Support protection keys in an AMD EPYC-Milan VM
cover Support protection keys in an AMD EPYC-Milan VM
AMD EPYC-Milan CPUs introduced support for protection keys, previously available only with Intel CPUs.
AMD chose to place the XSAVE state component for the protection keys at a different offset in the XSAVE state area than that chosen by Intel.
To accommodate this, modify QEMU to behave appropriately on AMD systems, allowing a VM to properly take advantage of the new feature.
Further, avoid manipulating XSAVE state components that are not present on AMD systems.
The code in patch 6 that changes the CPUID 0x0d leaf is mostly dumped somewhere that seemed to work - I'm not sure where it really belongs.
David Edmondson (7):
target/i386: Declare constants for XSAVE offsets target/i386: Use constants for XSAVE offsets target/i386: Clarify the padding requirements of X86XSaveArea target/i386: Prepare for per-vendor X86XSaveArea layout target/i386: Introduce AMD X86XSaveArea sub-union target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf 0xd target/i386: Manipulate only AMD XSAVE state on AMD
target/i386/cpu.c | 19 +++++---- target/i386/cpu.h | 80 ++++++++++++++++++++++++++++-------- target/i386/kvm/kvm.c | 57 +++++++++---------------- target/i386/tcg/fpu_helper.c | 20 ++++++--- target/i386/xsave_helper.c | 70 +++++++++++++++++++------------ 5 files changed, 152 insertions(+), 94 deletions(-)
Signature · 1 line
2.30.2
RFC PATCH 1/7 target/i386: Declare constants for XSAVE offsets
Declare and use manifest constants for the XSAVE state component offsets.
--- target/i386/cpu.h | 30 +++++++++++++++++++++++------- 1 file changed, 23 insertions(+), 7 deletions(-)
target/i386/cpu.h +23 -7
@@ -1305,6 +1305,22 @@ typedef struct XSavePKRU {uint32_t padding; } XSavePKRU; +#define XSAVE_FCW_FSW_OFFSET 0x000 +#define XSAVE_FTW_FOP_OFFSET 0x004 +#define XSAVE_CWD_RIP_OFFSET 0x008 +#define XSAVE_CWD_RDP_OFFSET 0x010 +#define XSAVE_MXCSR_OFFSET 0x018 +#define XSAVE_ST_SPACE_OFFSET 0x020 +#define XSAVE_XMM_SPACE_OFFSET 0x0a0 +#define XSAVE_XSTATE_BV_OFFSET 0x200 +#define XSAVE_AVX_OFFSET 0x240 +#define XSAVE_BNDREG_OFFSET 0x3c0 +#define XSAVE_BNDCSR_OFFSET 0x400 +#define XSAVE_OPMASK_OFFSET 0x440 +#define XSAVE_ZMM_HI256_OFFSET 0x480 +#define XSAVE_HI16_ZMM_OFFSET 0x680 +#define XSAVE_PKRU_OFFSET 0xa80 + typedef struct X86XSaveArea { X86LegacyXSaveArea legacy; X86XSaveHeader header;
@@ -1325,19 +1341,19 @@ typedef struct X86XSaveArea {XSavePKRU pkru_state; } X86XSaveArea; -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , avx_state) !=0x240 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , avx_state) !=XSAVE_AVX_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSaveAVX) !=0x100 ); -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , bndreg_state) !=0x3c0 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , bndreg_state) !=XSAVE_BNDREG_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSaveBNDREG) !=0x40 ); -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , bndcsr_state) !=0x400 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , bndcsr_state) !=XSAVE_BNDCSR_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSaveBNDCSR) !=0x40 ); -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , opmask_state) !=0x440 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , opmask_state) !=XSAVE_OPMASK_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSaveOpmask) !=0x40 ); -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , zmm_hi256_state) !=0x480 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , zmm_hi256_state) !=XSAVE_ZMM_HI256_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSaveZMM_Hi256) !=0x200 ); -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , hi16_zmm_state) !=0x680 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , hi16_zmm_state) !=XSAVE_HI16_ZMM_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSaveHi16_ZMM) !=0x400 ); -QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , pkru_state) !=0xA80 ); +QEMU_BUILD_BUG_ON (offsetof(X86XSaveArea , pkru_state) !=XSAVE_PKRU_OFFSET );QEMU_BUILD_BUG_ON (sizeof (XSavePKRU) !=0x8 ); typedef enum TPRAccess {
Signature · 1 line
2.30.2
RFC PATCH 2/7 target/i386: Use constants for XSAVE offsets
In reply to David EdmondsonWhere existing constants for XSAVE offsets exists, use them.
--- target/i386/kvm/kvm.c | 56 ++++++++++++++----------------------------- 1 file changed, 18 insertions(+), 38 deletions(-)
target/i386/kvm/kvm.c +18 -38
@@ -2397,44 +2397,24 @@ static int kvm_put_fpu(X86CPU *cpu)return kvm_vcpu_ioctl (CPU (cpu),KVM_SET_FPU , &fpu); } -#define XSAVE_FCW_FSW 0 -#define XSAVE_FTW_FOP 1 -#define XSAVE_CWD_RIP 2 -#define XSAVE_CWD_RDP 4 -#define XSAVE_MXCSR 6 -#define XSAVE_ST_SPACE 8 -#define XSAVE_XMM_SPACE 40 -#define XSAVE_XSTATE_BV 128 -#define XSAVE_YMMH_SPACE 144 -#define XSAVE_BNDREGS 240 -#define XSAVE_BNDCSR 256 -#define XSAVE_OPMASK 272 -#define XSAVE_ZMM_Hi256 288 -#define XSAVE_Hi16_ZMM 416 -#define XSAVE_PKRU 672 - -#define XSAVE_BYTE_OFFSET (word_offset) \ - ((word_offset) * sizeof_field(struct kvm_xsave, region[0])) - -#define ASSERT_OFFSET (word_offset, field) \ - QEMU_BUILD_BUG_ON(XSAVE_BYTE_OFFSET(word_offset) != \ - offsetof(X86XSaveArea, field)) - -ASSERT_OFFSET (XSAVE_FCW_FSW , legacy.fcw); -ASSERT_OFFSET (XSAVE_FTW_FOP , legacy.ftw); -ASSERT_OFFSET (XSAVE_CWD_RIP , legacy.fpip); -ASSERT_OFFSET (XSAVE_CWD_RDP , legacy.fpdp); -ASSERT_OFFSET (XSAVE_MXCSR , legacy.mxcsr); -ASSERT_OFFSET (XSAVE_ST_SPACE , legacy.fpregs); -ASSERT_OFFSET (XSAVE_XMM_SPACE , legacy.xmm_regs); -ASSERT_OFFSET (XSAVE_XSTATE_BV , header.xstate_bv); -ASSERT_OFFSET (XSAVE_YMMH_SPACE , avx_state); -ASSERT_OFFSET (XSAVE_BNDREGS , bndreg_state); -ASSERT_OFFSET (XSAVE_BNDCSR , bndcsr_state); -ASSERT_OFFSET (XSAVE_OPMASK , opmask_state); -ASSERT_OFFSET (XSAVE_ZMM_Hi256, zmm_hi256_state); -ASSERT_OFFSET (XSAVE_Hi16_ZMM, hi16_zmm_state); -ASSERT_OFFSET (XSAVE_PKRU , pkru_state); +#define ASSERT_OFFSET (offset, field) \ + QEMU_BUILD_BUG_ON(offset != offsetof(X86XSaveArea, field)) + +ASSERT_OFFSET (XSAVE_FCW_FSW_OFFSET , legacy.fcw); +ASSERT_OFFSET (XSAVE_FTW_FOP_OFFSET , legacy.ftw); +ASSERT_OFFSET (XSAVE_CWD_RIP_OFFSET , legacy.fpip); +ASSERT_OFFSET (XSAVE_CWD_RDP_OFFSET , legacy.fpdp); +ASSERT_OFFSET (XSAVE_MXCSR_OFFSET , legacy.mxcsr); +ASSERT_OFFSET (XSAVE_ST_SPACE_OFFSET , legacy.fpregs); +ASSERT_OFFSET (XSAVE_XMM_SPACE_OFFSET , legacy.xmm_regs); +ASSERT_OFFSET (XSAVE_XSTATE_BV_OFFSET , header.xstate_bv); +ASSERT_OFFSET (XSAVE_AVX_OFFSET , avx_state); +ASSERT_OFFSET (XSAVE_BNDREG_OFFSET , bndreg_state); +ASSERT_OFFSET (XSAVE_BNDCSR_OFFSET , bndcsr_state); +ASSERT_OFFSET (XSAVE_OPMASK_OFFSET , opmask_state); +ASSERT_OFFSET (XSAVE_ZMM_HI256_OFFSET , zmm_hi256_state); +ASSERT_OFFSET (XSAVE_HI16_ZMM_OFFSET , hi16_zmm_state); +ASSERT_OFFSET (XSAVE_PKRU_OFFSET , pkru_state);static int kvm_put_xsave (X86CPU *cpu) {
Signature · 1 line
2.30.2
RFC PATCH 3/7 target/i386: Clarify the padding requirements of X86XSaveArea
In reply to David EdmondsonReplace the hard-coded size of offsets or structure elements with defined constants or sizeof().
--- target/i386/cpu.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
target/i386/cpu.h +7 -1
@@ -1329,7 +1329,13 @@ typedef struct X86XSaveArea {/* AVX State: */ XSaveAVX avx_state; -uint8_t padding[960 -576 -sizeof (XSaveAVX)]; + +/* Ensure that XSaveBNDREG is properly aligned. */ +uint8_t padding[XSAVE_BNDREG_OFFSET + -sizeof (X86LegacyXSaveArea) + -sizeof (X86XSaveHeader) + -sizeof (XSaveAVX)]; +/* MPX State: */ XSaveBNDREG bndreg_state;XSaveBNDCSR bndcsr_state;
Signature · 1 line
2.30.2
RFC PATCH 4/7 target/i386: Prepare for per-vendor X86XSaveArea layout
In reply to David EdmondsonMove Intel specific components of X86XSaveArea into a sub-union.
--- target/i386/cpu.c | 12 ++++---- target/i386/cpu.h | 55 +++++++++++++++++++++--------------- target/i386/kvm/kvm.c | 12 ++++---- target/i386/tcg/fpu_helper.c | 12 ++++---- target/i386/xsave_helper.c | 24 ++++++++-------- 5 files changed, 63 insertions(+), 52 deletions(-)
target/i386/cpu.c +6 -6
@@ -1418,27 +1418,27 @@ static const ExtSaveArea x86_ext_save_areas[] = { .size = sizeof(XSaveAVX) }, [XSTATE_BNDREGS_BIT ] = { .feature = FEAT_7_0_EBX, .bits = CPUID_7_0_EBX_MPX, - .offset = offsetof(X86XSaveArea, bndreg_state), + .offset = offsetof(X86XSaveArea, intel.bndreg_state), .size = sizeof(XSaveBNDREG) }, [XSTATE_BNDCSR_BIT ] = { .feature = FEAT_7_0_EBX, .bits = CPUID_7_0_EBX_MPX, - .offset = offsetof(X86XSaveArea, bndcsr_state), + .offset = offsetof(X86XSaveArea, intel.bndcsr_state), .size = sizeof(XSaveBNDCSR) }, [XSTATE_OPMASK_BIT ] = { .feature = FEAT_7_0_EBX, .bits = CPUID_7_0_EBX_AVX512F, - .offset = offsetof(X86XSaveArea, opmask_state), + .offset = offsetof(X86XSaveArea, intel.opmask_state), .size = sizeof(XSaveOpmask) }, [XSTATE_ZMM_Hi256_BIT] = { .feature = FEAT_7_0_EBX, .bits = CPUID_7_0_EBX_AVX512F, - .offset = offsetof(X86XSaveArea, zmm_hi256_state), + .offset = offsetof(X86XSaveArea, intel.zmm_hi256_state), .size = sizeof(XSaveZMM_Hi256) }, [XSTATE_Hi16_ZMM_BIT] = { .feature = FEAT_7_0_EBX, .bits = CPUID_7_0_EBX_AVX512F, - .offset = offsetof(X86XSaveArea, hi16_zmm_state), + .offset = offsetof(X86XSaveArea, intel.hi16_zmm_state), .size = sizeof(XSaveHi16_ZMM) }, [XSTATE_PKRU_BIT ] = { .feature = FEAT_7_0_ECX, .bits = CPUID_7_0_ECX_PKU, - .offset = offsetof(X86XSaveArea, pkru_state), + .offset = offsetof(X86XSaveArea, intel.pkru_state), .size = sizeof(XSavePKRU) }, };
target/i386/cpu.h +33 -22
69 lines not on this page · raw message
target/i386/kvm/kvm.c +6 -6
@@ -2409,12 +2409,12 @@ ASSERT_OFFSET(XSAVE_ST_SPACE_OFFSET, legacy.fpregs);ASSERT_OFFSET (XSAVE_XMM_SPACE_OFFSET , legacy.xmm_regs);ASSERT_OFFSET (XSAVE_XSTATE_BV_OFFSET , header.xstate_bv);ASSERT_OFFSET (XSAVE_AVX_OFFSET , avx_state); -ASSERT_OFFSET (XSAVE_BNDREG_OFFSET , bndreg_state); -ASSERT_OFFSET (XSAVE_BNDCSR_OFFSET , bndcsr_state); -ASSERT_OFFSET (XSAVE_OPMASK_OFFSET , opmask_state); -ASSERT_OFFSET (XSAVE_ZMM_HI256_OFFSET , zmm_hi256_state); -ASSERT_OFFSET (XSAVE_HI16_ZMM_OFFSET , hi16_zmm_state); -ASSERT_OFFSET (XSAVE_PKRU_OFFSET , pkru_state); +ASSERT_OFFSET (XSAVE_BNDREG_OFFSET , intel.bndreg_state); +ASSERT_OFFSET (XSAVE_BNDCSR_OFFSET , intel.bndcsr_state); +ASSERT_OFFSET (XSAVE_OPMASK_OFFSET , intel.opmask_state); +ASSERT_OFFSET (XSAVE_ZMM_HI256_OFFSET , intel.zmm_hi256_state); +ASSERT_OFFSET (XSAVE_HI16_ZMM_OFFSET , intel.hi16_zmm_state); +ASSERT_OFFSET (XSAVE_PKRU_OFFSET , intel.pkru_state);static int kvm_put_xsave (X86CPU *cpu) {
target/i386/tcg/fpu_helper.c +6 -6
@@ -2637,13 +2637,13 @@ static void do_xsave(CPUX86State *env, target_ulong ptr, uint64_t rfbm,do_xsave_sse (env, ptr, ra); }if (opt &XSTATE_BNDREGS_MASK ) { -do_xsave_bndregs (env, ptr +XO (bndreg_state), ra); +do_xsave_bndregs (env, ptr +XO (intel.bndreg_state), ra); }if (opt &XSTATE_BNDCSR_MASK ) { -do_xsave_bndcsr (env, ptr +XO (bndcsr_state), ra); +do_xsave_bndcsr (env, ptr +XO (intel.bndcsr_state), ra); }if (opt &XSTATE_PKRU_MASK ) { -do_xsave_pkru (env, ptr +XO (pkru_state), ra); +do_xsave_pkru (env, ptr +XO (intel.pkru_state), ra); }/* Update the XSTATE_BV field. */
@@ -2836,7 +2836,7 @@ void helper_xrstor(CPUX86State *env, target_ulong ptr, uint64_t rfbm) }if (rfbm &XSTATE_BNDREGS_MASK ) {if (xstate_bv &XSTATE_BNDREGS_MASK ) { -do_xrstor_bndregs (env, ptr +XO (bndreg_state), ra); +do_xrstor_bndregs (env, ptr +XO (intel.bndreg_state), ra); env->hflags |=HF_MPX_IU_MASK ; }else {memset (env->bnd_regs,0 ,sizeof (env->bnd_regs));
@@ -2845,7 +2845,7 @@ void helper_xrstor(CPUX86State *env, target_ulong ptr, uint64_t rfbm) }if (rfbm &XSTATE_BNDCSR_MASK ) {if (xstate_bv &XSTATE_BNDCSR_MASK ) { -do_xrstor_bndcsr (env, ptr +XO (bndcsr_state), ra); +do_xrstor_bndcsr (env, ptr +XO (intel.bndcsr_state), ra); }else {memset (&env->bndcs_regs,0 ,sizeof (env->bndcs_regs)); }
@@ -2854,7 +2854,7 @@ void helper_xrstor(CPUX86State *env, target_ulong ptr, uint64_t rfbm)if (rfbm &XSTATE_PKRU_MASK ) {uint64_t old_pkru = env->pkru;if (xstate_bv &XSTATE_PKRU_MASK ) { -do_xrstor_pkru (env, ptr +XO (pkru_state), ra); +do_xrstor_pkru (env, ptr +XO (intel.pkru_state), ra); }else { env->pkru =0 ; }
target/i386/xsave_helper.c +12 -12
@@ -31,16 +31,16 @@ void x86_cpu_xsave_all_areas(X86CPU *cpu, X86XSaveArea *buf) sizeof env->fpregs); xsave->legacy.mxcsr = env->mxcsr; xsave->header.xstate_bv = env->xstate_bv; -memcpy (&xsave->bndreg_state.bnd_regs, env->bnd_regs, +memcpy (&xsave->intel.bndreg_state.bnd_regs, env->bnd_regs,sizeof env->bnd_regs); - xsave->bndcsr_state.bndcsr = env->bndcs_regs; -memcpy (&xsave->opmask_state.opmask_regs, env->opmask_regs, + xsave->intel.bndcsr_state.bndcsr = env->bndcs_regs; +memcpy (&xsave->intel.opmask_state.opmask_regs, env->opmask_regs,sizeof env->opmask_regs);for (i =0 ; i <CPU_NB_REGS ; i++) {uint8_t *xmm = xsave->legacy.xmm_regs[i];uint8_t *ymmh = xsave->avx_state.ymmh[i]; -uint8_t *zmmh = xsave->zmm_hi256_state.zmm_hi256[i]; +uint8_t *zmmh = xsave->intel.zmm_hi256_state.zmm_hi256[i];stq_p (xmm, env->xmm_regs[i].ZMM_Q (0 ));stq_p (xmm+8 , env->xmm_regs[i].ZMM_Q (1 ));stq_p (ymmh, env->xmm_regs[i].ZMM_Q (2 ));
@@ -52,9 +52,9 @@ void x86_cpu_xsave_all_areas(X86CPU *cpu, X86XSaveArea *buf) }#ifdef TARGET_X86_64 -memcpy (&xsave->hi16_zmm_state.hi16_zmm, &env->xmm_regs[16 ], +memcpy (&xsave->intel.hi16_zmm_state.hi16_zmm, &env->xmm_regs[16 ],16 *sizeof env->xmm_regs[16 ]); -memcpy (&xsave->pkru_state, &env->pkru,sizeof env->pkru); +memcpy (&xsave->intel.pkru_state, &env->pkru,sizeof env->pkru);#endif }
@@ -83,16 +83,16 @@ void x86_cpu_xrstor_all_areas(X86CPU *cpu, const X86XSaveArea *buf)memcpy (env->fpregs, &xsave->legacy.fpregs,sizeof env->fpregs); env->xstate_bv = xsave->header.xstate_bv; -memcpy (env->bnd_regs, &xsave->bndreg_state.bnd_regs, +memcpy (env->bnd_regs, &xsave->intel.bndreg_state.bnd_regs,sizeof env->bnd_regs); - env->bndcs_regs = xsave->bndcsr_state.bndcsr; -memcpy (env->opmask_regs, &xsave->opmask_state.opmask_regs, + env->bndcs_regs = xsave->intel.bndcsr_state.bndcsr; +memcpy (env->opmask_regs, &xsave->intel.opmask_state.opmask_regs,sizeof env->opmask_regs);for (i =0 ; i <CPU_NB_REGS ; i++) {const uint8_t *xmm = xsave->legacy.xmm_regs[i];const uint8_t *ymmh = xsave->avx_state.ymmh[i]; -const uint8_t *zmmh = xsave->zmm_hi256_state.zmm_hi256[i]; +const uint8_t *zmmh = xsave->intel.zmm_hi256_state.zmm_hi256[i]; env->xmm_regs[i].ZMM_Q (0 ) =ldq_p (xmm); env->xmm_regs[i].ZMM_Q (1 ) =ldq_p (xmm+8 ); env->xmm_regs[i].ZMM_Q (2 ) =ldq_p (ymmh);
@@ -104,9 +104,9 @@ void x86_cpu_xrstor_all_areas(X86CPU *cpu, const X86XSaveArea *buf) }#ifdef TARGET_X86_64 -memcpy (&env->xmm_regs[16 ], &xsave->hi16_zmm_state.hi16_zmm, +memcpy (&env->xmm_regs[16 ], &xsave->intel.hi16_zmm_state.hi16_zmm,16 *sizeof env->xmm_regs[16 ]); -memcpy (&env->pkru, &xsave->pkru_state,sizeof env->pkru); +memcpy (&env->pkru, &xsave->intel.pkru_state,sizeof env->pkru);#endif }
Signature · 1 line
2.30.2
RFC PATCH 5/7 target/i386: Introduce AMD X86XSaveArea sub-union
In reply to David EdmondsonAMD stores the pkru_state at a different offset to Intel.
--- target/i386/cpu.h | 17 +++++++++++++++-- target/i386/kvm/kvm.c | 3 ++- 2 files changed, 17 insertions(+), 3 deletions(-)
target/i386/cpu.h +15 -2
@@ -1319,7 +1319,8 @@ typedef struct XSavePKRU {#define XSAVE_OPMASK_OFFSET 0x440#define XSAVE_ZMM_HI256_OFFSET 0x480#define XSAVE_HI16_ZMM_OFFSET 0x680 -#define XSAVE_PKRU_OFFSET 0xa80 +#define XSAVE_INTEL_PKRU_OFFSET 0xa80 +#define XSAVE_AMD_PKRU_OFFSET 0x980 typedef struct X86XSaveArea { X86LegacyXSaveArea legacy;
@@ -1348,6 +1349,16 @@ typedef struct X86XSaveArea {/* PKRU State: */ XSavePKRU pkru_state; } intel; +struct { +/* Ensure that XSavePKRU is properly aligned. */ +uint8_t padding[XSAVE_AMD_PKRU_OFFSET + -sizeof (X86LegacyXSaveArea) + -sizeof (X86XSaveHeader) + -sizeof (XSaveAVX)]; + +/* PKRU State: */ +XSavePKRU pkru_state; + } amd; }; } X86XSaveArea;
@@ -1370,7 +1381,9 @@ QEMU_BUILD_BUG_ON(offsetof(X86XSaveArea, intel.hi16_zmm_state) != XSAVE_HI16_ZMM_OFFSET);QEMU_BUILD_BUG_ON (sizeof (XSaveHi16_ZMM) !=0x400 ); QEMU_BUILD_BUG_ON(offsetof(X86XSaveArea, intel.pkru_state) - != XSAVE_PKRU_OFFSET); + != XSAVE_INTEL_PKRU_OFFSET); +QEMU_BUILD_BUG_ON(offsetof(X86XSaveArea, amd.pkru_state) + != XSAVE_AMD_PKRU_OFFSET);QEMU_BUILD_BUG_ON (sizeof (XSavePKRU) !=0x8 ); typedef enum TPRAccess {
target/i386/kvm/kvm.c +2 -1
@@ -2414,7 +2414,8 @@ ASSERT_OFFSET(XSAVE_BNDCSR_OFFSET, intel.bndcsr_state);ASSERT_OFFSET (XSAVE_OPMASK_OFFSET , intel.opmask_state);ASSERT_OFFSET (XSAVE_ZMM_HI256_OFFSET , intel.zmm_hi256_state);ASSERT_OFFSET (XSAVE_HI16_ZMM_OFFSET , intel.hi16_zmm_state); -ASSERT_OFFSET (XSAVE_PKRU_OFFSET , intel.pkru_state); +ASSERT_OFFSET (XSAVE_INTEL_PKRU_OFFSET , intel.pkru_state); +ASSERT_OFFSET (XSAVE_AMD_PKRU_OFFSET , amd.pkru_state);static int kvm_put_xsave (X86CPU *cpu) {
Signature · 1 line
2.30.2
RFC PATCH 6/7 target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf 0xd
In reply to David EdmondsonAMD stores the pkru_state at a different offset to Intel, so update the CPUID leaf which indicates such.
--- target/i386/cpu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
target/i386/cpu.c +6 -1
@@ -1397,7 +1397,7 @@ typedef struct ExtSaveArea {uint32_t offset, size; } ExtSaveArea; -static const ExtSaveArea x86_ext_save_areas[] = { +static ExtSaveArea x86_ext_save_areas[] = { [XSTATE_FP_BIT ] = {/* x87 FP state component is always enabled if XSAVE is supported */ .feature =FEAT_1_ECX , .bits =CPUID_EXT_XSAVE ,
@@ -6088,6 +6088,11 @@ static void x86_cpu_filter_features(X86CPU *cpu, bool verbose)mark_unavailable_features (cpu,FEAT_7_0_EBX ,CPUID_7_0_EBX_INTEL_PT , prefix); } } + +if (IS_AMD_CPU (env)) { + x86_ext_save_areas[XSTATE_PKRU_BIT ].offset = + offsetof(X86XSaveArea, amd.pkru_state); + } }static void x86_cpu_hyperv_realize (X86CPU *cpu)
Signature · 1 line
2.30.2
RFC PATCH 7/7 target/i386: Manipulate only AMD XSAVE state on AMD
In reply to David EdmondsonOn AMD CPUs, ensure to save/load only the relevant XSAVE state.
--- target/i386/tcg/fpu_helper.c | 12 +++++-- target/i386/xsave_helper.c | 70 ++++++++++++++++++++++-------------- 2 files changed, 54 insertions(+), 28 deletions(-)
target/i386/tcg/fpu_helper.c +10 -2
@@ -2643,7 +2643,11 @@ static void do_xsave(CPUX86State *env, target_ulong ptr, uint64_t rfbm,do_xsave_bndcsr (env, ptr +XO (intel.bndcsr_state), ra); }if (opt &XSTATE_PKRU_MASK ) { -do_xsave_pkru (env, ptr +XO (intel.pkru_state), ra); +if (IS_AMD_CPU (env)) { +do_xsave_pkru (env, ptr +XO (amd.pkru_state), ra); + }else { +do_xsave_pkru (env, ptr +XO (intel.pkru_state), ra); + } }/* Update the XSTATE_BV field. */
@@ -2854,7 +2858,11 @@ void helper_xrstor(CPUX86State *env, target_ulong ptr, uint64_t rfbm)if (rfbm &XSTATE_PKRU_MASK ) {uint64_t old_pkru = env->pkru;if (xstate_bv &XSTATE_PKRU_MASK ) { -do_xrstor_pkru (env, ptr +XO (intel.pkru_state), ra); +if (IS_AMD_CPU (env)) { +do_xrstor_pkru (env, ptr +XO (amd.pkru_state), ra); + }else { +do_xrstor_pkru (env, ptr +XO (intel.pkru_state), ra); + } }else { env->pkru =0 ; }
target/i386/xsave_helper.c +44 -26
116 lines not on this page · raw message
Signature · 1 line
2.30.2
Patchew URL: https://patchew.org/QEMU/[email protected]/
Patchew URL: https://patchew.org/QEMU/[email protected]/
Hi,
This series seems to have some coding style problems. See output below for more information:
Type: series
Message-id: [email protected]
Subject: [RFC PATCH 0/7] Support protection keys in an AMD EPYC-Milan VM
=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base > /dev/null || exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram./scripts/checkpatch.pl --mailback base..
=== TEST SCRIPT END ===
Updating 3c8cf5a9c21ff8782164d1def7f44bd888713384
From https://github.com/patchew-project/qemu
* [new tag] patchew/[email protected] -> patchew/[email protected]
Switched to a new branch 'test'
9761ad4 target/i386: Manipulate only AMD XSAVE state on AMD fcba7d5 target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf 0xd 0493da2 target/i386: Introduce AMD X86XSaveArea sub-union e8d400c target/i386: Prepare for per-vendor X86XSaveArea layout 5a78b06 target/i386: Clarify the padding requirements of X86XSaveArea ba3c3af target/i386: Use constants for XSAVE offsets
844afa9 target/i386: Declare constants for XSAVE offsets
=== OUTPUT BEGIN ===
1/7 Checking commit 844afa9929e3 (target/i386: Declare constants for XSAVE offsets)
WARNING: line over 80 characters
#60: FILE: target/i386/cpu.h:1352:
+QEMU_BUILD_BUG_ON(offsetof(X86XSaveArea, zmm_hi256_state) != XSAVE_ZMM_HI256_OFFSET);
WARNING: line over 80 characters
#63: FILE: target/i386/cpu.h:1354:
+QEMU_BUILD_BUG_ON(offsetof(X86XSaveArea, hi16_zmm_state) != XSAVE_HI16_ZMM_OFFSET);
total: 0 errors, 2 warnings, 48 lines checked
Patch 1/7 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
2/7 Checking commit ba3c3afe9795 (target/i386: Use constants for XSAVE offsets)
3/7 Checking commit 5a78b069f6d4 (target/i386: Clarify the padding requirements of X86XSaveArea) 4/7 Checking commit e8d400c3e40e (target/i386: Prepare for per-vendor X86XSaveArea layout) 5/7 Checking commit 0493da29bcd9 (target/i386: Introduce AMD X86XSaveArea sub-union) 6/7 Checking commit fcba7d58090d (target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf 0xd) 7/7 Checking commit 9761ad41cd68 (target/i386: Manipulate only AMD XSAVE state on AMD)
ERROR: spaces required around that '+' (ctx:VxV)
#90: FILE: target/i386/xsave_helper.c:53:
+ stq_p(zmmh+8, env->xmm_regs[i].ZMM_Q(5));
^ERROR: spaces required around that '+' (ctx:VxV)
#91: FILE: target/i386/xsave_helper.c:54:
+ stq_p(zmmh+16, env->xmm_regs[i].ZMM_Q(6));
^ERROR: spaces required around that '+' (ctx:VxV)
#92: FILE: target/i386/xsave_helper.c:55:
+ stq_p(zmmh+24, env->xmm_regs[i].ZMM_Q(7));
^ERROR: spaces required around that '+' (ctx:VxV)
#150: FILE: target/i386/xsave_helper.c:114:
+ env->xmm_regs[i].ZMM_Q(5) = ldq_p(zmmh+8);
^ERROR: spaces required around that '+' (ctx:VxV)
#151: FILE: target/i386/xsave_helper.c:115:
+ env->xmm_regs[i].ZMM_Q(6) = ldq_p(zmmh+16);
^ERROR: spaces required around that '+' (ctx:VxV)
#152: FILE: target/i386/xsave_helper.c:116:
+ env->xmm_regs[i].ZMM_Q(7) = ldq_p(zmmh+24);
^total: 6 errors, 0 warnings, 140 lines checked
Patch 7/7 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in MAINTAINERS.
=== OUTPUT END ===
Test command exited with code: 1
The full log is available at
http://patchew.org/logs/[email protected]/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to [email protected]
Quoted 7 lines · David Edmondson
AMD EPYC-Milan CPUs introduced support for protection keys, previously available only with Intel CPUs.
AMD chose to place the XSAVE state component for the protection keys at a different offset in the XSAVE state area than that chosen by Intel.
Quoted 8 lines
To accommodate this, modify QEMU to behave appropriately on AMD systems, allowing a VM to properly take advantage of the new feature.
Further, avoid manipulating XSAVE state components that are not present on AMD systems.
The code in patch 6 that changes the CPUID
0x0dleaf is mostly dumped somewhere that seemed to work - I'm not sure where it really belongs.
Ping - any thoughts about this approach?
Quoted 9 lines
David Edmondson (7):
target/i386: Declare constants for XSAVE offsets target/i386: Use constants for XSAVE offsets target/i386: Clarify the padding requirements of X86XSaveArea target/i386: Prepare for per-vendor X86XSaveArea layout target/i386: Introduce AMD X86XSaveArea sub-union target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf0xdtarget/i386: Manipulate only AMD XSAVE state on AMD
Quoted 9 lines
target/i386/cpu.c | 19 +++++---- target/i386/cpu.h | 80 ++++++++++++++++++++++++++++-------- target/i386/kvm/kvm.c | 57 +++++++++---------------- target/i386/tcg/fpu_helper.c | 20 ++++++--- target/i386/xsave_helper.c | 70 +++++++++++++++++++------------ 5 files changed, 152 insertions(+), 94 deletions(-)Signature · 1 line
2.30.2
dme.
Signature · 1 line
You know your green from your red.
David, Are you still working on v2 of these series? I was going to test and review. Thanks
Quoted 53 lines
-----Original Message-----
From: David Edmondson <[email protected]>
Sent: Tuesday, June 8, 2021 3:25 AM
To: [email protected]
Cc: [email protected]; Eduardo Habkost <[email protected]>; Paolo Bonzini <[email protected]>; Marcelo Tosatti <[email protected]>; Richard Henderson <[email protected]>; Moger, Babu <[email protected]>
Subject: Re: [RFC PATCH 0/7] Support protection keys in an AMD EPYC-Milan VMQuoted 7 lines · David Edmondson
AMD EPYC-Milan CPUs introduced support for protection keys, previously available only with Intel CPUs.
AMD chose to place the XSAVE state component for the protection keys at a different offset in the XSAVE state area than that chosen by Intel.
Quoted 8 lines
To accommodate this, modify QEMU to behave appropriately on AMD systems, allowing a VM to properly take advantage of the new feature.
Further, avoid manipulating XSAVE state components that are not present on AMD systems.
The code in patch 6 that changes the CPUID
0x0dleaf is mostly dumped somewhere that seemed to work - I'm not sure where it really belongs.Ping - any thoughts about this approach?
Quoted 16 lines
David Edmondson (7):
target/i386: Declare constants for XSAVE offsets target/i386: Use constants for XSAVE offsets target/i386: Clarify the padding requirements of X86XSaveArea target/i386: Prepare for per-vendor X86XSaveArea layout target/i386: Introduce AMD X86XSaveArea sub-union target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf0xdtarget/i386: Manipulate only AMD XSAVE state on AMDtarget/i386/cpu.c | 19 +++++---- target/i386/cpu.h | 80 ++++++++++++++++++++++++++++-------- target/i386/kvm/kvm.c | 57 +++++++++---------------- target/i386/tcg/fpu_helper.c | 20 ++++++--- target/i386/xsave_helper.c | 70 +++++++++++++++++++------------ 5 files changed, 152 insertions(+), 94 deletions(-)Quoted 2 lines
--
2.30.2dme.
--
You know your green from your red.
Quoted 2 lines · Babu Moger
David, Are you still working on v2 of these series? I was going to test and review. Thanks
Yes. I have something that works, but it's messy in places. I hope to get it out in a couple of days.
Quoted 47 lines
Quoted 47 lines
-----Original Message-----
From: David Edmondson <[email protected]>
Sent: Tuesday, June 8, 2021 3:25 AM
To: [email protected]
Cc: [email protected]; Eduardo Habkost <[email protected]>; Paolo Bonzini <[email protected]>; Marcelo Tosatti <[email protected]>; Richard Henderson <[email protected]>; Moger, Babu <[email protected]>
Subject: Re: [RFC PATCH 0/7] Support protection keys in an AMD EPYC-Milan VMQuoted 7 lines · David Edmondson
AMD EPYC-Milan CPUs introduced support for protection keys, previously available only with Intel CPUs.
AMD chose to place the XSAVE state component for the protection keys at a different offset in the XSAVE state area than that chosen by Intel.
Quoted 8 lines
To accommodate this, modify QEMU to behave appropriately on AMD systems, allowing a VM to properly take advantage of the new feature.
Further, avoid manipulating XSAVE state components that are not present on AMD systems.
The code in patch 6 that changes the CPUID
0x0dleaf is mostly dumped somewhere that seemed to work - I'm not sure where it really belongs.Ping - any thoughts about this approach?
Quoted 16 lines
David Edmondson (7):
target/i386: Declare constants for XSAVE offsets target/i386: Use constants for XSAVE offsets target/i386: Clarify the padding requirements of X86XSaveArea target/i386: Prepare for per-vendor X86XSaveArea layout target/i386: Introduce AMD X86XSaveArea sub-union target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf0xdtarget/i386: Manipulate only AMD XSAVE state on AMDtarget/i386/cpu.c | 19 +++++---- target/i386/cpu.h | 80 ++++++++++++++++++++++++++++-------- target/i386/kvm/kvm.c | 57 +++++++++---------------- target/i386/tcg/fpu_helper.c | 20 ++++++--- target/i386/xsave_helper.c | 70 +++++++++++++++++++------------ 5 files changed, 152 insertions(+), 94 deletions(-)
Quoted 6 lines
Quoted 6 lines
Quoted 2 lines
--
2.30.2dme.
--
You know your green from your red.
dme.
Signature · 1 line
When you were the brightest star, who were the shadows?
Paolo Bonzini
maintainerFirst of all, sorry for the delayed review.
Quoted 9 lines · David Edmondson
AMD EPYC-Milan CPUs introduced support for protection keys, previously available only with Intel CPUs.
AMD chose to place the XSAVE state component for the protection keys at a different offset in the XSAVE state area than that chosen by Intel.
To accommodate this, modify QEMU to behave appropriately on AMD systems, allowing a VM to properly take advantage of the new feature.
Uff, that sucks. :(
If I understand correctly, the problem is that the layout of KVM_GET_XSAVE/KVM_SET_XSAVE depends on the host CPUID, which in retrospect would be obvious. Is that correct? If so, it would make sense and might even be easier to drop all usage of X86XSaveArea:
* update ext_save_areas based on CPUID information in kvm_cpu_instance_init
* make x86_cpu_xsave_all_areas and x86_cpu_xrstor_all_areas use the ext_save_areas offsets to build pointers to XSaveAVX, XSaveBNDREG, etc.
What do you think?
Paolo
Quoted 22 lines
Further, avoid manipulating XSAVE state components that are not present on AMD systems.
The code in patch 6 that changes the CPUID
0x0dleaf is mostly dumped somewhere that seemed to work - I'm not sure where it really belongs.David Edmondson (7):
target/i386: Declare constants for XSAVE offsets target/i386: Use constants for XSAVE offsets target/i386: Clarify the padding requirements of X86XSaveArea target/i386: Prepare for per-vendor X86XSaveArea layout target/i386: Introduce AMD X86XSaveArea sub-union target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf0xdtarget/i386: Manipulate only AMD XSAVE state on AMDtarget/i386/cpu.c | 19 +++++---- target/i386/cpu.h | 80 ++++++++++++++++++++++++++++-------- target/i386/kvm/kvm.c | 57 +++++++++---------------- target/i386/tcg/fpu_helper.c | 20 ++++++--- target/i386/xsave_helper.c | 70 +++++++++++++++++++------------ 5 files changed, 152 insertions(+), 94 deletions(-)
Quoted 10 lines · Paolo Bonzini
First of all, sorry for the delayed review.
Quoted 7 lines · David Edmondson
AMD EPYC-Milan CPUs introduced support for protection keys, previously available only with Intel CPUs.
AMD chose to place the XSAVE state component for the protection keys at a different offset in the XSAVE state area than that chosen by Intel.
Quoted 8 lines
Quoted 2 lines
To accommodate this, modify QEMU to behave appropriately on AMD systems, allowing a VM to properly take advantage of the new feature.
Uff, that sucks. :(
If I understand correctly, the problem is that the layout of KVM_GET_XSAVE/KVM_SET_XSAVE depends on the host CPUID, which in retrospect would be obvious. Is that correct?
Yes.
Quoted 9 lines
If so, it would make sense and might even be easier to drop all usage of X86XSaveArea:
* update
ext_save_areasbased on CPUID information inkvm_cpu_instance_init* make
x86_cpu_xsave_all_areasandx86_cpu_xrstor_all_areasuse theext_save_areasoffsets to build pointers to XSaveAVX, XSaveBNDREG, etc.What do you think?
I will produce a patch and send it out.
Quoted 24 lines
Paolo
Quoted 22 lines
Further, avoid manipulating XSAVE state components that are not present on AMD systems.
The code in patch 6 that changes the CPUID
0x0dleaf is mostly dumped somewhere that seemed to work - I'm not sure where it really belongs.David Edmondson (7):
target/i386: Declare constants for XSAVE offsets target/i386: Use constants for XSAVE offsets target/i386: Clarify the padding requirements of X86XSaveArea target/i386: Prepare for per-vendor X86XSaveArea layout target/i386: Introduce AMD X86XSaveArea sub-union target/i386: Adjust AMD XSAVE PKRU area offset in CPUID leaf0xdtarget/i386: Manipulate only AMD XSAVE state on AMDtarget/i386/cpu.c | 19 +++++---- target/i386/cpu.h | 80 ++++++++++++++++++++++++++++-------- target/i386/kvm/kvm.c | 57 +++++++++---------------- target/i386/tcg/fpu_helper.c | 20 ++++++--- target/i386/xsave_helper.c | 70 +++++++++++++++++++------------ 5 files changed, 152 insertions(+), 94 deletions(-)
dme.
Signature · 1 line
Oliver darling, call Mister Haney, I think our speakers are blown.