target/i386: add support for FRED
cover target/i386: add support for FRED
This patch set adds support for the Intel flexible return and event delivery (FRED) architecture to allow Qemu to run KVM guests with FRED enabled.
The FRED architecture defines simple new transitions that change privilege level (ring transitions). The FRED architecture was designed with the following goals:
1) Improve overall performance and response time by replacing event delivery through the interrupt descriptor table (IDT event delivery) and event return by the IRET instruction with lower latency transitions.
2) Improve software robustness by ensuring that event delivery establishes the full supervisor context and that event return establishes the full user context.
Search for the latest FRED spec in most search engines with this search pattern:
site:intel.com FRED (flexible return and event delivery) specification
Xin Li (4):
target/i386: add support for FRED in CPUID enumeration target/i386: mark CR4.FRED not reserved target/i386: enumerate VMX nested-exception support target/i386: add live migration support for FRED
target/i386/cpu.c | 7 +++++- target/i386/cpu.h | 40 +++++++++++++++++++++++++++++++- target/i386/kvm/kvm.c | 54 +++++++++++++++++++++++++++++++++++++++++++ target/i386/machine.c | 10 ++++++++ 4 files changed, 109 insertions(+), 2 deletions(-)
Signature · 1 line
2.34.1
PATCH 1/4 target/i386: add support for FRED in CPUID enumeration
FRED, i.e., the Intel flexible return and event delivery architecture, defines simple new transitions that change privilege level (ring transitions).
In addition to these transitions, the FRED architecture defines a new instruction (LKGS) for managing the state of the GS segment register. The LKGS instruction can be used by 64-bit operating systems that do not use the new FRED transitions.
The CPUID feature flag CPUID.(EAX=7,ECX=1):EAX[17] enumerates FRED, and the CPUID feature flag CPUID.(EAX=7,ECX=1):EAX[18] enumerates LKGS.
Add CPUID definitions for FRED/LKGS, and expose them to KVM guests only.
Because FRED relies on LKGS, add it to feature dependency map.
--- target/i386/cpu.c | 6 +++++- target/i386/cpu.h | 4 ++++ 2 files changed, 9 insertions(+), 1 deletion(-)
target/i386/cpu.c +5 -1
@@ -963,7 +963,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {"avx-vnni" ,"avx512-bf16" ,NULL ,"cmpccxadd" ,NULL ,NULL ,"fzrm" ,"fsrs" ,"fsrc" ,NULL ,NULL ,NULL , -NULL ,NULL ,NULL ,NULL , +NULL ,"fred" ,"lkgs" ,NULL ,NULL ,"amx-fp16" ,NULL ,"avx-ifma" ,NULL ,NULL ,NULL ,NULL , NULL, NULL, NULL, NULL,
@@ -1549,6 +1549,10 @@ static FeatureDep feature_dependencies[] = { .from = { FEAT_VMX_SECONDARY_CTLS, VMX_SECONDARY_EXEC_ENABLE_USER_WAIT_PAUSE }, .to = { FEAT_7_0_ECX, CPUID_7_0_ECX_WAITPKG }, }, + { + .from = { FEAT_7_1_EAX, CPUID_7_1_EAX_LKGS }, + .to = { FEAT_7_1_EAX, CPUID_7_1_EAX_FRED }, + }, }; typedef struct X86RegisterInfo32 {
target/i386/cpu.h +4 -0
@@ -932,6 +932,10 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w,#define CPUID_7_1_EDX_AVX_NE_CONVERT (1U << 5)/* PREFETCHIT0/1 Instructions */ #define CPUID_7_1_EDX_PREFETCHITI (1U << 14) +/* Flexible return and event delivery (FRED) */ +#define CPUID_7_1_EAX_FRED (1U << 17) +/* Load into IA32_KERNEL_GS_BASE (LKGS) */ +#define CPUID_7_1_EAX_LKGS (1U << 18)/* Do not exhibit MXCSR Configuration Dependent Timing (MCDT) behavior */ #define CPUID_7_2_EDX_MCDT_NO (1U << 5)
Signature · 1 line
2.34.1
PATCH 2/4 target/i386: mark CR4.FRED not reserved
In reply to Xin LiThe CR4.FRED bit, i.e., CR4[32], is no longer a reserved bit when FRED is exposed to guests, otherwise it is still a reserved bit.
--- target/i386/cpu.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)
target/i386/cpu.h +11 -1
@@ -262,6 +262,12 @@ typedef enum X86Seg {#define CR4_PKE_MASK (1U << 22)#define CR4_PKS_MASK (1U << 24) +#ifdef TARGET_X86_64 +#define CR4_FRED_MASK (1ULL << 32) +#else +#define CR4_FRED_MASK 0 +#endif +#define CR4_RESERVED_MASK \ (~(target_ulong)(CR4_VME_MASK | CR4_PVI_MASK | CR4_TSD_MASK \ | CR4_DE_MASK | CR4_PSE_MASK | CR4_PAE_MASK \
@@ -269,7 +275,8 @@ typedef enum X86Seg { | CR4_OSFXSR_MASK | CR4_OSXMMEXCPT_MASK | CR4_UMIP_MASK \ | CR4_LA57_MASK \ | CR4_FSGSBASE_MASK | CR4_PCIDE_MASK | CR4_OSXSAVE_MASK \ - | CR4_SMEP_MASK | CR4_SMAP_MASK | CR4_PKE_MASK | CR4_PKS_MASK)) + | CR4_SMEP_MASK | CR4_SMAP_MASK | CR4_PKE_MASK | CR4_PKS_MASK \ + | CR4_FRED_MASK))#define DR6_BD (1 << 13)#define DR6_BS (1 << 14)
@@ -2481,6 +2488,9 @@ static inline uint64_t cr4_reserved_bits(CPUX86State *env)if (!(env->features[FEAT_7_0_ECX ] &CPUID_7_0_ECX_PKS )) { reserved_bits |=CR4_PKS_MASK ; } +if (!(env->features[FEAT_7_1_EAX ] &CPUID_7_1_EAX_FRED )) { + reserved_bits |=CR4_FRED_MASK ; + }return reserved_bits; }
Signature · 1 line
2.34.1
PATCH 3/4 target/i386: enumerate VMX nested-exception support
In reply to Xin LiAllow VMX nested-exception support to be exposed in KVM guests, thus nested KVM guests can enumerate it.
--- target/i386/cpu.c | 1 + 1 file changed, 1 insertion(+)
target/i386/cpu.c +1 -0
@@ -1340,6 +1340,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .feat_names = { [54] = "vmx-ins-outs", [55] = "vmx-true-ctls", + [58] = "vmx-nested-exception", }, .msr = { .index = MSR_IA32_VMX_BASIC,
Signature · 1 line
2.34.1
Paolo Bonzini
maintainerRe: [PATCH 3/4] target/i386: enumerate VMX nested-exception support
Quoted 14 lines · Xin Li
Allow VMX nested-exception support to be exposed in KVM guests, thus nested KVM guests can enumerate it.
Tested-by Shan Kang <[email protected]>Signed-off-by Xin Li <[email protected]>--- target/i386/cpu.c | 1 + 1 file changed, 1 insertion(+)target/i386/cpu.c +0
-0
target/i386/cpu.c FeatureWordInfo feature_word_info[FEATURE_WORDS] = { · line 1346
Quoted 7 lines
target/i386/cpu.c +1
-0@@ -1340,6 +1340,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .feat_names = { [54] = "vmx-ins-outs", [55] = "vmx-true-ctls", + [58] = "vmx-nested-exception", }, .msr = { .index = MSR_IA32_VMX_BASIC,
Please also add it to scripts/kvm/vmxcap, and rebase on top of the recent introduction of MSR_VMX_BASIC_ANY_ERRCODE.
Paolo
PATCH 4/4 target/i386: add live migration support for FRED
In reply to Xin LiFRED CPU states are managed in 10 FRED MSRs, in addtion to a few existing CPU registers and MSRs, e.g., the CR4.FRED bit.
Add the 10 new FRED MSRs to x86 CPUArchState for live migration support.
--- target/i386/cpu.h | 24 +++++++++++++++++++ target/i386/kvm/kvm.c | 54 +++++++++++++++++++++++++++++++++++++++++++ target/i386/machine.c | 10 ++++++++ 3 files changed, 88 insertions(+)
target/i386/cpu.h +24 -0
@@ -529,6 +529,20 @@ typedef enum X86Seg {#define MSR_IA32_XFD 0x000001c4#define MSR_IA32_XFD_ERR 0x000001c5 +#define MSR_IA32_PL0_SSP 0x000006a4/* Stack level 0 shadow stack pointer in ring 0 */ + +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x000001cc/* Stack level 0 regular stack pointer */ +#define MSR_IA32_FRED_RSP1 0x000001cd/* Stack level 1 regular stack pointer */ +#define MSR_IA32_FRED_RSP2 0x000001ce/* Stack level 2 regular stack pointer */ +#define MSR_IA32_FRED_RSP3 0x000001cf/* Stack level 3 regular stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x000001d0/* FRED exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP/* Stack level 0 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_SSP1 0x000001d1/* Stack level 1 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_SSP2 0x000001d2/* Stack level 2 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_SSP3 0x000001d3/* Stack level 3 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_CONFIG 0x000001d4/* FRED Entrypoint and interrupt stack level */ +#define MSR_IA32_BNDCFGS 0x00000d90#define MSR_IA32_XSS 0x00000da0#define MSR_IA32_UMWAIT_CONTROL 0xe1
@@ -1680,6 +1694,16 @@ typedef struct CPUArchState {target_ulong cstar;target_ulong fmask;target_ulong kernelgsbase; +target_ulong fred_rsp0; +target_ulong fred_rsp1; +target_ulong fred_rsp2; +target_ulong fred_rsp3; +target_ulong fred_stklvls; +target_ulong fred_ssp0; +target_ulong fred_ssp1; +target_ulong fred_ssp2; +target_ulong fred_ssp3; +target_ulong fred_config;#endif uint64_t tsc_adjust;
target/i386/kvm/kvm.c +54 -0
72 lines not on this page · raw message
target/i386/machine.c +10 -0
@@ -1652,6 +1652,16 @@ const VMStateDescription vmstate_x86_cpu = {VMSTATE_UINT64 (env.cstar,X86CPU ),VMSTATE_UINT64 (env.fmask,X86CPU ),VMSTATE_UINT64 (env.kernelgsbase,X86CPU ), +VMSTATE_UINT64 (env.fred_rsp0,X86CPU ), +VMSTATE_UINT64 (env.fred_rsp1,X86CPU ), +VMSTATE_UINT64 (env.fred_rsp2,X86CPU ), +VMSTATE_UINT64 (env.fred_rsp3,X86CPU ), +VMSTATE_UINT64 (env.fred_stklvls,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp0,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp1,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp2,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp3,X86CPU ), +VMSTATE_UINT64 (env.fred_config,X86CPU ), #endif VMSTATE_UINT32(env.smbase, X86CPU),
Signature · 1 line
2.34.1
Re: [PATCH 4/4] target/i386: add live migration support for FRED
Quoted 145 lines · On 9/1/2023 1:30 PM, Li, Xin3 wrote:
FRED CPU states are managed in 10 FRED MSRs, in addtion to a few existing CPU registers and MSRs, e.g., the CR4.FRED bit.
Add the 10 new FRED MSRs to x86 CPUArchState for live migration support.
Tested-by Shan Kang <[email protected]>Signed-off-by Xin Li <[email protected]>--- target/i386/cpu.h | 24 +++++++++++++++++++ target/i386/kvm/kvm.c | 54 +++++++++++++++++++++++++++++++++++++++++++ target/i386/machine.c | 10 ++++++++ 3 files changed, 88 insertions(+)target/i386/cpu.h +24
-0@@ -529,6 +529,20 @@ typedef enum X86Seg {#define MSR_IA32_XFD 0x000001c4#define MSR_IA32_XFD_ERR 0x000001c5 +#define MSR_IA32_PL0_SSP 0x000006a4/* Stack level 0 shadow stack pointer in ring 0 */ + +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x000001cc/* Stack level 0 regular stack pointer */ +#define MSR_IA32_FRED_RSP1 0x000001cd/* Stack level 1 regular stack pointer */ +#define MSR_IA32_FRED_RSP2 0x000001ce/* Stack level 2 regular stack pointer */ +#define MSR_IA32_FRED_RSP3 0x000001cf/* Stack level 3 regular stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x000001d0/* FRED exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP/* Stack level 0 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_SSP1 0x000001d1/* Stack level 1 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_SSP2 0x000001d2/* Stack level 2 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_SSP3 0x000001d3/* Stack level 3 shadow stack pointer in ring 0 */ +#define MSR_IA32_FRED_CONFIG 0x000001d4/* FRED Entrypoint and interrupt stack level */ +#define MSR_IA32_BNDCFGS 0x00000d90#define MSR_IA32_XSS 0x00000da0#define MSR_IA32_UMWAIT_CONTROL 0xe1@@ -1680,6 +1694,16 @@ typedef struct CPUArchState {target_ulong cstar;target_ulong fmask;target_ulong kernelgsbase; +target_ulong fred_rsp0; +target_ulong fred_rsp1; +target_ulong fred_rsp2; +target_ulong fred_rsp3; +target_ulong fred_stklvls; +target_ulong fred_ssp0; +target_ulong fred_ssp1; +target_ulong fred_ssp2; +target_ulong fred_ssp3; +target_ulong fred_config;#endif uint64_t tsc_adjust;target/i386/kvm/kvm.c +54
-0@@ -3401,6 +3401,18 @@ static int kvm_put_msrs(X86CPU *cpu, int level)kvm_msr_entry_add (cpu,MSR_KERNELGSBASE , env->kernelgsbase);kvm_msr_entry_add (cpu,MSR_FMASK , env->fmask);kvm_msr_entry_add (cpu,MSR_LSTAR , env->lstar); +if (env->features[FEAT_7_1_EAX ] &CPUID_7_1_EAX_FRED ) { +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP0 , env->fred_rsp0); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP1 , env->fred_rsp1); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP2 , env->fred_rsp2); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP3 , env->fred_rsp3); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_STKLVLS , env->fred_stklvls); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP0 , env->fred_ssp0); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP1 , env->fred_ssp1); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP2 , env->fred_ssp2); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP3 , env->fred_ssp3); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_CONFIG , env->fred_config); + } }#endif @@ -3901,6 +3913,18 @@ static int kvm_get_msrs(X86CPU *cpu)kvm_msr_entry_add (cpu,MSR_KERNELGSBASE ,0 );kvm_msr_entry_add (cpu,MSR_FMASK ,0 );kvm_msr_entry_add (cpu,MSR_LSTAR ,0 ); +if (env->features[FEAT_7_1_EAX ] &CPUID_7_1_EAX_FRED ) { +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP0 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP1 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP2 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_RSP3 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_STKLVLS ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP0 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP1 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP2 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_SSP3 ,0 ); +kvm_msr_entry_add (cpu,MSR_IA32_FRED_CONFIG ,0 ); + } }#endif kvm_msr_entry_add (cpu,MSR_KVM_SYSTEM_TIME ,0 );@@ -4123,6 +4147,36 @@ static int kvm_get_msrs(X86CPU *cpu)case MSR_LSTAR : env->lstar = msrs[i].data;break ; +case MSR_IA32_FRED_RSP0 : + env->fred_rsp0 = msrs[i].data; +break ; +case MSR_IA32_FRED_RSP1 : + env->fred_rsp1 = msrs[i].data; +break ; +case MSR_IA32_FRED_RSP2 : + env->fred_rsp2 = msrs[i].data; +break ; +case MSR_IA32_FRED_RSP3 : + env->fred_rsp3 = msrs[i].data; +break ; +case MSR_IA32_FRED_STKLVLS : + env->fred_stklvls = msrs[i].data; +break ; +case MSR_IA32_FRED_SSP0 : + env->fred_ssp0 = msrs[i].data; +break ; +case MSR_IA32_FRED_SSP1 : + env->fred_ssp1 = msrs[i].data; +break ; +case MSR_IA32_FRED_SSP2 : + env->fred_ssp2 = msrs[i].data; +break ; +case MSR_IA32_FRED_SSP3 : + env->fred_ssp3 = msrs[i].data; +break ; +case MSR_IA32_FRED_CONFIG : + env->fred_config = msrs[i].data; +break ;#endif case MSR_IA32_TSC : env->tsc = msrs[i].data;target/i386/machine.c +3
-0@@ -1652,6 +1652,16 @@ const VMStateDescription vmstate_x86_cpu = {VMSTATE_UINT64 (env.cstar,X86CPU ),VMSTATE_UINT64 (env.fmask,X86CPU ),VMSTATE_UINT64 (env.kernelgsbase,X86CPU ), +VMSTATE_UINT64 (env.fred_rsp0,X86CPU ), +VMSTATE_UINT64 (env.fred_rsp1,X86CPU ), + VMSTATE_UINT64(env.fred_rsp2, X86CPU),
target/i386/machine.c const VMStateDescription vmstate_x86_cpu = { · line 1667
Quoted 10 lines
target/i386/machine.c +7
-0+VMSTATE_UINT64 (env.fred_rsp3,X86CPU ), +VMSTATE_UINT64 (env.fred_stklvls,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp0,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp1,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp2,X86CPU ), +VMSTATE_UINT64 (env.fred_ssp3,X86CPU ), +VMSTATE_UINT64 (env.fred_config,X86CPU ), #endif VMSTATE_UINT32(env.smbase, X86CPU),
IMO, it's better to split this patch into two, one is for FRED MSR access, the other is for LM support.
And move the FRED MSRs from basic x86_cpu part to .subsections part because FRED doesn't belong to basic CPU registers. In the .subsections part, you may define a struct to hold FRED MSRs then add .needed callback helper for QEMU to query whether FRED MSRs are necessary for live migration.
See other features, e.g., vmstate_msr_intel_sgx
RE: [PATCH 4/4] target/i386: add live migration support for FRED
Quoted 6 lines
Quoted 5 lines
FRED CPU states are managed in 10 FRED MSRs, in addtion to a few existing CPU registers and MSRs, e.g., the CR4.FRED bit.
Add the 10 new FRED MSRs to x86 CPUArchState for live migration support.
Quoted 7 lines
IMO, it's better to split this patch into two, one is for FRED MSR access, the other is for LM support.
And move the FRED MSRs from basic
x86_cpupart to .subsections part because FRED doesn't belong to basic CPU registers. In the .subsections part, you may define a struct to hold FRED MSRs then add .needed callback helper for QEMU to query whether FRED MSRs are necessary for live migration.
Good point!
Quoted 2 lines
See other features, e.g.,
vmstate_msr_intel_sgx