb->reg && sub_leaf == cb->sub_leaf) {
+ if (cpu_has(&boot_cpu_data, cb->feature))
+ cpuid_val |= BIT(cb->bit);
+ }
+ }
+
+ return cpuid_val;
+}
+EXPORT_SYMBOL_GPL(get_scattered_cpuid_leaf);
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 2836de3..9095c80 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -46,10 +46,6 @@

static struct class *cpuid_class;

-struct cpuid_regs {
- u32 eax, ebx, ecx, edx;
-};
-
static void cpuid_smp_cpuid(void *cmd_block)
{
struct cpuid_regs *cmd = (struct cpuid_regs *)cmd_block;
--
2.7.4