* [PATCH v3 1/2] i386: Add Intel Processor Trace feature support @ 2018-01-31 15:57 Luwei Kang 2018-01-31 15:57 ` [PATCH v3 2/2] i386: Add support to get/set/migrate Intel Processor Trace feature Luwei Kang 2018-02-07 14:53 ` [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Eduardo Habkost 0 siblings, 2 replies; 5+ messages in thread From: Luwei Kang @ 2018-01-31 15:57 UTC (permalink / raw) To: qemu-devel, kvm; +Cc: pbonzini, rth, ehabkost, mtosatti, Chao Peng, Luwei Kang From: Chao Peng <chao.p.peng@linux.intel.com> Expose Intel Processor Trace feature to guest. To make Intel PT live migration safe and get same CPUID information with same CPU model on diffrent host. CPUID[14] is constant in this patch. Intel PT use EPT is first supported in IceLake, the CPUID[14] get on this machine as default value. Intel PT would be disabled If any machine don't support this minial feature list. Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> Signed-off-by: Luwei Kang <luwei.kang@intel.com> --- target/i386/cpu.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++-- target/i386/cpu.h | 1 + target/i386/kvm.c | 23 +++++++++++++++++++++++ 3 files changed, 75 insertions(+), 2 deletions(-) diff --git a/target/i386/cpu.c b/target/i386/cpu.c index a49d222..aaa427a 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -172,7 +172,14 @@ #define L2_ITLB_4K_ASSOC 4 #define L2_ITLB_4K_ENTRIES 512 - +/* CPUID Leaf 0x14 constants: */ +#define INTLE_PT_MAX_SUBLEAF 0x1 +#define INTEL_PT_MINIMAL_EBX 0xf +#define INTEL_PT_MINIMAL_ECX 0x7 +#define INTLE_PT_ADDR_RANGES_NUM 0x2 /* Number of configurable address ranges */ +#define INTEL_PT_MTC_BITMAP (0x0249 << 16) /* Support ART(0,3,6,9) */ +#define INTEL_PT_CYCLE_BITMAP 0x1fff /* Support 0,2^(0~11) */ +#define INTEL_PT_PSB_BITMAP (0x003f << 16) /* Support 2K,4K,8K,16K,32K,64K */ static void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, uint32_t vendor2, uint32_t vendor3) @@ -427,7 +434,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = { NULL, NULL, "mpx", NULL, "avx512f", "avx512dq", "rdseed", "adx", "smap", "avx512ifma", "pcommit", "clflushopt", - "clwb", NULL, "avx512pf", "avx512er", + "clwb", "intel-pt", "avx512pf", "avx512er", "avx512cd", "sha-ni", "avx512bw", "avx512vl", }, .cpuid_eax = 7, @@ -3452,6 +3459,27 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, } break; } + case 0x14: { + /* Intel Processor Trace Enumeration */ + *eax = 0; + *ebx = 0; + *ecx = 0; + *edx = 0; + if (!(env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) || + !kvm_enabled()) { + break; + } + + if (count == 0) { + *eax = INTLE_PT_MAX_SUBLEAF; + *ebx = INTEL_PT_MINIMAL_EBX; + *ecx = INTEL_PT_MINIMAL_ECX; + } else if (count == 1) { + *eax = INTEL_PT_MTC_BITMAP | INTLE_PT_ADDR_RANGES_NUM; + *ebx = INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP; + } + break; + } case 0x40000000: /* * CPUID code in kvm_arch_init_vcpu() ignores stuff @@ -4082,6 +4110,27 @@ static int x86_cpu_filter_features(X86CPU *cpu) } } + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { + KVMState *s = CPU(cpu)->kvm_state; + uint32_t eax_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EAX); + uint32_t ebx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EBX); + uint32_t ecx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_ECX); + uint32_t eax_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EAX); + uint32_t ebx_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EBX); + + if (!eax_0 || + ((ebx_0 & INTEL_PT_MINIMAL_EBX) != INTEL_PT_MINIMAL_EBX) || + ((ecx_0 & INTEL_PT_MINIMAL_ECX) != INTEL_PT_MINIMAL_ECX) || + ((eax_1 & (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) != + (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) || + ((ebx_1 & (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) != + (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP))) { + env->features[FEAT_7_0_EBX] &= ~CPUID_7_0_EBX_INTEL_PT; + cpu->filtered_features[FEAT_7_0_EBX] |= CPUID_7_0_EBX_INTEL_PT; + rv = 1; + } + } + return rv; } diff --git a/target/i386/cpu.h b/target/i386/cpu.h index f91e37d..7facc8b 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -644,6 +644,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS]; #define CPUID_7_0_EBX_PCOMMIT (1U << 22) /* Persistent Commit */ #define CPUID_7_0_EBX_CLFLUSHOPT (1U << 23) /* Flush a Cache Line Optimized */ #define CPUID_7_0_EBX_CLWB (1U << 24) /* Cache Line Write Back */ +#define CPUID_7_0_EBX_INTEL_PT (1U << 25) /* Intel Processor Trace */ #define CPUID_7_0_EBX_AVX512PF (1U << 26) /* AVX-512 Prefetch */ #define CPUID_7_0_EBX_AVX512ER (1U << 27) /* AVX-512 Exponential and Reciprocal */ #define CPUID_7_0_EBX_AVX512CD (1U << 28) /* AVX-512 Conflict Detection */ diff --git a/target/i386/kvm.c b/target/i386/kvm.c index ad4b159..f9f4cd1 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -865,6 +865,29 @@ int kvm_arch_init_vcpu(CPUState *cs) c = &cpuid_data.entries[cpuid_i++]; } break; + case 0x14: { + uint32_t times; + + c->function = i; + c->index = 0; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); + times = c->eax; + + for (j = 1; j <= times; ++j) { + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { + fprintf(stderr, "cpuid_data is full, no space for " + "cpuid(eax:0x14,ecx:0x%x)\n", j); + abort(); + } + c = &cpuid_data.entries[cpuid_i++]; + c->function = i; + c->index = j; + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); + } + break; + } default: c->function = i; c->flags = 0; -- 1.8.3.1 ^ permalink raw reply related [flat|nested] 5+ messages in thread
* [PATCH v3 2/2] i386: Add support to get/set/migrate Intel Processor Trace feature 2018-01-31 15:57 [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Luwei Kang @ 2018-01-31 15:57 ` Luwei Kang 2018-02-07 14:53 ` [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Eduardo Habkost 1 sibling, 0 replies; 5+ messages in thread From: Luwei Kang @ 2018-01-31 15:57 UTC (permalink / raw) To: qemu-devel, kvm; +Cc: pbonzini, rth, ehabkost, mtosatti, Chao Peng, Luwei Kang From: Chao Peng <chao.p.peng@linux.intel.com> Add Intel Processor Trace related definition. It also add corresponding part to kvm_get/set_msr and vmstate. Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> Signed-off-by: Luwei Kang <luwei.kang@intel.com> --- target/i386/cpu.h | 22 ++++++++++++++++++++++ target/i386/kvm.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ target/i386/machine.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 111 insertions(+) diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 7facc8b..164d17f 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -419,6 +419,21 @@ typedef enum X86Seg { #define MSR_MC0_ADDR 0x402 #define MSR_MC0_MISC 0x403 +#define MSR_IA32_RTIT_OUTPUT_BASE 0x560 +#define MSR_IA32_RTIT_OUTPUT_MASK 0x561 +#define MSR_IA32_RTIT_CTL 0x570 +#define MSR_IA32_RTIT_STATUS 0x571 +#define MSR_IA32_RTIT_CR3_MATCH 0x572 +#define MSR_IA32_RTIT_ADDR0_A 0x580 +#define MSR_IA32_RTIT_ADDR0_B 0x581 +#define MSR_IA32_RTIT_ADDR1_A 0x582 +#define MSR_IA32_RTIT_ADDR1_B 0x583 +#define MSR_IA32_RTIT_ADDR2_A 0x584 +#define MSR_IA32_RTIT_ADDR2_B 0x585 +#define MSR_IA32_RTIT_ADDR3_A 0x586 +#define MSR_IA32_RTIT_ADDR3_B 0x587 +#define MAX_RTIT_ADDRS 8 + #define MSR_EFER 0xc0000080 #define MSR_EFER_SCE (1 << 0) @@ -1158,6 +1173,13 @@ typedef struct CPUX86State { uint64_t msr_hv_stimer_config[HV_STIMER_COUNT]; uint64_t msr_hv_stimer_count[HV_STIMER_COUNT]; + uint64_t msr_rtit_ctrl; + uint64_t msr_rtit_status; + uint64_t msr_rtit_output_base; + uint64_t msr_rtit_output_mask; + uint64_t msr_rtit_cr3_match; + uint64_t msr_rtit_addrs[MAX_RTIT_ADDRS]; + /* exception/interrupt handling */ int error_code; int exception_is_int; diff --git a/target/i386/kvm.c b/target/i386/kvm.c index f9f4cd1..097c953 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -1811,6 +1811,25 @@ static int kvm_put_msrs(X86CPU *cpu, int level) kvm_msr_entry_add(cpu, MSR_MTRRphysMask(i), mask); } } + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { + int addr_num = kvm_arch_get_supported_cpuid(kvm_state, + 0x14, 1, R_EAX) & 0x7; + + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CTL, + env->msr_rtit_ctrl); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_STATUS, + env->msr_rtit_status); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_BASE, + env->msr_rtit_output_base); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_MASK, + env->msr_rtit_output_mask); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CR3_MATCH, + env->msr_rtit_cr3_match); + for (i = 0; i < addr_num; i++) { + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_ADDR0_A + i, + env->msr_rtit_addrs[i]); + } + } /* Note: MSR_IA32_FEATURE_CONTROL is written separately, see * kvm_put_msr_feature_control. */ @@ -2124,6 +2143,20 @@ static int kvm_get_msrs(X86CPU *cpu) } } + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { + int addr_num = + kvm_arch_get_supported_cpuid(kvm_state, 0x14, 1, R_EAX) & 0x7; + + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CTL, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_STATUS, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_BASE, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_OUTPUT_MASK, 0); + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_CR3_MATCH, 0); + for (i = 0; i < addr_num; i++) { + kvm_msr_entry_add(cpu, MSR_IA32_RTIT_ADDR0_A + i, 0); + } + } + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MSRS, cpu->kvm_msr_buf); if (ret < 0) { return ret; @@ -2364,6 +2397,24 @@ static int kvm_get_msrs(X86CPU *cpu) case MSR_IA32_SPEC_CTRL: env->spec_ctrl = msrs[i].data; break; + case MSR_IA32_RTIT_CTL: + env->msr_rtit_ctrl = msrs[i].data; + break; + case MSR_IA32_RTIT_STATUS: + env->msr_rtit_status = msrs[i].data; + break; + case MSR_IA32_RTIT_OUTPUT_BASE: + env->msr_rtit_output_base = msrs[i].data; + break; + case MSR_IA32_RTIT_OUTPUT_MASK: + env->msr_rtit_output_mask = msrs[i].data; + break; + case MSR_IA32_RTIT_CR3_MATCH: + env->msr_rtit_cr3_match = msrs[i].data; + break; + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + env->msr_rtit_addrs[index - MSR_IA32_RTIT_ADDR0_A] = msrs[i].data; + break; } } diff --git a/target/i386/machine.c b/target/i386/machine.c index 361c05a..c05fe6f 100644 --- a/target/i386/machine.c +++ b/target/i386/machine.c @@ -837,6 +837,43 @@ static const VMStateDescription vmstate_spec_ctrl = { } }; +static bool intel_pt_enable_needed(void *opaque) +{ + X86CPU *cpu = opaque; + CPUX86State *env = &cpu->env; + int i; + + if (env->msr_rtit_ctrl || env->msr_rtit_status || + env->msr_rtit_output_base || env->msr_rtit_output_mask || + env->msr_rtit_cr3_match) { + return true; + } + + for (i = 0; i < MAX_RTIT_ADDRS; i++) { + if (env->msr_rtit_addrs[i]) { + return true; + } + } + + return false; +} + +static const VMStateDescription vmstate_msr_intel_pt = { + .name = "cpu/intel_pt", + .version_id = 1, + .minimum_version_id = 1, + .needed = intel_pt_enable_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64(env.msr_rtit_ctrl, X86CPU), + VMSTATE_UINT64(env.msr_rtit_status, X86CPU), + VMSTATE_UINT64(env.msr_rtit_output_base, X86CPU), + VMSTATE_UINT64(env.msr_rtit_output_mask, X86CPU), + VMSTATE_UINT64(env.msr_rtit_cr3_match, X86CPU), + VMSTATE_UINT64_ARRAY(env.msr_rtit_addrs, X86CPU, MAX_RTIT_ADDRS), + VMSTATE_END_OF_LIST() + } +}; + VMStateDescription vmstate_x86_cpu = { .name = "cpu", .version_id = 12, @@ -957,6 +994,7 @@ VMStateDescription vmstate_x86_cpu = { #endif &vmstate_spec_ctrl, &vmstate_mcg_ext_ctl, + &vmstate_msr_intel_pt, NULL } }; -- 1.8.3.1 ^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support 2018-01-31 15:57 [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Luwei Kang 2018-01-31 15:57 ` [PATCH v3 2/2] i386: Add support to get/set/migrate Intel Processor Trace feature Luwei Kang @ 2018-02-07 14:53 ` Eduardo Habkost 2018-02-08 1:24 ` Kang, Luwei 1 sibling, 1 reply; 5+ messages in thread From: Eduardo Habkost @ 2018-02-07 14:53 UTC (permalink / raw) To: Luwei Kang; +Cc: qemu-devel, kvm, mtosatti, Chao Peng, pbonzini, rth On Wed, Jan 31, 2018 at 11:57:45PM +0800, Luwei Kang wrote: > From: Chao Peng <chao.p.peng@linux.intel.com> > > Expose Intel Processor Trace feature to guest. > > To make Intel PT live migration safe and get same CPUID information > with same CPU model on diffrent host. CPUID[14] is constant in this > patch. Intel PT use EPT is first supported in IceLake, the CPUID[14] > get on this machine as default value. Intel PT would be disabled > If any machine don't support this minial feature list. > > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > Signed-off-by: Luwei Kang <luwei.kang@intel.com> > --- > target/i386/cpu.c | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++-- > target/i386/cpu.h | 1 + > target/i386/kvm.c | 23 +++++++++++++++++++++++ > 3 files changed, 75 insertions(+), 2 deletions(-) > > diff --git a/target/i386/cpu.c b/target/i386/cpu.c > index a49d222..aaa427a 100644 > --- a/target/i386/cpu.c > +++ b/target/i386/cpu.c > @@ -172,7 +172,14 @@ > #define L2_ITLB_4K_ASSOC 4 > #define L2_ITLB_4K_ENTRIES 512 > > - > +/* CPUID Leaf 0x14 constants: */ > +#define INTLE_PT_MAX_SUBLEAF 0x1 Typo. > +#define INTEL_PT_MINIMAL_EBX 0xf > +#define INTEL_PT_MINIMAL_ECX 0x7 I suggest documenting what capabilities are included in INTEL_PT_MINIMAL_* here. > +#define INTLE_PT_ADDR_RANGES_NUM 0x2 /* Number of configurable address ranges */ Typo. > +#define INTEL_PT_MTC_BITMAP (0x0249 << 16) /* Support ART(0,3,6,9) */ > +#define INTEL_PT_CYCLE_BITMAP 0x1fff /* Support 0,2^(0~11) */ > +#define INTEL_PT_PSB_BITMAP (0x003f << 16) /* Support 2K,4K,8K,16K,32K,64K */ > > static void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, > uint32_t vendor2, uint32_t vendor3) > @@ -427,7 +434,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = { > NULL, NULL, "mpx", NULL, > "avx512f", "avx512dq", "rdseed", "adx", > "smap", "avx512ifma", "pcommit", "clflushopt", > - "clwb", NULL, "avx512pf", "avx512er", > + "clwb", "intel-pt", "avx512pf", "avx512er", > "avx512cd", "sha-ni", "avx512bw", "avx512vl", > }, > .cpuid_eax = 7, > @@ -3452,6 +3459,27 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, > } > break; > } > + case 0x14: { > + /* Intel Processor Trace Enumeration */ > + *eax = 0; > + *ebx = 0; > + *ecx = 0; > + *edx = 0; > + if (!(env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) || > + !kvm_enabled()) { > + break; > + } > + > + if (count == 0) { > + *eax = INTLE_PT_MAX_SUBLEAF; > + *ebx = INTEL_PT_MINIMAL_EBX; > + *ecx = INTEL_PT_MINIMAL_ECX; > + } else if (count == 1) { > + *eax = INTEL_PT_MTC_BITMAP | INTLE_PT_ADDR_RANGES_NUM; > + *ebx = INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP; > + } > + break; > + } > case 0x40000000: > /* > * CPUID code in kvm_arch_init_vcpu() ignores stuff > @@ -4082,6 +4110,27 @@ static int x86_cpu_filter_features(X86CPU *cpu) > } > } > > + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { What if the accelerator is not KVM, but is reporting intel-pt as supported? > + KVMState *s = CPU(cpu)->kvm_state; > + uint32_t eax_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EAX); > + uint32_t ebx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EBX); > + uint32_t ecx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_ECX); > + uint32_t eax_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EAX); > + uint32_t ebx_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EBX); > + > + if (!eax_0 || OK. > + ((ebx_0 & INTEL_PT_MINIMAL_EBX) != INTEL_PT_MINIMAL_EBX) || How do we know if KVM is going to emulate #GP properly when setting a bit that is supported by the host CPU but cleared on the guest CPUID? Do we care? > + ((ecx_0 & INTEL_PT_MINIMAL_ECX) != INTEL_PT_MINIMAL_ECX) || Same comment as above. Also: bit 31 must match the host, meaning we must reject a host where ecx_0 & (1 << 31) is set. > + ((eax_1 & (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) != > + (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) || This will make the code accept hosts with 3 address ranges (0b011), but reject ones with 4 address ranges (0b100). This doesn't sound right to me. > + ((ebx_1 & (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) != > + (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP))) { How do we know if KVM is going to emulate #GP properly when setting an invalid CycThresh or PSBFreq value? Do we care? > + env->features[FEAT_7_0_EBX] &= ~CPUID_7_0_EBX_INTEL_PT; > + cpu->filtered_features[FEAT_7_0_EBX] |= CPUID_7_0_EBX_INTEL_PT; This matches what I have suggested. But I recommend adding a comment mentioning why we do this. Something like: /* * Processor Trace capabilities aren't configurable, so if the * host can't emulate the capabilities we report on * cpu_x86_cpuid(), intel-pt can't be enabled on the current host. */ > + rv = 1; > + } > + } > + > return rv; > } > > diff --git a/target/i386/cpu.h b/target/i386/cpu.h > index f91e37d..7facc8b 100644 > --- a/target/i386/cpu.h > +++ b/target/i386/cpu.h > @@ -644,6 +644,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS]; > #define CPUID_7_0_EBX_PCOMMIT (1U << 22) /* Persistent Commit */ > #define CPUID_7_0_EBX_CLFLUSHOPT (1U << 23) /* Flush a Cache Line Optimized */ > #define CPUID_7_0_EBX_CLWB (1U << 24) /* Cache Line Write Back */ > +#define CPUID_7_0_EBX_INTEL_PT (1U << 25) /* Intel Processor Trace */ > #define CPUID_7_0_EBX_AVX512PF (1U << 26) /* AVX-512 Prefetch */ > #define CPUID_7_0_EBX_AVX512ER (1U << 27) /* AVX-512 Exponential and Reciprocal */ > #define CPUID_7_0_EBX_AVX512CD (1U << 28) /* AVX-512 Conflict Detection */ > diff --git a/target/i386/kvm.c b/target/i386/kvm.c > index ad4b159..f9f4cd1 100644 > --- a/target/i386/kvm.c > +++ b/target/i386/kvm.c > @@ -865,6 +865,29 @@ int kvm_arch_init_vcpu(CPUState *cs) > c = &cpuid_data.entries[cpuid_i++]; > } > break; > + case 0x14: { > + uint32_t times; > + > + c->function = i; > + c->index = 0; > + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; > + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); > + times = c->eax; > + > + for (j = 1; j <= times; ++j) { > + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { > + fprintf(stderr, "cpuid_data is full, no space for " > + "cpuid(eax:0x14,ecx:0x%x)\n", j); > + abort(); > + } > + c = &cpuid_data.entries[cpuid_i++]; > + c->function = i; > + c->index = j; > + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; > + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); > + } > + break; > + } > default: > c->function = i; > c->flags = 0; > -- > 1.8.3.1 > > -- Eduardo ^ permalink raw reply [flat|nested] 5+ messages in thread
* RE: [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support 2018-02-07 14:53 ` [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Eduardo Habkost @ 2018-02-08 1:24 ` Kang, Luwei 2018-02-08 18:23 ` Eduardo Habkost 0 siblings, 1 reply; 5+ messages in thread From: Kang, Luwei @ 2018-02-08 1:24 UTC (permalink / raw) To: Eduardo Habkost Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, mtosatti@redhat.com, Chao Peng, pbonzini@redhat.com, rth@twiddle.net > On Wed, Jan 31, 2018 at 11:57:45PM +0800, Luwei Kang wrote: > > From: Chao Peng <chao.p.peng@linux.intel.com> > > > > Expose Intel Processor Trace feature to guest. > > > > To make Intel PT live migration safe and get same CPUID information > > with same CPU model on diffrent host. CPUID[14] is constant in this > > patch. Intel PT use EPT is first supported in IceLake, the CPUID[14] > > get on this machine as default value. Intel PT would be disabled If > > any machine don't support this minial feature list. > > > > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > > Signed-off-by: Luwei Kang <luwei.kang@intel.com> > > --- > > target/i386/cpu.c | 53 > > +++++++++++++++++++++++++++++++++++++++++++++++++++-- > > target/i386/cpu.h | 1 + > > target/i386/kvm.c | 23 +++++++++++++++++++++++ > > 3 files changed, 75 insertions(+), 2 deletions(-) > > > > diff --git a/target/i386/cpu.c b/target/i386/cpu.c index > > a49d222..aaa427a 100644 > > --- a/target/i386/cpu.c > > +++ b/target/i386/cpu.c > > @@ -172,7 +172,14 @@ > > #define L2_ITLB_4K_ASSOC 4 > > #define L2_ITLB_4K_ENTRIES 512 > > > > - > > +/* CPUID Leaf 0x14 constants: */ > > +#define INTLE_PT_MAX_SUBLEAF 0x1 > > Typo. > > > +#define INTEL_PT_MINIMAL_EBX 0xf > > +#define INTEL_PT_MINIMAL_ECX 0x7 > > I suggest documenting what capabilities are included in > INTEL_PT_MINIMAL_* here. > > > > +#define INTLE_PT_ADDR_RANGES_NUM 0x2 /* Number of configurable > > +address ranges */ > > Typo. > > > +#define INTEL_PT_MTC_BITMAP (0x0249 << 16) /* Support ART(0,3,6,9) */ > > +#define INTEL_PT_CYCLE_BITMAP 0x1fff /* Support 0,2^(0~11) */ > > +#define INTEL_PT_PSB_BITMAP (0x003f << 16) /* Support 2K,4K,8K,16K,32K,64K */ > > > > static void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, > > uint32_t vendor2, uint32_t > > vendor3) @@ -427,7 +434,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = { > > NULL, NULL, "mpx", NULL, > > "avx512f", "avx512dq", "rdseed", "adx", > > "smap", "avx512ifma", "pcommit", "clflushopt", > > - "clwb", NULL, "avx512pf", "avx512er", > > + "clwb", "intel-pt", "avx512pf", "avx512er", > > "avx512cd", "sha-ni", "avx512bw", "avx512vl", > > }, > > .cpuid_eax = 7, > > @@ -3452,6 +3459,27 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, > > } > > break; > > } > > + case 0x14: { > > + /* Intel Processor Trace Enumeration */ > > + *eax = 0; > > + *ebx = 0; > > + *ecx = 0; > > + *edx = 0; > > + if (!(env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) || > > + !kvm_enabled()) { > > + break; > > + } > > + > > + if (count == 0) { > > + *eax = INTLE_PT_MAX_SUBLEAF; > > + *ebx = INTEL_PT_MINIMAL_EBX; > > + *ecx = INTEL_PT_MINIMAL_ECX; > > + } else if (count == 1) { > > + *eax = INTEL_PT_MTC_BITMAP | INTLE_PT_ADDR_RANGES_NUM; > > + *ebx = INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP; > > + } > > + break; > > + } > > case 0x40000000: > > /* > > * CPUID code in kvm_arch_init_vcpu() ignores stuff @@ > > -4082,6 +4110,27 @@ static int x86_cpu_filter_features(X86CPU *cpu) > > } > > } > > > > + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { > > What if the accelerator is not KVM, but is reporting intel-pt as supported? I have add this check in cpu_x86_cpuid() but I think we'd better add kvm_enabled() check here as well. What is your opinion? > > > + KVMState *s = CPU(cpu)->kvm_state; > > + uint32_t eax_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EAX); > > + uint32_t ebx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EBX); > > + uint32_t ecx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_ECX); > > + uint32_t eax_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EAX); > > + uint32_t ebx_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, > > + R_EBX); > > + > > + if (!eax_0 || > > OK. > > > + ((ebx_0 & INTEL_PT_MINIMAL_EBX) != INTEL_PT_MINIMAL_EBX) > > + || > > How do we know if KVM is going to emulate #GP properly when setting a bit that is supported by the host CPU but cleared on the > guest CPUID? Do we care? I think it need KVM make this check and Qemu don't need aware this. For example, EBX[0].CR3_filter (IA32_RTIT_CTL.cr3 can't be set if 0) is support by host but we mask off this bit in kvm guest. Qemu will set the CPUID to KVM by ioctl KVM_SET_CPUID2. KVM will trap the behavior when KVM guest want to set IA32_RTIT_CTL.cr3. If we find EBX[0].CR3_filter is not supported a #GP will be emulated. This check will added in KVM patch set V5 and it still working in progress. > > > + ((ecx_0 & INTEL_PT_MINIMAL_ECX) != INTEL_PT_MINIMAL_ECX) > > + || > > Same comment as above. > > Also: bit 31 must match the host, meaning we must reject a host where ecx_0 & (1 << 31) is set. Get it, will add in next version. > > > > + ((eax_1 & (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) != > > + (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) || > > This will make the code accept hosts with 3 address ranges (0b011), but reject ones with 4 address ranges (0b100). This doesn't > sound right to me. I see, will fix it. > > > > + ((ebx_1 & (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) != > > + (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP))) { > > How do we know if KVM is going to emulate #GP properly when setting an invalid CycThresh or PSBFreq value? Do we care? It will check in KVM and will emulate a #GP if set an invalid value but I think qemu can't aware this. >From my point of view, I think qemu don't need to care or get this information. > > > > + env->features[FEAT_7_0_EBX] &= ~CPUID_7_0_EBX_INTEL_PT; > > + cpu->filtered_features[FEAT_7_0_EBX] |= > > + CPUID_7_0_EBX_INTEL_PT; > > This matches what I have suggested. But I recommend adding a comment mentioning why we do this. Something like: > > /* > * Processor Trace capabilities aren't configurable, so if the > * host can't emulate the capabilities we report on > * cpu_x86_cpuid(), intel-pt can't be enabled on the current host. > */ Agree. Thanks a lot for the code review. Luwei Kang > > > > + rv = 1; > > + } > > + } > > + > > return rv; > > } > > > > diff --git a/target/i386/cpu.h b/target/i386/cpu.h index > > f91e37d..7facc8b 100644 > > --- a/target/i386/cpu.h > > +++ b/target/i386/cpu.h > > @@ -644,6 +644,7 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS]; > > #define CPUID_7_0_EBX_PCOMMIT (1U << 22) /* Persistent Commit */ > > #define CPUID_7_0_EBX_CLFLUSHOPT (1U << 23) /* Flush a Cache Line Optimized */ > > #define CPUID_7_0_EBX_CLWB (1U << 24) /* Cache Line Write Back */ > > +#define CPUID_7_0_EBX_INTEL_PT (1U << 25) /* Intel Processor Trace */ > > #define CPUID_7_0_EBX_AVX512PF (1U << 26) /* AVX-512 Prefetch */ > > #define CPUID_7_0_EBX_AVX512ER (1U << 27) /* AVX-512 Exponential and > > Reciprocal */ #define CPUID_7_0_EBX_AVX512CD (1U << 28) /* AVX-512 > > Conflict Detection */ diff --git a/target/i386/kvm.c > > b/target/i386/kvm.c index ad4b159..f9f4cd1 100644 > > --- a/target/i386/kvm.c > > +++ b/target/i386/kvm.c > > @@ -865,6 +865,29 @@ int kvm_arch_init_vcpu(CPUState *cs) > > c = &cpuid_data.entries[cpuid_i++]; > > } > > break; > > + case 0x14: { > > + uint32_t times; > > + > > + c->function = i; > > + c->index = 0; > > + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; > > + cpu_x86_cpuid(env, i, 0, &c->eax, &c->ebx, &c->ecx, &c->edx); > > + times = c->eax; > > + > > + for (j = 1; j <= times; ++j) { > > + if (cpuid_i == KVM_MAX_CPUID_ENTRIES) { > > + fprintf(stderr, "cpuid_data is full, no space for " > > + "cpuid(eax:0x14,ecx:0x%x)\n", j); > > + abort(); > > + } > > + c = &cpuid_data.entries[cpuid_i++]; > > + c->function = i; > > + c->index = j; > > + c->flags = KVM_CPUID_FLAG_SIGNIFCANT_INDEX; > > + cpu_x86_cpuid(env, i, j, &c->eax, &c->ebx, &c->ecx, &c->edx); > > + } > > + break; > > + } > > default: > > c->function = i; > > c->flags = 0; > > -- > > 1.8.3.1 > > > > > > -- > Eduardo ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support 2018-02-08 1:24 ` Kang, Luwei @ 2018-02-08 18:23 ` Eduardo Habkost 0 siblings, 0 replies; 5+ messages in thread From: Eduardo Habkost @ 2018-02-08 18:23 UTC (permalink / raw) To: Kang, Luwei Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org, mtosatti@redhat.com, Chao Peng, pbonzini@redhat.com, rth@twiddle.net On Thu, Feb 08, 2018 at 01:24:46AM +0000, Kang, Luwei wrote: > > On Wed, Jan 31, 2018 at 11:57:45PM +0800, Luwei Kang wrote: > > > From: Chao Peng <chao.p.peng@linux.intel.com> > > > > > > Expose Intel Processor Trace feature to guest. > > > > > > To make Intel PT live migration safe and get same CPUID information > > > with same CPU model on diffrent host. CPUID[14] is constant in this > > > patch. Intel PT use EPT is first supported in IceLake, the CPUID[14] > > > get on this machine as default value. Intel PT would be disabled If > > > any machine don't support this minial feature list. > > > > > > Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com> > > > Signed-off-by: Luwei Kang <luwei.kang@intel.com> > > > --- > > > target/i386/cpu.c | 53 > > > +++++++++++++++++++++++++++++++++++++++++++++++++++-- > > > target/i386/cpu.h | 1 + > > > target/i386/kvm.c | 23 +++++++++++++++++++++++ > > > 3 files changed, 75 insertions(+), 2 deletions(-) > > > > > > diff --git a/target/i386/cpu.c b/target/i386/cpu.c index > > > a49d222..aaa427a 100644 > > > --- a/target/i386/cpu.c > > > +++ b/target/i386/cpu.c > > > @@ -172,7 +172,14 @@ > > > #define L2_ITLB_4K_ASSOC 4 > > > #define L2_ITLB_4K_ENTRIES 512 > > > > > > - > > > +/* CPUID Leaf 0x14 constants: */ > > > +#define INTLE_PT_MAX_SUBLEAF 0x1 > > > > Typo. > > > > > +#define INTEL_PT_MINIMAL_EBX 0xf > > > +#define INTEL_PT_MINIMAL_ECX 0x7 > > > > I suggest documenting what capabilities are included in > > INTEL_PT_MINIMAL_* here. > > > > > > > +#define INTLE_PT_ADDR_RANGES_NUM 0x2 /* Number of configurable > > > +address ranges */ > > > > Typo. > > > > > +#define INTEL_PT_MTC_BITMAP (0x0249 << 16) /* Support ART(0,3,6,9) */ > > > +#define INTEL_PT_CYCLE_BITMAP 0x1fff /* Support 0,2^(0~11) */ > > > +#define INTEL_PT_PSB_BITMAP (0x003f << 16) /* Support 2K,4K,8K,16K,32K,64K */ > > > > > > static void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, > > > uint32_t vendor2, uint32_t > > > vendor3) @@ -427,7 +434,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = { > > > NULL, NULL, "mpx", NULL, > > > "avx512f", "avx512dq", "rdseed", "adx", > > > "smap", "avx512ifma", "pcommit", "clflushopt", > > > - "clwb", NULL, "avx512pf", "avx512er", > > > + "clwb", "intel-pt", "avx512pf", "avx512er", > > > "avx512cd", "sha-ni", "avx512bw", "avx512vl", > > > }, > > > .cpuid_eax = 7, > > > @@ -3452,6 +3459,27 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, > > > } > > > break; > > > } > > > + case 0x14: { > > > + /* Intel Processor Trace Enumeration */ > > > + *eax = 0; > > > + *ebx = 0; > > > + *ecx = 0; > > > + *edx = 0; > > > + if (!(env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) || > > > + !kvm_enabled()) { > > > + break; > > > + } > > > + > > > + if (count == 0) { > > > + *eax = INTLE_PT_MAX_SUBLEAF; > > > + *ebx = INTEL_PT_MINIMAL_EBX; > > > + *ecx = INTEL_PT_MINIMAL_ECX; > > > + } else if (count == 1) { > > > + *eax = INTEL_PT_MTC_BITMAP | INTLE_PT_ADDR_RANGES_NUM; > > > + *ebx = INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP; > > > + } > > > + break; > > > + } > > > case 0x40000000: > > > /* > > > * CPUID code in kvm_arch_init_vcpu() ignores stuff @@ > > > -4082,6 +4110,27 @@ static int x86_cpu_filter_features(X86CPU *cpu) > > > } > > > } > > > > > > + if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { > > > > What if the accelerator is not KVM, but is reporting intel-pt as supported? > > I have add this check in cpu_x86_cpuid() but I think we'd better add kvm_enabled() check here as well. > What is your opinion? The function is going to crash if KVM is not enabled and the accelerator returns intel-pt is supported, as cpu->kvm_state will be NULL. > > > > > > + KVMState *s = CPU(cpu)->kvm_state; > > > + uint32_t eax_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EAX); > > > + uint32_t ebx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_EBX); > > > + uint32_t ecx_0 = kvm_arch_get_supported_cpuid(s, 0x14, 0, R_ECX); > > > + uint32_t eax_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, R_EAX); > > > + uint32_t ebx_1 = kvm_arch_get_supported_cpuid(s, 0x14, 1, > > > + R_EBX); > > > + > > > + if (!eax_0 || > > > > OK. > > > > > + ((ebx_0 & INTEL_PT_MINIMAL_EBX) != INTEL_PT_MINIMAL_EBX) > > > + || > > > > How do we know if KVM is going to emulate #GP properly when > > setting a bit that is supported by the host CPU but cleared > > on the guest CPUID? Do we care? > > I think it need KVM make this check and Qemu don't need aware > this. > For example, EBX[0].CR3_filter (IA32_RTIT_CTL.cr3 can't be set > if 0) is support by host but we mask off this bit in kvm guest. > Qemu will set the CPUID to KVM by ioctl KVM_SET_CPUID2. KVM > will trap the behavior when KVM guest want to set > IA32_RTIT_CTL.cr3. If we find EBX[0].CR3_filter is not > supported a #GP will be emulated. This check will added in KVM > patch set V5 and it still working in progress. I was assuming there would be released Linux versions where this wasn't implemented yet. If nothing was merged yet, we should be safe. > > > > > > + ((ecx_0 & INTEL_PT_MINIMAL_ECX) != INTEL_PT_MINIMAL_ECX) > > > + || > > > > Same comment as above. > > > > Also: bit 31 must match the host, meaning we must reject a > > host where ecx_0 & (1 << 31) is set. > > Get it, will add in next version. > > > > > > > > + ((eax_1 & (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) != > > > + (INTLE_PT_ADDR_RANGES_NUM | INTEL_PT_MTC_BITMAP)) || > > > > This will make the code accept hosts with 3 address ranges > > (0b011), but reject ones with 4 address ranges (0b100). This > > doesn't sound right to me. > > I see, will fix it. > > > > > > > > + ((ebx_1 & (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP)) != > > > + (INTEL_PT_PSB_BITMAP | INTEL_PT_CYCLE_BITMAP))) { > > > > How do we know if KVM is going to emulate #GP properly when > > setting an invalid CycThresh or PSBFreq value? Do we care? > > It will check in KVM and will emulate a #GP if set an invalid > value but I think qemu can't aware this. From my point of > view, I think qemu don't need to care or get this information. If all KVM versions that return 0x14 on GET_SUPPORTED_CPUID will emulate #GP properly, this will be OK. -- Eduardo ^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2018-02-08 18:23 UTC | newest] Thread overview: 5+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2018-01-31 15:57 [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Luwei Kang 2018-01-31 15:57 ` [PATCH v3 2/2] i386: Add support to get/set/migrate Intel Processor Trace feature Luwei Kang 2018-02-07 14:53 ` [Qemu-devel] [PATCH v3 1/2] i386: Add Intel Processor Trace feature support Eduardo Habkost 2018-02-08 1:24 ` Kang, Luwei 2018-02-08 18:23 ` Eduardo Habkost
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox